summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/RCU/Design/Requirements/Requirements.rst10
-rw-r--r--Documentation/RCU/stallwarn.rst6
-rw-r--r--Documentation/admin-guide/kernel-parameters.txt34
-rw-r--r--Documentation/features/time/context-tracking/arch-support.txt6
-rw-r--r--MAINTAINERS1
-rw-r--r--arch/Kconfig8
-rw-r--r--arch/arm/Kconfig2
-rw-r--r--arch/arm/kernel/entry-common.S4
-rw-r--r--arch/arm/kernel/entry-header.S12
-rw-r--r--arch/arm/mach-imx/cpuidle-imx6q.c5
-rw-r--r--arch/arm64/Kconfig2
-rw-r--r--arch/arm64/kernel/entry-common.c14
-rw-r--r--arch/csky/Kconfig2
-rw-r--r--arch/csky/kernel/entry.S8
-rw-r--r--arch/loongarch/Kconfig2
-rw-r--r--arch/mips/Kconfig2
-rw-r--r--arch/powerpc/Kconfig2
-rw-r--r--arch/powerpc/include/asm/context_tracking.h2
-rw-r--r--arch/riscv/Kconfig2
-rw-r--r--arch/riscv/kernel/entry.S12
-rw-r--r--arch/sparc/Kconfig2
-rw-r--r--arch/sparc/kernel/rtrap_64.S2
-rw-r--r--arch/x86/Kconfig4
-rw-r--r--arch/x86/mm/fault.c2
-rw-r--r--arch/xtensa/Kconfig2
-rw-r--r--arch/xtensa/kernel/entry.S8
-rw-r--r--drivers/acpi/processor_idle.c5
-rw-r--r--drivers/cpuidle/cpuidle-psci.c8
-rw-r--r--drivers/cpuidle/cpuidle-riscv-sbi.c8
-rw-r--r--drivers/cpuidle/cpuidle.c9
-rw-r--r--include/linux/context_tracking.h95
-rw-r--r--include/linux/context_tracking_irq.h21
-rw-r--r--include/linux/context_tracking_state.h113
-rw-r--r--include/linux/entry-common.h10
-rw-r--r--include/linux/hardirq.h12
-rw-r--r--include/linux/rcupdate.h45
-rw-r--r--include/linux/rcupdate_trace.h2
-rw-r--r--include/linux/rcutiny.h27
-rw-r--r--include/linux/rcutree.h11
-rw-r--r--include/linux/sched.h4
-rw-r--r--include/linux/tracepoint.h4
-rw-r--r--init/Kconfig4
-rw-r--r--init/init_task.c1
-rw-r--r--kernel/cfi.c4
-rw-r--r--kernel/context_tracking.c617
-rw-r--r--kernel/cpu_pm.c8
-rw-r--r--kernel/entry/common.c16
-rw-r--r--kernel/extable.c4
-rw-r--r--kernel/fork.c1
-rw-r--r--kernel/locking/lockdep.c2
-rw-r--r--kernel/rcu/Kconfig31
-rw-r--r--kernel/rcu/Kconfig.debug2
-rw-r--r--kernel/rcu/rcu.h19
-rw-r--r--kernel/rcu/rcuscale.c1
-rw-r--r--kernel/rcu/rcutorture.c247
-rw-r--r--kernel/rcu/refscale.c18
-rw-r--r--kernel/rcu/tasks.h541
-rw-r--r--kernel/rcu/tiny.c25
-rw-r--r--kernel/rcu/tree.c660
-rw-r--r--kernel/rcu/tree.h21
-rw-r--r--kernel/rcu/tree_exp.h115
-rw-r--r--kernel/rcu/tree_nocb.h266
-rw-r--r--kernel/rcu/tree_plugin.h82
-rw-r--r--kernel/rcu/tree_stall.h55
-rw-r--r--kernel/rcu/update.c15
-rw-r--r--kernel/sched/core.c34
-rw-r--r--kernel/sched/idle.c10
-rw-r--r--kernel/sched/sched.h1
-rw-r--r--kernel/smp.c4
-rw-r--r--kernel/softirq.c4
-rw-r--r--kernel/time/Kconfig37
-rw-r--r--kernel/time/tick-sched.c2
-rw-r--r--kernel/trace/trace.c8
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-check-branches.sh11
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-remote.sh1
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm.sh6
76 files changed, 2124 insertions, 1279 deletions
diff --git a/Documentation/RCU/Design/Requirements/Requirements.rst b/Documentation/RCU/Design/Requirements/Requirements.rst
index 04ed8bf27a0e..a0f8164c8513 100644
--- a/Documentation/RCU/Design/Requirements/Requirements.rst
+++ b/Documentation/RCU/Design/Requirements/Requirements.rst
@@ -1844,10 +1844,10 @@ that meets this requirement.
Furthermore, NMI handlers can be interrupted by what appear to RCU to be
normal interrupts. One way that this can happen is for code that
-directly invokes rcu_irq_enter() and rcu_irq_exit() to be called
+directly invokes ct_irq_enter() and ct_irq_exit() to be called
from an NMI handler. This astonishing fact of life prompted the current
-code structure, which has rcu_irq_enter() invoking
-rcu_nmi_enter() and rcu_irq_exit() invoking rcu_nmi_exit().
+code structure, which has ct_irq_enter() invoking
+ct_nmi_enter() and ct_irq_exit() invoking ct_nmi_exit().
And yes, I also learned of this requirement the hard way.
Loadable Modules
@@ -2195,7 +2195,7 @@ scheduling-clock interrupt be enabled when RCU needs it to be:
sections, and RCU believes this CPU to be idle, no problem. This
sort of thing is used by some architectures for light-weight
exception handlers, which can then avoid the overhead of
- rcu_irq_enter() and rcu_irq_exit() at exception entry and
+ ct_irq_enter() and ct_irq_exit() at exception entry and
exit, respectively. Some go further and avoid the entireties of
irq_enter() and irq_exit().
Just make very sure you are running some of your tests with
@@ -2226,7 +2226,7 @@ scheduling-clock interrupt be enabled when RCU needs it to be:
+-----------------------------------------------------------------------+
| **Answer**: |
+-----------------------------------------------------------------------+
-| One approach is to do ``rcu_irq_exit();rcu_irq_enter();`` every so |
+| One approach is to do ``ct_irq_exit();ct_irq_enter();`` every so |
| often. But given that long-running interrupt handlers can cause other |
| problems, not least for response time, shouldn't you work to keep |
| your interrupt handler's runtime within reasonable bounds? |
diff --git a/Documentation/RCU/stallwarn.rst b/Documentation/RCU/stallwarn.rst
index 794837eb519b..e38c587067fc 100644
--- a/Documentation/RCU/stallwarn.rst
+++ b/Documentation/RCU/stallwarn.rst
@@ -97,12 +97,12 @@ warnings:
which will include additional debugging information.
- A low-level kernel issue that either fails to invoke one of the
- variants of rcu_user_enter(), rcu_user_exit(), rcu_idle_enter(),
- rcu_idle_exit(), rcu_irq_enter(), or rcu_irq_exit() on the one
+ variants of rcu_eqs_enter(true), rcu_eqs_exit(true), ct_idle_enter(),
+ ct_idle_exit(), ct_irq_enter(), or ct_irq_exit() on the one
hand, or that invokes one of them too many times on the other.
Historically, the most frequent issue has been an omission
of either irq_enter() or irq_exit(), which in turn invoke
- rcu_irq_enter() or rcu_irq_exit(), respectively. Building your
+ ct_irq_enter() or ct_irq_exit(), respectively. Building your
kernel with CONFIG_RCU_EQS_DEBUG=y can help track down these types
of issues, which sometimes arise in architecture-specific code.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 79e724175a49..df9a5b60ee46 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3667,6 +3667,9 @@
just as if they had also been called out in the
rcu_nocbs= boot parameter.
+ Note that this argument takes precedence over
+ the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option.
+
noiotrap [SH] Disables trapped I/O port accesses.
noirqdebug [X86-32] Disables the code which attempts to detect and
@@ -4560,6 +4563,9 @@
no-callback mode from boot but the mode may be
toggled at runtime via cpusets.
+ Note that this argument takes precedence over
+ the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option.
+
rcu_nocb_poll [KNL]
Rather than requiring that offloaded CPUs
(specified by rcu_nocbs= above) explicitly
@@ -4669,6 +4675,34 @@
When RCU_NOCB_CPU is set, also adjust the
priority of NOCB callback kthreads.
+ rcutree.rcu_divisor= [KNL]
+ Set the shift-right count to use to compute
+ the callback-invocation batch limit bl from
+ the number of callbacks queued on this CPU.
+ The result will be bounded below by the value of
+ the rcutree.blimit kernel parameter. Every bl
+ callbacks, the softirq handler will exit in
+ order to allow the CPU to do other work.
+
+ Please note that this callback-invocation batch
+ limit applies only to non-offloaded callback
+ invocation. Offloaded callbacks are instead
+ invoked in the context of an rcuoc kthread, which
+ scheduler will preempt as it does any other task.
+
+ rcutree.nocb_nobypass_lim_per_jiffy= [KNL]
+ On callback-offloaded (rcu_nocbs) CPUs,
+ RCU reduces the lock contention that would
+ otherwise be caused by callback floods through
+ use of the ->nocb_bypass list. However, in the
+ common non-flooded case, RCU queues directly to
+ the main ->cblist in order to avoid the extra
+ overhead of the ->nocb_bypass list and its lock.
+ But if there are too many callbacks queued during
+ a single jiffy, RCU pre-queues the callbacks into
+ the ->nocb_bypass queue. The definition of "too
+ many" is supplied by this kernel boot parameter.
+
rcutree.rcu_nocb_gp_stride= [KNL]
Set the number of NOCB callback kthreads in
each group, which defaults to the square root
diff --git a/Documentation/features/time/context-tracking/arch-support.txt b/Documentation/features/time/context-tracking/arch-support.txt
index c9e0a16290e6..e59071a49090 100644
--- a/Documentation/features/time/context-tracking/arch-support.txt
+++ b/Documentation/features/time/context-tracking/arch-support.txt
@@ -1,7 +1,7 @@
#
-# Feature name: context-tracking
-# Kconfig: HAVE_CONTEXT_TRACKING
-# description: arch supports context tracking for NO_HZ_FULL
+# Feature name: user-context-tracking
+# Kconfig: HAVE_CONTEXT_TRACKING_USER
+# description: arch supports user context tracking for NO_HZ_FULL
#
-----------------------
| arch |status|
diff --git a/MAINTAINERS b/MAINTAINERS
index 7aa3658dc007..dfe5052aac91 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5165,6 +5165,7 @@ F: include/linux/console*
CONTEXT TRACKING
M: Frederic Weisbecker <frederic@kernel.org>
+M: "Paul E. McKenney" <paulmck@kernel.org>
S: Maintained
F: kernel/context_tracking.c
F: include/linux/context_tracking*
diff --git a/arch/Kconfig b/arch/Kconfig
index 5ea3e3838c21..761d169ba7fd 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -784,7 +784,7 @@ config HAVE_ARCH_WITHIN_STACK_FRAMES
and similar) by implementing an inline arch_within_stack_frames(),
which is used by CONFIG_HARDENED_USERCOPY.
-config HAVE_CONTEXT_TRACKING
+config HAVE_CONTEXT_TRACKING_USER
bool
help
Provide kernel/user boundaries probes necessary for subsystems
@@ -792,10 +792,10 @@ config HAVE_CONTEXT_TRACKING
Syscalls need to be wrapped inside user_exit()-user_enter(), either
optimized behind static key or 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
+ protected inside ct_irq_enter/ct_irq_exit() but preemption or signal
handling on irq exit still need to be protected.
-config HAVE_CONTEXT_TRACKING_OFFSTACK
+config HAVE_CONTEXT_TRACKING_USER_OFFSTACK
bool
help
Architecture neither relies on exception_enter()/exception_exit()
@@ -807,7 +807,7 @@ config HAVE_CONTEXT_TRACKING_OFFSTACK
- Critical entry code isn't preemptible (or better yet:
not interruptible).
- - No use of RCU read side critical sections, unless rcu_nmi_enter()
+ - No use of RCU read side critical sections, unless ct_nmi_enter()
got called.
- No use of instrumentation, unless instrumentation_begin() got
called.
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 405596676473..4294c0123857 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -84,7 +84,7 @@ config ARM
select HAVE_ARCH_TRANSPARENT_HUGEPAGE if ARM_LPAE
select HAVE_ARM_SMCCC if CPU_V7
select HAVE_EBPF_JIT if !CPU_ENDIAN_BE32
- select HAVE_CONTEXT_TRACKING
+ select HAVE_CONTEXT_TRACKING_USER
select HAVE_C_RECORDMCOUNT
select HAVE_BUILDTIME_MCOUNT_SORT
select HAVE_DEBUG_KMEMLEAK if !XIP_KERNEL
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 6a447ac67d80..405a607b754f 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -28,7 +28,7 @@
#include "entry-header.S"
saved_psr .req r8
-#if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING)
+#if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING_USER)
saved_pc .req r9
#define TRACE(x...) x
#else
@@ -38,7 +38,7 @@ saved_pc .req lr
.section .entry.text,"ax",%progbits
.align 5
-#if !(IS_ENABLED(CONFIG_TRACE_IRQFLAGS) || IS_ENABLED(CONFIG_CONTEXT_TRACKING) || \
+#if !(IS_ENABLED(CONFIG_TRACE_IRQFLAGS) || IS_ENABLED(CONFIG_CONTEXT_TRACKING_USER) || \
IS_ENABLED(CONFIG_DEBUG_RSEQ))
/*
* This is the fast syscall return path. We do as little as possible here,
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 5865621bf691..99411fa91350 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -366,25 +366,25 @@ ALT_UP_B(.L1_\@)
* between user and kernel mode.
*/
.macro ct_user_exit, save = 1
-#ifdef CONFIG_CONTEXT_TRACKING
+#ifdef CONFIG_CONTEXT_TRACKING_USER
.if \save
stmdb sp!, {r0-r3, ip, lr}
- bl context_tracking_user_exit
+ bl user_exit_callable
ldmia sp!, {r0-r3, ip, lr}
.else
- bl context_tracking_user_exit
+ bl user_exit_callable
.endif
#endif
.endm
.macro ct_user_enter, save = 1
-#ifdef CONFIG_CONTEXT_TRACKING
+#ifdef CONFIG_CONTEXT_TRACKING_USER
.if \save
stmdb sp!, {r0-r3, ip, lr}
- bl context_tracking_user_enter
+ bl user_enter_callable
ldmia sp!, {r0-r3, ip, lr}
.else
- bl context_tracking_user_enter
+ bl user_enter_callable
.endif
#endif
.endm
diff --git a/arch/arm/mach-imx/cpuidle-imx6q.c b/arch/arm/mach-imx/cpuidle-imx6q.c
index 094337dc1bc7..d086cbae09c3 100644
--- a/arch/arm/mach-imx/cpuidle-imx6q.c
+++ b/arch/arm/mach-imx/cpuidle-imx6q.c
@@ -3,6 +3,7 @@
* Copyright (C) 2012 Freescale Semiconductor, Inc.
*/
+#include <linux/context_tracking.h>
#include <linux/cpuidle.h>
#include <linux/module.h>
#include <asm/cpuidle.h>
@@ -24,9 +25,9 @@ static int imx6q_enter_wait(struct cpuidle_device *dev,
imx6_set_lpm(WAIT_UNCLOCKED);
raw_spin_unlock(&cpuidle_lock);
- rcu_idle_enter();
+ ct_idle_enter();
cpu_do_idle();
- rcu_idle_exit();
+ ct_idle_exit();
raw_spin_lock(&cpuidle_lock);
if (num_idle_cpus-- == num_online_cpus())
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 95839c8d7229..e05fc9743767 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -176,7 +176,7 @@ config ARM64
select HAVE_C_RECORDMCOUNT
select HAVE_CMPXCHG_DOUBLE
select HAVE_CMPXCHG_LOCAL
- select HAVE_CONTEXT_TRACKING
+ select HAVE_CONTEXT_TRACKING_USER
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 56cefd33eb8e..c75ca36b4a49 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -41,7 +41,7 @@ static __always_inline void __enter_from_kernel_mode(struct pt_regs *regs)
if (!IS_ENABLED(CONFIG_TINY_RCU) && is_idle_task(current)) {
lockdep_hardirqs_off(CALLER_ADDR0);
- rcu_irq_enter();
+ ct_irq_enter();
trace_hardirqs_off_finish();
regs->exit_rcu = true;
@@ -76,7 +76,7 @@ static __always_inline void __exit_to_kernel_mode(struct pt_regs *regs)
if (regs->exit_rcu) {
trace_hardirqs_on_prepare();
lockdep_hardirqs_on_prepare();
- rcu_irq_exit();
+ ct_irq_exit();
lockdep_hardirqs_on(CALLER_ADDR0);
return;
}
@@ -84,7 +84,7 @@ static __always_inline void __exit_to_kernel_mode(struct pt_regs *regs)
trace_hardirqs_on();
} else {
if (regs->exit_rcu)
- rcu_irq_exit();
+ ct_irq_exit();
}
}
@@ -161,7 +161,7 @@ static void noinstr arm64_enter_nmi(struct pt_regs *regs)
__nmi_enter();
lockdep_hardirqs_off(CALLER_ADDR0);
lockdep_hardirq_enter();
- rcu_nmi_enter();
+ ct_nmi_enter();
trace_hardirqs_off_finish();
ftrace_nmi_enter();
@@ -182,7 +182,7 @@ static void noinstr arm64_exit_nmi(struct pt_regs *regs)
lockdep_hardirqs_on_prepare();
}
- rcu_nmi_exit();
+ ct_nmi_exit();
lockdep_hardirq_exit();
if (restore)
lockdep_hardirqs_on(CALLER_ADDR0);
@@ -199,7 +199,7 @@ static void noinstr arm64_enter_el1_dbg(struct pt_regs *regs)
regs->lockdep_hardirqs = lockdep_hardirqs_enabled();
lockdep_hardirqs_off(CALLER_ADDR0);
- rcu_nmi_enter();
+ ct_nmi_enter();
trace_hardirqs_off_finish();
}
@@ -218,7 +218,7 @@ static void noinstr arm64_exit_el1_dbg(struct pt_regs *regs)
lockdep_hardirqs_on_prepare();
}
- rcu_nmi_exit();
+ ct_nmi_exit();
if (restore)
lockdep_hardirqs_on(CALLER_ADDR0);
}
diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index 21d72b078eef..f55ba1745f7b 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -42,7 +42,7 @@ config CSKY
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_MMAP_RND_BITS
select HAVE_ARCH_SECCOMP_FILTER
- select HAVE_CONTEXT_TRACKING
+ select HAVE_CONTEXT_TRACKING_USER
select HAVE_VIRT_CPU_ACCOUNTING_GEN
select HAVE_DEBUG_BUGVERBOSE
select HAVE_DEBUG_KMEMLEAK
diff --git a/arch/csky/kernel/entry.S b/arch/csky/kernel/entry.S
index a4ababf25e24..547b4cd1b24b 100644
--- a/arch/csky/kernel/entry.S
+++ b/arch/csky/kernel/entry.S
@@ -19,11 +19,11 @@
.endm
.macro context_tracking
-#ifdef CONFIG_CONTEXT_TRACKING
+#ifdef CONFIG_CONTEXT_TRACKING_USER
mfcr a0, epsr
btsti a0, 31
bt 1f
- jbsr context_tracking_user_exit
+ jbsr user_exit_callable
ldw a0, (sp, LSAVE_A0)
ldw a1, (sp, LSAVE_A1)
ldw a2, (sp, LSAVE_A2)
@@ -159,8 +159,8 @@ ret_from_exception:
and r10, r9
cmpnei r10, 0
bt exit_work
-#ifdef CONFIG_CONTEXT_TRACKING
- jbsr context_tracking_user_enter
+#ifdef CONFIG_CONTEXT_TRACKING_USER
+ jbsr user_enter_callable
#endif
1:
#ifdef CONFIG_PREEMPTION
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 83fe390f8449..fc2465892a60 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -75,7 +75,7 @@ config LOONGARCH
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
select HAVE_ASM_MODVERSIONS
- select HAVE_CONTEXT_TRACKING
+ select HAVE_CONTEXT_TRACKING_USER
select HAVE_DEBUG_STACKOVERFLOW
select HAVE_DMA_CONTIGUOUS
select HAVE_EXIT_THREAD
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index db09d45d59ec..9457894db237 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -56,7 +56,7 @@ config MIPS
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES
select HAVE_ASM_MODVERSIONS
- select HAVE_CONTEXT_TRACKING
+ select HAVE_CONTEXT_TRACKING_USER
select HAVE_TIF_NOHZ
select HAVE_C_RECORDMCOUNT
select HAVE_DEBUG_KMEMLEAK
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 303795dbceb4..a4f8a5276e5c 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -202,7 +202,7 @@ config PPC
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_TRACEHOOK
select HAVE_ASM_MODVERSIONS
- select HAVE_CONTEXT_TRACKING if PPC64
+ select HAVE_CONTEXT_TRACKING_USER if PPC64
select HAVE_C_RECORDMCOUNT
select HAVE_DEBUG_KMEMLEAK
select HAVE_DEBUG_STACKOVERFLOW
diff --git a/arch/powerpc/include/asm/context_tracking.h b/arch/powerpc/include/asm/context_tracking.h
index f2682b28b050..4b63931c49e0 100644
--- a/arch/powerpc/include/asm/context_tracking.h
+++ b/arch/powerpc/include/asm/context_tracking.h
@@ -2,7 +2,7 @@
#ifndef _ASM_POWERPC_CONTEXT_TRACKING_H
#define _ASM_POWERPC_CONTEXT_TRACKING_H
-#ifdef CONFIG_CONTEXT_TRACKING
+#ifdef CONFIG_CONTEXT_TRACKING_USER
#define SCHEDULE_USER bl schedule_user
#else
#define SCHEDULE_USER bl schedule
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index fcbb81feb7ad..51713e03c934 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -86,7 +86,7 @@ config RISCV
select HAVE_ARCH_THREAD_STRUCT_WHITELIST
select HAVE_ARCH_VMAP_STACK if MMU && 64BIT
select HAVE_ASM_MODVERSIONS
- select HAVE_CONTEXT_TRACKING
+ select HAVE_CONTEXT_TRACKING_USER
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_CONTIGUOUS if MMU
select HAVE_EBPF_JIT if MMU
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 2e5b88ca11ce..b9eda3fcbd6d 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -111,12 +111,12 @@ _save_context:
call __trace_hardirqs_off
#endif
-#ifdef CONFIG_CONTEXT_TRACKING
- /* If previous state is in user mode, call context_tracking_user_exit. */
+#ifdef CONFIG_CONTEXT_TRACKING_USER
+ /* If previous state is in user mode, call user_exit_callable(). */
li a0, SR_PP
and a0, s1, a0
bnez a0, skip_context_tracking
- call context_tracking_user_exit
+ call user_exit_callable
skip_context_tracking:
#endif
@@ -176,7 +176,7 @@ handle_syscall:
*/
csrs CSR_STATUS, SR_IE
#endif
-#if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING)
+#if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING_USER)
/* Recover a0 - a7 for system calls */
REG_L a0, PT_A0(sp)
REG_L a1, PT_A1(sp)
@@ -269,8 +269,8 @@ resume_userspace:
andi s1, s0, _TIF_WORK_MASK
bnez s1, work_pending
-#ifdef CONFIG_CONTEXT_TRACKING
- call context_tracking_user_enter
+#ifdef CONFIG_CONTEXT_TRACKING_USER
+ call user_enter_callable
#endif
/* Save unwound kernel stack pointer in thread_info */
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 4f7d1dfbc608..02f0a6084f04 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -73,7 +73,7 @@ config SPARC64
select HAVE_DYNAMIC_FTRACE
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_SYSCALL_TRACEPOINTS
- select HAVE_CONTEXT_TRACKING
+ select HAVE_CONTEXT_TRACKING_USER
select HAVE_TIF_NOHZ
select HAVE_DEBUG_KMEMLEAK
select IOMMU_HELPER
diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index c5fd4b450d9b..eef102765a7e 100644
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -15,7 +15,7 @@
#include <asm/visasm.h>
#include <asm/processor.h>
-#ifdef CONFIG_CONTEXT_TRACKING
+#ifdef CONFIG_CONTEXT_TRACKING_USER
# define SCHEDULE_USER schedule_user
#else
# define SCHEDULE_USER schedule
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1e419d1581bc..fb5900e2c29a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -186,8 +186,8 @@ config X86
select HAVE_ASM_MODVERSIONS
select HAVE_CMPXCHG_DOUBLE
select HAVE_CMPXCHG_LOCAL
- select HAVE_CONTEXT_TRACKING if X86_64
- select HAVE_CONTEXT_TRACKING_OFFSTACK if HAVE_CONTEXT_TRACKING
+ select HAVE_CONTEXT_TRACKING_USER if X86_64
+ select HAVE_CONTEXT_TRACKING_USER_OFFSTACK if HAVE_CONTEXT_TRACKING_USER
select HAVE_C_RECORDMCOUNT
select HAVE_OBJTOOL_MCOUNT if HAVE_OBJTOOL
select HAVE_BUILDTIME_MCOUNT_SORT
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index fad8faa29d04..971977c438fc 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1526,7 +1526,7 @@ DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
/*
* Entry handling for valid #PF from kernel mode is slightly
- * different: RCU is already watching and rcu_irq_enter() must not
+ * different: RCU is already watching and ct_irq_enter() must not
* be invoked because a kernel fault on a user space address might
* sleep.
*
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 0b0f0172cced..7927fed7bc83 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -33,7 +33,7 @@ config XTENSA
select HAVE_ARCH_KCSAN
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_TRACEHOOK
- select HAVE_CONTEXT_TRACKING
+ select HAVE_CONTEXT_TRACKING_USER
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_CONTIGUOUS
select HAVE_EXIT_THREAD
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index ab30bcb46290..272fff587907 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -455,10 +455,10 @@ KABI_W or a3, a3, a2
abi_call trace_hardirqs_off
1:
#endif
-#ifdef CONFIG_CONTEXT_TRACKING
+#ifdef CONFIG_CONTEXT_TRACKING_USER
l32i abi_tmp0, a1, PT_PS
bbci.l abi_tmp0, PS_UM_BIT, 1f
- abi_call context_tracking_user_exit
+ abi_call user_exit_callable
1:
#endif
@@ -544,8 +544,8 @@ common_exception_return:
j .Lrestore_state
.Lexit_tif_loop_user:
-#ifdef CONFIG_CONTEXT_TRACKING
- abi_call context_tracking_user_enter
+#ifdef CONFIG_CONTEXT_TRACKING_USER
+ abi_call user_enter_callable
#endif
#ifdef CONFIG_HAVE_HW_BREAKPOINT
_bbci.l abi_saved0, TIF_DB_DISABLED, 1f
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 13200969ccf3..16a1663d02d4 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -23,6 +23,7 @@
#include <linux/minmax.h>
#include <linux/perf_event.h>
#include <acpi/processor.h>
+#include <linux/context_tracking.h>
/*
* Include the apic definitions for x86 to have the APIC timer related defines
@@ -647,11 +648,11 @@ static int __cpuidle acpi_idle_enter_bm(struct cpuidle_driver *drv,
raw_spin_unlock(&c3_lock);
}
- rcu_idle_enter();
+ ct_idle_enter();
acpi_idle_do_entry(cx);
- rcu_idle_exit();
+ ct_idle_exit();
/* Re-enable bus master arbitration */
if (dis_bm) {
diff --git a/drivers/cpuidle/cpuidle-psci.c b/drivers/cpuidle/cpuidle-psci.c
index 540105ca0781..57bc3e3ae391 100644
--- a/drivers/cpuidle/cpuidle-psci.c
+++ b/drivers/cpuidle/cpuidle-psci.c
@@ -69,12 +69,12 @@ static int __psci_enter_domain_idle_state(struct cpuidle_device *dev,
return -1;
/* Do runtime PM to manage a hierarchical CPU toplogy. */
- rcu_irq_enter_irqson();
+ ct_irq_enter_irqson();
if (s2idle)
dev_pm_genpd_suspend(pd_dev);
else
pm_runtime_put_sync_suspend(pd_dev);
- rcu_irq_exit_irqson();
+ ct_irq_exit_irqson();
state = psci_get_domain_state();
if (!state)
@@ -82,12 +82,12 @@ static int __psci_enter_domain_idle_state(struct cpuidle_device *dev,
ret = psci_cpu_suspend_enter(state) ? -1 : idx;
- rcu_irq_enter_irqson();
+ ct_irq_enter_irqson();
if (s2idle)
dev_pm_genpd_resume(pd_dev);
else
pm_runtime_get_sync(pd_dev);
- rcu_irq_exit_irqson();
+ ct_irq_exit_irqson();
cpu_pm_exit();
diff --git a/drivers/cpuidle/cpuidle-riscv-sbi.c b/drivers/cpuidle/cpuidle-riscv-sbi.c
index 1151e5e2ba82..862a2876f1c9 100644
--- a/drivers/cpuidle/cpuidle-riscv-sbi.c
+++ b/drivers/cpuidle/cpuidle-riscv-sbi.c
@@ -116,12 +116,12 @@ static int __sbi_enter_domain_idle_state(struct cpuidle_device *dev,
return -1;
/* Do runtime PM to manage a hierarchical CPU toplogy. */
- rcu_irq_enter_irqson();
+ ct_irq_enter_irqson();
if (s2idle)
dev_pm_genpd_suspend(pd_dev);
else
pm_runtime_put_sync_suspend(pd_dev);
- rcu_irq_exit_irqson();
+ ct_irq_exit_irqson();
if (sbi_is_domain_state_available())
state = sbi_get_domain_state();
@@ -130,12 +130,12 @@ static int __sbi_enter_domain_idle_state(struct cpuidle_device *dev,
ret = sbi_suspend(state) ? -1 : idx;
- rcu_irq_enter_irqson();
+ ct_irq_enter_irqson();
if (s2idle)
dev_pm_genpd_resume(pd_dev);
else
pm_runtime_get_sync(pd_dev);
- rcu_irq_exit_irqson();
+ ct_irq_exit_irqson();
cpu_pm_exit();
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index ef2ea1b12cd8..62dd956025f3 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -23,6 +23,7 @@
#include <linux/suspend.h>
#include <linux/tick.h>
#include <linux/mmu_context.h>
+#include <linux/context_tracking.h>
#include <trace/events/power.h>
#include "cpuidle.h"
@@ -150,12 +151,12 @@ static void enter_s2idle_proper(struct cpuidle_driver *drv,
*/
stop_critical_timings();
if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE))
- rcu_idle_enter();
+ ct_idle_enter();
target_state->enter_s2idle(dev, drv, index);
if (WARN_ON_ONCE(!irqs_disabled()))
local_irq_disable();
if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE))
- rcu_idle_exit();
+ ct_idle_exit();
tick_unfreeze();
start_critical_timings();
@@ -233,10 +234,10 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
stop_critical_timings();
if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE))
- rcu_idle_enter();
+ ct_idle_enter();
entered_state = target_state->enter(dev, drv, index);
if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE))
- rcu_idle_exit();
+ ct_idle_exit();
start_critical_timings();
sched_clock_idle_wakeup_event();
diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index 7a14807c9d1a..dcef4a9e4d63 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -10,71 +10,72 @@
#include <asm/ptrace.h>
-#ifdef CONFIG_CONTEXT_TRACKING
-extern void context_tracking_cpu_set(int cpu);
+#ifdef CONFIG_CONTEXT_TRACKING_USER
+extern void ct_cpu_track_user(int cpu);
/* Called with interrupts disabled. */
-extern void __context_tracking_enter(enum ctx_state state);
-extern void __context_tracking_exit(enum ctx_state state);
+extern void __ct_user_enter(enum ctx_state state);
+extern void __ct_user_exit(enum ctx_state state);
-extern void context_tracking_enter(enum ctx_state state);
-extern void context_tracking_exit(enum ctx_state state);
-extern void context_tracking_user_enter(void);
-extern void context_tracking_user_exit(void);
+extern void ct_user_enter(enum ctx_state state);
+extern void ct_user_exit(enum ctx_state state);
+
+extern void user_enter_callable(void);
+extern void user_exit_callable(void);
static inline void user_enter(void)
{
if (context_tracking_enabled())
- context_tracking_enter(CONTEXT_USER);
+ ct_user_enter(CONTEXT_USER);
}
static inline void user_exit(void)
{
if (context_tracking_enabled())
- context_tracking_exit(CONTEXT_USER);
+ ct_user_exit(CONTEXT_USER);
}
/* Called with interrupts disabled. */
static __always_inline void user_enter_irqoff(void)
{
if (context_tracking_enabled())
- __context_tracking_enter(CONTEXT_USER);
+ __ct_user_enter(CONTEXT_USER);
}
static __always_inline void user_exit_irqoff(void)
{
if (context_tracking_enabled())
- __context_tracking_exit(CONTEXT_USER);
+ __ct_user_exit(CONTEXT_USER);
}
static inline enum ctx_state exception_enter(void)
{
enum ctx_state prev_ctx;
- if (IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_OFFSTACK) ||
+ if (IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK) ||
!context_tracking_enabled())
return 0;
- prev_ctx = this_cpu_read(context_tracking.state);
+ prev_ctx = __ct_state();
if (prev_ctx != CONTEXT_KERNEL)
- context_tracking_exit(prev_ctx);
+ ct_user_exit(prev_ctx);
return prev_ctx;
}
static inline void exception_exit(enum ctx_state prev_ctx)
{
- if (!IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_OFFSTACK) &&
+ if (!IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK) &&
context_tracking_enabled()) {
if (prev_ctx != CONTEXT_KERNEL)
- context_tracking_enter(prev_ctx);
+ ct_user_enter(prev_ctx);
}
}
static __always_inline bool context_tracking_guest_enter(void)
{
if (context_tracking_enabled())
- __context_tracking_enter(CONTEXT_GUEST);
+ __ct_user_enter(CONTEXT_GUEST);
return context_tracking_enabled_this_cpu();
}
@@ -82,40 +83,56 @@ static __always_inline bool context_tracking_guest_enter(void)
static __always_inline void context_tracking_guest_exit(void)
{
if (context_tracking_enabled())
- __context_tracking_exit(CONTEXT_GUEST);
+ __ct_user_exit(CONTEXT_GUEST);
}
-/**
- * ct_state() - return the current context tracking state if known
- *
- * Returns the current cpu's context tracking state if context tracking
- * is enabled. If context tracking is disabled, returns
- * CONTEXT_DISABLED. This should be used primarily for debugging.
- */
-static __always_inline enum ctx_state ct_state(void)
-{
- return context_tracking_enabled() ?
- this_cpu_read(context_tracking.state) : CONTEXT_DISABLED;
-}
+#define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond))
+
#else
static inline void user_enter(void) { }
static inline void user_exit(void) { }
static inline void user_enter_irqoff(void) { }
static inline void user_exit_irqoff(void) { }
-static inline enum ctx_state exception_enter(void) { return 0; }
+static inline int exception_enter(void) { return 0; }
static inline void exception_exit(enum ctx_state prev_ctx) { }
-static inline enum ctx_state ct_state(void) { return CONTEXT_DISABLED; }
+static inline int ct_state(void) { return -1; }
static __always_inline bool context_tracking_guest_enter(void) { return false; }
static inline void context_tracking_guest_exit(void) { }
+#define CT_WARN_ON(cond) do { } while (0)
+#endif /* !CONFIG_CONTEXT_TRACKING_USER */
-#endif /* !CONFIG_CONTEXT_TRACKING */
-
-#define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond))
-
-#ifdef CONFIG_CONTEXT_TRACKING_FORCE
+#ifdef CONFIG_CONTEXT_TRACKING_USER_FORCE
extern void context_tracking_init(void);
#else
static inline void context_tracking_init(void) { }
-#endif /* CONFIG_CONTEXT_TRACKING_FORCE */
+#endif /* CONFIG_CONTEXT_TRACKING_USER_FORCE */
+
+#ifdef CONFIG_CONTEXT_TRACKING_IDLE
+extern void ct_idle_enter(void);
+extern void ct_idle_exit(void);
+
+/*
+ * Is the current CPU in an extended quiescent state?
+ *
+ * No ordering, as we are sampling CPU-local information.
+ */
+static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void)
+{
+ return !(arch_atomic_read(this_cpu_ptr(&context_tracking.state)) & RCU_DYNTICKS_IDX);
+}
+
+/*
+ * Increment the current CPU's context_tracking structure's ->state field
+ * with ordering. Return the new value.
+ */
+static __always_inline unsigned long ct_state_inc(int incby)
+{
+ return arch_atomic_add_return(incby, this_cpu_ptr(&context_tracking.state));
+}
+
+#else
+static inline void ct_idle_enter(void) { }
+static inline void ct_idle_exit(void) { }
+#endif /* !CONFIG_CONTEXT_TRACKING_IDLE */
#endif
diff --git a/include/linux/context_tracking_irq.h b/include/linux/context_tracking_irq.h
new file mode 100644
index 000000000000..c50b5670c4a5
--- /dev/null
+++ b/include/linux/context_tracking_irq.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_CONTEXT_TRACKING_IRQ_H
+#define _LINUX_CONTEXT_TRACKING_IRQ_H
+
+#ifdef CONFIG_CONTEXT_TRACKING_IDLE
+void ct_irq_enter(void);
+void ct_irq_exit(void);
+void ct_irq_enter_irqson(void);
+void ct_irq_exit_irqson(void);
+void ct_nmi_enter(void);
+void ct_nmi_exit(void);
+#else
+static inline void ct_irq_enter(void) { }
+static inline void ct_irq_exit(void) { }
+static inline void ct_irq_enter_irqson(void) { }
+static inline void ct_irq_exit_irqson(void) { }
+static inline void ct_nmi_enter(void) { }
+static inline void ct_nmi_exit(void) { }
+#endif
+
+#endif
diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h
index ae1e63e26947..4a4d56f77180 100644
--- a/include/linux/context_tracking_state.h
+++ b/include/linux/context_tracking_state.h
@@ -4,8 +4,28 @@
#include <linux/percpu.h>
#include <linux/static_key.h>
+#include <linux/context_tracking_irq.h>
+
+/* Offset to allow distinguishing irq vs. task-based idle entry/exit. */
+#define DYNTICK_IRQ_NONIDLE ((LONG_MAX / 2) + 1)
+
+enum ctx_state {
+ CONTEXT_DISABLED = -1, /* returned by ct_state() if unknown */
+ CONTEXT_KERNEL = 0,
+ CONTEXT_IDLE = 1,
+ CONTEXT_USER = 2,
+ CONTEXT_GUEST = 3,
+ CONTEXT_MAX = 4,
+};
+
+/* Even value for idle, else odd. */
+#define RCU_DYNTICKS_IDX CONTEXT_MAX
+
+#define CT_STATE_MASK (CONTEXT_MAX - 1)
+#define CT_DYNTICKS_MASK (~CT_STATE_MASK)
struct context_tracking {
+#ifdef CONFIG_CONTEXT_TRACKING_USER
/*
* When active is false, probes are unset in order
* to minimize overhead: TIF flags are cleared
@@ -14,18 +34,73 @@ struct context_tracking {
*/
bool active;
int recursion;
- enum ctx_state {
- CONTEXT_DISABLED = -1, /* returned by ct_state() if unknown */
- CONTEXT_KERNEL = 0,
- CONTEXT_USER,
- CONTEXT_GUEST,
- } state;
+#endif
+#ifdef CONFIG_CONTEXT_TRACKING
+ atomic_t state;
+#endif
+#ifdef CONFIG_CONTEXT_TRACKING_IDLE
+ long dynticks_nesting; /* Track process nesting level. */
+ long dynticks_nmi_nesting; /* Track irq/NMI nesting level. */
+#endif
};
#ifdef CONFIG_CONTEXT_TRACKING
-extern struct static_key_false context_tracking_key;
DECLARE_PER_CPU(struct context_tracking, context_tracking);
+static __always_inline int __ct_state(void)
+{
+ return arch_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_STATE_MASK;
+}
+#endif
+
+#ifdef CONFIG_CONTEXT_TRACKING_IDLE
+static __always_inline int ct_dynticks(void)
+{
+ return atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_DYNTICKS_MASK;
+}
+
+static __always_inline int ct_dynticks_cpu(int cpu)
+{
+ struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu);
+
+ return atomic_read(&ct->state) & CT_DYNTICKS_MASK;
+}
+
+static __always_inline int ct_dynticks_cpu_acquire(int cpu)
+{
+ struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu);
+
+ return atomic_read_acquire(&ct->state) & CT_DYNTICKS_MASK;
+}
+
+static __always_inline long ct_dynticks_nesting(void)
+{
+ return __this_cpu_read(context_tracking.dynticks_nesting);
+}
+
+static __always_inline long ct_dynticks_nesting_cpu(int cpu)
+{
+ struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu);
+
+ return ct->dynticks_nesting;
+}
+
+static __always_inline long ct_dynticks_nmi_nesting(void)
+{
+ return __this_cpu_read(context_tracking.dynticks_nmi_nesting);
+}
+
+static __always_inline long ct_dynticks_nmi_nesting_cpu(int cpu)
+{
+ struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu);
+
+ return ct->dynticks_nmi_nesting;
+}
+#endif /* #ifdef CONFIG_CONTEXT_TRACKING_IDLE */
+
+#ifdef CONFIG_CONTEXT_TRACKING_USER
+extern struct static_key_false context_tracking_key;
+
static __always_inline bool context_tracking_enabled(void)
{
return static_branch_unlikely(&context_tracking_key);
@@ -41,15 +116,31 @@ static inline bool context_tracking_enabled_this_cpu(void)
return context_tracking_enabled() && __this_cpu_read(context_tracking.active);
}
-static __always_inline bool context_tracking_in_user(void)
+/**
+ * ct_state() - return the current context tracking state if known
+ *
+ * Returns the current cpu's context tracking state if context tracking
+ * is enabled. If context tracking is disabled, returns
+ * CONTEXT_DISABLED. This should be used primarily for debugging.
+ */
+static __always_inline int ct_state(void)
{
- return __this_cpu_read(context_tracking.state) == CONTEXT_USER;
+ int ret;
+
+ if (!context_tracking_enabled())
+ return CONTEXT_DISABLED;
+
+ preempt_disable();
+ ret = __ct_state();
+ preempt_enable();
+
+ return ret;
}
+
#else
-static __always_inline bool context_tracking_in_user(void) { return false; }
static __always_inline bool context_tracking_enabled(void) { return false; }
static __always_inline bool context_tracking_enabled_cpu(int cpu) { return false; }
static __always_inline bool context_tracking_enabled_this_cpu(void) { return false; }
-#endif /* CONFIG_CONTEXT_TRACKING */
+#endif /* CONFIG_CONTEXT_TRACKING_USER */
#endif
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index c92ac75d6556..84a466b176cf 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -357,7 +357,7 @@ void irqentry_exit_to_user_mode(struct pt_regs *regs);
/**
* struct irqentry_state - Opaque object for exception state storage
* @exit_rcu: Used exclusively in the irqentry_*() calls; signals whether the
- * exit path has to invoke rcu_irq_exit().
+ * exit path has to invoke ct_irq_exit().
* @lockdep: Used exclusively in the irqentry_nmi_*() calls; ensures that
* lockdep state is restored correctly on exit from nmi.
*
@@ -395,12 +395,12 @@ typedef struct irqentry_state {
*
* For kernel mode entries RCU handling is done conditional. If RCU is
* watching then the only RCU requirement is to check whether the tick has
- * to be restarted. If RCU is not watching then rcu_irq_enter() has to be
- * invoked on entry and rcu_irq_exit() on exit.
+ * to be restarted. If RCU is not watching then ct_irq_enter() has to be
+ * invoked on entry and ct_irq_exit() on exit.
*
- * Avoiding the rcu_irq_enter/exit() calls is an optimization but also
+ * Avoiding the ct_irq_enter/exit() calls is an optimization but also
* solves the problem of kernel mode pagefaults which can schedule, which
- * is not possible after invoking rcu_irq_enter() without undoing it.
+ * is not possible after invoking ct_irq_enter() without undoing it.
*
* For user mode entries irqentry_enter_from_user_mode() is invoked to
* establish the proper context for NOHZ_FULL. Otherwise scheduling on exit
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 76878b357ffa..d57cab4d4c06 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -92,14 +92,6 @@ void irq_exit_rcu(void);
#define arch_nmi_exit() do { } while (0)
#endif
-#ifdef CONFIG_TINY_RCU
-static inline void rcu_nmi_enter(void) { }
-static inline void rcu_nmi_exit(void) { }
-#else
-extern void rcu_nmi_enter(void);
-extern void rcu_nmi_exit(void);
-#endif
-
/*
* NMI vs Tracing
* --------------
@@ -124,7 +116,7 @@ extern void rcu_nmi_exit(void);
do { \
__nmi_enter(); \
lockdep_hardirq_enter(); \
- rcu_nmi_enter(); \
+ ct_nmi_enter(); \
instrumentation_begin(); \
ftrace_nmi_enter(); \
instrumentation_end(); \
@@ -143,7 +135,7 @@ extern void rcu_nmi_exit(void);
instrumentation_begin(); \
ftrace_nmi_exit(); \
instrumentation_end(); \
- rcu_nmi_exit(); \
+ ct_nmi_exit(); \
lockdep_hardirq_exit(); \
__nmi_exit(); \
} while (0)
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 1a32036c918c..f527f27e6438 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -29,6 +29,7 @@
#include <linux/lockdep.h>
#include <asm/processor.h>
#include <linux/cpumask.h>
+#include <linux/context_tracking_irq.h>
#define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b))
#define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b))
@@ -41,6 +42,7 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func);
void rcu_barrier_tasks(void);
void rcu_barrier_tasks_rude(void);
void synchronize_rcu(void);
+unsigned long get_completed_synchronize_rcu(void);
#ifdef CONFIG_PREEMPT_RCU
@@ -103,13 +105,11 @@ static inline void rcu_sysrq_start(void) { }
static inline void rcu_sysrq_end(void) { }
#endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */
-#ifdef CONFIG_NO_HZ_FULL
-void rcu_user_enter(void);
-void rcu_user_exit(void);
+#if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK))
+void rcu_irq_work_resched(void);
#else
-static inline void rcu_user_enter(void) { }
-static inline void rcu_user_exit(void) { }
-#endif /* CONFIG_NO_HZ_FULL */
+static inline void rcu_irq_work_resched(void) { }
+#endif
#ifdef CONFIG_RCU_NOCB_CPU
void rcu_init_nohz(void);
@@ -128,7 +128,7 @@ static inline void rcu_nocb_flush_deferred_wakeup(void) { }
* @a: Code that RCU needs to pay attention to.
*
* RCU read-side critical sections are forbidden in the inner idle loop,
- * that is, between the rcu_idle_enter() and the rcu_idle_exit() -- RCU
+ * that is, between the ct_idle_enter() and the ct_idle_exit() -- RCU
* will happily ignore any such read-side critical sections. However,
* things like powertop need tracepoints in the inner idle loop.
*
@@ -143,9 +143,9 @@ static inline void rcu_nocb_flush_deferred_wakeup(void) { }
*/
#define RCU_NONIDLE(a) \
do { \
- rcu_irq_enter_irqson(); \
+ ct_irq_enter_irqson(); \
do { a; } while (0); \
- rcu_irq_exit_irqson(); \
+ ct_irq_exit_irqson(); \
} while (0)
/*
@@ -169,13 +169,24 @@ void synchronize_rcu_tasks(void);
# endif
# ifdef CONFIG_TASKS_TRACE_RCU
-# define rcu_tasks_trace_qs(t) \
- do { \
- if (!likely(READ_ONCE((t)->trc_reader_checked)) && \
- !unlikely(READ_ONCE((t)->trc_reader_nesting))) { \
- smp_store_release(&(t)->trc_reader_checked, true); \
- smp_mb(); /* Readers partitioned by store. */ \
- } \
+// Bits for ->trc_reader_special.b.need_qs field.
+#define TRC_NEED_QS 0x1 // Task needs a quiescent state.
+#define TRC_NEED_QS_CHECKED 0x2 // Task has been checked for needing quiescent state.
+
+u8 rcu_trc_cmpxchg_need_qs(struct task_struct *t, u8 old, u8 new);
+void rcu_tasks_trace_qs_blkd(struct task_struct *t);
+
+# define rcu_tasks_trace_qs(t) \
+ do { \
+ int ___rttq_nesting = READ_ONCE((t)->trc_reader_nesting); \
+ \
+ if (likely(!READ_ONCE((t)->trc_reader_special.b.need_qs)) && \
+ likely(!___rttq_nesting)) { \
+ rcu_trc_cmpxchg_need_qs((t), 0, TRC_NEED_QS_CHECKED); \
+ } else if (___rttq_nesting && ___rttq_nesting != INT_MIN && \
+ !READ_ONCE((t)->trc_reader_special.b.blocked)) { \
+ rcu_tasks_trace_qs_blkd(t); \
+ } \
} while (0)
# else
# define rcu_tasks_trace_qs(t) do { } while (0)
@@ -184,7 +195,7 @@ void synchronize_rcu_tasks(void);
#define rcu_tasks_qs(t, preempt) \
do { \
rcu_tasks_classic_qs((t), (preempt)); \
- rcu_tasks_trace_qs((t)); \
+ rcu_tasks_trace_qs(t); \
} while (0)
# ifdef CONFIG_TASKS_RUDE_RCU
diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h
index 6f9c35817398..9bc8cbb33340 100644
--- a/include/linux/rcupdate_trace.h
+++ b/include/linux/rcupdate_trace.h
@@ -75,7 +75,7 @@ static inline void rcu_read_unlock_trace(void)
nesting = READ_ONCE(t->trc_reader_nesting) - 1;
barrier(); // Critical section before disabling.
// Disable IPI-based setting of .need_qs.
- WRITE_ONCE(t->trc_reader_nesting, INT_MIN);
+ WRITE_ONCE(t->trc_reader_nesting, INT_MIN + nesting);
if (likely(!READ_ONCE(t->trc_reader_special.s)) || nesting) {
WRITE_ONCE(t->trc_reader_nesting, nesting);
return; // We assume shallow reader nesting.
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 5fed476f977f..62815c0a2dce 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -23,6 +23,16 @@ static inline void cond_synchronize_rcu(unsigned long oldstate)
might_sleep();
}
+static inline unsigned long start_poll_synchronize_rcu_expedited(void)
+{
+ return start_poll_synchronize_rcu();
+}
+
+static inline void cond_synchronize_rcu_expedited(unsigned long oldstate)
+{
+ cond_synchronize_rcu(oldstate);
+}
+
extern void rcu_barrier(void);
static inline void synchronize_rcu_expedited(void)
@@ -38,7 +48,7 @@ static inline void synchronize_rcu_expedited(void)
*/
extern void kvfree(const void *addr);
-static inline void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
+static inline void __kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
{
if (head) {
call_rcu(head, func);
@@ -51,6 +61,15 @@ static inline void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
kvfree((void *) func);
}
+#ifdef CONFIG_KASAN_GENERIC
+void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func);
+#else
+static inline void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
+{
+ __kvfree_call_rcu(head, func);
+}
+#endif
+
void rcu_qs(void);
static inline void rcu_softirq_qs(void)
@@ -76,12 +95,6 @@ static inline int rcu_needs_cpu(void)
static inline void rcu_virt_note_context_switch(int cpu) { }
static inline void rcu_cpu_stall_reset(void) { }
static inline int rcu_jiffies_till_stall_check(void) { return 21 * HZ; }
-static inline void rcu_idle_enter(void) { }
-static inline void rcu_idle_exit(void) { }
-static inline void rcu_irq_enter(void) { }
-static inline void rcu_irq_exit_irqson(void) { }
-static inline void rcu_irq_enter_irqson(void) { }
-static inline void rcu_irq_exit(void) { }
static inline void rcu_irq_exit_check_preempt(void) { }
#define rcu_is_idle_cpu(cpu) \
(is_idle_task(current) && !in_nmi() && !in_hardirq() && !in_serving_softirq())
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 9c6cfb742504..47eaa4cb0df7 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -40,17 +40,13 @@ bool rcu_eqs_special_set(int cpu);
void rcu_momentary_dyntick_idle(void);
void kfree_rcu_scheduler_running(void);
bool rcu_gp_might_be_stalled(void);
+unsigned long start_poll_synchronize_rcu_expedited(void);
+void cond_synchronize_rcu_expedited(unsigned long oldstate);
unsigned long get_state_synchronize_rcu(void);
unsigned long start_poll_synchronize_rcu(void);
bool poll_state_synchronize_rcu(unsigned long oldstate);
void cond_synchronize_rcu(unsigned long oldstate);
-void rcu_idle_enter(void);
-void rcu_idle_exit(void);
-void rcu_irq_enter(void);
-void rcu_irq_exit(void);
-void rcu_irq_enter_irqson(void);
-void rcu_irq_exit_irqson(void);
bool rcu_is_idle_cpu(int cpu);
#ifdef CONFIG_PROVE_RCU
@@ -59,6 +55,9 @@ void rcu_irq_exit_check_preempt(void);
static inline void rcu_irq_exit_check_preempt(void) { }
#endif
+struct task_struct;
+void rcu_preempt_deferred_qs(struct task_struct *t);
+
void exit_rcu(void);
void rcu_scheduler_starting(void);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 88b8817b827d..d6b0866c71ed 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -843,8 +843,9 @@ struct task_struct {
int trc_reader_nesting;
int trc_ipi_to_cpu;
union rcu_special trc_reader_special;
- bool trc_reader_checked;
struct list_head trc_holdout_list;
+ struct list_head trc_blkd_node;
+ int trc_blkd_cpu;
#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
struct sched_info sched_info;
@@ -2223,6 +2224,7 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
extern bool sched_task_on_rq(struct task_struct *p);
extern unsigned long get_wchan(struct task_struct *p);
+extern struct task_struct *cpu_curr_snapshot(int cpu);
/*
* In order to reduce various lock holder preemption latencies provide an
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 28031b15f878..55717a2eda08 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -200,13 +200,13 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
*/ \
if (rcuidle) { \
__idx = srcu_read_lock_notrace(&tracepoint_srcu);\
- rcu_irq_enter_irqson(); \
+ ct_irq_enter_irqson(); \
} \
\
__DO_TRACE_CALL(name, TP_ARGS(args)); \
\
if (rcuidle) { \
- rcu_irq_exit_irqson(); \
+ ct_irq_exit_irqson(); \
srcu_read_unlock_notrace(&tracepoint_srcu, __idx);\
} \
\
diff --git a/init/Kconfig b/init/Kconfig
index e70702d36180..7f75a61eb52e 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -494,11 +494,11 @@ config VIRT_CPU_ACCOUNTING_NATIVE
config VIRT_CPU_ACCOUNTING_GEN
bool "Full dynticks CPU time accounting"
- depends on HAVE_CONTEXT_TRACKING
+ depends on HAVE_CONTEXT_TRACKING_USER
depends on HAVE_VIRT_CPU_ACCOUNTING_GEN
depends on GENERIC_CLOCKEVENTS
select VIRT_CPU_ACCOUNTING
- select CONTEXT_TRACKING
+ select CONTEXT_TRACKING_USER
help
Select this option to enable task and CPU time accounting on full
dynticks systems. This accounting is implemented by watching every
diff --git a/init/init_task.c b/init/init_task.c
index 73cc8f03511a..ff6c4b9bfe6b 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -157,6 +157,7 @@ struct task_struct init_task
.trc_reader_nesting = 0,
.trc_reader_special.s = 0,
.trc_holdout_list = LIST_HEAD_INIT(init_task.trc_holdout_list),
+ .trc_blkd_node = LIST_HEAD_INIT(init_task.trc_blkd_node),
#endif
#ifdef CONFIG_CPUSETS
.mems_allowed_seq = SEQCNT_SPINLOCK_ZERO(init_task.mems_allowed_seq,
diff --git a/kernel/cfi.c b/kernel/cfi.c
index 08102d19ec15..2046276ee234 100644
--- a/kernel/cfi.c
+++ b/kernel/cfi.c
@@ -295,7 +295,7 @@ static inline cfi_check_fn find_check_fn(unsigned long ptr)
rcu_idle = !rcu_is_watching();
if (rcu_idle) {
local_irq_save(flags);
- rcu_irq_enter();
+ ct_irq_enter();
}
if (IS_ENABLED(CONFIG_CFI_CLANG_SHADOW))
@@ -304,7 +304,7 @@ static inline cfi_check_fn find_check_fn(unsigned long ptr)
fn = find_module_check_fn(ptr);
if (rcu_idle) {
- rcu_irq_exit();
+ ct_irq_exit();
local_irq_restore(flags);
}
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 36a98c48aedc..77978e372377 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -1,18 +1,20 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * Context tracking: Probe on high level context boundaries such as kernel
- * and userspace. This includes syscalls and exceptions entry/exit.
+ * Context tracking: Probe on high level context boundaries such as kernel,
+ * userspace, guest or idle.
*
* This is used by RCU to remove its dependency on the timer tick while a CPU
- * runs in userspace.
+ * runs in idle, userspace or guest mode.
*
- * Started by Frederic Weisbecker:
+ * User/guest tracking started by Frederic Weisbecker:
*
- * Copyright (C) 2012 Red Hat, Inc., Frederic Weisbecker <fweisbec@redhat.com>
+ * Copyright (C) 2012 Red Hat, Inc., Frederic Weisbecker
*
* Many thanks to Gilad Ben-Yossef, Paul McKenney, Ingo Molnar, Andrew Morton,
* Steven Rostedt, Peter Zijlstra for suggestions and improvements.
*
+ * RCU extended quiescent state bits imported from kernel/rcu/tree.c
+ * where the relevant authorship may be found.
*/
#include <linux/context_tracking.h>
@@ -21,6 +23,411 @@
#include <linux/hardirq.h>
#include <linux/export.h>
#include <linux/kprobes.h>
+#include <trace/events/rcu.h>
+
+
+DEFINE_PER_CPU(struct context_tracking, context_tracking) = {
+#ifdef CONFIG_CONTEXT_TRACKING_IDLE
+ .dynticks_nesting = 1,
+ .dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE,
+#endif
+ .state = ATOMIC_INIT(RCU_DYNTICKS_IDX),
+};
+EXPORT_SYMBOL_GPL(context_tracking);
+
+#ifdef CONFIG_CONTEXT_TRACKING_IDLE
+#define TPS(x) tracepoint_string(x)
+
+/* Record the current task on dyntick-idle entry. */
+static __always_inline void rcu_dynticks_task_enter(void)
+{
+#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
+ WRITE_ONCE(current->rcu_tasks_idle_cpu, smp_processor_id());
+#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
+}
+
+/* Record no current task on dyntick-idle exit. */
+static __always_inline void rcu_dynticks_task_exit(void)
+{
+#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
+ WRITE_ONCE(current->rcu_tasks_idle_cpu, -1);
+#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
+}
+
+/* Turn on heavyweight RCU tasks trace readers on idle/user entry. */
+static __always_inline void rcu_dynticks_task_trace_enter(void)
+{
+#ifdef CONFIG_TASKS_TRACE_RCU
+ if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
+ current->trc_reader_special.b.need_mb = true;
+#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
+}
+
+/* Turn off heavyweight RCU tasks trace readers on idle/user exit. */
+static __always_inline void rcu_dynticks_task_trace_exit(void)
+{
+#ifdef CONFIG_TASKS_TRACE_RCU
+ if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
+ current->trc_reader_special.b.need_mb = false;
+#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
+}
+
+/*
+ * Record entry into an extended quiescent state. This is only to be
+ * called when not already in an extended quiescent state, that is,
+ * RCU is watching prior to the call to this function and is no longer
+ * watching upon return.
+ */
+static noinstr void ct_kernel_exit_state(int offset)
+{
+ int seq;
+
+ /*
+ * CPUs seeing atomic_add_return() must see prior RCU read-side
+ * critical sections, and we also must force ordering with the
+ * next idle sojourn.
+ */
+ rcu_dynticks_task_trace_enter(); // Before ->dynticks update!
+ seq = ct_state_inc(offset);
+ // RCU is no longer watching. Better be in extended quiescent state!
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && (seq & RCU_DYNTICKS_IDX));
+}
+
+/*
+ * Record exit from an extended quiescent state. This is only to be
+ * called from an extended quiescent state, that is, RCU is not watching
+ * prior to the call to this function and is watching upon return.
+ */
+static noinstr void ct_kernel_enter_state(int offset)
+{
+ int seq;
+
+ /*
+ * CPUs seeing atomic_add_return() must see prior idle sojourns,
+ * and we also must force ordering with the next RCU read-side
+ * critical section.
+ */
+ seq = ct_state_inc(offset);
+ // RCU is now watching. Better not be in an extended quiescent state!
+ rcu_dynticks_task_trace_exit(); // After ->dynticks update!
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(seq & RCU_DYNTICKS_IDX));
+}
+
+/*
+ * Enter an RCU extended quiescent state, which can be either the
+ * idle loop or adaptive-tickless usermode execution.
+ *
+ * We crowbar the ->dynticks_nmi_nesting field to zero to allow for
+ * the possibility of usermode upcalls having messed up our count
+ * of interrupt nesting level during the prior busy period.
+ */
+static void noinstr ct_kernel_exit(bool user, int offset)
+{
+ struct context_tracking *ct = this_cpu_ptr(&context_tracking);
+
+ WARN_ON_ONCE(ct_dynticks_nmi_nesting() != DYNTICK_IRQ_NONIDLE);
+ WRITE_ONCE(ct->dynticks_nmi_nesting, 0);
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+ ct_dynticks_nesting() == 0);
+ if (ct_dynticks_nesting() != 1) {
+ // RCU will still be watching, so just do accounting and leave.
+ ct->dynticks_nesting--;
+ return;
+ }
+
+ instrumentation_begin();
+ lockdep_assert_irqs_disabled();
+ trace_rcu_dyntick(TPS("Start"), ct_dynticks_nesting(), 0, ct_dynticks());
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
+ rcu_preempt_deferred_qs(current);
+
+ // instrumentation for the noinstr ct_kernel_exit_state()
+ instrument_atomic_write(&ct->state, sizeof(ct->state));
+
+ instrumentation_end();
+ WRITE_ONCE(ct->dynticks_nesting, 0); /* Avoid irq-access tearing. */
+ // RCU is watching here ...
+ ct_kernel_exit_state(offset);
+ // ... but is no longer watching here.
+ rcu_dynticks_task_enter();
+}
+
+/*
+ * Exit an RCU extended quiescent state, which can be either the
+ * idle loop or adaptive-tickless usermode execution.
+ *
+ * We crowbar the ->dynticks_nmi_nesting field to DYNTICK_IRQ_NONIDLE to
+ * allow for the possibility of usermode upcalls messing up our count of
+ * interrupt nesting level during the busy period that is just now starting.
+ */
+static void noinstr ct_kernel_enter(bool user, int offset)
+{
+ struct context_tracking *ct = this_cpu_ptr(&context_tracking);
+ long oldval;
+
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !raw_irqs_disabled());
+ oldval = ct_dynticks_nesting();
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0);
+ if (oldval) {
+ // RCU was already watching, so just do accounting and leave.
+ ct->dynticks_nesting++;
+ return;
+ }
+ rcu_dynticks_task_exit();
+ // RCU is not watching here ...
+ ct_kernel_enter_state(offset);
+ // ... but is watching here.
+ instrumentation_begin();
+
+ // instrumentation for the noinstr ct_kernel_enter_state()
+ instrument_atomic_write(&ct->state, sizeof(ct->state));
+
+ trace_rcu_dyntick(TPS("End"), ct_dynticks_nesting(), 1, ct_dynticks());
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
+ WRITE_ONCE(ct->dynticks_nesting, 1);
+ WARN_ON_ONCE(ct_dynticks_nmi_nesting());
+ WRITE_ONCE(ct->dynticks_nmi_nesting, DYNTICK_IRQ_NONIDLE);
+ instrumentation_end();
+}
+
+/**
+ * ct_nmi_exit - inform RCU of exit from NMI context
+ *
+ * If we are returning from the outermost NMI handler that interrupted an
+ * RCU-idle period, update ct->state and ct->dynticks_nmi_nesting
+ * to let the RCU grace-period handling know that the CPU is back to
+ * being RCU-idle.
+ *
+ * If you add or remove a call to ct_nmi_exit(), be sure to test
+ * with CONFIG_RCU_EQS_DEBUG=y.
+ */
+void noinstr ct_nmi_exit(void)
+{
+ struct context_tracking *ct = this_cpu_ptr(&context_tracking);
+
+ instrumentation_begin();
+ /*
+ * Check for ->dynticks_nmi_nesting underflow and bad ->dynticks.
+ * (We are exiting an NMI handler, so RCU better be paying attention
+ * to us!)
+ */
+ WARN_ON_ONCE(ct_dynticks_nmi_nesting() <= 0);
+ WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs());
+
+ /*
+ * If the nesting level is not 1, the CPU wasn't RCU-idle, so
+ * leave it in non-RCU-idle state.
+ */
+ if (ct_dynticks_nmi_nesting() != 1) {
+ trace_rcu_dyntick(TPS("--="), ct_dynticks_nmi_nesting(), ct_dynticks_nmi_nesting() - 2,
+ ct_dynticks());
+ WRITE_ONCE(ct->dynticks_nmi_nesting, /* No store tearing. */
+ ct_dynticks_nmi_nesting() - 2);
+ instrumentation_end();
+ return;
+ }
+
+ /* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */
+ trace_rcu_dyntick(TPS("Startirq"), ct_dynticks_nmi_nesting(), 0, ct_dynticks());
+ WRITE_ONCE(ct->dynticks_nmi_nesting, 0); /* Avoid store tearing. */
+
+ // instrumentation for the noinstr ct_kernel_exit_state()
+ instrument_atomic_write(&ct->state, sizeof(ct->state));
+ instrumentation_end();
+
+ // RCU is watching here ...
+ ct_kernel_exit_state(RCU_DYNTICKS_IDX);
+ // ... but is no longer watching here.
+
+ if (!in_nmi())
+ rcu_dynticks_task_enter();
+}
+
+/**
+ * ct_nmi_enter - inform RCU of entry to NMI context
+ *
+ * If the CPU was idle from RCU's viewpoint, update ct->state and
+ * ct->dynticks_nmi_nesting to let the RCU grace-period handling know
+ * that the CPU is active. This implementation permits nested NMIs, as
+ * long as the nesting level does not overflow an int. (You will probably
+ * run out of stack space first.)
+ *
+ * If you add or remove a call to ct_nmi_enter(), be sure to test
+ * with CONFIG_RCU_EQS_DEBUG=y.
+ */
+void noinstr ct_nmi_enter(void)
+{
+ long incby = 2;
+ struct context_tracking *ct = this_cpu_ptr(&context_tracking);
+
+ /* Complain about underflow. */
+ WARN_ON_ONCE(ct_dynticks_nmi_nesting() < 0);
+
+ /*
+ * If idle from RCU viewpoint, atomically increment ->dynticks
+ * to mark non-idle and increment ->dynticks_nmi_nesting by one.
+ * Otherwise, increment ->dynticks_nmi_nesting by two. This means
+ * if ->dynticks_nmi_nesting is equal to one, we are guaranteed
+ * to be in the outermost NMI handler that interrupted an RCU-idle
+ * period (observation due to Andy Lutomirski).
+ */
+ if (rcu_dynticks_curr_cpu_in_eqs()) {
+
+ if (!in_nmi())
+ rcu_dynticks_task_exit();
+
+ // RCU is not watching here ...
+ ct_kernel_enter_state(RCU_DYNTICKS_IDX);
+ // ... but is watching here.
+
+ instrumentation_begin();
+ // instrumentation for the noinstr rcu_dynticks_curr_cpu_in_eqs()
+ instrument_atomic_read(&ct->state, sizeof(ct->state));
+ // instrumentation for the noinstr ct_kernel_enter_state()
+ instrument_atomic_write(&ct->state, sizeof(ct->state));
+
+ incby = 1;
+ } else if (!in_nmi()) {
+ instrumentation_begin();
+ rcu_irq_enter_check_tick();
+ } else {
+ instrumentation_begin();
+ }
+
+ trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="),
+ ct_dynticks_nmi_nesting(),
+ ct_dynticks_nmi_nesting() + incby, ct_dynticks());
+ instrumentation_end();
+ WRITE_ONCE(ct->dynticks_nmi_nesting, /* Prevent store tearing. */
+ ct_dynticks_nmi_nesting() + incby);
+ barrier();
+}
+
+/**
+ * ct_idle_enter - inform RCU that current CPU is entering idle
+ *
+ * Enter idle mode, in other words, -leave- the mode in which RCU
+ * read-side critical sections can occur. (Though RCU read-side
+ * critical sections can occur in irq handlers in idle, a possibility
+ * handled by irq_enter() and irq_exit().)
+ *
+ * If you add or remove a call to ct_idle_enter(), be sure to test with
+ * CONFIG_RCU_EQS_DEBUG=y.
+ */
+void noinstr ct_idle_enter(void)
+{
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !raw_irqs_disabled());
+ ct_kernel_exit(false, RCU_DYNTICKS_IDX + CONTEXT_IDLE);
+}
+EXPORT_SYMBOL_GPL(ct_idle_enter);
+
+/**
+ * ct_idle_exit - inform RCU that current CPU is leaving idle
+ *
+ * Exit idle mode, in other words, -enter- the mode in which RCU
+ * read-side critical sections can occur.
+ *
+ * If you add or remove a call to ct_idle_exit(), be sure to test with
+ * CONFIG_RCU_EQS_DEBUG=y.
+ */
+void noinstr ct_idle_exit(void)
+{
+ unsigned long flags;
+
+ raw_local_irq_save(flags);
+ ct_kernel_enter(false, RCU_DYNTICKS_IDX - CONTEXT_IDLE);
+ raw_local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(ct_idle_exit);
+
+/**
+ * ct_irq_enter - inform RCU that current CPU is entering irq away from idle
+ *
+ * Enter an interrupt handler, which might possibly result in exiting
+ * idle mode, in other words, entering the mode in which read-side critical
+ * sections can occur. The caller must have disabled interrupts.
+ *
+ * Note that the Linux kernel is fully capable of entering an interrupt
+ * handler that it never exits, for example when doing upcalls to user mode!
+ * This code assumes that the idle loop never does upcalls to user mode.
+ * If your architecture's idle loop does do upcalls to user mode (or does
+ * anything else that results in unbalanced calls to the irq_enter() and
+ * irq_exit() functions), RCU will give you what you deserve, good and hard.
+ * But very infrequently and irreproducibly.
+ *
+ * Use things like work queues to work around this limitation.
+ *
+ * You have been warned.
+ *
+ * If you add or remove a call to ct_irq_enter(), be sure to test with
+ * CONFIG_RCU_EQS_DEBUG=y.
+ */
+noinstr void ct_irq_enter(void)
+{
+ lockdep_assert_irqs_disabled();
+ ct_nmi_enter();
+}
+
+/**
+ * ct_irq_exit - inform RCU that current CPU is exiting irq towards idle
+ *
+ * Exit from an interrupt handler, which might possibly result in entering
+ * idle mode, in other words, leaving the mode in which read-side critical
+ * sections can occur. The caller must have disabled interrupts.
+ *
+ * This code assumes that the idle loop never does anything that might
+ * result in unbalanced calls to irq_enter() and irq_exit(). If your
+ * architecture's idle loop violates this assumption, RCU will give you what
+ * you deserve, good and hard. But very infrequently and irreproducibly.
+ *
+ * Use things like work queues to work around this limitation.
+ *
+ * You have been warned.
+ *
+ * If you add or remove a call to ct_irq_exit(), be sure to test with
+ * CONFIG_RCU_EQS_DEBUG=y.
+ */
+noinstr void ct_irq_exit(void)
+{
+ lockdep_assert_irqs_disabled();
+ ct_nmi_exit();
+}
+
+/*
+ * Wrapper for ct_irq_enter() where interrupts are enabled.
+ *
+ * If you add or remove a call to ct_irq_enter_irqson(), be sure to test
+ * with CONFIG_RCU_EQS_DEBUG=y.
+ */
+void ct_irq_enter_irqson(void)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ ct_irq_enter();
+ local_irq_restore(flags);
+}
+
+/*
+ * Wrapper for ct_irq_exit() where interrupts are enabled.
+ *
+ * If you add or remove a call to ct_irq_exit_irqson(), be sure to test
+ * with CONFIG_RCU_EQS_DEBUG=y.
+ */
+void ct_irq_exit_irqson(void)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ ct_irq_exit();
+ local_irq_restore(flags);
+}
+#else
+static __always_inline void ct_kernel_exit(bool user, int offset) { }
+static __always_inline void ct_kernel_enter(bool user, int offset) { }
+#endif /* #ifdef CONFIG_CONTEXT_TRACKING_IDLE */
+
+#ifdef CONFIG_CONTEXT_TRACKING_USER
#define CREATE_TRACE_POINTS
#include <trace/events/context_tracking.h>
@@ -28,9 +435,6 @@
DEFINE_STATIC_KEY_FALSE(context_tracking_key);
EXPORT_SYMBOL_GPL(context_tracking_key);
-DEFINE_PER_CPU(struct context_tracking, context_tracking);
-EXPORT_SYMBOL_GPL(context_tracking);
-
static noinstr bool context_tracking_recursion_enter(void)
{
int recursion;
@@ -51,29 +455,32 @@ static __always_inline void context_tracking_recursion_exit(void)
}
/**
- * context_tracking_enter - Inform the context tracking that the CPU is going
- * enter user or guest space mode.
+ * __ct_user_enter - Inform the context tracking that the CPU is going
+ * to enter user or guest space mode.
*
* This function must be called right before we switch from the kernel
* to user or guest space, when it's guaranteed the remaining kernel
* instructions to execute won't use any RCU read side critical section
* because this function sets RCU in extended quiescent state.
*/
-void noinstr __context_tracking_enter(enum ctx_state state)
+void noinstr __ct_user_enter(enum ctx_state state)
{
+ struct context_tracking *ct = this_cpu_ptr(&context_tracking);
+ lockdep_assert_irqs_disabled();
+
/* Kernel threads aren't supposed to go to userspace */
WARN_ON_ONCE(!current->mm);
if (!context_tracking_recursion_enter())
return;
- if ( __this_cpu_read(context_tracking.state) != state) {
- if (__this_cpu_read(context_tracking.active)) {
+ if (__ct_state() != state) {
+ if (ct->active) {
/*
* At this stage, only low level arch entry code remains and
* then we'll run in userspace. We can assume there won't be
* any RCU read-side critical section until the next call to
- * user_exit() or rcu_irq_enter(). Let's remove RCU's dependency
+ * user_exit() or ct_irq_enter(). Let's remove RCU's dependency
* on the tick.
*/
if (state == CONTEXT_USER) {
@@ -82,35 +489,77 @@ void noinstr __context_tracking_enter(enum ctx_state state)
vtime_user_enter(current);
instrumentation_end();
}
- rcu_user_enter();
+ /*
+ * Other than generic entry implementation, we may be past the last
+ * rescheduling opportunity in the entry code. Trigger a self IPI
+ * that will fire and reschedule once we resume in user/guest mode.
+ */
+ rcu_irq_work_resched();
+
+ /*
+ * Enter RCU idle mode right before resuming userspace. No use of RCU
+ * is permitted between this call and rcu_eqs_exit(). This way the
+ * CPU doesn't need to maintain the tick for RCU maintenance purposes
+ * when the CPU runs in userspace.
+ */
+ ct_kernel_exit(true, RCU_DYNTICKS_IDX + state);
+
+ /*
+ * Special case if we only track user <-> kernel transitions for tickless
+ * cputime accounting but we don't support RCU extended quiescent state.
+ * In this we case we don't care about any concurrency/ordering.
+ */
+ if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE))
+ atomic_set(&ct->state, state);
+ } else {
+ /*
+ * Even if context tracking is disabled on this CPU, because it's outside
+ * the full dynticks mask for example, we still have to keep track of the
+ * context transitions and states to prevent inconsistency on those of
+ * other CPUs.
+ * If a task triggers an exception in userspace, sleep on the exception
+ * handler and then migrate to another CPU, that new CPU must know where
+ * the exception returns by the time we call exception_exit().
+ * This information can only be provided by the previous CPU when it called
+ * exception_enter().
+ * OTOH we can spare the calls to vtime and RCU when context_tracking.active
+ * is false because we know that CPU is not tickless.
+ */
+ if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE)) {
+ /* Tracking for vtime only, no concurrent RCU EQS accounting */
+ atomic_set(&ct->state, state);
+ } else {
+ /*
+ * Tracking for vtime and RCU EQS. Make sure we don't race
+ * with NMIs. OTOH we don't care about ordering here since
+ * RCU only requires RCU_DYNTICKS_IDX increments to be fully
+ * ordered.
+ */
+ atomic_add(state, &ct->state);
+ }
}
- /*
- * Even if context tracking is disabled on this CPU, because it's outside
- * the full dynticks mask for example, we still have to keep track of the
- * context transitions and states to prevent inconsistency on those of
- * other CPUs.
- * If a task triggers an exception in userspace, sleep on the exception
- * handler and then migrate to another CPU, that new CPU must know where
- * the exception returns by the time we call exception_exit().
- * This information can only be provided by the previous CPU when it called
- * exception_enter().
- * OTOH we can spare the calls to vtime and RCU when context_tracking.active
- * is false because we know that CPU is not tickless.
- */
- __this_cpu_write(context_tracking.state, state);
}
context_tracking_recursion_exit();
}
-EXPORT_SYMBOL_GPL(__context_tracking_enter);
+EXPORT_SYMBOL_GPL(__ct_user_enter);
-void context_tracking_enter(enum ctx_state state)
+/*
+ * OBSOLETE:
+ * This function should be noinstr but the below local_irq_restore() is
+ * unsafe because it involves illegal RCU uses through tracing and lockdep.
+ * This is unlikely to be fixed as this function is obsolete. The preferred
+ * way is to call __context_tracking_enter() through user_enter_irqoff()
+ * or context_tracking_guest_enter(). It should be the arch entry code
+ * responsibility to call into context tracking with IRQs disabled.
+ */
+void ct_user_enter(enum ctx_state state)
{
unsigned long flags;
/*
* Some contexts may involve an exception occuring in an irq,
* leading to that nesting:
- * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit()
+ * ct_irq_enter() rcu_eqs_exit(true) rcu_eqs_enter(true) ct_irq_exit()
* This would mess up the dyntick_nesting count though. And rcu_irq_*()
* helpers are enough to protect RCU uses inside the exception. So
* just return immediately if we detect we are in an IRQ.
@@ -119,21 +568,32 @@ void context_tracking_enter(enum ctx_state state)
return;
local_irq_save(flags);
- __context_tracking_enter(state);
+ __ct_user_enter(state);
local_irq_restore(flags);
}
-NOKPROBE_SYMBOL(context_tracking_enter);
-EXPORT_SYMBOL_GPL(context_tracking_enter);
+NOKPROBE_SYMBOL(ct_user_enter);
+EXPORT_SYMBOL_GPL(ct_user_enter);
-void context_tracking_user_enter(void)
+/**
+ * user_enter_callable() - Unfortunate ASM callable version of user_enter() for
+ * archs that didn't manage to check the context tracking
+ * static key from low level code.
+ *
+ * This OBSOLETE function should be noinstr but it unsafely calls
+ * local_irq_restore(), involving illegal RCU uses through tracing and lockdep.
+ * This is unlikely to be fixed as this function is obsolete. The preferred
+ * way is to call user_enter_irqoff(). It should be the arch entry code
+ * responsibility to call into context tracking with IRQs disabled.
+ */
+void user_enter_callable(void)
{
user_enter();
}
-NOKPROBE_SYMBOL(context_tracking_user_enter);
+NOKPROBE_SYMBOL(user_enter_callable);
/**
- * context_tracking_exit - Inform the context tracking that the CPU is
- * exiting user or guest mode and entering the kernel.
+ * __ct_user_exit - Inform the context tracking that the CPU is
+ * exiting user or guest mode and entering the kernel.
*
* This function must be called after we entered the kernel from user or
* guest space before any use of RCU read side critical section. This
@@ -143,32 +603,64 @@ NOKPROBE_SYMBOL(context_tracking_user_enter);
* This call supports re-entrancy. This way it can be called from any exception
* handler without needing to know if we came from userspace or not.
*/
-void noinstr __context_tracking_exit(enum ctx_state state)
+void noinstr __ct_user_exit(enum ctx_state state)
{
+ struct context_tracking *ct = this_cpu_ptr(&context_tracking);
+
if (!context_tracking_recursion_enter())
return;
- if (__this_cpu_read(context_tracking.state) == state) {
- if (__this_cpu_read(context_tracking.active)) {
+ if (__ct_state() == state) {
+ if (ct->active) {
/*
- * We are going to run code that may use RCU. Inform
- * RCU core about that (ie: we may need the tick again).
+ * Exit RCU idle mode while entering the kernel because it can
+ * run a RCU read side critical section anytime.
*/
- rcu_user_exit();
+ ct_kernel_enter(true, RCU_DYNTICKS_IDX - state);
if (state == CONTEXT_USER) {
instrumentation_begin();
vtime_user_exit(current);
trace_user_exit(0);
instrumentation_end();
}
+
+ /*
+ * Special case if we only track user <-> kernel transitions for tickless
+ * cputime accounting but we don't support RCU extended quiescent state.
+ * In this we case we don't care about any concurrency/ordering.
+ */
+ if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE))
+ atomic_set(&ct->state, CONTEXT_KERNEL);
+
+ } else {
+ if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE)) {
+ /* Tracking for vtime only, no concurrent RCU EQS accounting */
+ atomic_set(&ct->state, CONTEXT_KERNEL);
+ } else {
+ /*
+ * Tracking for vtime and RCU EQS. Make sure we don't race
+ * with NMIs. OTOH we don't care about ordering here since
+ * RCU only requires RCU_DYNTICKS_IDX increments to be fully
+ * ordered.
+ */
+ atomic_sub(state, &ct->state);
+ }
}
- __this_cpu_write(context_tracking.state, CONTEXT_KERNEL);
}
context_tracking_recursion_exit();
}
-EXPORT_SYMBOL_GPL(__context_tracking_exit);
+EXPORT_SYMBOL_GPL(__ct_user_exit);
-void context_tracking_exit(enum ctx_state state)
+/*
+ * OBSOLETE:
+ * This function should be noinstr but the below local_irq_save() is
+ * unsafe because it involves illegal RCU uses through tracing and lockdep.
+ * This is unlikely to be fixed as this function is obsolete. The preferred
+ * way is to call __context_tracking_exit() through user_exit_irqoff()
+ * or context_tracking_guest_exit(). It should be the arch entry code
+ * responsibility to call into context tracking with IRQs disabled.
+ */
+void ct_user_exit(enum ctx_state state)
{
unsigned long flags;
@@ -176,19 +668,30 @@ void context_tracking_exit(enum ctx_state state)
return;
local_irq_save(flags);
- __context_tracking_exit(state);
+ __ct_user_exit(state);
local_irq_restore(flags);
}
-NOKPROBE_SYMBOL(context_tracking_exit);
-EXPORT_SYMBOL_GPL(context_tracking_exit);
+NOKPROBE_SYMBOL(ct_user_exit);
+EXPORT_SYMBOL_GPL(ct_user_exit);
-void context_tracking_user_exit(void)
+/**
+ * user_exit_callable() - Unfortunate ASM callable version of user_exit() for
+ * archs that didn't manage to check the context tracking
+ * static key from low level code.
+ *
+ * This OBSOLETE function should be noinstr but it unsafely calls local_irq_save(),
+ * involving illegal RCU uses through tracing and lockdep. This is unlikely
+ * to be fixed as this function is obsolete. The preferred way is to call
+ * user_exit_irqoff(). It should be the arch entry code responsibility to
+ * call into context tracking with IRQs disabled.
+ */
+void user_exit_callable(void)
{
user_exit();
}
-NOKPROBE_SYMBOL(context_tracking_user_exit);
+NOKPROBE_SYMBOL(user_exit_callable);
-void __init context_tracking_cpu_set(int cpu)
+void __init ct_cpu_track_user(int cpu)
{
static __initdata bool initialized = false;
@@ -212,12 +715,14 @@ void __init context_tracking_cpu_set(int cpu)
initialized = true;
}
-#ifdef CONFIG_CONTEXT_TRACKING_FORCE
+#ifdef CONFIG_CONTEXT_TRACKING_USER_FORCE
void __init context_tracking_init(void)
{
int cpu;
for_each_possible_cpu(cpu)
- context_tracking_cpu_set(cpu);
+ ct_cpu_track_user(cpu);
}
#endif
+
+#endif /* #ifdef CONFIG_CONTEXT_TRACKING_USER */
diff --git a/kernel/cpu_pm.c b/kernel/cpu_pm.c
index 246efc74e3f3..ba4ba71facf9 100644
--- a/kernel/cpu_pm.c
+++ b/kernel/cpu_pm.c
@@ -35,11 +35,11 @@ static int cpu_pm_notify(enum cpu_pm_event event)
* disfunctional in cpu idle. Copy RCU_NONIDLE code to let RCU know
* this.
*/
- rcu_irq_enter_irqson();
+ ct_irq_enter_irqson();
rcu_read_lock();
ret = raw_notifier_call_chain(&cpu_pm_notifier.chain, event, NULL);
rcu_read_unlock();
- rcu_irq_exit_irqson();
+ ct_irq_exit_irqson();
return notifier_to_errno(ret);
}
@@ -49,11 +49,11 @@ static int cpu_pm_notify_robust(enum cpu_pm_event event_up, enum cpu_pm_event ev
unsigned long flags;
int ret;
- rcu_irq_enter_irqson();
+ ct_irq_enter_irqson();
raw_spin_lock_irqsave(&cpu_pm_notifier.lock, flags);
ret = raw_notifier_call_chain_robust(&cpu_pm_notifier.chain, event_up, event_down, NULL);
raw_spin_unlock_irqrestore(&cpu_pm_notifier.lock, flags);
- rcu_irq_exit_irqson();
+ ct_irq_exit_irqson();
return notifier_to_errno(ret);
}
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 032f164abe7c..063068a9ea9b 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -321,7 +321,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
}
/*
- * If this entry hit the idle task invoke rcu_irq_enter() whether
+ * If this entry hit the idle task invoke ct_irq_enter() whether
* RCU is watching or not.
*
* Interrupts can nest when the first interrupt invokes softirq
@@ -332,12 +332,12 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
* not nested into another interrupt.
*
* Checking for rcu_is_watching() here would prevent the nesting
- * interrupt to invoke rcu_irq_enter(). If that nested interrupt is
+ * interrupt to invoke ct_irq_enter(). If that nested interrupt is
* the tick then rcu_flavor_sched_clock_irq() would wrongfully
* assume that it is the first interrupt and eventually claim
* quiescent state and end grace periods prematurely.
*
- * Unconditionally invoke rcu_irq_enter() so RCU state stays
+ * Unconditionally invoke ct_irq_enter() so RCU state stays
* consistent.
*
* TINY_RCU does not support EQS, so let the compiler eliminate
@@ -350,7 +350,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
* as in irqentry_enter_from_user_mode().
*/
lockdep_hardirqs_off(CALLER_ADDR0);
- rcu_irq_enter();
+ ct_irq_enter();
instrumentation_begin();
trace_hardirqs_off_finish();
instrumentation_end();
@@ -418,7 +418,7 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
trace_hardirqs_on_prepare();
lockdep_hardirqs_on_prepare();
instrumentation_end();
- rcu_irq_exit();
+ ct_irq_exit();
lockdep_hardirqs_on(CALLER_ADDR0);
return;
}
@@ -436,7 +436,7 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
* was not watching on entry.
*/
if (state.exit_rcu)
- rcu_irq_exit();
+ ct_irq_exit();
}
}
@@ -449,7 +449,7 @@ irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs)
__nmi_enter();
lockdep_hardirqs_off(CALLER_ADDR0);
lockdep_hardirq_enter();
- rcu_nmi_enter();
+ ct_nmi_enter();
instrumentation_begin();
trace_hardirqs_off_finish();
@@ -469,7 +469,7 @@ void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state)
}
instrumentation_end();
- rcu_nmi_exit();
+ ct_nmi_exit();
lockdep_hardirq_exit();
if (irq_state.lockdep)
lockdep_hardirqs_on(CALLER_ADDR0);
diff --git a/kernel/extable.c b/kernel/extable.c
index bda5e9761541..71f482581cab 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -114,7 +114,7 @@ int kernel_text_address(unsigned long addr)
/* Treat this like an NMI as it can happen anywhere */
if (no_rcu)
- rcu_nmi_enter();
+ ct_nmi_enter();
if (is_module_text_address(addr))
goto out;
@@ -127,7 +127,7 @@ int kernel_text_address(unsigned long addr)
ret = 0;
out:
if (no_rcu)
- rcu_nmi_exit();
+ ct_nmi_exit();
return ret;
}
diff --git a/kernel/fork.c b/kernel/fork.c
index 9174146f6812..28772142022a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1814,6 +1814,7 @@ static inline void rcu_copy_process(struct task_struct *p)
p->trc_reader_nesting = 0;
p->trc_reader_special.s = 0;
INIT_LIST_HEAD(&p->trc_holdout_list);
+ INIT_LIST_HEAD(&p->trc_blkd_node);
#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
}
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index e2f179491b08..64a13eb56078 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -6571,7 +6571,7 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s)
/*
* If a CPU is in the RCU-free window in idle (ie: in the section
- * between rcu_idle_enter() and rcu_idle_exit(), then RCU
+ * between ct_idle_enter() and ct_idle_exit(), then RCU
* considers that CPU to be in an "extended quiescent state",
* which means that RCU will be completely ignoring that CPU.
* Therefore, rcu_read_lock() and friends have absolutely no
diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index 1c630e573548..d471d22a5e21 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -8,6 +8,8 @@ menu "RCU Subsystem"
config TREE_RCU
bool
default y if SMP
+ # Dynticks-idle tracking
+ select CONTEXT_TRACKING_IDLE
help
This option selects the RCU implementation that is
designed for very large SMP system with hundreds or
@@ -262,6 +264,35 @@ config RCU_NOCB_CPU
Say Y here if you need reduced OS jitter, despite added overhead.
Say N here if you are unsure.
+config RCU_NOCB_CPU_DEFAULT_ALL
+ bool "Offload RCU callback processing from all CPUs by default"
+ depends on RCU_NOCB_CPU
+ default n
+ help
+ Use this option to offload callback processing from all CPUs
+ by default, in the absence of the rcu_nocbs or nohz_full boot
+ parameter. This also avoids the need to use any boot parameters
+ to achieve the effect of offloading all CPUs on boot.
+
+ Say Y here if you want offload all CPUs by default on boot.
+ Say N here if you are unsure.
+
+config RCU_NOCB_CPU_CB_BOOST
+ bool "Offload RCU callback from real-time kthread"
+ depends on RCU_NOCB_CPU && RCU_BOOST
+ default y if PREEMPT_RT
+ help
+ Use this option to invoke offloaded callbacks as SCHED_FIFO
+ to avoid starvation by heavy SCHED_OTHER background load.
+ Of course, running as SCHED_FIFO during callback floods will
+ cause the rcuo[ps] kthreads to monopolize the CPU for hundreds
+ of milliseconds or more. Therefore, when enabling this option,
+ it is your responsibility to ensure that latency-sensitive
+ tasks either run with higher priority or run on some other CPU.
+
+ Say Y here if you want to set RT priority for offloading kthreads.
+ Say N here if you are building a !PREEMPT_RT kernel and are unsure.
+
config TASKS_TRACE_RCU_READ_MB
bool "Tasks Trace RCU readers use memory barriers in user and idle"
depends on RCU_EXPERT && TASKS_TRACE_RCU
diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug
index 9b64e55d4f61..4da05beb13d7 100644
--- a/kernel/rcu/Kconfig.debug
+++ b/kernel/rcu/Kconfig.debug
@@ -121,7 +121,7 @@ config RCU_EQS_DEBUG
config RCU_STRICT_GRACE_PERIOD
bool "Provide debug RCU implementation with short grace periods"
- depends on DEBUG_KERNEL && RCU_EXPERT && NR_CPUS <= 4
+ depends on DEBUG_KERNEL && RCU_EXPERT && NR_CPUS <= 4 && !TINY_RCU
default n
select PREEMPT_COUNT if PREEMPT=n
help
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 4916077119f3..be5979da07f5 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -12,10 +12,6 @@
#include <trace/events/rcu.h>
-/* Offset to allow distinguishing irq vs. task-based idle entry/exit. */
-#define DYNTICK_IRQ_NONIDLE ((LONG_MAX / 2) + 1)
-
-
/*
* Grace-period counter management.
*/
@@ -23,6 +19,9 @@
#define RCU_SEQ_CTR_SHIFT 2
#define RCU_SEQ_STATE_MASK ((1 << RCU_SEQ_CTR_SHIFT) - 1)
+/* Low-order bit definition for polled grace-period APIs. */
+#define RCU_GET_STATE_COMPLETED 0x1
+
extern int sysctl_sched_rt_runtime;
/*
@@ -120,6 +119,18 @@ static inline bool rcu_seq_done(unsigned long *sp, unsigned long s)
}
/*
+ * Given a snapshot from rcu_seq_snap(), determine whether or not a
+ * full update-side operation has occurred, but do not allow the
+ * (ULONG_MAX / 2) safety-factor/guard-band.
+ */
+static inline bool rcu_seq_done_exact(unsigned long *sp, unsigned long s)
+{
+ unsigned long cur_s = READ_ONCE(*sp);
+
+ return ULONG_CMP_GE(cur_s, s) || ULONG_CMP_LT(cur_s, s - (2 * RCU_SEQ_STATE_MASK + 1));
+}
+
+/*
* Has a grace period completed since the time the old gp_seq was collected?
*/
static inline bool rcu_seq_completed_gp(unsigned long old, unsigned long new)
diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
index 277a5bfb37d4..3ef02d4a8108 100644
--- a/kernel/rcu/rcuscale.c
+++ b/kernel/rcu/rcuscale.c
@@ -419,6 +419,7 @@ rcu_scale_writer(void *arg)
VERBOSE_SCALEOUT_STRING("rcu_scale_writer task started");
WARN_ON(!wdpp);
set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
+ current->flags |= PF_NO_SETAFFINITY;
sched_set_fifo_low(current);
if (holdoff)
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 7120165a9342..d8e1b270a065 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -75,62 +75,47 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com> and Josh Triplett <josh@
torture_param(int, extendables, RCUTORTURE_MAX_EXTEND,
"Extend readers by disabling bh (1), irqs (2), or preempt (4)");
-torture_param(int, fqs_duration, 0,
- "Duration of fqs bursts (us), 0 to disable");
+torture_param(int, fqs_duration, 0, "Duration of fqs bursts (us), 0 to disable");
torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)");
torture_param(int, fqs_stutter, 3, "Wait time between fqs bursts (s)");
-torture_param(int, fwd_progress, 1, "Test grace-period forward progress");
+torture_param(int, fwd_progress, 1, "Number of grace-period forward progress tasks (0 to disable)");
torture_param(int, fwd_progress_div, 4, "Fraction of CPU stall to wait");
-torture_param(int, fwd_progress_holdoff, 60,
- "Time between forward-progress tests (s)");
-torture_param(bool, fwd_progress_need_resched, 1,
- "Hide cond_resched() behind need_resched()");
+torture_param(int, fwd_progress_holdoff, 60, "Time between forward-progress tests (s)");
+torture_param(bool, fwd_progress_need_resched, 1, "Hide cond_resched() behind need_resched()");
torture_param(bool, gp_cond, false, "Use conditional/async GP wait primitives");
+torture_param(bool, gp_cond_exp, false, "Use conditional/async expedited GP wait primitives");
torture_param(bool, gp_exp, false, "Use expedited GP wait primitives");
-torture_param(bool, gp_normal, false,
- "Use normal (non-expedited) GP wait primitives");
+torture_param(bool, gp_normal, false, "Use normal (non-expedited) GP wait primitives");
torture_param(bool, gp_poll, false, "Use polling GP wait primitives");
+torture_param(bool, gp_poll_exp, false, "Use polling expedited GP wait primitives");
torture_param(bool, gp_sync, false, "Use synchronous GP wait primitives");
torture_param(int, irqreader, 1, "Allow RCU readers from irq handlers");
torture_param(int, leakpointer, 0, "Leak pointer dereferences from readers");
-torture_param(int, n_barrier_cbs, 0,
- "# of callbacks/kthreads for barrier testing");
+torture_param(int, n_barrier_cbs, 0, "# of callbacks/kthreads for barrier testing");
torture_param(int, nfakewriters, 4, "Number of RCU fake writer threads");
torture_param(int, nreaders, -1, "Number of RCU reader threads");
-torture_param(int, object_debug, 0,
- "Enable debug-object double call_rcu() testing");
+torture_param(int, object_debug, 0, "Enable debug-object double call_rcu() testing");
torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
-torture_param(int, onoff_interval, 0,
- "Time between CPU hotplugs (jiffies), 0=disable");
+torture_param(int, onoff_interval, 0, "Time between CPU hotplugs (jiffies), 0=disable");
torture_param(int, nocbs_nthreads, 0, "Number of NOCB toggle threads, 0 to disable");
torture_param(int, nocbs_toggle, 1000, "Time between toggling nocb state (ms)");
-torture_param(int, read_exit_delay, 13,
- "Delay between read-then-exit episodes (s)");
-torture_param(int, read_exit_burst, 16,
- "# of read-then-exit bursts per episode, zero to disable");
+torture_param(int, read_exit_delay, 13, "Delay between read-then-exit episodes (s)");
+torture_param(int, read_exit_burst, 16, "# of read-then-exit bursts per episode, zero to disable");
torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles");
torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable.");
torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable.");
-torture_param(int, stall_cpu_holdoff, 10,
- "Time to wait before starting stall (s).");
-torture_param(bool, stall_no_softlockup, false,
- "Avoid softlockup warning during cpu stall.");
+torture_param(int, stall_cpu_holdoff, 10, "Time to wait before starting stall (s).");
+torture_param(bool, stall_no_softlockup, false, "Avoid softlockup warning during cpu stall.");
torture_param(int, stall_cpu_irqsoff, 0, "Disable interrupts while stalling.");
torture_param(int, stall_cpu_block, 0, "Sleep while stalling.");
-torture_param(int, stall_gp_kthread, 0,
- "Grace-period kthread stall duration (s).");
-torture_param(int, stat_interval, 60,
- "Number of seconds between stats printk()s");
+torture_param(int, stall_gp_kthread, 0, "Grace-period kthread stall duration (s).");
+torture_param(int, stat_interval, 60, "Number of seconds between stats printk()s");
torture_param(int, stutter, 5, "Number of seconds to run/halt test");
torture_param(int, test_boost, 1, "Test RCU prio boost: 0=no, 1=maybe, 2=yes.");
-torture_param(int, test_boost_duration, 4,
- "Duration of each boost test, seconds.");
-torture_param(int, test_boost_interval, 7,
- "Interval between boost tests, seconds.");
-torture_param(bool, test_no_idle_hz, true,
- "Test support for tickless idle CPUs");
-torture_param(int, verbose, 1,
- "Enable verbose debugging printk()s");
+torture_param(int, test_boost_duration, 4, "Duration of each boost test, seconds.");
+torture_param(int, test_boost_interval, 7, "Interval between boost tests, seconds.");
+torture_param(bool, test_no_idle_hz, true, "Test support for tickless idle CPUs");
+torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
static char *torture_type = "rcu";
module_param(torture_type, charp, 0444);
@@ -209,12 +194,16 @@ static int rcu_torture_writer_state;
#define RTWS_DEF_FREE 3
#define RTWS_EXP_SYNC 4
#define RTWS_COND_GET 5
-#define RTWS_COND_SYNC 6
-#define RTWS_POLL_GET 7
-#define RTWS_POLL_WAIT 8
-#define RTWS_SYNC 9
-#define RTWS_STUTTER 10
-#define RTWS_STOPPING 11
+#define RTWS_COND_GET_EXP 6
+#define RTWS_COND_SYNC 7
+#define RTWS_COND_SYNC_EXP 8
+#define RTWS_POLL_GET 9
+#define RTWS_POLL_GET_EXP 10
+#define RTWS_POLL_WAIT 11
+#define RTWS_POLL_WAIT_EXP 12
+#define RTWS_SYNC 13
+#define RTWS_STUTTER 14
+#define RTWS_STOPPING 15
static const char * const rcu_torture_writer_state_names[] = {
"RTWS_FIXED_DELAY",
"RTWS_DELAY",
@@ -222,9 +211,13 @@ static const char * const rcu_torture_writer_state_names[] = {
"RTWS_DEF_FREE",
"RTWS_EXP_SYNC",
"RTWS_COND_GET",
+ "RTWS_COND_GET_EXP",
"RTWS_COND_SYNC",
+ "RTWS_COND_SYNC_EXP",
"RTWS_POLL_GET",
+ "RTWS_POLL_GET_EXP",
"RTWS_POLL_WAIT",
+ "RTWS_POLL_WAIT_EXP",
"RTWS_SYNC",
"RTWS_STUTTER",
"RTWS_STOPPING",
@@ -337,7 +330,12 @@ struct rcu_torture_ops {
void (*deferred_free)(struct rcu_torture *p);
void (*sync)(void);
void (*exp_sync)(void);
+ unsigned long (*get_gp_state_exp)(void);
+ unsigned long (*start_gp_poll_exp)(void);
+ bool (*poll_gp_state_exp)(unsigned long oldstate);
+ void (*cond_sync_exp)(unsigned long oldstate);
unsigned long (*get_gp_state)(void);
+ unsigned long (*get_gp_completed)(void);
unsigned long (*start_gp_poll)(void);
bool (*poll_gp_state)(unsigned long oldstate);
void (*cond_sync)(unsigned long oldstate);
@@ -504,9 +502,14 @@ static struct rcu_torture_ops rcu_ops = {
.sync = synchronize_rcu,
.exp_sync = synchronize_rcu_expedited,
.get_gp_state = get_state_synchronize_rcu,
+ .get_gp_completed = get_completed_synchronize_rcu,
.start_gp_poll = start_poll_synchronize_rcu,
.poll_gp_state = poll_state_synchronize_rcu,
.cond_sync = cond_synchronize_rcu,
+ .get_gp_state_exp = get_state_synchronize_rcu,
+ .start_gp_poll_exp = start_poll_synchronize_rcu_expedited,
+ .poll_gp_state_exp = poll_state_synchronize_rcu,
+ .cond_sync_exp = cond_synchronize_rcu_expedited,
.call = call_rcu,
.cb_barrier = rcu_barrier,
.fqs = rcu_force_quiescent_state,
@@ -1136,9 +1139,8 @@ rcu_torture_fqs(void *arg)
return 0;
}
-// Used by writers to randomly choose from the available grace-period
-// primitives. The only purpose of the initialization is to size the array.
-static int synctype[] = { RTWS_DEF_FREE, RTWS_EXP_SYNC, RTWS_COND_GET, RTWS_POLL_GET, RTWS_SYNC };
+// Used by writers to randomly choose from the available grace-period primitives.
+static int synctype[ARRAY_SIZE(rcu_torture_writer_state_names)] = { };
static int nsynctypes;
/*
@@ -1146,18 +1148,27 @@ static int nsynctypes;
*/
static void rcu_torture_write_types(void)
{
- bool gp_cond1 = gp_cond, gp_exp1 = gp_exp, gp_normal1 = gp_normal;
- bool gp_poll1 = gp_poll, gp_sync1 = gp_sync;
+ bool gp_cond1 = gp_cond, gp_cond_exp1 = gp_cond_exp, gp_exp1 = gp_exp;
+ bool gp_poll_exp1 = gp_poll_exp, gp_normal1 = gp_normal, gp_poll1 = gp_poll;
+ bool gp_sync1 = gp_sync;
/* Initialize synctype[] array. If none set, take default. */
- if (!gp_cond1 && !gp_exp1 && !gp_normal1 && !gp_poll1 && !gp_sync1)
- gp_cond1 = gp_exp1 = gp_normal1 = gp_poll1 = gp_sync1 = true;
+ if (!gp_cond1 && !gp_cond_exp1 && !gp_exp1 && !gp_poll_exp &&
+ !gp_normal1 && !gp_poll1 && !gp_sync1)
+ gp_cond1 = gp_cond_exp1 = gp_exp1 = gp_poll_exp1 =
+ gp_normal1 = gp_poll1 = gp_sync1 = true;
if (gp_cond1 && cur_ops->get_gp_state && cur_ops->cond_sync) {
synctype[nsynctypes++] = RTWS_COND_GET;
pr_info("%s: Testing conditional GPs.\n", __func__);
} else if (gp_cond && (!cur_ops->get_gp_state || !cur_ops->cond_sync)) {
pr_alert("%s: gp_cond without primitives.\n", __func__);
}
+ if (gp_cond_exp1 && cur_ops->get_gp_state_exp && cur_ops->cond_sync_exp) {
+ synctype[nsynctypes++] = RTWS_COND_GET_EXP;
+ pr_info("%s: Testing conditional expedited GPs.\n", __func__);
+ } else if (gp_cond_exp && (!cur_ops->get_gp_state_exp || !cur_ops->cond_sync_exp)) {
+ pr_alert("%s: gp_cond_exp without primitives.\n", __func__);
+ }
if (gp_exp1 && cur_ops->exp_sync) {
synctype[nsynctypes++] = RTWS_EXP_SYNC;
pr_info("%s: Testing expedited GPs.\n", __func__);
@@ -1176,6 +1187,12 @@ static void rcu_torture_write_types(void)
} else if (gp_poll && (!cur_ops->start_gp_poll || !cur_ops->poll_gp_state)) {
pr_alert("%s: gp_poll without primitives.\n", __func__);
}
+ if (gp_poll_exp1 && cur_ops->start_gp_poll_exp && cur_ops->poll_gp_state_exp) {
+ synctype[nsynctypes++] = RTWS_POLL_GET_EXP;
+ pr_info("%s: Testing polling expedited GPs.\n", __func__);
+ } else if (gp_poll_exp && (!cur_ops->start_gp_poll_exp || !cur_ops->poll_gp_state_exp)) {
+ pr_alert("%s: gp_poll_exp without primitives.\n", __func__);
+ }
if (gp_sync1 && cur_ops->sync) {
synctype[nsynctypes++] = RTWS_SYNC;
pr_info("%s: Testing normal GPs.\n", __func__);
@@ -1254,6 +1271,10 @@ rcu_torture_writer(void *arg)
rcu_torture_writer_state_getname(),
rcu_torture_writer_state,
cookie, cur_ops->get_gp_state());
+ if (cur_ops->get_gp_completed) {
+ cookie = cur_ops->get_gp_completed();
+ WARN_ON_ONCE(!cur_ops->poll_gp_state(cookie));
+ }
cur_ops->readunlock(idx);
}
switch (synctype[torture_random(&rand) % nsynctypes]) {
@@ -1263,7 +1284,12 @@ rcu_torture_writer(void *arg)
break;
case RTWS_EXP_SYNC:
rcu_torture_writer_state = RTWS_EXP_SYNC;
+ if (cur_ops->get_gp_state && cur_ops->poll_gp_state)
+ cookie = cur_ops->get_gp_state();
cur_ops->exp_sync();
+ cur_ops->exp_sync();
+ if (cur_ops->get_gp_state && cur_ops->poll_gp_state)
+ WARN_ON_ONCE(!cur_ops->poll_gp_state(cookie));
rcu_torture_pipe_update(old_rp);
break;
case RTWS_COND_GET:
@@ -1274,6 +1300,14 @@ rcu_torture_writer(void *arg)
cur_ops->cond_sync(gp_snap);
rcu_torture_pipe_update(old_rp);
break;
+ case RTWS_COND_GET_EXP:
+ rcu_torture_writer_state = RTWS_COND_GET_EXP;
+ gp_snap = cur_ops->get_gp_state_exp();
+ torture_hrtimeout_jiffies(torture_random(&rand) % 16, &rand);
+ rcu_torture_writer_state = RTWS_COND_SYNC_EXP;
+ cur_ops->cond_sync_exp(gp_snap);
+ rcu_torture_pipe_update(old_rp);
+ break;
case RTWS_POLL_GET:
rcu_torture_writer_state = RTWS_POLL_GET;
gp_snap = cur_ops->start_gp_poll();
@@ -1283,9 +1317,23 @@ rcu_torture_writer(void *arg)
&rand);
rcu_torture_pipe_update(old_rp);
break;
+ case RTWS_POLL_GET_EXP:
+ rcu_torture_writer_state = RTWS_POLL_GET_EXP;
+ gp_snap = cur_ops->start_gp_poll_exp();
+ rcu_torture_writer_state = RTWS_POLL_WAIT_EXP;
+ while (!cur_ops->poll_gp_state_exp(gp_snap))
+ torture_hrtimeout_jiffies(torture_random(&rand) % 16,
+ &rand);
+ rcu_torture_pipe_update(old_rp);
+ break;
case RTWS_SYNC:
rcu_torture_writer_state = RTWS_SYNC;
+ if (cur_ops->get_gp_state && cur_ops->poll_gp_state)
+ cookie = cur_ops->get_gp_state();
cur_ops->sync();
+ cur_ops->sync();
+ if (cur_ops->get_gp_state && cur_ops->poll_gp_state)
+ WARN_ON_ONCE(!cur_ops->poll_gp_state(cookie));
rcu_torture_pipe_update(old_rp);
break;
default:
@@ -1321,8 +1369,9 @@ rcu_torture_writer(void *arg)
if (list_empty(&rcu_tortures[i].rtort_free) &&
rcu_access_pointer(rcu_torture_current) !=
&rcu_tortures[i]) {
- rcu_ftrace_dump(DUMP_ALL);
+ tracing_off();
WARN(1, "%s: rtort_pipe_count: %d\n", __func__, rcu_tortures[i].rtort_pipe_count);
+ rcu_ftrace_dump(DUMP_ALL);
}
if (stutter_waited)
sched_set_normal(current, oldnice);
@@ -1384,6 +1433,11 @@ rcu_torture_fakewriter(void *arg)
torture_hrtimeout_jiffies(torture_random(&rand) % 16, &rand);
cur_ops->cond_sync(gp_snap);
break;
+ case RTWS_COND_GET_EXP:
+ gp_snap = cur_ops->get_gp_state_exp();
+ torture_hrtimeout_jiffies(torture_random(&rand) % 16, &rand);
+ cur_ops->cond_sync_exp(gp_snap);
+ break;
case RTWS_POLL_GET:
gp_snap = cur_ops->start_gp_poll();
while (!cur_ops->poll_gp_state(gp_snap)) {
@@ -1391,6 +1445,13 @@ rcu_torture_fakewriter(void *arg)
&rand);
}
break;
+ case RTWS_POLL_GET_EXP:
+ gp_snap = cur_ops->start_gp_poll_exp();
+ while (!cur_ops->poll_gp_state_exp(gp_snap)) {
+ torture_hrtimeout_jiffies(torture_random(&rand) % 16,
+ &rand);
+ }
+ break;
case RTWS_SYNC:
cur_ops->sync();
break;
@@ -1868,7 +1929,7 @@ rcu_torture_stats_print(void)
batchsummary[i] += READ_ONCE(per_cpu(rcu_torture_batch, cpu)[i]);
}
}
- for (i = RCU_TORTURE_PIPE_LEN - 1; i >= 0; i--) {
+ for (i = RCU_TORTURE_PIPE_LEN; i >= 0; i--) {
if (pipesummary[i] != 0)
break;
}
@@ -1990,7 +2051,13 @@ static void rcu_torture_mem_dump_obj(void)
static int z;
kcp = kmem_cache_create("rcuscale", 136, 8, SLAB_STORE_USER, NULL);
+ if (WARN_ON_ONCE(!kcp))
+ return;
rhp = kmem_cache_alloc(kcp, GFP_KERNEL);
+ if (WARN_ON_ONCE(!rhp)) {
+ kmem_cache_destroy(kcp);
+ return;
+ }
pr_alert("mem_dump_obj() slab test: rcu_torture_stats = %px, &rhp = %px, rhp = %px, &z = %px\n", stats_task, &rhp, rhp, &z);
pr_alert("mem_dump_obj(ZERO_SIZE_PTR):");
mem_dump_obj(ZERO_SIZE_PTR);
@@ -2007,6 +2074,8 @@ static void rcu_torture_mem_dump_obj(void)
kmem_cache_free(kcp, rhp);
kmem_cache_destroy(kcp);
rhp = kmalloc(sizeof(*rhp), GFP_KERNEL);
+ if (WARN_ON_ONCE(!rhp))
+ return;
pr_alert("mem_dump_obj() kmalloc test: rcu_torture_stats = %px, &rhp = %px, rhp = %px\n", stats_task, &rhp, rhp);
pr_alert("mem_dump_obj(kmalloc %px):", rhp);
mem_dump_obj(rhp);
@@ -2014,6 +2083,8 @@ static void rcu_torture_mem_dump_obj(void)
mem_dump_obj(&rhp->func);
kfree(rhp);
rhp = vmalloc(4096);
+ if (WARN_ON_ONCE(!rhp))
+ return;
pr_alert("mem_dump_obj() vmalloc test: rcu_torture_stats = %px, &rhp = %px, rhp = %px\n", stats_task, &rhp, rhp);
pr_alert("mem_dump_obj(vmalloc %px):", rhp);
mem_dump_obj(rhp);
@@ -2075,6 +2146,19 @@ static int rcutorture_booster_init(unsigned int cpu)
if (boost_tasks[cpu] != NULL)
return 0; /* Already created, nothing more to do. */
+ // Testing RCU priority boosting requires rcutorture do
+ // some serious abuse. Counter this by running ksoftirqd
+ // at higher priority.
+ if (IS_BUILTIN(CONFIG_RCU_TORTURE_TEST)) {
+ struct sched_param sp;
+ struct task_struct *t;
+
+ t = per_cpu(ksoftirqd, cpu);
+ WARN_ON_ONCE(!t);
+ sp.sched_priority = 2;
+ sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+ }
+
/* Don't allow time recalculation while creating a new task. */
mutex_lock(&boost_mutex);
rcu_torture_disable_rt_throttle();
@@ -2873,7 +2957,6 @@ static int rcu_torture_read_exit_child(void *trsp_in)
// Parent kthread which creates and destroys read-exit child kthreads.
static int rcu_torture_read_exit(void *unused)
{
- int count = 0;
bool errexit = false;
int i;
struct task_struct *tsp;
@@ -2885,34 +2968,28 @@ static int rcu_torture_read_exit(void *unused)
// Each pass through this loop does one read-exit episode.
do {
- if (++count > read_exit_burst) {
- VERBOSE_TOROUT_STRING("rcu_torture_read_exit: End of episode");
- rcu_barrier(); // Wait for task_struct free, avoid OOM.
- for (i = 0; i < read_exit_delay; i++) {
- schedule_timeout_uninterruptible(HZ);
- if (READ_ONCE(read_exit_child_stop))
- break;
+ VERBOSE_TOROUT_STRING("rcu_torture_read_exit: Start of episode");
+ for (i = 0; i < read_exit_burst; i++) {
+ if (READ_ONCE(read_exit_child_stop))
+ break;
+ stutter_wait("rcu_torture_read_exit");
+ // Spawn child.
+ tsp = kthread_run(rcu_torture_read_exit_child,
+ &trs, "%s", "rcu_torture_read_exit_child");
+ if (IS_ERR(tsp)) {
+ TOROUT_ERRSTRING("out of memory");
+ errexit = true;
+ break;
}
- if (!READ_ONCE(read_exit_child_stop))
- VERBOSE_TOROUT_STRING("rcu_torture_read_exit: Start of episode");
- count = 0;
- }
- if (READ_ONCE(read_exit_child_stop))
- break;
- // Spawn child.
- tsp = kthread_run(rcu_torture_read_exit_child,
- &trs, "%s",
- "rcu_torture_read_exit_child");
- if (IS_ERR(tsp)) {
- TOROUT_ERRSTRING("out of memory");
- errexit = true;
- tsp = NULL;
- break;
+ cond_resched();
+ kthread_stop(tsp);
+ n_read_exits++;
}
- cond_resched();
- kthread_stop(tsp);
- n_read_exits ++;
- stutter_wait("rcu_torture_read_exit");
+ VERBOSE_TOROUT_STRING("rcu_torture_read_exit: End of episode");
+ rcu_barrier(); // Wait for task_struct free, avoid OOM.
+ i = 0;
+ for (; !errexit && !READ_ONCE(read_exit_child_stop) && i < read_exit_delay; i++)
+ schedule_timeout_uninterruptible(HZ);
} while (!errexit && !READ_ONCE(read_exit_child_stop));
// Clean up and exit.
@@ -3122,6 +3199,7 @@ static void rcu_test_debug_objects(void)
pr_alert("%s: WARN: Duplicate call_rcu() test complete.\n", KBUILD_MODNAME);
destroy_rcu_head_on_stack(&rh1);
destroy_rcu_head_on_stack(&rh2);
+ kfree(rhp);
#else /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
pr_alert("%s: !CONFIG_DEBUG_OBJECTS_RCU_HEAD, not testing duplicate call_rcu()\n", KBUILD_MODNAME);
#endif /* #else #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
@@ -3329,21 +3407,6 @@ rcu_torture_init(void)
rcutor_hp = firsterr;
if (torture_init_error(firsterr))
goto unwind;
-
- // Testing RCU priority boosting requires rcutorture do
- // some serious abuse. Counter this by running ksoftirqd
- // at higher priority.
- if (IS_BUILTIN(CONFIG_RCU_TORTURE_TEST)) {
- for_each_online_cpu(cpu) {
- struct sched_param sp;
- struct task_struct *t;
-
- t = per_cpu(ksoftirqd, cpu);
- WARN_ON_ONCE(!t);
- sp.sched_priority = 2;
- sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
- }
- }
}
shutdown_jiffies = jiffies + shutdown_secs * HZ;
firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup);
diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c
index 909644abee67..435c884c02b5 100644
--- a/kernel/rcu/refscale.c
+++ b/kernel/rcu/refscale.c
@@ -385,7 +385,7 @@ static struct ref_scale_ops rwsem_ops = {
};
// Definitions for global spinlock
-static DEFINE_SPINLOCK(test_lock);
+static DEFINE_RAW_SPINLOCK(test_lock);
static void ref_lock_section(const int nloops)
{
@@ -393,8 +393,8 @@ static void ref_lock_section(const int nloops)
preempt_disable();
for (i = nloops; i >= 0; i--) {
- spin_lock(&test_lock);
- spin_unlock(&test_lock);
+ raw_spin_lock(&test_lock);
+ raw_spin_unlock(&test_lock);
}
preempt_enable();
}
@@ -405,9 +405,9 @@ static void ref_lock_delay_section(const int nloops, const int udl, const int nd
preempt_disable();
for (i = nloops; i >= 0; i--) {
- spin_lock(&test_lock);
+ raw_spin_lock(&test_lock);
un_delay(udl, ndl);
- spin_unlock(&test_lock);
+ raw_spin_unlock(&test_lock);
}
preempt_enable();
}
@@ -427,8 +427,8 @@ static void ref_lock_irq_section(const int nloops)
preempt_disable();
for (i = nloops; i >= 0; i--) {
- spin_lock_irqsave(&test_lock, flags);
- spin_unlock_irqrestore(&test_lock, flags);
+ raw_spin_lock_irqsave(&test_lock, flags);
+ raw_spin_unlock_irqrestore(&test_lock, flags);
}
preempt_enable();
}
@@ -440,9 +440,9 @@ static void ref_lock_irq_delay_section(const int nloops, const int udl, const in
preempt_disable();
for (i = nloops; i >= 0; i--) {
- spin_lock_irqsave(&test_lock, flags);
+ raw_spin_lock_irqsave(&test_lock, flags);
un_delay(udl, ndl);
- spin_unlock_irqrestore(&test_lock, flags);
+ raw_spin_unlock_irqrestore(&test_lock, flags);
}
preempt_enable();
}
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 3925e32159b5..83c7e6620d40 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -14,7 +14,7 @@
struct rcu_tasks;
typedef void (*rcu_tasks_gp_func_t)(struct rcu_tasks *rtp);
-typedef void (*pregp_func_t)(void);
+typedef void (*pregp_func_t)(struct list_head *hop);
typedef void (*pertask_func_t)(struct task_struct *t, struct list_head *hop);
typedef void (*postscan_func_t)(struct list_head *hop);
typedef void (*holdouts_func_t)(struct list_head *hop, bool ndrpt, bool *frptp);
@@ -29,6 +29,7 @@ typedef void (*postgp_func_t)(struct rcu_tasks *rtp);
* @rtp_work: Work queue for invoking callbacks.
* @rtp_irq_work: IRQ work queue for deferred wakeups.
* @barrier_q_head: RCU callback for barrier operation.
+ * @rtp_blkd_tasks: List of tasks blocked as readers.
* @cpu: CPU number corresponding to this entry.
* @rtpp: Pointer to the rcu_tasks structure.
*/
@@ -40,6 +41,7 @@ struct rcu_tasks_percpu {
struct work_struct rtp_work;
struct irq_work rtp_irq_work;
struct rcu_head barrier_q_head;
+ struct list_head rtp_blkd_tasks;
int cpu;
struct rcu_tasks *rtpp;
};
@@ -48,6 +50,7 @@ struct rcu_tasks_percpu {
* struct rcu_tasks - Definition for a Tasks-RCU-like mechanism.
* @cbs_wait: RCU wait allowing a new callback to get kthread's attention.
* @cbs_gbl_lock: Lock protecting callback list.
+ * @tasks_gp_mutex: Mutex protecting grace period, needed during mid-boot dead zone.
* @kthread_ptr: This flavor's grace-period/callback-invocation kthread.
* @gp_func: This flavor's grace-period-wait function.
* @gp_state: Grace period's most recent state transition (debugging).
@@ -79,6 +82,7 @@ struct rcu_tasks_percpu {
struct rcu_tasks {
struct rcuwait cbs_wait;
raw_spinlock_t cbs_gbl_lock;
+ struct mutex tasks_gp_mutex;
int gp_state;
int gp_sleep;
int init_fract;
@@ -119,6 +123,7 @@ static struct rcu_tasks rt_name = \
{ \
.cbs_wait = __RCUWAIT_INITIALIZER(rt_name.wait), \
.cbs_gbl_lock = __RAW_SPIN_LOCK_UNLOCKED(rt_name.cbs_gbl_lock), \
+ .tasks_gp_mutex = __MUTEX_INITIALIZER(rt_name.tasks_gp_mutex), \
.gp_func = gp, \
.call_func = call, \
.rtpcpu = &rt_name ## __percpu, \
@@ -140,6 +145,7 @@ static int rcu_task_ipi_delay __read_mostly = RCU_TASK_IPI_DELAY;
module_param(rcu_task_ipi_delay, int, 0644);
/* Control stall timeouts. Disable with <= 0, otherwise jiffies till stall. */
+#define RCU_TASK_BOOT_STALL_TIMEOUT (HZ * 30)
#define RCU_TASK_STALL_TIMEOUT (HZ * 60 * 10)
static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT;
module_param(rcu_task_stall_timeout, int, 0644);
@@ -253,6 +259,8 @@ static void cblist_init_generic(struct rcu_tasks *rtp)
INIT_WORK(&rtpcp->rtp_work, rcu_tasks_invoke_cbs_wq);
rtpcp->cpu = cpu;
rtpcp->rtpp = rtp;
+ if (!rtpcp->rtp_blkd_tasks.next)
+ INIT_LIST_HEAD(&rtpcp->rtp_blkd_tasks);
raw_spin_unlock_rcu_node(rtpcp); // irqs remain disabled.
}
raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags);
@@ -323,17 +331,6 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
irq_work_queue(&rtpcp->rtp_irq_work);
}
-// Wait for a grace period for the specified flavor of Tasks RCU.
-static void synchronize_rcu_tasks_generic(struct rcu_tasks *rtp)
-{
- /* Complain if the scheduler has not started. */
- RCU_LOCKDEP_WARN(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE,
- "synchronize_rcu_tasks called too soon");
-
- /* Wait for the grace period. */
- wait_rcu_gp(rtp->call_func);
-}
-
// RCU callback function for rcu_barrier_tasks_generic().
static void rcu_barrier_tasks_generic_cb(struct rcu_head *rhp)
{
@@ -439,6 +436,11 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp)
WRITE_ONCE(rtp->percpu_dequeue_lim, 1);
pr_info("Completing switch %s to CPU-0 callback queuing.\n", rtp->name);
}
+ for (cpu = rtp->percpu_dequeue_lim; cpu < nr_cpu_ids; cpu++) {
+ struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
+
+ WARN_ON_ONCE(rcu_segcblist_n_cbs(&rtpcp->cblist));
+ }
raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags);
}
@@ -497,10 +499,41 @@ static void rcu_tasks_invoke_cbs_wq(struct work_struct *wp)
rcu_tasks_invoke_cbs(rtp, rtpcp);
}
-/* RCU-tasks kthread that detects grace periods and invokes callbacks. */
-static int __noreturn rcu_tasks_kthread(void *arg)
+// Wait for one grace period.
+static void rcu_tasks_one_gp(struct rcu_tasks *rtp, bool midboot)
{
int needgpcb;
+
+ mutex_lock(&rtp->tasks_gp_mutex);
+
+ // If there were none, wait a bit and start over.
+ if (unlikely(midboot)) {
+ needgpcb = 0x2;
+ } else {
+ set_tasks_gp_state(rtp, RTGS_WAIT_CBS);
+ rcuwait_wait_event(&rtp->cbs_wait,
+ (needgpcb = rcu_tasks_need_gpcb(rtp)),
+ TASK_IDLE);
+ }
+
+ if (needgpcb & 0x2) {
+ // Wait for one grace period.
+ set_tasks_gp_state(rtp, RTGS_WAIT_GP);
+ rtp->gp_start = jiffies;
+ rcu_seq_start(&rtp->tasks_gp_seq);
+ rtp->gp_func(rtp);
+ rcu_seq_end(&rtp->tasks_gp_seq);
+ }
+
+ // Invoke callbacks.
+ set_tasks_gp_state(rtp, RTGS_INVOKE_CBS);
+ rcu_tasks_invoke_cbs(rtp, per_cpu_ptr(rtp->rtpcpu, 0));
+ mutex_unlock(&rtp->tasks_gp_mutex);
+}
+
+// RCU-tasks kthread that detects grace periods and invokes callbacks.
+static int __noreturn rcu_tasks_kthread(void *arg)
+{
struct rcu_tasks *rtp = arg;
/* Run on housekeeping CPUs by default. Sysadm can move if desired. */
@@ -514,29 +547,28 @@ static int __noreturn rcu_tasks_kthread(void *arg)
* This loop is terminated by the system going down. ;-)
*/
for (;;) {
- set_tasks_gp_state(rtp, RTGS_WAIT_CBS);
+ // Wait for one grace period and invoke any callbacks
+ // that are ready.
+ rcu_tasks_one_gp(rtp, false);
- /* If there were none, wait a bit and start over. */
- rcuwait_wait_event(&rtp->cbs_wait,
- (needgpcb = rcu_tasks_need_gpcb(rtp)),
- TASK_IDLE);
-
- if (needgpcb & 0x2) {
- // Wait for one grace period.
- set_tasks_gp_state(rtp, RTGS_WAIT_GP);
- rtp->gp_start = jiffies;
- rcu_seq_start(&rtp->tasks_gp_seq);
- rtp->gp_func(rtp);
- rcu_seq_end(&rtp->tasks_gp_seq);
- }
+ // Paranoid sleep to keep this from entering a tight loop.
+ schedule_timeout_idle(rtp->gp_sleep);
+ }
+}
- /* Invoke callbacks. */
- set_tasks_gp_state(rtp, RTGS_INVOKE_CBS);
- rcu_tasks_invoke_cbs(rtp, per_cpu_ptr(rtp->rtpcpu, 0));
+// Wait for a grace period for the specified flavor of Tasks RCU.
+static void synchronize_rcu_tasks_generic(struct rcu_tasks *rtp)
+{
+ /* Complain if the scheduler has not started. */
+ RCU_LOCKDEP_WARN(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE,
+ "synchronize_rcu_tasks called too soon");
- /* Paranoid sleep to keep this from entering a tight loop */
- schedule_timeout_idle(rtp->gp_sleep);
+ // If the grace-period kthread is running, use it.
+ if (READ_ONCE(rtp->kthread_ptr)) {
+ wait_rcu_gp(rtp->call_func);
+ return;
}
+ rcu_tasks_one_gp(rtp, true);
}
/* Spawn RCU-tasks grace-period kthread. */
@@ -630,7 +662,7 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
struct task_struct *t;
set_tasks_gp_state(rtp, RTGS_PRE_WAIT_GP);
- rtp->pregp_func();
+ rtp->pregp_func(&holdouts);
/*
* There were callbacks, so we need to wait for an RCU-tasks
@@ -639,10 +671,12 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
* and make a list of them in holdouts.
*/
set_tasks_gp_state(rtp, RTGS_SCAN_TASKLIST);
- rcu_read_lock();
- for_each_process_thread(g, t)
- rtp->pertask_func(t, &holdouts);
- rcu_read_unlock();
+ if (rtp->pertask_func) {
+ rcu_read_lock();
+ for_each_process_thread(g, t)
+ rtp->pertask_func(t, &holdouts);
+ rcu_read_unlock();
+ }
set_tasks_gp_state(rtp, RTGS_POST_SCAN_TASKLIST);
rtp->postscan_func(&holdouts);
@@ -760,7 +794,7 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
// disabling.
/* Pre-grace-period preparation. */
-static void rcu_tasks_pregp_step(void)
+static void rcu_tasks_pregp_step(struct list_head *hop)
{
/*
* Wait for all pre-existing t->on_rq and t->nvcsw transitions
@@ -1105,11 +1139,10 @@ EXPORT_SYMBOL_GPL(show_rcu_tasks_rude_gp_kthread);
// 3. Avoids expensive read-side instructions, having overhead similar
// to that of Preemptible RCU.
//
-// There are of course downsides. The grace-period code can send IPIs to
-// CPUs, even when those CPUs are in the idle loop or in nohz_full userspace.
-// It is necessary to scan the full tasklist, much as for Tasks RCU. There
-// is a single callback queue guarded by a single lock, again, much as for
-// Tasks RCU. If needed, these downsides can be at least partially remedied.
+// There are of course downsides. For example, the grace-period code
+// can send IPIs to CPUs, even when those CPUs are in the idle loop or
+// in nohz_full userspace. If needed, these downsides can be at least
+// partially remedied.
//
// Perhaps most important, this variant of RCU does not affect the vanilla
// flavors, rcu_preempt and rcu_sched. The fact that RCU Tasks Trace
@@ -1122,38 +1155,30 @@ EXPORT_SYMBOL_GPL(show_rcu_tasks_rude_gp_kthread);
// invokes these functions in this order:
//
// rcu_tasks_trace_pregp_step():
-// Initialize the count of readers and block CPU-hotplug operations.
-// rcu_tasks_trace_pertask(), invoked on every non-idle task:
-// Initialize per-task state and attempt to identify an immediate
-// quiescent state for that task, or, failing that, attempt to
-// set that task's .need_qs flag so that task's next outermost
-// rcu_read_unlock_trace() will report the quiescent state (in which
-// case the count of readers is incremented). If both attempts fail,
-// the task is added to a "holdout" list. Note that IPIs are used
-// to invoke trc_read_check_handler() in the context of running tasks
-// in order to avoid ordering overhead on common-case shared-variable
-// accessses.
+// Disables CPU hotplug, adds all currently executing tasks to the
+// holdout list, then checks the state of all tasks that blocked
+// or were preempted within their current RCU Tasks Trace read-side
+// critical section, adding them to the holdout list if appropriate.
+// Finally, this function re-enables CPU hotplug.
+// The ->pertask_func() pointer is NULL, so there is no per-task processing.
// rcu_tasks_trace_postscan():
-// Initialize state and attempt to identify an immediate quiescent
-// state as above (but only for idle tasks), unblock CPU-hotplug
-// operations, and wait for an RCU grace period to avoid races with
-// tasks that are in the process of exiting.
+// Invokes synchronize_rcu() to wait for late-stage exiting tasks
+// to finish exiting.
// check_all_holdout_tasks_trace(), repeatedly until holdout list is empty:
// Scans the holdout list, attempting to identify a quiescent state
// for each task on the list. If there is a quiescent state, the
-// corresponding task is removed from the holdout list.
+// corresponding task is removed from the holdout list. Once this
+// list is empty, the grace period has completed.
// rcu_tasks_trace_postgp():
-// Wait for the count of readers do drop to zero, reporting any stalls.
-// Also execute full memory barriers to maintain ordering with code
-// executing after the grace period.
+// Provides the needed full memory barrier and does debug checks.
//
// The exit_tasks_rcu_finish_trace() synchronizes with exiting tasks.
//
-// Pre-grace-period update-side code is ordered before the grace
-// period via the ->cbs_lock and barriers in rcu_tasks_kthread().
-// Pre-grace-period read-side code is ordered before the grace period by
-// atomic_dec_and_test() of the count of readers (for IPIed readers) and by
-// scheduler context-switch ordering (for locked-down non-running readers).
+// Pre-grace-period update-side code is ordered before the grace period
+// via the ->cbs_lock and barriers in rcu_tasks_kthread(). Pre-grace-period
+// read-side code is ordered before the grace period by atomic operations
+// on .b.need_qs flag of each task involved in this process, or by scheduler
+// context-switch ordering (for locked-down non-running readers).
// The lockdep state must be outside of #ifdef to be useful.
#ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -1165,9 +1190,6 @@ EXPORT_SYMBOL_GPL(rcu_trace_lock_map);
#ifdef CONFIG_TASKS_TRACE_RCU
-static atomic_t trc_n_readers_need_end; // Number of waited-for readers.
-static DECLARE_WAIT_QUEUE_HEAD(trc_wait); // List of holdout tasks.
-
// Record outstanding IPIs to each CPU. No point in sending two...
static DEFINE_PER_CPU(bool, trc_ipi_to_cpu);
@@ -1176,44 +1198,104 @@ static DEFINE_PER_CPU(bool, trc_ipi_to_cpu);
static unsigned long n_heavy_reader_attempts;
static unsigned long n_heavy_reader_updates;
static unsigned long n_heavy_reader_ofl_updates;
+static unsigned long n_trc_holdouts;
void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func);
DEFINE_RCU_TASKS(rcu_tasks_trace, rcu_tasks_wait_gp, call_rcu_tasks_trace,
"RCU Tasks Trace");
+/* Load from ->trc_reader_special.b.need_qs with proper ordering. */
+static u8 rcu_ld_need_qs(struct task_struct *t)
+{
+ smp_mb(); // Enforce full grace-period ordering.
+ return smp_load_acquire(&t->trc_reader_special.b.need_qs);
+}
+
+/* Store to ->trc_reader_special.b.need_qs with proper ordering. */
+static void rcu_st_need_qs(struct task_struct *t, u8 v)
+{
+ smp_store_release(&t->trc_reader_special.b.need_qs, v);
+ smp_mb(); // Enforce full grace-period ordering.
+}
+
/*
- * This irq_work handler allows rcu_read_unlock_trace() to be invoked
- * while the scheduler locks are held.
+ * Do a cmpxchg() on ->trc_reader_special.b.need_qs, allowing for
+ * the four-byte operand-size restriction of some platforms.
+ * Returns the old value, which is often ignored.
*/
-static void rcu_read_unlock_iw(struct irq_work *iwp)
+u8 rcu_trc_cmpxchg_need_qs(struct task_struct *t, u8 old, u8 new)
{
- wake_up(&trc_wait);
+ union rcu_special ret;
+ union rcu_special trs_old = READ_ONCE(t->trc_reader_special);
+ union rcu_special trs_new = trs_old;
+
+ if (trs_old.b.need_qs != old)
+ return trs_old.b.need_qs;
+ trs_new.b.need_qs = new;
+ ret.s = cmpxchg(&t->trc_reader_special.s, trs_old.s, trs_new.s);
+ return ret.b.need_qs;
}
-static DEFINE_IRQ_WORK(rcu_tasks_trace_iw, rcu_read_unlock_iw);
+EXPORT_SYMBOL_GPL(rcu_trc_cmpxchg_need_qs);
-/* If we are the last reader, wake up the grace-period kthread. */
+/*
+ * If we are the last reader, signal the grace-period kthread.
+ * Also remove from the per-CPU list of blocked tasks.
+ */
void rcu_read_unlock_trace_special(struct task_struct *t)
{
- int nq = READ_ONCE(t->trc_reader_special.b.need_qs);
+ unsigned long flags;
+ struct rcu_tasks_percpu *rtpcp;
+ union rcu_special trs;
+
+ // Open-coded full-word version of rcu_ld_need_qs().
+ smp_mb(); // Enforce full grace-period ordering.
+ trs = smp_load_acquire(&t->trc_reader_special);
- if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) &&
- t->trc_reader_special.b.need_mb)
+ if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) && t->trc_reader_special.b.need_mb)
smp_mb(); // Pairs with update-side barriers.
// Update .need_qs before ->trc_reader_nesting for irq/NMI handlers.
- if (nq)
- WRITE_ONCE(t->trc_reader_special.b.need_qs, false);
+ if (trs.b.need_qs == (TRC_NEED_QS_CHECKED | TRC_NEED_QS)) {
+ u8 result = rcu_trc_cmpxchg_need_qs(t, TRC_NEED_QS_CHECKED | TRC_NEED_QS,
+ TRC_NEED_QS_CHECKED);
+
+ WARN_ONCE(result != trs.b.need_qs, "%s: result = %d", __func__, result);
+ }
+ if (trs.b.blocked) {
+ rtpcp = per_cpu_ptr(rcu_tasks_trace.rtpcpu, t->trc_blkd_cpu);
+ raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
+ list_del_init(&t->trc_blkd_node);
+ WRITE_ONCE(t->trc_reader_special.b.blocked, false);
+ raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
+ }
WRITE_ONCE(t->trc_reader_nesting, 0);
- if (nq && atomic_dec_and_test(&trc_n_readers_need_end))
- irq_work_queue(&rcu_tasks_trace_iw);
}
EXPORT_SYMBOL_GPL(rcu_read_unlock_trace_special);
+/* Add a newly blocked reader task to its CPU's list. */
+void rcu_tasks_trace_qs_blkd(struct task_struct *t)
+{
+ unsigned long flags;
+ struct rcu_tasks_percpu *rtpcp;
+
+ local_irq_save(flags);
+ rtpcp = this_cpu_ptr(rcu_tasks_trace.rtpcpu);
+ raw_spin_lock_rcu_node(rtpcp); // irqs already disabled
+ t->trc_blkd_cpu = smp_processor_id();
+ if (!rtpcp->rtp_blkd_tasks.next)
+ INIT_LIST_HEAD(&rtpcp->rtp_blkd_tasks);
+ list_add(&t->trc_blkd_node, &rtpcp->rtp_blkd_tasks);
+ WRITE_ONCE(t->trc_reader_special.b.blocked, true);
+ raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
+}
+EXPORT_SYMBOL_GPL(rcu_tasks_trace_qs_blkd);
+
/* Add a task to the holdout list, if it is not already on the list. */
static void trc_add_holdout(struct task_struct *t, struct list_head *bhp)
{
if (list_empty(&t->trc_holdout_list)) {
get_task_struct(t);
list_add(&t->trc_holdout_list, bhp);
+ n_trc_holdouts++;
}
}
@@ -1223,37 +1305,36 @@ static void trc_del_holdout(struct task_struct *t)
if (!list_empty(&t->trc_holdout_list)) {
list_del_init(&t->trc_holdout_list);
put_task_struct(t);
+ n_trc_holdouts--;
}
}
/* IPI handler to check task state. */
static void trc_read_check_handler(void *t_in)
{
+ int nesting;
struct task_struct *t = current;
struct task_struct *texp = t_in;
// If the task is no longer running on this CPU, leave.
- if (unlikely(texp != t)) {
+ if (unlikely(texp != t))
goto reset_ipi; // Already on holdout list, so will check later.
- }
// If the task is not in a read-side critical section, and
// if this is the last reader, awaken the grace-period kthread.
- if (likely(!READ_ONCE(t->trc_reader_nesting))) {
- WRITE_ONCE(t->trc_reader_checked, true);
+ nesting = READ_ONCE(t->trc_reader_nesting);
+ if (likely(!nesting)) {
+ rcu_trc_cmpxchg_need_qs(t, 0, TRC_NEED_QS_CHECKED);
goto reset_ipi;
}
// If we are racing with an rcu_read_unlock_trace(), try again later.
- if (unlikely(READ_ONCE(t->trc_reader_nesting) < 0))
+ if (unlikely(nesting < 0))
goto reset_ipi;
- WRITE_ONCE(t->trc_reader_checked, true);
- // Get here if the task is in a read-side critical section. Set
- // its state so that it will awaken the grace-period kthread upon
- // exit from that critical section.
- atomic_inc(&trc_n_readers_need_end); // One more to wait on.
- WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs));
- WRITE_ONCE(t->trc_reader_special.b.need_qs, true);
+ // Get here if the task is in a read-side critical section.
+ // Set its state so that it will update state for the grace-period
+ // kthread upon exit from that critical section.
+ rcu_trc_cmpxchg_need_qs(t, 0, TRC_NEED_QS | TRC_NEED_QS_CHECKED);
reset_ipi:
// Allow future IPIs to be sent on CPU and for task.
@@ -1264,48 +1345,50 @@ reset_ipi:
}
/* Callback function for scheduler to check locked-down task. */
-static int trc_inspect_reader(struct task_struct *t, void *arg)
+static int trc_inspect_reader(struct task_struct *t, void *bhp_in)
{
+ struct list_head *bhp = bhp_in;
int cpu = task_cpu(t);
int nesting;
bool ofl = cpu_is_offline(cpu);
- if (task_curr(t)) {
- WARN_ON_ONCE(ofl && !is_idle_task(t));
-
+ if (task_curr(t) && !ofl) {
// If no chance of heavyweight readers, do it the hard way.
- if (!ofl && !IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
+ if (!IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
return -EINVAL;
// If heavyweight readers are enabled on the remote task,
// we can inspect its state despite its currently running.
// However, we cannot safely change its state.
n_heavy_reader_attempts++;
- if (!ofl && // Check for "running" idle tasks on offline CPUs.
- !rcu_dynticks_zero_in_eqs(cpu, &t->trc_reader_nesting))
+ // Check for "running" idle tasks on offline CPUs.
+ if (!rcu_dynticks_zero_in_eqs(cpu, &t->trc_reader_nesting))
return -EINVAL; // No quiescent state, do it the hard way.
n_heavy_reader_updates++;
- if (ofl)
- n_heavy_reader_ofl_updates++;
nesting = 0;
} else {
// The task is not running, so C-language access is safe.
nesting = t->trc_reader_nesting;
+ WARN_ON_ONCE(ofl && task_curr(t) && !is_idle_task(t));
+ if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) && ofl)
+ n_heavy_reader_ofl_updates++;
}
// If not exiting a read-side critical section, mark as checked
// so that the grace-period kthread will remove it from the
// holdout list.
- t->trc_reader_checked = nesting >= 0;
- if (nesting <= 0)
- return nesting ? -EINVAL : 0; // If in QS, done, otherwise try again later.
+ if (!nesting) {
+ rcu_trc_cmpxchg_need_qs(t, 0, TRC_NEED_QS_CHECKED);
+ return 0; // In QS, so done.
+ }
+ if (nesting < 0)
+ return -EINVAL; // Reader transitioning, try again later.
// The task is in a read-side critical section, so set up its
- // state so that it will awaken the grace-period kthread upon exit
- // from that critical section.
- atomic_inc(&trc_n_readers_need_end); // One more to wait on.
- WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs));
- WRITE_ONCE(t->trc_reader_special.b.need_qs, true);
+ // state so that it will update state upon exit from that critical
+ // section.
+ if (!rcu_trc_cmpxchg_need_qs(t, 0, TRC_NEED_QS | TRC_NEED_QS_CHECKED))
+ trc_add_holdout(t, bhp);
return 0;
}
@@ -1321,14 +1404,14 @@ static void trc_wait_for_one_reader(struct task_struct *t,
// The current task had better be in a quiescent state.
if (t == current) {
- t->trc_reader_checked = true;
+ rcu_trc_cmpxchg_need_qs(t, 0, TRC_NEED_QS_CHECKED);
WARN_ON_ONCE(READ_ONCE(t->trc_reader_nesting));
return;
}
// Attempt to nail down the task for inspection.
get_task_struct(t);
- if (!task_call_func(t, trc_inspect_reader, NULL)) {
+ if (!task_call_func(t, trc_inspect_reader, bhp)) {
put_task_struct(t);
return;
}
@@ -1366,56 +1449,93 @@ static void trc_wait_for_one_reader(struct task_struct *t,
}
}
+/*
+ * Initialize for first-round processing for the specified task.
+ * Return false if task is NULL or already taken care of, true otherwise.
+ */
+static bool rcu_tasks_trace_pertask_prep(struct task_struct *t, bool notself)
+{
+ // During early boot when there is only the one boot CPU, there
+ // is no idle task for the other CPUs. Also, the grace-period
+ // kthread is always in a quiescent state. In addition, just return
+ // if this task is already on the list.
+ if (unlikely(t == NULL) || (t == current && notself) || !list_empty(&t->trc_holdout_list))
+ return false;
+
+ rcu_st_need_qs(t, 0);
+ t->trc_ipi_to_cpu = -1;
+ return true;
+}
+
+/* Do first-round processing for the specified task. */
+static void rcu_tasks_trace_pertask(struct task_struct *t, struct list_head *hop)
+{
+ if (rcu_tasks_trace_pertask_prep(t, true))
+ trc_wait_for_one_reader(t, hop);
+}
+
/* Initialize for a new RCU-tasks-trace grace period. */
-static void rcu_tasks_trace_pregp_step(void)
+static void rcu_tasks_trace_pregp_step(struct list_head *hop)
{
+ LIST_HEAD(blkd_tasks);
int cpu;
-
- // Allow for fast-acting IPIs.
- atomic_set(&trc_n_readers_need_end, 1);
+ unsigned long flags;
+ struct rcu_tasks_percpu *rtpcp;
+ struct task_struct *t;
// There shouldn't be any old IPIs, but...
for_each_possible_cpu(cpu)
WARN_ON_ONCE(per_cpu(trc_ipi_to_cpu, cpu));
- // Disable CPU hotplug across the tasklist scan.
- // This also waits for all readers in CPU-hotplug code paths.
+ // Disable CPU hotplug across the CPU scan for the benefit of
+ // any IPIs that might be needed. This also waits for all readers
+ // in CPU-hotplug code paths.
cpus_read_lock();
-}
-/* Do first-round processing for the specified task. */
-static void rcu_tasks_trace_pertask(struct task_struct *t,
- struct list_head *hop)
-{
- // During early boot when there is only the one boot CPU, there
- // is no idle task for the other CPUs. Just return.
- if (unlikely(t == NULL))
- return;
+ // These rcu_tasks_trace_pertask_prep() calls are serialized to
+ // allow safe access to the hop list.
+ for_each_online_cpu(cpu) {
+ rcu_read_lock();
+ t = cpu_curr_snapshot(cpu);
+ if (rcu_tasks_trace_pertask_prep(t, true))
+ trc_add_holdout(t, hop);
+ rcu_read_unlock();
+ }
- WRITE_ONCE(t->trc_reader_special.b.need_qs, false);
- WRITE_ONCE(t->trc_reader_checked, false);
- t->trc_ipi_to_cpu = -1;
- trc_wait_for_one_reader(t, hop);
+ // Only after all running tasks have been accounted for is it
+ // safe to take care of the tasks that have blocked within their
+ // current RCU tasks trace read-side critical section.
+ for_each_possible_cpu(cpu) {
+ rtpcp = per_cpu_ptr(rcu_tasks_trace.rtpcpu, cpu);
+ raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
+ list_splice_init(&rtpcp->rtp_blkd_tasks, &blkd_tasks);
+ while (!list_empty(&blkd_tasks)) {
+ rcu_read_lock();
+ t = list_first_entry(&blkd_tasks, struct task_struct, trc_blkd_node);
+ list_del_init(&t->trc_blkd_node);
+ list_add(&t->trc_blkd_node, &rtpcp->rtp_blkd_tasks);
+ raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
+ rcu_tasks_trace_pertask(t, hop);
+ rcu_read_unlock();
+ raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
+ }
+ raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
+ }
+
+ // Re-enable CPU hotplug now that the holdout list is populated.
+ cpus_read_unlock();
}
/*
- * Do intermediate processing between task and holdout scans and
- * pick up the idle tasks.
+ * Do intermediate processing between task and holdout scans.
*/
static void rcu_tasks_trace_postscan(struct list_head *hop)
{
- int cpu;
-
- for_each_possible_cpu(cpu)
- rcu_tasks_trace_pertask(idle_task(cpu), hop);
-
- // Re-enable CPU hotplug now that the tasklist scan has completed.
- cpus_read_unlock();
-
// Wait for late-stage exiting tasks to finish exiting.
// These might have passed the call to exit_tasks_rcu_finish().
synchronize_rcu();
- // Any tasks that exit after this point will set ->trc_reader_checked.
+ // Any tasks that exit after this point will set
+ // TRC_NEED_QS_CHECKED in ->trc_reader_special.b.need_qs.
}
/* Communicate task state back to the RCU tasks trace stall warning request. */
@@ -1429,11 +1549,11 @@ static int trc_check_slow_task(struct task_struct *t, void *arg)
{
struct trc_stall_chk_rdr *trc_rdrp = arg;
- if (task_curr(t))
+ if (task_curr(t) && cpu_online(task_cpu(t)))
return false; // It is running, so decline to inspect it.
trc_rdrp->nesting = READ_ONCE(t->trc_reader_nesting);
trc_rdrp->ipi_to_cpu = READ_ONCE(t->trc_ipi_to_cpu);
- trc_rdrp->needqs = READ_ONCE(t->trc_reader_special.b.need_qs);
+ trc_rdrp->needqs = rcu_ld_need_qs(t);
return true;
}
@@ -1450,18 +1570,21 @@ static void show_stalled_task_trace(struct task_struct *t, bool *firstreport)
}
cpu = task_cpu(t);
if (!task_call_func(t, trc_check_slow_task, &trc_rdr))
- pr_alert("P%d: %c\n",
+ pr_alert("P%d: %c%c\n",
t->pid,
+ ".I"[t->trc_ipi_to_cpu >= 0],
".i"[is_idle_tsk]);
else
- pr_alert("P%d: %c%c%c nesting: %d%c cpu: %d\n",
+ pr_alert("P%d: %c%c%c%c nesting: %d%c%c cpu: %d%s\n",
t->pid,
".I"[trc_rdr.ipi_to_cpu >= 0],
".i"[is_idle_tsk],
".N"[cpu >= 0 && tick_nohz_full_cpu(cpu)],
+ ".B"[!!data_race(t->trc_reader_special.b.blocked)],
trc_rdr.nesting,
- " N"[!!trc_rdr.needqs],
- cpu);
+ " !CN"[trc_rdr.needqs & 0x3],
+ " ?"[trc_rdr.needqs > 0x3],
+ cpu, cpu_online(cpu) ? "" : "(offline)");
sched_show_task(t);
}
@@ -1481,18 +1604,18 @@ static void check_all_holdout_tasks_trace(struct list_head *hop,
{
struct task_struct *g, *t;
- // Disable CPU hotplug across the holdout list scan.
+ // Disable CPU hotplug across the holdout list scan for IPIs.
cpus_read_lock();
list_for_each_entry_safe(t, g, hop, trc_holdout_list) {
// If safe and needed, try to check the current task.
if (READ_ONCE(t->trc_ipi_to_cpu) == -1 &&
- !READ_ONCE(t->trc_reader_checked))
+ !(rcu_ld_need_qs(t) & TRC_NEED_QS_CHECKED))
trc_wait_for_one_reader(t, hop);
// If check succeeded, remove this task from the list.
if (smp_load_acquire(&t->trc_ipi_to_cpu) == -1 &&
- READ_ONCE(t->trc_reader_checked))
+ rcu_ld_need_qs(t) == TRC_NEED_QS_CHECKED)
trc_del_holdout(t);
else if (needreport)
show_stalled_task_trace(t, firstreport);
@@ -1516,10 +1639,6 @@ static void rcu_tasks_trace_empty_fn(void *unused)
static void rcu_tasks_trace_postgp(struct rcu_tasks *rtp)
{
int cpu;
- bool firstreport;
- struct task_struct *g, *t;
- LIST_HEAD(holdouts);
- long ret;
// Wait for any lingering IPI handlers to complete. Note that
// if a CPU has gone offline or transitioned to userspace in the
@@ -1530,37 +1649,6 @@ static void rcu_tasks_trace_postgp(struct rcu_tasks *rtp)
if (WARN_ON_ONCE(smp_load_acquire(per_cpu_ptr(&trc_ipi_to_cpu, cpu))))
smp_call_function_single(cpu, rcu_tasks_trace_empty_fn, NULL, 1);
- // Remove the safety count.
- smp_mb__before_atomic(); // Order vs. earlier atomics
- atomic_dec(&trc_n_readers_need_end);
- smp_mb__after_atomic(); // Order vs. later atomics
-
- // Wait for readers.
- set_tasks_gp_state(rtp, RTGS_WAIT_READERS);
- for (;;) {
- ret = wait_event_idle_exclusive_timeout(
- trc_wait,
- atomic_read(&trc_n_readers_need_end) == 0,
- READ_ONCE(rcu_task_stall_timeout));
- if (ret)
- break; // Count reached zero.
- // Stall warning time, so make a list of the offenders.
- rcu_read_lock();
- for_each_process_thread(g, t)
- if (READ_ONCE(t->trc_reader_special.b.need_qs))
- trc_add_holdout(t, &holdouts);
- rcu_read_unlock();
- firstreport = true;
- list_for_each_entry_safe(t, g, &holdouts, trc_holdout_list) {
- if (READ_ONCE(t->trc_reader_special.b.need_qs))
- show_stalled_task_trace(t, &firstreport);
- trc_del_holdout(t); // Release task_struct reference.
- }
- if (firstreport)
- pr_err("INFO: rcu_tasks_trace detected stalls? (Counter/taskslist mismatch?)\n");
- show_stalled_ipi_trace();
- pr_err("\t%d holdouts\n", atomic_read(&trc_n_readers_need_end));
- }
smp_mb(); // Caller's code must be ordered after wakeup.
// Pairs with pretty much every ordering primitive.
}
@@ -1568,11 +1656,14 @@ static void rcu_tasks_trace_postgp(struct rcu_tasks *rtp)
/* Report any needed quiescent state for this exiting task. */
static void exit_tasks_rcu_finish_trace(struct task_struct *t)
{
- WRITE_ONCE(t->trc_reader_checked, true);
+ union rcu_special trs = READ_ONCE(t->trc_reader_special);
+
+ rcu_trc_cmpxchg_need_qs(t, 0, TRC_NEED_QS_CHECKED);
WARN_ON_ONCE(READ_ONCE(t->trc_reader_nesting));
- WRITE_ONCE(t->trc_reader_nesting, 0);
- if (WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs)))
+ if (WARN_ON_ONCE(rcu_ld_need_qs(t) & TRC_NEED_QS || trs.b.blocked))
rcu_read_unlock_trace_special(t);
+ else
+ WRITE_ONCE(t->trc_reader_nesting, 0);
}
/**
@@ -1646,7 +1737,6 @@ static int __init rcu_spawn_tasks_trace_kthread(void)
rcu_tasks_trace.init_fract = 1;
}
rcu_tasks_trace.pregp_func = rcu_tasks_trace_pregp_step;
- rcu_tasks_trace.pertask_func = rcu_tasks_trace_pertask;
rcu_tasks_trace.postscan_func = rcu_tasks_trace_postscan;
rcu_tasks_trace.holdouts_func = check_all_holdout_tasks_trace;
rcu_tasks_trace.postgp_func = rcu_tasks_trace_postgp;
@@ -1659,7 +1749,8 @@ void show_rcu_tasks_trace_gp_kthread(void)
{
char buf[64];
- sprintf(buf, "N%d h:%lu/%lu/%lu", atomic_read(&trc_n_readers_need_end),
+ sprintf(buf, "N%lu h:%lu/%lu/%lu",
+ data_race(n_trc_holdouts),
data_race(n_heavy_reader_ofl_updates),
data_race(n_heavy_reader_updates),
data_race(n_heavy_reader_attempts));
@@ -1686,23 +1777,24 @@ struct rcu_tasks_test_desc {
struct rcu_head rh;
const char *name;
bool notrun;
+ unsigned long runstart;
};
static struct rcu_tasks_test_desc tests[] = {
{
.name = "call_rcu_tasks()",
/* If not defined, the test is skipped. */
- .notrun = !IS_ENABLED(CONFIG_TASKS_RCU),
+ .notrun = IS_ENABLED(CONFIG_TASKS_RCU),
},
{
.name = "call_rcu_tasks_rude()",
/* If not defined, the test is skipped. */
- .notrun = !IS_ENABLED(CONFIG_TASKS_RUDE_RCU),
+ .notrun = IS_ENABLED(CONFIG_TASKS_RUDE_RCU),
},
{
.name = "call_rcu_tasks_trace()",
/* If not defined, the test is skipped. */
- .notrun = !IS_ENABLED(CONFIG_TASKS_TRACE_RCU)
+ .notrun = IS_ENABLED(CONFIG_TASKS_TRACE_RCU)
}
};
@@ -1713,46 +1805,85 @@ static void test_rcu_tasks_callback(struct rcu_head *rhp)
pr_info("Callback from %s invoked.\n", rttd->name);
- rttd->notrun = true;
+ rttd->notrun = false;
}
static void rcu_tasks_initiate_self_tests(void)
{
+ unsigned long j = jiffies;
+
pr_info("Running RCU-tasks wait API self tests\n");
#ifdef CONFIG_TASKS_RCU
+ tests[0].runstart = j;
synchronize_rcu_tasks();
call_rcu_tasks(&tests[0].rh, test_rcu_tasks_callback);
#endif
#ifdef CONFIG_TASKS_RUDE_RCU
+ tests[1].runstart = j;
synchronize_rcu_tasks_rude();
call_rcu_tasks_rude(&tests[1].rh, test_rcu_tasks_callback);
#endif
#ifdef CONFIG_TASKS_TRACE_RCU
+ tests[2].runstart = j;
synchronize_rcu_tasks_trace();
call_rcu_tasks_trace(&tests[2].rh, test_rcu_tasks_callback);
#endif
}
+/*
+ * Return: 0 - test passed
+ * 1 - test failed, but have not timed out yet
+ * -1 - test failed and timed out
+ */
static int rcu_tasks_verify_self_tests(void)
{
int ret = 0;
int i;
+ unsigned long bst = rcu_task_stall_timeout;
+ if (bst <= 0 || bst > RCU_TASK_BOOT_STALL_TIMEOUT)
+ bst = RCU_TASK_BOOT_STALL_TIMEOUT;
for (i = 0; i < ARRAY_SIZE(tests); i++) {
- if (!tests[i].notrun) { // still hanging.
- pr_err("%s has been failed.\n", tests[i].name);
- ret = -1;
+ while (tests[i].notrun) { // still hanging.
+ if (time_after(jiffies, tests[i].runstart + bst)) {
+ pr_err("%s has failed boot-time tests.\n", tests[i].name);
+ ret = -1;
+ break;
+ }
+ ret = 1;
+ break;
}
}
-
- if (ret)
- WARN_ON(1);
+ WARN_ON(ret < 0);
return ret;
}
-late_initcall(rcu_tasks_verify_self_tests);
+
+/*
+ * Repeat the rcu_tasks_verify_self_tests() call once every second until the
+ * test passes or has timed out.
+ */
+static struct delayed_work rcu_tasks_verify_work;
+static void rcu_tasks_verify_work_fn(struct work_struct *work __maybe_unused)
+{
+ int ret = rcu_tasks_verify_self_tests();
+
+ if (ret <= 0)
+ return;
+
+ /* Test fails but not timed out yet, reschedule another check */
+ schedule_delayed_work(&rcu_tasks_verify_work, HZ);
+}
+
+static int rcu_tasks_verify_schedule_work(void)
+{
+ INIT_DELAYED_WORK(&rcu_tasks_verify_work, rcu_tasks_verify_work_fn);
+ rcu_tasks_verify_work_fn(NULL);
+ return 0;
+}
+late_initcall(rcu_tasks_verify_schedule_work);
#else /* #ifdef CONFIG_PROVE_RCU */
static void rcu_tasks_initiate_self_tests(void) { }
#endif /* #else #ifdef CONFIG_PROVE_RCU */
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 340b3f8b090d..f0561ee16b9c 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -58,7 +58,7 @@ void rcu_qs(void)
rcu_ctrlblk.donetail = rcu_ctrlblk.curtail;
raise_softirq_irqoff(RCU_SOFTIRQ);
}
- WRITE_ONCE(rcu_ctrlblk.gp_seq, rcu_ctrlblk.gp_seq + 1);
+ WRITE_ONCE(rcu_ctrlblk.gp_seq, rcu_ctrlblk.gp_seq + 2);
local_irq_restore(flags);
}
@@ -139,8 +139,10 @@ static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused
/*
* Wait for a grace period to elapse. But it is illegal to invoke
* synchronize_rcu() from within an RCU read-side critical section.
- * Therefore, any legal call to synchronize_rcu() is a quiescent
- * state, and so on a UP system, synchronize_rcu() need do nothing.
+ * Therefore, any legal call to synchronize_rcu() is a quiescent state,
+ * and so on a UP system, synchronize_rcu() need do nothing, other than
+ * let the polled APIs know that another grace period elapsed.
+ *
* (But Lai Jiangshan points out the benefits of doing might_sleep()
* to reduce latency.)
*
@@ -152,6 +154,7 @@ void synchronize_rcu(void)
lock_is_held(&rcu_lock_map) ||
lock_is_held(&rcu_sched_lock_map),
"Illegal synchronize_rcu() in RCU read-side critical section");
+ WRITE_ONCE(rcu_ctrlblk.gp_seq, rcu_ctrlblk.gp_seq + 2);
}
EXPORT_SYMBOL_GPL(synchronize_rcu);
@@ -213,10 +216,24 @@ EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu);
*/
bool poll_state_synchronize_rcu(unsigned long oldstate)
{
- return READ_ONCE(rcu_ctrlblk.gp_seq) != oldstate;
+ return oldstate == RCU_GET_STATE_COMPLETED || READ_ONCE(rcu_ctrlblk.gp_seq) != oldstate;
}
EXPORT_SYMBOL_GPL(poll_state_synchronize_rcu);
+#ifdef CONFIG_KASAN_GENERIC
+void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
+{
+ if (head) {
+ void *ptr = (void *) head - (unsigned long) func;
+
+ kasan_record_aux_stack_noalloc(ptr);
+ }
+
+ __kvfree_call_rcu(head, func);
+}
+EXPORT_SYMBOL_GPL(kvfree_call_rcu);
+#endif
+
void __init rcu_init(void)
{
open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index c25ba442044a..3dc968006ad0 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -62,6 +62,7 @@
#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/kasan.h>
+#include <linux/context_tracking.h>
#include "../time/tick-internal.h"
#include "tree.h"
@@ -75,9 +76,6 @@
/* Data structures. */
static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = {
- .dynticks_nesting = 1,
- .dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE,
- .dynticks = ATOMIC_INIT(1),
#ifdef CONFIG_RCU_NOCB_CPU
.cblist.flags = SEGCBLIST_RCU_CORE,
#endif
@@ -154,7 +152,11 @@ static void sync_sched_exp_online_cleanup(int cpu);
static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp);
static bool rcu_rdp_is_offloaded(struct rcu_data *rdp);
-/* rcuc/rcub/rcuop kthread realtime priority */
+/*
+ * rcuc/rcub/rcuop kthread realtime priority. The "rcuop"
+ * real-time priority(enabling/disabling) is controlled by
+ * the extra CONFIG_RCU_NOCB_CPU_CB_BOOST configuration.
+ */
static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0;
module_param(kthread_prio, int, 0444);
@@ -263,56 +265,6 @@ void rcu_softirq_qs(void)
}
/*
- * Increment the current CPU's rcu_data structure's ->dynticks field
- * with ordering. Return the new value.
- */
-static noinline noinstr unsigned long rcu_dynticks_inc(int incby)
-{
- return arch_atomic_add_return(incby, this_cpu_ptr(&rcu_data.dynticks));
-}
-
-/*
- * Record entry into an extended quiescent state. This is only to be
- * called when not already in an extended quiescent state, that is,
- * RCU is watching prior to the call to this function and is no longer
- * watching upon return.
- */
-static noinstr void rcu_dynticks_eqs_enter(void)
-{
- int seq;
-
- /*
- * CPUs seeing atomic_add_return() must see prior RCU read-side
- * critical sections, and we also must force ordering with the
- * next idle sojourn.
- */
- rcu_dynticks_task_trace_enter(); // Before ->dynticks update!
- seq = rcu_dynticks_inc(1);
- // RCU is no longer watching. Better be in extended quiescent state!
- WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && (seq & 0x1));
-}
-
-/*
- * Record exit from an extended quiescent state. This is only to be
- * called from an extended quiescent state, that is, RCU is not watching
- * prior to the call to this function and is watching upon return.
- */
-static noinstr void rcu_dynticks_eqs_exit(void)
-{
- int seq;
-
- /*
- * CPUs seeing atomic_add_return() must see prior idle sojourns,
- * and we also must force ordering with the next RCU read-side
- * critical section.
- */
- seq = rcu_dynticks_inc(1);
- // RCU is now watching. Better not be in an extended quiescent state!
- rcu_dynticks_task_trace_exit(); // After ->dynticks update!
- WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(seq & 0x1));
-}
-
-/*
* Reset the current CPU's ->dynticks counter to indicate that the
* newly onlined CPU is no longer in an extended quiescent state.
* This will either leave the counter unchanged, or increment it
@@ -324,31 +276,19 @@ static noinstr void rcu_dynticks_eqs_exit(void)
*/
static void rcu_dynticks_eqs_online(void)
{
- struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
-
- if (atomic_read(&rdp->dynticks) & 0x1)
+ if (ct_dynticks() & RCU_DYNTICKS_IDX)
return;
- rcu_dynticks_inc(1);
-}
-
-/*
- * Is the current CPU in an extended quiescent state?
- *
- * No ordering, as we are sampling CPU-local information.
- */
-static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void)
-{
- return !(arch_atomic_read(this_cpu_ptr(&rcu_data.dynticks)) & 0x1);
+ ct_state_inc(RCU_DYNTICKS_IDX);
}
/*
* Snapshot the ->dynticks counter with full ordering so as to allow
* stable comparison of this counter with past and future snapshots.
*/
-static int rcu_dynticks_snap(struct rcu_data *rdp)
+static int rcu_dynticks_snap(int cpu)
{
smp_mb(); // Fundamental RCU ordering guarantee.
- return atomic_read_acquire(&rdp->dynticks);
+ return ct_dynticks_cpu_acquire(cpu);
}
/*
@@ -357,15 +297,13 @@ static int rcu_dynticks_snap(struct rcu_data *rdp)
*/
static bool rcu_dynticks_in_eqs(int snap)
{
- return !(snap & 0x1);
+ return !(snap & RCU_DYNTICKS_IDX);
}
/* Return true if the specified CPU is currently idle from an RCU viewpoint. */
bool rcu_is_idle_cpu(int cpu)
{
- struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
-
- return rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp));
+ return rcu_dynticks_in_eqs(rcu_dynticks_snap(cpu));
}
/*
@@ -375,7 +313,7 @@ bool rcu_is_idle_cpu(int cpu)
*/
static bool rcu_dynticks_in_eqs_since(struct rcu_data *rdp, int snap)
{
- return snap != rcu_dynticks_snap(rdp);
+ return snap != rcu_dynticks_snap(rdp->cpu);
}
/*
@@ -384,19 +322,17 @@ static bool rcu_dynticks_in_eqs_since(struct rcu_data *rdp, int snap)
*/
bool rcu_dynticks_zero_in_eqs(int cpu, int *vp)
{
- struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
int snap;
// If not quiescent, force back to earlier extended quiescent state.
- snap = atomic_read(&rdp->dynticks) & ~0x1;
-
+ snap = ct_dynticks_cpu(cpu) & ~RCU_DYNTICKS_IDX;
smp_rmb(); // Order ->dynticks and *vp reads.
if (READ_ONCE(*vp))
return false; // Non-zero, so report failure;
smp_rmb(); // Order *vp read and ->dynticks re-read.
// If still in the same extended quiescent state, we are good!
- return snap == atomic_read(&rdp->dynticks);
+ return snap == ct_dynticks_cpu(cpu);
}
/*
@@ -415,9 +351,9 @@ notrace void rcu_momentary_dyntick_idle(void)
int seq;
raw_cpu_write(rcu_data.rcu_need_heavy_qs, false);
- seq = rcu_dynticks_inc(2);
+ seq = ct_state_inc(2 * RCU_DYNTICKS_IDX);
/* It is illegal to call this from idle state. */
- WARN_ON_ONCE(!(seq & 0x1));
+ WARN_ON_ONCE(!(seq & RCU_DYNTICKS_IDX));
rcu_preempt_deferred_qs(current);
}
EXPORT_SYMBOL_GPL(rcu_momentary_dyntick_idle);
@@ -442,13 +378,13 @@ static int rcu_is_cpu_rrupt_from_idle(void)
lockdep_assert_irqs_disabled();
/* Check for counter underflows */
- RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nesting) < 0,
+ RCU_LOCKDEP_WARN(ct_dynticks_nesting() < 0,
"RCU dynticks_nesting counter underflow!");
- RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nmi_nesting) <= 0,
+ RCU_LOCKDEP_WARN(ct_dynticks_nmi_nesting() <= 0,
"RCU dynticks_nmi_nesting counter underflow/zero!");
/* Are we at first interrupt nesting level? */
- nesting = __this_cpu_read(rcu_data.dynticks_nmi_nesting);
+ nesting = ct_dynticks_nmi_nesting();
if (nesting > 1)
return false;
@@ -458,7 +394,7 @@ static int rcu_is_cpu_rrupt_from_idle(void)
WARN_ON_ONCE(!nesting && !is_idle_task(current));
/* Does CPU appear to be idle from an RCU standpoint? */
- return __this_cpu_read(rcu_data.dynticks_nesting) == 0;
+ return ct_dynticks_nesting() == 0;
}
#define DEFAULT_RCU_BLIMIT (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ? 1000 : 10)
@@ -609,66 +545,7 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
}
EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
-/*
- * Enter an RCU extended quiescent state, which can be either the
- * idle loop or adaptive-tickless usermode execution.
- *
- * We crowbar the ->dynticks_nmi_nesting field to zero to allow for
- * the possibility of usermode upcalls having messed up our count
- * of interrupt nesting level during the prior busy period.
- */
-static noinstr void rcu_eqs_enter(bool user)
-{
- struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
-
- WARN_ON_ONCE(rdp->dynticks_nmi_nesting != DYNTICK_IRQ_NONIDLE);
- WRITE_ONCE(rdp->dynticks_nmi_nesting, 0);
- WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
- rdp->dynticks_nesting == 0);
- if (rdp->dynticks_nesting != 1) {
- // RCU will still be watching, so just do accounting and leave.
- rdp->dynticks_nesting--;
- return;
- }
-
- lockdep_assert_irqs_disabled();
- instrumentation_begin();
- trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, atomic_read(&rdp->dynticks));
- WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
- rcu_preempt_deferred_qs(current);
-
- // instrumentation for the noinstr rcu_dynticks_eqs_enter()
- instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
-
- instrumentation_end();
- WRITE_ONCE(rdp->dynticks_nesting, 0); /* Avoid irq-access tearing. */
- // RCU is watching here ...
- rcu_dynticks_eqs_enter();
- // ... but is no longer watching here.
- rcu_dynticks_task_enter();
-}
-
-/**
- * rcu_idle_enter - inform RCU that current CPU is entering idle
- *
- * Enter idle mode, in other words, -leave- the mode in which RCU
- * read-side critical sections can occur. (Though RCU read-side
- * critical sections can occur in irq handlers in idle, a possibility
- * handled by irq_enter() and irq_exit().)
- *
- * If you add or remove a call to rcu_idle_enter(), be sure to test with
- * CONFIG_RCU_EQS_DEBUG=y.
- */
-void rcu_idle_enter(void)
-{
- lockdep_assert_irqs_disabled();
- rcu_eqs_enter(false);
-}
-EXPORT_SYMBOL_GPL(rcu_idle_enter);
-
-#ifdef CONFIG_NO_HZ_FULL
-
-#if !defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK)
+#if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK))
/*
* An empty function that will trigger a reschedule on
* IRQ tail once IRQs get re-enabled on userspace/guest resume.
@@ -690,7 +567,7 @@ static DEFINE_PER_CPU(struct irq_work, late_wakeup_work) =
* last resort is to fire a local irq_work that will trigger a reschedule once IRQs
* get re-enabled again.
*/
-noinstr static void rcu_irq_work_resched(void)
+noinstr void rcu_irq_work_resched(void)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
@@ -706,114 +583,7 @@ noinstr static void rcu_irq_work_resched(void)
}
instrumentation_end();
}
-
-#else
-static inline void rcu_irq_work_resched(void) { }
-#endif
-
-/**
- * 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.
- *
- * If you add or remove a call to rcu_user_enter(), be sure to test with
- * CONFIG_RCU_EQS_DEBUG=y.
- */
-noinstr void rcu_user_enter(void)
-{
- lockdep_assert_irqs_disabled();
-
- /*
- * Other than generic entry implementation, we may be past the last
- * rescheduling opportunity in the entry code. Trigger a self IPI
- * that will fire and reschedule once we resume in user/guest mode.
- */
- rcu_irq_work_resched();
- rcu_eqs_enter(true);
-}
-
-#endif /* CONFIG_NO_HZ_FULL */
-
-/**
- * rcu_nmi_exit - inform RCU of exit from NMI context
- *
- * If we are returning from the outermost NMI handler that interrupted an
- * RCU-idle period, update rdp->dynticks and rdp->dynticks_nmi_nesting
- * to let the RCU grace-period handling know that the CPU is back to
- * being RCU-idle.
- *
- * If you add or remove a call to rcu_nmi_exit(), be sure to test
- * with CONFIG_RCU_EQS_DEBUG=y.
- */
-noinstr void rcu_nmi_exit(void)
-{
- struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
-
- instrumentation_begin();
- /*
- * Check for ->dynticks_nmi_nesting underflow and bad ->dynticks.
- * (We are exiting an NMI handler, so RCU better be paying attention
- * to us!)
- */
- WARN_ON_ONCE(rdp->dynticks_nmi_nesting <= 0);
- WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs());
-
- /*
- * If the nesting level is not 1, the CPU wasn't RCU-idle, so
- * leave it in non-RCU-idle state.
- */
- if (rdp->dynticks_nmi_nesting != 1) {
- trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2,
- atomic_read(&rdp->dynticks));
- WRITE_ONCE(rdp->dynticks_nmi_nesting, /* No store tearing. */
- rdp->dynticks_nmi_nesting - 2);
- instrumentation_end();
- return;
- }
-
- /* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */
- trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks));
- WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */
-
- // instrumentation for the noinstr rcu_dynticks_eqs_enter()
- instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
- instrumentation_end();
-
- // RCU is watching here ...
- rcu_dynticks_eqs_enter();
- // ... but is no longer watching here.
-
- if (!in_nmi())
- rcu_dynticks_task_enter();
-}
-
-/**
- * rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle
- *
- * Exit from an interrupt handler, which might possibly result in entering
- * idle mode, in other words, leaving the mode in which read-side critical
- * sections can occur. The caller must have disabled interrupts.
- *
- * This code assumes that the idle loop never does anything that might
- * result in unbalanced calls to irq_enter() and irq_exit(). If your
- * architecture's idle loop violates this assumption, RCU will give you what
- * you deserve, good and hard. But very infrequently and irreproducibly.
- *
- * Use things like work queues to work around this limitation.
- *
- * You have been warned.
- *
- * If you add or remove a call to rcu_irq_exit(), be sure to test with
- * CONFIG_RCU_EQS_DEBUG=y.
- */
-void noinstr rcu_irq_exit(void)
-{
- lockdep_assert_irqs_disabled();
- rcu_nmi_exit();
-}
+#endif /* #if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK)) */
#ifdef CONFIG_PROVE_RCU
/**
@@ -823,9 +593,9 @@ void rcu_irq_exit_check_preempt(void)
{
lockdep_assert_irqs_disabled();
- RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nesting) <= 0,
+ RCU_LOCKDEP_WARN(ct_dynticks_nesting() <= 0,
"RCU dynticks_nesting counter underflow/zero!");
- RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nmi_nesting) !=
+ RCU_LOCKDEP_WARN(ct_dynticks_nmi_nesting() !=
DYNTICK_IRQ_NONIDLE,
"Bad RCU dynticks_nmi_nesting counter\n");
RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(),
@@ -833,95 +603,8 @@ void rcu_irq_exit_check_preempt(void)
}
#endif /* #ifdef CONFIG_PROVE_RCU */
-/*
- * Wrapper for rcu_irq_exit() where interrupts are enabled.
- *
- * If you add or remove a call to rcu_irq_exit_irqson(), be sure to test
- * with CONFIG_RCU_EQS_DEBUG=y.
- */
-void rcu_irq_exit_irqson(void)
-{
- unsigned long flags;
-
- local_irq_save(flags);
- rcu_irq_exit();
- local_irq_restore(flags);
-}
-
-/*
- * Exit an RCU extended quiescent state, which can be either the
- * idle loop or adaptive-tickless usermode execution.
- *
- * We crowbar the ->dynticks_nmi_nesting field to DYNTICK_IRQ_NONIDLE to
- * allow for the possibility of usermode upcalls messing up our count of
- * interrupt nesting level during the busy period that is just now starting.
- */
-static void noinstr rcu_eqs_exit(bool user)
-{
- struct rcu_data *rdp;
- long oldval;
-
- lockdep_assert_irqs_disabled();
- rdp = this_cpu_ptr(&rcu_data);
- oldval = rdp->dynticks_nesting;
- WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0);
- if (oldval) {
- // RCU was already watching, so just do accounting and leave.
- rdp->dynticks_nesting++;
- return;
- }
- rcu_dynticks_task_exit();
- // RCU is not watching here ...
- rcu_dynticks_eqs_exit();
- // ... but is watching here.
- instrumentation_begin();
-
- // instrumentation for the noinstr rcu_dynticks_eqs_exit()
- instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
-
- trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks));
- WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
- WRITE_ONCE(rdp->dynticks_nesting, 1);
- WARN_ON_ONCE(rdp->dynticks_nmi_nesting);
- WRITE_ONCE(rdp->dynticks_nmi_nesting, DYNTICK_IRQ_NONIDLE);
- instrumentation_end();
-}
-
-/**
- * rcu_idle_exit - inform RCU that current CPU is leaving idle
- *
- * Exit idle mode, in other words, -enter- the mode in which RCU
- * read-side critical sections can occur.
- *
- * If you add or remove a call to rcu_idle_exit(), be sure to test with
- * CONFIG_RCU_EQS_DEBUG=y.
- */
-void rcu_idle_exit(void)
-{
- unsigned long flags;
-
- local_irq_save(flags);
- rcu_eqs_exit(false);
- local_irq_restore(flags);
-}
-EXPORT_SYMBOL_GPL(rcu_idle_exit);
-
#ifdef CONFIG_NO_HZ_FULL
/**
- * 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.
- *
- * If you add or remove a call to rcu_user_exit(), be sure to test with
- * CONFIG_RCU_EQS_DEBUG=y.
- */
-void noinstr rcu_user_exit(void)
-{
- rcu_eqs_exit(true);
-}
-
-/**
* __rcu_irq_enter_check_tick - Enable scheduler tick on CPU if RCU needs it.
*
* The scheduler tick is not normally enabled when CPUs enter the kernel
@@ -983,109 +666,6 @@ void __rcu_irq_enter_check_tick(void)
}
#endif /* CONFIG_NO_HZ_FULL */
-/**
- * rcu_nmi_enter - inform RCU of entry to NMI context
- *
- * If the CPU was idle from RCU's viewpoint, update rdp->dynticks and
- * rdp->dynticks_nmi_nesting to let the RCU grace-period handling know
- * that the CPU is active. This implementation permits nested NMIs, as
- * long as the nesting level does not overflow an int. (You will probably
- * run out of stack space first.)
- *
- * If you add or remove a call to rcu_nmi_enter(), be sure to test
- * with CONFIG_RCU_EQS_DEBUG=y.
- */
-noinstr void rcu_nmi_enter(void)
-{
- long incby = 2;
- struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
-
- /* Complain about underflow. */
- WARN_ON_ONCE(rdp->dynticks_nmi_nesting < 0);
-
- /*
- * If idle from RCU viewpoint, atomically increment ->dynticks
- * to mark non-idle and increment ->dynticks_nmi_nesting by one.
- * Otherwise, increment ->dynticks_nmi_nesting by two. This means
- * if ->dynticks_nmi_nesting is equal to one, we are guaranteed
- * to be in the outermost NMI handler that interrupted an RCU-idle
- * period (observation due to Andy Lutomirski).
- */
- if (rcu_dynticks_curr_cpu_in_eqs()) {
-
- if (!in_nmi())
- rcu_dynticks_task_exit();
-
- // RCU is not watching here ...
- rcu_dynticks_eqs_exit();
- // ... but is watching here.
-
- instrumentation_begin();
- // instrumentation for the noinstr rcu_dynticks_curr_cpu_in_eqs()
- instrument_atomic_read(&rdp->dynticks, sizeof(rdp->dynticks));
- // instrumentation for the noinstr rcu_dynticks_eqs_exit()
- instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
-
- incby = 1;
- } else if (!in_nmi()) {
- instrumentation_begin();
- rcu_irq_enter_check_tick();
- } else {
- instrumentation_begin();
- }
-
- trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="),
- rdp->dynticks_nmi_nesting,
- rdp->dynticks_nmi_nesting + incby, atomic_read(&rdp->dynticks));
- instrumentation_end();
- WRITE_ONCE(rdp->dynticks_nmi_nesting, /* Prevent store tearing. */
- rdp->dynticks_nmi_nesting + incby);
- barrier();
-}
-
-/**
- * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle
- *
- * Enter an interrupt handler, which might possibly result in exiting
- * idle mode, in other words, entering the mode in which read-side critical
- * sections can occur. The caller must have disabled interrupts.
- *
- * Note that the Linux kernel is fully capable of entering an interrupt
- * handler that it never exits, for example when doing upcalls to user mode!
- * This code assumes that the idle loop never does upcalls to user mode.
- * If your architecture's idle loop does do upcalls to user mode (or does
- * anything else that results in unbalanced calls to the irq_enter() and
- * irq_exit() functions), RCU will give you what you deserve, good and hard.
- * But very infrequently and irreproducibly.
- *
- * Use things like work queues to work around this limitation.
- *
- * You have been warned.
- *
- * If you add or remove a call to rcu_irq_enter(), be sure to test with
- * CONFIG_RCU_EQS_DEBUG=y.
- */
-noinstr void rcu_irq_enter(void)
-{
- lockdep_assert_irqs_disabled();
- rcu_nmi_enter();
-}
-
-/*
- * Wrapper for rcu_irq_enter() where interrupts are enabled.
- *
- * If you add or remove a call to rcu_irq_enter_irqson(), be sure to test
- * with CONFIG_RCU_EQS_DEBUG=y.
- */
-void rcu_irq_enter_irqson(void)
-{
- unsigned long flags;
-
- local_irq_save(flags);
- rcu_irq_enter();
- local_irq_restore(flags);
-}
-
/*
* Check to see if any future non-offloaded RCU-related work will need
* to be done by the current CPU, even if none need be done immediately,
@@ -1223,7 +803,7 @@ static void rcu_gpnum_ovf(struct rcu_node *rnp, struct rcu_data *rdp)
*/
static int dyntick_save_progress_counter(struct rcu_data *rdp)
{
- rdp->dynticks_snap = rcu_dynticks_snap(rdp);
+ rdp->dynticks_snap = rcu_dynticks_snap(rdp->cpu);
if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) {
trace_rcu_fqs(rcu_state.name, rdp->gp_seq, rdp->cpu, TPS("dti"));
rcu_gpnum_ovf(rdp->mynode, rdp);
@@ -1775,6 +1355,79 @@ static void rcu_strict_gp_boundary(void *unused)
invoke_rcu_core();
}
+// Has rcu_init() been invoked? This is used (for example) to determine
+// whether spinlocks may be acquired safely.
+static bool rcu_init_invoked(void)
+{
+ return !!rcu_state.n_online_cpus;
+}
+
+// Make the polled API aware of the beginning of a grace period.
+static void rcu_poll_gp_seq_start(unsigned long *snap)
+{
+ struct rcu_node *rnp = rcu_get_root();
+
+ if (rcu_init_invoked())
+ raw_lockdep_assert_held_rcu_node(rnp);
+
+ // If RCU was idle, note beginning of GP.
+ if (!rcu_seq_state(rcu_state.gp_seq_polled))
+ rcu_seq_start(&rcu_state.gp_seq_polled);
+
+ // Either way, record current state.
+ *snap = rcu_state.gp_seq_polled;
+}
+
+// Make the polled API aware of the end of a grace period.
+static void rcu_poll_gp_seq_end(unsigned long *snap)
+{
+ struct rcu_node *rnp = rcu_get_root();
+
+ if (rcu_init_invoked())
+ raw_lockdep_assert_held_rcu_node(rnp);
+
+ // If the previously noted GP is still in effect, record the
+ // end of that GP. Either way, zero counter to avoid counter-wrap
+ // problems.
+ if (*snap && *snap == rcu_state.gp_seq_polled) {
+ rcu_seq_end(&rcu_state.gp_seq_polled);
+ rcu_state.gp_seq_polled_snap = 0;
+ rcu_state.gp_seq_polled_exp_snap = 0;
+ } else {
+ *snap = 0;
+ }
+}
+
+// Make the polled API aware of the beginning of a grace period, but
+// where caller does not hold the root rcu_node structure's lock.
+static void rcu_poll_gp_seq_start_unlocked(unsigned long *snap)
+{
+ struct rcu_node *rnp = rcu_get_root();
+
+ if (rcu_init_invoked()) {
+ lockdep_assert_irqs_enabled();
+ raw_spin_lock_irq_rcu_node(rnp);
+ }
+ rcu_poll_gp_seq_start(snap);
+ if (rcu_init_invoked())
+ raw_spin_unlock_irq_rcu_node(rnp);
+}
+
+// Make the polled API aware of the end of a grace period, but where
+// caller does not hold the root rcu_node structure's lock.
+static void rcu_poll_gp_seq_end_unlocked(unsigned long *snap)
+{
+ struct rcu_node *rnp = rcu_get_root();
+
+ if (rcu_init_invoked()) {
+ lockdep_assert_irqs_enabled();
+ raw_spin_lock_irq_rcu_node(rnp);
+ }
+ rcu_poll_gp_seq_end(snap);
+ if (rcu_init_invoked())
+ raw_spin_unlock_irq_rcu_node(rnp);
+}
+
/*
* Initialize a new grace period. Return false if no grace period required.
*/
@@ -1810,6 +1463,7 @@ static noinline_for_stack bool rcu_gp_init(void)
rcu_seq_start(&rcu_state.gp_seq);
ASSERT_EXCLUSIVE_WRITER(rcu_state.gp_seq);
trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("start"));
+ rcu_poll_gp_seq_start(&rcu_state.gp_seq_polled_snap);
raw_spin_unlock_irq_rcu_node(rnp);
/*
@@ -1971,19 +1625,23 @@ static void rcu_gp_fqs(bool first_time)
*/
static noinline_for_stack void rcu_gp_fqs_loop(void)
{
- bool first_gp_fqs;
+ bool first_gp_fqs = true;
int gf = 0;
unsigned long j;
int ret;
struct rcu_node *rnp = rcu_get_root();
- first_gp_fqs = true;
j = READ_ONCE(jiffies_till_first_fqs);
if (rcu_state.cbovld)
gf = RCU_GP_FLAG_OVLD;
ret = 0;
for (;;) {
- if (!ret) {
+ if (rcu_state.cbovld) {
+ j = (j + 2) / 3;
+ if (j <= 0)
+ j = 1;
+ }
+ if (!ret || time_before(jiffies + j, rcu_state.jiffies_force_qs)) {
WRITE_ONCE(rcu_state.jiffies_force_qs, jiffies + j);
/*
* jiffies_force_qs before RCU_GP_WAIT_FQS state
@@ -2001,7 +1659,15 @@ static noinline_for_stack void rcu_gp_fqs_loop(void)
rcu_gp_torture_wait();
WRITE_ONCE(rcu_state.gp_state, RCU_GP_DOING_FQS);
/* Locking provides needed memory barriers. */
- /* If grace period done, leave loop. */
+ /*
+ * Exit the loop if the root rcu_node structure indicates that the grace period
+ * has ended, leave the loop. The rcu_preempt_blocked_readers_cgp(rnp) check
+ * is required only for single-node rcu_node trees because readers blocking
+ * the current grace period are queued only on leaf rcu_node structures.
+ * For multi-node trees, checking the root node's ->qsmask suffices, because a
+ * given root node's ->qsmask bit is cleared only when all CPUs and tasks from
+ * the corresponding leaf nodes have passed through their quiescent state.
+ */
if (!READ_ONCE(rnp->qsmask) &&
!rcu_preempt_blocked_readers_cgp(rnp))
break;
@@ -2069,6 +1735,7 @@ static noinline void rcu_gp_cleanup(void)
* safe for us to drop the lock in order to mark the grace
* period as completed in all of the rcu_node structures.
*/
+ rcu_poll_gp_seq_end(&rcu_state.gp_seq_polled_snap);
raw_spin_unlock_irq_rcu_node(rnp);
/*
@@ -2530,7 +2197,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
trace_rcu_batch_end(rcu_state.name, 0,
!rcu_segcblist_empty(&rdp->cblist),
need_resched(), is_idle_task(current),
- rcu_is_callbacks_kthread());
+ rcu_is_callbacks_kthread(rdp));
return;
}
@@ -2608,7 +2275,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
rcu_nocb_lock_irqsave(rdp, flags);
rdp->n_cbs_invoked += count;
trace_rcu_batch_end(rcu_state.name, count, !!rcl.head, need_resched(),
- is_idle_task(current), rcu_is_callbacks_kthread());
+ is_idle_task(current), rcu_is_callbacks_kthread(rdp));
/* Update counts and requeue any remaining callbacks. */
rcu_segcblist_insert_done_cbs(&rdp->cblist, &rcl);
@@ -3211,7 +2878,6 @@ struct kfree_rcu_cpu_work {
* @krw_arr: Array of batches of kfree_rcu() objects waiting for a grace period
* @lock: Synchronize access to this structure
* @monitor_work: Promote @head to @head_free after KFREE_DRAIN_JIFFIES
- * @monitor_todo: Tracks whether a @monitor_work delayed work is pending
* @initialized: The @rcu_work fields have been initialized
* @count: Number of objects for which GP not started
* @bkvcache:
@@ -3236,7 +2902,6 @@ struct kfree_rcu_cpu {
struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES];
raw_spinlock_t lock;
struct delayed_work monitor_work;
- bool monitor_todo;
bool initialized;
int count;
@@ -3416,6 +3081,18 @@ static void kfree_rcu_work(struct work_struct *work)
}
}
+static bool
+need_offload_krc(struct kfree_rcu_cpu *krcp)
+{
+ int i;
+
+ for (i = 0; i < FREE_N_CHANNELS; i++)
+ if (krcp->bkvhead[i])
+ return true;
+
+ return !!krcp->head;
+}
+
/*
* This function is invoked after the KFREE_DRAIN_JIFFIES timeout.
*/
@@ -3472,9 +3149,7 @@ static void kfree_rcu_monitor(struct work_struct *work)
// of the channels that is still busy we should rearm the
// work to repeat an attempt. Because previous batches are
// still in progress.
- if (!krcp->bkvhead[0] && !krcp->bkvhead[1] && !krcp->head)
- krcp->monitor_todo = false;
- else
+ if (need_offload_krc(krcp))
schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES);
raw_spin_unlock_irqrestore(&krcp->lock, flags);
@@ -3662,11 +3337,8 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
WRITE_ONCE(krcp->count, krcp->count + 1);
// Set timer to drain after KFREE_DRAIN_JIFFIES.
- if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
- !krcp->monitor_todo) {
- krcp->monitor_todo = true;
+ if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING)
schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES);
- }
unlock_return:
krc_this_cpu_unlock(krcp, flags);
@@ -3741,14 +3413,8 @@ void __init kfree_rcu_scheduler_running(void)
struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
raw_spin_lock_irqsave(&krcp->lock, flags);
- if ((!krcp->bkvhead[0] && !krcp->bkvhead[1] && !krcp->head) ||
- krcp->monitor_todo) {
- raw_spin_unlock_irqrestore(&krcp->lock, flags);
- continue;
- }
- krcp->monitor_todo = true;
- schedule_delayed_work_on(cpu, &krcp->monitor_work,
- KFREE_DRAIN_JIFFIES);
+ if (need_offload_krc(krcp))
+ schedule_delayed_work_on(cpu, &krcp->monitor_work, KFREE_DRAIN_JIFFIES);
raw_spin_unlock_irqrestore(&krcp->lock, flags);
}
}
@@ -3837,8 +3503,18 @@ void synchronize_rcu(void)
lock_is_held(&rcu_lock_map) ||
lock_is_held(&rcu_sched_lock_map),
"Illegal synchronize_rcu() in RCU read-side critical section");
- if (rcu_blocking_is_gp())
+ if (rcu_blocking_is_gp()) {
+ // Note well that this code runs with !PREEMPT && !SMP.
+ // In addition, all code that advances grace periods runs at
+ // process level. Therefore, this normal GP overlaps with
+ // other normal GPs only by being fully nested within them,
+ // which allows reuse of ->gp_seq_polled_snap.
+ rcu_poll_gp_seq_start_unlocked(&rcu_state.gp_seq_polled_snap);
+ rcu_poll_gp_seq_end_unlocked(&rcu_state.gp_seq_polled_snap);
+ if (rcu_init_invoked())
+ cond_resched_tasks_rcu_qs();
return; // Context allows vacuous grace periods.
+ }
if (rcu_gp_is_expedited())
synchronize_rcu_expedited();
else
@@ -3860,7 +3536,7 @@ unsigned long get_state_synchronize_rcu(void)
* before the load from ->gp_seq.
*/
smp_mb(); /* ^^^ */
- return rcu_seq_snap(&rcu_state.gp_seq);
+ return rcu_seq_snap(&rcu_state.gp_seq_polled);
}
EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
@@ -3889,7 +3565,13 @@ unsigned long start_poll_synchronize_rcu(void)
rdp = this_cpu_ptr(&rcu_data);
rnp = rdp->mynode;
raw_spin_lock_rcu_node(rnp); // irqs already disabled.
- needwake = rcu_start_this_gp(rnp, rdp, gp_seq);
+ // Note it is possible for a grace period to have elapsed between
+ // the above call to get_state_synchronize_rcu() and the below call
+ // to rcu_seq_snap. This is OK, the worst that happens is that we
+ // get a grace period that no one needed. These accesses are ordered
+ // by smp_mb(), and we are accessing them in the opposite order
+ // from which they are updated at grace-period start, as required.
+ needwake = rcu_start_this_gp(rnp, rdp, rcu_seq_snap(&rcu_state.gp_seq));
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
if (needwake)
rcu_gp_kthread_wake();
@@ -3911,7 +3593,7 @@ EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu);
*
* Yes, this function does not take counter wrap into account.
* But counter wrap is harmless. If the counter wraps, we have waited for
- * more than 2 billion grace periods (and way more on a 64-bit system!).
+ * more than a billion grace periods (and way more on a 64-bit system!).
* Those needing to keep oldstate values for very long time periods
* (many hours even on 32-bit systems) should check them occasionally
* and either refresh them or set a flag indicating that the grace period
@@ -3924,7 +3606,8 @@ EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu);
*/
bool poll_state_synchronize_rcu(unsigned long oldstate)
{
- if (rcu_seq_done(&rcu_state.gp_seq, oldstate)) {
+ if (oldstate == RCU_GET_STATE_COMPLETED ||
+ rcu_seq_done_exact(&rcu_state.gp_seq_polled, oldstate)) {
smp_mb(); /* Ensure GP ends before subsequent accesses. */
return true;
}
@@ -3935,20 +3618,20 @@ EXPORT_SYMBOL_GPL(poll_state_synchronize_rcu);
/**
* cond_synchronize_rcu - Conditionally wait for an RCU grace period
*
- * @oldstate: value from get_state_synchronize_rcu() or start_poll_synchronize_rcu()
+ * @oldstate: value from get_state_synchronize_rcu(), start_poll_synchronize_rcu(), or start_poll_synchronize_rcu_expedited()
*
* If a full RCU grace period has elapsed since the earlier call to
* get_state_synchronize_rcu() or start_poll_synchronize_rcu(), just return.
* Otherwise, invoke synchronize_rcu() to wait for a full grace period.
*
- * Yes, this function does not take counter wrap into account. But
- * counter wrap is harmless. If the counter wraps, we have waited for
+ * Yes, this function does not take counter wrap into account.
+ * But counter wrap is harmless. If the counter wraps, we have waited for
* more than 2 billion grace periods (and way more on a 64-bit system!),
- * so waiting for one additional grace period should be just fine.
+ * so waiting for a couple of additional grace periods should be just fine.
*
* This function provides the same memory-ordering guarantees that
* would be provided by a synchronize_rcu() that was invoked at the call
- * to the function that provided @oldstate, and that returned at the end
+ * to the function that provided @oldstate and that returned at the end
* of this function.
*/
void cond_synchronize_rcu(unsigned long oldstate)
@@ -4221,13 +3904,14 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
static void __init
rcu_boot_init_percpu_data(int cpu)
{
+ struct context_tracking *ct = this_cpu_ptr(&context_tracking);
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
/* Set up local state, ensuring consistent view of global state. */
rdp->grpmask = leaf_node_cpu_bit(rdp->mynode, cpu);
INIT_WORK(&rdp->strict_work, strict_work_handler);
- WARN_ON_ONCE(rdp->dynticks_nesting != 1);
- WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp)));
+ WARN_ON_ONCE(ct->dynticks_nesting != 1);
+ WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(cpu)));
rdp->barrier_seq_snap = rcu_state.barrier_sequence;
rdp->rcu_ofl_gp_seq = rcu_state.gp_seq;
rdp->rcu_ofl_gp_flags = RCU_GP_CLEANED;
@@ -4251,6 +3935,7 @@ rcu_boot_init_percpu_data(int cpu)
int rcutree_prepare_cpu(unsigned int cpu)
{
unsigned long flags;
+ struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu);
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
struct rcu_node *rnp = rcu_get_root();
@@ -4259,7 +3944,7 @@ int rcutree_prepare_cpu(unsigned int cpu)
rdp->qlen_last_fqs_check = 0;
rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs);
rdp->blimit = blimit;
- rdp->dynticks_nesting = 1; /* CPU not up, no tearing. */
+ ct->dynticks_nesting = 1; /* CPU not up, no tearing. */
raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
/*
@@ -4441,6 +4126,7 @@ void rcu_report_dead(unsigned int cpu)
rdp->rcu_ofl_gp_flags = READ_ONCE(rcu_state.gp_flags);
if (rnp->qsmask & mask) { /* RCU waiting on outgoing CPU? */
/* Report quiescent state -before- changing ->qsmaskinitnext! */
+ rcu_disable_urgency_upon_qs(rdp);
rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
raw_spin_lock_irqsave_rcu_node(rnp, flags);
}
@@ -4486,6 +4172,7 @@ void rcutree_migrate_callbacks(int cpu)
needwake = needwake || rcu_advance_cbs(my_rnp, my_rdp);
rcu_segcblist_disable(&rdp->cblist);
WARN_ON_ONCE(rcu_segcblist_empty(&my_rdp->cblist) != !rcu_segcblist_n_cbs(&my_rdp->cblist));
+ check_cb_ovld_locked(my_rdp, my_rnp);
if (rcu_rdp_is_offloaded(my_rdp)) {
raw_spin_unlock_rcu_node(my_rnp); /* irqs remain disabled. */
__call_rcu_nocb_wake(my_rdp, true, flags);
@@ -4701,6 +4388,9 @@ static void __init rcu_init_one(void)
init_waitqueue_head(&rnp->exp_wq[3]);
spin_lock_init(&rnp->exp_lock);
mutex_init(&rnp->boost_kthread_mutex);
+ raw_spin_lock_init(&rnp->exp_poll_lock);
+ rnp->exp_seq_poll_rq = RCU_GET_STATE_COMPLETED;
+ INIT_WORK(&rnp->exp_poll_wq, sync_rcu_do_polled_gp);
}
}
@@ -4926,6 +4616,10 @@ void __init rcu_init(void)
qovld_calc = DEFAULT_RCU_QOVLD_MULT * qhimark;
else
qovld_calc = qovld;
+
+ // Kick-start any polled grace periods that started early.
+ if (!(per_cpu_ptr(&rcu_data, cpu)->mynode->exp_seq_poll_rq & 0x1))
+ (void)start_poll_synchronize_rcu_expedited();
}
#include "tree_stall.h"
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 2ccf5845957d..d4a97e40ea9c 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -133,6 +133,10 @@ struct rcu_node {
wait_queue_head_t exp_wq[4];
struct rcu_exp_work rew;
bool exp_need_flush; /* Need to flush workitem? */
+ raw_spinlock_t exp_poll_lock;
+ /* Lock and data for polled expedited grace periods. */
+ unsigned long exp_seq_poll_rq;
+ struct work_struct exp_poll_wq;
} ____cacheline_internodealigned_in_smp;
/*
@@ -187,9 +191,6 @@ struct rcu_data {
/* 3) dynticks interface. */
int dynticks_snap; /* Per-GP tracking for dynticks. */
- long dynticks_nesting; /* Track process nesting level. */
- long dynticks_nmi_nesting; /* Track irq/NMI nesting level. */
- atomic_t dynticks; /* Even value for idle, else odd. */
bool rcu_need_heavy_qs; /* GP old, so heavy quiescent state! */
bool rcu_urgent_qs; /* GP old need light quiescent state. */
bool rcu_forced_tick; /* Forced tick to provide QS. */
@@ -235,6 +236,7 @@ struct rcu_data {
* if rdp_gp.
*/
struct list_head nocb_entry_rdp; /* rcu_data node in wakeup chain. */
+ struct rcu_data *nocb_toggling_rdp; /* rdp queued for (de-)offloading */
/* The following fields are used by CB kthread, hence new cacheline. */
struct rcu_data *nocb_gp_rdp ____cacheline_internodealigned_in_smp;
@@ -323,6 +325,9 @@ struct rcu_state {
short gp_state; /* GP kthread sleep state. */
unsigned long gp_wake_time; /* Last GP kthread wake. */
unsigned long gp_wake_seq; /* ->gp_seq at ^^^. */
+ unsigned long gp_seq_polled; /* GP seq for polled API. */
+ unsigned long gp_seq_polled_snap; /* ->gp_seq_polled at normal GP start. */
+ unsigned long gp_seq_polled_exp_snap; /* ->gp_seq_polled at expedited GP start. */
/* End of fields guarded by root rcu_node's lock. */
@@ -425,12 +430,11 @@ static void rcu_flavor_sched_clock_irq(int user);
static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck);
static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
-static bool rcu_is_callbacks_kthread(void);
+static bool rcu_is_callbacks_kthread(struct rcu_data *rdp);
static void rcu_cpu_kthread_setup(unsigned int cpu);
static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp);
static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
static bool rcu_preempt_need_deferred_qs(struct task_struct *t);
-static void rcu_preempt_deferred_qs(struct task_struct *t);
static void zero_cpu_stall_ticks(struct rcu_data *rdp);
static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp);
static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq);
@@ -470,10 +474,6 @@ do { \
static void rcu_bind_gp_kthread(void);
static bool rcu_nohz_full_cpu(void);
-static void rcu_dynticks_task_enter(void);
-static void rcu_dynticks_task_exit(void);
-static void rcu_dynticks_task_trace_enter(void);
-static void rcu_dynticks_task_trace_exit(void);
/* Forward declarations for tree_stall.h */
static void record_gp_stall_check_time(void);
@@ -481,3 +481,6 @@ static void rcu_iw_handler(struct irq_work *iwp);
static void check_cpu_stall(struct rcu_data *rdp);
static void rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
const unsigned long gpssdelay);
+
+/* Forward declarations for tree_exp.h. */
+static void sync_rcu_do_polled_gp(struct work_struct *wp);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 0f70f62039a9..be667583a554 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -18,6 +18,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp);
static void rcu_exp_gp_seq_start(void)
{
rcu_seq_start(&rcu_state.expedited_sequence);
+ rcu_poll_gp_seq_start_unlocked(&rcu_state.gp_seq_polled_exp_snap);
}
/*
@@ -34,6 +35,7 @@ static __maybe_unused unsigned long rcu_exp_gp_seq_endval(void)
*/
static void rcu_exp_gp_seq_end(void)
{
+ rcu_poll_gp_seq_end_unlocked(&rcu_state.gp_seq_polled_exp_snap);
rcu_seq_end(&rcu_state.expedited_sequence);
smp_mb(); /* Ensure that consecutive grace periods serialize. */
}
@@ -356,7 +358,7 @@ static void __sync_rcu_exp_select_node_cpus(struct rcu_exp_work *rewp)
!(rnp->qsmaskinitnext & mask)) {
mask_ofl_test |= mask;
} else {
- snap = rcu_dynticks_snap(rdp);
+ snap = rcu_dynticks_snap(cpu);
if (rcu_dynticks_in_eqs(snap))
mask_ofl_test |= mask;
else
@@ -621,7 +623,6 @@ static void synchronize_rcu_expedited_wait(void)
return;
if (rcu_stall_is_suppressed())
continue;
- panic_on_rcu_stall();
trace_rcu_stall_warning(rcu_state.name, TPS("ExpeditedStall"));
pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {",
rcu_state.name);
@@ -636,10 +637,11 @@ static void synchronize_rcu_expedited_wait(void)
continue;
ndetected++;
rdp = per_cpu_ptr(&rcu_data, cpu);
- pr_cont(" %d-%c%c%c", cpu,
+ pr_cont(" %d-%c%c%c%c", cpu,
"O."[!!cpu_online(cpu)],
"o."[!!(rdp->grpmask & rnp->expmaskinit)],
- "N."[!!(rdp->grpmask & rnp->expmaskinitnext)]);
+ "N."[!!(rdp->grpmask & rnp->expmaskinitnext)],
+ "D."[!!(rdp->cpu_no_qs.b.exp)]);
}
}
pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n",
@@ -669,6 +671,7 @@ static void synchronize_rcu_expedited_wait(void)
}
}
jiffies_stall = 3 * rcu_exp_jiffies_till_stall_check() + 3;
+ panic_on_rcu_stall();
}
}
@@ -913,8 +916,18 @@ void synchronize_rcu_expedited(void)
"Illegal synchronize_rcu_expedited() in RCU read-side critical section");
/* Is the state is such that the call is a grace period? */
- if (rcu_blocking_is_gp())
- return;
+ if (rcu_blocking_is_gp()) {
+ // Note well that this code runs with !PREEMPT && !SMP.
+ // In addition, all code that advances grace periods runs
+ // at process level. Therefore, this expedited GP overlaps
+ // with other expedited GPs only by being fully nested within
+ // them, which allows reuse of ->gp_seq_polled_exp_snap.
+ rcu_poll_gp_seq_start_unlocked(&rcu_state.gp_seq_polled_exp_snap);
+ rcu_poll_gp_seq_end_unlocked(&rcu_state.gp_seq_polled_exp_snap);
+ if (rcu_init_invoked())
+ cond_resched();
+ return; // Context allows vacuous grace periods.
+ }
/* If expedited grace periods are prohibited, fall back to normal. */
if (rcu_gp_is_normal()) {
@@ -950,3 +963,93 @@ void synchronize_rcu_expedited(void)
synchronize_rcu_expedited_destroy_work(&rew);
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
+
+/*
+ * Ensure that start_poll_synchronize_rcu_expedited() has the expedited
+ * RCU grace periods that it needs.
+ */
+static void sync_rcu_do_polled_gp(struct work_struct *wp)
+{
+ unsigned long flags;
+ int i = 0;
+ struct rcu_node *rnp = container_of(wp, struct rcu_node, exp_poll_wq);
+ unsigned long s;
+
+ raw_spin_lock_irqsave(&rnp->exp_poll_lock, flags);
+ s = rnp->exp_seq_poll_rq;
+ rnp->exp_seq_poll_rq = RCU_GET_STATE_COMPLETED;
+ raw_spin_unlock_irqrestore(&rnp->exp_poll_lock, flags);
+ if (s == RCU_GET_STATE_COMPLETED)
+ return;
+ while (!poll_state_synchronize_rcu(s)) {
+ synchronize_rcu_expedited();
+ if (i == 10 || i == 20)
+ pr_info("%s: i = %d s = %lx gp_seq_polled = %lx\n", __func__, i, s, READ_ONCE(rcu_state.gp_seq_polled));
+ i++;
+ }
+ raw_spin_lock_irqsave(&rnp->exp_poll_lock, flags);
+ s = rnp->exp_seq_poll_rq;
+ if (poll_state_synchronize_rcu(s))
+ rnp->exp_seq_poll_rq = RCU_GET_STATE_COMPLETED;
+ raw_spin_unlock_irqrestore(&rnp->exp_poll_lock, flags);
+}
+
+/**
+ * start_poll_synchronize_rcu_expedited - Snapshot current RCU state and start expedited grace period
+ *
+ * Returns a cookie to pass to a call to cond_synchronize_rcu(),
+ * cond_synchronize_rcu_expedited(), or poll_state_synchronize_rcu(),
+ * allowing them to determine whether or not any sort of grace period has
+ * elapsed in the meantime. If the needed expedited grace period is not
+ * already slated to start, initiates that grace period.
+ */
+unsigned long start_poll_synchronize_rcu_expedited(void)
+{
+ unsigned long flags;
+ struct rcu_data *rdp;
+ struct rcu_node *rnp;
+ unsigned long s;
+
+ s = get_state_synchronize_rcu();
+ rdp = per_cpu_ptr(&rcu_data, raw_smp_processor_id());
+ rnp = rdp->mynode;
+ if (rcu_init_invoked())
+ raw_spin_lock_irqsave(&rnp->exp_poll_lock, flags);
+ if (!poll_state_synchronize_rcu(s)) {
+ rnp->exp_seq_poll_rq = s;
+ if (rcu_init_invoked())
+ queue_work(rcu_gp_wq, &rnp->exp_poll_wq);
+ }
+ if (rcu_init_invoked())
+ raw_spin_unlock_irqrestore(&rnp->exp_poll_lock, flags);
+
+ return s;
+}
+EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu_expedited);
+
+/**
+ * cond_synchronize_rcu_expedited - Conditionally wait for an expedited RCU grace period
+ *
+ * @oldstate: value from get_state_synchronize_rcu(), start_poll_synchronize_rcu(), or start_poll_synchronize_rcu_expedited()
+ *
+ * If any type of full RCU grace period has elapsed since the earlier
+ * call to get_state_synchronize_rcu(), start_poll_synchronize_rcu(),
+ * or start_poll_synchronize_rcu_expedited(), just return. Otherwise,
+ * invoke synchronize_rcu_expedited() to wait for a full grace period.
+ *
+ * Yes, this function does not take counter wrap into account.
+ * But counter wrap is harmless. If the counter wraps, we have waited for
+ * more than 2 billion grace periods (and way more on a 64-bit system!),
+ * so waiting for a couple of additional grace periods should be just fine.
+ *
+ * This function provides the same memory-ordering guarantees that
+ * would be provided by a synchronize_rcu() that was invoked at the call
+ * to the function that provided @oldstate and that returned at the end
+ * of this function.
+ */
+void cond_synchronize_rcu_expedited(unsigned long oldstate)
+{
+ if (!poll_state_synchronize_rcu(oldstate))
+ synchronize_rcu_expedited();
+}
+EXPORT_SYMBOL_GPL(cond_synchronize_rcu_expedited);
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index 46694e13398a..a8f574d8850d 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -546,52 +546,51 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
}
}
-/*
- * Check if we ignore this rdp.
- *
- * We check that without holding the nocb lock but
- * we make sure not to miss a freshly offloaded rdp
- * with the current ordering:
- *
- * rdp_offload_toggle() nocb_gp_enabled_cb()
- * ------------------------- ----------------------------
- * WRITE flags LOCK nocb_gp_lock
- * LOCK nocb_gp_lock READ/WRITE nocb_gp_sleep
- * READ/WRITE nocb_gp_sleep UNLOCK nocb_gp_lock
- * UNLOCK nocb_gp_lock READ flags
- */
-static inline bool nocb_gp_enabled_cb(struct rcu_data *rdp)
-{
- u8 flags = SEGCBLIST_OFFLOADED | SEGCBLIST_KTHREAD_GP;
-
- return rcu_segcblist_test_flags(&rdp->cblist, flags);
-}
-
-static inline bool nocb_gp_update_state_deoffloading(struct rcu_data *rdp,
- bool *needwake_state)
+static int nocb_gp_toggle_rdp(struct rcu_data *rdp,
+ bool *wake_state)
{
struct rcu_segcblist *cblist = &rdp->cblist;
+ unsigned long flags;
+ int ret;
- if (rcu_segcblist_test_flags(cblist, SEGCBLIST_OFFLOADED)) {
- if (!rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_GP)) {
- rcu_segcblist_set_flags(cblist, SEGCBLIST_KTHREAD_GP);
- if (rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB))
- *needwake_state = true;
- }
- return false;
+ rcu_nocb_lock_irqsave(rdp, flags);
+ if (rcu_segcblist_test_flags(cblist, SEGCBLIST_OFFLOADED) &&
+ !rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_GP)) {
+ /*
+ * Offloading. Set our flag and notify the offload worker.
+ * We will handle this rdp until it ever gets de-offloaded.
+ */
+ rcu_segcblist_set_flags(cblist, SEGCBLIST_KTHREAD_GP);
+ if (rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB))
+ *wake_state = true;
+ ret = 1;
+ } else if (!rcu_segcblist_test_flags(cblist, SEGCBLIST_OFFLOADED) &&
+ rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_GP)) {
+ /*
+ * De-offloading. Clear our flag and notify the de-offload worker.
+ * We will ignore this rdp until it ever gets re-offloaded.
+ */
+ rcu_segcblist_clear_flags(cblist, SEGCBLIST_KTHREAD_GP);
+ if (!rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB))
+ *wake_state = true;
+ ret = 0;
+ } else {
+ WARN_ON_ONCE(1);
+ ret = -1;
}
- /*
- * De-offloading. Clear our flag and notify the de-offload worker.
- * We will ignore this rdp until it ever gets re-offloaded.
- */
- WARN_ON_ONCE(!rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_GP));
- rcu_segcblist_clear_flags(cblist, SEGCBLIST_KTHREAD_GP);
- if (!rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB))
- *needwake_state = true;
- return true;
+ rcu_nocb_unlock_irqrestore(rdp, flags);
+
+ return ret;
}
+static void nocb_gp_sleep(struct rcu_data *my_rdp, int cpu)
+{
+ trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Sleep"));
+ swait_event_interruptible_exclusive(my_rdp->nocb_gp_wq,
+ !READ_ONCE(my_rdp->nocb_gp_sleep));
+ trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("EndSleep"));
+}
/*
* No-CBs GP kthreads come here to wait for additional callbacks to show up
@@ -609,7 +608,7 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
bool needwait_gp = false; // This prevents actual uninitialized use.
bool needwake;
bool needwake_gp;
- struct rcu_data *rdp;
+ struct rcu_data *rdp, *rdp_toggling = NULL;
struct rcu_node *rnp;
unsigned long wait_gp_seq = 0; // Suppress "use uninitialized" warning.
bool wasempty = false;
@@ -634,19 +633,10 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
* is added to the list, so the skipped-over rcu_data structures
* won't be ignored for long.
*/
- list_for_each_entry_rcu(rdp, &my_rdp->nocb_head_rdp, nocb_entry_rdp, 1) {
- bool needwake_state = false;
-
- if (!nocb_gp_enabled_cb(rdp))
- continue;
+ list_for_each_entry(rdp, &my_rdp->nocb_head_rdp, nocb_entry_rdp) {
trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("Check"));
rcu_nocb_lock_irqsave(rdp, flags);
- if (nocb_gp_update_state_deoffloading(rdp, &needwake_state)) {
- rcu_nocb_unlock_irqrestore(rdp, flags);
- if (needwake_state)
- swake_up_one(&rdp->nocb_state_wq);
- continue;
- }
+ lockdep_assert_held(&rdp->nocb_lock);
bypass_ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass);
if (bypass_ncbs &&
(time_after(j, READ_ONCE(rdp->nocb_bypass_first) + 1) ||
@@ -656,8 +646,6 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
bypass_ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass);
} else if (!bypass_ncbs && rcu_segcblist_empty(&rdp->cblist)) {
rcu_nocb_unlock_irqrestore(rdp, flags);
- if (needwake_state)
- swake_up_one(&rdp->nocb_state_wq);
continue; /* No callbacks here, try next. */
}
if (bypass_ncbs) {
@@ -705,8 +693,6 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
}
if (needwake_gp)
rcu_gp_kthread_wake();
- if (needwake_state)
- swake_up_one(&rdp->nocb_state_wq);
}
my_rdp->nocb_gp_bypass = bypass;
@@ -723,13 +709,19 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
/* Polling, so trace if first poll in the series. */
if (gotcbs)
trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Poll"));
- schedule_timeout_idle(1);
+ if (list_empty(&my_rdp->nocb_head_rdp)) {
+ raw_spin_lock_irqsave(&my_rdp->nocb_gp_lock, flags);
+ if (!my_rdp->nocb_toggling_rdp)
+ WRITE_ONCE(my_rdp->nocb_gp_sleep, true);
+ raw_spin_unlock_irqrestore(&my_rdp->nocb_gp_lock, flags);
+ /* Wait for any offloading rdp */
+ nocb_gp_sleep(my_rdp, cpu);
+ } else {
+ schedule_timeout_idle(1);
+ }
} else if (!needwait_gp) {
/* Wait for callbacks to appear. */
- trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Sleep"));
- swait_event_interruptible_exclusive(my_rdp->nocb_gp_wq,
- !READ_ONCE(my_rdp->nocb_gp_sleep));
- trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("EndSleep"));
+ nocb_gp_sleep(my_rdp, cpu);
} else {
rnp = my_rdp->mynode;
trace_rcu_this_gp(rnp, my_rdp, wait_gp_seq, TPS("StartWait"));
@@ -739,15 +731,49 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
!READ_ONCE(my_rdp->nocb_gp_sleep));
trace_rcu_this_gp(rnp, my_rdp, wait_gp_seq, TPS("EndWait"));
}
+
if (!rcu_nocb_poll) {
raw_spin_lock_irqsave(&my_rdp->nocb_gp_lock, flags);
+ // (De-)queue an rdp to/from the group if its nocb state is changing
+ rdp_toggling = my_rdp->nocb_toggling_rdp;
+ if (rdp_toggling)
+ my_rdp->nocb_toggling_rdp = NULL;
+
if (my_rdp->nocb_defer_wakeup > RCU_NOCB_WAKE_NOT) {
WRITE_ONCE(my_rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT);
del_timer(&my_rdp->nocb_timer);
}
WRITE_ONCE(my_rdp->nocb_gp_sleep, true);
raw_spin_unlock_irqrestore(&my_rdp->nocb_gp_lock, flags);
+ } else {
+ rdp_toggling = READ_ONCE(my_rdp->nocb_toggling_rdp);
+ if (rdp_toggling) {
+ /*
+ * Paranoid locking to make sure nocb_toggling_rdp is well
+ * reset *before* we (re)set SEGCBLIST_KTHREAD_GP or we could
+ * race with another round of nocb toggling for this rdp.
+ * Nocb locking should prevent from that already but we stick
+ * to paranoia, especially in rare path.
+ */
+ raw_spin_lock_irqsave(&my_rdp->nocb_gp_lock, flags);
+ my_rdp->nocb_toggling_rdp = NULL;
+ raw_spin_unlock_irqrestore(&my_rdp->nocb_gp_lock, flags);
+ }
+ }
+
+ if (rdp_toggling) {
+ bool wake_state = false;
+ int ret;
+
+ ret = nocb_gp_toggle_rdp(rdp_toggling, &wake_state);
+ if (ret == 1)
+ list_add_tail(&rdp_toggling->nocb_entry_rdp, &my_rdp->nocb_head_rdp);
+ else if (ret == 0)
+ list_del(&rdp_toggling->nocb_entry_rdp);
+ if (wake_state)
+ swake_up_one(&rdp_toggling->nocb_state_wq);
}
+
my_rdp->nocb_gp_seq = -1;
WARN_ON(signal_pending(current));
}
@@ -966,16 +992,15 @@ static int rdp_offload_toggle(struct rcu_data *rdp,
swake_up_one(&rdp->nocb_cb_wq);
raw_spin_lock_irqsave(&rdp_gp->nocb_gp_lock, flags);
+ // Queue this rdp for add/del to/from the list to iterate on rcuog
+ WRITE_ONCE(rdp_gp->nocb_toggling_rdp, rdp);
if (rdp_gp->nocb_gp_sleep) {
rdp_gp->nocb_gp_sleep = false;
wake_gp = true;
}
raw_spin_unlock_irqrestore(&rdp_gp->nocb_gp_lock, flags);
- if (wake_gp)
- wake_up_process(rdp_gp->nocb_gp_kthread);
-
- return 0;
+ return wake_gp;
}
static long rcu_nocb_rdp_deoffload(void *arg)
@@ -983,9 +1008,15 @@ static long rcu_nocb_rdp_deoffload(void *arg)
struct rcu_data *rdp = arg;
struct rcu_segcblist *cblist = &rdp->cblist;
unsigned long flags;
- int ret;
+ int wake_gp;
+ struct rcu_data *rdp_gp = rdp->nocb_gp_rdp;
- WARN_ON_ONCE(rdp->cpu != raw_smp_processor_id());
+ /*
+ * rcu_nocb_rdp_deoffload() may be called directly if
+ * rcuog/o[p] spawn failed, because at this time the rdp->cpu
+ * is not online yet.
+ */
+ WARN_ON_ONCE((rdp->cpu != raw_smp_processor_id()) && cpu_online(rdp->cpu));
pr_info("De-offloading %d\n", rdp->cpu);
@@ -1009,12 +1040,41 @@ static long rcu_nocb_rdp_deoffload(void *arg)
*/
rcu_segcblist_set_flags(cblist, SEGCBLIST_RCU_CORE);
invoke_rcu_core();
- ret = rdp_offload_toggle(rdp, false, flags);
- swait_event_exclusive(rdp->nocb_state_wq,
- !rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB |
- SEGCBLIST_KTHREAD_GP));
- /* Stop nocb_gp_wait() from iterating over this structure. */
- list_del_rcu(&rdp->nocb_entry_rdp);
+ wake_gp = rdp_offload_toggle(rdp, false, flags);
+
+ mutex_lock(&rdp_gp->nocb_gp_kthread_mutex);
+ if (rdp_gp->nocb_gp_kthread) {
+ if (wake_gp)
+ wake_up_process(rdp_gp->nocb_gp_kthread);
+
+ /*
+ * If rcuo[p] kthread spawn failed, directly remove SEGCBLIST_KTHREAD_CB.
+ * Just wait SEGCBLIST_KTHREAD_GP to be cleared by rcuog.
+ */
+ if (!rdp->nocb_cb_kthread) {
+ rcu_nocb_lock_irqsave(rdp, flags);
+ rcu_segcblist_clear_flags(&rdp->cblist, SEGCBLIST_KTHREAD_CB);
+ rcu_nocb_unlock_irqrestore(rdp, flags);
+ }
+
+ swait_event_exclusive(rdp->nocb_state_wq,
+ !rcu_segcblist_test_flags(cblist,
+ SEGCBLIST_KTHREAD_CB | SEGCBLIST_KTHREAD_GP));
+ } else {
+ /*
+ * No kthread to clear the flags for us or remove the rdp from the nocb list
+ * to iterate. Do it here instead. Locking doesn't look stricly necessary
+ * but we stick to paranoia in this rare path.
+ */
+ rcu_nocb_lock_irqsave(rdp, flags);
+ rcu_segcblist_clear_flags(&rdp->cblist,
+ SEGCBLIST_KTHREAD_CB | SEGCBLIST_KTHREAD_GP);
+ rcu_nocb_unlock_irqrestore(rdp, flags);
+
+ list_del(&rdp->nocb_entry_rdp);
+ }
+ mutex_unlock(&rdp_gp->nocb_gp_kthread_mutex);
+
/*
* Lock one last time to acquire latest callback updates from kthreads
* so we can later handle callbacks locally without locking.
@@ -1035,7 +1095,7 @@ static long rcu_nocb_rdp_deoffload(void *arg)
WARN_ON_ONCE(rcu_cblist_n_cbs(&rdp->nocb_bypass));
- return ret;
+ return 0;
}
int rcu_nocb_cpu_deoffload(int cpu)
@@ -1043,8 +1103,8 @@ int rcu_nocb_cpu_deoffload(int cpu)
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
int ret = 0;
- mutex_lock(&rcu_state.barrier_mutex);
cpus_read_lock();
+ mutex_lock(&rcu_state.barrier_mutex);
if (rcu_rdp_is_offloaded(rdp)) {
if (cpu_online(cpu)) {
ret = work_on_cpu(cpu, rcu_nocb_rdp_deoffload, rdp);
@@ -1055,8 +1115,8 @@ int rcu_nocb_cpu_deoffload(int cpu)
ret = -EINVAL;
}
}
- cpus_read_unlock();
mutex_unlock(&rcu_state.barrier_mutex);
+ cpus_read_unlock();
return ret;
}
@@ -1067,7 +1127,8 @@ static long rcu_nocb_rdp_offload(void *arg)
struct rcu_data *rdp = arg;
struct rcu_segcblist *cblist = &rdp->cblist;
unsigned long flags;
- int ret;
+ int wake_gp;
+ struct rcu_data *rdp_gp = rdp->nocb_gp_rdp;
WARN_ON_ONCE(rdp->cpu != raw_smp_processor_id());
/*
@@ -1077,17 +1138,10 @@ static long rcu_nocb_rdp_offload(void *arg)
if (!rdp->nocb_gp_rdp)
return -EINVAL;
- pr_info("Offloading %d\n", rdp->cpu);
+ if (WARN_ON_ONCE(!rdp_gp->nocb_gp_kthread))
+ return -EINVAL;
- /*
- * Cause future nocb_gp_wait() invocations to iterate over
- * structure, resetting ->nocb_gp_sleep and waking up the related
- * "rcuog". Since nocb_gp_wait() in turn locks ->nocb_gp_lock
- * before setting ->nocb_gp_sleep again, we are guaranteed to
- * iterate this newly added structure before "rcuog" goes to
- * sleep again.
- */
- list_add_tail_rcu(&rdp->nocb_entry_rdp, &rdp->nocb_gp_rdp->nocb_head_rdp);
+ pr_info("Offloading %d\n", rdp->cpu);
/*
* Can't use rcu_nocb_lock_irqsave() before SEGCBLIST_LOCKING
@@ -1111,7 +1165,9 @@ static long rcu_nocb_rdp_offload(void *arg)
* WRITE flags READ callbacks
* rcu_nocb_unlock() rcu_nocb_unlock()
*/
- ret = rdp_offload_toggle(rdp, true, flags);
+ wake_gp = rdp_offload_toggle(rdp, true, flags);
+ if (wake_gp)
+ wake_up_process(rdp_gp->nocb_gp_kthread);
swait_event_exclusive(rdp->nocb_state_wq,
rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB) &&
rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_GP));
@@ -1124,7 +1180,7 @@ static long rcu_nocb_rdp_offload(void *arg)
rcu_segcblist_clear_flags(cblist, SEGCBLIST_RCU_CORE);
rcu_nocb_unlock_irqrestore(rdp, flags);
- return ret;
+ return 0;
}
int rcu_nocb_cpu_offload(int cpu)
@@ -1132,8 +1188,8 @@ int rcu_nocb_cpu_offload(int cpu)
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
int ret = 0;
- mutex_lock(&rcu_state.barrier_mutex);
cpus_read_lock();
+ mutex_lock(&rcu_state.barrier_mutex);
if (!rcu_rdp_is_offloaded(rdp)) {
if (cpu_online(cpu)) {
ret = work_on_cpu(cpu, rcu_nocb_rdp_offload, rdp);
@@ -1144,8 +1200,8 @@ int rcu_nocb_cpu_offload(int cpu)
ret = -EINVAL;
}
}
- cpus_read_unlock();
mutex_unlock(&rcu_state.barrier_mutex);
+ cpus_read_unlock();
return ret;
}
@@ -1155,11 +1211,21 @@ void __init rcu_init_nohz(void)
{
int cpu;
bool need_rcu_nocb_mask = false;
+ bool offload_all = false;
struct rcu_data *rdp;
+#if defined(CONFIG_RCU_NOCB_CPU_DEFAULT_ALL)
+ if (!rcu_state.nocb_is_setup) {
+ need_rcu_nocb_mask = true;
+ offload_all = true;
+ }
+#endif /* #if defined(CONFIG_RCU_NOCB_CPU_DEFAULT_ALL) */
+
#if defined(CONFIG_NO_HZ_FULL)
- if (tick_nohz_full_running && !cpumask_empty(tick_nohz_full_mask))
+ if (tick_nohz_full_running && !cpumask_empty(tick_nohz_full_mask)) {
need_rcu_nocb_mask = true;
+ offload_all = false; /* NO_HZ_FULL has its own mask. */
+ }
#endif /* #if defined(CONFIG_NO_HZ_FULL) */
if (need_rcu_nocb_mask) {
@@ -1180,6 +1246,9 @@ void __init rcu_init_nohz(void)
cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask);
#endif /* #if defined(CONFIG_NO_HZ_FULL) */
+ if (offload_all)
+ cpumask_setall(rcu_nocb_mask);
+
if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
pr_info("\tNote: kernel parameter 'rcu_nocbs=', 'nohz_full', or 'isolcpus=' contains nonexistent CPUs.\n");
cpumask_and(rcu_nocb_mask, cpu_possible_mask,
@@ -1246,7 +1315,7 @@ static void rcu_spawn_cpu_nocb_kthread(int cpu)
"rcuog/%d", rdp_gp->cpu);
if (WARN_ONCE(IS_ERR(t), "%s: Could not start rcuo GP kthread, OOM is now expected behavior\n", __func__)) {
mutex_unlock(&rdp_gp->nocb_gp_kthread_mutex);
- return;
+ goto end;
}
WRITE_ONCE(rdp_gp->nocb_gp_kthread, t);
if (kthread_prio)
@@ -1258,12 +1327,21 @@ static void rcu_spawn_cpu_nocb_kthread(int cpu)
t = kthread_run(rcu_nocb_cb_kthread, rdp,
"rcuo%c/%d", rcu_state.abbr, cpu);
if (WARN_ONCE(IS_ERR(t), "%s: Could not start rcuo CB kthread, OOM is now expected behavior\n", __func__))
- return;
+ goto end;
- if (kthread_prio)
+ if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_CB_BOOST) && kthread_prio)
sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+
WRITE_ONCE(rdp->nocb_cb_kthread, t);
WRITE_ONCE(rdp->nocb_gp_kthread, rdp_gp->nocb_gp_kthread);
+ return;
+end:
+ mutex_lock(&rcu_state.barrier_mutex);
+ if (rcu_rdp_is_offloaded(rdp)) {
+ rcu_nocb_rdp_deoffload(rdp);
+ cpumask_clear_cpu(cpu, rcu_nocb_mask);
+ }
+ mutex_unlock(&rcu_state.barrier_mutex);
}
/* How many CB CPU IDs per GP kthread? Default of -1 for sqrt(nr_cpu_ids). */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index c8ba0fe17267..438ecae6bd7e 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -460,7 +460,7 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp)
* be quite short, for example, in the case of the call from
* rcu_read_unlock_special().
*/
-static void
+static notrace void
rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
{
bool empty_exp;
@@ -581,7 +581,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
* is disabled. This function cannot be expected to understand these
* nuances, so the caller must handle them.
*/
-static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
+static notrace bool rcu_preempt_need_deferred_qs(struct task_struct *t)
{
return (__this_cpu_read(rcu_data.cpu_no_qs.b.exp) ||
READ_ONCE(t->rcu_read_unlock_special.s)) &&
@@ -595,7 +595,7 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
* evaluate safety in terms of interrupt, softirq, and preemption
* disabling.
*/
-static void rcu_preempt_deferred_qs(struct task_struct *t)
+notrace void rcu_preempt_deferred_qs(struct task_struct *t)
{
unsigned long flags;
@@ -899,8 +899,8 @@ void rcu_note_context_switch(bool preempt)
this_cpu_write(rcu_data.rcu_urgent_qs, false);
if (unlikely(raw_cpu_read(rcu_data.rcu_need_heavy_qs)))
rcu_momentary_dyntick_idle();
- rcu_tasks_qs(current, preempt);
out:
+ rcu_tasks_qs(current, preempt);
trace_rcu_utilization(TPS("End context switch"));
}
EXPORT_SYMBOL_GPL(rcu_note_context_switch);
@@ -926,7 +926,7 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp)
* Because there is no preemptible RCU, there can be no deferred quiescent
* states.
*/
-static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
+static notrace bool rcu_preempt_need_deferred_qs(struct task_struct *t)
{
return false;
}
@@ -935,7 +935,7 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
// period for a quiescent state from this CPU. Note that requests from
// tasks are handled when removing the task from the blocked-tasks list
// below.
-static void rcu_preempt_deferred_qs(struct task_struct *t)
+notrace void rcu_preempt_deferred_qs(struct task_struct *t)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
@@ -1012,6 +1012,25 @@ static void rcu_cpu_kthread_setup(unsigned int cpu)
WRITE_ONCE(rdp->rcuc_activity, jiffies);
}
+static bool rcu_is_callbacks_nocb_kthread(struct rcu_data *rdp)
+{
+#ifdef CONFIG_RCU_NOCB_CPU
+ return rdp->nocb_cb_kthread == current;
+#else
+ return false;
+#endif
+}
+
+/*
+ * Is the current CPU running the RCU-callbacks kthread?
+ * Caller must have preemption disabled.
+ */
+static bool rcu_is_callbacks_kthread(struct rcu_data *rdp)
+{
+ return rdp->rcu_cpu_kthread_task == current ||
+ rcu_is_callbacks_nocb_kthread(rdp);
+}
+
#ifdef CONFIG_RCU_BOOST
/*
@@ -1140,7 +1159,8 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
(rnp->gp_tasks != NULL &&
rnp->boost_tasks == NULL &&
rnp->qsmask == 0 &&
- (!time_after(rnp->boost_time, jiffies) || rcu_state.cbovld))) {
+ (!time_after(rnp->boost_time, jiffies) || rcu_state.cbovld ||
+ IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)))) {
if (rnp->exp_tasks == NULL)
WRITE_ONCE(rnp->boost_tasks, rnp->gp_tasks);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -1151,15 +1171,6 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
}
}
-/*
- * Is the current CPU running the RCU-callbacks kthread?
- * Caller must have preemption disabled.
- */
-static bool rcu_is_callbacks_kthread(void)
-{
- return __this_cpu_read(rcu_data.rcu_cpu_kthread_task) == current;
-}
-
#define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000)
/*
@@ -1242,11 +1253,6 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
-static bool rcu_is_callbacks_kthread(void)
-{
- return false;
-}
-
static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
{
}
@@ -1290,37 +1296,3 @@ static void rcu_bind_gp_kthread(void)
return;
housekeeping_affine(current, HK_TYPE_RCU);
}
-
-/* Record the current task on dyntick-idle entry. */
-static __always_inline void rcu_dynticks_task_enter(void)
-{
-#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
- WRITE_ONCE(current->rcu_tasks_idle_cpu, smp_processor_id());
-#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
-}
-
-/* Record no current task on dyntick-idle exit. */
-static __always_inline void rcu_dynticks_task_exit(void)
-{
-#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
- WRITE_ONCE(current->rcu_tasks_idle_cpu, -1);
-#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
-}
-
-/* Turn on heavyweight RCU tasks trace readers on idle/user entry. */
-static __always_inline void rcu_dynticks_task_trace_enter(void)
-{
-#ifdef CONFIG_TASKS_TRACE_RCU
- if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
- current->trc_reader_special.b.need_mb = true;
-#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
-}
-
-/* Turn off heavyweight RCU tasks trace readers on idle/user exit. */
-static __always_inline void rcu_dynticks_task_trace_exit(void)
-{
-#ifdef CONFIG_TASKS_TRACE_RCU
- if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
- current->trc_reader_special.b.need_mb = false;
-#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
-}
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index a001e1e7a992..c3fbbcc09327 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -409,7 +409,19 @@ static bool rcu_is_gp_kthread_starving(unsigned long *jp)
static bool rcu_is_rcuc_kthread_starving(struct rcu_data *rdp, unsigned long *jp)
{
- unsigned long j = jiffies - READ_ONCE(rdp->rcuc_activity);
+ int cpu;
+ struct task_struct *rcuc;
+ unsigned long j;
+
+ rcuc = rdp->rcu_cpu_kthread_task;
+ if (!rcuc)
+ return false;
+
+ cpu = task_cpu(rcuc);
+ if (cpu_is_offline(cpu) || idle_cpu(cpu))
+ return false;
+
+ j = jiffies - READ_ONCE(rdp->rcuc_activity);
if (jp)
*jp = j;
@@ -434,6 +446,9 @@ static void print_cpu_stall_info(int cpu)
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
char *ticks_title;
unsigned long ticks_value;
+ bool rcuc_starved;
+ unsigned long j;
+ char buf[32];
/*
* We could be printing a lot while holding a spinlock. Avoid
@@ -450,8 +465,11 @@ static void print_cpu_stall_info(int cpu)
}
delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
falsepositive = rcu_is_gp_kthread_starving(NULL) &&
- rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp));
- pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n",
+ rcu_dynticks_in_eqs(rcu_dynticks_snap(cpu));
+ rcuc_starved = rcu_is_rcuc_kthread_starving(rdp, &j);
+ if (rcuc_starved)
+ sprintf(buf, " rcuc=%ld jiffies(starved)", j);
+ pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%04x/%ld/%#lx softirq=%u/%u fqs=%ld%s%s\n",
cpu,
"O."[!!cpu_online(cpu)],
"o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
@@ -460,36 +478,14 @@ static void print_cpu_stall_info(int cpu)
rdp->rcu_iw_pending ? (int)min(delta, 9UL) + '0' :
"!."[!delta],
ticks_value, ticks_title,
- rcu_dynticks_snap(rdp) & 0xfff,
- rdp->dynticks_nesting, rdp->dynticks_nmi_nesting,
+ rcu_dynticks_snap(cpu) & 0xffff,
+ ct_dynticks_nesting_cpu(cpu), ct_dynticks_nmi_nesting_cpu(cpu),
rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
data_race(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart,
+ rcuc_starved ? buf : "",
falsepositive ? " (false positive?)" : "");
}
-static void rcuc_kthread_dump(struct rcu_data *rdp)
-{
- int cpu;
- unsigned long j;
- struct task_struct *rcuc;
-
- rcuc = rdp->rcu_cpu_kthread_task;
- if (!rcuc)
- return;
-
- cpu = task_cpu(rcuc);
- if (cpu_is_offline(cpu) || idle_cpu(cpu))
- return;
-
- if (!rcu_is_rcuc_kthread_starving(rdp, &j))
- return;
-
- pr_err("%s kthread starved for %ld jiffies\n", rcuc->comm, j);
- sched_show_task(rcuc);
- if (!trigger_single_cpu_backtrace(cpu))
- dump_cpu_task(cpu);
-}
-
/* Complain about starvation of grace-period kthread. */
static void rcu_check_gp_kthread_starvation(void)
{
@@ -661,9 +657,6 @@ static void print_cpu_stall(unsigned long gps)
rcu_check_gp_kthread_expired_fqs_timer();
rcu_check_gp_kthread_starvation();
- if (!use_softirq)
- rcuc_kthread_dump(rdp);
-
rcu_dump_cpu_stacks();
raw_spin_lock_irqsave_rcu_node(rnp, flags);
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index fc7fef575606..738842c4886b 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -85,7 +85,7 @@ module_param(rcu_normal_after_boot, int, 0444);
* and while lockdep is disabled.
*
* Note that if the CPU is in the idle loop from an RCU point of view (ie:
- * that we are in the section between rcu_idle_enter() and rcu_idle_exit())
+ * that we are in the section between ct_idle_enter() and ct_idle_exit())
* then rcu_read_lock_held() sets ``*ret`` to false even if the CPU did an
* rcu_read_lock(). The reason for this is that RCU ignores CPUs that are
* in such a section, considering these as in extended quiescent state,
@@ -516,6 +516,19 @@ int rcu_cpu_stall_suppress_at_boot __read_mostly; // !0 = suppress boot stalls.
EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress_at_boot);
module_param(rcu_cpu_stall_suppress_at_boot, int, 0444);
+/**
+ * get_completed_synchronize_rcu - Return a pre-completed polled state cookie
+ *
+ * Returns a value that will always be treated by functions like
+ * poll_state_synchronize_rcu() as a cookie whose grace period has already
+ * completed.
+ */
+unsigned long get_completed_synchronize_rcu(void)
+{
+ return RCU_GET_STATE_COMPLETED;
+}
+EXPORT_SYMBOL_GPL(get_completed_synchronize_rcu);
+
#ifdef CONFIG_PROVE_RCU
/*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a1143acbf7a0..189999007f32 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4263,6 +4263,38 @@ int task_call_func(struct task_struct *p, task_call_f func, void *arg)
}
/**
+ * cpu_curr_snapshot - Return a snapshot of the currently running task
+ * @cpu: The CPU on which to snapshot the task.
+ *
+ * Returns the task_struct pointer of the task "currently" running on
+ * the specified CPU. If the same task is running on that CPU throughout,
+ * the return value will be a pointer to that task's task_struct structure.
+ * If the CPU did any context switches even vaguely concurrently with the
+ * execution of this function, the return value will be a pointer to the
+ * task_struct structure of a randomly chosen task that was running on
+ * that CPU somewhere around the time that this function was executing.
+ *
+ * If the specified CPU was offline, the return value is whatever it
+ * is, perhaps a pointer to the task_struct structure of that CPU's idle
+ * task, but there is no guarantee. Callers wishing a useful return
+ * value must take some action to ensure that the specified CPU remains
+ * online throughout.
+ *
+ * This function executes full memory barriers before and after fetching
+ * the pointer, which permits the caller to confine this function's fetch
+ * with respect to the caller's accesses to other shared variables.
+ */
+struct task_struct *cpu_curr_snapshot(int cpu)
+{
+ struct task_struct *t;
+
+ smp_mb(); /* Pairing determined by caller's synchronization design. */
+ t = rcu_dereference(cpu_curr(cpu));
+ smp_mb(); /* Pairing determined by caller's synchronization design. */
+ return t;
+}
+
+/**
* wake_up_process - Wake up a specific process
* @p: The process to be woken up.
*
@@ -6563,7 +6595,7 @@ void __sched schedule_idle(void)
} while (need_resched());
}
-#if defined(CONFIG_CONTEXT_TRACKING) && !defined(CONFIG_HAVE_CONTEXT_TRACKING_OFFSTACK)
+#if defined(CONFIG_CONTEXT_TRACKING_USER) && !defined(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK)
asmlinkage __visible void __sched schedule_user(void)
{
/*
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 328cccbee444..f26ab2675f7d 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -53,14 +53,14 @@ static noinline int __cpuidle cpu_idle_poll(void)
{
trace_cpu_idle(0, smp_processor_id());
stop_critical_timings();
- rcu_idle_enter();
+ ct_idle_enter();
local_irq_enable();
while (!tif_need_resched() &&
(cpu_idle_force_poll || tick_check_broadcast_expired()))
cpu_relax();
- rcu_idle_exit();
+ ct_idle_exit();
start_critical_timings();
trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
@@ -98,12 +98,12 @@ void __cpuidle default_idle_call(void)
*
* Trace IRQs enable here, then switch off RCU, and have
* arch_cpu_idle() use raw_local_irq_enable(). Note that
- * rcu_idle_enter() relies on lockdep IRQ state, so switch that
+ * ct_idle_enter() relies on lockdep IRQ state, so switch that
* last -- this is very similar to the entry code.
*/
trace_hardirqs_on_prepare();
lockdep_hardirqs_on_prepare();
- rcu_idle_enter();
+ ct_idle_enter();
lockdep_hardirqs_on(_THIS_IP_);
arch_cpu_idle();
@@ -116,7 +116,7 @@ void __cpuidle default_idle_call(void)
*/
raw_local_irq_disable();
lockdep_hardirqs_off(_THIS_IP_);
- rcu_idle_exit();
+ ct_idle_exit();
lockdep_hardirqs_on(_THIS_IP_);
raw_local_irq_enable();
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index aad7f5ee9666..a6f071b2acac 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -27,6 +27,7 @@
#include <linux/capability.h>
#include <linux/cgroup_api.h>
#include <linux/cgroup.h>
+#include <linux/context_tracking.h>
#include <linux/cpufreq.h>
#include <linux/cpumask_api.h>
#include <linux/ctype.h>
diff --git a/kernel/smp.c b/kernel/smp.c
index dd215f439426..650810a6f29b 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -174,9 +174,9 @@ static int __init csdlock_debug(char *str)
if (val)
static_branch_enable(&csdlock_debug_enabled);
- return 0;
+ return 1;
}
-early_param("csdlock_debug", csdlock_debug);
+__setup("csdlock_debug=", csdlock_debug);
static DEFINE_PER_CPU(call_single_data_t *, cur_csd);
static DEFINE_PER_CPU(smp_call_func_t, cur_csd_func);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 9f0aef8aa9ff..c8a6913c067d 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -620,7 +620,7 @@ void irq_enter_rcu(void)
*/
void irq_enter(void)
{
- rcu_irq_enter();
+ ct_irq_enter();
irq_enter_rcu();
}
@@ -672,7 +672,7 @@ void irq_exit_rcu(void)
void irq_exit(void)
{
__irq_exit_rcu();
- rcu_irq_exit();
+ ct_irq_exit();
/* must be last! */
lockdep_hardirq_exit();
}
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 27b7868b5c30..a41753be1a2b 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -73,6 +73,15 @@ config TIME_KUNIT_TEST
If unsure, say N.
+config CONTEXT_TRACKING
+ bool
+
+config CONTEXT_TRACKING_IDLE
+ bool
+ select CONTEXT_TRACKING
+ help
+ Tracks idle state on behalf of RCU.
+
if GENERIC_CLOCKEVENTS
menu "Timers subsystem"
@@ -111,7 +120,7 @@ config NO_HZ_FULL
# NO_HZ_COMMON dependency
# We need at least one periodic CPU for timekeeping
depends on SMP
- depends on HAVE_CONTEXT_TRACKING
+ depends on HAVE_CONTEXT_TRACKING_USER
# VIRT_CPU_ACCOUNTING_GEN dependency
depends on HAVE_VIRT_CPU_ACCOUNTING_GEN
select NO_HZ_COMMON
@@ -137,31 +146,37 @@ config NO_HZ_FULL
endchoice
-config CONTEXT_TRACKING
- bool
+config CONTEXT_TRACKING_USER
+ bool
+ depends on HAVE_CONTEXT_TRACKING_USER
+ select CONTEXT_TRACKING
+ help
+ Track transitions between kernel and user on behalf of RCU and
+ tickless cputime accounting. The former case relies on context
+ tracking to enter/exit RCU extended quiescent states.
-config CONTEXT_TRACKING_FORCE
- bool "Force context tracking"
- depends on CONTEXT_TRACKING
+config CONTEXT_TRACKING_USER_FORCE
+ bool "Force user context tracking"
+ depends on CONTEXT_TRACKING_USER
default y if !NO_HZ_FULL
help
The major pre-requirement for full dynticks to work is to
- support the context tracking subsystem. But there are also
+ support the user context tracking subsystem. But there are also
other dependencies to provide in order to make the full
dynticks working.
This option stands for testing when an arch implements the
- context tracking backend but doesn't yet fulfill all the
+ user context tracking backend but doesn't yet fulfill all the
requirements to make the full dynticks feature working.
Without the full dynticks, there is no way to test the support
- for context tracking and the subsystems that rely on it: RCU
+ for user context tracking and the subsystems that rely on it: RCU
userspace extended quiescent state and tickless cputime
accounting. This option copes with the absence of the full
- dynticks subsystem by forcing the context tracking on all
+ dynticks subsystem by forcing the user context tracking on all
CPUs in the system.
Say Y only if you're working on the development of an
- architecture backend for the context tracking.
+ architecture backend for the user context tracking.
Say N otherwise, this option brings an overhead that you
don't want in production.
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 30049580cd62..b0e3c9205946 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -570,7 +570,7 @@ void __init tick_nohz_init(void)
}
for_each_cpu(cpu, tick_nohz_full_mask)
- context_tracking_cpu_set(cpu);
+ ct_cpu_track_user(cpu);
ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
"kernel/nohz:predown", NULL,
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index b8dd54627075..0c517c8c8999 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3105,17 +3105,17 @@ void __trace_stack(struct trace_array *tr, unsigned int trace_ctx,
}
/*
- * When an NMI triggers, RCU is enabled via rcu_nmi_enter(),
+ * When an NMI triggers, RCU is enabled via ct_nmi_enter(),
* but if the above rcu_is_watching() failed, then the NMI
- * triggered someplace critical, and rcu_irq_enter() should
+ * triggered someplace critical, and ct_irq_enter() should
* not be called from NMI.
*/
if (unlikely(in_nmi()))
return;
- rcu_irq_enter_irqson();
+ ct_irq_enter_irqson();
__ftrace_trace_stack(buffer, trace_ctx, skip, NULL);
- rcu_irq_exit_irqson();
+ ct_irq_exit_irqson();
}
/**
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh
index f17000a2ccf1..ed0ec7f0927e 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh
@@ -35,7 +35,7 @@ then
exit 1
fi
-# Remember where we started so that we can get back and the end.
+# Remember where we started so that we can get back at the end.
curcommit="`git status | head -1 | awk '{ print $NF }'`"
nfail=0
@@ -73,15 +73,10 @@ do
# Test the specified commit.
git checkout $i > $resdir/$ds/$idir/git-checkout.out 2>&1
echo git checkout return code: $? "(Commit $ntry: $i)"
- kvm.sh --allcpus --duration 3 --trust-make > $resdir/$ds/$idir/kvm.sh.out 2>&1
+ kvm.sh --allcpus --duration 3 --trust-make --datestamp "$ds/$idir" > $resdir/$ds/$idir/kvm.sh.out 2>&1
ret=$?
echo kvm.sh return code $ret for commit $i from branch $gitbr
-
- # Move the build products to their resting place.
- runresdir="`grep -m 1 '^Results directory:' < $resdir/$ds/$idir/kvm.sh.out | sed -e 's/^Results directory://'`"
- mv $runresdir $resdir/$ds/$idir
- rrd="`echo $runresdir | sed -e 's,^.*/,,'`"
- echo Run results: $resdir/$ds/$idir/$rrd
+ echo Run results: $resdir/$ds/$idir
if test "$ret" -ne 0
then
# Failure, so leave all evidence intact.
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh
index 0ff59bd8b640..9f0a5d5ff2dd 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh
@@ -262,6 +262,7 @@ echo All batches started. `date` | tee -a "$oldrun/remote-log"
# Wait for all remaining scenarios to complete and collect results.
for i in $systems
do
+ echo " ---" Waiting for $i `date` | tee -a "$oldrun/remote-log"
while checkremotefile "$i" "$resdir/$ds/remote.run"
do
sleep 30
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 263e16aeca0e..6c734818a875 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -164,7 +164,7 @@ do
shift
;;
--gdb)
- TORTURE_KCONFIG_GDB_ARG="CONFIG_DEBUG_INFO=y"; export TORTURE_KCONFIG_GDB_ARG
+ TORTURE_KCONFIG_GDB_ARG="CONFIG_DEBUG_INFO_NONE=n CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y"; export TORTURE_KCONFIG_GDB_ARG
TORTURE_BOOT_GDB_ARG="nokaslr"; export TORTURE_BOOT_GDB_ARG
TORTURE_QEMU_GDB_ARG="-s -S"; export TORTURE_QEMU_GDB_ARG
;;
@@ -180,7 +180,7 @@ do
shift
;;
--kasan)
- TORTURE_KCONFIG_KASAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KASAN=y"; export TORTURE_KCONFIG_KASAN_ARG
+ TORTURE_KCONFIG_KASAN_ARG="CONFIG_DEBUG_INFO_NONE=n CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_KASAN=y"; export TORTURE_KCONFIG_KASAN_ARG
if test -n "$torture_qemu_mem_default"
then
TORTURE_QEMU_MEM=2G
@@ -192,7 +192,7 @@ do
shift
;;
--kcsan)
- TORTURE_KCONFIG_KCSAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KCSAN=y CONFIG_KCSAN_STRICT=y CONFIG_KCSAN_REPORT_ONCE_IN_MS=100000 CONFIG_KCSAN_VERBOSE=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y"; export TORTURE_KCONFIG_KCSAN_ARG
+ TORTURE_KCONFIG_KCSAN_ARG="CONFIG_DEBUG_INFO_NONE=n CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_KCSAN=y CONFIG_KCSAN_STRICT=y CONFIG_KCSAN_REPORT_ONCE_IN_MS=100000 CONFIG_KCSAN_VERBOSE=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y"; export TORTURE_KCONFIG_KCSAN_ARG
;;
--kmake-arg|--kmake-args)
checkarg --kmake-arg "(kernel make arguments)" $# "$2" '.*' '^error$'