| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20160307155232.60a44030@gandalf.local.home>
Date: Mon, 7 Mar 2016 15:52:32 -0500
From: Steven Rostedt <rostedt@...dmis.org>
To: LKML <linux-kernel@...r.kernel.org>,
linux-rt-users <linux-rt-users@...r.kernel.org>
Cc: Thomas Gleixner <tglx@...utronix.de>,
Carsten Emde <C.Emde@...dl.org>,
John Kacur <jkacur@...hat.com>,
Sebastian Andrzej Siewior <bigeasy@...utronix.de>
Subject: [ANNOUNCE] 3.18.27-rt27
Dear RT Folks,
I'm pleased to announce the 3.18.27-rt27 stable release.
You can get this release via the git tree at:
git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-stable-rt.git
branch: v3.18-rt
Head SHA1: a69d68687e04e6f5e9b79a5ac8dacc9d86f195c7
Or to build 3.18.27-rt27 directly, the following patches should be applied:
http://www.kernel.org/pub/linux/kernel/v3.x/linux-3.18.tar.xz
http://www.kernel.org/pub/linux/kernel/v3.x/patch-3.18.27.xz
http://www.kernel.org/pub/linux/kernel/projects/rt/3.18/patch-3.18.27-rt27.patch.xz
You can also build from 3.18.27-rt26 by applying the incremental patch:
http://www.kernel.org/pub/linux/kernel/projects/rt/3.18/incr/patch-3.18.27-rt26-rt27.patch.xz
Enjoy,
-- Steve
Changes from v3.18.27-rt26:
---
Clark Williams (1):
rcu/torture: Comment out rcu_bh ops on PREEMPT_RT_FULL
Mike Galbraith (4):
sched,rt: __always_inline preemptible_lazy()
drm,radeon,i915: Use preempt_disable/enable_rt() where recommended
drm,i915: Use local_lock/unlock_irq() in intel_pipe_update_start/end()
tracing: Fix probe_wakeup_latency_hist_start() prototype
Sebastian Andrzej Siewior (11):
sched: reset task's lockless wake-queues on fork()
ptrace: don't open IRQs in ptrace_freeze_traced() too early
net: move xmit_recursion to per-task variable on -RT
preempt-lazy: Add the lazy-preemption check to preempt_schedule()
softirq: split timer softirqs out of ksoftirqd
net: provide a way to delegate processing a softirq to ksoftirqd
latencyhist: disable jump-labels
kernel: migrate_disable() do fastpath in atomic & irqs-off
kernel: softirq: unlock with irqs on
kernel/stop_machine: partly revert "stop_machine: Use raw spinlocks"
kernel: sched: Fix preempt_disable_ip recodring for preempt_disable()
Steven Rostedt (Red Hat) (1):
Linux 3.18.27-rt27
Thomas Gleixner (1):
tick/broadcast: Make broadcast hrtimer irqsafe
Yang Shi (3):
arm64: replace read_lock to rcu lock in call_step_hook
trace: Use rcuidle version for preemptoff_hist trace point
f2fs: Mutex can't be used by down_write_nest_lock()
----
arch/Kconfig | 1 +
arch/arm64/kernel/debug-monitors.c | 21 +++---
drivers/gpu/drm/i915/i915_irq.c | 2 +
drivers/gpu/drm/i915/intel_sprite.c | 11 ++--
drivers/gpu/drm/radeon/radeon_display.c | 2 +
fs/f2fs/f2fs.h | 4 +-
include/linux/ftrace.h | 12 ++++
include/linux/interrupt.h | 8 +++
include/linux/netdevice.h | 9 +++
include/linux/sched.h | 3 +-
include/trace/events/hist.h | 1 +
kernel/fork.c | 1 +
kernel/ptrace.c | 6 +-
kernel/rcu/rcutorture.c | 7 ++
kernel/sched/core.c | 52 ++++++++-------
kernel/softirq.c | 112 ++++++++++++++++++++++++++++----
kernel/stop_machine.c | 40 +++---------
kernel/time/tick-broadcast-hrtimer.c | 1 +
kernel/trace/latency_hist.c | 4 +-
kernel/trace/trace_irqsoff.c | 8 +--
localversion-rt | 2 +-
net/core/dev.c | 43 ++++++++++--
22 files changed, 251 insertions(+), 99 deletions(-)
---------------------------
diff --git a/arch/Kconfig b/arch/Kconfig
index 84d340b061a9..efb75aee313a 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -50,6 +50,7 @@ config KPROBES
config JUMP_LABEL
bool "Optimize very unlikely/likely branches"
depends on HAVE_ARCH_JUMP_LABEL
+ depends on (!INTERRUPT_OFF_HIST && !PREEMPT_OFF_HIST && !WAKEUP_LATENCY_HIST && !MISSED_TIMER_OFFSETS_HIST)
help
This option enables a transparent branch optimization that
makes certain almost-always-true or almost-always-false branch
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index b056369fd47d..4c6f340c90fa 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -184,20 +184,21 @@ static void clear_regs_spsr_ss(struct pt_regs *regs)
/* EL1 Single Step Handler hooks */
static LIST_HEAD(step_hook);
-static DEFINE_RWLOCK(step_hook_lock);
+static DEFINE_SPINLOCK(step_hook_lock);
void register_step_hook(struct step_hook *hook)
{
- write_lock(&step_hook_lock);
- list_add(&hook->node, &step_hook);
- write_unlock(&step_hook_lock);
+ spin_lock(&step_hook_lock);
+ list_add_rcu(&hook->node, &step_hook);
+ spin_unlock(&step_hook_lock);
}
void unregister_step_hook(struct step_hook *hook)
{
- write_lock(&step_hook_lock);
- list_del(&hook->node);
- write_unlock(&step_hook_lock);
+ spin_lock(&step_hook_lock);
+ list_del_rcu(&hook->node);
+ spin_unlock(&step_hook_lock);
+ synchronize_rcu();
}
/*
@@ -211,15 +212,15 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr)
struct step_hook *hook;
int retval = DBG_HOOK_ERROR;
- read_lock(&step_hook_lock);
+ rcu_read_lock();
- list_for_each_entry(hook, &step_hook, node) {
+ list_for_each_entry_rcu(hook, &step_hook, node) {
retval = hook->fn(regs, esr);
if (retval == DBG_HOOK_HANDLED)
break;
}
- read_unlock(&step_hook_lock);
+ rcu_read_unlock();
return retval;
}
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 23329b48766f..763e9c004f23 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -943,6 +943,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
/* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */
+ preempt_disable_rt();
/* Get optional system timestamp before query. */
if (stime)
@@ -994,6 +995,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
*etime = ktime_get();
/* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */
+ preempt_enable_rt();
spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 4edebce7f213..c7c118476758 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -36,6 +36,7 @@
#include "intel_drv.h"
#include <drm/i915_drm.h>
#include "i915_drv.h"
+#include <linux/locallock.h>
static int usecs_to_scanlines(const struct drm_display_mode *mode, int usecs)
{
@@ -46,6 +47,8 @@ static int usecs_to_scanlines(const struct drm_display_mode *mode, int usecs)
return DIV_ROUND_UP(usecs * mode->crtc_clock, 1000 * mode->crtc_htotal);
}
+static DEFINE_LOCAL_IRQ_LOCK(pipe_update_lock);
+
static bool intel_pipe_update_start(struct intel_crtc *crtc, uint32_t *start_vbl_count)
{
struct drm_device *dev = crtc->base.dev;
@@ -72,7 +75,7 @@ static bool intel_pipe_update_start(struct intel_crtc *crtc, uint32_t *start_vbl
if (WARN_ON(drm_vblank_get(dev, pipe)))
return false;
- local_irq_disable();
+ local_lock_irq(pipe_update_lock);
trace_i915_pipe_update_start(crtc, min, max);
@@ -94,11 +97,11 @@ static bool intel_pipe_update_start(struct intel_crtc *crtc, uint32_t *start_vbl
break;
}
- local_irq_enable();
+ local_unlock_irq(pipe_update_lock);
timeout = schedule_timeout(timeout);
- local_irq_disable();
+ local_lock_irq(pipe_update_lock);
}
finish_wait(wq, &wait);
@@ -120,7 +123,7 @@ static void intel_pipe_update_end(struct intel_crtc *crtc, u32 start_vbl_count)
trace_i915_pipe_update_end(crtc, end_vbl_count);
- local_irq_enable();
+ local_unlock_irq(pipe_update_lock);
if (start_vbl_count != end_vbl_count)
DRM_ERROR("Atomic update failure on pipe %c (start=%u end=%u)\n",
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 21e6e9745d00..7acf4536c827 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -1784,6 +1784,7 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc, unsigned int fl
struct radeon_device *rdev = dev->dev_private;
/* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */
+ preempt_disable_rt();
/* Get optional system timestamp before query. */
if (stime)
@@ -1876,6 +1877,7 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc, unsigned int fl
*etime = ktime_get();
/* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */
+ preempt_enable_rt();
/* Decode into vertical and horizontal scanout position. */
*vpos = position & 0x1fff;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 8171e80b2ee9..5bb02f8e1f06 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -22,7 +22,6 @@
#ifdef CONFIG_F2FS_CHECK_FS
#define f2fs_bug_on(sbi, condition) BUG_ON(condition)
-#define f2fs_down_write(x, y) down_write_nest_lock(x, y)
#else
#define f2fs_bug_on(sbi, condition) \
do { \
@@ -31,7 +30,6 @@
sbi->need_fsck = true; \
} \
} while (0)
-#define f2fs_down_write(x, y) down_write(x)
#endif
/*
@@ -699,7 +697,7 @@ static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
{
- f2fs_down_write(&sbi->cp_rwsem, &sbi->cp_mutex);
+ down_write(&sbi->cp_rwsem);
}
static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 662697babd48..7bb6024e935e 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -643,6 +643,18 @@ static inline void __ftrace_enabled_restore(int enabled)
#define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5))
#define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6))
+static inline unsigned long get_lock_parent_ip(void)
+{
+ unsigned long addr = CALLER_ADDR0;
+
+ if (!in_lock_functions(addr))
+ return addr;
+ addr = CALLER_ADDR1;
+ if (!in_lock_functions(addr))
+ return addr;
+ return CALLER_ADDR2;
+}
+
#ifdef CONFIG_IRQSOFF_TRACER
extern void time_hardirqs_on(unsigned long a0, unsigned long a1);
extern void time_hardirqs_off(unsigned long a0, unsigned long a1);
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 86628c733be7..ce50b6ebd65d 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -444,6 +444,14 @@ extern void thread_do_softirq(void);
extern void open_softirq(int nr, void (*action)(struct softirq_action *));
extern void softirq_init(void);
extern void __raise_softirq_irqoff(unsigned int nr);
+#ifdef CONFIG_PREEMPT_RT_FULL
+extern void __raise_softirq_irqoff_ksoft(unsigned int nr);
+#else
+static inline void __raise_softirq_irqoff_ksoft(unsigned int nr)
+{
+ __raise_softirq_irqoff(nr);
+}
+#endif
extern void raise_softirq_irqoff(unsigned int nr);
extern void raise_softirq(unsigned int nr);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ff0f50dcea4a..dab2603bcdba 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2130,11 +2130,20 @@ void netdev_freemem(struct net_device *dev);
void synchronize_net(void);
int init_dummy_netdev(struct net_device *dev);
+#ifdef CONFIG_PREEMPT_RT_FULL
+static inline int dev_recursion_level(void)
+{
+ return current->xmit_recursion;
+}
+
+#else
+
DECLARE_PER_CPU(int, xmit_recursion);
static inline int dev_recursion_level(void)
{
return this_cpu_read(xmit_recursion);
}
+#endif
struct net_device *dev_get_by_index(struct net *net, int ifindex);
struct net_device *__dev_get_by_index(struct net *net, int ifindex);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index bdc27dbffbe2..acb9c0a2f15b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -178,8 +178,6 @@ extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
extern void calc_global_load(unsigned long ticks);
extern void update_cpu_load_nohz(void);
-extern unsigned long get_parent_ip(unsigned long addr);
-
extern void dump_cpu_task(int cpu);
struct seq_file;
@@ -1523,6 +1521,7 @@ struct task_struct {
struct mutex_waiter *blocked_on;
#endif
#ifdef CONFIG_PREEMPT_RT_FULL
+ int xmit_recursion;
int pagefault_disabled;
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
diff --git a/include/trace/events/hist.h b/include/trace/events/hist.h
index 6122e4286177..f7710de1b1f3 100644
--- a/include/trace/events/hist.h
+++ b/include/trace/events/hist.h
@@ -9,6 +9,7 @@
#if !defined(CONFIG_PREEMPT_OFF_HIST) && !defined(CONFIG_INTERRUPT_OFF_HIST)
#define trace_preemptirqsoff_hist(a, b)
+#define trace_preemptirqsoff_hist_rcuidle(a, b)
#else
TRACE_EVENT(preemptirqsoff_hist,
diff --git a/kernel/fork.c b/kernel/fork.c
index 3a8ecfb38831..1c4edaf4ec36 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -364,6 +364,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
#endif
tsk->splice_pipe = NULL;
tsk->task_frag.page = NULL;
+ tsk->wake_q.next = NULL;
account_kernel_stack(ti, 1);
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 09d76da725af..ac364db5622b 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -129,12 +129,14 @@ static bool ptrace_freeze_traced(struct task_struct *task)
spin_lock_irq(&task->sighand->siglock);
if (task_is_traced(task) && !__fatal_signal_pending(task)) {
- raw_spin_lock_irq(&task->pi_lock);
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
if (task->state & __TASK_TRACED)
task->state = __TASK_TRACED;
else
task->saved_state = __TASK_TRACED;
- raw_spin_unlock_irq(&task->pi_lock);
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
ret = true;
}
spin_unlock_irq(&task->sighand->siglock);
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 240fa9094f83..ff0f2d5d6267 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -392,6 +392,7 @@ static struct rcu_torture_ops rcu_ops = {
.name = "rcu"
};
+#ifndef CONFIG_PREEMPT_RT_FULL
/*
* Definitions for rcu_bh torture testing.
*/
@@ -435,6 +436,12 @@ static struct rcu_torture_ops rcu_bh_ops = {
.name = "rcu_bh"
};
+#else
+static struct rcu_torture_ops rcu_bh_ops = {
+ .ttype = INVALID_RCU_FLAVOR,
+};
+#endif
+
/*
* Don't even think about trying any of these in real life!!!
* The names includes "busted", and they really means it!
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9e01a8f358f8..ecbc559abf7c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2704,16 +2704,6 @@ u64 scheduler_tick_max_deferment(void)
}
#endif
-notrace unsigned long get_parent_ip(unsigned long addr)
-{
- if (in_lock_functions(addr)) {
- addr = CALLER_ADDR2;
- if (in_lock_functions(addr))
- addr = CALLER_ADDR3;
- }
- return addr;
-}
-
#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
defined(CONFIG_PREEMPT_TRACER))
@@ -2735,7 +2725,7 @@ void preempt_count_add(int val)
PREEMPT_MASK - 10);
#endif
if (preempt_count() == val) {
- unsigned long ip = get_parent_ip(CALLER_ADDR1);
+ unsigned long ip = get_lock_parent_ip();
#ifdef CONFIG_DEBUG_PREEMPT
current->preempt_disable_ip = ip;
#endif
@@ -2762,7 +2752,7 @@ void preempt_count_sub(int val)
#endif
if (preempt_count() == val)
- trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
+ trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip());
__preempt_count_sub(val);
}
EXPORT_SYMBOL(preempt_count_sub);
@@ -2859,7 +2849,7 @@ void migrate_disable(void)
{
struct task_struct *p = current;
- if (in_atomic()) {
+ if (in_atomic() || irqs_disabled()) {
#ifdef CONFIG_SCHED_DEBUG
p->migrate_disable_atomic++;
#endif
@@ -2893,7 +2883,7 @@ void migrate_enable(void)
unsigned long flags;
struct rq *rq;
- if (in_atomic()) {
+ if (in_atomic() || irqs_disabled()) {
#ifdef CONFIG_SCHED_DEBUG
p->migrate_disable_atomic--;
#endif
@@ -3164,6 +3154,30 @@ void __sched schedule_preempt_disabled(void)
preempt_disable();
}
+#ifdef CONFIG_PREEMPT_LAZY
+/*
+ * If TIF_NEED_RESCHED is then we allow to be scheduled away since this is
+ * set by a RT task. Oterwise we try to avoid beeing scheduled out as long as
+ * preempt_lazy_count counter >0.
+ */
+static __always_inline int preemptible_lazy(void)
+{
+ if (test_thread_flag(TIF_NEED_RESCHED))
+ return 1;
+ if (current_thread_info()->preempt_lazy_count)
+ return 0;
+ return 1;
+}
+
+#else
+
+static int preemptible_lazy(void)
+{
+ return 1;
+}
+
+#endif
+
#ifdef CONFIG_PREEMPT
/*
* this is the entry point to schedule() from in-kernel preemption
@@ -3178,15 +3192,9 @@ asmlinkage __visible void __sched notrace preempt_schedule(void)
*/
if (likely(!preemptible()))
return;
-
-#ifdef CONFIG_PREEMPT_LAZY
- /*
- * Check for lazy preemption
- */
- if (current_thread_info()->preempt_lazy_count &&
- !test_thread_flag(TIF_NEED_RESCHED))
+ if (!preemptible_lazy())
return;
-#endif
+
do {
__preempt_count_add(PREEMPT_ACTIVE);
/*
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 3242af874438..89c490b405ad 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -58,6 +58,10 @@ EXPORT_SYMBOL(irq_stat);
static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp;
DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
+#ifdef CONFIG_PREEMPT_RT_FULL
+#define TIMER_SOFTIRQS ((1 << TIMER_SOFTIRQ) | (1 << HRTIMER_SOFTIRQ))
+DEFINE_PER_CPU(struct task_struct *, ktimer_softirqd);
+#endif
const char * const softirq_to_name[NR_SOFTIRQS] = {
"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
@@ -171,6 +175,17 @@ static void wakeup_softirqd(void)
wake_up_process(tsk);
}
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void wakeup_timer_softirqd(void)
+{
+ /* Interrupts are disabled: no need to stop preemption */
+ struct task_struct *tsk = __this_cpu_read(ktimer_softirqd);
+
+ if (tsk && tsk->state != TASK_RUNNING)
+ wake_up_process(tsk);
+}
+#endif
+
static void handle_softirq(unsigned int vec_nr)
{
struct softirq_action *h = softirq_vec + vec_nr;
@@ -276,7 +291,7 @@ void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
raw_local_irq_restore(flags);
if (preempt_count() == cnt)
- trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
+ trace_preempt_off(CALLER_ADDR0, get_lock_parent_ip());
}
EXPORT_SYMBOL(__local_bh_disable_ip);
#endif /* CONFIG_TRACE_IRQFLAGS */
@@ -474,7 +489,6 @@ void __raise_softirq_irqoff(unsigned int nr)
static inline void local_bh_disable_nort(void) { local_bh_disable(); }
static inline void _local_bh_enable_nort(void) { _local_bh_enable(); }
static void ksoftirqd_set_sched_params(unsigned int cpu) { }
-static void ksoftirqd_clr_sched_params(unsigned int cpu, bool online) { }
#else /* !PREEMPT_RT_FULL */
@@ -550,8 +564,10 @@ static void do_current_softirqs(int need_rcu_bh_qs)
do_single_softirq(i, need_rcu_bh_qs);
}
softirq_clr_runner(i);
- unlock_softirq(i);
WARN_ON(current->softirq_nestcnt != 1);
+ local_irq_enable();
+ unlock_softirq(i);
+ local_irq_disable();
}
}
@@ -649,8 +665,12 @@ void thread_do_softirq(void)
static void do_raise_softirq_irqoff(unsigned int nr)
{
+ unsigned int mask;
+
+ mask = 1UL << nr;
+
trace_softirq_raise(nr);
- or_softirq_pending(1UL << nr);
+ or_softirq_pending(mask);
/*
* If we are not in a hard interrupt and inside a bh disabled
@@ -659,16 +679,51 @@ static void do_raise_softirq_irqoff(unsigned int nr)
* delegate it to ksoftirqd.
*/
if (!in_irq() && current->softirq_nestcnt)
- current->softirqs_raised |= (1U << nr);
- else if (__this_cpu_read(ksoftirqd))
- __this_cpu_read(ksoftirqd)->softirqs_raised |= (1U << nr);
+ current->softirqs_raised |= mask;
+ else if (!__this_cpu_read(ksoftirqd) || !__this_cpu_read(ktimer_softirqd))
+ return;
+
+ if (mask & TIMER_SOFTIRQS)
+ __this_cpu_read(ktimer_softirqd)->softirqs_raised |= mask;
+ else
+ __this_cpu_read(ksoftirqd)->softirqs_raised |= mask;
}
+static void wakeup_proper_softirq(unsigned int nr)
+{
+ if ((1UL << nr) & TIMER_SOFTIRQS)
+ wakeup_timer_softirqd();
+ else
+ wakeup_softirqd();
+}
+
+
void __raise_softirq_irqoff(unsigned int nr)
{
do_raise_softirq_irqoff(nr);
if (!in_irq() && !current->softirq_nestcnt)
- wakeup_softirqd();
+ wakeup_proper_softirq(nr);
+}
+
+/*
+ * Same as __raise_softirq_irqoff() but will process them in ksoftirqd
+ */
+void __raise_softirq_irqoff_ksoft(unsigned int nr)
+{
+ unsigned int mask;
+
+ if (WARN_ON_ONCE(!__this_cpu_read(ksoftirqd) ||
+ !__this_cpu_read(ktimer_softirqd)))
+ return;
+ mask = 1UL << nr;
+
+ trace_softirq_raise(nr);
+ or_softirq_pending(mask);
+ if (mask & TIMER_SOFTIRQS)
+ __this_cpu_read(ktimer_softirqd)->softirqs_raised |= mask;
+ else
+ __this_cpu_read(ksoftirqd)->softirqs_raised |= mask;
+ wakeup_proper_softirq(nr);
}
/*
@@ -694,7 +749,7 @@ void raise_softirq_irqoff(unsigned int nr)
* raise a WARN() if the condition is met.
*/
if (!current->softirq_nestcnt)
- wakeup_softirqd();
+ wakeup_proper_softirq(nr);
}
static inline int ksoftirqd_softirq_pending(void)
@@ -707,22 +762,37 @@ static inline void _local_bh_enable_nort(void) { }
static inline void ksoftirqd_set_sched_params(unsigned int cpu)
{
+ /* Take over all but timer pending softirqs when starting */
+ local_irq_disable();
+ current->softirqs_raised = local_softirq_pending() & ~TIMER_SOFTIRQS;
+ local_irq_enable();
+}
+
+static inline void ktimer_softirqd_set_sched_params(unsigned int cpu)
+{
struct sched_param param = { .sched_priority = 1 };
sched_setscheduler(current, SCHED_FIFO, ¶m);
- /* Take over all pending softirqs when starting */
+
+ /* Take over timer pending softirqs when starting */
local_irq_disable();
- current->softirqs_raised = local_softirq_pending();
+ current->softirqs_raised = local_softirq_pending() & TIMER_SOFTIRQS;
local_irq_enable();
}
-static inline void ksoftirqd_clr_sched_params(unsigned int cpu, bool online)
+static inline void ktimer_softirqd_clr_sched_params(unsigned int cpu,
+ bool online)
{
struct sched_param param = { .sched_priority = 0 };
sched_setscheduler(current, SCHED_NORMAL, ¶m);
}
+static int ktimer_softirqd_should_run(unsigned int cpu)
+{
+ return current->softirqs_raised;
+}
+
#endif /* PREEMPT_RT_FULL */
/*
* Enter an interrupt context.
@@ -772,6 +842,9 @@ static inline void invoke_softirq(void)
if (__this_cpu_read(ksoftirqd) &&
__this_cpu_read(ksoftirqd)->softirqs_raised)
wakeup_softirqd();
+ if (__this_cpu_read(ktimer_softirqd) &&
+ __this_cpu_read(ktimer_softirqd)->softirqs_raised)
+ wakeup_timer_softirqd();
local_irq_restore(flags);
#endif
}
@@ -1209,17 +1282,30 @@ static struct notifier_block cpu_nfb = {
static struct smp_hotplug_thread softirq_threads = {
.store = &ksoftirqd,
.setup = ksoftirqd_set_sched_params,
- .cleanup = ksoftirqd_clr_sched_params,
.thread_should_run = ksoftirqd_should_run,
.thread_fn = run_ksoftirqd,
.thread_comm = "ksoftirqd/%u",
};
+#ifdef CONFIG_PREEMPT_RT_FULL
+static struct smp_hotplug_thread softirq_timer_threads = {
+ .store = &ktimer_softirqd,
+ .setup = ktimer_softirqd_set_sched_params,
+ .cleanup = ktimer_softirqd_clr_sched_params,
+ .thread_should_run = ktimer_softirqd_should_run,
+ .thread_fn = run_ksoftirqd,
+ .thread_comm = "ktimersoftd/%u",
+};
+#endif
+
static __init int spawn_ksoftirqd(void)
{
register_cpu_notifier(&cpu_nfb);
BUG_ON(smpboot_register_percpu_thread(&softirq_threads));
+#ifdef CONFIG_PREEMPT_RT_FULL
+ BUG_ON(smpboot_register_percpu_thread(&softirq_timer_threads));
+#endif
return 0;
}
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 1af29ad20970..d3ea2452e291 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -30,7 +30,7 @@ struct cpu_stop_done {
atomic_t nr_todo; /* nr left to execute */
bool executed; /* actually executed? */
int ret; /* collected return value */
- struct task_struct *waiter; /* woken when nr_todo reaches 0 */
+ struct completion completion; /* fired if nr_todo reaches 0 */
};
/* the actual stopper, one per every possible cpu, enabled on online cpus */
@@ -56,7 +56,7 @@ static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo)
{
memset(done, 0, sizeof(*done));
atomic_set(&done->nr_todo, nr_todo);
- done->waiter = current;
+ init_completion(&done->completion);
}
/* signal completion unless @done is NULL */
@@ -65,10 +65,8 @@ static void cpu_stop_signal_done(struct cpu_stop_done *done, bool executed)
if (done) {
if (executed)
done->executed = true;
- if (atomic_dec_and_test(&done->nr_todo)) {
- wake_up_process(done->waiter);
- done->waiter = NULL;
- }
+ if (atomic_dec_and_test(&done->nr_todo))
+ complete(&done->completion);
}
}
@@ -91,22 +89,6 @@ static void cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
raw_spin_unlock_irqrestore(&stopper->lock, flags);
}
-static void wait_for_stop_done(struct cpu_stop_done *done)
-{
- set_current_state(TASK_UNINTERRUPTIBLE);
- while (atomic_read(&done->nr_todo)) {
- schedule();
- set_current_state(TASK_UNINTERRUPTIBLE);
- }
- /*
- * We need to wait until cpu_stop_signal_done() has cleared
- * done->waiter.
- */
- while (done->waiter)
- cpu_relax();
- set_current_state(TASK_RUNNING);
-}
-
/**
* stop_one_cpu - stop a cpu
* @cpu: cpu to stop
@@ -138,7 +120,7 @@ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
cpu_stop_init_done(&done, 1);
cpu_stop_queue_work(cpu, &work);
- wait_for_stop_done(&done);
+ wait_for_completion(&done.completion);
return done.executed ? done.ret : -ENOENT;
}
@@ -315,7 +297,7 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
lg_local_unlock(&stop_cpus_lock);
preempt_enable_nort();
- wait_for_stop_done(&done);
+ wait_for_completion(&done.completion);
return done.executed ? done.ret : -ENOENT;
}
@@ -380,7 +362,7 @@ static int __stop_cpus(const struct cpumask *cpumask,
cpu_stop_init_done(&done, cpumask_weight(cpumask));
queue_stop_cpus_work(cpumask, fn, arg, &done, false);
- wait_for_stop_done(&done);
+ wait_for_completion(&done.completion);
return done.executed ? done.ret : -ENOENT;
}
@@ -511,13 +493,7 @@ repeat:
kallsyms_lookup((unsigned long)fn, NULL, NULL, NULL,
ksym_buf), arg);
- /*
- * Make sure that the wakeup and setting done->waiter
- * to NULL is atomic.
- */
- local_irq_disable();
cpu_stop_signal_done(done, true);
- local_irq_enable();
goto repeat;
}
}
@@ -676,7 +652,7 @@ int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data,
ret = multi_cpu_stop(&msdata);
/* Busy wait for completion. */
- while (atomic_read(&done.nr_todo))
+ while (!completion_done(&done.completion))
cpu_relax();
mutex_unlock(&stop_cpus_mutex);
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index 6aac4beedbbe..943c03395e46 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -109,5 +109,6 @@ void tick_setup_hrtimer_broadcast(void)
{
hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
bctimer.function = bc_handler;
+ bctimer.irqsafe = true;
clockevents_register_device(&ce_broadcast_hrtimer);
}
diff --git a/kernel/trace/latency_hist.c b/kernel/trace/latency_hist.c
index 66a69eb5329c..b6c1d14b71c4 100644
--- a/kernel/trace/latency_hist.c
+++ b/kernel/trace/latency_hist.c
@@ -115,7 +115,7 @@ static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist_sharedprio);
static char *wakeup_latency_hist_dir = "wakeup";
static char *wakeup_latency_hist_dir_sharedprio = "sharedprio";
static notrace void probe_wakeup_latency_hist_start(void *v,
- struct task_struct *p, int success);
+ struct task_struct *p);
static notrace void probe_wakeup_latency_hist_stop(void *v,
struct task_struct *prev, struct task_struct *next);
static notrace void probe_sched_migrate_task(void *,
@@ -869,7 +869,7 @@ static notrace void probe_sched_migrate_task(void *v, struct task_struct *task,
}
static notrace void probe_wakeup_latency_hist_start(void *v,
- struct task_struct *p, int success)
+ struct task_struct *p)
{
unsigned long flags;
struct task_struct *curr = current;
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index de4f1a812c41..d1940b095d85 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -436,13 +436,13 @@ void start_critical_timings(void)
{
if (preempt_trace() || irq_trace())
start_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
- trace_preemptirqsoff_hist(TRACE_START, 1);
+ trace_preemptirqsoff_hist_rcuidle(TRACE_START, 1);
}
EXPORT_SYMBOL_GPL(start_critical_timings);
void stop_critical_timings(void)
{
- trace_preemptirqsoff_hist(TRACE_STOP, 0);
+ trace_preemptirqsoff_hist_rcuidle(TRACE_STOP, 0);
if (preempt_trace() || irq_trace())
stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
}
@@ -487,7 +487,7 @@ inline void print_irqtrace_events(struct task_struct *curr)
*/
void trace_hardirqs_on(void)
{
- trace_preemptirqsoff_hist(IRQS_ON, 0);
+ trace_preemptirqsoff_hist_rcuidle(IRQS_ON, 0);
if (!preempt_trace() && irq_trace())
stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
}
@@ -497,7 +497,7 @@ void trace_hardirqs_off(void)
{
if (!preempt_trace() && irq_trace())
start_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
- trace_preemptirqsoff_hist(IRQS_OFF, 1);
+ trace_preemptirqsoff_hist_rcuidle(IRQS_OFF, 1);
}
EXPORT_SYMBOL(trace_hardirqs_off);
diff --git a/localversion-rt b/localversion-rt
index 2e9afd4a0afd..be1e37b64ad0 100644
--- a/localversion-rt
+++ b/localversion-rt
@@ -1 +1 @@
--rt26
+-rt27
diff --git a/net/core/dev.c b/net/core/dev.c
index 39d2a0ba38ed..da674bb38606 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2861,9 +2861,44 @@ static void skb_update_prio(struct sk_buff *skb)
#define skb_update_prio(skb)
#endif
+#ifdef CONFIG_PREEMPT_RT_FULL
+
+static inline int xmit_rec_read(void)
+{
+ return current->xmit_recursion;
+}
+
+static inline void xmit_rec_inc(void)
+{
+ current->xmit_recursion++;
+}
+
+static inline void xmit_rec_dec(void)
+{
+ current->xmit_recursion--;
+}
+
+#else
+
DEFINE_PER_CPU(int, xmit_recursion);
EXPORT_SYMBOL(xmit_recursion);
+static inline int xmit_rec_read(void)
+{
+ return __this_cpu_read(xmit_recursion);
+}
+
+static inline void xmit_rec_inc(void)
+{
+ __this_cpu_inc(xmit_recursion);
+}
+
+static inline int xmit_rec_dec(void)
+{
+ __this_cpu_dec(xmit_recursion);
+}
+#endif
+
#define RECURSION_LIMIT 10
/**
@@ -2965,7 +3000,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
if (txq->xmit_lock_owner != cpu) {
- if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT)
+ if (xmit_rec_read() > RECURSION_LIMIT)
goto recursion_alert;
skb = validate_xmit_skb(skb, dev);
@@ -2975,9 +3010,9 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
HARD_TX_LOCK(dev, txq, cpu);
if (!netif_xmit_stopped(txq)) {
- __this_cpu_inc(xmit_recursion);
+ xmit_rec_inc();
skb = dev_hard_start_xmit(skb, dev, txq, &rc);
- __this_cpu_dec(xmit_recursion);
+ xmit_rec_dec();
if (dev_xmit_complete(rc)) {
HARD_TX_UNLOCK(dev, txq);
goto out;
@@ -4644,7 +4679,7 @@ out:
softnet_break:
sd->time_squeeze++;
- __raise_softirq_irqoff(NET_RX_SOFTIRQ);
+ __raise_softirq_irqoff_ksoft(NET_RX_SOFTIRQ);
goto out;
}
Powered by blists - more mailing lists