debian-packaging
/
linux
8
0
Fork 0
Code Releases Activity

[rt] Update to 4.16.15-rt7

This commit is contained in:
Bastian Blank 2018-06-19 15:28:34 +02:00
parent 560930a22f
commit ac887964a0
526 changed files with 595 additions and 23464 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
debian/changelog vendored
View File

@ -435,6 +435,7 @@ linux (4.16.16-1) UNRELEASED; urgency=medium
[ Bastian Blank ]
* hv_netvsc: Fix a network regression after ifdown/ifup
* [rt] Update to 4.16.15-rt7.
[ Vagrant Cascadian ]
* [arm64] Enable configuration options used in Firefly-RK3399:

2
debian/config/defines vendored
View File

@ -113,7 +113,7 @@ debug-info: true
signed-code: false
[featureset-rt_base]
enabled: false
enabled: true
[description]
part-long-up: This kernel is not suitable for SMP (multi-processor,

1
debian/patches/features/all/rt/0001-ARM-at91-add-TCB-registers-definitions.patch vendored
View File

@ -1,7 +1,6 @@
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Wed, 18 Apr 2018 12:51:38 +0200
Subject: [PATCH 1/6] ARM: at91: add TCB registers definitions
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Add registers and bits definitions for the timer counter blocks found on
Atmel ARM SoCs.

49
debian/patches/features/all/rt/suspend-prevernt-might-sleep-splats.patch → debian/patches/features/all/rt/0001-PM-suspend-Prevent-might-sleep-splats.patch vendored
View File

@ -1,28 +1,35 @@
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 15 Jul 2010 10:29:00 +0200
Subject: suspend: Prevent might sleep splats
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Subject: [PATCH 1/4] PM / suspend: Prevent might sleep splats
timekeeping suspend/resume calls read_persistant_clock() which takes
timekeeping suspend/resume calls read_persistent_clock() which takes
rtc_lock. That results in might sleep warnings because at that point
we run with interrupts disabled.
We cannot convert rtc_lock to a raw spinlock as that would trigger
other might sleep warnings.
As a temporary workaround we disable the might sleep warnings by
setting system_state to SYSTEM_SUSPEND before calling sysdev_suspend()
and restoring it to SYSTEM_RUNNING afer sysdev_resume().
As a workaround we disable the might sleep warnings by setting
system_state to SYSTEM_SUSPEND before calling sysdev_suspend() and
restoring it to SYSTEM_RUNNING afer sysdev_resume(). There is no lock
contention because hibernate / suspend to RAM is single-CPU at this
point.
Needs to be revisited.
In s2idle's case the system_state is set to SYSTEM_SUSPEND before
timekeeping_suspend() which is invoked by the last CPU. In the resume
case it set back to SYSTEM_RUNNING after timekeeping_resume() which is
invoked by the first CPU in the resume case. The other CPUs will block
on tick_freeze_lock.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
[bigeasy: cover s2idle]
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/linux/kernel.h | 1 +
kernel/power/hibernate.c | 7 +++++++
kernel/power/suspend.c | 4 ++++
3 files changed, 12 insertions(+)
include/linux/kernel.h | 1 +
kernel/power/hibernate.c | 7 +++++++
kernel/power/suspend.c | 4 ++++
kernel/time/tick-common.c | 2 ++
4 files changed, 14 insertions(+)
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@ -105,3 +112,21 @@ Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
arch_suspend_enable_irqs();
BUG_ON(irqs_disabled());
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -490,6 +490,7 @@ void tick_freeze(void)
if (tick_freeze_depth == num_online_cpus()) {
trace_suspend_resume(TPS("timekeeping_freeze"),
smp_processor_id(), true);
+ system_state = SYSTEM_SUSPEND;
timekeeping_suspend();
} else {
tick_suspend_local();
@@ -513,6 +514,7 @@ void tick_unfreeze(void)
if (tick_freeze_depth == num_online_cpus()) {
timekeeping_resume();
+ system_state = SYSTEM_RUNNING;
trace_suspend_resume(TPS("timekeeping_freeze"),
smp_processor_id(), false);
} else {

9
debian/patches/features/all/rt/0001-bdi-use-refcount_t-for-reference-counting-instead-at.patch vendored
View File

@ -1,7 +1,6 @@
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 7 May 2018 16:51:09 +0200
Subject: [PATCH] bdi: use refcount_t for reference counting instead atomic_t
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
refcount_t type and corresponding API should be used instead of atomic_t when
the variable is used as a reference counter. This allows to avoid accidental
@ -54,7 +53,7 @@ Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -460,10 +460,10 @@ wb_congested_get_create(struct backing_d
@@ -461,10 +461,10 @@ wb_congested_get_create(struct backing_d
if (new_congested) {
/* !found and storage for new one already allocated, insert */
congested = new_congested;
@ -67,7 +66,7 @@ Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
}
spin_unlock_irqrestore(&cgwb_lock, flags);
@@ -473,13 +473,13 @@ wb_congested_get_create(struct backing_d
@@ -474,13 +474,13 @@ wb_congested_get_create(struct backing_d
if (!new_congested)
return NULL;
@ -83,7 +82,7 @@ Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
spin_unlock_irqrestore(&cgwb_lock, flags);
kfree(new_congested);
return congested;
@@ -496,7 +496,7 @@ void wb_congested_put(struct bdi_writeba
@@ -497,7 +497,7 @@ void wb_congested_put(struct bdi_writeba
unsigned long flags;
local_irq_save(flags);
@ -92,7 +91,7 @@ Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
local_irq_restore(flags);
return;
}
@@ -806,7 +806,7 @@ static int cgwb_bdi_init(struct backing_
@@ -807,7 +807,7 @@ static int cgwb_bdi_init(struct backing_
if (!bdi->wb_congested)
return -ENOMEM;

1
debian/patches/features/all/rt/0001-get-rid-of-trylock-loop-in-locking-dentries-on-shrin.patch vendored
View File

@ -2,7 +2,6 @@ From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 23 Feb 2018 21:54:18 -0500
Subject: [PATCH 01/17] get rid of trylock loop in locking dentries on shrink
list
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit 3b3f09f48ba78c0634e929849860a6447d057eed

1
debian/patches/features/all/rt/0001-iommu-amd-Use-raw-locks-on-atomic-context-paths.patch vendored
View File

@ -1,7 +1,6 @@
From: Scott Wood <swood@redhat.com>
Date: Sun, 21 Jan 2018 03:28:54 -0600
Subject: [PATCH 1/3] iommu/amd: Use raw locks on atomic context paths
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit 27790398c2aed917828dc3c6f81240d57f1584c9

57
debian/patches/features/all/rt/0001-spinlock-atomic_dec_and_lock-Add-an-irqsave-variant.patch vendored Normal file
View File

@ -0,0 +1,57 @@
From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Fri, 4 May 2018 17:45:29 +0200
Subject: [PATCH 1/3] spinlock: atomic_dec_and_lock: Add an irqsave variant
There are in-tree users of atomic_dec_and_lock() which must acquire the
spin lock with interrupts disabled. To workaround the lack of an irqsave
variant of atomic_dec_and_lock() they use local_irq_save() at the call
site. This causes extra code and creates in some places unneeded long
interrupt disabled times. These places need also extra treatment for
PREEMPT_RT due to the disconnect of the irq disabling and the lock
function.
Implement the missing irqsave variant of the function.
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/linux/spinlock.h | 5 +++++
lib/dec_and_lock.c | 16 ++++++++++++++++
2 files changed, 21 insertions(+)
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -409,6 +409,11 @@ extern int _atomic_dec_and_lock(atomic_t
#define atomic_dec_and_lock(atomic, lock) \
__cond_lock(lock, _atomic_dec_and_lock(atomic, lock))
+extern int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock,
+ unsigned long *flags);
+#define atomic_dec_and_lock_irqsave(atomic, lock, flags) \
+ __cond_lock(lock, _atomic_dec_and_lock_irqsave(atomic, lock, &(flags)))
+
int alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask,
size_t max_size, unsigned int cpu_mult,
gfp_t gfp);
--- a/lib/dec_and_lock.c
+++ b/lib/dec_and_lock.c
@@ -33,3 +33,19 @@ int _atomic_dec_and_lock(atomic_t *atomi
}
EXPORT_SYMBOL(_atomic_dec_and_lock);
+
+int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock,
+ unsigned long *flags)
+{
+ /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
+ if (atomic_add_unless(atomic, -1, 1))
+ return 0;
+
+ /* Otherwise do it the slow way */
+ spin_lock_irqsave(lock, *flags);
+ if (atomic_dec_and_test(atomic))
+ return 1;
+ spin_unlock_irqrestore(lock, *flags);
+ return 0;
+}
+EXPORT_SYMBOL(_atomic_dec_and_lock_irqsave);

273
debian/patches/features/all/rt/0001-timers-Use-static-keys-for-migrate_enable-nohz_activ.patch vendored
View File

@ -1,273 +0,0 @@
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 20 Dec 2017 17:12:50 +0100
Subject: [PATCH 01/29] timers: Use static keys for migrate_enable/nohz_active
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
The members migrate_enable and nohz_active in the timer/hrtimer per CPU
bases have been introduced to avoid accessing global variables for these
decisions.
Still that results in a (cache hot) load and conditional branch, which can
be avoided by using static keys.
Implement it with static keys and optimize for the most critical case of
high performance networking which tends to disable the timer migration
functionality.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/linux/hrtimer.h | 4 --
kernel/time/hrtimer.c | 17 ++-------
kernel/time/tick-internal.h | 19 ++++++----
kernel/time/tick-sched.c | 2 -
kernel/time/timer.c | 83 ++++++++++++++++++++++----------------------
5 files changed, 61 insertions(+), 64 deletions(-)
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -153,8 +153,6 @@ enum hrtimer_base_type {
* @cpu: cpu number
* @active_bases: Bitfield to mark bases with active timers
* @clock_was_set_seq: Sequence counter of clock was set events
- * @migration_enabled: The migration of hrtimers to other cpus is enabled
- * @nohz_active: The nohz functionality is enabled
* @expires_next: absolute time of the next event which was scheduled
* via clock_set_next_event()
* @next_timer: Pointer to the first expiring timer
@@ -178,8 +176,6 @@ struct hrtimer_cpu_base {
unsigned int cpu;
unsigned int active_bases;
unsigned int clock_was_set_seq;
- bool migration_enabled;
- bool nohz_active;
#ifdef CONFIG_HIGH_RES_TIMERS
unsigned int in_hrtirq : 1,
hres_active : 1,
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -178,23 +178,16 @@ hrtimer_check_target(struct hrtimer *tim
#endif
}
-#ifdef CONFIG_NO_HZ_COMMON
-static inline
-struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
- int pinned)
-{
- if (pinned || !base->migration_enabled)
- return base;
- return &per_cpu(hrtimer_bases, get_nohz_timer_target());
-}
-#else
static inline
struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
int pinned)
{
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+ if (static_branch_unlikely(&timers_migration_enabled) && !pinned)
+ return &per_cpu(hrtimer_bases, get_nohz_timer_target());
+#endif
return base;
}
-#endif
/*
* We switch the timer base to a power-optimized selected CPU target,
@@ -971,7 +964,7 @@ void hrtimer_start_range_ns(struct hrtim
* Kick to reschedule the next tick to handle the new timer
* on dynticks target.
*/
- if (new_base->cpu_base->nohz_active)
+ if (is_timers_nohz_active())
wake_up_nohz_cpu(new_base->cpu_base->cpu);
} else {
hrtimer_reprogram(timer, new_base);
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -150,14 +150,19 @@ static inline void tick_nohz_init(void)
#ifdef CONFIG_NO_HZ_COMMON
extern unsigned long tick_nohz_active;
-#else
+extern void timers_update_nohz(void);
+extern struct static_key_false timers_nohz_active;
+static inline bool is_timers_nohz_active(void)
+{
+ return static_branch_unlikely(&timers_nohz_active);
+}
+# ifdef CONFIG_SMP
+extern struct static_key_false timers_migration_enabled;
+# endif
+#else /* CONFIG_NO_HZ_COMMON */
+static inline void timers_update_nohz(void) { }
#define tick_nohz_active (0)
-#endif
-
-#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
-extern void timers_update_migration(bool update_nohz);
-#else
-static inline void timers_update_migration(bool update_nohz) { }
+static inline bool is_timers_nohz_active(void) { return false; }
#endif
DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases);
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1131,7 +1131,7 @@ static inline void tick_nohz_activate(st
ts->nohz_mode = mode;
/* One update is enough */
if (!test_and_set_bit(0, &tick_nohz_active))
- timers_update_migration(true);
+ timers_update_nohz();
}
/**
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -200,8 +200,6 @@ struct timer_base {
unsigned long clk;
unsigned long next_expiry;
unsigned int cpu;
- bool migration_enabled;
- bool nohz_active;
bool is_idle;
bool must_forward_clk;
DECLARE_BITMAP(pending_map, WHEEL_SIZE);
@@ -210,45 +208,59 @@ struct timer_base {
static DEFINE_PER_CPU(struct timer_base, timer_bases[NR_BASES]);
-#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+#ifdef CONFIG_NO_HZ_COMMON
+
+DEFINE_STATIC_KEY_FALSE(timers_nohz_active);
+static DEFINE_MUTEX(timer_keys_mutex);
+
+static void timer_update_keys(struct work_struct *work);
+static DECLARE_WORK(timer_update_work, timer_update_keys);
+
+#ifdef CONFIG_SMP
unsigned int sysctl_timer_migration = 1;
-void timers_update_migration(bool update_nohz)
+DEFINE_STATIC_KEY_FALSE(timers_migration_enabled);
+
+static void timers_update_migration(void)
{
bool on = sysctl_timer_migration && tick_nohz_active;
- unsigned int cpu;
- /* Avoid the loop, if nothing to update */
- if (this_cpu_read(timer_bases[BASE_STD].migration_enabled) == on)
- return;
+ if (on)
+ static_branch_enable(&timers_migration_enabled);
+ else
+ static_branch_disable(&timers_migration_enabled);
+}
+#else
+static inline void timers_update_migration(void) { }
+#endif /* !CONFIG_SMP */
- for_each_possible_cpu(cpu) {
- per_cpu(timer_bases[BASE_STD].migration_enabled, cpu) = on;
- per_cpu(timer_bases[BASE_DEF].migration_enabled, cpu) = on;
- per_cpu(hrtimer_bases.migration_enabled, cpu) = on;
- if (!update_nohz)
- continue;
- per_cpu(timer_bases[BASE_STD].nohz_active, cpu) = true;
- per_cpu(timer_bases[BASE_DEF].nohz_active, cpu) = true;
- per_cpu(hrtimer_bases.nohz_active, cpu) = true;
- }
+static void timer_update_keys(struct work_struct *work)
+{
+ mutex_lock(&timer_keys_mutex);
+ timers_update_migration();
+ static_branch_enable(&timers_nohz_active);
+ mutex_unlock(&timer_keys_mutex);
+}
+
+void timers_update_nohz(void)
+{
+ schedule_work(&timer_update_work);
}
int timer_migration_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
- static DEFINE_MUTEX(mutex);
int ret;
- mutex_lock(&mutex);
+ mutex_lock(&timer_keys_mutex);
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (!ret && write)
- timers_update_migration(false);
- mutex_unlock(&mutex);
+ timers_update_migration();
+ mutex_unlock(&timer_keys_mutex);
return ret;
}
-#endif
+#endif /* NO_HZ_COMMON */
static unsigned long round_jiffies_common(unsigned long j, int cpu,
bool force_up)
@@ -534,7 +546,7 @@ static void
static void
trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
{
- if (!IS_ENABLED(CONFIG_NO_HZ_COMMON) || !base->nohz_active)
+ if (!is_timers_nohz_active())
return;
/*
@@ -840,21 +852,20 @@ static inline struct timer_base *get_tim
return get_timer_cpu_base(tflags, tflags & TIMER_CPUMASK);
}
-#ifdef CONFIG_NO_HZ_COMMON
static inline struct timer_base *
get_target_base(struct timer_base *base, unsigned tflags)
{
-#ifdef CONFIG_SMP
- if ((tflags & TIMER_PINNED) || !base->migration_enabled)
- return get_timer_this_cpu_base(tflags);
- return get_timer_cpu_base(tflags, get_nohz_timer_target());
-#else
- return get_timer_this_cpu_base(tflags);
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+ if (static_branch_unlikely(&timers_migration_enabled) &&
+ !(tflags & TIMER_PINNED))
+ return get_timer_cpu_base(tflags, get_nohz_timer_target());
#endif
+ return get_timer_this_cpu_base(tflags);
}
static inline void forward_timer_base(struct timer_base *base)
{
+#ifdef CONFIG_NO_HZ_COMMON
unsigned long jnow;
/*
@@ -878,16 +889,8 @@ static inline void forward_timer_base(st
base->clk = jnow;
else
base->clk = base->next_expiry;
-}
-#else
-static inline struct timer_base *
-get_target_base(struct timer_base *base, unsigned tflags)
-{
- return get_timer_this_cpu_base(tflags);
-}
-
-static inline void forward_timer_base(struct timer_base *base) { }
#endif
+}
/*

1
debian/patches/features/all/rt/0001-tracing-Add-field-modifier-parsing-hist-error-for-hi.patch vendored
View File

@ -2,7 +2,6 @@ From: Steven Rostedt <rostedt@goodmis.org>
Date: Wed, 16 May 2018 09:36:43 -0400
Subject: [PATCH 1/5] tracing: Add field modifier parsing hist error for hist
triggers
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
From: Tom Zanussi <tom.zanussi@linux.intel.com>

3142
debian/patches/features/all/rt/0001-tracing-Move-hist-trigger-Documentation-to-histogram.patch vendored
View File

File diff suppressed because it is too large Load Diff

128
debian/patches/features/all/rt/0001-tracing-Steve-s-unofficial-trace_recursive_lock-patc.patch vendored
View File

@ -1,128 +0,0 @@
From: Steven Rostedt <rostedt@goodmis.org>
Date: Fri, 22 Sep 2017 14:58:15 -0500
Subject: [PATCH 01/42] tracing: Steve's unofficial trace_recursive_lock()
patch
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
On Tue, 5 Sep 2017 16:57:52 -0500
Tom Zanussi <tom.zanussi@linux.intel.com> wrote:
> Synthetic event generation requires the reservation of a second event
> while the reservation of a previous event is still in progress. The
> trace_recursive_lock() check in ring_buffer_lock_reserve() prevents
> this however.
>
> This sets up a special reserve pathway for this particular case,
> leaving existing pathways untouched, other than an additional check in
> ring_buffer_lock_reserve() and trace_event_buffer_reserve(). These
> checks could be gotten rid of as well, with copies of those functions,
> but for now try to avoid that unless necessary.
>
> Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
I've been planing on changing that lock, which may help you here
without having to mess around with parameters. That is to simply add a
counter. Would this patch help you. You can add a patch to increment
the count to 5 with an explanation of handling synthetic events, but
even getting to 4 is extremely unlikely.
I'll make this into an official patch if this works for you, and then
you can include it in your series.
-- Steve
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/trace/ring_buffer.c | 66 ++++++++++++---------------------------------
1 file changed, 18 insertions(+), 48 deletions(-)
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2542,61 +2542,29 @@ rb_wakeups(struct ring_buffer *buffer, s
* The lock and unlock are done within a preempt disable section.
* The current_context per_cpu variable can only be modified
* by the current task between lock and unlock. But it can
- * be modified more than once via an interrupt. To pass this
- * information from the lock to the unlock without having to
- * access the 'in_interrupt()' functions again (which do show
- * a bit of overhead in something as critical as function tracing,
- * we use a bitmask trick.
+ * be modified more than once via an interrupt. There are four
+ * different contexts that we need to consider.
*
- * bit 0 = NMI context
- * bit 1 = IRQ context
- * bit 2 = SoftIRQ context
- * bit 3 = normal context.
- *
- * This works because this is the order of contexts that can
- * preempt other contexts. A SoftIRQ never preempts an IRQ
- * context.
- *
- * When the context is determined, the corresponding bit is
- * checked and set (if it was set, then a recursion of that context
- * happened).
- *
- * On unlock, we need to clear this bit. To do so, just subtract
- * 1 from the current_context and AND it to itself.
- *
- * (binary)
- * 101 - 1 = 100
- * 101 & 100 = 100 (clearing bit zero)
- *
- * 1010 - 1 = 1001
- * 1010 & 1001 = 1000 (clearing bit 1)
- *
- * The least significant bit can be cleared this way, and it
- * just so happens that it is the same bit corresponding to
- * the current context.
+ * Normal context.
+ * SoftIRQ context
+ * IRQ context
+ * NMI context
+ *
+ * If for some reason the ring buffer starts to recurse, we
+ * only allow that to happen at most 4 times (one for each
+ * context). If it happens 5 times, then we consider this a
+ * recusive loop and do not let it go further.
*/
static __always_inline int
trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
{
- unsigned int val = cpu_buffer->current_context;
- int bit;
-
- if (in_interrupt()) {
- if (in_nmi())
- bit = RB_CTX_NMI;
- else if (in_irq())
- bit = RB_CTX_IRQ;
- else
- bit = RB_CTX_SOFTIRQ;
- } else
- bit = RB_CTX_NORMAL;
-
- if (unlikely(val & (1 << bit)))
+ if (cpu_buffer->current_context >= 4)
return 1;
- val |= (1 << bit);
- cpu_buffer->current_context = val;
+ cpu_buffer->current_context++;
+ /* Interrupts must see this update */
+ barrier();
return 0;
}
@@ -2604,7 +2572,9 @@ trace_recursive_lock(struct ring_buffer_
static __always_inline void
trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer)
{
- cpu_buffer->current_context &= cpu_buffer->current_context - 1;
+ /* Don't let the dec leak out */
+ barrier();
+ cpu_buffer->current_context--;
}
/**

82
debian/patches/features/all/rt/0002-PM-wakeup-Make-events_lock-a-RAW_SPINLOCK.patch vendored Normal file
View File

@ -0,0 +1,82 @@
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Fri, 25 May 2018 09:57:42 +0200
Subject: [PATCH 2/4] PM / wakeup: Make events_lock a RAW_SPINLOCK
The `events_lock' is acquired during suspend while interrupts are
disabled even on RT. The lock is taken only for a very brief moment.
Make it a RAW lock which avoids "sleeping while atomic" warnings on RT.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
drivers/base/power/wakeup.c | 18 +++++++++---------
1 file changed, 9 insertions(+), 9 deletions(-)
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -57,7 +57,7 @@ static void split_counters(unsigned int
/* A preserved old value of the events counter. */
static unsigned int saved_count;
-static DEFINE_SPINLOCK(events_lock);
+static DEFINE_RAW_SPINLOCK(events_lock);
static void pm_wakeup_timer_fn(struct timer_list *t);
@@ -185,9 +185,9 @@ void wakeup_source_add(struct wakeup_sou
ws->active = false;
ws->last_time = ktime_get();
- spin_lock_irqsave(&events_lock, flags);
+ raw_spin_lock_irqsave(&events_lock, flags);
list_add_rcu(&ws->entry, &wakeup_sources);
- spin_unlock_irqrestore(&events_lock, flags);
+ raw_spin_unlock_irqrestore(&events_lock, flags);
}
EXPORT_SYMBOL_GPL(wakeup_source_add);
@@ -202,9 +202,9 @@ void wakeup_source_remove(struct wakeup_
if (WARN_ON(!ws))
return;
- spin_lock_irqsave(&events_lock, flags);
+ raw_spin_lock_irqsave(&events_lock, flags);
list_del_rcu(&ws->entry);
- spin_unlock_irqrestore(&events_lock, flags);
+ raw_spin_unlock_irqrestore(&events_lock, flags);
synchronize_srcu(&wakeup_srcu);
}
EXPORT_SYMBOL_GPL(wakeup_source_remove);
@@ -843,7 +843,7 @@ bool pm_wakeup_pending(void)
unsigned long flags;
bool ret = false;
- spin_lock_irqsave(&events_lock, flags);
+ raw_spin_lock_irqsave(&events_lock, flags);
if (events_check_enabled) {
unsigned int cnt, inpr;
@@ -851,7 +851,7 @@ bool pm_wakeup_pending(void)
ret = (cnt != saved_count || inpr > 0);
events_check_enabled = !ret;
}
- spin_unlock_irqrestore(&events_lock, flags);
+ raw_spin_unlock_irqrestore(&events_lock, flags);
if (ret) {
pr_info("PM: Wakeup pending, aborting suspend\n");
@@ -940,13 +940,13 @@ bool pm_save_wakeup_count(unsigned int c
unsigned long flags;
events_check_enabled = false;
- spin_lock_irqsave(&events_lock, flags);
+ raw_spin_lock_irqsave(&events_lock, flags);
split_counters(&cnt, &inpr);
if (cnt == count && inpr == 0) {
saved_count = count;
events_check_enabled = true;
}
- spin_unlock_irqrestore(&events_lock, flags);
+ raw_spin_unlock_irqrestore(&events_lock, flags);
return events_check_enabled;
}

1
debian/patches/features/all/rt/0002-clocksource-drivers-Add-a-new-driver-for-the-Atmel-A.patch vendored
View File

@ -2,7 +2,6 @@ From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Wed, 18 Apr 2018 12:51:39 +0200
Subject: [PATCH 2/6] clocksource/drivers: Add a new driver for the Atmel ARM
TC blocks
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Add a driver for the Atmel Timer Counter Blocks. This driver provides a
clocksource and two clockevent devices.

13
debian/patches/features/all/rt/0007-md-raid5-Use-irqsave-variant-of-refcount_dec_and_loc.patch → debian/patches/features/all/rt/0002-drivers-md-raid5-Use-irqsave-variant-of-atomic_dec_a.patch vendored
View File

@ -1,14 +1,13 @@
From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Wed, 4 Apr 2018 11:43:58 +0200
Subject: [PATCH] md: raid5: Use irqsave variant of refcount_dec_and_lock()
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Date: Fri, 4 May 2018 17:45:32 +0200
Subject: [PATCH 2/3] drivers/md/raid5: Use irqsave variant of
atomic_dec_and_lock()
The irqsave variant of refcount_dec_and_lock handles irqsave/restore when
The irqsave variant of atomic_dec_and_lock handles irqsave/restore when
taking/releasing the spin lock. With this variant the call of
local_irq_save is no longer required.
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
[bigeasy: s@atomic_dec_and_lock@refcount_dec_and_lock@g ]
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
drivers/md/raid5.c | 5 ++---
@ -22,8 +21,8 @@ Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
slow_path:
- local_irq_save(flags);
/* we are ok here if STRIPE_ON_RELEASE_LIST is set or not */
- if (refcount_dec_and_lock(&sh->count, &conf->device_lock)) {
+ if (refcount_dec_and_lock_irqsave(&sh->count, &conf->device_lock, &flags)) {
- if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) {
+ if (atomic_dec_and_lock_irqsave(&sh->count, &conf->device_lock, flags)) {
INIT_LIST_HEAD(&list);
hash = sh->hash_lock_index;
do_release_stripe(conf, sh, &list);

37
debian/patches/features/all/rt/0002-hrtimer-Correct-blantanly-wrong-comment.patch vendored
View File

@ -1,37 +0,0 @@
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 20 Dec 2017 17:12:51 +0100
Subject: [PATCH 02/29] hrtimer: Correct blantanly wrong comment
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
The protection of a hrtimer which runs its callback against migration to a
different CPU has nothing to do with hard interrupt context.
The protection against migration of a hrtimer running the expiry callback
is the pointer in the cpu_base which holds a pointer to the currently
running timer. This pointer is evaluated in the code which potentially
switches the timer base and makes sure it's kept on the CPU on which the
callback is running.
Reported-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/time/hrtimer.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1197,9 +1197,9 @@ static void __run_hrtimer(struct hrtimer
timer->is_rel = false;
/*
- * Because we run timers from hardirq context, there is no chance
- * they get migrated to another cpu, therefore its safe to unlock
- * the timer base.
+ * The timer is marked as running in the cpu base, so it is
+ * protected against migration to a different CPU even if the lock
+ * is dropped.
*/
raw_spin_unlock(&cpu_base->lock);
trace_hrtimer_expire_entry(timer, now);

1
debian/patches/features/all/rt/0002-iommu-amd-Don-t-use-dev_data-in-irte_ga_set_affinity.patch vendored
View File

@ -1,7 +1,6 @@
From: Scott Wood <swood@redhat.com>
Date: Sun, 28 Jan 2018 14:22:19 -0600
Subject: [PATCH 2/3] iommu/amd: Don't use dev_data in irte_ga_set_affinity()
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit 01ee04badefd296eb7a4430497373be9b7b16783

1
debian/patches/features/all/rt/0002-iommu-amd-Turn-dev_data_list-into-a-lock-less-list.patch vendored
View File

@ -1,7 +1,6 @@
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 22 Mar 2018 16:22:34 +0100
Subject: [PATCH 02/10] iommu/amd: Turn dev_data_list into a lock less list
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit 779da73273fc4c4c6f41579a95e4fb7880a1720e

53
debian/patches/features/all/rt/0002-nohz-Prevent-erroneous-tick-stop-invocations.patch vendored
View File

@ -1,53 +0,0 @@
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 22 Dec 2017 15:51:13 +0100
Subject: [PATCH 2/4] nohz: Prevent erroneous tick stop invocations
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.8-rt9.tar.xz
The conditions in irq_exit() to invoke tick_nohz_irq_exit() are:
if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu))
This is too permissive in various aspects:
1) If need_resched() is set, then the tick cannot be stopped whether
the CPU is idle or in nohz full mode.
2) If need_resched() is not set, but softirqs are pending then this is an
indication that the softirq code punted and delegated the execution to
softirqd. need_resched() is not true because the current interrupted
task takes precedence over softirqd.
Invoking tick_nohz_irq_exit() in these cases can cause an endless loop of
timer interrupts because the timer wheel contains an expired timer, but
softirqs are not yet executed. So it returns an immediate expiry request,
which causes the timer to fire immediately again. Lather, rinse and
repeat....
Prevent that by making the conditions proper and only allow invokation when
in idle or nohz full mode and neither need_resched() nor
local_softirq_pending() are set.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/softirq.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 4e09821f9d9e..6d260b1229a1 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -381,7 +381,8 @@ static inline void tick_irq_exit(void)
int cpu = smp_processor_id();
/* Make sure that timer wheel updates are propagated */
- if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) {
+ if ((idle_cpu(cpu) || tick_nohz_full_cpu(cpu)) &&
+ !need_resched() && !local_softirq_pending()) {
if (!in_interrupt())
tick_nohz_irq_exit();
}
--
2.15.1

1
debian/patches/features/all/rt/0002-now-lock_parent-can-t-run-into-killed-dentry.patch vendored
View File

@ -1,7 +1,6 @@
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 23 Feb 2018 22:07:35 -0500
Subject: [PATCH 02/17] now lock_parent() can't run into killed dentry
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit 65d8eb5a8f5480756105173de147ef5d60163e2f

24
debian/patches/features/all/rt/0002-tracing-Add-Documentation-for-log2-modifier.patch vendored
View File

@ -1,24 +0,0 @@
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Mon, 15 Jan 2018 20:51:36 -0600
Subject: [PATCH 02/37] tracing: Add Documentation for log2 modifier
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
Add a line for the log2 modifier, to keep it aligned with
tracing/README.
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
Documentation/trace/histogram.txt | 1 +
1 file changed, 1 insertion(+)
--- a/Documentation/trace/histogram.txt
+++ b/Documentation/trace/histogram.txt
@@ -73,6 +73,7 @@
.sym-offset display an address as a symbol and offset
.syscall display a syscall id as a system call name
.execname display a common_pid as a program name
+ .log2 display log2 value rather than raw number
Note that in general the semantics of a given field aren't
interpreted when applying a modifier to it, but there are some

1
debian/patches/features/all/rt/0002-tracing-Add-field-parsing-hist-error-for-hist-trigge.patch vendored
View File

@ -1,7 +1,6 @@
From: Steven Rostedt <rostedt@goodmis.org>
Date: Wed, 16 May 2018 09:36:44 -0400
Subject: [PATCH 2/5] tracing: Add field parsing hist error for hist triggers
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
From: Tom Zanussi <tom.zanussi@linux.intel.com>

189
debian/patches/features/all/rt/0002-tracing-Reverse-the-order-of-trace_types_lock-and-ev.patch vendored
View File

@ -1,189 +0,0 @@
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Fri, 22 Sep 2017 14:58:16 -0500
Subject: [PATCH 02/42] tracing: Reverse the order of trace_types_lock and
event_mutex
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
In order to make future changes where we need to call
tracing_set_clock() from within an event command, the order of
trace_types_lock and event_mutex must be reversed, as the event command
will hold event_mutex and the trace_types_lock is taken from within
tracing_set_clock().
Requested-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/trace/trace.c | 5 +++++
kernel/trace/trace_events.c | 31 +++++++++++++++----------------
2 files changed, 20 insertions(+), 16 deletions(-)
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -7671,6 +7671,7 @@ static int instance_mkdir(const char *na
struct trace_array *tr;
int ret;
+ mutex_lock(&event_mutex);
mutex_lock(&trace_types_lock);
ret = -EEXIST;
@@ -7726,6 +7727,7 @@ static int instance_mkdir(const char *na
list_add(&tr->list, &ftrace_trace_arrays);
mutex_unlock(&trace_types_lock);
+ mutex_unlock(&event_mutex);
return 0;
@@ -7737,6 +7739,7 @@ static int instance_mkdir(const char *na
out_unlock:
mutex_unlock(&trace_types_lock);
+ mutex_unlock(&event_mutex);
return ret;
@@ -7749,6 +7752,7 @@ static int instance_rmdir(const char *na
int ret;
int i;
+ mutex_lock(&event_mutex);
mutex_lock(&trace_types_lock);
ret = -ENODEV;
@@ -7794,6 +7798,7 @@ static int instance_rmdir(const char *na
out_unlock:
mutex_unlock(&trace_types_lock);
+ mutex_unlock(&event_mutex);
return ret;
}
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1406,8 +1406,8 @@ static int subsystem_open(struct inode *
return -ENODEV;
/* Make sure the system still exists */
- mutex_lock(&trace_types_lock);
mutex_lock(&event_mutex);
+ mutex_lock(&trace_types_lock);
list_for_each_entry(tr, &ftrace_trace_arrays, list) {
list_for_each_entry(dir, &tr->systems, list) {
if (dir == inode->i_private) {
@@ -1421,8 +1421,8 @@ static int subsystem_open(struct inode *
}
}
exit_loop:
- mutex_unlock(&event_mutex);
mutex_unlock(&trace_types_lock);
+ mutex_unlock(&event_mutex);
if (!system)
return -ENODEV;
@@ -2308,15 +2308,15 @@ static void __add_event_to_tracers(struc
int trace_add_event_call(struct trace_event_call *call)
{
int ret;
- mutex_lock(&trace_types_lock);
mutex_lock(&event_mutex);
+ mutex_lock(&trace_types_lock);
ret = __register_event(call, NULL);
if (ret >= 0)
__add_event_to_tracers(call);
- mutex_unlock(&event_mutex);
mutex_unlock(&trace_types_lock);
+ mutex_unlock(&event_mutex);
return ret;
}
@@ -2370,13 +2370,13 @@ int trace_remove_event_call(struct trace
{
int ret;
- mutex_lock(&trace_types_lock);
mutex_lock(&event_mutex);
+ mutex_lock(&trace_types_lock);
down_write(&trace_event_sem);
ret = probe_remove_event_call(call);
up_write(&trace_event_sem);
- mutex_unlock(&event_mutex);
mutex_unlock(&trace_types_lock);
+ mutex_unlock(&event_mutex);
return ret;
}
@@ -2438,8 +2438,8 @@ static int trace_module_notify(struct no
{
struct module *mod = data;
- mutex_lock(&trace_types_lock);
mutex_lock(&event_mutex);
+ mutex_lock(&trace_types_lock);
switch (val) {
case MODULE_STATE_COMING:
trace_module_add_events(mod);
@@ -2448,8 +2448,8 @@ static int trace_module_notify(struct no
trace_module_remove_events(mod);
break;
}
- mutex_unlock(&event_mutex);
mutex_unlock(&trace_types_lock);
+ mutex_unlock(&event_mutex);
return 0;
}
@@ -2964,24 +2964,24 @@ create_event_toplevel_files(struct dentr
* creates the event hierachry in the @parent/events directory.
*
* Returns 0 on success.
+ *
+ * Must be called with event_mutex held.
*/
int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr)
{
int ret;
- mutex_lock(&event_mutex);
+ lockdep_assert_held(&event_mutex);
ret = create_event_toplevel_files(parent, tr);
if (ret)
- goto out_unlock;
+ goto out;
down_write(&trace_event_sem);
__trace_add_event_dirs(tr);
up_write(&trace_event_sem);
- out_unlock:
- mutex_unlock(&event_mutex);
-
+ out:
return ret;
}
@@ -3010,9 +3010,10 @@ early_event_add_tracer(struct dentry *pa
return ret;
}
+/* Must be called with event_mutex held */
int event_trace_del_tracer(struct trace_array *tr)
{
- mutex_lock(&event_mutex);
+ lockdep_assert_held(&event_mutex);
/* Disable any event triggers and associated soft-disabled events */
clear_event_triggers(tr);
@@ -3033,8 +3034,6 @@ int event_trace_del_tracer(struct trace_
tr->event_dir = NULL;
- mutex_unlock(&event_mutex);
-
return 0;
}

1
debian/patches/features/all/rt/0002-userns-use-refcount_t-for-reference-counting-instead.patch vendored
View File

@ -2,7 +2,6 @@ From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 7 May 2018 17:09:42 +0200
Subject: [PATCH] userns: use refcount_t for reference counting instead
atomic_t
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
refcount_t type and corresponding API should be used instead of atomic_t when
the variable is used as a reference counter. This allows to avoid accidental

53
debian/patches/features/all/rt/0003-PM-s2idle-Make-s2idle_wait_head-swait-based.patch vendored Normal file
View File

@ -0,0 +1,53 @@
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Fri, 25 May 2018 10:05:13 +0200
Subject: [PATCH 3/4] PM / s2idle: Make s2idle_wait_head swait based
s2idle_wait_head is used during s2idle with interrupts disabled even on
RT. There is no "custom" wake up function so swait could be used instead
which is also lower weight compared to the wait_queue.
Make s2idle_wait_head a swait_queue_head.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/power/suspend.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -27,6 +27,7 @@
#include <linux/export.h>
#include <linux/suspend.h>
#include <linux/syscore_ops.h>
+#include <linux/swait.h>
#include <linux/ftrace.h>
#include <trace/events/power.h>
#include <linux/compiler.h>
@@ -57,7 +58,7 @@ EXPORT_SYMBOL_GPL(pm_suspend_global_flag
static const struct platform_suspend_ops *suspend_ops;
static const struct platform_s2idle_ops *s2idle_ops;
-static DECLARE_WAIT_QUEUE_HEAD(s2idle_wait_head);
+static DECLARE_SWAIT_QUEUE_HEAD(s2idle_wait_head);
enum s2idle_states __read_mostly s2idle_state;
static DEFINE_SPINLOCK(s2idle_lock);
@@ -91,8 +92,8 @@ static void s2idle_enter(void)
/* Push all the CPUs into the idle loop. */
wake_up_all_idle_cpus();
/* Make the current CPU wait so it can enter the idle loop too. */
- wait_event(s2idle_wait_head,
- s2idle_state == S2IDLE_STATE_WAKE);
+ swait_event(s2idle_wait_head,
+ s2idle_state == S2IDLE_STATE_WAKE);
cpuidle_pause();
put_online_cpus();
@@ -159,7 +160,7 @@ void s2idle_wake(void)
spin_lock_irqsave(&s2idle_lock, flags);
if (s2idle_state > S2IDLE_STATE_NONE) {
s2idle_state = S2IDLE_STATE_WAKE;
- wake_up(&s2idle_wait_head);
+ swake_up(&s2idle_wait_head);
}
spin_unlock_irqrestore(&s2idle_lock, flags);
}

1
debian/patches/features/all/rt/0003-clocksource-drivers-atmel-pit-make-option-silent.patch vendored
View File

@ -1,7 +1,6 @@
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Wed, 18 Apr 2018 12:51:40 +0200
Subject: [PATCH 3/6] clocksource/drivers: atmel-pit: make option silent
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
To conform with the other option, make the ATMEL_PIT option silent so it
can be selected from the platform

6
debian/patches/features/all/rt/0008-md-raid5-Do-not-disable-irq-on-release_inactive_stri.patch → debian/patches/features/all/rt/0003-drivers-md-raid5-Do-not-disable-irq-on-release_inact.patch vendored
View File

@ -1,8 +1,7 @@
From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Wed, 4 Apr 2018 11:43:59 +0200
Subject: [PATCH] md: raid5: Do not disable irq on
Date: Fri, 4 May 2018 17:45:33 +0200
Subject: [PATCH 3/3] drivers/md/raid5: Do not disable irq on
release_inactive_stripe_list() call
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
There is no need to invoke release_inactive_stripe_list() with interrupts
disabled. All call sites, except raid5_release_stripe(), unlock
@ -11,7 +10,6 @@ disabled. All call sites, except raid5_release_stripe(), unlock
Make it consistent.
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
[bigeasy: s@atomic_dec_and_lock@refcount_dec_and_lock@g ]
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
drivers/md/raid5.c | 3 +--

43
debian/patches/features/all/rt/0003-hrtimer-Fix-kerneldoc-for-struct-hrtimer_cpu_base.patch vendored
View File

@ -1,43 +0,0 @@
From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Wed, 20 Dec 2017 17:12:52 +0100
Subject: [PATCH 03/29] hrtimer: Fix kerneldoc for struct hrtimer_cpu_base
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
The sequence '/**' marks the start of a struct description. Add the
missing second asterisk. While at it adapt the ordering of the struct
members to the struct definition and document the purpose of
expires_next more precisely.
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/linux/hrtimer.h | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -144,7 +144,7 @@ enum hrtimer_base_type {
HRTIMER_MAX_CLOCK_BASES,
};
-/*
+/**
* struct hrtimer_cpu_base - the per cpu clock bases
* @lock: lock protecting the base and associated clock bases
* and timers
@@ -153,12 +153,12 @@ enum hrtimer_base_type {
* @cpu: cpu number
* @active_bases: Bitfield to mark bases with active timers
* @clock_was_set_seq: Sequence counter of clock was set events
- * @expires_next: absolute time of the next event which was scheduled
- * via clock_set_next_event()
- * @next_timer: Pointer to the first expiring timer
* @in_hrtirq: hrtimer_interrupt() is currently executing
* @hres_active: State of high resolution mode
* @hang_detected: The last hrtimer interrupt detected a hang
+ * @expires_next: absolute time of the next event, is required for remote
+ * hrtimer enqueue
+ * @next_timer: Pointer to the first expiring timer
* @nr_events: Total number of hrtimer interrupt events
* @nr_retries: Total number of hrtimer interrupt retries
* @nr_hangs: Total number of hrtimer interrupt hangs

1
debian/patches/features/all/rt/0003-iommu-amd-Avoid-locking-get_irq_table-from-atomic-co.patch vendored
View File

@ -2,7 +2,6 @@ From: Scott Wood <swood@redhat.com>
Date: Wed, 14 Feb 2018 17:36:28 -0600
Subject: [PATCH 3/3] iommu/amd: Avoid locking get_irq_table() from atomic
context
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit df42a04b15f19a842393dc98a84cbc52b1f8ed49

1
debian/patches/features/all/rt/0003-iommu-amd-Split-domain-id-out-of-amd_iommu_devtable_.patch vendored
View File

@ -2,7 +2,6 @@ From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 22 Mar 2018 16:22:35 +0100
Subject: [PATCH 03/10] iommu/amd: Split domain id out of
amd_iommu_devtable_lock
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit 2bc00180890427dcc092b2f2b0d03c904bcade29

365
debian/patches/features/all/rt/0003-md-raid5-use-refcount_t-for-reference-counting-inste.patch vendored
View File

@ -1,365 +0,0 @@
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 7 May 2018 17:42:52 +0200
Subject: [PATCH] md: raid5: use refcount_t for reference counting instead
atomic_t
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
refcount_t type and corresponding API should be used instead of atomic_t when
the variable is used as a reference counter. This allows to avoid accidental
refcounter overflows that might lead to use-after-free situations.
Most changes are 1:1 replacements except for
BUG_ON(atomic_inc_return(&sh->count) != 1);
which has been turned into
refcount_inc(&sh->count);
BUG_ON(refcount_read(&sh->count) != 1);
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
drivers/md/raid5-cache.c | 8 ++---
drivers/md/raid5-ppl.c | 2 -
drivers/md/raid5.c | 67 +++++++++++++++++++++++------------------------
drivers/md/raid5.h | 4 +-
4 files changed, 41 insertions(+), 40 deletions(-)
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -1049,7 +1049,7 @@ int r5l_write_stripe(struct r5l_log *log
* don't delay.
*/
clear_bit(STRIPE_DELAYED, &sh->state);
- atomic_inc(&sh->count);
+ refcount_inc(&sh->count);
mutex_lock(&log->io_mutex);
/* meta + data */
@@ -1388,7 +1388,7 @@ static void r5c_flush_stripe(struct r5co
lockdep_assert_held(&conf->device_lock);
list_del_init(&sh->lru);
- atomic_inc(&sh->count);
+ refcount_inc(&sh->count);
set_bit(STRIPE_HANDLE, &sh->state);
atomic_inc(&conf->active_stripes);
@@ -1491,7 +1491,7 @@ static void r5c_do_reclaim(struct r5conf
*/
if (!list_empty(&sh->lru) &&
!test_bit(STRIPE_HANDLE, &sh->state) &&
- atomic_read(&sh->count) == 0) {
+ refcount_read(&sh->count) == 0) {
r5c_flush_stripe(conf, sh);
if (count++ >= R5C_RECLAIM_STRIPE_GROUP)
break;
@@ -2912,7 +2912,7 @@ int r5c_cache_data(struct r5l_log *log,
* don't delay.
*/
clear_bit(STRIPE_DELAYED, &sh->state);
- atomic_inc(&sh->count);
+ refcount_inc(&sh->count);
mutex_lock(&log->io_mutex);
/* meta + data */
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -388,7 +388,7 @@ int ppl_write_stripe(struct r5conf *conf
set_bit(STRIPE_LOG_TRAPPED, &sh->state);
clear_bit(STRIPE_DELAYED, &sh->state);
- atomic_inc(&sh->count);
+ refcount_inc(&sh->count);
if (ppl_log_stripe(log, sh)) {
spin_lock_irq(&ppl_conf->no_mem_stripes_lock);
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -306,7 +306,7 @@ static void do_release_stripe(struct r5c
static void __release_stripe(struct r5conf *conf, struct stripe_head *sh,
struct list_head *temp_inactive_list)
{
- if (atomic_dec_and_test(&sh->count))
+ if (refcount_dec_and_test(&sh->count))
do_release_stripe(conf, sh, temp_inactive_list);
}
@@ -398,7 +398,7 @@ void raid5_release_stripe(struct stripe_
/* Avoid release_list until the last reference.
*/
- if (atomic_add_unless(&sh->count, -1, 1))
+ if (refcount_dec_not_one(&sh->count))
return;
if (unlikely(!conf->mddev->thread) ||
@@ -411,7 +411,7 @@ void raid5_release_stripe(struct stripe_
slow_path:
local_irq_save(flags);
/* we are ok here if STRIPE_ON_RELEASE_LIST is set or not */
- if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) {
+ if (refcount_dec_and_lock(&sh->count, &conf->device_lock)) {
INIT_LIST_HEAD(&list);
hash = sh->hash_lock_index;
do_release_stripe(conf, sh, &list);
@@ -501,7 +501,7 @@ static void init_stripe(struct stripe_he
struct r5conf *conf = sh->raid_conf;
int i, seq;
- BUG_ON(atomic_read(&sh->count) != 0);
+ BUG_ON(refcount_read(&sh->count) != 0);
BUG_ON(test_bit(STRIPE_HANDLE, &sh->state));
BUG_ON(stripe_operations_active(sh));
BUG_ON(sh->batch_head);
@@ -678,11 +678,11 @@ raid5_get_active_stripe(struct r5conf *c
&conf->cache_state);
} else {
init_stripe(sh, sector, previous);
- atomic_inc(&sh->count);
+ refcount_inc(&sh->count);
}
- } else if (!atomic_inc_not_zero(&sh->count)) {
+ } else if (!refcount_inc_not_zero(&sh->count)) {
spin_lock(&conf->device_lock);
- if (!atomic_read(&sh->count)) {
+ if (!refcount_read(&sh->count)) {
if (!test_bit(STRIPE_HANDLE, &sh->state))
atomic_inc(&conf->active_stripes);
BUG_ON(list_empty(&sh->lru) &&
@@ -698,7 +698,7 @@ raid5_get_active_stripe(struct r5conf *c
sh->group = NULL;
}
}
- atomic_inc(&sh->count);
+ refcount_inc(&sh->count);
spin_unlock(&conf->device_lock);
}
} while (sh == NULL);
@@ -760,9 +760,9 @@ static void stripe_add_to_batch_list(str
hash = stripe_hash_locks_hash(head_sector);
spin_lock_irq(conf->hash_locks + hash);
head = __find_stripe(conf, head_sector, conf->generation);
- if (head && !atomic_inc_not_zero(&head->count)) {
+ if (head && !refcount_inc_not_zero(&head->count)) {
spin_lock(&conf->device_lock);
- if (!atomic_read(&head->count)) {
+ if (!refcount_read(&head->count)) {
if (!test_bit(STRIPE_HANDLE, &head->state))
atomic_inc(&conf->active_stripes);
BUG_ON(list_empty(&head->lru) &&
@@ -778,7 +778,7 @@ static void stripe_add_to_batch_list(str
head->group = NULL;
}
}
- atomic_inc(&head->count);
+ refcount_inc(&head->count);
spin_unlock(&conf->device_lock);
}
spin_unlock_irq(conf->hash_locks + hash);
@@ -847,7 +847,7 @@ static void stripe_add_to_batch_list(str
sh->batch_head->bm_seq = seq;
}
- atomic_inc(&sh->count);
+ refcount_inc(&sh->count);
unlock_out:
unlock_two_stripes(head, sh);
out:
@@ -1110,9 +1110,9 @@ static void ops_run_io(struct stripe_hea
pr_debug("%s: for %llu schedule op %d on disc %d\n",
__func__, (unsigned long long)sh->sector,
bi->bi_opf, i);
- atomic_inc(&sh->count);
+ refcount_inc(&sh->count);
if (sh != head_sh)
- atomic_inc(&head_sh->count);
+ refcount_inc(&head_sh->count);
if (use_new_offset(conf, sh))
bi->bi_iter.bi_sector = (sh->sector
+ rdev->new_data_offset);
@@ -1174,9 +1174,9 @@ static void ops_run_io(struct stripe_hea
"replacement disc %d\n",
__func__, (unsigned long long)sh->sector,
rbi->bi_opf, i);
- atomic_inc(&sh->count);
+ refcount_inc(&sh->count);
if (sh != head_sh)
- atomic_inc(&head_sh->count);
+ refcount_inc(&head_sh->count);
if (use_new_offset(conf, sh))
rbi->bi_iter.bi_sector = (sh->sector
+ rrdev->new_data_offset);
@@ -1354,7 +1354,7 @@ static void ops_run_biofill(struct strip
}
}
- atomic_inc(&sh->count);
+ refcount_inc(&sh->count);
init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_biofill, sh, NULL);
async_trigger_callback(&submit);
}
@@ -1432,7 +1432,7 @@ ops_run_compute5(struct stripe_head *sh,
if (i != target)
xor_srcs[count++] = sh->dev[i].page;
- atomic_inc(&sh->count);
+ refcount_inc(&sh->count);
init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, NULL,
ops_complete_compute, sh, to_addr_conv(sh, percpu, 0));
@@ -1521,7 +1521,7 @@ ops_run_compute6_1(struct stripe_head *s
BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
dest = tgt->page;
- atomic_inc(&sh->count);
+ refcount_inc(&sh->count);
if (target == qd_idx) {
count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_ALL);
@@ -1596,7 +1596,7 @@ ops_run_compute6_2(struct stripe_head *s
pr_debug("%s: stripe: %llu faila: %d failb: %d\n",
__func__, (unsigned long long)sh->sector, faila, failb);
- atomic_inc(&sh->count);
+ refcount_inc(&sh->count);
if (failb == syndrome_disks+1) {
/* Q disk is one of the missing disks */
@@ -1867,7 +1867,7 @@ ops_run_reconstruct5(struct stripe_head
break;
}
if (i >= sh->disks) {
- atomic_inc(&sh->count);
+ refcount_inc(&sh->count);
set_bit(R5_Discard, &sh->dev[pd_idx].flags);
ops_complete_reconstruct(sh);
return;
@@ -1908,7 +1908,7 @@ ops_run_reconstruct5(struct stripe_head
flags = ASYNC_TX_ACK |
(prexor ? ASYNC_TX_XOR_DROP_DST : ASYNC_TX_XOR_ZERO_DST);
- atomic_inc(&head_sh->count);
+ refcount_inc(&head_sh->count);
init_async_submit(&submit, flags, tx, ops_complete_reconstruct, head_sh,
to_addr_conv(sh, percpu, j));
} else {
@@ -1950,7 +1950,7 @@ ops_run_reconstruct6(struct stripe_head
break;
}
if (i >= sh->disks) {
- atomic_inc(&sh->count);
+ refcount_inc(&sh->count);
set_bit(R5_Discard, &sh->dev[sh->pd_idx].flags);
set_bit(R5_Discard, &sh->dev[sh->qd_idx].flags);
ops_complete_reconstruct(sh);
@@ -1974,7 +1974,7 @@ ops_run_reconstruct6(struct stripe_head
struct stripe_head, batch_list) == head_sh;
if (last_stripe) {
- atomic_inc(&head_sh->count);
+ refcount_inc(&head_sh->count);
init_async_submit(&submit, txflags, tx, ops_complete_reconstruct,
head_sh, to_addr_conv(sh, percpu, j));
} else
@@ -2031,7 +2031,7 @@ static void ops_run_check_p(struct strip
tx = async_xor_val(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
&sh->ops.zero_sum_result, &submit);
- atomic_inc(&sh->count);
+ refcount_inc(&sh->count);
init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_check, sh, NULL);
tx = async_trigger_callback(&submit);
}
@@ -2050,7 +2050,7 @@ static void ops_run_check_pq(struct stri
if (!checkp)
srcs[count] = NULL;
- atomic_inc(&sh->count);
+ refcount_inc(&sh->count);
init_async_submit(&submit, ASYNC_TX_ACK, NULL, ops_complete_check,
sh, to_addr_conv(sh, percpu, 0));
async_syndrome_val(srcs, 0, count+2, STRIPE_SIZE,
@@ -2150,7 +2150,7 @@ static struct stripe_head *alloc_stripe(
INIT_LIST_HEAD(&sh->lru);
INIT_LIST_HEAD(&sh->r5c);
INIT_LIST_HEAD(&sh->log_list);
- atomic_set(&sh->count, 1);
+ refcount_set(&sh->count, 1);
sh->raid_conf = conf;
sh->log_start = MaxSector;
for (i = 0; i < disks; i++) {
@@ -2451,7 +2451,7 @@ static int drop_one_stripe(struct r5conf
spin_unlock_irq(conf->hash_locks + hash);
if (!sh)
return 0;
- BUG_ON(atomic_read(&sh->count));
+ BUG_ON(refcount_read(&sh->count));
shrink_buffers(sh);
free_stripe(conf->slab_cache, sh);
atomic_dec(&conf->active_stripes);
@@ -2483,7 +2483,7 @@ static void raid5_end_read_request(struc
break;
pr_debug("end_read_request %llu/%d, count: %d, error %d.\n",
- (unsigned long long)sh->sector, i, atomic_read(&sh->count),
+ (unsigned long long)sh->sector, i, refcount_read(&sh->count),
bi->bi_status);
if (i == disks) {
bio_reset(bi);
@@ -2620,7 +2620,7 @@ static void raid5_end_write_request(stru
}
}
pr_debug("end_write_request %llu/%d, count %d, error: %d.\n",
- (unsigned long long)sh->sector, i, atomic_read(&sh->count),
+ (unsigned long long)sh->sector, i, refcount_read(&sh->count),
bi->bi_status);
if (i == disks) {
bio_reset(bi);
@@ -4687,7 +4687,7 @@ static void handle_stripe(struct stripe_
pr_debug("handling stripe %llu, state=%#lx cnt=%d, "
"pd_idx=%d, qd_idx=%d\n, check:%d, reconstruct:%d\n",
(unsigned long long)sh->sector, sh->state,
- atomic_read(&sh->count), sh->pd_idx, sh->qd_idx,
+ refcount_read(&sh->count), sh->pd_idx, sh->qd_idx,
sh->check_state, sh->reconstruct_state);
analyse_stripe(sh, &s);
@@ -5062,7 +5062,7 @@ static void activate_bit_delay(struct r5
struct stripe_head *sh = list_entry(head.next, struct stripe_head, lru);
int hash;
list_del_init(&sh->lru);
- atomic_inc(&sh->count);
+ refcount_inc(&sh->count);
hash = sh->hash_lock_index;
__release_stripe(conf, sh, &temp_inactive_list[hash]);
}
@@ -5387,7 +5387,8 @@ static struct stripe_head *__get_priorit
sh->group = NULL;
}
list_del_init(&sh->lru);
- BUG_ON(atomic_inc_return(&sh->count) != 1);
+ refcount_inc(&sh->count);
+ BUG_ON(refcount_read(&sh->count) != 1);
return sh;
}
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -4,7 +4,7 @@
#include <linux/raid/xor.h>
#include <linux/dmaengine.h>
-
+#include <linux/refcount.h>
/*
*
* Each stripe contains one buffer per device. Each buffer can be in
@@ -208,7 +208,7 @@ struct stripe_head {
short ddf_layout;/* use DDF ordering to calculate Q */
short hash_lock_index;
unsigned long state; /* state flags */
- atomic_t count; /* nr of active thread/requests */
+ refcount_t count; /* nr of active thread/requests */
int bm_seq; /* sequence number for bitmap flushes */
int disks; /* disks in stripe */
int overwrite_disks; /* total overwrite disks in stripe,

1
debian/patches/features/all/rt/0003-split-the-slow-part-of-lock_parent-off.patch vendored
View File

@ -1,7 +1,6 @@
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 23 Feb 2018 22:11:34 -0500
Subject: [PATCH 03/17] split the slow part of lock_parent() off
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit 8b987a46a1e0e93d4cb4babea06ea274e2e2b658

115
debian/patches/features/all/rt/0003-tracing-Add-support-to-detect-and-avoid-duplicates.patch vendored
View File

@ -1,115 +0,0 @@
From: Vedang Patel <vedang.patel@intel.com>
Date: Mon, 15 Jan 2018 20:51:37 -0600
Subject: [PATCH 03/37] tracing: Add support to detect and avoid duplicates
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
A duplicate in the tracing_map hash table is when 2 different entries
have the same key and, as a result, the key_hash. This is possible due
to a race condition in the algorithm. This race condition is inherent to
the algorithm and not a bug. This was fine because, until now, we were
only interested in the sum of all the values related to a particular
key (the duplicates are dealt with in tracing_map_sort_entries()). But,
with the inclusion of variables[1], we are interested in individual
values. So, it will not be clear what value to choose when
there are duplicates. So, the duplicates need to be removed.
The duplicates can occur in the code in the following scenarios:
- A thread is in the process of adding a new element. It has
successfully executed cmpxchg() and inserted the key. But, it is still
not done acquiring the trace_map_elt struct, populating it and storing
the pointer to the struct in the value field of tracing_map hash table.
If another thread comes in at this time and wants to add an element with
the same key, it will not see the current element and add a new one.
- There are multiple threads trying to execute cmpxchg at the same time,
one of the threads will succeed and the others will fail. The ones which
fail will go ahead increment 'idx' and add a new element there creating
a duplicate.
This patch detects and avoids the first condition by asking the thread
which detects the duplicate to loop one more time. There is also a
possibility of infinite loop if the thread which is trying to insert
goes to sleep indefinitely and the one which is trying to insert a new
element detects a duplicate. Which is why, the thread loops for
map_size iterations before returning NULL.
The second scenario is avoided by preventing the threads which failed
cmpxchg() from incrementing idx. This way, they will loop
around and check if the thread which succeeded in executing cmpxchg()
had the same key.
[1] http://lkml.kernel.org/r/cover.1498510759.git.tom.zanussi@linux.intel.com
Signed-off-by: Vedang Patel <vedang.patel@intel.com>
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/trace/tracing_map.c | 41 ++++++++++++++++++++++++++++++++++++-----
1 file changed, 36 insertions(+), 5 deletions(-)
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -414,7 +414,9 @@ static inline struct tracing_map_elt *
__tracing_map_insert(struct tracing_map *map, void *key, bool lookup_only)
{
u32 idx, key_hash, test_key;
+ int dup_try = 0;
struct tracing_map_entry *entry;
+ struct tracing_map_elt *val;
key_hash = jhash(key, map->key_size, 0);
if (key_hash == 0)
@@ -426,11 +428,33 @@ static inline struct tracing_map_elt *
entry = TRACING_MAP_ENTRY(map->map, idx);
test_key = entry->key;
- if (test_key && test_key == key_hash && entry->val &&
- keys_match(key, entry->val->key, map->key_size)) {
- if (!lookup_only)
- atomic64_inc(&map->hits);
- return entry->val;
+ if (test_key && test_key == key_hash) {
+ val = READ_ONCE(entry->val);
+ if (val &&
+ keys_match(key, val->key, map->key_size)) {
+ if (!lookup_only)
+ atomic64_inc(&map->hits);
+ return val;
+ } else if (unlikely(!val)) {
+ /*
+ * The key is present. But, val (pointer to elt
+ * struct) is still NULL. which means some other
+ * thread is in the process of inserting an
+ * element.
+ *
+ * On top of that, it's key_hash is same as the
+ * one being inserted right now. So, it's
+ * possible that the element has the same
+ * key as well.
+ */
+
+ dup_try++;
+ if (dup_try > map->map_size) {
+ atomic64_inc(&map->drops);
+ break;
+ }
+ continue;
+ }
}
if (!test_key) {
@@ -452,6 +476,13 @@ static inline struct tracing_map_elt *
atomic64_inc(&map->hits);
return entry->val;
+ } else {
+ /*
+ * cmpxchg() failed. Loop around once
+ * more to check what key was inserted.
+ */
+ dup_try++;
+ continue;
}
}

1
debian/patches/features/all/rt/0003-tracing-Restore-proper-field-flag-printing-when-disp.patch vendored
View File

@ -2,7 +2,6 @@ From: Steven Rostedt <rostedt@goodmis.org>
Date: Wed, 16 May 2018 09:36:45 -0400
Subject: [PATCH 3/5] tracing: Restore proper field flag printing when
displaying triggers
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
From: Tom Zanussi <tom.zanussi@linux.intel.com>

1
debian/patches/features/all/rt/0004-ARM-at91-Implement-clocksource-selection.patch vendored
View File

@ -1,7 +1,6 @@
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Wed, 18 Apr 2018 12:51:41 +0200
Subject: [PATCH 4/6] ARM: at91: Implement clocksource selection
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Allow selecting and unselecting the PIT clocksource driver so it doesn't
have to be compile when unused.

68
debian/patches/features/all/rt/0004-PM-wakeup-Make-s2idle_lock-a-RAW_SPINLOCK.patch vendored Normal file
View File

@ -0,0 +1,68 @@
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Fri, 25 May 2018 10:16:05 +0200
Subject: [PATCH 4/4] PM / wakeup: Make s2idle_lock a RAW_SPINLOCK
The `s2idle_lock' is acquired during suspend while interrupts are
disabled even on RT. The lock is acquired for short sections only.
Make it a RAW lock which avoids "sleeping while atomic" warnings on RT.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/power/suspend.c | 14 +++++++-------
1 file changed, 7 insertions(+), 7 deletions(-)
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -61,7 +61,7 @@ static const struct platform_s2idle_ops
static DECLARE_SWAIT_QUEUE_HEAD(s2idle_wait_head);
enum s2idle_states __read_mostly s2idle_state;
-static DEFINE_SPINLOCK(s2idle_lock);
+static DEFINE_RAW_SPINLOCK(s2idle_lock);
void s2idle_set_ops(const struct platform_s2idle_ops *ops)
{
@@ -79,12 +79,12 @@ static void s2idle_enter(void)
{
trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_TO_IDLE, true);
- spin_lock_irq(&s2idle_lock);
+ raw_spin_lock_irq(&s2idle_lock);
if (pm_wakeup_pending())
goto out;
s2idle_state = S2IDLE_STATE_ENTER;
- spin_unlock_irq(&s2idle_lock);
+ raw_spin_unlock_irq(&s2idle_lock);
get_online_cpus();
cpuidle_resume();
@@ -98,11 +98,11 @@ static void s2idle_enter(void)
cpuidle_pause();
put_online_cpus();
- spin_lock_irq(&s2idle_lock);
+ raw_spin_lock_irq(&s2idle_lock);
out:
s2idle_state = S2IDLE_STATE_NONE;
- spin_unlock_irq(&s2idle_lock);
+ raw_spin_unlock_irq(&s2idle_lock);
trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_TO_IDLE, false);
}
@@ -157,12 +157,12 @@ void s2idle_wake(void)
{
unsigned long flags;
- spin_lock_irqsave(&s2idle_lock, flags);
+ raw_spin_lock_irqsave(&s2idle_lock, flags);
if (s2idle_state > S2IDLE_STATE_NONE) {
s2idle_state = S2IDLE_STATE_WAKE;
swake_up(&s2idle_wait_head);
}
- spin_unlock_irqrestore(&s2idle_lock, flags);
+ raw_spin_unlock_irqrestore(&s2idle_lock, flags);
}
EXPORT_SYMBOL_GPL(s2idle_wake);

1
debian/patches/features/all/rt/0004-dput-consolidate-the-do-we-need-to-retain-it-into-an.patch vendored
View File

@ -2,7 +2,6 @@ From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 23 Feb 2018 21:07:24 -0500
Subject: [PATCH 04/17] dput(): consolidate the "do we need to retain it?" into
an inlined helper
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit a338579f2f3d6a15c78f1dc7de4c248b4183fcea

81
debian/patches/features/all/rt/0004-hrtimer-Cleanup-clock-argument-in-schedule_hrtimeout.patch vendored
View File

@ -1,81 +0,0 @@
From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Wed, 20 Dec 2017 17:12:53 +0100
Subject: [PATCH 04/29] hrtimer: Cleanup clock argument in
schedule_hrtimeout_range_clock()
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
schedule_hrtimeout_range_clock() uses an integer for the clock id
instead of the predefined type "clockid_t". The ID of the clock is
indicated in hrtimer code as clock_id. Therefore change the name of
the variable as well to make it consistent.
While at it, clean up the description for the function parameters clock_id
and mode. The clock modes and the clock ids are not restricted as the
comment suggests. Fix the mode description as well for the callers of
schedule_hrtimeout_range_clock().
No functional change.
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/linux/hrtimer.h | 2 +-
kernel/time/hrtimer.c | 12 ++++++------
2 files changed, 7 insertions(+), 7 deletions(-)
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -462,7 +462,7 @@ extern int schedule_hrtimeout_range(ktim
extern int schedule_hrtimeout_range_clock(ktime_t *expires,
u64 delta,
const enum hrtimer_mode mode,
- int clock);
+ clockid_t clock_id);
extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode);
/* Soft interrupt function to run the hrtimer queues: */
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1664,12 +1664,12 @@ void __init hrtimers_init(void)
* schedule_hrtimeout_range_clock - sleep until timeout
* @expires: timeout value (ktime_t)
* @delta: slack in expires timeout (ktime_t)
- * @mode: timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
- * @clock: timer clock, CLOCK_MONOTONIC or CLOCK_REALTIME
+ * @mode: timer mode
+ * @clock_id: timer clock to be used
*/
int __sched
schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta,
- const enum hrtimer_mode mode, int clock)
+ const enum hrtimer_mode mode, clockid_t clock_id)
{
struct hrtimer_sleeper t;
@@ -1690,7 +1690,7 @@ schedule_hrtimeout_range_clock(ktime_t *
return -EINTR;
}
- hrtimer_init_on_stack(&t.timer, clock, mode);
+ hrtimer_init_on_stack(&t.timer, clock_id, mode);
hrtimer_set_expires_range_ns(&t.timer, *expires, delta);
hrtimer_init_sleeper(&t, current);
@@ -1712,7 +1712,7 @@ schedule_hrtimeout_range_clock(ktime_t *
* schedule_hrtimeout_range - sleep until timeout
* @expires: timeout value (ktime_t)
* @delta: slack in expires timeout (ktime_t)
- * @mode: timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
+ * @mode: timer mode
*
* Make the current task sleep until the given expiry time has
* elapsed. The routine will return immediately unless
@@ -1751,7 +1751,7 @@ EXPORT_SYMBOL_GPL(schedule_hrtimeout_ran
/**
* schedule_hrtimeout - sleep until timeout
* @expires: timeout value (ktime_t)
- * @mode: timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
+ * @mode: timer mode
*
* Make the current task sleep until the given expiry time has
* elapsed. The routine will return immediately unless

1
debian/patches/features/all/rt/0004-iommu-amd-Split-irq_lookup_table-out-of-the-amd_iomm.patch vendored
View File

@ -2,7 +2,6 @@ From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 22 Mar 2018 16:22:36 +0100
Subject: [PATCH 04/10] iommu/amd: Split irq_lookup_table out of the
amd_iommu_devtable_lock
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit ea6166f4b83e9cfba1c18f46a764d50045682fe5

1
debian/patches/features/all/rt/0004-locking-refcount-implement-refcount_dec_and_lock_irq.patch vendored
View File

@ -2,7 +2,6 @@ From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Mon, 7 May 2018 16:44:57 +0200
Subject: [PATCH] locking/refcount: implement
refcount_dec_and_lock_irqsave()
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
There are in-tree users of refcount_dec_and_lock() which must acquire the
spin lock with interrupts disabled. To workaround the lack of an irqsave

45
debian/patches/features/all/rt/0004-timerqueue-Document-return-values-of-timerqueue_add-.patch vendored
View File

@ -1,45 +0,0 @@
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 22 Dec 2017 15:51:15 +0100
Subject: [PATCH 4/4] timerqueue: Document return values of
timerqueue_add/del()
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.8-rt9.tar.xz
The return values of timerqueue_add/del() are not documented in the kernel doc
comment. Add proper documentation.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: rt@linutronix.de
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
lib/timerqueue.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/lib/timerqueue.c b/lib/timerqueue.c
index 4a720ed4fdaf..0d54bcbc8170 100644
--- a/lib/timerqueue.c
+++ b/lib/timerqueue.c
@@ -33,8 +33,9 @@
* @head: head of timerqueue
* @node: timer node to be added
*
- * Adds the timer node to the timerqueue, sorted by the
- * node's expires value.
+ * Adds the timer node to the timerqueue, sorted by the node's expires
+ * value. Returns true if the newly added timer is the first expiring timer in
+ * the queue.
*/
bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node)
{
@@ -70,7 +71,8 @@ EXPORT_SYMBOL_GPL(timerqueue_add);
* @head: head of timerqueue
* @node: timer node to be removed
*
- * Removes the timer node from the timerqueue.
+ * Removes the timer node from the timerqueue. Returns true if the queue is
+ * not empty after the remove.
*/
bool timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node)
{
--
2.15.1

189
debian/patches/features/all/rt/0004-tracing-Remove-code-which-merges-duplicates.patch vendored
View File

@ -1,189 +0,0 @@
From: Vedang Patel <vedang.patel@intel.com>
Date: Mon, 15 Jan 2018 20:51:38 -0600
Subject: [PATCH 04/37] tracing: Remove code which merges duplicates
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
We now have the logic to detect and remove duplicates in the
tracing_map hash table. The code which merges duplicates in the
histogram is redundant now. So, modify this code just to detect
duplicates. The duplication detection code is still kept to ensure
that any rare race condition which might cause duplicates does not go
unnoticed.
Signed-off-by: Vedang Patel <vedang.patel@intel.com>
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/trace/trace_events_hist.c | 11 -----
kernel/trace/tracing_map.c | 83 ++-------------------------------------
kernel/trace/tracing_map.h | 7 ---
3 files changed, 6 insertions(+), 95 deletions(-)
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -340,16 +340,6 @@ static int hist_trigger_elt_comm_alloc(s
return 0;
}
-static void hist_trigger_elt_comm_copy(struct tracing_map_elt *to,
- struct tracing_map_elt *from)
-{
- char *comm_from = from->private_data;
- char *comm_to = to->private_data;
-
- if (comm_from)
- memcpy(comm_to, comm_from, TASK_COMM_LEN + 1);
-}
-
static void hist_trigger_elt_comm_init(struct tracing_map_elt *elt)
{
char *comm = elt->private_data;
@@ -360,7 +350,6 @@ static void hist_trigger_elt_comm_init(s
static const struct tracing_map_ops hist_trigger_elt_comm_ops = {
.elt_alloc = hist_trigger_elt_comm_alloc,
- .elt_copy = hist_trigger_elt_comm_copy,
.elt_free = hist_trigger_elt_comm_free,
.elt_init = hist_trigger_elt_comm_init,
};
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -847,67 +847,15 @@ create_sort_entry(void *key, struct trac
return sort_entry;
}
-static struct tracing_map_elt *copy_elt(struct tracing_map_elt *elt)
-{
- struct tracing_map_elt *dup_elt;
- unsigned int i;
-
- dup_elt = tracing_map_elt_alloc(elt->map);
- if (IS_ERR(dup_elt))
- return NULL;
-
- if (elt->map->ops && elt->map->ops->elt_copy)
- elt->map->ops->elt_copy(dup_elt, elt);
-
- dup_elt->private_data = elt->private_data;
- memcpy(dup_elt->key, elt->key, elt->map->key_size);
-
- for (i = 0; i < elt->map->n_fields; i++) {
- atomic64_set(&dup_elt->fields[i].sum,
- atomic64_read(&elt->fields[i].sum));
- dup_elt->fields[i].cmp_fn = elt->fields[i].cmp_fn;
- }
-
- return dup_elt;
-}
-
-static int merge_dup(struct tracing_map_sort_entry **sort_entries,
- unsigned int target, unsigned int dup)
-{
- struct tracing_map_elt *target_elt, *elt;
- bool first_dup = (target - dup) == 1;
- int i;
-
- if (first_dup) {
- elt = sort_entries[target]->elt;
- target_elt = copy_elt(elt);
- if (!target_elt)
- return -ENOMEM;
- sort_entries[target]->elt = target_elt;
- sort_entries[target]->elt_copied = true;
- } else
- target_elt = sort_entries[target]->elt;
-
- elt = sort_entries[dup]->elt;
-
- for (i = 0; i < elt->map->n_fields; i++)
- atomic64_add(atomic64_read(&elt->fields[i].sum),
- &target_elt->fields[i].sum);
-
- sort_entries[dup]->dup = true;
-
- return 0;
-}
-
-static int merge_dups(struct tracing_map_sort_entry **sort_entries,
+static void detect_dups(struct tracing_map_sort_entry **sort_entries,
int n_entries, unsigned int key_size)
{
unsigned int dups = 0, total_dups = 0;
- int err, i, j;
+ int i;
void *key;
if (n_entries < 2)
- return total_dups;
+ return;
sort(sort_entries, n_entries, sizeof(struct tracing_map_sort_entry *),
(int (*)(const void *, const void *))cmp_entries_dup, NULL);
@@ -916,30 +864,14 @@ static int merge_dups(struct tracing_map
for (i = 1; i < n_entries; i++) {
if (!memcmp(sort_entries[i]->key, key, key_size)) {
dups++; total_dups++;
- err = merge_dup(sort_entries, i - dups, i);
- if (err)
- return err;
continue;
}
key = sort_entries[i]->key;
dups = 0;
}
- if (!total_dups)
- return total_dups;
-
- for (i = 0, j = 0; i < n_entries; i++) {
- if (!sort_entries[i]->dup) {
- sort_entries[j] = sort_entries[i];
- if (j++ != i)
- sort_entries[i] = NULL;
- } else {
- destroy_sort_entry(sort_entries[i]);
- sort_entries[i] = NULL;
- }
- }
-
- return total_dups;
+ WARN_ONCE(total_dups > 0,
+ "Duplicates detected: %d\n", total_dups);
}
static bool is_key(struct tracing_map *map, unsigned int field_idx)
@@ -1065,10 +997,7 @@ int tracing_map_sort_entries(struct trac
return 1;
}
- ret = merge_dups(entries, n_entries, map->key_size);
- if (ret < 0)
- goto free;
- n_entries -= ret;
+ detect_dups(entries, n_entries, map->key_size);
if (is_key(map, sort_keys[0].field_idx))
cmp_entries_fn = cmp_entries_key;
--- a/kernel/trace/tracing_map.h
+++ b/kernel/trace/tracing_map.h
@@ -215,11 +215,6 @@ struct tracing_map {
* Element allocation occurs before tracing begins, when the
* tracing_map_init() call is made by client code.
*
- * @elt_copy: At certain points in the lifetime of an element, it may
- * need to be copied. The copy should include a copy of the
- * client-allocated data, which can be copied into the 'to'
- * element from the 'from' element.
- *
* @elt_free: When a tracing_map_elt is freed, this function is called
* and allows client-allocated per-element data to be freed.
*
@@ -233,8 +228,6 @@ struct tracing_map {
*/
struct tracing_map_ops {
int (*elt_alloc)(struct tracing_map_elt *elt);
- void (*elt_copy)(struct tracing_map_elt *to,
- struct tracing_map_elt *from);
void (*elt_free)(struct tracing_map_elt *elt);
void (*elt_clear)(struct tracing_map_elt *elt);
void (*elt_init)(struct tracing_map_elt *elt);

27
debian/patches/features/all/rt/0004-tracing-Remove-lookups-from-tracing_map-hitcount.patch vendored
View File

@ -1,27 +0,0 @@
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Fri, 22 Sep 2017 14:58:18 -0500
Subject: [PATCH 04/42] tracing: Remove lookups from tracing_map hitcount
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
Lookups inflate the hitcount, making it essentially useless. Only
inserts and updates should really affect the hitcount anyway, so
explicitly filter lookups out.
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/trace/tracing_map.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -428,7 +428,8 @@ static inline struct tracing_map_elt *
if (test_key && test_key == key_hash && entry->val &&
keys_match(key, entry->val->key, map->key_size)) {
- atomic64_inc(&map->hits);
+ if (!lookup_only)
+ atomic64_inc(&map->hits);
return entry->val;
}

1
debian/patches/features/all/rt/0004-tracing-Uninitialized-variable-in-create_tracing_map.patch vendored
View File

@ -2,7 +2,6 @@ From: Steven Rostedt <rostedt@goodmis.org>
Date: Wed, 16 May 2018 09:36:46 -0400
Subject: [PATCH 4/5] tracing: Uninitialized variable in
create_tracing_map_fields()
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
From: Dan Carpenter <dan.carpenter@oracle.com>

1
debian/patches/features/all/rt/0005-ARM-configs-at91-use-new-TCB-timer-driver.patch vendored
View File

@ -1,7 +1,6 @@
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Wed, 18 Apr 2018 12:51:42 +0200
Subject: [PATCH 5/6] ARM: configs: at91: use new TCB timer driver
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Unselecting ATMEL_TCLIB switches the TCB timer driver from tcb_clksrc to
timer-atmel-tcb.

3
debian/patches/features/all/rt/0005-bdi-Use-irqsave-variant-of-refcount_dec_and_lock.patch vendored
View File

@ -1,7 +1,6 @@
From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Wed, 4 Apr 2018 11:43:56 +0200
Subject: [PATCH] bdi: Use irqsave variant of refcount_dec_and_lock()
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
The irqsave variant of refcount_dec_and_lock handles irqsave/restore when
taking/releasing the spin lock. With this variant the call of
@ -16,7 +15,7 @@ Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -495,11 +495,8 @@ void wb_congested_put(struct bdi_writeba
@@ -496,11 +496,8 @@ void wb_congested_put(struct bdi_writeba
{
unsigned long flags;

1
debian/patches/features/all/rt/0005-handle-move-to-LRU-in-retain_dentry.patch vendored
View File

@ -1,7 +1,6 @@
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 6 Mar 2018 21:37:31 -0500
Subject: [PATCH 05/17] handle move to LRU in retain_dentry()
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit 62d9956cefe6ecc4b43a7fae37af78ba7adaceaa

61
debian/patches/features/all/rt/0005-hrtimer-Fix-hrtimer-function-description.patch vendored
View File

@ -1,61 +0,0 @@
From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Wed, 20 Dec 2017 17:12:54 +0100
Subject: [PATCH 05/29] hrtimer: Fix hrtimer function description
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
The hrtimer_start[_range_ns]() starts a timer reliable on this CPU only
when HRTIMER_MODE_PINNED is set. Furthermore the HRTIMER_MODE_PINNED mode
is not considered, when a hrtimer is initialized.
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/linux/hrtimer.h | 6 +++---
kernel/time/hrtimer.c | 9 +++++----
2 files changed, 8 insertions(+), 7 deletions(-)
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -361,11 +361,11 @@ extern void hrtimer_start_range_ns(struc
u64 range_ns, const enum hrtimer_mode mode);
/**
- * hrtimer_start - (re)start an hrtimer on the current CPU
+ * hrtimer_start - (re)start an hrtimer
* @timer: the timer to be added
* @tim: expiry time
- * @mode: expiry mode: absolute (HRTIMER_MODE_ABS) or
- * relative (HRTIMER_MODE_REL)
+ * @mode: timer mode: absolute (HRTIMER_MODE_ABS) or
+ * relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED)
*/
static inline void hrtimer_start(struct hrtimer *timer, ktime_t tim,
const enum hrtimer_mode mode)
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -926,12 +926,12 @@ static inline ktime_t hrtimer_update_low
}
/**
- * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
+ * hrtimer_start_range_ns - (re)start an hrtimer
* @timer: the timer to be added
* @tim: expiry time
* @delta_ns: "slack" range for the timer
- * @mode: expiry mode: absolute (HRTIMER_MODE_ABS) or
- * relative (HRTIMER_MODE_REL)
+ * @mode: timer mode: absolute (HRTIMER_MODE_ABS) or
+ * relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED)
*/
void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
u64 delta_ns, const enum hrtimer_mode mode)
@@ -1109,7 +1109,8 @@ static void __hrtimer_init(struct hrtime
* hrtimer_init - initialize a timer to the given clock
* @timer: the timer to be initialized
* @clock_id: the clock to be used
- * @mode: timer mode abs/rel
+ * @mode: timer mode: absolute (HRTIMER_MODE_ABS) or
+ * relative (HRTIMER_MODE_REL); pinned is not considered here!
*/
void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
enum hrtimer_mode mode)

1
debian/patches/features/all/rt/0005-iommu-amd-Remove-the-special-case-from-alloc_irq_tab.patch vendored
View File

@ -2,7 +2,6 @@ From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 22 Mar 2018 16:22:37 +0100
Subject: [PATCH 05/10] iommu/amd: Remove the special case from
alloc_irq_table()
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit fde65dd3d3096e8f6ecc7bbe544eb91f4220772c

129
debian/patches/features/all/rt/0005-ring-buffer-Add-interface-for-setting-absolute-time-.patch vendored
View File

@ -1,129 +0,0 @@
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Mon, 15 Jan 2018 20:51:39 -0600
Subject: [PATCH 05/37] ring-buffer: Add interface for setting absolute time
stamps
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
Define a new function, tracing_set_time_stamp_abs(), which can be used
to enable or disable the use of absolute timestamps rather than time
deltas for a trace array.
Only the interface is added here; a subsequent patch will add the
underlying implementation.
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Baohong Liu <baohong.liu@intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/linux/ring_buffer.h | 2 ++
kernel/trace/ring_buffer.c | 11 +++++++++++
kernel/trace/trace.c | 33 ++++++++++++++++++++++++++++++++-
kernel/trace/trace.h | 3 +++
4 files changed, 48 insertions(+), 1 deletion(-)
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -181,6 +181,8 @@ void ring_buffer_normalize_time_stamp(st
int cpu, u64 *ts);
void ring_buffer_set_clock(struct ring_buffer *buffer,
u64 (*clock)(void));
+void ring_buffer_set_time_stamp_abs(struct ring_buffer *buffer, bool abs);
+bool ring_buffer_time_stamp_abs(struct ring_buffer *buffer);
size_t ring_buffer_page_len(void *page);
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -489,6 +489,7 @@ struct ring_buffer {
u64 (*clock)(void);
struct rb_irq_work irq_work;
+ bool time_stamp_abs;
};
struct ring_buffer_iter {
@@ -1383,6 +1384,16 @@ void ring_buffer_set_clock(struct ring_b
buffer->clock = clock;
}
+void ring_buffer_set_time_stamp_abs(struct ring_buffer *buffer, bool abs)
+{
+ buffer->time_stamp_abs = abs;
+}
+
+bool ring_buffer_time_stamp_abs(struct ring_buffer *buffer)
+{
+ return buffer->time_stamp_abs;
+}
+
static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer);
static inline unsigned long rb_page_entries(struct buffer_page *bpage)
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2269,7 +2269,7 @@ trace_event_buffer_lock_reserve(struct r
*current_rb = trace_file->tr->trace_buffer.buffer;
- if ((trace_file->flags &
+ if (!ring_buffer_time_stamp_abs(*current_rb) && (trace_file->flags &
(EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED)) &&
(entry = this_cpu_read(trace_buffered_event))) {
/* Try to use the per cpu buffer first */
@@ -6286,6 +6286,37 @@ static int tracing_clock_open(struct ino
return ret;
}
+
+int tracing_set_time_stamp_abs(struct trace_array *tr, bool abs)
+{
+ int ret = 0;
+
+ mutex_lock(&trace_types_lock);
+
+ if (abs && tr->time_stamp_abs_ref++)
+ goto out;
+
+ if (!abs) {
+ if (WARN_ON_ONCE(!tr->time_stamp_abs_ref)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (--tr->time_stamp_abs_ref)
+ goto out;
+ }
+
+ ring_buffer_set_time_stamp_abs(tr->trace_buffer.buffer, abs);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+ if (tr->max_buffer.buffer)
+ ring_buffer_set_time_stamp_abs(tr->max_buffer.buffer, abs);
+#endif
+ out:
+ mutex_unlock(&trace_types_lock);
+
+ return ret;
+}
struct ftrace_buffer_info {
struct trace_iterator iter;
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -273,6 +273,7 @@ struct trace_array {
/* function tracing enabled */
int function_enabled;
#endif
+ int time_stamp_abs_ref;
};
enum {
@@ -286,6 +287,8 @@ extern struct mutex trace_types_lock;
extern int trace_array_get(struct trace_array *tr);
extern void trace_array_put(struct trace_array *tr);
+extern int tracing_set_time_stamp_abs(struct trace_array *tr, bool abs);
+
/*
* The global tracer (top) should be the first trace array added,
* but we check the flag anyway.

1
debian/patches/features/all/rt/0005-tracing-Fix-a-potential-NULL-dereference.patch vendored
View File

@ -1,7 +1,6 @@
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 23 Mar 2018 14:37:36 +0300
Subject: [PATCH 5/5] tracing: Fix a potential NULL dereference
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
We forgot to set the error code on this path so we return ERR_PTR(0)
which is NULL. It results in a NULL dereference in the caller.

25
debian/patches/features/all/rt/0005-tracing-Increase-tracing-map-KEYS_MAX-size.patch vendored
View File

@ -1,25 +0,0 @@
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Fri, 22 Sep 2017 14:58:19 -0500
Subject: [PATCH 05/42] tracing: Increase tracing map KEYS_MAX size
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
The current default for the number of subkeys in a compound key is 2,
which is too restrictive. Increase it to a more realistic value of 3.
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/trace/tracing_map.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/kernel/trace/tracing_map.h
+++ b/kernel/trace/tracing_map.h
@@ -6,7 +6,7 @@
#define TRACING_MAP_BITS_MAX 17
#define TRACING_MAP_BITS_MIN 7
-#define TRACING_MAP_KEYS_MAX 2
+#define TRACING_MAP_KEYS_MAX 3
#define TRACING_MAP_VALS_MAX 3
#define TRACING_MAP_FIELDS_MAX (TRACING_MAP_KEYS_MAX + \
TRACING_MAP_VALS_MAX)

1
debian/patches/features/all/rt/0006-ARM-configs-at91-unselect-PIT.patch vendored
View File

@ -1,7 +1,6 @@
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Wed, 18 Apr 2018 12:51:43 +0200
Subject: [PATCH 6/6] ARM: configs: at91: unselect PIT
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
The PIT is not required anymore to successfully boot and may actually harm
in case preempt-rt is used because the PIT interrupt is shared.

1
debian/patches/features/all/rt/0006-get-rid-of-trylock-loop-around-dentry_kill.patch vendored
View File

@ -1,7 +1,6 @@
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 23 Feb 2018 21:25:42 -0500
Subject: [PATCH 06/17] get rid of trylock loop around dentry_kill()
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit f657a666fd1b1b9fe59963943c74c245ae66f4cc

41
debian/patches/features/all/rt/0006-hrtimer-Ensure-POSIX-compliance-relative-CLOCK_REALT.patch vendored
View File

@ -1,41 +0,0 @@
From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Wed, 20 Dec 2017 17:12:55 +0100
Subject: [PATCH 06/29] hrtimer: Ensure POSIX compliance (relative
CLOCK_REALTIME hrtimers)
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
POSIX specification defines, that relative CLOCK_REALTIME timers are not
affected by clock modifications. Those timers have to use CLOCK_MONOTONIC
to ensure POSIX compliance.
The introduction of the additional mode HRTIMER_MODE_PINNED broke this
requirement for pinned timers. There is no user space visible impact
because user space timers are not using the pinned mode, but for
consistency reasons this needs to be fixed.
Check whether the mode has the HRTIMER_MODE_REL bit set instead of
comparing with HRTIMER_MODE_ABS.
Fixes: 597d0275736d ("timers: Framework for identifying pinned timers")
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/time/hrtimer.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1097,7 +1097,12 @@ static void __hrtimer_init(struct hrtime
cpu_base = raw_cpu_ptr(&hrtimer_bases);
- if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS)
+ /*
+ * Posix magic: Relative CLOCK_REALTIME timers are not affected by
+ * clock modifications, so they needs to become CLOCK_MONOTONIC to
+ * ensure Posix compliance.
+ */
+ if (clock_id == CLOCK_REALTIME && mode & HRTIMER_MODE_REL)
clock_id = CLOCK_MONOTONIC;
base = hrtimer_clockid_to_base(clock_id);

1
debian/patches/features/all/rt/0006-iommu-amd-Use-table-instead-irt-as-variable-name-in-.patch vendored
View File

@ -2,7 +2,6 @@ From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 22 Mar 2018 16:22:38 +0100
Subject: [PATCH 06/10] iommu/amd: Use `table' instead `irt' as variable name
in amd_iommu_update_ga()
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit 4fde541c9dc114c5b448ad34b0286fe8b7c550f1

319
debian/patches/features/all/rt/0006-ring-buffer-Redefine-the-unimplemented-RINGBUF_TYPE_.patch vendored
View File

@ -1,319 +0,0 @@
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Mon, 15 Jan 2018 20:51:40 -0600
Subject: [PATCH 06/37] ring-buffer: Redefine the unimplemented
RINGBUF_TYPE_TIME_STAMP
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
RINGBUF_TYPE_TIME_STAMP is defined but not used, and from what I can
gather was reserved for something like an absolute timestamp feature
for the ring buffer, if not a complete replacement of the current
time_delta scheme.
This code redefines RINGBUF_TYPE_TIME_STAMP to implement absolute time
stamps. Another way to look at it is that it essentially forces
extended time_deltas for all events.
The motivation for doing this is to enable time_deltas that aren't
dependent on previous events in the ring buffer, making it feasible to
use the ring_buffer_event timetamps in a more random-access way, for
purposes other than serial event printing.
To set/reset this mode, use tracing_set_timestamp_abs() from the
previous interface patch.
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/linux/ring_buffer.h | 12 ++---
kernel/trace/ring_buffer.c | 104 ++++++++++++++++++++++++++++++++------------
2 files changed, 83 insertions(+), 33 deletions(-)
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -37,10 +37,12 @@ struct ring_buffer_event {
* array[0] = time delta (28 .. 59)
* size = 8 bytes
*
- * @RINGBUF_TYPE_TIME_STAMP: Sync time stamp with external clock
- * array[0] = tv_nsec
- * array[1..2] = tv_sec
- * size = 16 bytes
+ * @RINGBUF_TYPE_TIME_STAMP: Absolute timestamp
+ * Same format as TIME_EXTEND except that the
+ * value is an absolute timestamp, not a delta
+ * event.time_delta contains bottom 27 bits
+ * array[0] = top (28 .. 59) bits
+ * size = 8 bytes
*
* <= @RINGBUF_TYPE_DATA_TYPE_LEN_MAX:
* Data record
@@ -57,12 +59,12 @@ enum ring_buffer_type {
RINGBUF_TYPE_DATA_TYPE_LEN_MAX = 28,
RINGBUF_TYPE_PADDING,
RINGBUF_TYPE_TIME_EXTEND,
- /* FIXME: RINGBUF_TYPE_TIME_STAMP not implemented */
RINGBUF_TYPE_TIME_STAMP,
};
unsigned ring_buffer_event_length(struct ring_buffer_event *event);
void *ring_buffer_event_data(struct ring_buffer_event *event);
+u64 ring_buffer_event_time_stamp(struct ring_buffer_event *event);
/*
* ring_buffer_discard_commit will remove an event that has not
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -42,6 +42,8 @@ int ring_buffer_print_entry_header(struc
RINGBUF_TYPE_PADDING);
trace_seq_printf(s, "\ttime_extend : type == %d\n",
RINGBUF_TYPE_TIME_EXTEND);
+ trace_seq_printf(s, "\ttime_stamp : type == %d\n",
+ RINGBUF_TYPE_TIME_STAMP);
trace_seq_printf(s, "\tdata max type_len == %d\n",
RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
@@ -141,12 +143,15 @@ int ring_buffer_print_entry_header(struc
enum {
RB_LEN_TIME_EXTEND = 8,
- RB_LEN_TIME_STAMP = 16,
+ RB_LEN_TIME_STAMP = 8,
};
#define skip_time_extend(event) \
((struct ring_buffer_event *)((char *)event + RB_LEN_TIME_EXTEND))
+#define extended_time(event) \
+ (event->type_len >= RINGBUF_TYPE_TIME_EXTEND)
+
static inline int rb_null_event(struct ring_buffer_event *event)
{
return event->type_len == RINGBUF_TYPE_PADDING && !event->time_delta;
@@ -210,7 +215,7 @@ rb_event_ts_length(struct ring_buffer_ev
{
unsigned len = 0;
- if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) {
+ if (extended_time(event)) {
/* time extends include the data event after it */
len = RB_LEN_TIME_EXTEND;
event = skip_time_extend(event);
@@ -232,7 +237,7 @@ unsigned ring_buffer_event_length(struct
{
unsigned length;
- if (event->type_len == RINGBUF_TYPE_TIME_EXTEND)
+ if (extended_time(event))
event = skip_time_extend(event);
length = rb_event_length(event);
@@ -249,7 +254,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_leng
static __always_inline void *
rb_event_data(struct ring_buffer_event *event)
{
- if (event->type_len == RINGBUF_TYPE_TIME_EXTEND)
+ if (extended_time(event))
event = skip_time_extend(event);
BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
/* If length is in len field, then array[0] has the data */
@@ -276,6 +281,27 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data
#define TS_MASK ((1ULL << TS_SHIFT) - 1)
#define TS_DELTA_TEST (~TS_MASK)
+/**
+ * ring_buffer_event_time_stamp - return the event's extended timestamp
+ * @event: the event to get the timestamp of
+ *
+ * Returns the extended timestamp associated with a data event.
+ * An extended time_stamp is a 64-bit timestamp represented
+ * internally in a special way that makes the best use of space
+ * contained within a ring buffer event. This function decodes
+ * it and maps it to a straight u64 value.
+ */
+u64 ring_buffer_event_time_stamp(struct ring_buffer_event *event)
+{
+ u64 ts;
+
+ ts = event->array[0];
+ ts <<= TS_SHIFT;
+ ts += event->time_delta;
+
+ return ts;
+}
+
/* Flag when events were overwritten */
#define RB_MISSED_EVENTS (1 << 31)
/* Missed count stored at end */
@@ -2225,12 +2251,15 @@ rb_move_tail(struct ring_buffer_per_cpu
/* Slow path, do not inline */
static noinline struct ring_buffer_event *
-rb_add_time_stamp(struct ring_buffer_event *event, u64 delta)
+rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs)
{
- event->type_len = RINGBUF_TYPE_TIME_EXTEND;
+ if (abs)
+ event->type_len = RINGBUF_TYPE_TIME_STAMP;
+ else
+ event->type_len = RINGBUF_TYPE_TIME_EXTEND;
- /* Not the first event on the page? */
- if (rb_event_index(event)) {
+ /* Not the first event on the page, or not delta? */
+ if (abs || rb_event_index(event)) {
event->time_delta = delta & TS_MASK;
event->array[0] = delta >> TS_SHIFT;
} else {
@@ -2273,7 +2302,9 @@ rb_update_event(struct ring_buffer_per_c
* add it to the start of the resevered space.
*/
if (unlikely(info->add_timestamp)) {
- event = rb_add_time_stamp(event, delta);
+ bool abs = ring_buffer_time_stamp_abs(cpu_buffer->buffer);
+
+ event = rb_add_time_stamp(event, info->delta, abs);
length -= RB_LEN_TIME_EXTEND;
delta = 0;
}
@@ -2461,7 +2492,7 @@ static __always_inline void rb_end_commi
static inline void rb_event_discard(struct ring_buffer_event *event)
{
- if (event->type_len == RINGBUF_TYPE_TIME_EXTEND)
+ if (extended_time(event))
event = skip_time_extend(event);
/* array[0] holds the actual length for the discarded event */
@@ -2505,10 +2536,11 @@ rb_update_write_stamp(struct ring_buffer
cpu_buffer->write_stamp =
cpu_buffer->commit_page->page->time_stamp;
else if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) {
- delta = event->array[0];
- delta <<= TS_SHIFT;
- delta += event->time_delta;
+ delta = ring_buffer_event_time_stamp(event);
cpu_buffer->write_stamp += delta;
+ } else if (event->type_len == RINGBUF_TYPE_TIME_STAMP) {
+ delta = ring_buffer_event_time_stamp(event);
+ cpu_buffer->write_stamp = delta;
} else
cpu_buffer->write_stamp += event->time_delta;
}
@@ -2661,7 +2693,7 @@ static struct ring_buffer_event *
* If this is the first commit on the page, then it has the same
* timestamp as the page itself.
*/
- if (!tail)
+ if (!tail && !ring_buffer_time_stamp_abs(cpu_buffer->buffer))
info->delta = 0;
/* See if we shot pass the end of this buffer page */
@@ -2739,8 +2771,11 @@ rb_reserve_next_event(struct ring_buffer
/* make sure this diff is calculated here */
barrier();
- /* Did the write stamp get updated already? */
- if (likely(info.ts >= cpu_buffer->write_stamp)) {
+ if (ring_buffer_time_stamp_abs(buffer)) {
+ info.delta = info.ts;
+ rb_handle_timestamp(cpu_buffer, &info);
+ } else /* Did the write stamp get updated already? */
+ if (likely(info.ts >= cpu_buffer->write_stamp)) {
info.delta = diff;
if (unlikely(test_time_stamp(info.delta)))
rb_handle_timestamp(cpu_buffer, &info);
@@ -3422,14 +3457,13 @@ rb_update_read_stamp(struct ring_buffer_
return;
case RINGBUF_TYPE_TIME_EXTEND:
- delta = event->array[0];
- delta <<= TS_SHIFT;
- delta += event->time_delta;
+ delta = ring_buffer_event_time_stamp(event);
cpu_buffer->read_stamp += delta;
return;
case RINGBUF_TYPE_TIME_STAMP:
- /* FIXME: not implemented */
+ delta = ring_buffer_event_time_stamp(event);
+ cpu_buffer->read_stamp = delta;
return;
case RINGBUF_TYPE_DATA:
@@ -3453,14 +3487,13 @@ rb_update_iter_read_stamp(struct ring_bu
return;
case RINGBUF_TYPE_TIME_EXTEND:
- delta = event->array[0];
- delta <<= TS_SHIFT;
- delta += event->time_delta;
+ delta = ring_buffer_event_time_stamp(event);
iter->read_stamp += delta;
return;
case RINGBUF_TYPE_TIME_STAMP:
- /* FIXME: not implemented */
+ delta = ring_buffer_event_time_stamp(event);
+ iter->read_stamp = delta;
return;
case RINGBUF_TYPE_DATA:
@@ -3684,6 +3717,8 @@ rb_buffer_peek(struct ring_buffer_per_cp
struct buffer_page *reader;
int nr_loops = 0;
+ if (ts)
+ *ts = 0;
again:
/*
* We repeat when a time extend is encountered.
@@ -3720,12 +3755,17 @@ rb_buffer_peek(struct ring_buffer_per_cp
goto again;
case RINGBUF_TYPE_TIME_STAMP:
- /* FIXME: not implemented */
+ if (ts) {
+ *ts = ring_buffer_event_time_stamp(event);
+ ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
+ cpu_buffer->cpu, ts);
+ }
+ /* Internal data, OK to advance */
rb_advance_reader(cpu_buffer);
goto again;
case RINGBUF_TYPE_DATA:
- if (ts) {
+ if (ts && !(*ts)) {
*ts = cpu_buffer->read_stamp + event->time_delta;
ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
cpu_buffer->cpu, ts);
@@ -3750,6 +3790,9 @@ rb_iter_peek(struct ring_buffer_iter *it
struct ring_buffer_event *event;
int nr_loops = 0;
+ if (ts)
+ *ts = 0;
+
cpu_buffer = iter->cpu_buffer;
buffer = cpu_buffer->buffer;
@@ -3802,12 +3845,17 @@ rb_iter_peek(struct ring_buffer_iter *it
goto again;
case RINGBUF_TYPE_TIME_STAMP:
- /* FIXME: not implemented */
+ if (ts) {
+ *ts = ring_buffer_event_time_stamp(event);
+ ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
+ cpu_buffer->cpu, ts);
+ }
+ /* Internal data, OK to advance */
rb_advance_iter(iter);
goto again;
case RINGBUF_TYPE_DATA:
- if (ts) {
+ if (ts && !(*ts)) {
*ts = iter->read_stamp + event->time_delta;
ring_buffer_normalize_time_stamp(buffer,
cpu_buffer->cpu, ts);

318
debian/patches/features/all/rt/0006-tracing-Make-traceprobe-parsing-code-reusable.patch vendored
View File

@ -1,318 +0,0 @@
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Fri, 22 Sep 2017 14:58:20 -0500
Subject: [PATCH 06/42] tracing: Make traceprobe parsing code reusable
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
traceprobe_probes_write() and traceprobe_command() actually contain
nothing that ties them to kprobes - the code is generically useful for
similar types of parsing elsewhere, so separate it out and move it to
trace.c/trace.h.
Other than moving it, the only change is in naming:
traceprobe_probes_write() becomes trace_parse_run_command() and
traceprobe_command() becomes trace_run_command().
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/trace/trace.c | 86 ++++++++++++++++++++++++++++++++++++++++++++
kernel/trace/trace.h | 7 +++
kernel/trace/trace_kprobe.c | 18 ++++-----
kernel/trace/trace_probe.c | 86 --------------------------------------------
kernel/trace/trace_probe.h | 7 ---
kernel/trace/trace_uprobe.c | 2 -
6 files changed, 103 insertions(+), 103 deletions(-)
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -8265,6 +8265,92 @@ void ftrace_dump(enum ftrace_dump_mode o
}
EXPORT_SYMBOL_GPL(ftrace_dump);
+int trace_run_command(const char *buf, int (*createfn)(int, char **))
+{
+ char **argv;
+ int argc, ret;
+
+ argc = 0;
+ ret = 0;
+ argv = argv_split(GFP_KERNEL, buf, &argc);
+ if (!argv)
+ return -ENOMEM;
+
+ if (argc)
+ ret = createfn(argc, argv);
+
+ argv_free(argv);
+
+ return ret;
+}
+
+#define WRITE_BUFSIZE 4096
+
+ssize_t trace_parse_run_command(struct file *file, const char __user *buffer,
+ size_t count, loff_t *ppos,
+ int (*createfn)(int, char **))
+{
+ char *kbuf, *buf, *tmp;
+ int ret = 0;
+ size_t done = 0;
+ size_t size;
+
+ kbuf = kmalloc(WRITE_BUFSIZE, GFP_KERNEL);
+ if (!kbuf)
+ return -ENOMEM;
+
+ while (done < count) {
+ size = count - done;
+
+ if (size >= WRITE_BUFSIZE)
+ size = WRITE_BUFSIZE - 1;
+
+ if (copy_from_user(kbuf, buffer + done, size)) {
+ ret = -EFAULT;
+ goto out;
+ }
+ kbuf[size] = '\0';
+ buf = kbuf;
+ do {
+ tmp = strchr(buf, '\n');
+ if (tmp) {
+ *tmp = '\0';
+ size = tmp - buf + 1;
+ } else {
+ size = strlen(buf);
+ if (done + size < count) {
+ if (buf != kbuf)
+ break;
+ /* This can accept WRITE_BUFSIZE - 2 ('\n' + '\0') */
+ pr_warn("Line length is too long: Should be less than %d\n",
+ WRITE_BUFSIZE - 2);
+ ret = -EINVAL;
+ goto out;
+ }
+ }
+ done += size;
+
+ /* Remove comments */
+ tmp = strchr(buf, '#');
+
+ if (tmp)
+ *tmp = '\0';
+
+ ret = trace_run_command(buf, createfn);
+ if (ret)
+ goto out;
+ buf += size;
+
+ } while (done < count);
+ }
+ ret = done;
+
+out:
+ kfree(kbuf);
+
+ return ret;
+}
+
__init static int tracer_alloc_buffers(void)
{
int ring_buf_size;
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1755,6 +1755,13 @@ void trace_printk_start_comm(void);
int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set);
int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled);
+#define MAX_EVENT_NAME_LEN 64
+
+extern int trace_run_command(const char *buf, int (*createfn)(int, char**));
+extern ssize_t trace_parse_run_command(struct file *file,
+ const char __user *buffer, size_t count, loff_t *ppos,
+ int (*createfn)(int, char**));
+
/*
* Normal trace_printk() and friends allocates special buffers
* to do the manipulation, as well as saves the print formats
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -907,8 +907,8 @@ static int probes_open(struct inode *ino
static ssize_t probes_write(struct file *file, const char __user *buffer,
size_t count, loff_t *ppos)
{
- return traceprobe_probes_write(file, buffer, count, ppos,
- create_trace_kprobe);
+ return trace_parse_run_command(file, buffer, count, ppos,
+ create_trace_kprobe);
}
static const struct file_operations kprobe_events_ops = {
@@ -1433,9 +1433,9 @@ static __init int kprobe_trace_self_test
pr_info("Testing kprobe tracing: ");
- ret = traceprobe_command("p:testprobe kprobe_trace_selftest_target "
- "$stack $stack0 +0($stack)",
- create_trace_kprobe);
+ ret = trace_run_command("p:testprobe kprobe_trace_selftest_target "
+ "$stack $stack0 +0($stack)",
+ create_trace_kprobe);
if (WARN_ON_ONCE(ret)) {
pr_warn("error on probing function entry.\n");
warn++;
@@ -1455,8 +1455,8 @@ static __init int kprobe_trace_self_test
}
}
- ret = traceprobe_command("r:testprobe2 kprobe_trace_selftest_target "
- "$retval", create_trace_kprobe);
+ ret = trace_run_command("r:testprobe2 kprobe_trace_selftest_target "
+ "$retval", create_trace_kprobe);
if (WARN_ON_ONCE(ret)) {
pr_warn("error on probing function return.\n");
warn++;
@@ -1526,13 +1526,13 @@ static __init int kprobe_trace_self_test
disable_trace_kprobe(tk, file);
}
- ret = traceprobe_command("-:testprobe", create_trace_kprobe);
+ ret = trace_run_command("-:testprobe", create_trace_kprobe);
if (WARN_ON_ONCE(ret)) {
pr_warn("error on deleting a probe.\n");
warn++;
}
- ret = traceprobe_command("-:testprobe2", create_trace_kprobe);
+ ret = trace_run_command("-:testprobe2", create_trace_kprobe);
if (WARN_ON_ONCE(ret)) {
pr_warn("error on deleting a probe.\n");
warn++;
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -623,92 +623,6 @@ void traceprobe_free_probe_arg(struct pr
kfree(arg->comm);
}
-int traceprobe_command(const char *buf, int (*createfn)(int, char **))
-{
- char **argv;
- int argc, ret;
-
- argc = 0;
- ret = 0;
- argv = argv_split(GFP_KERNEL, buf, &argc);
- if (!argv)
- return -ENOMEM;
-
- if (argc)
- ret = createfn(argc, argv);
-
- argv_free(argv);
-
- return ret;
-}
-
-#define WRITE_BUFSIZE 4096
-
-ssize_t traceprobe_probes_write(struct file *file, const char __user *buffer,
- size_t count, loff_t *ppos,
- int (*createfn)(int, char **))
-{
- char *kbuf, *buf, *tmp;
- int ret = 0;
- size_t done = 0;
- size_t size;
-
- kbuf = kmalloc(WRITE_BUFSIZE, GFP_KERNEL);
- if (!kbuf)
- return -ENOMEM;
-
- while (done < count) {
- size = count - done;
-
- if (size >= WRITE_BUFSIZE)
- size = WRITE_BUFSIZE - 1;
-
- if (copy_from_user(kbuf, buffer + done, size)) {
- ret = -EFAULT;
- goto out;
- }
- kbuf[size] = '\0';
- buf = kbuf;
- do {
- tmp = strchr(buf, '\n');
- if (tmp) {
- *tmp = '\0';
- size = tmp - buf + 1;
- } else {
- size = strlen(buf);
- if (done + size < count) {
- if (buf != kbuf)
- break;
- /* This can accept WRITE_BUFSIZE - 2 ('\n' + '\0') */
- pr_warn("Line length is too long: Should be less than %d\n",
- WRITE_BUFSIZE - 2);
- ret = -EINVAL;
- goto out;
- }
- }
- done += size;
-
- /* Remove comments */
- tmp = strchr(buf, '#');
-
- if (tmp)
- *tmp = '\0';
-
- ret = traceprobe_command(buf, createfn);
- if (ret)
- goto out;
- buf += size;
-
- } while (done < count);
- }
- ret = done;
-
-out:
- kfree(kbuf);
-
- return ret;
-}
-
static int __set_print_fmt(struct trace_probe *tp, char *buf, int len,
bool is_return)
{
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -42,7 +42,6 @@
#define MAX_TRACE_ARGS 128
#define MAX_ARGSTR_LEN 63
-#define MAX_EVENT_NAME_LEN 64
#define MAX_STRING_SIZE PATH_MAX
/* Reserved field names */
@@ -356,12 +355,6 @@ extern void traceprobe_free_probe_arg(st
extern int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset);
-extern ssize_t traceprobe_probes_write(struct file *file,
- const char __user *buffer, size_t count, loff_t *ppos,
- int (*createfn)(int, char**));
-
-extern int traceprobe_command(const char *buf, int (*createfn)(int, char**));
-
/* Sum up total data length for dynamic arraies (strings) */
static nokprobe_inline int
__get_data_size(struct trace_probe *tp, struct pt_regs *regs)
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -651,7 +651,7 @@ static int probes_open(struct inode *ino
static ssize_t probes_write(struct file *file, const char __user *buffer,
size_t count, loff_t *ppos)
{
- return traceprobe_probes_write(file, buffer, count, ppos, create_trace_uprobe);
+ return trace_parse_run_command(file, buffer, count, ppos, create_trace_uprobe);
}
static const struct file_operations uprobe_events_ops = {

1
debian/patches/features/all/rt/0006-userns-Use-irqsave-variant-of-refcount_dec_and_lock.patch vendored
View File

@ -1,7 +1,6 @@
From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Wed, 4 Apr 2018 11:43:57 +0200
Subject: [PATCH] userns: Use irqsave variant of refcount_dec_and_lock()
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
The irqsave variant of refcount_dec_and_lock handles irqsave/restore when
taking/releasing the spin lock. With this variant the call of

1
debian/patches/features/all/rt/0007-fs-dcache-Avoid-a-try_lock-loop-in-shrink_dentry_lis.patch vendored
View File

@ -2,7 +2,6 @@ From: John Ogness <john.ogness@linutronix.de>
Date: Fri, 23 Feb 2018 00:50:24 +0100
Subject: [PATCH 07/17] fs/dcache: Avoid a try_lock loop in
shrink_dentry_list()
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit 8f04da2adbdffed8dc4b2feb00ec3b3d84683885

46
debian/patches/features/all/rt/0007-hrtimer-Cleanup-hrtimer_mode-enum.patch vendored
View File

@ -1,46 +0,0 @@
From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Wed, 20 Dec 2017 17:12:56 +0100
Subject: [PATCH 07/29] hrtimer: Cleanup hrtimer_mode enum
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
It's not obvious that the HRTIMER_MODE variants are bit combinations
because all modes are hard coded constants.
Change it so the bit meanings are clear and use the symbols for creating
modes which combine bits.
While at it get rid of the ugly tail comments.
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/linux/hrtimer.h | 16 +++++++++++-----
1 file changed, 11 insertions(+), 5 deletions(-)
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -28,13 +28,19 @@ struct hrtimer_cpu_base;
/*
* Mode arguments of xxx_hrtimer functions:
+ *
+ * HRTIMER_MODE_ABS - Time value is absolute
+ * HRTIMER_MODE_REL - Time value is relative to now
+ * HRTIMER_MODE_PINNED - Timer is bound to CPU (is only considered
+ * when starting the timer)
*/
enum hrtimer_mode {
- HRTIMER_MODE_ABS = 0x0, /* Time value is absolute */
- HRTIMER_MODE_REL = 0x1, /* Time value is relative to now */
- HRTIMER_MODE_PINNED = 0x02, /* Timer is bound to CPU */
- HRTIMER_MODE_ABS_PINNED = 0x02,
- HRTIMER_MODE_REL_PINNED = 0x03,
+ HRTIMER_MODE_ABS = 0x00,
+ HRTIMER_MODE_REL = 0x01,
+ HRTIMER_MODE_PINNED = 0x02,
+
+ HRTIMER_MODE_ABS_PINNED = HRTIMER_MODE_ABS | HRTIMER_MODE_PINNED,
+ HRTIMER_MODE_REL_PINNED = HRTIMER_MODE_REL | HRTIMER_MODE_PINNED,
};
/*

1
debian/patches/features/all/rt/0007-iommu-amd-Factor-out-setting-the-remap-table-for-a-d.patch vendored
View File

@ -2,7 +2,6 @@ From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 22 Mar 2018 16:22:39 +0100
Subject: [PATCH 07/10] iommu/amd: Factor out setting the remap table for a
devid
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit 2fcc1e8ac4a8514c64f946178fc36c2e30e56a41

134
debian/patches/features/all/rt/0007-tracing-Add-timestamp_mode-trace-file.patch vendored
View File

@ -1,134 +0,0 @@
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Mon, 15 Jan 2018 20:51:41 -0600
Subject: [PATCH 07/37] tracing: Add timestamp_mode trace file
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
Add a new option flag indicating whether or not the ring buffer is in
'absolute timestamp' mode.
Currently this is only set/unset by hist triggers that make use of a
common_timestamp. As such, there's no reason to make this writeable
for users - its purpose is only to allow users to determine
unequivocally whether or not the ring buffer is in that mode (although
absolute timestamps can coexist with the normal delta timestamps, when
the ring buffer is in absolute mode, timestamps written while absolute
mode is in effect take up more space in the buffer, and are not as
efficient).
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
Documentation/trace/ftrace.txt | 24 ++++++++++++++++++++
kernel/trace/trace.c | 47 +++++++++++++++++++++++++++++++++++++++++
2 files changed, 71 insertions(+)
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -539,6 +539,30 @@ After mounting tracefs you will have acc
See events.txt for more information.
+ timestamp_mode:
+
+ Certain tracers may change the timestamp mode used when
+ logging trace events into the event buffer. Events with
+ different modes can coexist within a buffer but the mode in
+ effect when an event is logged determines which timestamp mode
+ is used for that event. The default timestamp mode is
+ 'delta'.
+
+ Usual timestamp modes for tracing:
+
+ # cat timestamp_mode
+ [delta] absolute
+
+ The timestamp mode with the square brackets around it is the
+ one in effect.
+
+ delta: Default timestamp mode - timestamp is a delta against
+ a per-buffer timestamp.
+
+ absolute: The timestamp is a full timestamp, not a delta
+ against some other value. As such it takes up more
+ space and is less efficient.
+
hwlat_detector:
Directory for the Hardware Latency Detector.
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4520,6 +4520,9 @@ static const char readme_msg[] =
#ifdef CONFIG_X86_64
" x86-tsc: TSC cycle counter\n"
#endif
+ "\n timestamp_mode\t-view the mode used to timestamp events\n"
+ " delta: Delta difference against a buffer-wide timestamp\n"
+ " absolute: Absolute (standalone) timestamp\n"
"\n trace_marker\t\t- Writes into this file writes into the kernel buffer\n"
"\n trace_marker_raw\t\t- Writes into this file writes binary data into the kernel buffer\n"
" tracing_cpumask\t- Limit which CPUs to trace\n"
@@ -6287,6 +6290,40 @@ static int tracing_clock_open(struct ino
return ret;
}
+static int tracing_time_stamp_mode_show(struct seq_file *m, void *v)
+{
+ struct trace_array *tr = m->private;
+
+ mutex_lock(&trace_types_lock);
+
+ if (ring_buffer_time_stamp_abs(tr->trace_buffer.buffer))
+ seq_puts(m, "delta [absolute]\n");
+ else
+ seq_puts(m, "[delta] absolute\n");
+
+ mutex_unlock(&trace_types_lock);
+
+ return 0;
+}
+
+static int tracing_time_stamp_mode_open(struct inode *inode, struct file *file)
+{
+ struct trace_array *tr = inode->i_private;
+ int ret;
+
+ if (tracing_disabled)
+ return -ENODEV;
+
+ if (trace_array_get(tr))
+ return -ENODEV;
+
+ ret = single_open(file, tracing_time_stamp_mode_show, inode->i_private);
+ if (ret < 0)
+ trace_array_put(tr);
+
+ return ret;
+}
+
int tracing_set_time_stamp_abs(struct trace_array *tr, bool abs)
{
int ret = 0;
@@ -6565,6 +6602,13 @@ static const struct file_operations trac
.write = tracing_clock_write,
};
+static const struct file_operations trace_time_stamp_mode_fops = {
+ .open = tracing_time_stamp_mode_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = tracing_single_release_tr,
+};
+
#ifdef CONFIG_TRACER_SNAPSHOT
static const struct file_operations snapshot_fops = {
.open = tracing_snapshot_open,
@@ -7887,6 +7931,9 @@ init_tracer_tracefs(struct trace_array *
trace_create_file("tracing_on", 0644, d_tracer,
tr, &rb_simple_fops);
+ trace_create_file("timestamp_mode", 0444, d_tracer, tr,
+ &trace_time_stamp_mode_fops);
+
create_trace_options_dir(tr);
#if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)

44
debian/patches/features/all/rt/0007-tracing-Clean-up-hist_field_flags-enum.patch vendored
View File

@ -1,44 +0,0 @@
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Fri, 22 Sep 2017 14:58:21 -0500
Subject: [PATCH 07/42] tracing: Clean up hist_field_flags enum
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
As we add more flags, specifying explicit integers for the flag values
becomes more unwieldy and error-prone - switch them over to left-shift
values.
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/trace/trace_events_hist.c | 20 ++++++++++----------
1 file changed, 10 insertions(+), 10 deletions(-)
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -110,16 +110,16 @@ DEFINE_HIST_FIELD_FN(u8);
#define HIST_KEY_SIZE_MAX (MAX_FILTER_STR_VAL + HIST_STACKTRACE_SIZE)
enum hist_field_flags {
- HIST_FIELD_FL_HITCOUNT = 1,
- HIST_FIELD_FL_KEY = 2,
- HIST_FIELD_FL_STRING = 4,
- HIST_FIELD_FL_HEX = 8,
- HIST_FIELD_FL_SYM = 16,
- HIST_FIELD_FL_SYM_OFFSET = 32,
- HIST_FIELD_FL_EXECNAME = 64,
- HIST_FIELD_FL_SYSCALL = 128,
- HIST_FIELD_FL_STACKTRACE = 256,
- HIST_FIELD_FL_LOG2 = 512,
+ HIST_FIELD_FL_HITCOUNT = 1 << 0,
+ HIST_FIELD_FL_KEY = 1 << 1,
+ HIST_FIELD_FL_STRING = 1 << 2,
+ HIST_FIELD_FL_HEX = 1 << 3,
+ HIST_FIELD_FL_SYM = 1 << 4,
+ HIST_FIELD_FL_SYM_OFFSET = 1 << 5,
+ HIST_FIELD_FL_EXECNAME = 1 << 6,
+ HIST_FIELD_FL_SYSCALL = 1 << 7,
+ HIST_FIELD_FL_STACKTRACE = 1 << 8,
+ HIST_FIELD_FL_LOG2 = 1 << 9,
};
struct hist_trigger_attrs {

1
debian/patches/features/all/rt/0008-dcache.c-trim-includes.patch vendored
View File

@ -1,7 +1,6 @@
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 25 Feb 2018 02:47:29 -0500
Subject: [PATCH 08/17] dcache.c: trim includes
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit 43986d63b60fd0152d9038ee3f0f9294efa8c983

1
debian/patches/features/all/rt/0008-iommu-amd-Drop-the-lock-while-allocating-new-irq-rem.patch vendored
View File

@ -2,7 +2,6 @@ From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 22 Mar 2018 16:22:40 +0100
Subject: [PATCH 08/10] iommu/amd: Drop the lock while allocating new irq remap
table
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit 993ca6e063a69a0c65ca42ed449b6bc1b3844151

175
debian/patches/features/all/rt/0008-tracing-Add-hist_field_name-accessor.patch vendored
View File

@ -1,175 +0,0 @@
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Fri, 22 Sep 2017 14:58:22 -0500
Subject: [PATCH 08/42] tracing: Add hist_field_name() accessor
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
In preparation for hist_fields that won't be strictly based on
trace_event_fields, add a new hist_field_name() accessor to allow that
flexibility and update associated users.
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/trace/trace_events_hist.c | 67 ++++++++++++++++++++++++++-------------
1 file changed, 45 insertions(+), 22 deletions(-)
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -146,6 +146,23 @@ struct hist_trigger_data {
struct tracing_map *map;
};
+static const char *hist_field_name(struct hist_field *field,
+ unsigned int level)
+{
+ const char *field_name = "";
+
+ if (level > 1)
+ return field_name;
+
+ if (field->field)
+ field_name = field->field->name;
+
+ if (field_name == NULL)
+ field_name = "";
+
+ return field_name;
+}
+
static hist_field_fn_t select_value_fn(int field_size, int field_is_signed)
{
hist_field_fn_t fn = NULL;
@@ -653,7 +670,6 @@ static int is_descending(const char *str
static int create_sort_keys(struct hist_trigger_data *hist_data)
{
char *fields_str = hist_data->attrs->sort_key_str;
- struct ftrace_event_field *field = NULL;
struct tracing_map_sort_key *sort_key;
int descending, ret = 0;
unsigned int i, j;
@@ -670,7 +686,9 @@ static int create_sort_keys(struct hist_
}
for (i = 0; i < TRACING_MAP_SORT_KEYS_MAX; i++) {
+ struct hist_field *hist_field;
char *field_str, *field_name;
+ const char *test_name;
sort_key = &hist_data->sort_keys[i];
@@ -703,8 +721,10 @@ static int create_sort_keys(struct hist_
}
for (j = 1; j < hist_data->n_fields; j++) {
- field = hist_data->fields[j]->field;
- if (field && (strcmp(field_name, field->name) == 0)) {
+ hist_field = hist_data->fields[j];
+ test_name = hist_field_name(hist_field, 0);
+
+ if (strcmp(field_name, test_name) == 0) {
sort_key->field_idx = j;
descending = is_descending(field_str);
if (descending < 0) {
@@ -952,6 +972,7 @@ hist_trigger_entry_print(struct seq_file
struct hist_field *key_field;
char str[KSYM_SYMBOL_LEN];
bool multiline = false;
+ const char *field_name;
unsigned int i;
u64 uval;
@@ -963,26 +984,27 @@ hist_trigger_entry_print(struct seq_file
if (i > hist_data->n_vals)
seq_puts(m, ", ");
+ field_name = hist_field_name(key_field, 0);
+
if (key_field->flags & HIST_FIELD_FL_HEX) {
uval = *(u64 *)(key + key_field->offset);
- seq_printf(m, "%s: %llx",
- key_field->field->name, uval);
+ seq_printf(m, "%s: %llx", field_name, uval);
} else if (key_field->flags & HIST_FIELD_FL_SYM) {
uval = *(u64 *)(key + key_field->offset);
sprint_symbol_no_offset(str, uval);
- seq_printf(m, "%s: [%llx] %-45s",
- key_field->field->name, uval, str);
+ seq_printf(m, "%s: [%llx] %-45s", field_name,
+ uval, str);
} else if (key_field->flags & HIST_FIELD_FL_SYM_OFFSET) {
uval = *(u64 *)(key + key_field->offset);
sprint_symbol(str, uval);
- seq_printf(m, "%s: [%llx] %-55s",
- key_field->field->name, uval, str);
+ seq_printf(m, "%s: [%llx] %-55s", field_name,
+ uval, str);
} else if (key_field->flags & HIST_FIELD_FL_EXECNAME) {
char *comm = elt->private_data;
uval = *(u64 *)(key + key_field->offset);
- seq_printf(m, "%s: %-16s[%10llu]",
- key_field->field->name, comm, uval);
+ seq_printf(m, "%s: %-16s[%10llu]", field_name,
+ comm, uval);
} else if (key_field->flags & HIST_FIELD_FL_SYSCALL) {
const char *syscall_name;
@@ -991,8 +1013,8 @@ hist_trigger_entry_print(struct seq_file
if (!syscall_name)
syscall_name = "unknown_syscall";
- seq_printf(m, "%s: %-30s[%3llu]",
- key_field->field->name, syscall_name, uval);
+ seq_printf(m, "%s: %-30s[%3llu]", field_name,
+ syscall_name, uval);
} else if (key_field->flags & HIST_FIELD_FL_STACKTRACE) {
seq_puts(m, "stacktrace:\n");
hist_trigger_stacktrace_print(m,
@@ -1000,15 +1022,14 @@ hist_trigger_entry_print(struct seq_file
HIST_STACKTRACE_DEPTH);
multiline = true;
} else if (key_field->flags & HIST_FIELD_FL_LOG2) {
- seq_printf(m, "%s: ~ 2^%-2llu", key_field->field->name,
+ seq_printf(m, "%s: ~ 2^%-2llu", field_name,
*(u64 *)(key + key_field->offset));
} else if (key_field->flags & HIST_FIELD_FL_STRING) {
- seq_printf(m, "%s: %-50s", key_field->field->name,
+ seq_printf(m, "%s: %-50s", field_name,
(char *)(key + key_field->offset));
} else {
uval = *(u64 *)(key + key_field->offset);
- seq_printf(m, "%s: %10llu", key_field->field->name,
- uval);
+ seq_printf(m, "%s: %10llu", field_name, uval);
}
}
@@ -1021,13 +1042,13 @@ hist_trigger_entry_print(struct seq_file
tracing_map_read_sum(elt, HITCOUNT_IDX));
for (i = 1; i < hist_data->n_vals; i++) {
+ field_name = hist_field_name(hist_data->fields[i], 0);
+
if (hist_data->fields[i]->flags & HIST_FIELD_FL_HEX) {
- seq_printf(m, " %s: %10llx",
- hist_data->fields[i]->field->name,
+ seq_printf(m, " %s: %10llx", field_name,
tracing_map_read_sum(elt, i));
} else {
- seq_printf(m, " %s: %10llu",
- hist_data->fields[i]->field->name,
+ seq_printf(m, " %s: %10llu", field_name,
tracing_map_read_sum(elt, i));
}
}
@@ -1142,7 +1163,9 @@ static const char *get_hist_field_flags(
static void hist_field_print(struct seq_file *m, struct hist_field *hist_field)
{
- seq_printf(m, "%s", hist_field->field->name);
+ const char *field_name = hist_field_name(hist_field, 0);
+
+ seq_printf(m, "%s", field_name);
if (hist_field->flags) {
const char *flags_str = get_hist_field_flags(hist_field);

299
debian/patches/features/all/rt/0008-tracing-Give-event-triggers-access-to-ring_buffer_ev.patch vendored
View File

@ -1,299 +0,0 @@
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Mon, 15 Jan 2018 20:51:42 -0600
Subject: [PATCH 08/37] tracing: Give event triggers access to
ring_buffer_event
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
The ring_buffer event can provide a timestamp that may be useful to
various triggers - pass it into the handlers for that purpose.
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/linux/trace_events.h | 14 ++++++----
kernel/trace/trace.h | 9 +++---
kernel/trace/trace_events_hist.c | 11 +++++---
kernel/trace/trace_events_trigger.c | 47 ++++++++++++++++++++++--------------
4 files changed, 49 insertions(+), 32 deletions(-)
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -402,11 +402,13 @@ enum event_trigger_type {
extern int filter_match_preds(struct event_filter *filter, void *rec);
-extern enum event_trigger_type event_triggers_call(struct trace_event_file *file,
- void *rec);
-extern void event_triggers_post_call(struct trace_event_file *file,
- enum event_trigger_type tt,
- void *rec);
+extern enum event_trigger_type
+event_triggers_call(struct trace_event_file *file, void *rec,
+ struct ring_buffer_event *event);
+extern void
+event_triggers_post_call(struct trace_event_file *file,
+ enum event_trigger_type tt,
+ void *rec, struct ring_buffer_event *event);
bool trace_event_ignore_this_pid(struct trace_event_file *trace_file);
@@ -426,7 +428,7 @@ trace_trigger_soft_disabled(struct trace
if (!(eflags & EVENT_FILE_FL_TRIGGER_COND)) {
if (eflags & EVENT_FILE_FL_TRIGGER_MODE)
- event_triggers_call(file, NULL);
+ event_triggers_call(file, NULL, NULL);
if (eflags & EVENT_FILE_FL_SOFT_DISABLED)
return true;
if (eflags & EVENT_FILE_FL_PID_FILTER)
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1296,7 +1296,7 @@ static inline bool
unsigned long eflags = file->flags;
if (eflags & EVENT_FILE_FL_TRIGGER_COND)
- *tt = event_triggers_call(file, entry);
+ *tt = event_triggers_call(file, entry, event);
if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags) ||
(unlikely(file->flags & EVENT_FILE_FL_FILTERED) &&
@@ -1333,7 +1333,7 @@ event_trigger_unlock_commit(struct trace
trace_buffer_unlock_commit(file->tr, buffer, event, irq_flags, pc);
if (tt)
- event_triggers_post_call(file, tt, entry);
+ event_triggers_post_call(file, tt, entry, event);
}
/**
@@ -1366,7 +1366,7 @@ event_trigger_unlock_commit_regs(struct
irq_flags, pc, regs);
if (tt)
- event_triggers_post_call(file, tt, entry);
+ event_triggers_post_call(file, tt, entry, event);
}
#define FILTER_PRED_INVALID ((unsigned short)-1)
@@ -1591,7 +1591,8 @@ extern int register_trigger_hist_enable_
*/
struct event_trigger_ops {
void (*func)(struct event_trigger_data *data,
- void *rec);
+ void *rec,
+ struct ring_buffer_event *rbe);
int (*init)(struct event_trigger_ops *ops,
struct event_trigger_data *data);
void (*free)(struct event_trigger_ops *ops,
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -909,7 +909,8 @@ static inline void add_to_key(char *comp
memcpy(compound_key + key_field->offset, key, size);
}
-static void event_hist_trigger(struct event_trigger_data *data, void *rec)
+static void event_hist_trigger(struct event_trigger_data *data, void *rec,
+ struct ring_buffer_event *event)
{
struct hist_trigger_data *hist_data = data->private_data;
bool use_compound_key = (hist_data->n_keys > 1);
@@ -1660,7 +1661,8 @@ static struct event_command trigger_hist
}
static void
-hist_enable_trigger(struct event_trigger_data *data, void *rec)
+hist_enable_trigger(struct event_trigger_data *data, void *rec,
+ struct ring_buffer_event *event)
{
struct enable_trigger_data *enable_data = data->private_data;
struct event_trigger_data *test;
@@ -1676,7 +1678,8 @@ hist_enable_trigger(struct event_trigger
}
static void
-hist_enable_count_trigger(struct event_trigger_data *data, void *rec)
+hist_enable_count_trigger(struct event_trigger_data *data, void *rec,
+ struct ring_buffer_event *event)
{
if (!data->count)
return;
@@ -1684,7 +1687,7 @@ hist_enable_count_trigger(struct event_t
if (data->count != -1)
(data->count)--;
- hist_enable_trigger(data, rec);
+ hist_enable_trigger(data, rec, event);
}
static struct event_trigger_ops hist_enable_trigger_ops = {
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -63,7 +63,8 @@ void trigger_data_free(struct event_trig
* any trigger that should be deferred, ETT_NONE if nothing to defer.
*/
enum event_trigger_type
-event_triggers_call(struct trace_event_file *file, void *rec)
+event_triggers_call(struct trace_event_file *file, void *rec,
+ struct ring_buffer_event *event)
{
struct event_trigger_data *data;
enum event_trigger_type tt = ETT_NONE;
@@ -76,7 +77,7 @@ event_triggers_call(struct trace_event_f
if (data->paused)
continue;
if (!rec) {
- data->ops->func(data, rec);
+ data->ops->func(data, rec, event);
continue;
}
filter = rcu_dereference_sched(data->filter);
@@ -86,7 +87,7 @@ event_triggers_call(struct trace_event_f
tt |= data->cmd_ops->trigger_type;
continue;
}
- data->ops->func(data, rec);
+ data->ops->func(data, rec, event);
}
return tt;
}
@@ -108,7 +109,7 @@ EXPORT_SYMBOL_GPL(event_triggers_call);
void
event_triggers_post_call(struct trace_event_file *file,
enum event_trigger_type tt,
- void *rec)
+ void *rec, struct ring_buffer_event *event)
{
struct event_trigger_data *data;
@@ -116,7 +117,7 @@ event_triggers_post_call(struct trace_ev
if (data->paused)
continue;
if (data->cmd_ops->trigger_type & tt)
- data->ops->func(data, rec);
+ data->ops->func(data, rec, event);
}
}
EXPORT_SYMBOL_GPL(event_triggers_post_call);
@@ -909,7 +910,8 @@ void set_named_trigger_data(struct event
}
static void
-traceon_trigger(struct event_trigger_data *data, void *rec)
+traceon_trigger(struct event_trigger_data *data, void *rec,
+ struct ring_buffer_event *event)
{
if (tracing_is_on())
return;
@@ -918,7 +920,8 @@ traceon_trigger(struct event_trigger_dat
}
static void
-traceon_count_trigger(struct event_trigger_data *data, void *rec)
+traceon_count_trigger(struct event_trigger_data *data, void *rec,
+ struct ring_buffer_event *event)
{
if (tracing_is_on())
return;
@@ -933,7 +936,8 @@ traceon_count_trigger(struct event_trigg
}
static void
-traceoff_trigger(struct event_trigger_data *data, void *rec)
+traceoff_trigger(struct event_trigger_data *data, void *rec,
+ struct ring_buffer_event *event)
{
if (!tracing_is_on())
return;
@@ -942,7 +946,8 @@ traceoff_trigger(struct event_trigger_da
}
static void
-traceoff_count_trigger(struct event_trigger_data *data, void *rec)
+traceoff_count_trigger(struct event_trigger_data *data, void *rec,
+ struct ring_buffer_event *event)
{
if (!tracing_is_on())
return;
@@ -1039,13 +1044,15 @@ static struct event_command trigger_trac
#ifdef CONFIG_TRACER_SNAPSHOT
static void
-snapshot_trigger(struct event_trigger_data *data, void *rec)
+snapshot_trigger(struct event_trigger_data *data, void *rec,
+ struct ring_buffer_event *event)
{
tracing_snapshot();
}
static void
-snapshot_count_trigger(struct event_trigger_data *data, void *rec)
+snapshot_count_trigger(struct event_trigger_data *data, void *rec,
+ struct ring_buffer_event *event)
{
if (!data->count)
return;
@@ -1053,7 +1060,7 @@ snapshot_count_trigger(struct event_trig
if (data->count != -1)
(data->count)--;
- snapshot_trigger(data, rec);
+ snapshot_trigger(data, rec, event);
}
static int
@@ -1132,13 +1139,15 @@ static __init int register_trigger_snaps
#define STACK_SKIP 3
static void
-stacktrace_trigger(struct event_trigger_data *data, void *rec)
+stacktrace_trigger(struct event_trigger_data *data, void *rec,
+ struct ring_buffer_event *event)
{
trace_dump_stack(STACK_SKIP);
}
static void
-stacktrace_count_trigger(struct event_trigger_data *data, void *rec)
+stacktrace_count_trigger(struct event_trigger_data *data, void *rec,
+ struct ring_buffer_event *event)
{
if (!data->count)
return;
@@ -1146,7 +1155,7 @@ stacktrace_count_trigger(struct event_tr
if (data->count != -1)
(data->count)--;
- stacktrace_trigger(data, rec);
+ stacktrace_trigger(data, rec, event);
}
static int
@@ -1208,7 +1217,8 @@ static __init void unregister_trigger_tr
}
static void
-event_enable_trigger(struct event_trigger_data *data, void *rec)
+event_enable_trigger(struct event_trigger_data *data, void *rec,
+ struct ring_buffer_event *event)
{
struct enable_trigger_data *enable_data = data->private_data;
@@ -1219,7 +1229,8 @@ event_enable_trigger(struct event_trigge
}
static void
-event_enable_count_trigger(struct event_trigger_data *data, void *rec)
+event_enable_count_trigger(struct event_trigger_data *data, void *rec,
+ struct ring_buffer_event *event)
{
struct enable_trigger_data *enable_data = data->private_data;
@@ -1233,7 +1244,7 @@ event_enable_count_trigger(struct event_
if (data->count != -1)
(data->count)--;
- event_enable_trigger(data, rec);
+ event_enable_trigger(data, rec, event);
}
int event_enable_trigger_print(struct seq_file *m,

56
debian/patches/features/all/rt/0008-tracing-hrtimer-Take-all-clock-bases-and-modes-into-.patch vendored
View File

@ -1,56 +0,0 @@
From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Wed, 20 Dec 2017 17:12:57 +0100
Subject: [PATCH 08/29] tracing/hrtimer: Take all clock bases and modes into
account
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
So far only CLOCK_MONOTONIC and CLOCK_REALTIME were taken into account as
well as HRTIMER_MODE_ABS/REL in hrtimer_init tracepoint. The query for
detecting timer mode ABS or REL is not valid, since the introduction of
HRTIMER_MODE_PINNED.
HRTIMER_MODE_PINNED is not evaluated in hrtimer_init() call. But for the
sake of completeness print all given modes.
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/trace/events/timer.h | 20 ++++++++++++++++----
1 file changed, 16 insertions(+), 4 deletions(-)
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -136,6 +136,20 @@ DEFINE_EVENT(timer_class, timer_cancel,
TP_ARGS(timer)
);
+#define decode_clockid(type) \
+ __print_symbolic(type, \
+ { CLOCK_REALTIME, "CLOCK_REALTIME" }, \
+ { CLOCK_MONOTONIC, "CLOCK_MONOTONIC" }, \
+ { CLOCK_BOOTTIME, "CLOCK_BOOTTIME" }, \
+ { CLOCK_TAI, "CLOCK_TAI" })
+
+#define decode_hrtimer_mode(mode) \
+ __print_symbolic(mode, \
+ { HRTIMER_MODE_ABS, "ABS" }, \
+ { HRTIMER_MODE_REL, "REL" }, \
+ { HRTIMER_MODE_ABS_PINNED, "ABS|PINNED" }, \
+ { HRTIMER_MODE_REL_PINNED, "REL|PINNED" })
+
/**
* hrtimer_init - called when the hrtimer is initialized
* @hrtimer: pointer to struct hrtimer
@@ -162,10 +176,8 @@ TRACE_EVENT(hrtimer_init,
),
TP_printk("hrtimer=%p clockid=%s mode=%s", __entry->hrtimer,
- __entry->clockid == CLOCK_REALTIME ?
- "CLOCK_REALTIME" : "CLOCK_MONOTONIC",
- __entry->mode == HRTIMER_MODE_ABS ?
- "HRTIMER_MODE_ABS" : "HRTIMER_MODE_REL")
+ decode_clockid(__entry->clockid),
+ decode_hrtimer_mode(__entry->mode))
);
/**

1
debian/patches/features/all/rt/0009-iommu-amd-Make-amd_iommu_devtable_lock-a-spin_lock.patch vendored
View File

@ -1,7 +1,6 @@
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 22 Mar 2018 16:22:41 +0100
Subject: [PATCH 09/10] iommu/amd: Make amd_iommu_devtable_lock a spin_lock
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit 2cd1083d79a0a8c223af430ca97884c28a1e2fc0

1
debian/patches/features/all/rt/0009-split-d_path-and-friends-into-a-separate-file.patch vendored
View File

@ -1,7 +1,6 @@
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 5 Mar 2018 19:15:50 -0500
Subject: [PATCH 09/17] split d_path() and friends into a separate file
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit 7a5cf791a747640adb2a1b5e3838321b26953a23

140
debian/patches/features/all/rt/0009-tracing-Add-ring-buffer-event-param-to-hist-field-fu.patch vendored
View File

@ -1,140 +0,0 @@
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Mon, 15 Jan 2018 20:51:43 -0600
Subject: [PATCH 09/37] tracing: Add ring buffer event param to hist field
functions
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
Some events such as timestamps require access to a ring_buffer_event
struct; add a param so that hist field functions can access that.
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/trace/trace_events_hist.c | 39 ++++++++++++++++++++++++---------------
1 file changed, 24 insertions(+), 15 deletions(-)
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -26,7 +26,8 @@
struct hist_field;
-typedef u64 (*hist_field_fn_t) (struct hist_field *field, void *event);
+typedef u64 (*hist_field_fn_t) (struct hist_field *field, void *event,
+ struct ring_buffer_event *rbe);
#define HIST_FIELD_OPERANDS_MAX 2
@@ -40,24 +41,28 @@ struct hist_field {
struct hist_field *operands[HIST_FIELD_OPERANDS_MAX];
};
-static u64 hist_field_none(struct hist_field *field, void *event)
+static u64 hist_field_none(struct hist_field *field, void *event,
+ struct ring_buffer_event *rbe)
{
return 0;
}
-static u64 hist_field_counter(struct hist_field *field, void *event)
+static u64 hist_field_counter(struct hist_field *field, void *event,
+ struct ring_buffer_event *rbe)
{
return 1;
}
-static u64 hist_field_string(struct hist_field *hist_field, void *event)
+static u64 hist_field_string(struct hist_field *hist_field, void *event,
+ struct ring_buffer_event *rbe)
{
char *addr = (char *)(event + hist_field->field->offset);
return (u64)(unsigned long)addr;
}
-static u64 hist_field_dynstring(struct hist_field *hist_field, void *event)
+static u64 hist_field_dynstring(struct hist_field *hist_field, void *event,
+ struct ring_buffer_event *rbe)
{
u32 str_item = *(u32 *)(event + hist_field->field->offset);
int str_loc = str_item & 0xffff;
@@ -66,24 +71,28 @@ static u64 hist_field_dynstring(struct h
return (u64)(unsigned long)addr;
}
-static u64 hist_field_pstring(struct hist_field *hist_field, void *event)
+static u64 hist_field_pstring(struct hist_field *hist_field, void *event,
+ struct ring_buffer_event *rbe)
{
char **addr = (char **)(event + hist_field->field->offset);
return (u64)(unsigned long)*addr;
}
-static u64 hist_field_log2(struct hist_field *hist_field, void *event)
+static u64 hist_field_log2(struct hist_field *hist_field, void *event,
+ struct ring_buffer_event *rbe)
{
struct hist_field *operand = hist_field->operands[0];
- u64 val = operand->fn(operand, event);
+ u64 val = operand->fn(operand, event, rbe);
return (u64) ilog2(roundup_pow_of_two(val));
}
#define DEFINE_HIST_FIELD_FN(type) \
-static u64 hist_field_##type(struct hist_field *hist_field, void *event)\
+ static u64 hist_field_##type(struct hist_field *hist_field, \
+ void *event, \
+ struct ring_buffer_event *rbe) \
{ \
type *addr = (type *)(event + hist_field->field->offset); \
\
@@ -871,8 +880,8 @@ create_hist_data(unsigned int map_bits,
}
static void hist_trigger_elt_update(struct hist_trigger_data *hist_data,
- struct tracing_map_elt *elt,
- void *rec)
+ struct tracing_map_elt *elt, void *rec,
+ struct ring_buffer_event *rbe)
{
struct hist_field *hist_field;
unsigned int i;
@@ -880,7 +889,7 @@ static void hist_trigger_elt_update(stru
for_each_hist_val_field(i, hist_data) {
hist_field = hist_data->fields[i];
- hist_val = hist_field->fn(hist_field, rec);
+ hist_val = hist_field->fn(hist_field, rec, rbe);
tracing_map_update_sum(elt, i, hist_val);
}
}
@@ -910,7 +919,7 @@ static inline void add_to_key(char *comp
}
static void event_hist_trigger(struct event_trigger_data *data, void *rec,
- struct ring_buffer_event *event)
+ struct ring_buffer_event *rbe)
{
struct hist_trigger_data *hist_data = data->private_data;
bool use_compound_key = (hist_data->n_keys > 1);
@@ -939,7 +948,7 @@ static void event_hist_trigger(struct ev
key = entries;
} else {
- field_contents = key_field->fn(key_field, rec);
+ field_contents = key_field->fn(key_field, rec, rbe);
if (key_field->flags & HIST_FIELD_FL_STRING) {
key = (void *)(unsigned long)field_contents;
use_compound_key = true;
@@ -956,7 +965,7 @@ static void event_hist_trigger(struct ev
elt = tracing_map_insert(hist_data->map, key);
if (elt)
- hist_trigger_elt_update(hist_data, elt, rec);
+ hist_trigger_elt_update(hist_data, elt, rec, rbe);
}
static void hist_trigger_stacktrace_print(struct seq_file *m,

1
debian/patches/features/all/rt/0009-tracing-Move-hist-trigger-Documentation-to-histogram.patch vendored
View File

@ -2,7 +2,6 @@ From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Mon, 15 Jan 2018 20:51:35 -0600
Subject: [PATCH 09/48] tracing: Move hist trigger Documentation to
histogram.txt
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
The hist trigger Documentation takes up a large part of events.txt -
since it will be getting even larger, move it to a separate file.

115
debian/patches/features/all/rt/0009-tracing-Reimplement-log2.patch vendored
View File

@ -1,115 +0,0 @@
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Fri, 22 Sep 2017 14:58:23 -0500
Subject: [PATCH 09/42] tracing: Reimplement log2
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
log2 as currently implemented applies only to u64 trace_event_field
derived fields, and assumes that anything it's applied to is a u64
field.
To prepare for synthetic fields like latencies, log2 should be
applicable to those as well, so take the opportunity now to fix the
current problems as well as expand to more general uses.
log2 should be thought of as a chaining function rather than a field
type. To enable this as well as possible future function
implementations, add a hist_field operand array into the hist_field
definition for this purpose, and make use of it to implement the log2
'function'.
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/trace/trace_events_hist.c | 31 +++++++++++++++++++++++++++----
1 file changed, 27 insertions(+), 4 deletions(-)
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -28,12 +28,16 @@ struct hist_field;
typedef u64 (*hist_field_fn_t) (struct hist_field *field, void *event);
+#define HIST_FIELD_OPERANDS_MAX 2
+
struct hist_field {
struct ftrace_event_field *field;
unsigned long flags;
hist_field_fn_t fn;
unsigned int size;
unsigned int offset;
+ unsigned int is_signed;
+ struct hist_field *operands[HIST_FIELD_OPERANDS_MAX];
};
static u64 hist_field_none(struct hist_field *field, void *event)
@@ -71,7 +75,9 @@ static u64 hist_field_pstring(struct his
static u64 hist_field_log2(struct hist_field *hist_field, void *event)
{
- u64 val = *(u64 *)(event + hist_field->field->offset);
+ struct hist_field *operand = hist_field->operands[0];
+
+ u64 val = operand->fn(operand, event);
return (u64) ilog2(roundup_pow_of_two(val));
}
@@ -156,6 +162,8 @@ static const char *hist_field_name(struc
if (field->field)
field_name = field->field->name;
+ else if (field->flags & HIST_FIELD_FL_LOG2)
+ field_name = hist_field_name(field->operands[0], ++level);
if (field_name == NULL)
field_name = "";
@@ -357,8 +365,20 @@ static const struct tracing_map_ops hist
.elt_init = hist_trigger_elt_comm_init,
};
-static void destroy_hist_field(struct hist_field *hist_field)
+static void destroy_hist_field(struct hist_field *hist_field,
+ unsigned int level)
{
+ unsigned int i;
+
+ if (level > 2)
+ return;
+
+ if (!hist_field)
+ return;
+
+ for (i = 0; i < HIST_FIELD_OPERANDS_MAX; i++)
+ destroy_hist_field(hist_field->operands[i], level + 1);
+
kfree(hist_field);
}
@@ -385,7 +405,10 @@ static struct hist_field *create_hist_fi
}
if (flags & HIST_FIELD_FL_LOG2) {
+ unsigned long fl = flags & ~HIST_FIELD_FL_LOG2;
hist_field->fn = hist_field_log2;
+ hist_field->operands[0] = create_hist_field(field, fl);
+ hist_field->size = hist_field->operands[0]->size;
goto out;
}
@@ -405,7 +428,7 @@ static struct hist_field *create_hist_fi
hist_field->fn = select_value_fn(field->size,
field->is_signed);
if (!hist_field->fn) {
- destroy_hist_field(hist_field);
+ destroy_hist_field(hist_field, 0);
return NULL;
}
}
@@ -422,7 +445,7 @@ static void destroy_hist_fields(struct h
for (i = 0; i < TRACING_MAP_FIELDS_MAX; i++) {
if (hist_data->fields[i]) {
- destroy_hist_field(hist_data->fields[i]);
+ destroy_hist_field(hist_data->fields[i], 0);
hist_data->fields[i] = NULL;
}
}

114
debian/patches/features/all/rt/0009-tracing-hrtimer-Print-hrtimer-mode-in-hrtimer_start-.patch vendored
View File

@ -1,114 +0,0 @@
From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Wed, 20 Dec 2017 17:12:58 +0100
Subject: [PATCH 09/29] tracing/hrtimer: Print hrtimer mode in hrtimer_start
tracepoint
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
The hrtimer_start tracepoint lacks the mode information. The mode is
important because consecutive starts can switch from ABS to REL or from
PINNED to non PINNED.
Add the mode information.
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/trace/events/timer.h | 13 ++++++++-----
kernel/time/hrtimer.c | 16 +++++++++-------
2 files changed, 17 insertions(+), 12 deletions(-)
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -186,15 +186,16 @@ TRACE_EVENT(hrtimer_init,
*/
TRACE_EVENT(hrtimer_start,
- TP_PROTO(struct hrtimer *hrtimer),
+ TP_PROTO(struct hrtimer *hrtimer, enum hrtimer_mode mode),
- TP_ARGS(hrtimer),
+ TP_ARGS(hrtimer, mode),
TP_STRUCT__entry(
__field( void *, hrtimer )
__field( void *, function )
__field( s64, expires )
__field( s64, softexpires )
+ __field( enum hrtimer_mode, mode )
),
TP_fast_assign(
@@ -202,12 +203,14 @@ TRACE_EVENT(hrtimer_start,
__entry->function = hrtimer->function;
__entry->expires = hrtimer_get_expires(hrtimer);
__entry->softexpires = hrtimer_get_softexpires(hrtimer);
+ __entry->mode = mode;
),
- TP_printk("hrtimer=%p function=%pf expires=%llu softexpires=%llu",
- __entry->hrtimer, __entry->function,
+ TP_printk("hrtimer=%p function=%pf expires=%llu softexpires=%llu "
+ "mode=%s", __entry->hrtimer, __entry->function,
(unsigned long long) __entry->expires,
- (unsigned long long) __entry->softexpires)
+ (unsigned long long) __entry->softexpires,
+ decode_hrtimer_mode(__entry->mode))
);
/**
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -435,10 +435,11 @@ debug_init(struct hrtimer *timer, clocki
trace_hrtimer_init(timer, clockid, mode);
}
-static inline void debug_activate(struct hrtimer *timer)
+static inline void debug_activate(struct hrtimer *timer,
+ enum hrtimer_mode mode)
{
debug_hrtimer_activate(timer);
- trace_hrtimer_start(timer);
+ trace_hrtimer_start(timer, mode);
}
static inline void debug_deactivate(struct hrtimer *timer)
@@ -830,9 +831,10 @@ EXPORT_SYMBOL_GPL(hrtimer_forward);
* Returns 1 when the new timer is the leftmost timer in the tree.
*/
static int enqueue_hrtimer(struct hrtimer *timer,
- struct hrtimer_clock_base *base)
+ struct hrtimer_clock_base *base,
+ enum hrtimer_mode mode)
{
- debug_activate(timer);
+ debug_activate(timer, mode);
base->cpu_base->active_bases |= 1 << base->index;
@@ -955,7 +957,7 @@ void hrtimer_start_range_ns(struct hrtim
/* Switch the timer base, if necessary: */
new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
- leftmost = enqueue_hrtimer(timer, new_base);
+ leftmost = enqueue_hrtimer(timer, new_base, mode);
if (!leftmost)
goto unlock;
@@ -1224,7 +1226,7 @@ static void __run_hrtimer(struct hrtimer
*/
if (restart != HRTIMER_NORESTART &&
!(timer->state & HRTIMER_STATE_ENQUEUED))
- enqueue_hrtimer(timer, base);
+ enqueue_hrtimer(timer, base, HRTIMER_MODE_ABS);
/*
* Separate the ->running assignment from the ->state assignment.
@@ -1623,7 +1625,7 @@ static void migrate_hrtimer_list(struct
* sort out already expired timers and reprogram the
* event device.
*/
- enqueue_hrtimer(timer, new_base);
+ enqueue_hrtimer(timer, new_base, HRTIMER_MODE_ABS);
}
}

85
debian/patches/features/all/rt/0010-hrtimer-Switch-for-loop-to-_ffs-evaluation.patch vendored
View File

@ -1,85 +0,0 @@
From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Wed, 20 Dec 2017 17:12:59 +0100
Subject: [PATCH 10/29] hrtimer: Switch for loop to _ffs() evaluation
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
Looping over all clock bases to find active bits is suboptimal if not all
bases are active.
Avoid this by converting it to a __ffs() evaluation. The functionallity is
outsourced into an own function and is called via a macro as suggested by
Peter Zijlstra.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/time/hrtimer.c | 31 +++++++++++++++++++++----------
1 file changed, 21 insertions(+), 10 deletions(-)
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -448,6 +448,23 @@ static inline void debug_deactivate(stru
trace_hrtimer_cancel(timer);
}
+static struct hrtimer_clock_base *
+__next_base(struct hrtimer_cpu_base *cpu_base, unsigned int *active)
+{
+ unsigned int idx;
+
+ if (!*active)
+ return NULL;
+
+ idx = __ffs(*active);
+ *active &= ~(1U << idx);
+
+ return &cpu_base->clock_base[idx];
+}
+
+#define for_each_active_base(base, cpu_base, active) \
+ while ((base = __next_base((cpu_base), &(active))))
+
#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
static inline void hrtimer_update_next_timer(struct hrtimer_cpu_base *cpu_base,
struct hrtimer *timer)
@@ -459,18 +476,15 @@ static inline void hrtimer_update_next_t
static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
{
- struct hrtimer_clock_base *base = cpu_base->clock_base;
+ struct hrtimer_clock_base *base;
unsigned int active = cpu_base->active_bases;
ktime_t expires, expires_next = KTIME_MAX;
hrtimer_update_next_timer(cpu_base, NULL);
- for (; active; base++, active >>= 1) {
+ for_each_active_base(base, cpu_base, active) {
struct timerqueue_node *next;
struct hrtimer *timer;
- if (!(active & 0x01))
- continue;
-
next = timerqueue_getnext(&base->active);
timer = container_of(next, struct hrtimer, node);
expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
@@ -1243,16 +1257,13 @@ static void __run_hrtimer(struct hrtimer
static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now)
{
- struct hrtimer_clock_base *base = cpu_base->clock_base;
+ struct hrtimer_clock_base *base;
unsigned int active = cpu_base->active_bases;
- for (; active; base++, active >>= 1) {
+ for_each_active_base(base, cpu_base, active) {
struct timerqueue_node *node;
ktime_t basenow;
- if (!(active & 0x01))
- continue;
-
basenow = ktime_add(now, base->offset);
while ((node = timerqueue_getnext(&base->active))) {

1
debian/patches/features/all/rt/0010-iommu-amd-Return-proper-error-code-in-irq_remapping_.patch vendored
View File

@ -2,7 +2,6 @@ From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 22 Mar 2018 16:22:42 +0100
Subject: [PATCH 10/10] iommu/amd: Return proper error code in
irq_remapping_alloc()
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit 29d049be9438278c47253a74cf8d0ddf36bd5d68

1
debian/patches/features/all/rt/0010-take-out-orphan-externs-empty_string-slash_string.patch vendored
View File

@ -1,7 +1,6 @@
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 7 Mar 2018 12:47:04 -0500
Subject: [PATCH 10/17] take out orphan externs (empty_string/slash_string)
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit 903ddaf49329076862d65f7284d825759ff67bd6

1
debian/patches/features/all/rt/0010-tracing-Add-Documentation-for-log2-modifier.patch vendored
View File

@ -1,7 +1,6 @@
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Mon, 15 Jan 2018 20:51:36 -0600
Subject: [PATCH 10/48] tracing: Add Documentation for log2 modifier
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Add a line for the log2 modifier, to keep it aligned with
tracing/README.

109
debian/patches/features/all/rt/0010-tracing-Break-out-hist-trigger-assignment-parsing.patch vendored
View File

@ -1,109 +0,0 @@
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Mon, 15 Jan 2018 20:51:44 -0600
Subject: [PATCH 10/37] tracing: Break out hist trigger assignment parsing
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
This will make it easier to add variables, and makes the parsing code
cleaner regardless.
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Rajvi Jingar <rajvi.jingar@intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/trace/trace_events_hist.c | 72 +++++++++++++++++++++++++++------------
1 file changed, 51 insertions(+), 21 deletions(-)
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -251,6 +251,51 @@ static void destroy_hist_trigger_attrs(s
kfree(attrs);
}
+static int parse_assignment(char *str, struct hist_trigger_attrs *attrs)
+{
+ int ret = 0;
+
+ if ((strncmp(str, "key=", strlen("key=")) == 0) ||
+ (strncmp(str, "keys=", strlen("keys=")) == 0)) {
+ attrs->keys_str = kstrdup(str, GFP_KERNEL);
+ if (!attrs->keys_str) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ } else if ((strncmp(str, "val=", strlen("val=")) == 0) ||
+ (strncmp(str, "vals=", strlen("vals=")) == 0) ||
+ (strncmp(str, "values=", strlen("values=")) == 0)) {
+ attrs->vals_str = kstrdup(str, GFP_KERNEL);
+ if (!attrs->vals_str) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ } else if (strncmp(str, "sort=", strlen("sort=")) == 0) {
+ attrs->sort_key_str = kstrdup(str, GFP_KERNEL);
+ if (!attrs->sort_key_str) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ } else if (strncmp(str, "name=", strlen("name=")) == 0) {
+ attrs->name = kstrdup(str, GFP_KERNEL);
+ if (!attrs->name) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ } else if (strncmp(str, "size=", strlen("size=")) == 0) {
+ int map_bits = parse_map_size(str);
+
+ if (map_bits < 0) {
+ ret = map_bits;
+ goto out;
+ }
+ attrs->map_bits = map_bits;
+ } else
+ ret = -EINVAL;
+ out:
+ return ret;
+}
+
static struct hist_trigger_attrs *parse_hist_trigger_attrs(char *trigger_str)
{
struct hist_trigger_attrs *attrs;
@@ -263,33 +308,18 @@ static struct hist_trigger_attrs *parse_
while (trigger_str) {
char *str = strsep(&trigger_str, ":");
- if ((strncmp(str, "key=", strlen("key=")) == 0) ||
- (strncmp(str, "keys=", strlen("keys=")) == 0))
- attrs->keys_str = kstrdup(str, GFP_KERNEL);
- else if ((strncmp(str, "val=", strlen("val=")) == 0) ||
- (strncmp(str, "vals=", strlen("vals=")) == 0) ||
- (strncmp(str, "values=", strlen("values=")) == 0))
- attrs->vals_str = kstrdup(str, GFP_KERNEL);
- else if (strncmp(str, "sort=", strlen("sort=")) == 0)
- attrs->sort_key_str = kstrdup(str, GFP_KERNEL);
- else if (strncmp(str, "name=", strlen("name=")) == 0)
- attrs->name = kstrdup(str, GFP_KERNEL);
- else if (strcmp(str, "pause") == 0)
+ if (strchr(str, '=')) {
+ ret = parse_assignment(str, attrs);
+ if (ret)
+ goto free;
+ } else if (strcmp(str, "pause") == 0)
attrs->pause = true;
else if ((strcmp(str, "cont") == 0) ||
(strcmp(str, "continue") == 0))
attrs->cont = true;
else if (strcmp(str, "clear") == 0)
attrs->clear = true;
- else if (strncmp(str, "size=", strlen("size=")) == 0) {
- int map_bits = parse_map_size(str);
-
- if (map_bits < 0) {
- ret = map_bits;
- goto free;
- }
- attrs->map_bits = map_bits;
- } else {
+ else {
ret = -EINVAL;
goto free;
}

1
debian/patches/features/all/rt/0011-fold-lookup_real-into-__lookup_hash.patch vendored
View File

@ -1,7 +1,6 @@
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 8 Mar 2018 11:00:45 -0500
Subject: [PATCH 11/17] fold lookup_real() into __lookup_hash()
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit a03ece5ff2bd7a9abaa0e8ddfe5f79d79e5984c8

192
debian/patches/features/all/rt/0011-hrtimer-Store-running-timer-in-hrtimer_clock_base.patch vendored
View File

@ -1,192 +0,0 @@
From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Wed, 20 Dec 2017 17:13:00 +0100
Subject: [PATCH 11/29] hrtimer: Store running timer in hrtimer_clock_base
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
The pointer to the currently running timer is stored in hrtimer_cpu_base
before the base lock is dropped and the callback is invoked.
This results in two levels of indirections and the upcoming support for
softirq based hrtimer requires splitting the "running" storage into soft
and hard irq context expiry.
Storing both in the cpu base would require conditionals in all code paths
accessing that information.
It's possible to have a per clock base sequence count and running pointer
without changing the semantics of the related mechanisms because the timer
base pointer cannot be changed while a timer is running the callback.
Unfortunately this makes cpu_clock base larger than 32 bytes on 32bit
kernels. Instead of having huge gaps due to alignment, remove the alignment
and let the compiler pack cpu base for 32bit. The resulting cache access
patterns are fortunately not really different from the current
behaviour. On 64bit kernels the 64byte alignment stays and the behaviour is
unchanged. This was determined by analyzing the resulting layout and
looking at the number of cache lines involved for the frequently used
clocks.
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/linux/hrtimer.h | 20 +++++++++-----------
kernel/time/hrtimer.c | 28 +++++++++++++---------------
2 files changed, 22 insertions(+), 26 deletions(-)
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -118,9 +118,9 @@ struct hrtimer_sleeper {
};
#ifdef CONFIG_64BIT
-# define HRTIMER_CLOCK_BASE_ALIGN 64
+# define __hrtimer_clock_base_align ____cacheline_aligned
#else
-# define HRTIMER_CLOCK_BASE_ALIGN 32
+# define __hrtimer_clock_base_align
#endif
/**
@@ -129,18 +129,22 @@ struct hrtimer_sleeper {
* @index: clock type index for per_cpu support when moving a
* timer to a base on another cpu.
* @clockid: clock id for per_cpu support
+ * @seq: seqcount around __run_hrtimer
+ * @running: pointer to the currently running hrtimer
* @active: red black tree root node for the active timers
* @get_time: function to retrieve the current time of the clock
* @offset: offset of this clock to the monotonic base
*/
struct hrtimer_clock_base {
struct hrtimer_cpu_base *cpu_base;
- int index;
+ unsigned int index;
clockid_t clockid;
+ seqcount_t seq;
+ struct hrtimer *running;
struct timerqueue_head active;
ktime_t (*get_time)(void);
ktime_t offset;
-} __attribute__((__aligned__(HRTIMER_CLOCK_BASE_ALIGN)));
+} __hrtimer_clock_base_align;
enum hrtimer_base_type {
HRTIMER_BASE_MONOTONIC,
@@ -154,8 +158,6 @@ enum hrtimer_base_type {
* struct hrtimer_cpu_base - the per cpu clock bases
* @lock: lock protecting the base and associated clock bases
* and timers
- * @seq: seqcount around __run_hrtimer
- * @running: pointer to the currently running hrtimer
* @cpu: cpu number
* @active_bases: Bitfield to mark bases with active timers
* @clock_was_set_seq: Sequence counter of clock was set events
@@ -177,8 +179,6 @@ enum hrtimer_base_type {
*/
struct hrtimer_cpu_base {
raw_spinlock_t lock;
- seqcount_t seq;
- struct hrtimer *running;
unsigned int cpu;
unsigned int active_bases;
unsigned int clock_was_set_seq;
@@ -198,8 +198,6 @@ struct hrtimer_cpu_base {
static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time)
{
- BUILD_BUG_ON(sizeof(struct hrtimer_clock_base) > HRTIMER_CLOCK_BASE_ALIGN);
-
timer->node.expires = time;
timer->_softexpires = time;
}
@@ -424,7 +422,7 @@ static inline int hrtimer_is_queued(stru
*/
static inline int hrtimer_callback_running(struct hrtimer *timer)
{
- return timer->base->cpu_base->running == timer;
+ return timer->base->running == timer;
}
/* Forward a hrtimer so it expires after now: */
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -70,7 +70,6 @@
DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
{
.lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock),
- .seq = SEQCNT_ZERO(hrtimer_bases.seq),
.clock_base =
{
{
@@ -118,7 +117,6 @@ static const int hrtimer_clock_to_base_t
* timer->base->cpu_base
*/
static struct hrtimer_cpu_base migration_cpu_base = {
- .seq = SEQCNT_ZERO(migration_cpu_base),
.clock_base = { { .cpu_base = &migration_cpu_base, }, },
};
@@ -1150,19 +1148,19 @@ EXPORT_SYMBOL_GPL(hrtimer_init);
*/
bool hrtimer_active(const struct hrtimer *timer)
{
- struct hrtimer_cpu_base *cpu_base;
+ struct hrtimer_clock_base *base;
unsigned int seq;
do {
- cpu_base = READ_ONCE(timer->base->cpu_base);
- seq = raw_read_seqcount_begin(&cpu_base->seq);
+ base = READ_ONCE(timer->base);
+ seq = raw_read_seqcount_begin(&base->seq);
if (timer->state != HRTIMER_STATE_INACTIVE ||
- cpu_base->running == timer)
+ base->running == timer)
return true;
- } while (read_seqcount_retry(&cpu_base->seq, seq) ||
- cpu_base != READ_ONCE(timer->base->cpu_base));
+ } while (read_seqcount_retry(&base->seq, seq) ||
+ base != READ_ONCE(timer->base));
return false;
}
@@ -1196,16 +1194,16 @@ static void __run_hrtimer(struct hrtimer
lockdep_assert_held(&cpu_base->lock);
debug_deactivate(timer);
- cpu_base->running = timer;
+ base->running = timer;
/*
* Separate the ->running assignment from the ->state assignment.
*
* As with a regular write barrier, this ensures the read side in
- * hrtimer_active() cannot observe cpu_base->running == NULL &&
+ * hrtimer_active() cannot observe base->running == NULL &&
* timer->state == INACTIVE.
*/
- raw_write_seqcount_barrier(&cpu_base->seq);
+ raw_write_seqcount_barrier(&base->seq);
__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0);
fn = timer->function;
@@ -1246,13 +1244,13 @@ static void __run_hrtimer(struct hrtimer
* Separate the ->running assignment from the ->state assignment.
*
* As with a regular write barrier, this ensures the read side in
- * hrtimer_active() cannot observe cpu_base->running == NULL &&
+ * hrtimer_active() cannot observe base->running.timer == NULL &&
* timer->state == INACTIVE.
*/
- raw_write_seqcount_barrier(&cpu_base->seq);
+ raw_write_seqcount_barrier(&base->seq);
- WARN_ON_ONCE(cpu_base->running != timer);
- cpu_base->running = NULL;
+ WARN_ON_ONCE(base->running != timer);
+ base->running = NULL;
}
static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now)

243
debian/patches/features/all/rt/0011-tracing-Add-hist-trigger-timestamp-support.patch vendored
View File

@ -1,243 +0,0 @@
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Mon, 15 Jan 2018 20:51:45 -0600
Subject: [PATCH 11/37] tracing: Add hist trigger timestamp support
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
Add support for a timestamp event field. This is actually a 'pseudo-'
event field in that it behaves like it's part of the event record, but
is really part of the corresponding ring buffer event.
To make use of the timestamp field, users can specify
"common_timestamp" as a field name for any histogram. Note that this
doesn't make much sense on its own either as either a key or value,
but needs to be supported even so, since follow-on patches will add
support for making use of this field in time deltas. The
common_timestamp 'field' is not a bona fide event field - so you won't
find it in the event description - but rather it's a synthetic field
that can be used like a real field.
Note that the use of this field requires the ring buffer be put into
'absolute timestamp' mode, which saves the complete timestamp for each
event rather than an offset. This mode will be enabled if and only if
a histogram makes use of the "common_timestamp" field.
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Baohong Liu <baohong.liu@intel.com>
[kasan use-after-free fix]
Signed-off-by: Vedang Patel <vedang.patel@intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/trace/trace_events_hist.c | 94 +++++++++++++++++++++++++++++----------
1 file changed, 71 insertions(+), 23 deletions(-)
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -89,6 +89,12 @@ static u64 hist_field_log2(struct hist_f
return (u64) ilog2(roundup_pow_of_two(val));
}
+static u64 hist_field_timestamp(struct hist_field *hist_field, void *event,
+ struct ring_buffer_event *rbe)
+{
+ return ring_buffer_event_time_stamp(rbe);
+}
+
#define DEFINE_HIST_FIELD_FN(type) \
static u64 hist_field_##type(struct hist_field *hist_field, \
void *event, \
@@ -135,6 +141,7 @@ enum hist_field_flags {
HIST_FIELD_FL_SYSCALL = 1 << 7,
HIST_FIELD_FL_STACKTRACE = 1 << 8,
HIST_FIELD_FL_LOG2 = 1 << 9,
+ HIST_FIELD_FL_TIMESTAMP = 1 << 10,
};
struct hist_trigger_attrs {
@@ -159,6 +166,7 @@ struct hist_trigger_data {
struct trace_event_file *event_file;
struct hist_trigger_attrs *attrs;
struct tracing_map *map;
+ bool enable_timestamps;
};
static const char *hist_field_name(struct hist_field *field,
@@ -173,6 +181,8 @@ static const char *hist_field_name(struc
field_name = field->field->name;
else if (field->flags & HIST_FIELD_FL_LOG2)
field_name = hist_field_name(field->operands[0], ++level);
+ else if (field->flags & HIST_FIELD_FL_TIMESTAMP)
+ field_name = "common_timestamp";
if (field_name == NULL)
field_name = "";
@@ -440,6 +450,12 @@ static struct hist_field *create_hist_fi
goto out;
}
+ if (flags & HIST_FIELD_FL_TIMESTAMP) {
+ hist_field->fn = hist_field_timestamp;
+ hist_field->size = sizeof(u64);
+ goto out;
+ }
+
if (WARN_ON_ONCE(!field))
goto out;
@@ -517,10 +533,15 @@ static int create_val_field(struct hist_
}
}
- field = trace_find_event_field(file->event_call, field_name);
- if (!field || !field->size) {
- ret = -EINVAL;
- goto out;
+ if (strcmp(field_name, "common_timestamp") == 0) {
+ flags |= HIST_FIELD_FL_TIMESTAMP;
+ hist_data->enable_timestamps = true;
+ } else {
+ field = trace_find_event_field(file->event_call, field_name);
+ if (!field || !field->size) {
+ ret = -EINVAL;
+ goto out;
+ }
}
hist_data->fields[val_idx] = create_hist_field(field, flags);
@@ -615,16 +636,22 @@ static int create_key_field(struct hist_
}
}
- field = trace_find_event_field(file->event_call, field_name);
- if (!field || !field->size) {
- ret = -EINVAL;
- goto out;
- }
+ if (strcmp(field_name, "common_timestamp") == 0) {
+ flags |= HIST_FIELD_FL_TIMESTAMP;
+ hist_data->enable_timestamps = true;
+ key_size = sizeof(u64);
+ } else {
+ field = trace_find_event_field(file->event_call, field_name);
+ if (!field || !field->size) {
+ ret = -EINVAL;
+ goto out;
+ }
- if (is_string_field(field))
- key_size = MAX_FILTER_STR_VAL;
- else
- key_size = field->size;
+ if (is_string_field(field))
+ key_size = MAX_FILTER_STR_VAL;
+ else
+ key_size = field->size;
+ }
}
hist_data->fields[key_idx] = create_hist_field(field, flags);
@@ -820,6 +847,9 @@ static int create_tracing_map_fields(str
if (hist_field->flags & HIST_FIELD_FL_STACKTRACE)
cmp_fn = tracing_map_cmp_none;
+ else if (!field)
+ cmp_fn = tracing_map_cmp_num(hist_field->size,
+ hist_field->is_signed);
else if (is_string_field(field))
cmp_fn = tracing_map_cmp_string;
else
@@ -1217,7 +1247,11 @@ static void hist_field_print(struct seq_
{
const char *field_name = hist_field_name(hist_field, 0);
- seq_printf(m, "%s", field_name);
+ if (hist_field->flags & HIST_FIELD_FL_TIMESTAMP)
+ seq_puts(m, "common_timestamp");
+ else if (field_name)
+ seq_printf(m, "%s", field_name);
+
if (hist_field->flags) {
const char *flags_str = get_hist_field_flags(hist_field);
@@ -1268,27 +1302,25 @@ static int event_hist_trigger_print(stru
for (i = 0; i < hist_data->n_sort_keys; i++) {
struct tracing_map_sort_key *sort_key;
+ unsigned int idx;
sort_key = &hist_data->sort_keys[i];
+ idx = sort_key->field_idx;
+
+ if (WARN_ON(idx >= TRACING_MAP_FIELDS_MAX))
+ return -EINVAL;
if (i > 0)
seq_puts(m, ",");
- if (sort_key->field_idx == HITCOUNT_IDX)
+ if (idx == HITCOUNT_IDX)
seq_puts(m, "hitcount");
- else {
- unsigned int idx = sort_key->field_idx;
-
- if (WARN_ON(idx >= TRACING_MAP_FIELDS_MAX))
- return -EINVAL;
-
+ else
hist_field_print(m, hist_data->fields[idx]);
- }
if (sort_key->descending)
seq_puts(m, ".descending");
}
-
seq_printf(m, ":size=%u", (1 << hist_data->map->map_bits));
if (data->filter_str)
@@ -1456,6 +1488,10 @@ static bool hist_trigger_match(struct ev
return false;
if (key_field->offset != key_field_test->offset)
return false;
+ if (key_field->size != key_field_test->size)
+ return false;
+ if (key_field->is_signed != key_field_test->is_signed)
+ return false;
}
for (i = 0; i < hist_data->n_sort_keys; i++) {
@@ -1538,6 +1574,9 @@ static int hist_register_trigger(char *g
update_cond_flag(file);
+ if (hist_data->enable_timestamps)
+ tracing_set_time_stamp_abs(file->tr, true);
+
if (trace_event_trigger_enable_disable(file, 1) < 0) {
list_del_rcu(&data->list);
update_cond_flag(file);
@@ -1572,17 +1611,26 @@ static void hist_unregister_trigger(char
if (unregistered && test->ops->free)
test->ops->free(test->ops, test);
+
+ if (hist_data->enable_timestamps) {
+ if (unregistered)
+ tracing_set_time_stamp_abs(file->tr, false);
+ }
}
static void hist_unreg_all(struct trace_event_file *file)
{
struct event_trigger_data *test, *n;
+ struct hist_trigger_data *hist_data;
list_for_each_entry_safe(test, n, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
+ hist_data = test->private_data;
list_del_rcu(&test->list);
trace_event_trigger_enable_disable(file, 0);
update_cond_flag(file);
+ if (hist_data->enable_timestamps)
+ tracing_set_time_stamp_abs(file->tr, false);
if (test->ops->free)
test->ops->free(test->ops, test);
}

1
debian/patches/features/all/rt/0011-tracing-Add-support-to-detect-and-avoid-duplicates.patch vendored
View File

@ -1,7 +1,6 @@
From: Vedang Patel <vedang.patel@intel.com>
Date: Mon, 15 Jan 2018 20:51:37 -0600
Subject: [PATCH 11/48] tracing: Add support to detect and avoid duplicates
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
A duplicate in the tracing_map hash table is when 2 different entries
have the same key and, as a result, the key_hash. This is possible due

1
debian/patches/features/all/rt/0012-debugfs_lookup-switch-to-lookup_one_len_unlocked.patch vendored
View File

@ -1,7 +1,6 @@
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 8 Mar 2018 11:01:22 -0500
Subject: [PATCH 12/17] debugfs_lookup(): switch to lookup_one_len_unlocked()
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit cd1c0c9321999737073dcfc3364e194e02604bce

34
debian/patches/features/all/rt/0012-hrtimer-Make-room-in-struct-hrtimer_cpu_base.patch vendored
View File

@ -1,34 +0,0 @@
From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Wed, 20 Dec 2017 17:13:01 +0100
Subject: [PATCH 12/29] hrtimer: Make room in struct hrtimer_cpu_base
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
The upcoming softirq based hrtimers support requires an additional field in
the hrtimer_cpu_base struct, which would grow the struct size beyond a
cache line.
The struct members nr_retries and nr_hangs of hrtimer_cpu_base are solely
used for diagnostic output and have no requirement to be unsigned int.
Make them unsigned short to create room for the new struct member. No
functional change.
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/linux/hrtimer.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -189,8 +189,8 @@ struct hrtimer_cpu_base {
ktime_t expires_next;
struct hrtimer *next_timer;
unsigned int nr_events;
- unsigned int nr_retries;
- unsigned int nr_hangs;
+ unsigned short nr_retries;
+ unsigned short nr_hangs;
unsigned int max_hang_time;
#endif
struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES];

221
debian/patches/features/all/rt/0012-tracing-Add-per-element-variable-support-to-tracing_.patch vendored
View File

@ -1,221 +0,0 @@
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Mon, 15 Jan 2018 20:51:46 -0600
Subject: [PATCH 12/37] tracing: Add per-element variable support to
tracing_map
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
In order to allow information to be passed between trace events, add
support for per-element variables to tracing_map. This provides a
means for histograms to associate a value or values with an entry when
it's saved or updated, and retrieved by a subsequent event occurrences.
Variables can be set using tracing_map_set_var() and read using
tracing_map_read_var(). tracing_map_var_set() returns true or false
depending on whether or not the variable has been set or not, which is
important for event-matching applications.
tracing_map_read_var_once() reads the variable and resets it to the
'unset' state, implementing read-once variables, which are also
important for event-matching uses.
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/trace/tracing_map.c | 108 +++++++++++++++++++++++++++++++++++++++++++++
kernel/trace/tracing_map.h | 11 ++++
2 files changed, 119 insertions(+)
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -66,6 +66,73 @@ u64 tracing_map_read_sum(struct tracing_
return (u64)atomic64_read(&elt->fields[i].sum);
}
+/**
+ * tracing_map_set_var - Assign a tracing_map_elt's variable field
+ * @elt: The tracing_map_elt
+ * @i: The index of the given variable associated with the tracing_map_elt
+ * @n: The value to assign
+ *
+ * Assign n to variable i associated with the specified tracing_map_elt
+ * instance. The index i is the index returned by the call to
+ * tracing_map_add_var() when the tracing map was set up.
+ */
+void tracing_map_set_var(struct tracing_map_elt *elt, unsigned int i, u64 n)
+{
+ atomic64_set(&elt->vars[i], n);
+ elt->var_set[i] = true;
+}
+
+/**
+ * tracing_map_var_set - Return whether or not a variable has been set
+ * @elt: The tracing_map_elt
+ * @i: The index of the given variable associated with the tracing_map_elt
+ *
+ * Return true if the variable has been set, false otherwise. The
+ * index i is the index returned by the call to tracing_map_add_var()
+ * when the tracing map was set up.
+ */
+bool tracing_map_var_set(struct tracing_map_elt *elt, unsigned int i)
+{
+ return elt->var_set[i];
+}
+
+/**
+ * tracing_map_read_var - Return the value of a tracing_map_elt's variable field
+ * @elt: The tracing_map_elt
+ * @i: The index of the given variable associated with the tracing_map_elt
+ *
+ * Retrieve the value of the variable i associated with the specified
+ * tracing_map_elt instance. The index i is the index returned by the
+ * call to tracing_map_add_var() when the tracing map was set
+ * up.
+ *
+ * Return: The variable value associated with field i for elt.
+ */
+u64 tracing_map_read_var(struct tracing_map_elt *elt, unsigned int i)
+{
+ return (u64)atomic64_read(&elt->vars[i]);
+}
+
+/**
+ * tracing_map_read_var_once - Return and reset a tracing_map_elt's variable field
+ * @elt: The tracing_map_elt
+ * @i: The index of the given variable associated with the tracing_map_elt
+ *
+ * Retrieve the value of the variable i associated with the specified
+ * tracing_map_elt instance, and reset the variable to the 'not set'
+ * state. The index i is the index returned by the call to
+ * tracing_map_add_var() when the tracing map was set up. The reset
+ * essentially makes the variable a read-once variable if it's only
+ * accessed using this function.
+ *
+ * Return: The variable value associated with field i for elt.
+ */
+u64 tracing_map_read_var_once(struct tracing_map_elt *elt, unsigned int i)
+{
+ elt->var_set[i] = false;
+ return (u64)atomic64_read(&elt->vars[i]);
+}
+
int tracing_map_cmp_string(void *val_a, void *val_b)
{
char *a = val_a;
@@ -171,6 +238,28 @@ int tracing_map_add_sum_field(struct tra
}
/**
+ * tracing_map_add_var - Add a field describing a tracing_map var
+ * @map: The tracing_map
+ *
+ * Add a var to the map and return the index identifying it in the map
+ * and associated tracing_map_elts. This is the index used for
+ * instance to update a var for a particular tracing_map_elt using
+ * tracing_map_update_var() or reading it via tracing_map_read_var().
+ *
+ * Return: The index identifying the var in the map and associated
+ * tracing_map_elts, or -EINVAL on error.
+ */
+int tracing_map_add_var(struct tracing_map *map)
+{
+ int ret = -EINVAL;
+
+ if (map->n_vars < TRACING_MAP_VARS_MAX)
+ ret = map->n_vars++;
+
+ return ret;
+}
+
+/**
* tracing_map_add_key_field - Add a field describing a tracing_map key
* @map: The tracing_map
* @offset: The offset within the key
@@ -280,6 +369,11 @@ static void tracing_map_elt_clear(struct
if (elt->fields[i].cmp_fn == tracing_map_cmp_atomic64)
atomic64_set(&elt->fields[i].sum, 0);
+ for (i = 0; i < elt->map->n_vars; i++) {
+ atomic64_set(&elt->vars[i], 0);
+ elt->var_set[i] = false;
+ }
+
if (elt->map->ops && elt->map->ops->elt_clear)
elt->map->ops->elt_clear(elt);
}
@@ -306,6 +400,8 @@ static void tracing_map_elt_free(struct
if (elt->map->ops && elt->map->ops->elt_free)
elt->map->ops->elt_free(elt);
kfree(elt->fields);
+ kfree(elt->vars);
+ kfree(elt->var_set);
kfree(elt->key);
kfree(elt);
}
@@ -332,6 +428,18 @@ static struct tracing_map_elt *tracing_m
err = -ENOMEM;
goto free;
}
+
+ elt->vars = kcalloc(map->n_vars, sizeof(*elt->vars), GFP_KERNEL);
+ if (!elt->vars) {
+ err = -ENOMEM;
+ goto free;
+ }
+
+ elt->var_set = kcalloc(map->n_vars, sizeof(*elt->var_set), GFP_KERNEL);
+ if (!elt->var_set) {
+ err = -ENOMEM;
+ goto free;
+ }
tracing_map_elt_init_fields(elt);
--- a/kernel/trace/tracing_map.h
+++ b/kernel/trace/tracing_map.h
@@ -10,6 +10,7 @@
#define TRACING_MAP_VALS_MAX 3
#define TRACING_MAP_FIELDS_MAX (TRACING_MAP_KEYS_MAX + \
TRACING_MAP_VALS_MAX)
+#define TRACING_MAP_VARS_MAX 16
#define TRACING_MAP_SORT_KEYS_MAX 2
typedef int (*tracing_map_cmp_fn_t) (void *val_a, void *val_b);
@@ -137,6 +138,8 @@ struct tracing_map_field {
struct tracing_map_elt {
struct tracing_map *map;
struct tracing_map_field *fields;
+ atomic64_t *vars;
+ bool *var_set;
void *key;
void *private_data;
};
@@ -192,6 +195,7 @@ struct tracing_map {
int key_idx[TRACING_MAP_KEYS_MAX];
unsigned int n_keys;
struct tracing_map_sort_key sort_key;
+ unsigned int n_vars;
atomic64_t hits;
atomic64_t drops;
};
@@ -241,6 +245,7 @@ tracing_map_create(unsigned int map_bits
extern int tracing_map_init(struct tracing_map *map);
extern int tracing_map_add_sum_field(struct tracing_map *map);
+extern int tracing_map_add_var(struct tracing_map *map);
extern int tracing_map_add_key_field(struct tracing_map *map,
unsigned int offset,
tracing_map_cmp_fn_t cmp_fn);
@@ -260,7 +265,13 @@ extern int tracing_map_cmp_none(void *va
extern void tracing_map_update_sum(struct tracing_map_elt *elt,
unsigned int i, u64 n);
+extern void tracing_map_set_var(struct tracing_map_elt *elt,
+ unsigned int i, u64 n);
+extern bool tracing_map_var_set(struct tracing_map_elt *elt, unsigned int i);
extern u64 tracing_map_read_sum(struct tracing_map_elt *elt, unsigned int i);
+extern u64 tracing_map_read_var(struct tracing_map_elt *elt, unsigned int i);
+extern u64 tracing_map_read_var_once(struct tracing_map_elt *elt, unsigned int i);
+
extern void tracing_map_set_field_descr(struct tracing_map *map,
unsigned int i,
unsigned int key_offset,

1
debian/patches/features/all/rt/0012-tracing-Remove-code-which-merges-duplicates.patch vendored
View File

@ -1,7 +1,6 @@
From: Vedang Patel <vedang.patel@intel.com>
Date: Mon, 15 Jan 2018 20:51:38 -0600
Subject: [PATCH 12/48] tracing: Remove code which merges duplicates
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
We now have the logic to detect and remove duplicates in the
tracing_map hash table. The code which merges duplicates in the

150
debian/patches/features/all/rt/0013-hrtimer-Reduce-conditional-code-hres_active.patch vendored
View File

@ -1,150 +0,0 @@
From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Wed, 20 Dec 2017 17:13:02 +0100
Subject: [PATCH 13/29] hrtimer: Reduce conditional code (hres_active)
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
The hrtimer_cpu_base struct has the CONFIG_HIGH_RES_TIMERS conditional
struct member hres_active. All related functions to this member are
conditional as well.
There is no functional change, when the hres_active member is
unconditional with all related functions and is set to zero during
initialization.
The conditional code sections can be avoided by adding IS_ENABLED(HIGHRES)
conditionals into common functions, which ensures dead code elimination.
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/linux/hrtimer.h | 20 ++++++++------------
kernel/time/hrtimer.c | 31 +++++++++++++++----------------
2 files changed, 23 insertions(+), 28 deletions(-)
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -161,8 +161,8 @@ enum hrtimer_base_type {
* @cpu: cpu number
* @active_bases: Bitfield to mark bases with active timers
* @clock_was_set_seq: Sequence counter of clock was set events
- * @in_hrtirq: hrtimer_interrupt() is currently executing
* @hres_active: State of high resolution mode
+ * @in_hrtirq: hrtimer_interrupt() is currently executing
* @hang_detected: The last hrtimer interrupt detected a hang
* @expires_next: absolute time of the next event, is required for remote
* hrtimer enqueue
@@ -182,9 +182,9 @@ struct hrtimer_cpu_base {
unsigned int cpu;
unsigned int active_bases;
unsigned int clock_was_set_seq;
+ unsigned int hres_active : 1;
#ifdef CONFIG_HIGH_RES_TIMERS
unsigned int in_hrtirq : 1,
- hres_active : 1,
hang_detected : 1;
ktime_t expires_next;
struct hrtimer *next_timer;
@@ -266,16 +266,17 @@ static inline ktime_t hrtimer_cb_get_tim
return timer->base->get_time();
}
+static inline int hrtimer_is_hres_active(struct hrtimer *timer)
+{
+ return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ?
+ timer->base->cpu_base->hres_active : 0;
+}
+
#ifdef CONFIG_HIGH_RES_TIMERS
struct clock_event_device;
extern void hrtimer_interrupt(struct clock_event_device *dev);
-static inline int hrtimer_is_hres_active(struct hrtimer *timer)
-{
- return timer->base->cpu_base->hres_active;
-}
-
/*
* The resolution of the clocks. The resolution value is returned in
* the clock_getres() system call to give application programmers an
@@ -298,11 +299,6 @@ extern unsigned int hrtimer_resolution;
#define hrtimer_resolution (unsigned int)LOW_RES_NSEC
-static inline int hrtimer_is_hres_active(struct hrtimer *timer)
-{
- return 0;
-}
-
static inline void clock_was_set_delayed(void) { }
#endif
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -512,6 +512,20 @@ static inline ktime_t hrtimer_update_bas
offs_real, offs_boot, offs_tai);
}
+/*
+ * Is the high resolution mode active ?
+ */
+static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base)
+{
+ return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ?
+ cpu_base->hres_active : 0;
+}
+
+static inline int hrtimer_hres_active(void)
+{
+ return __hrtimer_hres_active(this_cpu_ptr(&hrtimer_bases));
+}
+
/* High resolution timer related functions */
#ifdef CONFIG_HIGH_RES_TIMERS
@@ -541,19 +555,6 @@ static inline int hrtimer_is_hres_enable
}
/*
- * Is the high resolution mode active ?
- */
-static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base)
-{
- return cpu_base->hres_active;
-}
-
-static inline int hrtimer_hres_active(void)
-{
- return __hrtimer_hres_active(this_cpu_ptr(&hrtimer_bases));
-}
-
-/*
* Reprogram the event source with checking both queues for the
* next event
* Called with interrupts disabled and base->lock held
@@ -662,7 +663,6 @@ static inline void hrtimer_init_hres(str
{
base->expires_next = KTIME_MAX;
base->hang_detected = 0;
- base->hres_active = 0;
base->next_timer = NULL;
}
@@ -722,8 +722,6 @@ void clock_was_set_delayed(void)
#else
-static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *b) { return 0; }
-static inline int hrtimer_hres_active(void) { return 0; }
static inline int hrtimer_is_hres_enabled(void) { return 0; }
static inline void hrtimer_switch_to_hres(void) { }
static inline void
@@ -1605,6 +1603,7 @@ int hrtimers_prepare_cpu(unsigned int cp
cpu_base->active_bases = 0;
cpu_base->cpu = cpu;
+ cpu_base->hres_active = 0;
hrtimer_init_hres(cpu_base);
return 0;
}

1
debian/patches/features/all/rt/0013-lustre-get-rid-of-pointless-casts-to-struct-dentry.patch vendored
View File

@ -1,7 +1,6 @@
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 9 Mar 2018 18:06:03 -0500
Subject: [PATCH 13/17] lustre: get rid of pointless casts to struct dentry *
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit 5bf1ddf7ee0e23598a620ef9ea2b0f00e804859d

1
debian/patches/features/all/rt/0013-ring-buffer-Add-interface-for-setting-absolute-time-.patch vendored
View File

@ -2,7 +2,6 @@ From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Mon, 15 Jan 2018 20:51:39 -0600
Subject: [PATCH 13/48] ring-buffer: Add interface for setting absolute time
stamps
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Define a new function, tracing_set_time_stamp_abs(), which can be used
to enable or disable the use of absolute timestamps rather than time

79
debian/patches/features/all/rt/0013-tracing-Add-hist_data-member-to-hist_field.patch vendored
View File

@ -1,79 +0,0 @@
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Mon, 15 Jan 2018 20:51:47 -0600
Subject: [PATCH 13/37] tracing: Add hist_data member to hist_field
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
Allow hist_data access via hist_field. Some users of hist_fields
require or will require more access to the associated hist_data.
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/trace/trace_events_hist.c | 14 +++++++++-----
1 file changed, 9 insertions(+), 5 deletions(-)
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -39,6 +39,7 @@ struct hist_field {
unsigned int offset;
unsigned int is_signed;
struct hist_field *operands[HIST_FIELD_OPERANDS_MAX];
+ struct hist_trigger_data *hist_data;
};
static u64 hist_field_none(struct hist_field *field, void *event,
@@ -420,7 +421,8 @@ static void destroy_hist_field(struct hi
kfree(hist_field);
}
-static struct hist_field *create_hist_field(struct ftrace_event_field *field,
+static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
+ struct ftrace_event_field *field,
unsigned long flags)
{
struct hist_field *hist_field;
@@ -432,6 +434,8 @@ static struct hist_field *create_hist_fi
if (!hist_field)
return NULL;
+ hist_field->hist_data = hist_data;
+
if (flags & HIST_FIELD_FL_HITCOUNT) {
hist_field->fn = hist_field_counter;
goto out;
@@ -445,7 +449,7 @@ static struct hist_field *create_hist_fi
if (flags & HIST_FIELD_FL_LOG2) {
unsigned long fl = flags & ~HIST_FIELD_FL_LOG2;
hist_field->fn = hist_field_log2;
- hist_field->operands[0] = create_hist_field(field, fl);
+ hist_field->operands[0] = create_hist_field(hist_data, field, fl);
hist_field->size = hist_field->operands[0]->size;
goto out;
}
@@ -498,7 +502,7 @@ static void destroy_hist_fields(struct h
static int create_hitcount_val(struct hist_trigger_data *hist_data)
{
hist_data->fields[HITCOUNT_IDX] =
- create_hist_field(NULL, HIST_FIELD_FL_HITCOUNT);
+ create_hist_field(hist_data, NULL, HIST_FIELD_FL_HITCOUNT);
if (!hist_data->fields[HITCOUNT_IDX])
return -ENOMEM;
@@ -544,7 +548,7 @@ static int create_val_field(struct hist_
}
}
- hist_data->fields[val_idx] = create_hist_field(field, flags);
+ hist_data->fields[val_idx] = create_hist_field(hist_data, field, flags);
if (!hist_data->fields[val_idx]) {
ret = -ENOMEM;
goto out;
@@ -654,7 +658,7 @@ static int create_key_field(struct hist_
}
}
- hist_data->fields[key_idx] = create_hist_field(field, flags);
+ hist_data->fields[key_idx] = create_hist_field(hist_data, field, flags);
if (!hist_data->fields[key_idx]) {
ret = -ENOMEM;
goto out;

36
debian/patches/features/all/rt/0014-hrtimer-Use-accesor-functions-instead-of-direct-acce.patch vendored
View File

@ -1,36 +0,0 @@
From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Wed, 20 Dec 2017 17:13:03 +0100
Subject: [PATCH 14/29] hrtimer: Use accesor functions instead of direct access
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
__hrtimer_hres_active() is now available unconditionally. Replace the
direct access to hrtimer_cpu_base.hres_active.
No functional change.
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/time/hrtimer.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -564,7 +564,7 @@ hrtimer_force_reprogram(struct hrtimer_c
{
ktime_t expires_next;
- if (!cpu_base->hres_active)
+ if (!__hrtimer_hres_active(cpu_base))
return;
expires_next = __hrtimer_get_next_event(cpu_base);
@@ -673,7 +673,7 @@ static void retrigger_next_event(void *a
{
struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
- if (!base->hres_active)
+ if (!__hrtimer_hres_active(base))
return;
raw_spin_lock(&base->lock);

1
debian/patches/features/all/rt/0014-oprofilefs-don-t-oops-on-allocation-failure.patch vendored
View File

@ -1,7 +1,6 @@
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 10 Mar 2018 16:40:33 -0500
Subject: [PATCH 14/17] oprofilefs: don't oops on allocation failure
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit a7498968338da9b928f5d8054acc8be6ed2bc14c

1
debian/patches/features/all/rt/0014-ring-buffer-Redefine-the-unimplemented-RINGBUF_TYPE_.patch vendored
View File

@ -2,7 +2,6 @@ From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Mon, 15 Jan 2018 20:51:40 -0600
Subject: [PATCH 14/48] ring-buffer: Redefine the unimplemented
RINGBUF_TYPE_TIME_STAMP
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
RINGBUF_TYPE_TIME_STAMP is defined but not used, and from what I can
gather was reserved for something like an absolute timestamp feature

154
debian/patches/features/all/rt/0014-tracing-Add-usecs-modifier-for-hist-trigger-timestam.patch vendored
View File

@ -1,154 +0,0 @@
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Mon, 15 Jan 2018 20:51:48 -0600
Subject: [PATCH 14/37] tracing: Add usecs modifier for hist trigger timestamps
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
Appending .usecs onto a common_timestamp field will cause the
timestamp value to be in microseconds instead of the default
nanoseconds. A typical latency histogram using usecs would look like
this:
# echo 'hist:keys=pid,prio:ts0=common_timestamp.usecs ...
# echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0 ...
This also adds an external trace_clock_in_ns() to trace.c for the
timestamp conversion.
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
Documentation/trace/histogram.txt | 1 +
kernel/trace/trace.c | 13 +++++++++++--
kernel/trace/trace.h | 2 ++
kernel/trace/trace_events_hist.c | 28 ++++++++++++++++++++++------
4 files changed, 36 insertions(+), 8 deletions(-)
--- a/Documentation/trace/histogram.txt
+++ b/Documentation/trace/histogram.txt
@@ -74,6 +74,7 @@
.syscall display a syscall id as a system call name
.execname display a common_pid as a program name
.log2 display log2 value rather than raw number
+ .usecs display a common_timestamp in microseconds
Note that in general the semantics of a given field aren't
interpreted when applying a modifier to it, but there are some
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1170,6 +1170,14 @@ static struct {
ARCH_TRACE_CLOCKS
};
+bool trace_clock_in_ns(struct trace_array *tr)
+{
+ if (trace_clocks[tr->clock_id].in_ns)
+ return true;
+
+ return false;
+}
+
/*
* trace_parser_get_init - gets the buffer for trace parser
*/
@@ -4699,8 +4707,9 @@ static const char readme_msg[] =
"\t .sym display an address as a symbol\n"
"\t .sym-offset display an address as a symbol and offset\n"
"\t .execname display a common_pid as a program name\n"
- "\t .syscall display a syscall id as a syscall name\n\n"
- "\t .log2 display log2 value rather than raw number\n\n"
+ "\t .syscall display a syscall id as a syscall name\n"
+ "\t .log2 display log2 value rather than raw number\n"
+ "\t .usecs display a common_timestamp in microseconds\n\n"
"\t The 'pause' parameter can be used to pause an existing hist\n"
"\t trigger or to start a hist trigger but not log any events\n"
"\t until told to do so. 'continue' can be used to start or\n"
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -289,6 +289,8 @@ extern void trace_array_put(struct trace
extern int tracing_set_time_stamp_abs(struct trace_array *tr, bool abs);
+extern bool trace_clock_in_ns(struct trace_array *tr);
+
/*
* The global tracer (top) should be the first trace array added,
* but we check the flag anyway.
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -90,12 +90,6 @@ static u64 hist_field_log2(struct hist_f
return (u64) ilog2(roundup_pow_of_two(val));
}
-static u64 hist_field_timestamp(struct hist_field *hist_field, void *event,
- struct ring_buffer_event *rbe)
-{
- return ring_buffer_event_time_stamp(rbe);
-}
-
#define DEFINE_HIST_FIELD_FN(type) \
static u64 hist_field_##type(struct hist_field *hist_field, \
void *event, \
@@ -143,6 +137,7 @@ enum hist_field_flags {
HIST_FIELD_FL_STACKTRACE = 1 << 8,
HIST_FIELD_FL_LOG2 = 1 << 9,
HIST_FIELD_FL_TIMESTAMP = 1 << 10,
+ HIST_FIELD_FL_TIMESTAMP_USECS = 1 << 11,
};
struct hist_trigger_attrs {
@@ -153,6 +148,7 @@ struct hist_trigger_attrs {
bool pause;
bool cont;
bool clear;
+ bool ts_in_usecs;
unsigned int map_bits;
};
@@ -170,6 +166,20 @@ struct hist_trigger_data {
bool enable_timestamps;
};
+static u64 hist_field_timestamp(struct hist_field *hist_field, void *event,
+ struct ring_buffer_event *rbe)
+{
+ struct hist_trigger_data *hist_data = hist_field->hist_data;
+ struct trace_array *tr = hist_data->event_file->tr;
+
+ u64 ts = ring_buffer_event_time_stamp(rbe);
+
+ if (hist_data->attrs->ts_in_usecs && trace_clock_in_ns(tr))
+ ts = ns2usecs(ts);
+
+ return ts;
+}
+
static const char *hist_field_name(struct hist_field *field,
unsigned int level)
{
@@ -634,6 +644,8 @@ static int create_key_field(struct hist_
flags |= HIST_FIELD_FL_SYSCALL;
else if (strcmp(field_str, "log2") == 0)
flags |= HIST_FIELD_FL_LOG2;
+ else if (strcmp(field_str, "usecs") == 0)
+ flags |= HIST_FIELD_FL_TIMESTAMP_USECS;
else {
ret = -EINVAL;
goto out;
@@ -643,6 +655,8 @@ static int create_key_field(struct hist_
if (strcmp(field_name, "common_timestamp") == 0) {
flags |= HIST_FIELD_FL_TIMESTAMP;
hist_data->enable_timestamps = true;
+ if (flags & HIST_FIELD_FL_TIMESTAMP_USECS)
+ hist_data->attrs->ts_in_usecs = true;
key_size = sizeof(u64);
} else {
field = trace_find_event_field(file->event_call, field_name);
@@ -1243,6 +1257,8 @@ static const char *get_hist_field_flags(
flags_str = "syscall";
else if (hist_field->flags & HIST_FIELD_FL_LOG2)
flags_str = "log2";
+ else if (hist_field->flags & HIST_FIELD_FL_TIMESTAMP_USECS)
+ flags_str = "usecs";
return flags_str;
}

131
debian/patches/features/all/rt/0015-hrtimer-Make-the-remote-enqueue-check-unconditional.patch vendored
View File

@ -1,131 +0,0 @@
From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Wed, 20 Dec 2017 17:13:04 +0100
Subject: [PATCH 15/29] hrtimer: Make the remote enqueue check unconditional
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
hrtimer_cpu_base.expires_next is used to cache the next event armed in the
timer hardware. The value is used to check whether an hrtimer can be
enqueued remotely. If the new hrtimer is expiring before expires_next, then
remote enqueue is not possible as the remote hrtimer hardware cannot be
accessed for reprogramming to an earlier expiry time.
The remote enqueue check is currently conditional on
CONFIG_HIGH_RES_TIMERS=y and hrtimer_cpu_base.hres_active. There is no
compelling reason to make this conditional.
Move hrtimer_cpu_base.expires_next out of the CONFIG_HIGH_RES_TIMERS=y
guarded area and remove the conditionals in hrtimer_check_target().
The check is currently a NOOP for the CONFIG_HIGH_RES_TIMERS=n and the
!hrtimer_cpu_base.hres_active case because in these cases nothing updates
hrtimer_cpu_base.expires_next yet. This will be changed with later patches
which further reduce the #ifdef zoo in this code.
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/linux/hrtimer.h | 6 +++---
kernel/time/hrtimer.c | 26 ++++++--------------------
2 files changed, 9 insertions(+), 23 deletions(-)
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -164,13 +164,13 @@ enum hrtimer_base_type {
* @hres_active: State of high resolution mode
* @in_hrtirq: hrtimer_interrupt() is currently executing
* @hang_detected: The last hrtimer interrupt detected a hang
- * @expires_next: absolute time of the next event, is required for remote
- * hrtimer enqueue
* @next_timer: Pointer to the first expiring timer
* @nr_events: Total number of hrtimer interrupt events
* @nr_retries: Total number of hrtimer interrupt retries
* @nr_hangs: Total number of hrtimer interrupt hangs
* @max_hang_time: Maximum time spent in hrtimer_interrupt
+ * @expires_next: absolute time of the next event, is required for remote
+ * hrtimer enqueue
* @clock_base: array of clock bases for this cpu
*
* Note: next_timer is just an optimization for __remove_hrtimer().
@@ -186,13 +186,13 @@ struct hrtimer_cpu_base {
#ifdef CONFIG_HIGH_RES_TIMERS
unsigned int in_hrtirq : 1,
hang_detected : 1;
- ktime_t expires_next;
struct hrtimer *next_timer;
unsigned int nr_events;
unsigned short nr_retries;
unsigned short nr_hangs;
unsigned int max_hang_time;
#endif
+ ktime_t expires_next;
struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES];
} ____cacheline_aligned;
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -154,26 +154,21 @@ struct hrtimer_clock_base *lock_hrtimer_
}
/*
- * With HIGHRES=y we do not migrate the timer when it is expiring
- * before the next event on the target cpu because we cannot reprogram
- * the target cpu hardware and we would cause it to fire late.
+ * We do not migrate the timer when it is expiring before the next
+ * event on the target cpu. When high resolution is enabled, we cannot
+ * reprogram the target cpu hardware and we would cause it to fire
+ * late. To keep it simple, we handle the high resolution enabled and
+ * disabled case similar.
*
* Called with cpu_base->lock of target cpu held.
*/
static int
hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
{
-#ifdef CONFIG_HIGH_RES_TIMERS
ktime_t expires;
- if (!new_base->cpu_base->hres_active)
- return 0;
-
expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset);
return expires <= new_base->cpu_base->expires_next;
-#else
- return 0;
-#endif
}
static inline
@@ -657,16 +652,6 @@ static void hrtimer_reprogram(struct hrt
}
/*
- * Initialize the high resolution related parts of cpu_base
- */
-static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
-{
- base->expires_next = KTIME_MAX;
- base->hang_detected = 0;
- base->next_timer = NULL;
-}
-
-/*
* Retrigger next event is called after clock was set
*
* Called with interrupts disabled via on_each_cpu()
@@ -731,7 +716,6 @@ static inline int hrtimer_reprogram(stru
{
return 0;
}
-static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
static inline void retrigger_next_event(void *arg) { }
#endif /* CONFIG_HIGH_RES_TIMERS */
@@ -1604,7 +1588,7 @@ int hrtimers_prepare_cpu(unsigned int cp
cpu_base->active_bases = 0;
cpu_base->cpu = cpu;
cpu_base->hres_active = 0;
- hrtimer_init_hres(cpu_base);
+ cpu_base->expires_next = KTIME_MAX;
return 0;
}

1
debian/patches/features/all/rt/0015-make-non-exchanging-__d_move-copy-d_parent-rather-th.patch vendored
View File

@ -2,7 +2,6 @@ From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 10 Mar 2018 23:15:52 -0500
Subject: [PATCH 15/17] make non-exchanging __d_move() copy ->d_parent rather
than swap them
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Upstream commit 076515fc926793e162fc6525bed1679ef2bbf269

1
debian/patches/features/all/rt/0015-tracing-Add-timestamp_mode-trace-file.patch vendored
View File

@ -1,7 +1,6 @@
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Mon, 15 Jan 2018 20:51:41 -0600
Subject: [PATCH 15/48] tracing: Add timestamp_mode trace file
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.16/older/patches-4.16.8-rt3.tar.xz
Add a new option flag indicating whether or not the ring buffer is in
'absolute timestamp' mode.

779
debian/patches/features/all/rt/0015-tracing-Add-variable-support-to-hist-triggers.patch vendored
View File

@ -1,779 +0,0 @@
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Mon, 15 Jan 2018 20:51:49 -0600
Subject: [PATCH 15/37] tracing: Add variable support to hist triggers
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.15-rt13.tar.xz
Add support for saving the value of a current event's event field by
assigning it to a variable that can be read by a subsequent event.
The basic syntax for saving a variable is to simply prefix a unique
variable name not corresponding to any keyword along with an '=' sign
to any event field.
Both keys and values can be saved and retrieved in this way:
# echo 'hist:keys=next_pid:vals=$ts0:ts0=common_timestamp ...
# echo 'hist:timer_pid=common_pid:key=$timer_pid ...'
If a variable isn't a key variable or prefixed with 'vals=', the
associated event field will be saved in a variable but won't be summed
as a value:
# echo 'hist:keys=next_pid:ts1=common_timestamp:...
Multiple variables can be assigned at the same time:
# echo 'hist:keys=pid:vals=$ts0,$b,field2:ts0=common_timestamp,b=field1 ...
Multiple (or single) variables can also be assigned at the same time
using separate assignments:
# echo 'hist:keys=pid:vals=$ts0:ts0=common_timestamp:b=field1:c=field2 ...
Variables set as above can be used by being referenced from another
event, as described in a subsequent patch.
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Baohong Liu <baohong.liu@intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/trace/trace_events_hist.c | 370 ++++++++++++++++++++++++++++++++++-----
1 file changed, 331 insertions(+), 39 deletions(-)
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -30,6 +30,13 @@ typedef u64 (*hist_field_fn_t) (struct h
struct ring_buffer_event *rbe);
#define HIST_FIELD_OPERANDS_MAX 2
+#define HIST_FIELDS_MAX (TRACING_MAP_FIELDS_MAX + TRACING_MAP_VARS_MAX)
+
+struct hist_var {
+ char *name;
+ struct hist_trigger_data *hist_data;
+ unsigned int idx;
+};
struct hist_field {
struct ftrace_event_field *field;
@@ -40,6 +47,7 @@ struct hist_field {
unsigned int is_signed;
struct hist_field *operands[HIST_FIELD_OPERANDS_MAX];
struct hist_trigger_data *hist_data;
+ struct hist_var var;
};
static u64 hist_field_none(struct hist_field *field, void *event,
@@ -138,6 +146,13 @@ enum hist_field_flags {
HIST_FIELD_FL_LOG2 = 1 << 9,
HIST_FIELD_FL_TIMESTAMP = 1 << 10,
HIST_FIELD_FL_TIMESTAMP_USECS = 1 << 11,
+ HIST_FIELD_FL_VAR = 1 << 12,
+};
+
+struct var_defs {
+ unsigned int n_vars;
+ char *name[TRACING_MAP_VARS_MAX];
+ char *expr[TRACING_MAP_VARS_MAX];
};
struct hist_trigger_attrs {
@@ -150,13 +165,19 @@ struct hist_trigger_attrs {
bool clear;
bool ts_in_usecs;
unsigned int map_bits;
+
+ char *assignment_str[TRACING_MAP_VARS_MAX];
+ unsigned int n_assignments;
+
+ struct var_defs var_defs;
};
struct hist_trigger_data {
- struct hist_field *fields[TRACING_MAP_FIELDS_MAX];
+ struct hist_field *fields[HIST_FIELDS_MAX];
unsigned int n_vals;
unsigned int n_keys;
unsigned int n_fields;
+ unsigned int n_vars;
unsigned int key_size;
struct tracing_map_sort_key sort_keys[TRACING_MAP_SORT_KEYS_MAX];
unsigned int n_sort_keys;
@@ -164,6 +185,7 @@ struct hist_trigger_data {
struct hist_trigger_attrs *attrs;
struct tracing_map *map;
bool enable_timestamps;
+ bool remove;
};
static u64 hist_field_timestamp(struct hist_field *hist_field, void *event,
@@ -180,6 +202,48 @@ static u64 hist_field_timestamp(struct h
return ts;
}
+static struct hist_field *find_var_field(struct hist_trigger_data *hist_data,
+ const char *var_name)
+{
+ struct hist_field *hist_field, *found = NULL;
+ int i;
+
+ for_each_hist_field(i, hist_data) {
+ hist_field = hist_data->fields[i];
+ if (hist_field && hist_field->flags & HIST_FIELD_FL_VAR &&
+ strcmp(hist_field->var.name, var_name) == 0) {
+ found = hist_field;
+ break;
+ }
+ }
+
+ return found;
+}
+
+static struct hist_field *find_var(struct hist_trigger_data *hist_data,
+ struct trace_event_file *file,
+ const char *var_name)
+{
+ struct hist_trigger_data *test_data;
+ struct event_trigger_data *test;
+ struct hist_field *hist_field;
+
+ hist_field = find_var_field(hist_data, var_name);
+ if (hist_field)
+ return hist_field;
+
+ list_for_each_entry_rcu(test, &file->triggers, list) {
+ if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
+ test_data = test->private_data;
+ hist_field = find_var_field(test_data, var_name);
+ if (hist_field)
+ return hist_field;
+ }
+ }
+
+ return NULL;
+}
+
static const char *hist_field_name(struct hist_field *field,
unsigned int level)
{
@@ -262,9 +326,14 @@ static int parse_map_size(char *str)
static void destroy_hist_trigger_attrs(struct hist_trigger_attrs *attrs)
{
+ unsigned int i;
+
if (!attrs)
return;
+ for (i = 0; i < attrs->n_assignments; i++)
+ kfree(attrs->assignment_str[i]);
+
kfree(attrs->name);
kfree(attrs->sort_key_str);
kfree(attrs->keys_str);
@@ -311,8 +380,22 @@ static int parse_assignment(char *str, s
goto out;
}
attrs->map_bits = map_bits;
- } else
- ret = -EINVAL;
+ } else {
+ char *assignment;
+
+ if (attrs->n_assignments == TRACING_MAP_VARS_MAX) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ assignment = kstrdup(str, GFP_KERNEL);
+ if (!assignment) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ attrs->assignment_str[attrs->n_assignments++] = assignment;
+ }
out:
return ret;
}
@@ -428,12 +511,15 @@ static void destroy_hist_field(struct hi
for (i = 0; i < HIST_FIELD_OPERANDS_MAX; i++)
destroy_hist_field(hist_field->operands[i], level + 1);
+ kfree(hist_field->var.name);
+
kfree(hist_field);
}
static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
struct ftrace_event_field *field,
- unsigned long flags)
+ unsigned long flags,
+ char *var_name)
{
struct hist_field *hist_field;
@@ -459,7 +545,7 @@ static struct hist_field *create_hist_fi
if (flags & HIST_FIELD_FL_LOG2) {
unsigned long fl = flags & ~HIST_FIELD_FL_LOG2;
hist_field->fn = hist_field_log2;
- hist_field->operands[0] = create_hist_field(hist_data, field, fl);
+ hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL);
hist_field->size = hist_field->operands[0]->size;
goto out;
}
@@ -494,14 +580,23 @@ static struct hist_field *create_hist_fi
hist_field->field = field;
hist_field->flags = flags;
+ if (var_name) {
+ hist_field->var.name = kstrdup(var_name, GFP_KERNEL);
+ if (!hist_field->var.name)
+ goto free;
+ }
+
return hist_field;
+ free:
+ destroy_hist_field(hist_field, 0);
+ return NULL;
}
static void destroy_hist_fields(struct hist_trigger_data *hist_data)
{
unsigned int i;
- for (i = 0; i < TRACING_MAP_FIELDS_MAX; i++) {
+ for (i = 0; i < HIST_FIELDS_MAX; i++) {
if (hist_data->fields[i]) {
destroy_hist_field(hist_data->fields[i], 0);
hist_data->fields[i] = NULL;
@@ -512,11 +607,12 @@ static void destroy_hist_fields(struct h
static int create_hitcount_val(struct hist_trigger_data *hist_data)
{
hist_data->fields[HITCOUNT_IDX] =
- create_hist_field(hist_data, NULL, HIST_FIELD_FL_HITCOUNT);
+ create_hist_field(hist_data, NULL, HIST_FIELD_FL_HITCOUNT, NULL);
if (!hist_data->fields[HITCOUNT_IDX])
return -ENOMEM;
hist_data->n_vals++;
+ hist_data->n_fields++;
if (WARN_ON(hist_data->n_vals > TRACING_MAP_VALS_MAX))
return -EINVAL;
@@ -524,19 +620,16 @@ static int create_hitcount_val(struct hi
return 0;
}
-static int create_val_field(struct hist_trigger_data *hist_data,
- unsigned int val_idx,
- struct trace_event_file *file,
- char *field_str)
+static int __create_val_field(struct hist_trigger_data *hist_data,
+ unsigned int val_idx,
+ struct trace_event_file *file,
+ char *var_name, char *field_str,
+ unsigned long flags)
{
struct ftrace_event_field *field = NULL;
- unsigned long flags = 0;
char *field_name;
int ret = 0;
- if (WARN_ON(val_idx >= TRACING_MAP_VALS_MAX))
- return -EINVAL;
-
field_name = strsep(&field_str, ".");
if (field_str) {
if (strcmp(field_str, "hex") == 0)
@@ -558,25 +651,58 @@ static int create_val_field(struct hist_
}
}
- hist_data->fields[val_idx] = create_hist_field(hist_data, field, flags);
+ hist_data->fields[val_idx] = create_hist_field(hist_data, field, flags, var_name);
if (!hist_data->fields[val_idx]) {
ret = -ENOMEM;
goto out;
}
++hist_data->n_vals;
+ ++hist_data->n_fields;
- if (WARN_ON(hist_data->n_vals > TRACING_MAP_VALS_MAX))
+ if (WARN_ON(hist_data->n_vals > TRACING_MAP_VALS_MAX + TRACING_MAP_VARS_MAX))
ret = -EINVAL;
out:
return ret;
}
+static int create_val_field(struct hist_trigger_data *hist_data,
+ unsigned int val_idx,
+ struct trace_event_file *file,
+ char *field_str)
+{
+ if (WARN_ON(val_idx >= TRACING_MAP_VALS_MAX))
+ return -EINVAL;
+
+ return __create_val_field(hist_data, val_idx, file, NULL, field_str, 0);
+}
+
+static int create_var_field(struct hist_trigger_data *hist_data,
+ unsigned int val_idx,
+ struct trace_event_file *file,
+ char *var_name, char *expr_str)
+{
+ unsigned long flags = 0;
+
+ if (WARN_ON(val_idx >= TRACING_MAP_VALS_MAX + TRACING_MAP_VARS_MAX))
+ return -EINVAL;
+ if (find_var(hist_data, file, var_name) && !hist_data->remove) {
+ return -EINVAL;
+ }
+
+ flags |= HIST_FIELD_FL_VAR;
+ hist_data->n_vars++;
+ if (WARN_ON(hist_data->n_vars > TRACING_MAP_VARS_MAX))
+ return -EINVAL;
+
+ return __create_val_field(hist_data, val_idx, file, var_name, expr_str, flags);
+}
+
static int create_val_fields(struct hist_trigger_data *hist_data,
struct trace_event_file *file)
{
char *fields_str, *field_str;
- unsigned int i, j;
+ unsigned int i, j = 1;
int ret;
ret = create_hitcount_val(hist_data);
@@ -596,12 +722,15 @@ static int create_val_fields(struct hist
field_str = strsep(&fields_str, ",");
if (!field_str)
break;
+
if (strcmp(field_str, "hitcount") == 0)
continue;
+
ret = create_val_field(hist_data, j++, file, field_str);
if (ret)
goto out;
}
+
if (fields_str && (strcmp(fields_str, "hitcount") != 0))
ret = -EINVAL;
out:
@@ -615,11 +744,12 @@ static int create_key_field(struct hist_
char *field_str)
{
struct ftrace_event_field *field = NULL;
+ struct hist_field *hist_field = NULL;
unsigned long flags = 0;
unsigned int key_size;
int ret = 0;
- if (WARN_ON(key_idx >= TRACING_MAP_FIELDS_MAX))
+ if (WARN_ON(key_idx >= HIST_FIELDS_MAX))
return -EINVAL;
flags |= HIST_FIELD_FL_KEY;
@@ -627,6 +757,7 @@ static int create_key_field(struct hist_
if (strcmp(field_str, "stacktrace") == 0) {
flags |= HIST_FIELD_FL_STACKTRACE;
key_size = sizeof(unsigned long) * HIST_STACKTRACE_DEPTH;
+ hist_field = create_hist_field(hist_data, NULL, flags, NULL);
} else {
char *field_name = strsep(&field_str, ".");
@@ -672,7 +803,7 @@ static int create_key_field(struct hist_
}
}
- hist_data->fields[key_idx] = create_hist_field(hist_data, field, flags);
+ hist_data->fields[key_idx] = create_hist_field(hist_data, field, flags, NULL);
if (!hist_data->fields[key_idx]) {
ret = -ENOMEM;
goto out;
@@ -688,6 +819,7 @@ static int create_key_field(struct hist_
}
hist_data->n_keys++;
+ hist_data->n_fields++;
if (WARN_ON(hist_data->n_keys > TRACING_MAP_KEYS_MAX))
return -EINVAL;
@@ -731,21 +863,111 @@ static int create_key_fields(struct hist
return ret;
}
+static int create_var_fields(struct hist_trigger_data *hist_data,
+ struct trace_event_file *file)
+{
+ unsigned int i, j = hist_data->n_vals;
+ int ret = 0;
+
+ unsigned int n_vars = hist_data->attrs->var_defs.n_vars;
+
+ for (i = 0; i < n_vars; i++) {
+ char *var_name = hist_data->attrs->var_defs.name[i];
+ char *expr = hist_data->attrs->var_defs.expr[i];
+
+ ret = create_var_field(hist_data, j++, file, var_name, expr);
+ if (ret)
+ goto out;
+ }
+ out:
+ return ret;
+}
+
+static void free_var_defs(struct hist_trigger_data *hist_data)
+{
+ unsigned int i;
+
+ for (i = 0; i < hist_data->attrs->var_defs.n_vars; i++) {
+ kfree(hist_data->attrs->var_defs.name[i]);
+ kfree(hist_data->attrs->var_defs.expr[i]);
+ }
+
+ hist_data->attrs->var_defs.n_vars = 0;
+}
+
+static int parse_var_defs(struct hist_trigger_data *hist_data)
+{
+ char *s, *str, *var_name, *field_str;
+ unsigned int i, j, n_vars = 0;
+ int ret = 0;
+
+ for (i = 0; i < hist_data->attrs->n_assignments; i++) {
+ str = hist_data->attrs->assignment_str[i];
+ for (j = 0; j < TRACING_MAP_VARS_MAX; j++) {
+ field_str = strsep(&str, ",");
+ if (!field_str)
+ break;
+
+ var_name = strsep(&field_str, "=");
+ if (!var_name || !field_str) {
+ ret = -EINVAL;
+ goto free;
+ }
+
+ if (n_vars == TRACING_MAP_VARS_MAX) {
+ ret = -EINVAL;
+ goto free;
+ }
+
+ s = kstrdup(var_name, GFP_KERNEL);
+ if (!s) {
+ ret = -ENOMEM;
+ goto free;
+ }
+ hist_data->attrs->var_defs.name[n_vars] = s;
+
+ s = kstrdup(field_str, GFP_KERNEL);
+ if (!s) {
+ kfree(hist_data->attrs->var_defs.name[n_vars]);
+ ret = -ENOMEM;
+ goto free;
+ }
+ hist_data->attrs->var_defs.expr[n_vars++] = s;
+
+ hist_data->attrs->var_defs.n_vars = n_vars;
+ }
+ }
+
+ return ret;
+ free:
+ free_var_defs(hist_data);
+
+ return ret;
+}
+
static int create_hist_fields(struct hist_trigger_data *hist_data,
struct trace_event_file *file)
{
int ret;
+ ret = parse_var_defs(hist_data);
+ if (ret)
+ goto out;
+
ret = create_val_fields(hist_data, file);
if (ret)
goto out;
- ret = create_key_fields(hist_data, file);
+ ret = create_var_fields(hist_data, file);
if (ret)
goto out;
- hist_data->n_fields = hist_data->n_vals + hist_data->n_keys;
+ ret = create_key_fields(hist_data, file);
+ if (ret)
+ goto out;
out:
+ free_var_defs(hist_data);
+
return ret;
}
@@ -768,7 +990,7 @@ static int create_sort_keys(struct hist_
char *fields_str = hist_data->attrs->sort_key_str;
struct tracing_map_sort_key *sort_key;
int descending, ret = 0;
- unsigned int i, j;
+ unsigned int i, j, k;
hist_data->n_sort_keys = 1; /* we always have at least one, hitcount */
@@ -816,12 +1038,19 @@ static int create_sort_keys(struct hist_
continue;
}
- for (j = 1; j < hist_data->n_fields; j++) {
+ for (j = 1, k = 1; j < hist_data->n_fields; j++) {
+ unsigned int idx;
+
hist_field = hist_data->fields[j];
+ if (hist_field->flags & HIST_FIELD_FL_VAR)
+ continue;
+
+ idx = k++;
+
test_name = hist_field_name(hist_field, 0);
if (strcmp(field_name, test_name) == 0) {
- sort_key->field_idx = j;
+ sort_key->field_idx = idx;
descending = is_descending(field_str);
if (descending < 0) {
ret = descending;
@@ -836,6 +1065,7 @@ static int create_sort_keys(struct hist_
break;
}
}
+
hist_data->n_sort_keys = i;
out:
return ret;
@@ -876,12 +1106,19 @@ static int create_tracing_map_fields(str
idx = tracing_map_add_key_field(map,
hist_field->offset,
cmp_fn);
-
- } else
+ } else if (!(hist_field->flags & HIST_FIELD_FL_VAR))
idx = tracing_map_add_sum_field(map);
if (idx < 0)
return idx;
+
+ if (hist_field->flags & HIST_FIELD_FL_VAR) {
+ idx = tracing_map_add_var(map);
+ if (idx < 0)
+ return idx;
+ hist_field->var.idx = idx;
+ hist_field->var.hist_data = hist_data;
+ }
}
return 0;
@@ -905,7 +1142,8 @@ static bool need_tracing_map_ops(struct
static struct hist_trigger_data *
create_hist_data(unsigned int map_bits,
struct hist_trigger_attrs *attrs,
- struct trace_event_file *file)
+ struct trace_event_file *file,
+ bool remove)
{
const struct tracing_map_ops *map_ops = NULL;
struct hist_trigger_data *hist_data;
@@ -916,6 +1154,7 @@ create_hist_data(unsigned int map_bits,
return ERR_PTR(-ENOMEM);
hist_data->attrs = attrs;
+ hist_data->remove = remove;
ret = create_hist_fields(hist_data, file);
if (ret)
@@ -962,14 +1201,28 @@ static void hist_trigger_elt_update(stru
struct ring_buffer_event *rbe)
{
struct hist_field *hist_field;
- unsigned int i;
+ unsigned int i, var_idx;
u64 hist_val;
for_each_hist_val_field(i, hist_data) {
hist_field = hist_data->fields[i];
hist_val = hist_field->fn(hist_field, rec, rbe);
+ if (hist_field->flags & HIST_FIELD_FL_VAR) {
+ var_idx = hist_field->var.idx;
+ tracing_map_set_var(elt, var_idx, hist_val);
+ continue;
+ }
tracing_map_update_sum(elt, i, hist_val);
}
+
+ for_each_hist_key_field(i, hist_data) {
+ hist_field = hist_data->fields[i];
+ if (hist_field->flags & HIST_FIELD_FL_VAR) {
+ hist_val = hist_field->fn(hist_field, rec, rbe);
+ var_idx = hist_field->var.idx;
+ tracing_map_set_var(elt, var_idx, hist_val);
+ }
+ }
}
static inline void add_to_key(char *compound_key, void *key,
@@ -1144,6 +1397,9 @@ hist_trigger_entry_print(struct seq_file
for (i = 1; i < hist_data->n_vals; i++) {
field_name = hist_field_name(hist_data->fields[i], 0);
+ if (hist_data->fields[i]->flags & HIST_FIELD_FL_VAR)
+ continue;
+
if (hist_data->fields[i]->flags & HIST_FIELD_FL_HEX) {
seq_printf(m, " %s: %10llx", field_name,
tracing_map_read_sum(elt, i));
@@ -1267,6 +1523,9 @@ static void hist_field_print(struct seq_
{
const char *field_name = hist_field_name(hist_field, 0);
+ if (hist_field->var.name)
+ seq_printf(m, "%s=", hist_field->var.name);
+
if (hist_field->flags & HIST_FIELD_FL_TIMESTAMP)
seq_puts(m, "common_timestamp");
else if (field_name)
@@ -1285,7 +1544,8 @@ static int event_hist_trigger_print(stru
struct event_trigger_data *data)
{
struct hist_trigger_data *hist_data = data->private_data;
- struct hist_field *key_field;
+ struct hist_field *field;
+ bool have_var = false;
unsigned int i;
seq_puts(m, "hist:");
@@ -1296,25 +1556,47 @@ static int event_hist_trigger_print(stru
seq_puts(m, "keys=");
for_each_hist_key_field(i, hist_data) {
- key_field = hist_data->fields[i];
+ field = hist_data->fields[i];
if (i > hist_data->n_vals)
seq_puts(m, ",");
- if (key_field->flags & HIST_FIELD_FL_STACKTRACE)
+ if (field->flags & HIST_FIELD_FL_STACKTRACE)
seq_puts(m, "stacktrace");
else
- hist_field_print(m, key_field);
+ hist_field_print(m, field);
}
seq_puts(m, ":vals=");
for_each_hist_val_field(i, hist_data) {
+ field = hist_data->fields[i];
+ if (field->flags & HIST_FIELD_FL_VAR) {
+ have_var = true;
+ continue;
+ }
+
if (i == HITCOUNT_IDX)
seq_puts(m, "hitcount");
else {
seq_puts(m, ",");
- hist_field_print(m, hist_data->fields[i]);
+ hist_field_print(m, field);
+ }
+ }
+
+ if (have_var) {
+ unsigned int n = 0;
+
+ seq_puts(m, ":");
+
+ for_each_hist_val_field(i, hist_data) {
+ field = hist_data->fields[i];
+
+ if (field->flags & HIST_FIELD_FL_VAR) {
+ if (n++)
+ seq_puts(m, ",");
+ hist_field_print(m, field);
+ }
}
}
@@ -1322,7 +1604,10 @@ static int event_hist_trigger_print(stru
for (i = 0; i < hist_data->n_sort_keys; i++) {
struct tracing_map_sort_key *sort_key;
- unsigned int idx;
+ unsigned int idx, first_key_idx;
+
+ /* skip VAR vals */
+ first_key_idx = hist_data->n_vals - hist_data->n_vars;
sort_key = &hist_data->sort_keys[i];
idx = sort_key->field_idx;
@@ -1335,8 +1620,11 @@ static int event_hist_trigger_print(stru
if (idx == HITCOUNT_IDX)
seq_puts(m, "hitcount");
- else
+ else {
+ if (idx >= first_key_idx)
+ idx += hist_data->n_vars;
hist_field_print(m, hist_data->fields[idx]);
+ }
if (sort_key->descending)
seq_puts(m, ".descending");
@@ -1633,7 +1921,7 @@ static void hist_unregister_trigger(char
test->ops->free(test->ops, test);
if (hist_data->enable_timestamps) {
- if (unregistered)
+ if (!hist_data->remove || unregistered)
tracing_set_time_stamp_abs(file->tr, false);
}
}
@@ -1666,12 +1954,16 @@ static int event_hist_trigger_func(struc
struct hist_trigger_attrs *attrs;
struct event_trigger_ops *trigger_ops;
struct hist_trigger_data *hist_data;
+ bool remove = false;
char *trigger;
int ret = 0;
if (!param)
return -EINVAL;
+ if (glob[0] == '!')
+ remove = true;
+
/* separate the trigger from the filter (k:v [if filter]) */
trigger = strsep(&param, " \t");
if (!trigger)
@@ -1684,7 +1976,7 @@ static int event_hist_trigger_func(struc
if (attrs->map_bits)
hist_trigger_bits = attrs->map_bits;
- hist_data = create_hist_data(hist_trigger_bits, attrs, file);
+ hist_data = create_hist_data(hist_trigger_bits, attrs, file, remove);
if (IS_ERR(hist_data)) {
destroy_hist_trigger_attrs(attrs);
return PTR_ERR(hist_data);
@@ -1713,7 +2005,7 @@ static int event_hist_trigger_func(struc
goto out_free;
}
- if (glob[0] == '!') {
+ if (remove) {
cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file);
ret = 0;
goto out_free;

Some files were not shown because too many files have changed in this diff Show More