* [PATCH v6 16/46] time/clocksource: Use get/put_online_cpus_atomic() to prevent CPU offline
From: Srivatsa S. Bhat @ 2013-02-18 12:40 UTC (permalink / raw)
To: tglx, peterz, tj, oleg, paulmck, rusty, mingo, akpm, namhyung
Cc: rostedt, wangyun, xiaoguangrong, rjw, sbw, fweisbec, linux,
nikunj, srivatsa.bhat, linux-pm, linux-arch, linux-arm-kernel,
linuxppc-dev, netdev, linux-doc, linux-kernel, walken,
vincent.guittot
In-Reply-To: <20130218123714.26245.61816.stgit@srivatsabhat.in.ibm.com>
Once stop_machine() is gone from the CPU offline path, we won't be able to
depend on preempt_disable() or local_irq_disable() to prevent CPUs from going
offline from under us.
Use the get/put_online_cpus_atomic() APIs to prevent CPUs from going offline,
while invoking from atomic context.
Cc: John Stultz <john.stultz@linaro.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
---
kernel/time/clocksource.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index c958338..1c8d735 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -30,6 +30,7 @@
#include <linux/sched.h> /* for spin_unlock_irq() using preempt_count() m68k */
#include <linux/tick.h>
#include <linux/kthread.h>
+#include <linux/cpu.h>
void timecounter_init(struct timecounter *tc,
const struct cyclecounter *cc,
@@ -320,11 +321,13 @@ static void clocksource_watchdog(unsigned long data)
* Cycle through CPUs to check if the CPUs stay synchronized
* to each other.
*/
+ get_online_cpus_atomic();
next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask);
if (next_cpu >= nr_cpu_ids)
next_cpu = cpumask_first(cpu_online_mask);
watchdog_timer.expires += WATCHDOG_INTERVAL;
add_timer_on(&watchdog_timer, next_cpu);
+ put_online_cpus_atomic();
out:
spin_unlock(&watchdog_lock);
}
@@ -336,7 +339,9 @@ static inline void clocksource_start_watchdog(void)
init_timer(&watchdog_timer);
watchdog_timer.function = clocksource_watchdog;
watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
+ get_online_cpus_atomic();
add_timer_on(&watchdog_timer, cpumask_first(cpu_online_mask));
+ put_online_cpus_atomic();
watchdog_running = 1;
}
^ permalink raw reply related
* [PATCH v6 15/46] tick: Use get/put_online_cpus_atomic() to prevent CPU offline
From: Srivatsa S. Bhat @ 2013-02-18 12:40 UTC (permalink / raw)
To: tglx, peterz, tj, oleg, paulmck, rusty, mingo, akpm, namhyung
Cc: rostedt, wangyun, xiaoguangrong, rjw, sbw, fweisbec, linux,
nikunj, srivatsa.bhat, linux-pm, linux-arch, linux-arm-kernel,
linuxppc-dev, netdev, linux-doc, linux-kernel, walken,
vincent.guittot
In-Reply-To: <20130218123714.26245.61816.stgit@srivatsabhat.in.ibm.com>
Once stop_machine() is gone from the CPU offline path, we won't be able to
depend on preempt_disable() or local_irq_disable() to prevent CPUs from
going offline from under us.
Use the get/put_online_cpus_atomic() APIs to prevent CPUs from going offline,
while invoking from atomic context.
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
---
kernel/time/tick-broadcast.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index f113755..d123a2c 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -160,6 +160,7 @@ static void tick_do_broadcast(struct cpumask *mask)
*/
static void tick_do_periodic_broadcast(void)
{
+ get_online_cpus_atomic();
raw_spin_lock(&tick_broadcast_lock);
cpumask_and(to_cpumask(tmpmask),
@@ -167,6 +168,7 @@ static void tick_do_periodic_broadcast(void)
tick_do_broadcast(to_cpumask(tmpmask));
raw_spin_unlock(&tick_broadcast_lock);
+ put_online_cpus_atomic();
}
/*
^ permalink raw reply related
* [PATCH v6 14/46] sched/rt: Use get/put_online_cpus_atomic() to prevent CPU offline
From: Srivatsa S. Bhat @ 2013-02-18 12:40 UTC (permalink / raw)
To: tglx, peterz, tj, oleg, paulmck, rusty, mingo, akpm, namhyung
Cc: rostedt, wangyun, xiaoguangrong, rjw, sbw, fweisbec, linux,
nikunj, srivatsa.bhat, linux-pm, linux-arch, linux-arm-kernel,
linuxppc-dev, netdev, linux-doc, linux-kernel, walken,
vincent.guittot
In-Reply-To: <20130218123714.26245.61816.stgit@srivatsabhat.in.ibm.com>
Once stop_machine() is gone from the CPU offline path, we won't be able to
depend on preempt_disable() or local_irq_disable() to prevent CPUs from
going offline from under us.
Use the get/put_online_cpus_atomic() APIs to prevent CPUs from going offline,
while invoking from atomic context.
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
---
kernel/sched/rt.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 4f02b28..e546c98 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -6,6 +6,7 @@
#include "sched.h"
#include <linux/slab.h>
+#include <linux/cpu.h>
static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
@@ -26,7 +27,9 @@ static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer)
if (!overrun)
break;
+ get_online_cpus_atomic();
idle = do_sched_rt_period_timer(rt_b, overrun);
+ put_online_cpus_atomic();
}
return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
^ permalink raw reply related
* [PATCH v6 13/46] sched/migration: Use raw_spin_lock/unlock since interrupts are already disabled
From: Srivatsa S. Bhat @ 2013-02-18 12:40 UTC (permalink / raw)
To: tglx, peterz, tj, oleg, paulmck, rusty, mingo, akpm, namhyung
Cc: rostedt, wangyun, xiaoguangrong, rjw, sbw, fweisbec, linux,
nikunj, srivatsa.bhat, linux-pm, linux-arch, linux-arm-kernel,
linuxppc-dev, netdev, linux-doc, linux-kernel, walken,
vincent.guittot
In-Reply-To: <20130218123714.26245.61816.stgit@srivatsabhat.in.ibm.com>
We need not use the raw_spin_lock_irqsave/restore primitives because
all CPU_DYING notifiers run with interrupts disabled. So just use
raw_spin_lock/unlock.
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
---
kernel/sched/core.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ead8af6..71741d0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4870,9 +4870,7 @@ static void calc_load_migrate(struct rq *rq)
* Migrate all tasks from the rq, sleeping tasks will be migrated by
* try_to_wake_up()->select_task_rq().
*
- * Called with rq->lock held even though we'er in stop_machine() and
- * there's no concurrency possible, we hold the required locks anyway
- * because of lock validation efforts.
+ * Called with rq->lock held.
*/
static void migrate_tasks(unsigned int dead_cpu)
{
@@ -4884,8 +4882,8 @@ static void migrate_tasks(unsigned int dead_cpu)
* Fudge the rq selection such that the below task selection loop
* doesn't get stuck on the currently eligible stop task.
*
- * We're currently inside stop_machine() and the rq is either stuck
- * in the stop_machine_cpu_stop() loop, or we're executing this code,
+ * We're currently inside stop_one_cpu() and the rq is either stuck
+ * in the cpu_stopper_thread(), or we're executing this code,
* either way we should never end up calling schedule() until we're
* done here.
*/
@@ -5154,14 +5152,14 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
case CPU_DYING:
sched_ttwu_pending();
/* Update our root-domain */
- raw_spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock(&rq->lock); /* Interrupts already disabled */
if (rq->rd) {
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
set_rq_offline(rq);
}
migrate_tasks(cpu);
BUG_ON(rq->nr_running != 1); /* the migration thread */
- raw_spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock(&rq->lock);
break;
case CPU_DEAD:
^ permalink raw reply related
* [PATCH v6 12/46] sched/timer: Use get/put_online_cpus_atomic() to prevent CPU offline
From: Srivatsa S. Bhat @ 2013-02-18 12:40 UTC (permalink / raw)
To: tglx, peterz, tj, oleg, paulmck, rusty, mingo, akpm, namhyung
Cc: rostedt, wangyun, xiaoguangrong, rjw, sbw, fweisbec, linux,
nikunj, srivatsa.bhat, linux-pm, linux-arch, linux-arm-kernel,
linuxppc-dev, netdev, linux-doc, linux-kernel, walken,
vincent.guittot
In-Reply-To: <20130218123714.26245.61816.stgit@srivatsabhat.in.ibm.com>
Once stop_machine() is gone from the CPU offline path, we won't be able to
depend on preempt_disable() or local_irq_disable() to prevent CPUs from going
offline from under us.
Use the get/put_online_cpus_atomic() APIs to prevent CPUs from going offline,
while invoking from atomic context.
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
---
kernel/sched/core.c | 24 +++++++++++++++++++++---
kernel/sched/fair.c | 5 ++++-
kernel/timer.c | 2 ++
3 files changed, 27 insertions(+), 4 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 26058d0..ead8af6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1117,11 +1117,11 @@ void kick_process(struct task_struct *p)
{
int cpu;
- preempt_disable();
+ get_online_cpus_atomic();
cpu = task_cpu(p);
if ((cpu != smp_processor_id()) && task_curr(p))
smp_send_reschedule(cpu);
- preempt_enable();
+ put_online_cpus_atomic();
}
EXPORT_SYMBOL_GPL(kick_process);
#endif /* CONFIG_SMP */
@@ -1129,6 +1129,10 @@ EXPORT_SYMBOL_GPL(kick_process);
#ifdef CONFIG_SMP
/*
* ->cpus_allowed is protected by both rq->lock and p->pi_lock
+ *
+ * Must be called under get/put_online_cpus_atomic() or
+ * equivalent, to avoid CPUs from going offline from underneath
+ * us.
*/
static int select_fallback_rq(int cpu, struct task_struct *p)
{
@@ -1192,6 +1196,9 @@ out:
/*
* The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable.
+ *
+ * Must be called under get/put_online_cpus_atomic(), to prevent
+ * CPUs from going offline from underneath us.
*/
static inline
int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
@@ -1432,6 +1439,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
int cpu, success = 0;
smp_wmb();
+ get_online_cpus_atomic();
raw_spin_lock_irqsave(&p->pi_lock, flags);
if (!(p->state & state))
goto out;
@@ -1472,6 +1480,7 @@ stat:
ttwu_stat(p, cpu, wake_flags);
out:
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+ put_online_cpus_atomic();
return success;
}
@@ -1693,6 +1702,7 @@ void wake_up_new_task(struct task_struct *p)
unsigned long flags;
struct rq *rq;
+ get_online_cpus_atomic();
raw_spin_lock_irqsave(&p->pi_lock, flags);
#ifdef CONFIG_SMP
/*
@@ -1713,6 +1723,7 @@ void wake_up_new_task(struct task_struct *p)
p->sched_class->task_woken(rq, p);
#endif
task_rq_unlock(rq, p, &flags);
+ put_online_cpus_atomic();
}
#ifdef CONFIG_PREEMPT_NOTIFIERS
@@ -2610,6 +2621,7 @@ void sched_exec(void)
unsigned long flags;
int dest_cpu;
+ get_online_cpus_atomic();
raw_spin_lock_irqsave(&p->pi_lock, flags);
dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0);
if (dest_cpu == smp_processor_id())
@@ -2619,11 +2631,13 @@ void sched_exec(void)
struct migration_arg arg = { p, dest_cpu };
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+ put_online_cpus_atomic();
stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg);
return;
}
unlock:
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+ put_online_cpus_atomic();
}
#endif
@@ -4373,6 +4387,7 @@ bool __sched yield_to(struct task_struct *p, bool preempt)
unsigned long flags;
bool yielded = 0;
+ get_online_cpus_atomic();
local_irq_save(flags);
rq = this_rq();
@@ -4400,13 +4415,14 @@ again:
* Make p's CPU reschedule; pick_next_entity takes care of
* fairness.
*/
- if (preempt && rq != p_rq)
+ if (preempt && rq != p_rq && cpu_online(task_cpu(p)))
resched_task(p_rq->curr);
}
out:
double_rq_unlock(rq, p_rq);
local_irq_restore(flags);
+ put_online_cpus_atomic();
if (yielded)
schedule();
@@ -4811,9 +4827,11 @@ static int migration_cpu_stop(void *data)
* The original target cpu might have gone down and we might
* be on another cpu but it doesn't matter.
*/
+ get_online_cpus_atomic();
local_irq_disable();
__migrate_task(arg->task, raw_smp_processor_id(), arg->dest_cpu);
local_irq_enable();
+ put_online_cpus_atomic();
return 0;
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 81fa536..c602d5c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5695,8 +5695,11 @@ void trigger_load_balance(struct rq *rq, int cpu)
likely(!on_null_domain(cpu)))
raise_softirq(SCHED_SOFTIRQ);
#ifdef CONFIG_NO_HZ
- if (nohz_kick_needed(rq, cpu) && likely(!on_null_domain(cpu)))
+ if (nohz_kick_needed(rq, cpu) && likely(!on_null_domain(cpu))) {
+ get_online_cpus_atomic();
nohz_balancer_kick(cpu);
+ put_online_cpus_atomic();
+ }
#endif
}
diff --git a/kernel/timer.c b/kernel/timer.c
index 367d008..b1820e3 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -924,6 +924,7 @@ void add_timer_on(struct timer_list *timer, int cpu)
timer_stats_timer_set_start_info(timer);
BUG_ON(timer_pending(timer) || !timer->function);
+ get_online_cpus_atomic();
spin_lock_irqsave(&base->lock, flags);
timer_set_base(timer, base);
debug_activate(timer, timer->expires);
@@ -938,6 +939,7 @@ void add_timer_on(struct timer_list *timer, int cpu)
*/
wake_up_idle_cpu(cpu);
spin_unlock_irqrestore(&base->lock, flags);
+ put_online_cpus_atomic();
}
EXPORT_SYMBOL_GPL(add_timer_on);
^ permalink raw reply related
* [PATCH v6 11/46] smp, cpu hotplug: Fix on_each_cpu_*() to prevent CPU offline properly
From: Srivatsa S. Bhat @ 2013-02-18 12:39 UTC (permalink / raw)
To: tglx, peterz, tj, oleg, paulmck, rusty, mingo, akpm, namhyung
Cc: rostedt, wangyun, xiaoguangrong, rjw, sbw, fweisbec, linux,
nikunj, srivatsa.bhat, linux-pm, linux-arch, linux-arm-kernel,
linuxppc-dev, netdev, linux-doc, linux-kernel, walken,
vincent.guittot
In-Reply-To: <20130218123714.26245.61816.stgit@srivatsabhat.in.ibm.com>
Once stop_machine() is gone from the CPU offline path, we won't be able to
depend on preempt_disable() to prevent CPUs from going offline from under us.
Use the get/put_online_cpus_atomic() APIs to prevent CPUs from going offline,
while invoking from atomic context.
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
---
kernel/smp.c | 25 +++++++++++++++----------
1 file changed, 15 insertions(+), 10 deletions(-)
diff --git a/kernel/smp.c b/kernel/smp.c
index 0f40d36..a8fd381 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -699,12 +699,12 @@ int on_each_cpu(void (*func) (void *info), void *info, int wait)
unsigned long flags;
int ret = 0;
- preempt_disable();
+ get_online_cpus_atomic();
ret = smp_call_function(func, info, wait);
local_irq_save(flags);
func(info);
local_irq_restore(flags);
- preempt_enable();
+ put_online_cpus_atomic();
return ret;
}
EXPORT_SYMBOL(on_each_cpu);
@@ -726,7 +726,11 @@ EXPORT_SYMBOL(on_each_cpu);
void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
void *info, bool wait)
{
- int cpu = get_cpu();
+ int cpu;
+
+ get_online_cpus_atomic();
+
+ cpu = smp_processor_id();
smp_call_function_many(mask, func, info, wait);
if (cpumask_test_cpu(cpu, mask)) {
@@ -734,7 +738,7 @@ void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
func(info);
local_irq_enable();
}
- put_cpu();
+ put_online_cpus_atomic();
}
EXPORT_SYMBOL(on_each_cpu_mask);
@@ -759,8 +763,9 @@ EXPORT_SYMBOL(on_each_cpu_mask);
* The function might sleep if the GFP flags indicates a non
* atomic allocation is allowed.
*
- * Preemption is disabled to protect against CPUs going offline but not online.
- * CPUs going online during the call will not be seen or sent an IPI.
+ * We use get/put_online_cpus_atomic() to prevent CPUs from going
+ * offline in-between our operation. CPUs coming online during the
+ * call will not be seen or sent an IPI.
*
* You must not call this function with disabled interrupts or
* from a hardware interrupt handler or from a bottom half handler.
@@ -775,26 +780,26 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
might_sleep_if(gfp_flags & __GFP_WAIT);
if (likely(zalloc_cpumask_var(&cpus, (gfp_flags|__GFP_NOWARN)))) {
- preempt_disable();
+ get_online_cpus_atomic();
for_each_online_cpu(cpu)
if (cond_func(cpu, info))
cpumask_set_cpu(cpu, cpus);
on_each_cpu_mask(cpus, func, info, wait);
- preempt_enable();
+ put_online_cpus_atomic();
free_cpumask_var(cpus);
} else {
/*
* No free cpumask, bother. No matter, we'll
* just have to IPI them one by one.
*/
- preempt_disable();
+ get_online_cpus_atomic();
for_each_online_cpu(cpu)
if (cond_func(cpu, info)) {
ret = smp_call_function_single(cpu, func,
info, wait);
WARN_ON_ONCE(!ret);
}
- preempt_enable();
+ put_online_cpus_atomic();
}
}
EXPORT_SYMBOL(on_each_cpu_cond);
^ permalink raw reply related
* [PATCH v6 10/46] smp, cpu hotplug: Fix smp_call_function_*() to prevent CPU offline properly
From: Srivatsa S. Bhat @ 2013-02-18 12:39 UTC (permalink / raw)
To: tglx, peterz, tj, oleg, paulmck, rusty, mingo, akpm, namhyung
Cc: rostedt, wangyun, xiaoguangrong, rjw, sbw, fweisbec, linux,
nikunj, srivatsa.bhat, linux-pm, linux-arch, linux-arm-kernel,
linuxppc-dev, netdev, linux-doc, linux-kernel, walken,
vincent.guittot
In-Reply-To: <20130218123714.26245.61816.stgit@srivatsabhat.in.ibm.com>
Once stop_machine() is gone from the CPU offline path, we won't be able to
depend on preempt_disable() to prevent CPUs from going offline from under us.
Use the get/put_online_cpus_atomic() APIs to prevent CPUs from going offline,
while invoking from atomic context.
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
---
kernel/smp.c | 40 ++++++++++++++++++++++++++--------------
1 file changed, 26 insertions(+), 14 deletions(-)
diff --git a/kernel/smp.c b/kernel/smp.c
index 69f38bd..0f40d36 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -315,7 +315,8 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
* prevent preemption and reschedule on another processor,
* as well as CPU removal
*/
- this_cpu = get_cpu();
+ get_online_cpus_atomic();
+ this_cpu = smp_processor_id();
/*
* Can deadlock when called with interrupts disabled.
@@ -347,7 +348,7 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
}
}
- put_cpu();
+ put_online_cpus_atomic();
return err;
}
@@ -376,8 +377,10 @@ int smp_call_function_any(const struct cpumask *mask,
const struct cpumask *nodemask;
int ret;
+ get_online_cpus_atomic();
/* Try for same CPU (cheapest) */
- cpu = get_cpu();
+ cpu = smp_processor_id();
+
if (cpumask_test_cpu(cpu, mask))
goto call;
@@ -393,7 +396,7 @@ int smp_call_function_any(const struct cpumask *mask,
cpu = cpumask_any_and(mask, cpu_online_mask);
call:
ret = smp_call_function_single(cpu, func, info, wait);
- put_cpu();
+ put_online_cpus_atomic();
return ret;
}
EXPORT_SYMBOL_GPL(smp_call_function_any);
@@ -414,25 +417,28 @@ void __smp_call_function_single(int cpu, struct call_single_data *data,
unsigned int this_cpu;
unsigned long flags;
- this_cpu = get_cpu();
+ get_online_cpus_atomic();
+
+ this_cpu = smp_processor_id();
+
/*
* Can deadlock when called with interrupts disabled.
* We allow cpu's that are not yet online though, as no one else can
* send smp call function interrupt to this cpu and as such deadlocks
* can't happen.
*/
- WARN_ON_ONCE(cpu_online(smp_processor_id()) && wait && irqs_disabled()
+ WARN_ON_ONCE(cpu_online(this_cpu) && wait && irqs_disabled()
&& !oops_in_progress);
if (cpu == this_cpu) {
local_irq_save(flags);
data->func(data->info);
local_irq_restore(flags);
- } else {
+ } else if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
csd_lock(data);
generic_exec_single(cpu, data, wait);
}
- put_cpu();
+ put_online_cpus_atomic();
}
/**
@@ -456,6 +462,8 @@ void smp_call_function_many(const struct cpumask *mask,
unsigned long flags;
int refs, cpu, next_cpu, this_cpu = smp_processor_id();
+ get_online_cpus_atomic();
+
/*
* Can deadlock when called with interrupts disabled.
* We allow cpu's that are not yet online though, as no one else can
@@ -472,17 +480,18 @@ void smp_call_function_many(const struct cpumask *mask,
/* No online cpus? We're done. */
if (cpu >= nr_cpu_ids)
- return;
+ goto out_unlock;
/* Do we have another CPU which isn't us? */
next_cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
if (next_cpu == this_cpu)
- next_cpu = cpumask_next_and(next_cpu, mask, cpu_online_mask);
+ next_cpu = cpumask_next_and(next_cpu, mask,
+ cpu_online_mask);
/* Fastpath: do that cpu by itself. */
if (next_cpu >= nr_cpu_ids) {
smp_call_function_single(cpu, func, info, wait);
- return;
+ goto out_unlock;
}
data = &__get_cpu_var(cfd_data);
@@ -528,7 +537,7 @@ void smp_call_function_many(const struct cpumask *mask,
/* Some callers race with other cpus changing the passed mask */
if (unlikely(!refs)) {
csd_unlock(&data->csd);
- return;
+ goto out_unlock;
}
/*
@@ -565,6 +574,9 @@ void smp_call_function_many(const struct cpumask *mask,
/* Optionally wait for the CPUs to complete */
if (wait)
csd_lock_wait(&data->csd);
+
+out_unlock:
+ put_online_cpus_atomic();
}
EXPORT_SYMBOL(smp_call_function_many);
@@ -585,9 +597,9 @@ EXPORT_SYMBOL(smp_call_function_many);
*/
int smp_call_function(smp_call_func_t func, void *info, int wait)
{
- preempt_disable();
+ get_online_cpus_atomic();
smp_call_function_many(cpu_online_mask, func, info, wait);
- preempt_enable();
+ put_online_cpus_atomic();
return 0;
}
^ permalink raw reply related
* [PATCH v6 09/46] CPU hotplug: Convert preprocessor macros to static inline functions
From: Srivatsa S. Bhat @ 2013-02-18 12:39 UTC (permalink / raw)
To: tglx, peterz, tj, oleg, paulmck, rusty, mingo, akpm, namhyung
Cc: rostedt, wangyun, xiaoguangrong, rjw, sbw, fweisbec, linux,
nikunj, srivatsa.bhat, linux-pm, linux-arch, linux-arm-kernel,
linuxppc-dev, netdev, linux-doc, linux-kernel, walken,
vincent.guittot
In-Reply-To: <20130218123714.26245.61816.stgit@srivatsabhat.in.ibm.com>
On 12/05/2012 06:10 AM, Andrew Morton wrote:
"static inline C functions would be preferred if possible. Feel free to
fix up the wrong crufty surrounding code as well ;-)"
Convert the macros in the CPU hotplug code to static inline C functions.
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
include/linux/cpu.h | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index cf24da1..eb79f47 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -198,10 +198,10 @@ static inline void cpu_hotplug_driver_unlock(void)
#else /* CONFIG_HOTPLUG_CPU */
-#define get_online_cpus() do { } while (0)
-#define put_online_cpus() do { } while (0)
-#define get_online_cpus_atomic() do { } while (0)
-#define put_online_cpus_atomic() do { } while (0)
+static inline void get_online_cpus(void) {}
+static inline void put_online_cpus(void) {}
+static inline void get_online_cpus_atomic(void) {}
+static inline void put_online_cpus_atomic(void) {}
#define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0)
/* These aren't inline functions due to a GCC bug. */
#define register_hotcpu_notifier(nb) ({ (void)(nb); 0; })
^ permalink raw reply related
* [PATCH v6 08/46] CPU hotplug: Provide APIs to prevent CPU offline from atomic context
From: Srivatsa S. Bhat @ 2013-02-18 12:39 UTC (permalink / raw)
To: tglx, peterz, tj, oleg, paulmck, rusty, mingo, akpm, namhyung
Cc: linux-arch, linux, nikunj, linux-pm, fweisbec, linux-doc,
linux-kernel, rostedt, xiaoguangrong, rjw, sbw, wangyun,
srivatsa.bhat, netdev, vincent.guittot, walken, linuxppc-dev,
linux-arm-kernel
In-Reply-To: <20130218123714.26245.61816.stgit@srivatsabhat.in.ibm.com>
There are places where preempt_disable() or local_irq_disable() are used
to prevent any CPU from going offline during the critical section. Let us
call them as "atomic hotplug readers" ("atomic" because they run in atomic,
non-preemptible contexts).
Today, preempt_disable() or its equivalent works because the hotplug writer
uses stop_machine() to take CPUs offline. But once stop_machine() is gone
from the CPU hotplug offline path, the readers won't be able to prevent
CPUs from going offline using preempt_disable().
So the intent here is to provide synchronization APIs for such atomic hotplug
readers, to prevent (any) CPUs from going offline, without depending on
stop_machine() at the writer-side. The new APIs will look something like
this: get_online_cpus_atomic() and put_online_cpus_atomic()
Some important design requirements and considerations:
-----------------------------------------------------
1. Scalable synchronization at the reader-side, especially in the fast-path
Any synchronization at the atomic hotplug readers side must be highly
scalable - avoid global single-holder locks/counters etc. Because, these
paths currently use the extremely fast preempt_disable(); our replacement
to preempt_disable() should not become ridiculously costly and also should
not serialize the readers among themselves needlessly.
At a minimum, the new APIs must be extremely fast at the reader side
atleast in the fast-path, when no CPU offline writers are active.
2. preempt_disable() was recursive. The replacement should also be recursive.
3. No (new) lock-ordering restrictions
preempt_disable() was super-flexible. It didn't impose any ordering
restrictions or rules for nesting. Our replacement should also be equally
flexible and usable.
4. No deadlock possibilities
Regular per-cpu locking is not the way to go if we want to have relaxed
rules for lock-ordering. Because, we can end up in circular-locking
dependencies as explained in https://lkml.org/lkml/2012/12/6/290
So, avoid the usual per-cpu locking schemes (per-cpu locks/per-cpu atomic
counters with spin-on-contention etc) as much as possible, to avoid
numerous deadlock possibilities from creeping in.
Implementation of the design:
----------------------------
We use per-CPU reader-writer locks for synchronization because:
a. They are quite fast and scalable in the fast-path (when no writers are
active), since they use fast per-cpu counters in those paths.
b. They are recursive at the reader side.
c. They provide a good amount of safety against deadlocks; they don't
spring new deadlock possibilities on us from out of nowhere. As a
result, they have relaxed locking rules and are quite flexible, and
thus are best suited for replacing usages of preempt_disable() or
local_irq_disable() at the reader side.
Together, these satisfy all the requirements mentioned above.
I'm indebted to Michael Wang and Xiao Guangrong for their numerous thoughtful
suggestions and ideas, which inspired and influenced many of the decisions in
this as well as previous designs. Thanks a lot Michael and Xiao!
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Howells <dhowells@redhat.com>
Cc: "James E.J. Bottomley" <jejb@parisc-linux.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: uclinux-dist-devel@blackfin.uclinux.org
Cc: linux-ia64@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: linux-am33-list@redhat.com
Cc: linux-parisc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-s390@vger.kernel.org
Cc: linux-sh@vger.kernel.org
Cc: sparclinux@vger.kernel.org
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
arch/arm/Kconfig | 1 +
arch/blackfin/Kconfig | 1 +
arch/ia64/Kconfig | 1 +
arch/mips/Kconfig | 1 +
arch/mn10300/Kconfig | 1 +
arch/parisc/Kconfig | 1 +
arch/powerpc/Kconfig | 1 +
arch/s390/Kconfig | 1 +
arch/sh/Kconfig | 1 +
arch/sparc/Kconfig | 1 +
arch/x86/Kconfig | 1 +
include/linux/cpu.h | 4 ++++
kernel/cpu.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++--
13 files changed, 68 insertions(+), 2 deletions(-)
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 67874b8..cb6b94b 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1616,6 +1616,7 @@ config NR_CPUS
config HOTPLUG_CPU
bool "Support for hot-pluggable CPUs"
depends on SMP && HOTPLUG
+ select PERCPU_RWLOCK
help
Say Y here to experiment with turning CPUs off and on. CPUs
can be controlled through /sys/devices/system/cpu.
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index b6f3ad5..83d9882 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -261,6 +261,7 @@ config NR_CPUS
config HOTPLUG_CPU
bool "Support for hot-pluggable CPUs"
depends on SMP && HOTPLUG
+ select PERCPU_RWLOCK
default y
config BF_REV_MIN
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 3279646..c246772 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -378,6 +378,7 @@ config HOTPLUG_CPU
bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
depends on SMP && EXPERIMENTAL
select HOTPLUG
+ select PERCPU_RWLOCK
default n
---help---
Say Y here to experiment with turning CPUs off and on. CPUs
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 2ac626a..f97c479 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -956,6 +956,7 @@ config SYS_HAS_EARLY_PRINTK
config HOTPLUG_CPU
bool "Support for hot-pluggable CPUs"
depends on SMP && HOTPLUG && SYS_SUPPORTS_HOTPLUG_CPU
+ select PERCPU_RWLOCK
help
Say Y here to allow turning CPUs off and on. CPUs can be
controlled through /sys/devices/system/cpu.
diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig
index e70001c..a64e488 100644
--- a/arch/mn10300/Kconfig
+++ b/arch/mn10300/Kconfig
@@ -60,6 +60,7 @@ config ARCH_HAS_ILOG2_U32
config HOTPLUG_CPU
def_bool n
+ select PERCPU_RWLOCK
source "init/Kconfig"
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index b77feff..6f55cd4 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -226,6 +226,7 @@ config HOTPLUG_CPU
bool
default y if SMP
select HOTPLUG
+ select PERCPU_RWLOCK
config ARCH_SELECT_MEMORY_MODEL
def_bool y
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 17903f1..56b1f15 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -336,6 +336,7 @@ config HOTPLUG_CPU
bool "Support for enabling/disabling CPUs"
depends on SMP && HOTPLUG && EXPERIMENTAL && (PPC_PSERIES || \
PPC_PMAC || PPC_POWERNV || (PPC_85xx && !PPC_E500MC))
+ select PERCPU_RWLOCK
---help---
Say Y here to be able to disable and re-enable individual
CPUs at runtime on SMP machines.
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index b5ea38c..a9aafb4 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -299,6 +299,7 @@ config HOTPLUG_CPU
prompt "Support for hot-pluggable CPUs"
depends on SMP
select HOTPLUG
+ select PERCPU_RWLOCK
help
Say Y here to be able to turn CPUs off and on. CPUs
can be controlled through /sys/devices/system/cpu/cpu#.
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index babc2b8..8c92eef 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -765,6 +765,7 @@ config NR_CPUS
config HOTPLUG_CPU
bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
depends on SMP && HOTPLUG && EXPERIMENTAL
+ select PERCPU_RWLOCK
help
Say Y here to experiment with turning CPUs off and on. CPUs
can be controlled through /sys/devices/system/cpu.
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index cb9c333..b22f29d 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -254,6 +254,7 @@ config HOTPLUG_CPU
bool "Support for hot-pluggable CPUs"
depends on SPARC64 && SMP
select HOTPLUG
+ select PERCPU_RWLOCK
help
Say Y here to experiment with turning CPUs off and on. CPUs
can be controlled through /sys/devices/system/cpu/cpu#.
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 225543b..1a6d50d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1689,6 +1689,7 @@ config PHYSICAL_ALIGN
config HOTPLUG_CPU
bool "Support for hot-pluggable CPUs"
depends on SMP && HOTPLUG
+ select PERCPU_RWLOCK
---help---
Say Y here to allow turning CPUs off and on. CPUs can be
controlled through /sys/devices/system/cpu.
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index ce7a074..cf24da1 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -175,6 +175,8 @@ extern struct bus_type cpu_subsys;
extern void get_online_cpus(void);
extern void put_online_cpus(void);
+extern void get_online_cpus_atomic(void);
+extern void put_online_cpus_atomic(void);
#define hotcpu_notifier(fn, pri) cpu_notifier(fn, pri)
#define register_hotcpu_notifier(nb) register_cpu_notifier(nb)
#define unregister_hotcpu_notifier(nb) unregister_cpu_notifier(nb)
@@ -198,6 +200,8 @@ static inline void cpu_hotplug_driver_unlock(void)
#define get_online_cpus() do { } while (0)
#define put_online_cpus() do { } while (0)
+#define get_online_cpus_atomic() do { } while (0)
+#define put_online_cpus_atomic() do { } while (0)
#define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0)
/* These aren't inline functions due to a GCC bug. */
#define register_hotcpu_notifier(nb) ({ (void)(nb); 0; })
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 3046a50..58dd1df 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1,6 +1,18 @@
/* CPU control.
* (C) 2001, 2002, 2003, 2004 Rusty Russell
*
+ * Rework of the CPU hotplug offline mechanism to remove its dependence on
+ * the heavy-weight stop_machine() primitive, by Srivatsa S. Bhat and
+ * Paul E. McKenney.
+ *
+ * Copyright (C) IBM Corporation, 2012-2013
+ * Authors: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
+ * Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ *
+ * With lots of invaluable suggestions from:
+ * Oleg Nesterov <oleg@redhat.com>
+ * Tejun Heo <tj@kernel.org>
+ *
* This code is licenced under the GPL.
*/
#include <linux/proc_fs.h>
@@ -19,6 +31,7 @@
#include <linux/mutex.h>
#include <linux/gfp.h>
#include <linux/suspend.h>
+#include <linux/percpu-rwlock.h>
#include "smpboot.h"
@@ -133,6 +146,38 @@ static void cpu_hotplug_done(void)
mutex_unlock(&cpu_hotplug.lock);
}
+/*
+ * Per-CPU Reader-Writer lock to synchronize between atomic hotplug
+ * readers and the CPU offline hotplug writer.
+ */
+DEFINE_STATIC_PERCPU_RWLOCK(hotplug_pcpu_rwlock);
+
+/*
+ * Invoked by atomic hotplug reader (a task which wants to prevent
+ * CPU offline, but which can't afford to sleep), to prevent CPUs from
+ * going offline. So, you can call this function from atomic contexts
+ * (including interrupt handlers).
+ *
+ * Note: This does NOT prevent CPUs from coming online! It only prevents
+ * CPUs from going offline.
+ *
+ * You can call this function recursively.
+ *
+ * Returns with preemption disabled (but interrupts remain as they are;
+ * they are not disabled).
+ */
+void get_online_cpus_atomic(void)
+{
+ percpu_read_lock_irqsafe(&hotplug_pcpu_rwlock);
+}
+EXPORT_SYMBOL_GPL(get_online_cpus_atomic);
+
+void put_online_cpus_atomic(void)
+{
+ percpu_read_unlock_irqsafe(&hotplug_pcpu_rwlock);
+}
+EXPORT_SYMBOL_GPL(put_online_cpus_atomic);
+
#else /* #if CONFIG_HOTPLUG_CPU */
static void cpu_hotplug_begin(void) {}
static void cpu_hotplug_done(void) {}
@@ -246,15 +291,21 @@ struct take_cpu_down_param {
static int __ref take_cpu_down(void *_param)
{
struct take_cpu_down_param *param = _param;
+ unsigned long flags;
int err;
+ percpu_write_lock_irqsave(&hotplug_pcpu_rwlock, &flags);
+
/* Ensure this CPU doesn't handle any more interrupts. */
err = __cpu_disable();
if (err < 0)
- return err;
+ goto out;
cpu_notify(CPU_DYING | param->mod, param->hcpu);
- return 0;
+
+out:
+ percpu_write_unlock_irqrestore(&hotplug_pcpu_rwlock, &flags);
+ return err;
}
/* Requires cpu_add_remove_lock to be held */
^ permalink raw reply related
* [PATCH v6 07/46] percpu_rwlock: Allow writers to be readers, and add lockdep annotations
From: Srivatsa S. Bhat @ 2013-02-18 12:39 UTC (permalink / raw)
To: tglx, peterz, tj, oleg, paulmck, rusty, mingo, akpm, namhyung
Cc: rostedt, wangyun, xiaoguangrong, rjw, sbw, fweisbec, linux,
nikunj, srivatsa.bhat, linux-pm, linux-arch, linux-arm-kernel,
linuxppc-dev, netdev, linux-doc, linux-kernel, walken,
vincent.guittot
In-Reply-To: <20130218123714.26245.61816.stgit@srivatsabhat.in.ibm.com>
CPU hotplug (which will be the first user of per-CPU rwlocks) has a special
requirement with respect to locking: the writer, after acquiring the per-CPU
rwlock for write, must be allowed to take the same lock for read, without
deadlocking and without getting complaints from lockdep. In comparison, this
is similar to what get_online_cpus()/put_online_cpus() does today: it allows
a hotplug writer (who holds the cpu_hotplug.lock mutex) to invoke it without
locking issues, because it silently returns if the caller is the hotplug
writer itself.
This can be easily achieved with per-CPU rwlocks as well (even without a
"is this a writer?" check) by incrementing the per-CPU refcount of the writer
immediately after taking the global rwlock for write, and then decrementing
the per-CPU refcount before releasing the global rwlock.
This ensures that any reader that comes along on that CPU while the writer is
active (on that same CPU), notices the non-zero value of the nested counter
and assumes that it is a nested read-side critical section and proceeds by
just incrementing the refcount. Thus we prevent the reader from taking the
global rwlock for read, which prevents the writer from deadlocking itself.
Add that support and teach lockdep about this special locking scheme so
that it knows that this sort of usage is valid. Also add the required lockdep
annotations to enable it to detect common locking problems with per-CPU
rwlocks.
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
---
lib/percpu-rwlock.c | 33 +++++++++++++++++++++++++++++++++
1 file changed, 33 insertions(+)
diff --git a/lib/percpu-rwlock.c b/lib/percpu-rwlock.c
index ed36531..bf95e40 100644
--- a/lib/percpu-rwlock.c
+++ b/lib/percpu-rwlock.c
@@ -102,6 +102,10 @@ void percpu_read_lock_irqsafe(struct percpu_rwlock *pcpu_rwlock)
if (likely(!writer_active(pcpu_rwlock))) {
this_cpu_inc(pcpu_rwlock->rw_state->reader_refcnt);
+
+ /* Pretend that we take global_rwlock for lockdep */
+ rwlock_acquire_read(&pcpu_rwlock->global_rwlock.dep_map,
+ 0, 0, _RET_IP_);
} else {
/* Writer is active, so switch to global rwlock. */
@@ -126,6 +130,12 @@ void percpu_read_lock_irqsafe(struct percpu_rwlock *pcpu_rwlock)
if (!writer_active(pcpu_rwlock)) {
this_cpu_inc(pcpu_rwlock->rw_state->reader_refcnt);
read_unlock(&pcpu_rwlock->global_rwlock);
+
+ /*
+ * Pretend that we take global_rwlock for lockdep
+ */
+ rwlock_acquire_read(&pcpu_rwlock->global_rwlock.dep_map,
+ 0, 0, _RET_IP_);
}
}
@@ -162,6 +172,13 @@ void percpu_read_unlock_irqsafe(struct percpu_rwlock *pcpu_rwlock)
*/
smp_mb();
this_cpu_dec(pcpu_rwlock->rw_state->reader_refcnt);
+
+ /*
+ * Since this is the last decrement, it is time to pretend
+ * to lockdep that we are releasing the read lock.
+ */
+ rwlock_release(&pcpu_rwlock->global_rwlock.dep_map,
+ 1, _RET_IP_);
} else {
read_unlock(&pcpu_rwlock->global_rwlock);
}
@@ -200,6 +217,16 @@ void percpu_write_lock_irqsave(struct percpu_rwlock *pcpu_rwlock,
smp_mb(); /* Complete the wait-for-readers, before taking the lock */
write_lock_irqsave(&pcpu_rwlock->global_rwlock, *flags);
+
+ /*
+ * It is desirable to allow the writer to acquire the percpu-rwlock
+ * for read (if necessary), without deadlocking or getting complaints
+ * from lockdep. To achieve that, just increment the reader_refcnt of
+ * this CPU - that way, any attempt by the writer to acquire the
+ * percpu-rwlock for read, will get treated as a case of nested percpu
+ * reader, which is safe, from a locking perspective.
+ */
+ this_cpu_inc(pcpu_rwlock->rw_state->reader_refcnt);
}
void percpu_write_unlock_irqrestore(struct percpu_rwlock *pcpu_rwlock,
@@ -207,6 +234,12 @@ void percpu_write_unlock_irqrestore(struct percpu_rwlock *pcpu_rwlock,
{
unsigned int cpu;
+ /*
+ * Undo the special increment that we had done in the write-lock path
+ * in order to allow writers to be readers.
+ */
+ this_cpu_dec(pcpu_rwlock->rw_state->reader_refcnt);
+
/* Complete the critical section before clearing ->writer_signal */
smp_mb();
^ permalink raw reply related
* [PATCH v6 06/46] percpu_rwlock: Rearrange the read-lock code to fastpath nested percpu readers
From: Srivatsa S. Bhat @ 2013-02-18 12:39 UTC (permalink / raw)
To: tglx, peterz, tj, oleg, paulmck, rusty, mingo, akpm, namhyung
Cc: rostedt, wangyun, xiaoguangrong, rjw, sbw, fweisbec, linux,
nikunj, srivatsa.bhat, linux-pm, linux-arch, linux-arm-kernel,
linuxppc-dev, netdev, linux-doc, linux-kernel, walken,
vincent.guittot
In-Reply-To: <20130218123714.26245.61816.stgit@srivatsabhat.in.ibm.com>
If we are dealing with a nester percpu reader, we can optimize away quite
a few costly operations. Improve that fastpath further, by avoiding the
unnecessary addition and subtraction of 'READER_PRESENT' to reader_refcnt,
by rearranging the code a bit.
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
---
lib/percpu-rwlock.c | 14 ++++++--------
1 file changed, 6 insertions(+), 8 deletions(-)
diff --git a/lib/percpu-rwlock.c b/lib/percpu-rwlock.c
index ce7e440..ed36531 100644
--- a/lib/percpu-rwlock.c
+++ b/lib/percpu-rwlock.c
@@ -80,23 +80,21 @@ void percpu_read_lock_irqsafe(struct percpu_rwlock *pcpu_rwlock)
preempt_disable();
/*
- * Let the writer know that a reader is active, even before we choose
- * our reader-side synchronization scheme.
- */
- this_cpu_add(pcpu_rwlock->rw_state->reader_refcnt, READER_PRESENT);
-
- /*
* If we are already using per-cpu refcounts, it is not safe to switch
* the synchronization scheme. So continue using the refcounts.
*/
if (reader_uses_percpu_refcnt(pcpu_rwlock)) {
this_cpu_inc(pcpu_rwlock->rw_state->reader_refcnt);
- this_cpu_sub(pcpu_rwlock->rw_state->reader_refcnt,
- READER_PRESENT);
return;
}
/*
+ * Let the writer know that a reader is active, even before we choose
+ * our reader-side synchronization scheme.
+ */
+ this_cpu_add(pcpu_rwlock->rw_state->reader_refcnt, READER_PRESENT);
+
+ /*
* The write to 'reader_refcnt' must be visible before we read
* 'writer_signal'.
*/
^ permalink raw reply related
* [PATCH v6 05/46] percpu_rwlock: Make percpu-rwlocks IRQ-safe, optimally
From: Srivatsa S. Bhat @ 2013-02-18 12:39 UTC (permalink / raw)
To: tglx, peterz, tj, oleg, paulmck, rusty, mingo, akpm, namhyung
Cc: linux-arch, linux, nikunj, linux-pm, fweisbec, linux-doc,
linux-kernel, rostedt, xiaoguangrong, rjw, sbw, wangyun,
srivatsa.bhat, netdev, vincent.guittot, walken, linuxppc-dev,
linux-arm-kernel
In-Reply-To: <20130218123714.26245.61816.stgit@srivatsabhat.in.ibm.com>
If interrupt handlers can also be readers, then one of the ways to make
per-CPU rwlocks safe, is to disable interrupts at the reader side before
trying to acquire the per-CPU rwlock and keep it disabled throughout the
duration of the read-side critical section.
The goal is to avoid cases such as:
1. writer is active and it holds the global rwlock for write
2. a regular reader comes in and marks itself as present (by incrementing
its per-CPU refcount) before checking whether writer is active.
3. an interrupt hits the reader;
[If it had not hit, the reader would have noticed that the writer is
active and would have decremented its refcount and would have tried
to acquire the global rwlock for read].
Since the interrupt handler also happens to be a reader, it notices
the non-zero refcount (which was due to the reader who got interrupted)
and thinks that this is a nested read-side critical section and
proceeds to take the fastpath, which is wrong. The interrupt handler
should have noticed that the writer is active and taken the rwlock
for read.
So, disabling interrupts can help avoid this problem (at the cost of keeping
the interrupts disabled for quite long).
But Oleg had a brilliant idea by which we can do much better than that:
we can manage with disabling interrupts _just_ during the updates (writes to
per-CPU refcounts) to safe-guard against races with interrupt handlers.
Beyond that, we can keep the interrupts enabled and still be safe w.r.t
interrupt handlers that can act as readers.
Basically the idea is that we differentiate between the *part* of the
per-CPU refcount that we use for reference counting vs the part that we use
merely to make the writer wait for us to switch over to the right
synchronization scheme.
The scheme involves splitting the per-CPU refcounts into 2 parts:
eg: the lower 16 bits are used to track the nesting depth of the reader
(a "nested-counter"), and the remaining (upper) bits are used to merely mark
the presence of the reader.
As long as the overall reader_refcnt is non-zero, the writer waits for the
reader (assuming that the reader is still actively using per-CPU refcounts for
synchronization).
The reader first sets one of the higher bits to mark its presence, and then
uses the lower 16 bits to manage the nesting depth. So, an interrupt handler
coming in as illustrated above will be able to distinguish between "this is
a nested read-side critical section" vs "we have merely marked our presence
to make the writer wait for us to switch" by looking at the same refcount.
Thus, it makes it unnecessary to keep interrupts disabled throughout the
read-side critical section, despite having the possibility of interrupt
handlers being readers themselves.
Implement this logic and rename the locking functions appropriately, to
reflect what they do.
Based-on-idea-by: Oleg Nesterov <oleg@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
---
include/linux/percpu-rwlock.h | 10 ++++---
lib/percpu-rwlock.c | 57 ++++++++++++++++++++++++++---------------
2 files changed, 42 insertions(+), 25 deletions(-)
diff --git a/include/linux/percpu-rwlock.h b/include/linux/percpu-rwlock.h
index 5590b1e..8c9e145 100644
--- a/include/linux/percpu-rwlock.h
+++ b/include/linux/percpu-rwlock.h
@@ -38,11 +38,13 @@ struct percpu_rwlock {
rwlock_t global_rwlock;
};
-extern void percpu_read_lock(struct percpu_rwlock *);
-extern void percpu_read_unlock(struct percpu_rwlock *);
+extern void percpu_read_lock_irqsafe(struct percpu_rwlock *);
+extern void percpu_read_unlock_irqsafe(struct percpu_rwlock *);
-extern void percpu_write_lock(struct percpu_rwlock *);
-extern void percpu_write_unlock(struct percpu_rwlock *);
+extern void percpu_write_lock_irqsave(struct percpu_rwlock *,
+ unsigned long *flags);
+extern void percpu_write_unlock_irqrestore(struct percpu_rwlock *,
+ unsigned long *flags);
extern int __percpu_init_rwlock(struct percpu_rwlock *,
const char *, struct lock_class_key *);
diff --git a/lib/percpu-rwlock.c b/lib/percpu-rwlock.c
index edefdea..ce7e440 100644
--- a/lib/percpu-rwlock.c
+++ b/lib/percpu-rwlock.c
@@ -30,11 +30,15 @@
#include <asm/processor.h>
+#define READER_PRESENT (1UL << 16)
+#define READER_REFCNT_MASK (READER_PRESENT - 1)
+
#define reader_yet_to_switch(pcpu_rwlock, cpu) \
(ACCESS_ONCE(per_cpu_ptr((pcpu_rwlock)->rw_state, cpu)->reader_refcnt))
-#define reader_percpu_nesting_depth(pcpu_rwlock) \
- (__this_cpu_read((pcpu_rwlock)->rw_state->reader_refcnt))
+#define reader_percpu_nesting_depth(pcpu_rwlock) \
+ (__this_cpu_read((pcpu_rwlock)->rw_state->reader_refcnt) & \
+ READER_REFCNT_MASK)
#define reader_uses_percpu_refcnt(pcpu_rwlock) \
reader_percpu_nesting_depth(pcpu_rwlock)
@@ -71,7 +75,7 @@ void percpu_free_rwlock(struct percpu_rwlock *pcpu_rwlock)
pcpu_rwlock->rw_state = NULL;
}
-void percpu_read_lock(struct percpu_rwlock *pcpu_rwlock)
+void percpu_read_lock_irqsafe(struct percpu_rwlock *pcpu_rwlock)
{
preempt_disable();
@@ -79,14 +83,18 @@ void percpu_read_lock(struct percpu_rwlock *pcpu_rwlock)
* Let the writer know that a reader is active, even before we choose
* our reader-side synchronization scheme.
*/
- this_cpu_inc(pcpu_rwlock->rw_state->reader_refcnt);
+ this_cpu_add(pcpu_rwlock->rw_state->reader_refcnt, READER_PRESENT);
/*
* If we are already using per-cpu refcounts, it is not safe to switch
* the synchronization scheme. So continue using the refcounts.
*/
- if (reader_nested_percpu(pcpu_rwlock))
+ if (reader_uses_percpu_refcnt(pcpu_rwlock)) {
+ this_cpu_inc(pcpu_rwlock->rw_state->reader_refcnt);
+ this_cpu_sub(pcpu_rwlock->rw_state->reader_refcnt,
+ READER_PRESENT);
return;
+ }
/*
* The write to 'reader_refcnt' must be visible before we read
@@ -95,9 +103,19 @@ void percpu_read_lock(struct percpu_rwlock *pcpu_rwlock)
smp_mb();
if (likely(!writer_active(pcpu_rwlock))) {
- goto out;
+ this_cpu_inc(pcpu_rwlock->rw_state->reader_refcnt);
} else {
/* Writer is active, so switch to global rwlock. */
+
+ /*
+ * While we are spinning on ->global_rwlock, an
+ * interrupt can hit us, and the interrupt handler
+ * might call this function. The distinction between
+ * READER_PRESENT and the refcnt helps ensure that the
+ * interrupt handler also takes this branch and spins
+ * on the ->global_rwlock, as long as the writer is
+ * active.
+ */
read_lock(&pcpu_rwlock->global_rwlock);
/*
@@ -107,29 +125,24 @@ void percpu_read_lock(struct percpu_rwlock *pcpu_rwlock)
* refcounts. (This also helps avoid heterogeneous nesting of
* readers).
*/
- if (writer_active(pcpu_rwlock)) {
- /*
- * The above writer_active() check can get reordered
- * with this_cpu_dec() below, but this is OK, because
- * holding the rwlock is conservative.
- */
- this_cpu_dec(pcpu_rwlock->rw_state->reader_refcnt);
- } else {
+ if (!writer_active(pcpu_rwlock)) {
+ this_cpu_inc(pcpu_rwlock->rw_state->reader_refcnt);
read_unlock(&pcpu_rwlock->global_rwlock);
}
}
-out:
+ this_cpu_sub(pcpu_rwlock->rw_state->reader_refcnt, READER_PRESENT);
+
/* Prevent reordering of any subsequent reads/writes */
smp_mb();
}
-void percpu_read_unlock(struct percpu_rwlock *pcpu_rwlock)
+void percpu_read_unlock_irqsafe(struct percpu_rwlock *pcpu_rwlock)
{
/*
* We never allow heterogeneous nesting of readers. So it is trivial
* to find out the kind of reader we are, and undo the operation
- * done by our corresponding percpu_read_lock().
+ * done by our corresponding percpu_read_lock_irqsafe().
*/
/* Try to fast-path: a nested percpu reader is the simplest case */
@@ -158,7 +171,8 @@ void percpu_read_unlock(struct percpu_rwlock *pcpu_rwlock)
preempt_enable();
}
-void percpu_write_lock(struct percpu_rwlock *pcpu_rwlock)
+void percpu_write_lock_irqsave(struct percpu_rwlock *pcpu_rwlock,
+ unsigned long *flags)
{
unsigned int cpu;
@@ -187,10 +201,11 @@ void percpu_write_lock(struct percpu_rwlock *pcpu_rwlock)
}
smp_mb(); /* Complete the wait-for-readers, before taking the lock */
- write_lock(&pcpu_rwlock->global_rwlock);
+ write_lock_irqsave(&pcpu_rwlock->global_rwlock, *flags);
}
-void percpu_write_unlock(struct percpu_rwlock *pcpu_rwlock)
+void percpu_write_unlock_irqrestore(struct percpu_rwlock *pcpu_rwlock,
+ unsigned long *flags)
{
unsigned int cpu;
@@ -205,6 +220,6 @@ void percpu_write_unlock(struct percpu_rwlock *pcpu_rwlock)
for_each_possible_cpu(cpu)
per_cpu_ptr(pcpu_rwlock->rw_state, cpu)->writer_signal = false;
- write_unlock(&pcpu_rwlock->global_rwlock);
+ write_unlock_irqrestore(&pcpu_rwlock->global_rwlock, *flags);
}
^ permalink raw reply related
* [PATCH v6 04/46] percpu_rwlock: Implement the core design of Per-CPU Reader-Writer Locks
From: Srivatsa S. Bhat @ 2013-02-18 12:38 UTC (permalink / raw)
To: tglx, peterz, tj, oleg, paulmck, rusty, mingo, akpm, namhyung
Cc: rostedt, wangyun, xiaoguangrong, rjw, sbw, fweisbec, linux,
nikunj, srivatsa.bhat, linux-pm, linux-arch, linux-arm-kernel,
linuxppc-dev, netdev, linux-doc, linux-kernel, walken,
vincent.guittot
In-Reply-To: <20130218123714.26245.61816.stgit@srivatsabhat.in.ibm.com>
Using global rwlocks as the backend for per-CPU rwlocks helps us avoid many
lock-ordering related problems (unlike per-cpu locks). However, global
rwlocks lead to unnecessary cache-line bouncing even when there are no
writers present, which can slow down the system needlessly.
Per-cpu counters can help solve the cache-line bouncing problem. So we
actually use the best of both: per-cpu counters (no-waiting) at the reader
side in the fast-path, and global rwlocks in the slowpath.
[ Fastpath = no writer is active; Slowpath = a writer is active ]
IOW, the readers just increment/decrement their per-cpu refcounts (disabling
interrupts during the updates, if necessary) when no writer is active.
When a writer becomes active, he signals all readers to switch to global
rwlocks for the duration of his activity. The readers switch over when it
is safe for them (ie., when they are about to start a fresh, non-nested
read-side critical section) and start using (holding) the global rwlock for
read in their subsequent critical sections.
The writer waits for every existing reader to switch, and then acquires the
global rwlock for write and enters his critical section. Later, the writer
signals all readers that he is done, and that they can go back to using their
per-cpu refcounts again.
Note that the lock-safety (despite the per-cpu scheme) comes from the fact
that the readers can *choose* _when_ to switch to rwlocks upon the writer's
signal. And the readers don't wait on anybody based on the per-cpu counters.
The only true synchronization that involves waiting at the reader-side in this
scheme, is the one arising from the global rwlock, which is safe from circular
locking dependency issues.
Reader-writer locks and per-cpu counters are recursive, so they can be
used in a nested fashion in the reader-path, which makes per-CPU rwlocks also
recursive. Also, this design of switching the synchronization scheme ensures
that you can safely nest and use these locks in a very flexible manner.
I'm indebted to Michael Wang and Xiao Guangrong for their numerous thoughtful
suggestions and ideas, which inspired and influenced many of the decisions in
this as well as previous designs. Thanks a lot Michael and Xiao!
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
---
lib/percpu-rwlock.c | 139 ++++++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 137 insertions(+), 2 deletions(-)
diff --git a/lib/percpu-rwlock.c b/lib/percpu-rwlock.c
index f938096..edefdea 100644
--- a/lib/percpu-rwlock.c
+++ b/lib/percpu-rwlock.c
@@ -27,6 +27,24 @@
#include <linux/percpu-rwlock.h>
#include <linux/errno.h>
+#include <asm/processor.h>
+
+
+#define reader_yet_to_switch(pcpu_rwlock, cpu) \
+ (ACCESS_ONCE(per_cpu_ptr((pcpu_rwlock)->rw_state, cpu)->reader_refcnt))
+
+#define reader_percpu_nesting_depth(pcpu_rwlock) \
+ (__this_cpu_read((pcpu_rwlock)->rw_state->reader_refcnt))
+
+#define reader_uses_percpu_refcnt(pcpu_rwlock) \
+ reader_percpu_nesting_depth(pcpu_rwlock)
+
+#define reader_nested_percpu(pcpu_rwlock) \
+ (reader_percpu_nesting_depth(pcpu_rwlock) > 1)
+
+#define writer_active(pcpu_rwlock) \
+ (__this_cpu_read((pcpu_rwlock)->rw_state->writer_signal))
+
int __percpu_init_rwlock(struct percpu_rwlock *pcpu_rwlock,
const char *name, struct lock_class_key *rwlock_key)
@@ -55,21 +73,138 @@ void percpu_free_rwlock(struct percpu_rwlock *pcpu_rwlock)
void percpu_read_lock(struct percpu_rwlock *pcpu_rwlock)
{
- read_lock(&pcpu_rwlock->global_rwlock);
+ preempt_disable();
+
+ /*
+ * Let the writer know that a reader is active, even before we choose
+ * our reader-side synchronization scheme.
+ */
+ this_cpu_inc(pcpu_rwlock->rw_state->reader_refcnt);
+
+ /*
+ * If we are already using per-cpu refcounts, it is not safe to switch
+ * the synchronization scheme. So continue using the refcounts.
+ */
+ if (reader_nested_percpu(pcpu_rwlock))
+ return;
+
+ /*
+ * The write to 'reader_refcnt' must be visible before we read
+ * 'writer_signal'.
+ */
+ smp_mb();
+
+ if (likely(!writer_active(pcpu_rwlock))) {
+ goto out;
+ } else {
+ /* Writer is active, so switch to global rwlock. */
+ read_lock(&pcpu_rwlock->global_rwlock);
+
+ /*
+ * We might have raced with a writer going inactive before we
+ * took the read-lock. So re-evaluate whether we still need to
+ * hold the rwlock or if we can switch back to per-cpu
+ * refcounts. (This also helps avoid heterogeneous nesting of
+ * readers).
+ */
+ if (writer_active(pcpu_rwlock)) {
+ /*
+ * The above writer_active() check can get reordered
+ * with this_cpu_dec() below, but this is OK, because
+ * holding the rwlock is conservative.
+ */
+ this_cpu_dec(pcpu_rwlock->rw_state->reader_refcnt);
+ } else {
+ read_unlock(&pcpu_rwlock->global_rwlock);
+ }
+ }
+
+out:
+ /* Prevent reordering of any subsequent reads/writes */
+ smp_mb();
}
void percpu_read_unlock(struct percpu_rwlock *pcpu_rwlock)
{
- read_unlock(&pcpu_rwlock->global_rwlock);
+ /*
+ * We never allow heterogeneous nesting of readers. So it is trivial
+ * to find out the kind of reader we are, and undo the operation
+ * done by our corresponding percpu_read_lock().
+ */
+
+ /* Try to fast-path: a nested percpu reader is the simplest case */
+ if (reader_nested_percpu(pcpu_rwlock)) {
+ this_cpu_dec(pcpu_rwlock->rw_state->reader_refcnt);
+ preempt_enable();
+ return;
+ }
+
+ /*
+ * Now we are left with only 2 options: a non-nested percpu reader,
+ * or a reader holding rwlock
+ */
+ if (reader_uses_percpu_refcnt(pcpu_rwlock)) {
+ /*
+ * Complete the critical section before decrementing the
+ * refcnt. We can optimize this away if we are a nested
+ * reader (the case above).
+ */
+ smp_mb();
+ this_cpu_dec(pcpu_rwlock->rw_state->reader_refcnt);
+ } else {
+ read_unlock(&pcpu_rwlock->global_rwlock);
+ }
+
+ preempt_enable();
}
void percpu_write_lock(struct percpu_rwlock *pcpu_rwlock)
{
+ unsigned int cpu;
+
+ /*
+ * Tell all readers that a writer is becoming active, so that they
+ * start switching over to the global rwlock.
+ */
+ for_each_possible_cpu(cpu)
+ per_cpu_ptr(pcpu_rwlock->rw_state, cpu)->writer_signal = true;
+
+ smp_mb();
+
+ /*
+ * Wait for every reader to see the writer's signal and switch from
+ * percpu refcounts to global rwlock.
+ *
+ * If a reader is still using percpu refcounts, wait for him to switch.
+ * Else, we can safely go ahead, because either the reader has already
+ * switched over, or the next reader that comes along on that CPU will
+ * notice the writer's signal and will switch over to the rwlock.
+ */
+
+ for_each_possible_cpu(cpu) {
+ while (reader_yet_to_switch(pcpu_rwlock, cpu))
+ cpu_relax();
+ }
+
+ smp_mb(); /* Complete the wait-for-readers, before taking the lock */
write_lock(&pcpu_rwlock->global_rwlock);
}
void percpu_write_unlock(struct percpu_rwlock *pcpu_rwlock)
{
+ unsigned int cpu;
+
+ /* Complete the critical section before clearing ->writer_signal */
+ smp_mb();
+
+ /*
+ * Inform all readers that we are done, so that they can switch back
+ * to their per-cpu refcounts. (We don't need to wait for them to
+ * see it).
+ */
+ for_each_possible_cpu(cpu)
+ per_cpu_ptr(pcpu_rwlock->rw_state, cpu)->writer_signal = false;
+
write_unlock(&pcpu_rwlock->global_rwlock);
}
^ permalink raw reply related
* [PATCH v6 03/46] percpu_rwlock: Provide a way to define and init percpu-rwlocks at compile time
From: Srivatsa S. Bhat @ 2013-02-18 12:38 UTC (permalink / raw)
To: tglx, peterz, tj, oleg, paulmck, rusty, mingo, akpm, namhyung
Cc: rostedt, wangyun, xiaoguangrong, rjw, sbw, fweisbec, linux,
nikunj, srivatsa.bhat, linux-pm, linux-arch, linux-arm-kernel,
linuxppc-dev, netdev, linux-doc, linux-kernel, walken,
vincent.guittot
In-Reply-To: <20130218123714.26245.61816.stgit@srivatsabhat.in.ibm.com>
Add the support for defining and initializing percpu-rwlocks at compile time
for those users who would like to use percpu-rwlocks really early in the boot
process (even before dynamic per-CPU allocations can begin).
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
---
include/linux/percpu-rwlock.h | 15 +++++++++++++++
1 file changed, 15 insertions(+)
diff --git a/include/linux/percpu-rwlock.h b/include/linux/percpu-rwlock.h
index 74eaf4d..5590b1e 100644
--- a/include/linux/percpu-rwlock.h
+++ b/include/linux/percpu-rwlock.h
@@ -49,6 +49,21 @@ extern int __percpu_init_rwlock(struct percpu_rwlock *,
extern void percpu_free_rwlock(struct percpu_rwlock *);
+
+#define __PERCPU_RWLOCK_INIT(name) \
+ { \
+ .rw_state = &name##_rw_state, \
+ .global_rwlock = __RW_LOCK_UNLOCKED(name.global_rwlock) \
+ }
+
+#define DEFINE_PERCPU_RWLOCK(name) \
+ static DEFINE_PER_CPU(struct rw_state, name##_rw_state); \
+ struct percpu_rwlock (name) = __PERCPU_RWLOCK_INIT(name);
+
+#define DEFINE_STATIC_PERCPU_RWLOCK(name) \
+ static DEFINE_PER_CPU(struct rw_state, name##_rw_state); \
+ static struct percpu_rwlock(name) = __PERCPU_RWLOCK_INIT(name);
+
#define percpu_init_rwlock(pcpu_rwlock) \
({ static struct lock_class_key rwlock_key; \
__percpu_init_rwlock(pcpu_rwlock, #pcpu_rwlock, &rwlock_key); \
^ permalink raw reply related
* [PATCH v6 02/46] percpu_rwlock: Introduce per-CPU variables for the reader and the writer
From: Srivatsa S. Bhat @ 2013-02-18 12:38 UTC (permalink / raw)
To: tglx, peterz, tj, oleg, paulmck, rusty, mingo, akpm, namhyung
Cc: rostedt, wangyun, xiaoguangrong, rjw, sbw, fweisbec, linux,
nikunj, srivatsa.bhat, linux-pm, linux-arch, linux-arm-kernel,
linuxppc-dev, netdev, linux-doc, linux-kernel, walken,
vincent.guittot
In-Reply-To: <20130218123714.26245.61816.stgit@srivatsabhat.in.ibm.com>
Per-CPU rwlocks ought to give better performance than global rwlocks.
That is where the "per-CPU" component comes in. So introduce the necessary
per-CPU variables that would be necessary at the reader and the writer sides,
and add the support for dynamically initializing per-CPU rwlocks.
These per-CPU variables will be used subsequently to implement the core
algorithm behind per-CPU rwlocks.
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
---
include/linux/percpu-rwlock.h | 8 ++++++++
lib/percpu-rwlock.c | 12 ++++++++++++
2 files changed, 20 insertions(+)
diff --git a/include/linux/percpu-rwlock.h b/include/linux/percpu-rwlock.h
index 0caf81f..74eaf4d 100644
--- a/include/linux/percpu-rwlock.h
+++ b/include/linux/percpu-rwlock.h
@@ -28,7 +28,13 @@
#include <linux/lockdep.h>
#include <linux/spinlock.h>
+struct rw_state {
+ unsigned long reader_refcnt;
+ bool writer_signal;
+};
+
struct percpu_rwlock {
+ struct rw_state __percpu *rw_state;
rwlock_t global_rwlock;
};
@@ -41,6 +47,8 @@ extern void percpu_write_unlock(struct percpu_rwlock *);
extern int __percpu_init_rwlock(struct percpu_rwlock *,
const char *, struct lock_class_key *);
+extern void percpu_free_rwlock(struct percpu_rwlock *);
+
#define percpu_init_rwlock(pcpu_rwlock) \
({ static struct lock_class_key rwlock_key; \
__percpu_init_rwlock(pcpu_rwlock, #pcpu_rwlock, &rwlock_key); \
diff --git a/lib/percpu-rwlock.c b/lib/percpu-rwlock.c
index 111a238..f938096 100644
--- a/lib/percpu-rwlock.c
+++ b/lib/percpu-rwlock.c
@@ -31,6 +31,10 @@
int __percpu_init_rwlock(struct percpu_rwlock *pcpu_rwlock,
const char *name, struct lock_class_key *rwlock_key)
{
+ pcpu_rwlock->rw_state = alloc_percpu(struct rw_state);
+ if (unlikely(!pcpu_rwlock->rw_state))
+ return -ENOMEM;
+
/* ->global_rwlock represents the whole percpu_rwlock for lockdep */
#ifdef CONFIG_DEBUG_SPINLOCK
__rwlock_init(&pcpu_rwlock->global_rwlock, name, rwlock_key);
@@ -41,6 +45,14 @@ int __percpu_init_rwlock(struct percpu_rwlock *pcpu_rwlock,
return 0;
}
+void percpu_free_rwlock(struct percpu_rwlock *pcpu_rwlock)
+{
+ free_percpu(pcpu_rwlock->rw_state);
+
+ /* Catch use-after-free bugs */
+ pcpu_rwlock->rw_state = NULL;
+}
+
void percpu_read_lock(struct percpu_rwlock *pcpu_rwlock)
{
read_lock(&pcpu_rwlock->global_rwlock);
^ permalink raw reply related
* [PATCH v6 00/46] CPU hotplug: stop_machine()-free CPU hotplug
From: Srivatsa S. Bhat @ 2013-02-18 12:38 UTC (permalink / raw)
To: tglx, peterz, tj, oleg, paulmck, rusty, mingo, akpm, namhyung
Cc: rostedt, wangyun, xiaoguangrong, rjw, sbw, fweisbec, linux,
nikunj, srivatsa.bhat, linux-pm, linux-arch, linux-arm-kernel,
linuxppc-dev, netdev, linux-doc, linux-kernel, walken,
vincent.guittot
Hi,
This patchset removes CPU hotplug's dependence on stop_machine() from the CPU
offline path and provides an alternative (set of APIs) to preempt_disable() to
prevent CPUs from going offline, which can be invoked from atomic context.
The motivation behind the removal of stop_machine() is to avoid its ill-effects
and thus improve the design of CPU hotplug. (More description regarding this
is available in the patches).
All the users of preempt_disable()/local_irq_disable() who used to use it to
prevent CPU offline, have been converted to the new primitives introduced in the
patchset. Also, the CPU_DYING notifiers have been audited to check whether
they can cope up with the removal of stop_machine() or whether they need to
use new locks for synchronization (all CPU_DYING notifiers looked OK, without
the need for any new locks).
Applies on current mainline (v3.8-rc7+).
This patchset is available in the following git branch:
git://github.com/srivatsabhat/linux.git stop-machine-free-cpu-hotplug-v6
Overview of the patches:
-----------------------
Patches 1 to 7 introduce a generic, flexible Per-CPU Reader-Writer Locking
scheme.
Patch 8 uses this synchronization mechanism to build the
get/put_online_cpus_atomic() APIs which can be used from atomic context, to
prevent CPUs from going offline.
Patch 9 is a cleanup; it converts preprocessor macros to static inline
functions.
Patches 10 to 43 convert various call-sites to use the new APIs.
Patch 44 is the one which actually removes stop_machine() from the CPU
offline path.
Patch 45 decouples stop_machine() and CPU hotplug from Kconfig.
Patch 46 updates the documentation to reflect the new APIs.
Changes in v6:
--------------
* Fixed issues related to memory barriers, as pointed out by Paul and Oleg.
* Fixed the locking issue related to clockevents_lock, which was being
triggered when cpu idle was enabled.
* Some code restructuring to improve readability and to enhance some fastpath
optimizations.
* Randconfig build-fixes, reported by Fengguang Wu.
Changes in v5:
--------------
Exposed a new generic locking scheme: Flexible Per-CPU Reader-Writer locks,
based on the synchronization schemes already discussed in the previous
versions, and used it in CPU hotplug, to implement the new APIs.
Audited the CPU_DYING notifiers in the kernel source tree and replaced
usages of preempt_disable() with the new get/put_online_cpus_atomic() APIs
where necessary.
Changes in v4:
--------------
The synchronization scheme has been simplified quite a bit, which makes it
look a lot less complex than before. Some highlights:
* Implicit ACKs:
The earlier design required the readers to explicitly ACK the writer's
signal. The new design uses implicit ACKs instead. The reader switching
over to rwlock implicitly tells the writer to stop waiting for that reader.
* No atomic operations:
Since we got rid of explicit ACKs, we no longer have the need for a reader
and a writer to update the same counter. So we can get rid of atomic ops
too.
Changes in v3:
--------------
* Dropped the _light() and _full() variants of the APIs. Provided a single
interface: get/put_online_cpus_atomic().
* Completely redesigned the synchronization mechanism again, to make it
fast and scalable at the reader-side in the fast-path (when no hotplug
writers are active). This new scheme also ensures that there is no
possibility of deadlocks due to circular locking dependency.
In summary, this provides the scalability and speed of per-cpu rwlocks
(without actually using them), while avoiding the downside (deadlock
possibilities) which is inherent in any per-cpu locking scheme that is
meant to compete with preempt_disable()/enable() in terms of flexibility.
The problem with using per-cpu locking to replace preempt_disable()/enable
was explained here:
https://lkml.org/lkml/2012/12/6/290
Basically we use per-cpu counters (for scalability) when no writers are
active, and then switch to global rwlocks (for lock-safety) when a writer
becomes active. It is a slightly complex scheme, but it is based on
standard principles of distributed algorithms.
Changes in v2:
-------------
* Completely redesigned the synchronization scheme to avoid using any extra
cpumasks.
* Provided APIs for 2 types of atomic hotplug readers: "light" (for
light-weight) and "full". We wish to have more "light" readers than
the "full" ones, to avoid indirectly inducing the "stop_machine effect"
without even actually using stop_machine().
And the patches show that it _is_ generally true: 5 patches deal with
"light" readers, whereas only 1 patch deals with a "full" reader.
Also, the "light" readers happen to be in very hot paths. So it makes a
lot of sense to have such a distinction and a corresponding light-weight
API.
Links to previous versions:
v5: http://lwn.net/Articles/533553/
v4: https://lkml.org/lkml/2012/12/11/209
v3: https://lkml.org/lkml/2012/12/7/287
v2: https://lkml.org/lkml/2012/12/5/322
v1: https://lkml.org/lkml/2012/12/4/88
--
Paul E. McKenney (1):
cpu: No more __stop_machine() in _cpu_down()
Srivatsa S. Bhat (45):
percpu_rwlock: Introduce the global reader-writer lock backend
percpu_rwlock: Introduce per-CPU variables for the reader and the writer
percpu_rwlock: Provide a way to define and init percpu-rwlocks at compile time
percpu_rwlock: Implement the core design of Per-CPU Reader-Writer Locks
percpu_rwlock: Make percpu-rwlocks IRQ-safe, optimally
percpu_rwlock: Rearrange the read-lock code to fastpath nested percpu readers
percpu_rwlock: Allow writers to be readers, and add lockdep annotations
CPU hotplug: Provide APIs to prevent CPU offline from atomic context
CPU hotplug: Convert preprocessor macros to static inline functions
smp, cpu hotplug: Fix smp_call_function_*() to prevent CPU offline properly
smp, cpu hotplug: Fix on_each_cpu_*() to prevent CPU offline properly
sched/timer: Use get/put_online_cpus_atomic() to prevent CPU offline
sched/migration: Use raw_spin_lock/unlock since interrupts are already disabled
sched/rt: Use get/put_online_cpus_atomic() to prevent CPU offline
tick: Use get/put_online_cpus_atomic() to prevent CPU offline
time/clocksource: Use get/put_online_cpus_atomic() to prevent CPU offline
clockevents: Use get/put_online_cpus_atomic() in clockevents_notify()
softirq: Use get/put_online_cpus_atomic() to prevent CPU offline
irq: Use get/put_online_cpus_atomic() to prevent CPU offline
net: Use get/put_online_cpus_atomic() to prevent CPU offline
block: Use get/put_online_cpus_atomic() to prevent CPU offline
crypto: pcrypt - Protect access to cpu_online_mask with get/put_online_cpus()
infiniband: ehca: Use get/put_online_cpus_atomic() to prevent CPU offline
[SCSI] fcoe: Use get/put_online_cpus_atomic() to prevent CPU offline
staging: octeon: Use get/put_online_cpus_atomic() to prevent CPU offline
x86: Use get/put_online_cpus_atomic() to prevent CPU offline
perf/x86: Use get/put_online_cpus_atomic() to prevent CPU offline
KVM: Use get/put_online_cpus_atomic() to prevent CPU offline from atomic context
kvm/vmx: Use get/put_online_cpus_atomic() to prevent CPU offline
x86/xen: Use get/put_online_cpus_atomic() to prevent CPU offline
alpha/smp: Use get/put_online_cpus_atomic() to prevent CPU offline
blackfin/smp: Use get/put_online_cpus_atomic() to prevent CPU offline
cris/smp: Use get/put_online_cpus_atomic() to prevent CPU offline
hexagon/smp: Use get/put_online_cpus_atomic() to prevent CPU offline
ia64: Use get/put_online_cpus_atomic() to prevent CPU offline
m32r: Use get/put_online_cpus_atomic() to prevent CPU offline
MIPS: Use get/put_online_cpus_atomic() to prevent CPU offline
mn10300: Use get/put_online_cpus_atomic() to prevent CPU offline
parisc: Use get/put_online_cpus_atomic() to prevent CPU offline
powerpc: Use get/put_online_cpus_atomic() to prevent CPU offline
sh: Use get/put_online_cpus_atomic() to prevent CPU offline
sparc: Use get/put_online_cpus_atomic() to prevent CPU offline
tile: Use get/put_online_cpus_atomic() to prevent CPU offline
CPU hotplug, stop_machine: Decouple CPU hotplug from stop_machine() in Kconfig
Documentation/cpu-hotplug: Remove references to stop_machine()
Documentation/cpu-hotplug.txt | 17 +-
arch/alpha/kernel/smp.c | 19 +-
arch/arm/Kconfig | 1
arch/blackfin/Kconfig | 1
arch/blackfin/mach-common/smp.c | 6 -
arch/cris/arch-v32/kernel/smp.c | 8 +
arch/hexagon/kernel/smp.c | 5
arch/ia64/Kconfig | 1
arch/ia64/kernel/irq_ia64.c | 13 +
arch/ia64/kernel/perfmon.c | 6 +
arch/ia64/kernel/smp.c | 23 ++
arch/ia64/mm/tlb.c | 6 -
arch/m32r/kernel/smp.c | 12 +
arch/mips/Kconfig | 1
arch/mips/kernel/cevt-smtc.c | 8 +
arch/mips/kernel/smp.c | 16 +-
arch/mips/kernel/smtc.c | 3
arch/mips/mm/c-octeon.c | 4
arch/mn10300/Kconfig | 1
arch/mn10300/kernel/smp.c | 2
arch/mn10300/mm/cache-smp.c | 5
arch/mn10300/mm/tlb-smp.c | 15 +
arch/parisc/Kconfig | 1
arch/parisc/kernel/smp.c | 4
arch/powerpc/Kconfig | 1
arch/powerpc/mm/mmu_context_nohash.c | 2
arch/s390/Kconfig | 1
arch/sh/Kconfig | 1
arch/sh/kernel/smp.c | 12 +
arch/sparc/Kconfig | 1
arch/sparc/kernel/leon_smp.c | 2
arch/sparc/kernel/smp_64.c | 9 -
arch/sparc/kernel/sun4d_smp.c | 2
arch/sparc/kernel/sun4m_smp.c | 3
arch/tile/kernel/smp.c | 4
arch/x86/Kconfig | 1
arch/x86/include/asm/ipi.h | 5
arch/x86/kernel/apic/apic_flat_64.c | 10 +
arch/x86/kernel/apic/apic_numachip.c | 5
arch/x86/kernel/apic/es7000_32.c | 5
arch/x86/kernel/apic/io_apic.c | 7 -
arch/x86/kernel/apic/ipi.c | 10 +
arch/x86/kernel/apic/x2apic_cluster.c | 4
arch/x86/kernel/apic/x2apic_uv_x.c | 4
arch/x86/kernel/cpu/mcheck/therm_throt.c | 4
arch/x86/kernel/cpu/perf_event_intel_uncore.c | 5
arch/x86/kvm/vmx.c | 8 +
arch/x86/mm/tlb.c | 14 +
arch/x86/xen/mmu.c | 11 +
arch/x86/xen/smp.c | 9 +
block/blk-softirq.c | 4
crypto/pcrypt.c | 4
drivers/infiniband/hw/ehca/ehca_irq.c | 8 +
drivers/scsi/fcoe/fcoe.c | 7 +
drivers/staging/octeon/ethernet-rx.c | 3
include/linux/cpu.h | 8 +
include/linux/percpu-rwlock.h | 74 +++++++
include/linux/stop_machine.h | 2
init/Kconfig | 2
kernel/cpu.c | 59 +++++-
kernel/irq/manage.c | 7 +
kernel/sched/core.c | 36 +++-
kernel/sched/fair.c | 5
kernel/sched/rt.c | 3
kernel/smp.c | 65 ++++--
kernel/softirq.c | 3
kernel/time/clockevents.c | 3
kernel/time/clocksource.c | 5
kernel/time/tick-broadcast.c | 2
kernel/timer.c | 2
lib/Kconfig | 3
lib/Makefile | 1
lib/percpu-rwlock.c | 256 +++++++++++++++++++++++++
net/core/dev.c | 9 +
virt/kvm/kvm_main.c | 10 +
75 files changed, 776 insertions(+), 123 deletions(-)
create mode 100644 include/linux/percpu-rwlock.h
create mode 100644 lib/percpu-rwlock.c
Regards,
Srivatsa S. Bhat
IBM Linux Technology Center
^ permalink raw reply
* [RFC PATCH] xfrm: release neighbor upon dst destruction
From: Romain KUNTZ @ 2013-02-18 12:36 UTC (permalink / raw)
To: netdev@vger.kernel.org
Cc: Steffen Klassert, davem@davemloft.net Miller,
yoshfuji@linux-ipv6.org Hideaki
Neighbor is cloned in xfrm6_fill_dst but seems to never be released.
Neighbor entry should be released when XFRM6 dst entry is destroyed
in xfrm6_dst_destroy, otherwise references may be kept forever on
the device pointed by the neighbor entry.
I may not have understood all the subtleties of XFRM & dst so I would
be happy to receive comments on this patch.
Signed-off-by: Romain Kuntz <r.kuntz@ipflavors.com>
---
net/ipv6/xfrm6_policy.c | 2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index c984413..8f32718 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -236,6 +236,8 @@ static void xfrm6_dst_destroy(struct dst_entry *dst)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
+ if (likely(xdst->u.rt6.n))
+ neigh_release(xdst->u.rt6.n);
if (likely(xdst->u.rt6.rt6i_idev))
in6_dev_put(xdst->u.rt6.rt6i_idev);
dst_destroy_metrics_generic(dst);
--
1.7.2.5
^ permalink raw reply related
* [PATCH NET-NEXT] bonding: fix bond_release_all inconsistencies
From: Nikolay Aleksandrov @ 2013-02-18 12:27 UTC (permalink / raw)
To: netdev; +Cc: andy, fubar, davem
This patch fixes the following inconsistencies in bond_release_all:
- IFF_BONDING flag is not stripped from slaves
- MTU is not restored
- no netdev notifiers are sent
Instead of trying to keep bond_release and bond_release_all in sync
I think we can re-use bond_release as the environment for calling it
is correct (RTNL is held). I have been running tests for the past
week and they came out successful. The only way for bond_release to fail
is for the slave to be attached in a different bond or to not be a slave
but that cannot happen as RTNL is held and no slave manipulations can be
achieved.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
---
drivers/net/bonding/bond_main.c | 106 ++--------------------------------------
1 file changed, 5 insertions(+), 101 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 94c1534..fcfc880 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2140,113 +2140,17 @@ static int bond_release_and_destroy(struct net_device *bond_dev,
/*
* This function releases all slaves.
*/
-static int bond_release_all(struct net_device *bond_dev)
+static void bond_release_all(struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
- struct slave *slave;
- struct net_device *slave_dev;
- struct sockaddr addr;
-
- write_lock_bh(&bond->lock);
-
- netif_carrier_off(bond_dev);
if (bond->slave_cnt == 0)
- goto out;
-
- bond->current_arp_slave = NULL;
- bond->primary_slave = NULL;
- bond_change_active_slave(bond, NULL);
-
- while ((slave = bond->first_slave) != NULL) {
- /* Inform AD package of unbinding of slave
- * before slave is detached from the list.
- */
- if (bond->params.mode == BOND_MODE_8023AD)
- bond_3ad_unbind_slave(slave);
-
- slave_dev = slave->dev;
- bond_detach_slave(bond, slave);
-
- /* now that the slave is detached, unlock and perform
- * all the undo steps that should not be called from
- * within a lock.
- */
- write_unlock_bh(&bond->lock);
-
- /* unregister rx_handler early so bond_handle_frame wouldn't
- * be called for this slave anymore.
- */
- netdev_rx_handler_unregister(slave_dev);
- synchronize_net();
-
- if (bond_is_lb(bond)) {
- /* must be called only after the slave
- * has been detached from the list
- */
- bond_alb_deinit_slave(bond, slave);
- }
-
- bond_destroy_slave_symlinks(bond_dev, slave_dev);
- bond_del_vlans_from_slave(bond, slave_dev);
-
- /* If the mode USES_PRIMARY, then we should only remove its
- * promisc and mc settings if it was the curr_active_slave, but that was
- * already taken care of above when we detached the slave
- */
- if (!USES_PRIMARY(bond->params.mode)) {
- /* unset promiscuity level from slave */
- if (bond_dev->flags & IFF_PROMISC)
- dev_set_promiscuity(slave_dev, -1);
-
- /* unset allmulti level from slave */
- if (bond_dev->flags & IFF_ALLMULTI)
- dev_set_allmulti(slave_dev, -1);
-
- /* flush master's mc_list from slave */
- netif_addr_lock_bh(bond_dev);
- bond_mc_list_flush(bond_dev, slave_dev);
- netif_addr_unlock_bh(bond_dev);
- }
-
- bond_upper_dev_unlink(bond_dev, slave_dev);
-
- slave_disable_netpoll(slave);
-
- /* close slave before restoring its mac address */
- dev_close(slave_dev);
-
- if (!bond->params.fail_over_mac) {
- /* restore original ("permanent") mac address*/
- memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN);
- addr.sa_family = slave_dev->type;
- dev_set_mac_address(slave_dev, &addr);
- }
-
- kfree(slave);
-
- /* re-acquire the lock before getting the next slave */
- write_lock_bh(&bond->lock);
- }
-
- eth_hw_addr_random(bond_dev);
- bond->dev_addr_from_first = true;
-
- if (bond_vlan_used(bond)) {
- pr_warning("%s: Warning: clearing HW address of %s while it still has VLANs.\n",
- bond_dev->name, bond_dev->name);
- pr_warning("%s: When re-adding slaves, make sure the bond's HW address matches its VLANs'.\n",
- bond_dev->name);
- }
-
+ return;
+ while (bond->first_slave != NULL)
+ bond_release(bond_dev, bond->first_slave->dev);
pr_info("%s: released all slaves\n", bond_dev->name);
-out:
- write_unlock_bh(&bond->lock);
-
- bond_compute_features(bond);
-
- return 0;
+ return;
}
/*
--
1.7.11.7
^ permalink raw reply related
* [PATCH] net: wireless: hostap: hostap_ap.c: Return -ENOMEM instead of -1 for if kmalloc() fails.
From: Kumar Amit Mehta @ 2013-02-18 12:13 UTC (permalink / raw)
To: j; +Cc: linville, wireless, netdev, linux-kernel, kernel-janitors
When memory allocation using, kmalloc() fails, report appropriate error value.
Signed-off-by: Kumar Amit Mehta <gmate.amit@gmail.com>
---
drivers/net/wireless/hostap/hostap_ap.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/wireless/hostap/hostap_ap.c b/drivers/net/wireless/hostap/hostap_ap.c
index c6ea995..dd9a18f 100644
--- a/drivers/net/wireless/hostap/hostap_ap.c
+++ b/drivers/net/wireless/hostap/hostap_ap.c
@@ -376,7 +376,7 @@ int ap_control_add_mac(struct mac_restrictions *mac_restrictions, u8 *mac)
entry = kmalloc(sizeof(struct mac_entry), GFP_KERNEL);
if (entry == NULL)
- return -1;
+ return -ENOMEM;
memcpy(entry->addr, mac, ETH_ALEN);
--
1.7.9.5
^ permalink raw reply related
* AW: ixgbe: Regression, unsupported SFP+ modules on 10Gbit/s X520 NIC no longer work with allow_unsupported_sfp=1
From: Stefan Behte @ 2013-02-18 12:13 UTC (permalink / raw)
To: Tantilov, Emil S, netdev
Cc: Skidmore, Donald C, Kirsher, Jeffrey T, Fujinaka, Todd,
Ronciak, John
In-Reply-To: <87618083B2453E4A8714035B62D67992337B4938@FMSMSX102.amr.corp.intel.com>
[-- Attachment #1: Type: text/plain, Size: 11485 bytes --]
Hi,
>I don't think this is a regression since the check you are bypassing with your patch has nothing to do with the unsupported SFP modules lock (this check is few lines below).
No, that part skipped by the goto.
>The check you are trying to bypass is actually for supported 1gig SFP module types.
Actually that's inaccurate: if it's not a compatible module, it's being marked as unsupported. That's the whole purpose of that code.
//if it's not a 10GE Module
if (comp_codes_10g == 0 &&
// and if the current module is NOT compatible (hw->phy.sfp_type must be 9, 10, 11 or 12, see ixgbe_type.h)
!(hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core1 ||
hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core0 ||
hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 ||
hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1)) {
// then mark hardware as unsupported -> the SFP will not be enabled
// but it should be, if allow_unsupported_sfp=1
hw->phy.type = ixgbe_phy_sfp_unsupported;
status = IXGBE_ERR_SFP_NOT_SUPPORTED;
// skip other stuff, e.g. the checks you mentioned below
goto out;
}
Ok, my patch is not nice. I've attached one that completely removes the block, as IMHO its only purpose is to lock out non-intel SFPs. Of course I've verified that the code works (at least for me :)).
>1. What is the SFP+ module you are using (make/model/type)?
The module is a TP-Link TL-SM311LS 1000BASE-LX LC.
>2. What is the hw->phy.sfp_type set to (you can add a printk, or if you plug it in after load there should be a "detected SFP+" message in dmesg).
It's in the log I sent:
[13920.949008] ixgbe 0000:02:00.1: MAC: 2, PHY: 14, SFP+: 65535, PBA No: E68793-005
So hw->phy.sfp_type is 65535.
>3. You said that you get the interfaces, but are they operational (link, pass traffic etc)?
I'm going to run some longterm tests for reliability. But yes, they appear to be working just fine.
>4. Because you mentioned that this is a regression - was there a previous version of the driver that loads without the unsupported errors with this SFP module?
Not sure, but as a result of the discussion (http://marc.info/?l=e1000-devel&m=132697406314730&w=2) there was a decision and patch that would allow non-intel SFPs.
So I don't care too much what we call this - the driver does not work as intended: Intel is preventing use of 3rd-party SFPs.
So can we please remove this lock-in?
Best regards,
Stefan Behte
--------------------------------------------
Stefan Behte
Teamleiter Systemadministration
Babiel GmbH
Erkrather Str. 224a
D-40233 Düsseldorf
Tel: 0211-179349 0
Fax: 0211-179349 29
E-Mail: s.behte@babiel.com
Internet: http://www.babiel.com
Geschäftsführer: Georg Babiel, Dr. Rainer Babiel, Harald Babiel Amtsgericht Düsseldorf HRB 38633
~~~~~~~~~~~~~~ DISCLAIMER ~~~~~~~~~~~~~~~
The information transmitted in this electronic mail message may contain confidential and or privileged materials. Any review, retransmission, dissemination or other use of or taking of any action in reliance upon, this information by persons or entities other than the intended recipient is prohibited. If you receive such e-mails in error, please contact the sender and delete the material from any computer.
-----Ursprüngliche Nachricht-----
Von: Tantilov, Emil S [mailto:emil.s.tantilov@intel.com]
Gesendet: Freitag, 15. Februar 2013 21:14
An: Stefan Behte; netdev@vger.kernel.org
Cc: Skidmore, Donald C; Kirsher, Jeffrey T; Fujinaka, Todd; Ronciak, John
Betreff: RE: ixgbe: Regression, unsupported SFP+ modules on 10Gbit/s X520 NIC no longer work with allow_unsupported_sfp=1
Stefan,
I don't think this is a regression since the check you are bypassing with your patch has nothing to do with the unsupported SFP modules lock (this check is few lines below). The check you are trying to bypass is actually for supported 1gig SFP module types. Could you provide some additional information about your setup?
1. What is the SFP+ module you are using (make/model/type)?
2. What is the hw->phy.sfp_type set to (you can add a printk, or if you plug it in after load there should be a "detected SFP+" message in dmesg).
3. You said that you get the interfaces, but are they operational (link, pass traffic etc)?
4. Because you mentioned that this is a regression - was there a previous version of the driver that loads without the unsupported errors with this SFP module?
Thanks,
Emil
>-----Original Message-----
>From: netdev-owner@vger.kernel.org [mailto:netdev-owner@vger.kernel.org] On
>Behalf Of Stefan Behte
>Sent: Thursday, February 14, 2013 4:58 PM
>To: netdev@vger.kernel.org
>Subject: ixgbe: Regression, unsupported SFP+ modules on 10Gbit/s X520 NIC
>no longer work with allow_unsupported_sfp=1
>
>Hello,
>
>I was told to send a mail, even though I had already opened
>https://bugzilla.kernel.org/show_bug.cgi?id=53901.
>
>Someone patched the ixgbe driver, and now non-intel SFPs do not work
>anymore, again. The issue of intel "lock-in" was discussed before here:
>http://marc.info/?l=e1000-devel&m=132697406314730&w=2
>
>A tested patch is attached.
>
>Here is what I do:
>
># modinfo ixgbe | grep parm
>parm: max_vfs:Maximum number of virtual functions to allocate per
>physical function - default is zero and maximum value is 63 (uint)
>parm: allow_unsupported_sfp:Allow unsupported and untested SFP+
>modules on 82599-based adapters (uint)
>parm: debug:Debug level (0=none,...,16=all) (int)
>
># modprobe -r ixgbe
># modprobe ixgbe allow_unsupported_sfp=0
># dmesg | grep ixgbe
>[13690.355090] ixgbe: Intel(R) 10 Gigabit PCI Express Network Driver -
>version 3.9.15-k
>[13690.355092] ixgbe: Copyright (c) 1999-2012 Intel Corporation.
>[13690.373128] ixgbe 0000:02:00.0: failed to load because an unsupported
>SFP+ module type was detected.
>[13690.373177] ixgbe 0000:02:00.0: Reload the driver after installing a
>supported module.
>[13690.390987] ixgbe 0000:02:00.1: failed to load because an unsupported
>SFP+ module type was detected.
>[13690.391036] ixgbe 0000:02:00.1: Reload the driver after installing a
>supported module.
>
># modprobe -r ixgbe
># modprobe ixgbe allow_unsupported_sfp=1
># dmesg | grep ixgbe
>[13679.088849] dca service started, version 1.12.1
>[13679.091174] ixgbe: Intel(R) 10 Gigabit PCI Express Network Driver -
>version 3.9.15-k
>[13679.091177] ixgbe: Copyright (c) 1999-2012 Intel Corporation.
>[13679.109194] ixgbe 0000:02:00.0: failed to load because an unsupported
>SFP+ module type was detected.
>[13679.109243] ixgbe 0000:02:00.0: Reload the driver after installing a
>supported module.
>[13679.127399] ixgbe 0000:02:00.1: failed to load because an unsupported
>SFP+ module type was detected.
>[13679.127450] ixgbe 0000:02:00.1: Reload the driver after installing a
>supported module.
>[13690.352712] dca service started, version 1.12.1
>
>
>With the patch:
>
># modprobe -r ixgbe
># modprobe ixgbe allow_unsupported_sfp=0
># dmesg | grep ixgbe
>[13907.870087] ixgbe: Intel(R) 10 Gigabit PCI Express Network Driver -
>version 3.9.15-k
>[13907.870089] ixgbe: Copyright (c) 1999-2012 Intel Corporation.
>[13907.888106] ixgbe 0000:02:00.0: failed to load because an unsupported
>SFP+ module type was detected.
>[13907.888155] ixgbe 0000:02:00.0: Reload the driver after installing a
>supported module.
>[13907.906187] ixgbe 0000:02:00.1: failed to load because an unsupported
>SFP+ module type was detected.
>[13907.906237] ixgbe 0000:02:00.1: Reload the driver after installing a
>supported module.
>
>
># modprobe -r ixgbe
># modprobe ixgbe allow_unsupported_sfp=1
># dmesg | grep ixgbe
>[13914.534758] ixgbe: Intel(R) 10 Gigabit PCI Express Network Driver -
>version3.9.15-k
>[13914.534761] ixgbe: Copyright (c) 1999-2012 Intel Corporation.
>[13914.552820] ixgbe 0000:02:00.0 (unregistered net_device): WARNING: Intel
>(R) Network Connections are quality tested using Intel (R) Ethernet Optics.
>Using untested modules is not supported and may cause unstable operation or
>damage to
>the module or the adapter. Intel Corporation is not responsible for any
>harm caused by using untested modules.
>[13917.741931] ixgbe 0000:02:00.0: irq 50 for MSI/MSI-X
>[13917.741938] ixgbe 0000:02:00.0: irq 51 for MSI/MSI-X
>[13917.741942] ixgbe 0000:02:00.0: irq 52 for MSI/MSI-X
>[13917.741951] ixgbe 0000:02:00.0: irq 53 for MSI/MSI-X
>[13917.741955] ixgbe 0000:02:00.0: irq 54 for MSI/MSI-X
>[13917.741960] ixgbe 0000:02:00.0: irq 55 for MSI/MSI-X
>[13917.741965] ixgbe 0000:02:00.0: irq 56 for MSI/MSI-X
>[13917.741969] ixgbe 0000:02:00.0: irq 57 for MSI/MSI-X
>[13917.741973] ixgbe 0000:02:00.0: irq 58 for MSI/MSI-X
>[13917.742002] ixgbe 0000:02:00.0: Multiqueue Enabled: Rx Queue count = 8,
>Tx Queue count = 8
>[13917.742126] ixgbe 0000:02:00.0: (PCI Express:5.0GT/s:Width x8)
>90:e2:ba:37:3b:18
>[13917.742207] ixgbe 0000:02:00.0: MAC: 2, PHY: 14, SFP+: 65535, PBA No:
>E68793-005
>[13917.743461] ixgbe 0000:02:00.0: Intel(R) 10 Gigabit Network Connection
>[13917.761578] ixgbe 0000:02:00.1 (unregistered net_device): WARNING: Intel
>(R) Network Connections are quality tested using Intel (R) Ethernet Optics.
>Using untested modules is not supported and may cause unstable operation or
>damage to the module or the adapter. Intel Corporation is not responsible
>for any harm caused by using untested modules.
>[13920.948726] ixgbe 0000:02:00.1: irq 59 for MSI/MSI-X
>[13920.948737] ixgbe 0000:02:00.1: irq 60 for MSI/MSI-X
>[13920.948742] ixgbe 0000:02:00.1: irq 61 for MSI/MSI-X
>[13920.948746] ixgbe 0000:02:00.1: irq 62 for MSI/MSI-X
>[13920.948751] ixgbe 0000:02:00.1: irq 63 for MSI/MSI-X
>[13920.948757] ixgbe 0000:02:00.1: irq 64 for MSI/MSI-X
>[13920.948761] ixgbe 0000:02:00.1: irq 65 for MSI/MSI-X
>[13920.948767] ixgbe 0000:02:00.1: irq 66 for MSI/MSI-X
>[13920.948774] ixgbe 0000:02:00.1: irq 67 for MSI/MSI-X
>[13920.948803] ixgbe 0000:02:00.1: Multiqueue Enabled: Rx Queue count = 8,
>Tx Queue count = 8
>[13920.948927] ixgbe 0000:02:00.1: (PCI Express:5.0GT/s:Width x8)
>90:e2:ba:37:3b:19
>[13920.949008] ixgbe 0000:02:00.1: MAC: 2, PHY: 14, SFP+: 65535, PBA No:
>E68793-005
>[13920.950237] ixgbe 0000:02:00.1: Intel(R) 10 Gigabit Network Connection
>
>And then I get two nice Interfaces. Please apply. :)
>
>
>Best regards,
>
>Stefan Behte
>
>Babiel GmbH
>Moskauer Strasse 27
>D-40227 Düsseldorf
>
>Tel: 0211-179349 0
>Fax: 0211-179349 29
>E-Mail: S.Behte@babiel.com
>Internet: http://www.babiel.com
>
>Geschäftsführer: Georg Babiel, Dr. Rainer Babiel, Harald Babiel
>Amtsgericht Düsseldorf HRB 38633
>
>~~~~~~~~~~~~~~ DISCLAIMER ~~~~~~~~~~~~~~~
>
>The information transmitted in this electronic mail message may contain
>confidential and or privileged materials. Any review, retransmission,
>dissemination or other use of or taking of any action in reliance upon,
>this information by persons or entities other than the intended recipient
>is prohibited. If you receive such e-mails in error, please contact the
>sender and delete the material from any computer.
[-- Attachment #2: remove-intel-sfp-vendor-lock-in.patch --]
[-- Type: application/octet-stream, Size: 722 bytes --]
--- linux-3.7.7.ori/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c 2013-02-11 18:05:09.000000000 +0100
+++ ixgbe_phy.c 2013-02-18 12:48:46.000000000 +0100
@@ -1055,17 +1055,6 @@
goto out;
}
- /* Verify supported 1G SFP modules */
- if (comp_codes_10g == 0 &&
- !(hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core1 ||
- hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core0 ||
- hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 ||
- hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1)) {
- hw->phy.type = ixgbe_phy_sfp_unsupported;
- status = IXGBE_ERR_SFP_NOT_SUPPORTED;
- goto out;
- }
-
/* Anything else 82598-based is supported */
if (hw->mac.type == ixgbe_mac_82598EB) {
status = 0;
^ permalink raw reply
* Re: [PATCH v2 1/1] eventfd: implementation of EFD_MASK flag
From: Martin Sustrik @ 2013-02-18 11:57 UTC (permalink / raw)
To: Andrew Morton
Cc: Alexander Viro, Sha Zhengju, linux-fsdevel, linux-kernel, netdev,
Michael Kerrisk, Davide Libenzi, Andy Lutomirski, Eric Wong
In-Reply-To: <20130214145430.04f8750c.akpm@linux-foundation.org>
On 14/02/13 23:54, Andrew Morton wrote:
> This patch adds userspace interfaces which will require manpage
> updates. Please Cc Michael and work with him on getting those changes
> completed.
Right. It adds the efd_mask structure. As far as I understand how it
works is that the actual user-space definition of the structure should
be provided by glibc (sys/eventfd.h), right?
If so, should the man page be updated now? If so, it may result in the
situation where the man page describes a structure that's not available
in the user space yet.
Is there a formal process to do this kind of kernel+glibc+docs changes?
Martin
^ permalink raw reply
* [PATCH] net: wireless: orinoco: orinoco_usb.c: fix DMA buffers on stack
From: Kumar Amit Mehta @ 2013-02-18 11:37 UTC (permalink / raw)
To: linville
Cc: sarah.a.sharp, dan.carpenter, linux-wireless, netdev,
linux-kernel, kernel-janitors
This patch fixes an instance of DMA buffer on stack(being passed to
usb_control_msg) for the wireless USB version of the Agere Orinoco card driver.
It also fixes the missing audit for the return value of firmware download
routine. Found using smatch.
Signed-off-by: Kumar Amit Mehta <gmate.amit@gmail.com>
---
drivers/net/wireless/orinoco/orinoco_usb.c | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/drivers/net/wireless/orinoco/orinoco_usb.c b/drivers/net/wireless/orinoco/orinoco_usb.c
index 01624dc..7744f42 100644
--- a/drivers/net/wireless/orinoco/orinoco_usb.c
+++ b/drivers/net/wireless/orinoco/orinoco_usb.c
@@ -804,10 +804,15 @@ static inline int ezusb_8051_cpucs(struct ezusb_priv *upriv, int reset)
static int ezusb_firmware_download(struct ezusb_priv *upriv,
struct ez_usb_fw *fw)
{
- u8 fw_buffer[FW_BUF_SIZE];
+ u8 *fw_buffer;
int retval, addr;
int variant_offset;
+ fw_buffer = kmalloc(FW_BUF_SIZE, GFP_KERNEL);
+ if (!fw_buffer) {
+ printk(KERN_ERR PFX "Out of memory for firmware buffer.\n");
+ return -ENOMEM;
+ }
/*
* This byte is 1 and should be replaced with 0. The offset is
* 0x10AD in version 0.0.6. The byte in question should follow
@@ -859,6 +864,7 @@ static int ezusb_firmware_download(struct ezusb_priv *upriv,
printk(KERN_ERR PFX "Firmware download failed, error %d\n",
retval);
exit:
+ kfree(fw_buffer);
return retval;
}
@@ -1681,7 +1687,8 @@ static int ezusb_probe(struct usb_interface *interface,
firmware.code = fw_entry->data;
}
if (firmware.size && firmware.code) {
- ezusb_firmware_download(upriv, &firmware);
+ if (ezusb_firmware_download(upriv, &firmware))
+ goto error;
} else {
err("No firmware to download");
goto error;
--
1.7.9.5
^ permalink raw reply related
* [PATCH v3 1/1] eventfd: implementation of EFD_MASK flag
From: Martin Sustrik @ 2013-02-18 11:34 UTC (permalink / raw)
To: viro, handai.szj, linux-fsdevel, linux-kernel, netdev, davidel,
normalperson
Cc: mtk.manpages, Martin Sustrik
When implementing network protocols in user space, one has to implement
fake file descriptors to represent the sockets for the protocol.
Polling on such fake file descriptors is a problem (poll/select/epoll accept
only true file descriptors) and forces protocol implementers to use various
workarounds resulting in complex, non-standard and convoluted APIs.
More generally, ability to create full-blown file descriptors for
userspace-to-userspace signalling is missing. While eventfd(2) goes half the way
towards this goal it has follwoing shorcomings:
I. There's no way to signal POLLPRI, POLLHUP etc.
II. There's no way to signal arbitrary combination of POLL* flags. Most notably,
simultaneous !POLLIN and !POLLOUT, which is a perfectly valid combination
for a network protocol (rx buffer is empty and tx buffer is full), cannot be
signaled using eventfd.
This patch implements new EFD_MASK flag which solves the above problems.
Additionally, to provide a way to associate user-space state with eventfd
object, it allows to attach user-space data to the file descriptor.
The semantics of EFD_MASK are as follows:
eventfd(2):
If eventfd is created with EFD_MASK flag set, it is initialised in such a way
as to signal no events on the file descriptor when it is polled on. 'initval'
argument is ignored.
write(2):
User is allowed to write only buffers containing the following structure:
struct efd_mask {
short events;
union {
void *ptr;
uint32_t u32;
uint64_t u64;
};
};
The value of 'events' should be any combination of event flags as defined by
poll(2) function (POLLIN, POLLOUT, POLLERR, POLLHUP etc.) Specified events will
be signaled when polling (select, poll, epoll) on the eventfd is done later on.
'ptr', 'u32' or 'u64' are opaque data that are not interpreted by eventfd
object.
read(2):
User is allowed to read an efd_mask structure from the eventfd marked by
EFD_MASK. Returned value shall be the last one written to the eventfd.
select(2), poll(2) and similar:
When polling on the eventfd marked by EFD_MASK flag, all the events specified
in last written 'events' field shall be signaled.
Signed-off-by: Martin Sustrik <sustrik@250bpm.com>
---
Following changes were made to the patch since v2:
- eventfd_mask structure renamed to efd_mask to keep user-space prefixes
consistent
- efd_mask is __packed for all architectures
- eventfd.h header file added to uapi; given there wasn't one so far, in
addition to moving efd_mask there, I've moved also all the eventfd flags that
are meant to be visible from the user space
- comment for 'mask' member eventfd_ctx added
- synchronisation bugs in eventfd_read fixed
- several variable declarations moved from the beginning of the function to
the blocks where they are used
- changelog text made simpler and more up to the point
There was also a request to explain why this functionality is needed. I've
written an article explaining the problems user-space network protocol
implementers face here: http://www.250bpm.com/blog:16
---
fs/eventfd.c | 194 ++++++++++++++++++++++++++++--------------
include/linux/eventfd.h | 17 +---
include/uapi/linux/eventfd.h | 40 +++++++++
3 files changed, 172 insertions(+), 79 deletions(-)
create mode 100644 include/uapi/linux/eventfd.h
diff --git a/fs/eventfd.c b/fs/eventfd.c
index 35470d9..8f821b1 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -2,6 +2,7 @@
* fs/eventfd.c
*
* Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org>
+ * Copyright (C) 2013 Martin Sustrik <sustrik@250bpm.com>
*
*/
@@ -22,18 +23,31 @@
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
+#define EFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK)
+#define EFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS | EFD_SEMAPHORE | EFD_MASK)
+#define EFD_MASK_VALID_EVENTS (POLLIN | POLLPRI | POLLOUT | POLLERR | POLLHUP)
+
struct eventfd_ctx {
struct kref kref;
wait_queue_head_t wqh;
- /*
- * Every time that a write(2) is performed on an eventfd, the
- * value of the __u64 being written is added to "count" and a
- * wakeup is performed on "wqh". A read(2) will return the "count"
- * value to userspace, and will reset "count" to zero. The kernel
- * side eventfd_signal() also, adds to the "count" counter and
- * issue a wakeup.
- */
- __u64 count;
+ union {
+ /*
+ * Every time that a write(2) is performed on an eventfd, the
+ * value of the __u64 being written is added to "count" and a
+ * wakeup is performed on "wqh". A read(2) will return the
+ * "count" value to userspace, and will reset "count" to zero.
+ * The kernel side eventfd_signal() also, adds to the "count"
+ * counter and issue a wakeup.
+ */
+ __u64 count;
+
+ /*
+ * When using eventfd in EFD_MASK mode this stracture stores the
+ * current events to be signaled on the eventfd (events member)
+ * along with opaque user-defined data (data member).
+ */
+ struct efd_mask mask;
+ };
unsigned int flags;
};
@@ -55,6 +69,9 @@ __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n)
{
unsigned long flags;
+ /* This function should never be used with eventfd in the mask mode. */
+ BUG_ON(ctx->flags & EFD_MASK);
+
spin_lock_irqsave(&ctx->wqh.lock, flags);
if (ULLONG_MAX - ctx->count < n)
n = ULLONG_MAX - ctx->count;
@@ -123,12 +140,16 @@ static unsigned int eventfd_poll(struct file *file, poll_table *wait)
poll_wait(file, &ctx->wqh, wait);
spin_lock_irqsave(&ctx->wqh.lock, flags);
- if (ctx->count > 0)
- events |= POLLIN;
- if (ctx->count == ULLONG_MAX)
- events |= POLLERR;
- if (ULLONG_MAX - 1 > ctx->count)
- events |= POLLOUT;
+ if (ctx->flags & EFD_MASK) {
+ events = ctx->mask.events;
+ } else {
+ if (ctx->count > 0)
+ events |= POLLIN;
+ if (ctx->count == ULLONG_MAX)
+ events |= POLLERR;
+ if (ULLONG_MAX - 1 > ctx->count)
+ events |= POLLOUT;
+ }
spin_unlock_irqrestore(&ctx->wqh.lock, flags);
return events;
@@ -158,6 +179,9 @@ int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_t *wait,
{
unsigned long flags;
+ /* This function should never be used with eventfd in the mask mode. */
+ BUG_ON(ctx->flags & EFD_MASK);
+
spin_lock_irqsave(&ctx->wqh.lock, flags);
eventfd_ctx_do_read(ctx, cnt);
__remove_wait_queue(&ctx->wqh, wait);
@@ -188,6 +212,9 @@ ssize_t eventfd_ctx_read(struct eventfd_ctx *ctx, int no_wait, __u64 *cnt)
ssize_t res;
DECLARE_WAITQUEUE(wait, current);
+ /* This function should never be used with eventfd in the mask mode. */
+ BUG_ON(ctx->flags & EFD_MASK);
+
spin_lock_irq(&ctx->wqh.lock);
*cnt = 0;
res = -EAGAIN;
@@ -227,63 +254,92 @@ static ssize_t eventfd_read(struct file *file, char __user *buf, size_t count,
loff_t *ppos)
{
struct eventfd_ctx *ctx = file->private_data;
- ssize_t res;
- __u64 cnt;
- if (count < sizeof(cnt))
- return -EINVAL;
- res = eventfd_ctx_read(ctx, file->f_flags & O_NONBLOCK, &cnt);
- if (res < 0)
- return res;
-
- return put_user(cnt, (__u64 __user *) buf) ? -EFAULT : sizeof(cnt);
+ if (ctx->flags & EFD_MASK) {
+ struct efd_mask mask;
+ if (count < sizeof(mask))
+ return -EINVAL;
+ spin_lock_irq(&ctx->wqh.lock);
+ mask = ctx->mask;
+ spin_unlock_irq(&ctx->wqh.lock);
+ if (copy_to_user(buf, &mask, sizeof(mask)))
+ return -EFAULT;
+ return sizeof(mask);
+ } else {
+ ssize_t res;
+ __u64 cnt;
+ if (count < sizeof(cnt))
+ return -EINVAL;
+ res = eventfd_ctx_read(ctx, file->f_flags & O_NONBLOCK, &cnt);
+ if (res < 0)
+ return res;
+ return put_user(cnt, (__u64 __user *) buf) ?
+ -EFAULT : sizeof(cnt);
+ }
}
static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t count,
loff_t *ppos)
{
struct eventfd_ctx *ctx = file->private_data;
- ssize_t res;
- __u64 ucnt;
- DECLARE_WAITQUEUE(wait, current);
- if (count < sizeof(ucnt))
- return -EINVAL;
- if (copy_from_user(&ucnt, buf, sizeof(ucnt)))
- return -EFAULT;
- if (ucnt == ULLONG_MAX)
- return -EINVAL;
- spin_lock_irq(&ctx->wqh.lock);
- res = -EAGAIN;
- if (ULLONG_MAX - ctx->count > ucnt)
- res = sizeof(ucnt);
- else if (!(file->f_flags & O_NONBLOCK)) {
- __add_wait_queue(&ctx->wqh, &wait);
- for (res = 0;;) {
- set_current_state(TASK_INTERRUPTIBLE);
- if (ULLONG_MAX - ctx->count > ucnt) {
- res = sizeof(ucnt);
- break;
- }
- if (signal_pending(current)) {
- res = -ERESTARTSYS;
- break;
+ if (ctx->flags & EFD_MASK) {
+ struct efd_mask mask;
+ if (count < sizeof(mask))
+ return -EINVAL;
+ if (copy_from_user(&mask, buf, sizeof(mask)))
+ return -EFAULT;
+ if (mask.events & ~EFD_MASK_VALID_EVENTS)
+ return -EINVAL;
+ spin_lock_irq(&ctx->wqh.lock);
+ memcpy(&ctx->mask, &mask, sizeof(ctx->mask));
+ if (waitqueue_active(&ctx->wqh))
+ wake_up_locked_poll(&ctx->wqh,
+ (unsigned long)ctx->mask.events);
+ spin_unlock_irq(&ctx->wqh.lock);
+ return sizeof(ctx->mask);
+ } else {
+ ssize_t res;
+ __u64 ucnt;
+ DECLARE_WAITQUEUE(wait, current);
+ if (count < sizeof(ucnt))
+ return -EINVAL;
+ if (copy_from_user(&ucnt, buf, sizeof(ucnt)))
+ return -EFAULT;
+ if (ucnt == ULLONG_MAX)
+ return -EINVAL;
+ spin_lock_irq(&ctx->wqh.lock);
+ res = -EAGAIN;
+ if (ULLONG_MAX - ctx->count > ucnt)
+ res = sizeof(ucnt);
+ else if (!(file->f_flags & O_NONBLOCK)) {
+ __add_wait_queue(&ctx->wqh, &wait);
+ for (res = 0;;) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (ULLONG_MAX - ctx->count > ucnt) {
+ res = sizeof(ucnt);
+ break;
+ }
+ if (signal_pending(current)) {
+ res = -ERESTARTSYS;
+ break;
+ }
+ spin_unlock_irq(&ctx->wqh.lock);
+ schedule();
+ spin_lock_irq(&ctx->wqh.lock);
}
- spin_unlock_irq(&ctx->wqh.lock);
- schedule();
- spin_lock_irq(&ctx->wqh.lock);
+ __remove_wait_queue(&ctx->wqh, &wait);
+ __set_current_state(TASK_RUNNING);
}
- __remove_wait_queue(&ctx->wqh, &wait);
- __set_current_state(TASK_RUNNING);
- }
- if (likely(res > 0)) {
- ctx->count += ucnt;
- if (waitqueue_active(&ctx->wqh))
- wake_up_locked_poll(&ctx->wqh, POLLIN);
- }
- spin_unlock_irq(&ctx->wqh.lock);
+ if (likely(res > 0)) {
+ ctx->count += ucnt;
+ if (waitqueue_active(&ctx->wqh))
+ wake_up_locked_poll(&ctx->wqh, POLLIN);
+ }
+ spin_unlock_irq(&ctx->wqh.lock);
- return res;
+ return res;
+ }
}
#ifdef CONFIG_PROC_FS
@@ -293,8 +349,13 @@ static int eventfd_show_fdinfo(struct seq_file *m, struct file *f)
int ret;
spin_lock_irq(&ctx->wqh.lock);
- ret = seq_printf(m, "eventfd-count: %16llx\n",
- (unsigned long long)ctx->count);
+ if (ctx->flags & EFD_MASK) {
+ ret = seq_printf(m, "eventfd-mask: %x\n",
+ (unsigned)ctx->mask.events);
+ } else {
+ ret = seq_printf(m, "eventfd-count: %16llx\n",
+ (unsigned long long)ctx->count);
+ }
spin_unlock_irq(&ctx->wqh.lock);
return ret;
@@ -412,7 +473,12 @@ struct file *eventfd_file_create(unsigned int count, int flags)
kref_init(&ctx->kref);
init_waitqueue_head(&ctx->wqh);
- ctx->count = count;
+ if (flags & EFD_MASK) {
+ ctx->mask.events = 0;
+ ctx->mask.data = 0;
+ } else {
+ ctx->count = count;
+ }
ctx->flags = flags;
file = anon_inode_getfile("[eventfd]", &eventfd_fops, ctx,
diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index 3c3ef19..218aba6 100644
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -8,24 +8,11 @@
#ifndef _LINUX_EVENTFD_H
#define _LINUX_EVENTFD_H
-#include <linux/fcntl.h>
+#include <uapi/linux/eventfd.h>
+
#include <linux/file.h>
#include <linux/wait.h>
-/*
- * CAREFUL: Check include/asm-generic/fcntl.h when defining
- * new flags, since they might collide with O_* ones. We want
- * to re-use O_* flags that couldn't possibly have a meaning
- * from eventfd, in order to leave a free define-space for
- * shared O_* flags.
- */
-#define EFD_SEMAPHORE (1 << 0)
-#define EFD_CLOEXEC O_CLOEXEC
-#define EFD_NONBLOCK O_NONBLOCK
-
-#define EFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK)
-#define EFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS | EFD_SEMAPHORE)
-
#ifdef CONFIG_EVENTFD
struct file *eventfd_file_create(unsigned int count, int flags);
diff --git a/include/uapi/linux/eventfd.h b/include/uapi/linux/eventfd.h
new file mode 100644
index 0000000..03057a5
--- /dev/null
+++ b/include/uapi/linux/eventfd.h
@@ -0,0 +1,40 @@
+/*
+ * Copyright (C) 2013 Martin Sustrik <sustrik@250bpm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _UAPI_LINUX_EVENTFD_H
+#define _UAPI_LINUX_EVENTFD_H
+
+/* For O_CLOEXEC */
+#include <linux/fcntl.h>
+#include <linux/types.h>
+
+/*
+ * CAREFUL: Check include/asm-generic/fcntl.h when defining
+ * new flags, since they might collide with O_* ones. We want
+ * to re-use O_* flags that couldn't possibly have a meaning
+ * from eventfd, in order to leave a free define-space for
+ * shared O_* flags.
+ */
+
+/* Provide semaphore-like semantics for reads from the eventfd. */
+#define EFD_SEMAPHORE (1 << 0)
+/* Provide event mask semantics for the eventfd. */
+#define EFD_MASK (1 << 1)
+/* Set the close-on-exec (FD_CLOEXEC) flag on the eventfd. */
+#define EFD_CLOEXEC O_CLOEXEC
+/* Create the eventfd in non-blocking mode. */
+#define EFD_NONBLOCK O_NONBLOCK
+
+/* Structure to read/write to eventfd in EFD_MASK mode. */
+struct efd_mask {
+ __u32 events;
+ __u64 data;
+} __packed;
+
+#endif /* _UAPI_LINUX_EVENTFD_H */
--
1.7.4.1
^ permalink raw reply related
* [PATCH net-next 1/4] net: proc: change proc_net_fops_create to proc_create
From: Gao feng @ 2013-02-18 11:34 UTC (permalink / raw)
To: netdev; +Cc: ebiederm, davem, containers, Gao feng
Right now, some modules such as bonding use proc_create
to create proc entries under /proc/net/, and other modules
such as ipv4 use proc_net_fops_create.
It looks a little chaos.this patch changes all of
proc_net_fops_create to proc_create. we can remove
proc_net_fops_create after this patch.
Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
---
drivers/connector/connector.c | 2 +-
drivers/net/hamradio/bpqether.c | 3 ++-
drivers/net/hamradio/scc.c | 2 +-
drivers/net/hamradio/yam.c | 2 +-
drivers/net/ppp/pppoe.c | 2 +-
net/ax25/af_ax25.c | 7 ++++---
net/bluetooth/af_bluetooth.c | 2 +-
net/core/dev.c | 7 ++++---
net/core/dev_addr_lists.c | 2 +-
net/core/sock.c | 2 +-
net/dccp/probe.c | 2 +-
net/decnet/af_decnet.c | 2 +-
net/decnet/dn_dev.c | 2 +-
net/decnet/dn_neigh.c | 3 ++-
net/decnet/dn_route.c | 3 ++-
net/ipv4/arp.c | 2 +-
net/ipv4/fib_trie.c | 8 ++++----
net/ipv4/igmp.c | 5 +++--
net/ipv4/ipconfig.c | 2 +-
net/ipv4/ipmr.c | 4 ++--
net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c | 6 +++---
net/ipv4/ping.c | 2 +-
net/ipv4/proc.c | 7 ++++---
net/ipv4/raw.c | 2 +-
net/ipv4/route.c | 4 ++--
net/ipv4/tcp_probe.c | 2 +-
net/ipv6/addrconf.c | 2 +-
net/ipv6/anycast.c | 2 +-
net/ipv6/ip6_flowlabel.c | 4 ++--
net/ipv6/ip6mr.c | 4 ++--
net/ipv6/mcast.c | 6 +++---
net/ipv6/proc.c | 6 +++---
net/ipv6/raw.c | 2 +-
net/ipv6/route.c | 4 ++--
net/key/af_key.c | 2 +-
net/l2tp/l2tp_ppp.c | 3 ++-
net/netfilter/ipvs/ip_vs_app.c | 2 +-
net/netfilter/ipvs/ip_vs_conn.c | 4 ++--
net/netfilter/ipvs/ip_vs_ctl.c | 8 ++++----
net/netfilter/nf_conntrack_expect.c | 3 ++-
net/netfilter/nf_conntrack_standalone.c | 2 +-
net/netlink/af_netlink.c | 2 +-
net/netrom/af_netrom.c | 6 +++---
net/packet/af_packet.c | 2 +-
net/phonet/pn_dev.c | 4 ++--
net/rose/af_rose.c | 11 +++++++----
net/rxrpc/af_rxrpc.c | 5 +++--
net/sched/sch_api.c | 2 +-
net/sctp/probe.c | 4 ++--
net/unix/af_unix.c | 2 +-
net/wireless/wext-proc.c | 3 ++-
net/xfrm/xfrm_proc.c | 4 ++--
52 files changed, 100 insertions(+), 86 deletions(-)
diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index 7b69591..ed17a57 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -276,7 +276,7 @@ static int cn_init(void)
cn_already_initialized = 1;
- proc_net_fops_create(&init_net, "connector", S_IRUGO, &cn_file_ops);
+ proc_create("connector", S_IRUGO, init_net.proc_net, &cn_file_ops);
return 0;
}
diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c
index c2e5497..61f2884 100644
--- a/drivers/net/hamradio/bpqether.c
+++ b/drivers/net/hamradio/bpqether.c
@@ -586,7 +586,8 @@ static int bpq_device_event(struct notifier_block *this,unsigned long event, voi
static int __init bpq_init_driver(void)
{
#ifdef CONFIG_PROC_FS
- if (!proc_net_fops_create(&init_net, "bpqether", S_IRUGO, &bpq_info_fops)) {
+ if (!proc_create("bpqether", S_IRUGO, init_net.proc_net,
+ &bpq_info_fops)) {
printk(KERN_ERR
"bpq: cannot create /proc/net/bpqether entry.\n");
return -ENOENT;
diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c
index 1b4a47b..cab13f4 100644
--- a/drivers/net/hamradio/scc.c
+++ b/drivers/net/hamradio/scc.c
@@ -2118,7 +2118,7 @@ static int __init scc_init_driver (void)
}
rtnl_unlock();
- proc_net_fops_create(&init_net, "z8530drv", 0, &scc_net_seq_fops);
+ proc_create("z8530drv", 0, init_net.proc_net, &scc_net_seq_fops);
return 0;
}
diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c
index c6645f1..92847d2 100644
--- a/drivers/net/hamradio/yam.c
+++ b/drivers/net/hamradio/yam.c
@@ -1167,7 +1167,7 @@ static int __init yam_init_driver(void)
yam_timer.expires = jiffies + HZ / 100;
add_timer(&yam_timer);
- proc_net_fops_create(&init_net, "yam", S_IRUGO, &yam_info_fops);
+ proc_create("yam", S_IRUGO, init_net.proc_net, &yam_info_fops);
return 0;
error:
while (--i >= 0) {
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 20f31d0..d7fa96c 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -1134,7 +1134,7 @@ static __net_init int pppoe_init_net(struct net *net)
rwlock_init(&pn->hash_lock);
- pde = proc_net_fops_create(net, "pppoe", S_IRUGO, &pppoe_seq_fops);
+ pde = proc_create("pppoe", S_IRUGO, net->proc_net, &pppoe_seq_fops);
#ifdef CONFIG_PROC_FS
if (!pde)
return -ENOMEM;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 779095d..b6ccbea 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1992,9 +1992,10 @@ static int __init ax25_init(void)
dev_add_pack(&ax25_packet_type);
register_netdevice_notifier(&ax25_dev_notifier);
- proc_net_fops_create(&init_net, "ax25_route", S_IRUGO, &ax25_route_fops);
- proc_net_fops_create(&init_net, "ax25", S_IRUGO, &ax25_info_fops);
- proc_net_fops_create(&init_net, "ax25_calls", S_IRUGO, &ax25_uid_fops);
+ proc_create("ax25_route", S_IRUGO, init_net.proc_net,
+ &ax25_route_fops);
+ proc_create("ax25", S_IRUGO, init_net.proc_net, &ax25_info_fops);
+ proc_create("ax25_calls", S_IRUGO, init_net.proc_net, &ax25_uid_fops);
out:
return rc;
}
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 5355df6..8412b63 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -641,7 +641,7 @@ int bt_procfs_init(struct module* module, struct net *net, const char *name,
sk_list->fops.llseek = seq_lseek;
sk_list->fops.release = seq_release_private;
- pde = proc_net_fops_create(net, name, 0, &sk_list->fops);
+ pde = proc_create(name, 0, net->proc_net, &sk_list->fops);
if (!pde)
return -ENOMEM;
diff --git a/net/core/dev.c b/net/core/dev.c
index 6ad3789..73e0565 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4722,11 +4722,12 @@ static int __net_init dev_proc_net_init(struct net *net)
{
int rc = -ENOMEM;
- if (!proc_net_fops_create(net, "dev", S_IRUGO, &dev_seq_fops))
+ if (!proc_create("dev", S_IRUGO, net->proc_net, &dev_seq_fops))
goto out;
- if (!proc_net_fops_create(net, "softnet_stat", S_IRUGO, &softnet_seq_fops))
+ if (!proc_create("softnet_stat", S_IRUGO, net->proc_net,
+ &softnet_seq_fops))
goto out_dev;
- if (!proc_net_fops_create(net, "ptype", S_IRUGO, &ptype_seq_fops))
+ if (!proc_create("ptype", S_IRUGO, net->proc_net, &ptype_seq_fops))
goto out_softnet;
if (wext_proc_init(net))
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index b079c7b..7c62ec4 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -780,7 +780,7 @@ static const struct file_operations dev_mc_seq_fops = {
static int __net_init dev_mc_net_init(struct net *net)
{
- if (!proc_net_fops_create(net, "dev_mcast", 0, &dev_mc_seq_fops))
+ if (!proc_create("dev_mcast", 0, net->proc_net, &dev_mc_seq_fops))
return -ENOMEM;
return 0;
}
diff --git a/net/core/sock.c b/net/core/sock.c
index f1e14e2..b4d562ef 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2836,7 +2836,7 @@ static const struct file_operations proto_seq_fops = {
static __net_init int proto_init_net(struct net *net)
{
- if (!proc_net_fops_create(net, "protocols", S_IRUGO, &proto_seq_fops))
+ if (!proc_create("protocols", S_IRUGO, net->proc_net, &proto_seq_fops))
return -ENOMEM;
return 0;
diff --git a/net/dccp/probe.c b/net/dccp/probe.c
index 0a8d6eb..d183589 100644
--- a/net/dccp/probe.c
+++ b/net/dccp/probe.c
@@ -171,7 +171,7 @@ static __init int dccpprobe_init(void)
spin_lock_init(&dccpw.lock);
if (kfifo_alloc(&dccpw.fifo, bufsize, GFP_KERNEL))
return ret;
- if (!proc_net_fops_create(&init_net, procname, S_IRUSR, &dccpprobe_fops))
+ if (!proc_create(procname, S_IRUSR, init_net.proc_net, &dccpprobe_fops))
goto err0;
ret = setup_jprobe();
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 64d9843..f916013 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -2384,7 +2384,7 @@ static int __init decnet_init(void)
dev_add_pack(&dn_dix_packet_type);
register_netdevice_notifier(&dn_dev_notifier);
- proc_net_fops_create(&init_net, "decnet", S_IRUGO, &dn_socket_seq_fops);
+ proc_create("decnet", S_IRUGO, init_net.proc_net, &dn_socket_seq_fops);
dn_register_sysctl();
out:
return rc;
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index e47ba9f..a04894a 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -1412,7 +1412,7 @@ void __init dn_dev_init(void)
rtnl_register(PF_DECnet, RTM_DELADDR, dn_nl_deladdr, NULL, NULL);
rtnl_register(PF_DECnet, RTM_GETADDR, NULL, dn_nl_dump_ifaddr, NULL);
- proc_net_fops_create(&init_net, "decnet_dev", S_IRUGO, &dn_dev_seq_fops);
+ proc_create("decnet_dev", S_IRUGO, init_net.proc_net, &dn_dev_seq_fops);
#ifdef CONFIG_SYSCTL
{
diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c
index 856636a..f3408f3 100644
--- a/net/decnet/dn_neigh.c
+++ b/net/decnet/dn_neigh.c
@@ -590,7 +590,8 @@ static const struct file_operations dn_neigh_seq_fops = {
void __init dn_neigh_init(void)
{
neigh_table_init(&dn_neigh_table);
- proc_net_fops_create(&init_net, "decnet_neigh", S_IRUGO, &dn_neigh_seq_fops);
+ proc_create("decnet_neigh", S_IRUGO, init_net.proc_net,
+ &dn_neigh_seq_fops);
}
void __exit dn_neigh_cleanup(void)
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 1550028..8afb257 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1901,7 +1901,8 @@ void __init dn_route_init(void)
dn_dst_ops.gc_thresh = (dn_rt_hash_mask + 1);
- proc_net_fops_create(&init_net, "decnet_cache", S_IRUGO, &dn_rt_cache_seq_fops);
+ proc_create("decnet_cache", S_IRUGO, init_net.proc_net,
+ &dn_rt_cache_seq_fops);
#ifdef CONFIG_DECNET_ROUTER
rtnl_register(PF_DECnet, RTM_GETROUTE, dn_cache_getroute,
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index ded146b..b04c114 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1405,7 +1405,7 @@ static const struct file_operations arp_seq_fops = {
static int __net_init arp_net_init(struct net *net)
{
- if (!proc_net_fops_create(net, "arp", S_IRUGO, &arp_seq_fops))
+ if (!proc_create("arp", S_IRUGO, net->proc_net, &arp_seq_fops))
return -ENOMEM;
return 0;
}
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 31d771c..67c1d4b 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2607,14 +2607,14 @@ static const struct file_operations fib_route_fops = {
int __net_init fib_proc_init(struct net *net)
{
- if (!proc_net_fops_create(net, "fib_trie", S_IRUGO, &fib_trie_fops))
+ if (!proc_create("fib_trie", S_IRUGO, net->proc_net, &fib_trie_fops))
goto out1;
- if (!proc_net_fops_create(net, "fib_triestat", S_IRUGO,
- &fib_triestat_fops))
+ if (!proc_create("fib_triestat", S_IRUGO, net->proc_net,
+ &fib_triestat_fops))
goto out2;
- if (!proc_net_fops_create(net, "route", S_IRUGO, &fib_route_fops))
+ if (!proc_create("route", S_IRUGO, net->proc_net, &fib_route_fops))
goto out3;
return 0;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 736ab70..be85628 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2646,10 +2646,11 @@ static int __net_init igmp_net_init(struct net *net)
{
struct proc_dir_entry *pde;
- pde = proc_net_fops_create(net, "igmp", S_IRUGO, &igmp_mc_seq_fops);
+ pde = proc_create("igmp", S_IRUGO, net->proc_net, &igmp_mc_seq_fops);
if (!pde)
goto out_igmp;
- pde = proc_net_fops_create(net, "mcfilter", S_IRUGO, &igmp_mcf_seq_fops);
+ pde = proc_create("mcfilter", S_IRUGO, net->proc_net,
+ &igmp_mcf_seq_fops);
if (!pde)
goto out_mcfilter;
return 0;
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index a2e50ae..98cbc68 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1394,7 +1394,7 @@ static int __init ip_auto_config(void)
unsigned int i;
#ifdef CONFIG_PROC_FS
- proc_net_fops_create(&init_net, "pnp", S_IRUGO, &pnp_seq_fops);
+ proc_create("pnp", S_IRUGO, init_net.proc_net, &pnp_seq_fops);
#endif /* CONFIG_PROC_FS */
if (!ic_enable)
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 7085b9b..160a8b8 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2703,9 +2703,9 @@ static int __net_init ipmr_net_init(struct net *net)
#ifdef CONFIG_PROC_FS
err = -ENOMEM;
- if (!proc_net_fops_create(net, "ip_mr_vif", 0, &ipmr_vif_fops))
+ if (!proc_create("ip_mr_vif", 0, net->proc_net, &ipmr_vif_fops))
goto proc_vif_fail;
- if (!proc_net_fops_create(net, "ip_mr_cache", 0, &ipmr_mfc_fops))
+ if (!proc_create("ip_mr_cache", 0, net->proc_net, &ipmr_mfc_fops))
goto proc_cache_fail;
#endif
return 0;
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index 9682b36..48bc681 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -417,12 +417,12 @@ static int __net_init ip_conntrack_net_init(struct net *net)
{
struct proc_dir_entry *proc, *proc_exp, *proc_stat;
- proc = proc_net_fops_create(net, "ip_conntrack", 0440, &ct_file_ops);
+ proc = proc_create("ip_conntrack", 0440, net->proc_net, &ct_file_ops);
if (!proc)
goto err1;
- proc_exp = proc_net_fops_create(net, "ip_conntrack_expect", 0440,
- &ip_exp_file_ops);
+ proc_exp = proc_create("ip_conntrack_expect", 0440, net->proc_net,
+ &ip_exp_file_ops);
if (!proc_exp)
goto err2;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 6f9c072..fc62a13 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -889,7 +889,7 @@ static int ping_proc_register(struct net *net)
struct proc_dir_entry *p;
int rc = 0;
- p = proc_net_fops_create(net, "icmp", S_IRUGO, &ping_seq_fops);
+ p = proc_create("icmp", S_IRUGO, net->proc_net, &ping_seq_fops);
if (!p)
rc = -ENOMEM;
return rc;
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 8de53e1..954bcd4 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -471,11 +471,12 @@ static const struct file_operations netstat_seq_fops = {
static __net_init int ip_proc_init_net(struct net *net)
{
- if (!proc_net_fops_create(net, "sockstat", S_IRUGO, &sockstat_seq_fops))
+ if (!proc_create("sockstat", S_IRUGO, net->proc_net,
+ &sockstat_seq_fops))
goto out_sockstat;
- if (!proc_net_fops_create(net, "netstat", S_IRUGO, &netstat_seq_fops))
+ if (!proc_create("netstat", S_IRUGO, net->proc_net, &netstat_seq_fops))
goto out_netstat;
- if (!proc_net_fops_create(net, "snmp", S_IRUGO, &snmp_seq_fops))
+ if (!proc_create("snmp", S_IRUGO, net->proc_net, &snmp_seq_fops))
goto out_snmp;
return 0;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 6f08991..5043a7d 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -1050,7 +1050,7 @@ static const struct file_operations raw_seq_fops = {
static __net_init int raw_init_net(struct net *net)
{
- if (!proc_net_fops_create(net, "raw", S_IRUGO, &raw_seq_fops))
+ if (!proc_create("raw", S_IRUGO, net->proc_net, &raw_seq_fops))
return -ENOMEM;
return 0;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a0fcc47..3bdd1b1 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -384,8 +384,8 @@ static int __net_init ip_rt_do_proc_init(struct net *net)
{
struct proc_dir_entry *pde;
- pde = proc_net_fops_create(net, "rt_cache", S_IRUGO,
- &rt_cache_seq_fops);
+ pde = proc_create("rt_cache", S_IRUGO, net->proc_net,
+ &rt_cache_seq_fops);
if (!pde)
goto err1;
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index 4526fe6..1e3a1fb 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -234,7 +234,7 @@ static __init int tcpprobe_init(void)
if (!tcp_probe.log)
goto err0;
- if (!proc_net_fops_create(&init_net, procname, S_IRUSR, &tcpprobe_fops))
+ if (!proc_create(procname, S_IRUSR, init_net.proc_net, &tcpprobe_fops))
goto err0;
ret = register_jprobe(&tcp_jprobe);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 86c235d..bad7108 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3325,7 +3325,7 @@ static const struct file_operations if6_fops = {
static int __net_init if6_proc_net_init(struct net *net)
{
- if (!proc_net_fops_create(net, "if_inet6", S_IRUGO, &if6_fops))
+ if (!proc_create("if_inet6", S_IRUGO, net->proc_net, &if6_fops))
return -ENOMEM;
return 0;
}
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 921b8b3..5a8c009 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -509,7 +509,7 @@ static const struct file_operations ac6_seq_fops = {
int __net_init ac6_proc_init(struct net *net)
{
- if (!proc_net_fops_create(net, "anycast6", S_IRUGO, &ac6_seq_fops))
+ if (!proc_create("anycast6", S_IRUGO, net->proc_net, &ac6_seq_fops))
return -ENOMEM;
return 0;
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index a7da2f4..900d79e 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -806,8 +806,8 @@ static const struct file_operations ip6fl_seq_fops = {
static int __net_init ip6_flowlabel_proc_init(struct net *net)
{
- if (!proc_net_fops_create(net, "ip6_flowlabel",
- S_IRUGO, &ip6fl_seq_fops))
+ if (!proc_create("ip6_flowlabel", S_IRUGO, net->proc_net,
+ &ip6fl_seq_fops))
return -ENOMEM;
return 0;
}
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 351ce98..fdfd96d 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1359,9 +1359,9 @@ static int __net_init ip6mr_net_init(struct net *net)
#ifdef CONFIG_PROC_FS
err = -ENOMEM;
- if (!proc_net_fops_create(net, "ip6_mr_vif", 0, &ip6mr_vif_fops))
+ if (!proc_create("ip6_mr_vif", 0, net->proc_net, &ip6mr_vif_fops))
goto proc_vif_fail;
- if (!proc_net_fops_create(net, "ip6_mr_cache", 0, &ip6mr_mfc_fops))
+ if (!proc_create("ip6_mr_cache", 0, net->proc_net, &ip6mr_mfc_fops))
goto proc_cache_fail;
#endif
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 3a2849f..de7d4b9 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2599,10 +2599,10 @@ static int __net_init igmp6_proc_init(struct net *net)
int err;
err = -ENOMEM;
- if (!proc_net_fops_create(net, "igmp6", S_IRUGO, &igmp6_mc_seq_fops))
+ if (!proc_create("igmp6", S_IRUGO, net->proc_net, &igmp6_mc_seq_fops))
goto out;
- if (!proc_net_fops_create(net, "mcfilter6", S_IRUGO,
- &igmp6_mcf_seq_fops))
+ if (!proc_create("mcfilter6", S_IRUGO, net->proc_net,
+ &igmp6_mcf_seq_fops))
goto out_proc_net_igmp6;
err = 0;
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 745a320..cf8901d 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -295,11 +295,11 @@ int snmp6_unregister_dev(struct inet6_dev *idev)
static int __net_init ipv6_proc_init_net(struct net *net)
{
- if (!proc_net_fops_create(net, "sockstat6", S_IRUGO,
- &sockstat6_seq_fops))
+ if (!proc_create("sockstat6", S_IRUGO, net->proc_net,
+ &sockstat6_seq_fops))
return -ENOMEM;
- if (!proc_net_fops_create(net, "snmp6", S_IRUGO, &snmp6_seq_fops))
+ if (!proc_create("snmp6", S_IRUGO, net->proc_net, &snmp6_seq_fops))
goto proc_snmp6_fail;
net->mib.proc_net_devsnmp6 = proc_mkdir("dev_snmp6", net->proc_net);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 70fa814..ff42fb3 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1292,7 +1292,7 @@ static const struct file_operations raw6_seq_fops = {
static int __net_init raw6_init_net(struct net *net)
{
- if (!proc_net_fops_create(net, "raw6", S_IRUGO, &raw6_seq_fops))
+ if (!proc_create("raw6", S_IRUGO, net->proc_net, &raw6_seq_fops))
return -ENOMEM;
return 0;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index f3328bc..e1228d8 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2995,8 +2995,8 @@ static void __net_exit ip6_route_net_exit(struct net *net)
static int __net_init ip6_route_net_init_late(struct net *net)
{
#ifdef CONFIG_PROC_FS
- proc_net_fops_create(net, "ipv6_route", 0, &ipv6_route_proc_fops);
- proc_net_fops_create(net, "rt6_stats", S_IRUGO, &rt6_stats_seq_fops);
+ proc_create("ipv6_route", 0, net->proc_net, &ipv6_route_proc_fops);
+ proc_create("rt6_stats", S_IRUGO, net->proc_net, &rt6_stats_seq_fops);
#endif
return 0;
}
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 7b3ba32..021a429 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3740,7 +3740,7 @@ static int __net_init pfkey_init_proc(struct net *net)
{
struct proc_dir_entry *e;
- e = proc_net_fops_create(net, "pfkey", 0, &pfkey_proc_ops);
+ e = proc_create("pfkey", 0, net->proc_net, &pfkey_proc_ops);
if (e == NULL)
return -ENOMEM;
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 716605c..3ca270b 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1783,7 +1783,8 @@ static __net_init int pppol2tp_init_net(struct net *net)
struct proc_dir_entry *pde;
int err = 0;
- pde = proc_net_fops_create(net, "pppol2tp", S_IRUGO, &pppol2tp_proc_fops);
+ pde = proc_create("pppol2tp", S_IRUGO, net->proc_net,
+ &pppol2tp_proc_fops);
if (!pde) {
err = -ENOMEM;
goto out;
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index 9713e6e..1db8a25 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -605,7 +605,7 @@ int __net_init ip_vs_app_net_init(struct net *net)
struct netns_ipvs *ipvs = net_ipvs(net);
INIT_LIST_HEAD(&ipvs->app_list);
- proc_net_fops_create(net, "ip_vs_app", 0, &ip_vs_app_fops);
+ proc_create("ip_vs_app", 0, net->proc_net, &ip_vs_app_fops);
return 0;
}
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 68e368a..91ae112 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -1291,8 +1291,8 @@ int __net_init ip_vs_conn_net_init(struct net *net)
atomic_set(&ipvs->conn_count, 0);
- proc_net_fops_create(net, "ip_vs_conn", 0, &ip_vs_conn_fops);
- proc_net_fops_create(net, "ip_vs_conn_sync", 0, &ip_vs_conn_sync_fops);
+ proc_create("ip_vs_conn", 0, net->proc_net, &ip_vs_conn_fops);
+ proc_create("ip_vs_conn_sync", 0, net->proc_net, &ip_vs_conn_sync_fops);
return 0;
}
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index ec664cb..7d69181 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3800,10 +3800,10 @@ int __net_init ip_vs_control_net_init(struct net *net)
spin_lock_init(&ipvs->tot_stats.lock);
- proc_net_fops_create(net, "ip_vs", 0, &ip_vs_info_fops);
- proc_net_fops_create(net, "ip_vs_stats", 0, &ip_vs_stats_fops);
- proc_net_fops_create(net, "ip_vs_stats_percpu", 0,
- &ip_vs_stats_percpu_fops);
+ proc_create("ip_vs", 0, net->proc_net, &ip_vs_info_fops);
+ proc_create("ip_vs_stats", 0, net->proc_net, &ip_vs_stats_fops);
+ proc_create("ip_vs_stats_percpu", 0, net->proc_net,
+ &ip_vs_stats_percpu_fops);
if (ip_vs_control_net_init_sysctl(net))
goto err;
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index bdd3418..4c15f8d 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -571,7 +571,8 @@ static int exp_proc_init(struct net *net)
#ifdef CONFIG_NF_CONNTRACK_PROCFS
struct proc_dir_entry *proc;
- proc = proc_net_fops_create(net, "nf_conntrack_expect", 0440, &exp_file_ops);
+ proc = proc_create("nf_conntrack_expect", 0440, net->proc_net,
+ &exp_file_ops);
if (!proc)
return -ENOMEM;
#endif /* CONFIG_NF_CONNTRACK_PROCFS */
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 7936bf7..bee9aec 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -366,7 +366,7 @@ static int nf_conntrack_standalone_init_proc(struct net *net)
{
struct proc_dir_entry *pde;
- pde = proc_net_fops_create(net, "nf_conntrack", 0440, &ct_file_ops);
+ pde = proc_create("nf_conntrack", 0440, net->proc_net, &ct_file_ops);
if (!pde)
goto out_nf_conntrack;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 74827e3..50084c4 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2145,7 +2145,7 @@ static const struct net_proto_family netlink_family_ops = {
static int __net_init netlink_net_init(struct net *net)
{
#ifdef CONFIG_PROC_FS
- if (!proc_net_fops_create(net, "netlink", 0, &netlink_seq_fops))
+ if (!proc_create("netlink", 0, net->proc_net, &netlink_seq_fops))
return -ENOMEM;
#endif
return 0;
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 7261eb8..71b8613 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1452,9 +1452,9 @@ static int __init nr_proto_init(void)
nr_loopback_init();
- proc_net_fops_create(&init_net, "nr", S_IRUGO, &nr_info_fops);
- proc_net_fops_create(&init_net, "nr_neigh", S_IRUGO, &nr_neigh_fops);
- proc_net_fops_create(&init_net, "nr_nodes", S_IRUGO, &nr_nodes_fops);
+ proc_create("nr", S_IRUGO, init_net.proc_net, &nr_info_fops);
+ proc_create("nr_neigh", S_IRUGO, init_net.proc_net, &nr_neigh_fops);
+ proc_create("nr_nodes", S_IRUGO, init_net.proc_net, &nr_nodes_fops);
out:
return rc;
fail:
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index c111bd0..b7b2d56 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3828,7 +3828,7 @@ static int __net_init packet_net_init(struct net *net)
mutex_init(&net->packet.sklist_lock);
INIT_HLIST_HEAD(&net->packet.sklist);
- if (!proc_net_fops_create(net, "packet", 0, &packet_seq_fops))
+ if (!proc_create("packet", 0, net->proc_net, &packet_seq_fops))
return -ENOMEM;
return 0;
diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c
index 5bf6341..0e527c9 100644
--- a/net/phonet/pn_dev.c
+++ b/net/phonet/pn_dev.c
@@ -320,7 +320,7 @@ static int __net_init phonet_init_net(struct net *net)
{
struct phonet_net *pnn = phonet_pernet(net);
- if (!proc_net_fops_create(net, "phonet", 0, &pn_sock_seq_fops))
+ if (!proc_create("phonet", 0, net->proc_net, &pn_sock_seq_fops))
return -ENOMEM;
INIT_LIST_HEAD(&pnn->pndevs.list);
@@ -348,7 +348,7 @@ int __init phonet_device_init(void)
if (err)
return err;
- proc_net_fops_create(&init_net, "pnresource", 0, &pn_res_seq_fops);
+ proc_create("pnresource", 0, init_net.proc_net, &pn_res_seq_fops);
register_netdevice_notifier(&phonet_device_notifier);
err = phonet_netlink_register();
if (err)
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index c4719ce..5fd8aac 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1575,10 +1575,13 @@ static int __init rose_proto_init(void)
rose_add_loopback_neigh();
- proc_net_fops_create(&init_net, "rose", S_IRUGO, &rose_info_fops);
- proc_net_fops_create(&init_net, "rose_neigh", S_IRUGO, &rose_neigh_fops);
- proc_net_fops_create(&init_net, "rose_nodes", S_IRUGO, &rose_nodes_fops);
- proc_net_fops_create(&init_net, "rose_routes", S_IRUGO, &rose_routes_fops);
+ proc_create("rose", S_IRUGO, init_net.proc_net, &rose_info_fops);
+ proc_create("rose_neigh", S_IRUGO, init_net.proc_net,
+ &rose_neigh_fops);
+ proc_create("rose_nodes", S_IRUGO, init_net.proc_net,
+ &rose_nodes_fops);
+ proc_create("rose_routes", S_IRUGO, init_net.proc_net,
+ &rose_routes_fops);
out:
return rc;
fail:
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 5b0fd29..59c7c7d 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -839,8 +839,9 @@ static int __init af_rxrpc_init(void)
}
#ifdef CONFIG_PROC_FS
- proc_net_fops_create(&init_net, "rxrpc_calls", 0, &rxrpc_call_seq_fops);
- proc_net_fops_create(&init_net, "rxrpc_conns", 0, &rxrpc_connection_seq_fops);
+ proc_create("rxrpc_calls", 0, init_net.proc_net, &rxrpc_call_seq_fops);
+ proc_create("rxrpc_conns", 0, init_net.proc_net,
+ &rxrpc_connection_seq_fops);
#endif
return 0;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index fe1ba54..d8cf7d3 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1768,7 +1768,7 @@ static int __net_init psched_net_init(struct net *net)
{
struct proc_dir_entry *e;
- e = proc_net_fops_create(net, "psched", 0, &psched_fops);
+ e = proc_create("psched", 0, net->proc_net, &psched_fops);
if (e == NULL)
return -ENOMEM;
diff --git a/net/sctp/probe.c b/net/sctp/probe.c
index 261b7b9..dd507f5 100644
--- a/net/sctp/probe.c
+++ b/net/sctp/probe.c
@@ -195,8 +195,8 @@ static __init int sctpprobe_init(void)
if (kfifo_alloc(&sctpw.fifo, bufsize, GFP_KERNEL))
return ret;
- if (!proc_net_fops_create(&init_net, procname, S_IRUSR,
- &sctpprobe_fops))
+ if (!proc_create(procname, S_IRUSR, init_net.proc_net,
+ &sctpprobe_fops))
goto free_kfifo;
ret = register_jprobe(&sctp_recv_probe);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 0c61236..0c479b6 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2402,7 +2402,7 @@ static int __net_init unix_net_init(struct net *net)
goto out;
#ifdef CONFIG_PROC_FS
- if (!proc_net_fops_create(net, "unix", 0, &unix_seq_fops)) {
+ if (!proc_create("unix", 0, net->proc_net, &unix_seq_fops)) {
unix_sysctl_unregister(net);
goto out;
}
diff --git a/net/wireless/wext-proc.c b/net/wireless/wext-proc.c
index 8bafa31..00fc5bb 100644
--- a/net/wireless/wext-proc.c
+++ b/net/wireless/wext-proc.c
@@ -143,7 +143,8 @@ static const struct file_operations wireless_seq_fops = {
int __net_init wext_proc_init(struct net *net)
{
/* Create /proc/net/wireless entry */
- if (!proc_net_fops_create(net, "wireless", S_IRUGO, &wireless_seq_fops))
+ if (!proc_create("wireless", S_IRUGO, net->proc_net,
+ &wireless_seq_fops))
return -ENOMEM;
return 0;
diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c
index 6039038..9abe14f 100644
--- a/net/xfrm/xfrm_proc.c
+++ b/net/xfrm/xfrm_proc.c
@@ -74,8 +74,8 @@ static const struct file_operations xfrm_statistics_seq_fops = {
int __net_init xfrm_proc_init(struct net *net)
{
- if (!proc_net_fops_create(net, "xfrm_stat", S_IRUGO,
- &xfrm_statistics_seq_fops))
+ if (!proc_create("xfrm_stat", S_IRUGO, net->proc_net,
+ &xfrm_statistics_seq_fops))
return -ENOMEM;
return 0;
}
--
1.7.11.7
^ permalink raw reply related
* [PATCH net-next 3/4] net: proc: change proc_net_remove to remove_proc_entry
From: Gao feng @ 2013-02-18 11:34 UTC (permalink / raw)
To: netdev; +Cc: ebiederm, davem, containers, Gao feng
In-Reply-To: <1361187297-2527-1-git-send-email-gaofeng@cn.fujitsu.com>
proc_net_remove is only used to remove proc entries
that under /proc/net,it's not a general function for
removing proc entries of netns. if we want to remove
some proc entries which under /proc/net/stat/, we still
need to call remove_proc_entry.
this patch use remove_proc_entry to replace proc_net_remove.
we can remove proc_net_remove after this patch.
Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
---
drivers/connector/connector.c | 2 +-
drivers/net/hamradio/bpqether.c | 2 +-
drivers/net/hamradio/scc.c | 2 +-
drivers/net/hamradio/yam.c | 2 +-
drivers/net/ppp/pppoe.c | 2 +-
net/8021q/vlanproc.c | 2 +-
net/atm/proc.c | 2 +-
net/ax25/af_ax25.c | 6 +++---
net/bluetooth/af_bluetooth.c | 2 +-
net/can/bcm.c | 2 +-
net/can/proc.c | 2 +-
net/core/dev.c | 12 ++++++------
net/core/dev_addr_lists.c | 2 +-
net/core/pktgen.c | 4 ++--
net/core/sock.c | 2 +-
net/dccp/probe.c | 4 ++--
net/decnet/af_decnet.c | 2 +-
net/decnet/dn_dev.c | 2 +-
net/decnet/dn_neigh.c | 2 +-
net/decnet/dn_route.c | 2 +-
net/ipv4/arp.c | 2 +-
net/ipv4/fib_trie.c | 10 +++++-----
net/ipv4/igmp.c | 6 +++---
net/ipv4/ipmr.c | 6 +++---
net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c | 8 ++++----
net/ipv4/ping.c | 2 +-
net/ipv4/proc.c | 10 +++++-----
net/ipv4/raw.c | 2 +-
net/ipv4/tcp_ipv4.c | 2 +-
net/ipv4/tcp_probe.c | 4 ++--
net/ipv4/udp.c | 2 +-
net/ipv6/addrconf.c | 2 +-
net/ipv6/anycast.c | 2 +-
net/ipv6/ip6_flowlabel.c | 2 +-
net/ipv6/ip6mr.c | 6 +++---
net/ipv6/mcast.c | 6 +++---
net/ipv6/proc.c | 10 +++++-----
net/ipv6/raw.c | 2 +-
net/ipv6/route.c | 4 ++--
net/key/af_key.c | 2 +-
net/l2tp/l2tp_ppp.c | 2 +-
net/netfilter/ipvs/ip_vs_app.c | 2 +-
net/netfilter/ipvs/ip_vs_conn.c | 4 ++--
net/netfilter/ipvs/ip_vs_ctl.c | 6 +++---
net/netfilter/nf_conntrack_expect.c | 2 +-
net/netfilter/nf_conntrack_standalone.c | 4 ++--
net/netfilter/x_tables.c | 10 +++++-----
net/netfilter/xt_hashlimit.c | 6 +++---
net/netfilter/xt_recent.c | 2 +-
net/netlink/af_netlink.c | 2 +-
net/netrom/af_netrom.c | 6 +++---
net/packet/af_packet.c | 2 +-
net/phonet/pn_dev.c | 4 ++--
net/rose/af_rose.c | 8 ++++----
net/rxrpc/af_rxrpc.c | 4 ++--
net/sched/sch_api.c | 2 +-
net/sctp/probe.c | 4 ++--
net/unix/af_unix.c | 2 +-
net/wireless/wext-proc.c | 2 +-
net/xfrm/xfrm_proc.c | 2 +-
60 files changed, 112 insertions(+), 112 deletions(-)
diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index ed17a57..f1b7e24 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -287,7 +287,7 @@ static void cn_fini(void)
cn_already_initialized = 0;
- proc_net_remove(&init_net, "connector");
+ remove_proc_entry("connector", init_net.proc_net);
cn_queue_free_dev(dev->cbdev);
netlink_kernel_release(dev->nls);
diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c
index 61f2884..02de6c8 100644
--- a/drivers/net/hamradio/bpqether.c
+++ b/drivers/net/hamradio/bpqether.c
@@ -611,7 +611,7 @@ static void __exit bpq_cleanup_driver(void)
unregister_netdevice_notifier(&bpq_dev_notifier);
- proc_net_remove(&init_net, "bpqether");
+ remove_proc_entry("bpqether", init_net.proc_net);
rtnl_lock();
while (!list_empty(&bpq_devices)) {
diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c
index cab13f4..bc1d521 100644
--- a/drivers/net/hamradio/scc.c
+++ b/drivers/net/hamradio/scc.c
@@ -2173,7 +2173,7 @@ static void __exit scc_cleanup_driver(void)
if (Vector_Latch)
release_region(Vector_Latch, 1);
- proc_net_remove(&init_net, "z8530drv");
+ remove_proc_entry("z8530drv", init_net.proc_net);
}
MODULE_AUTHOR("Joerg Reuter <jreuter@yaina.de>");
diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c
index 92847d2..4cf8f10 100644
--- a/drivers/net/hamradio/yam.c
+++ b/drivers/net/hamradio/yam.c
@@ -1199,7 +1199,7 @@ static void __exit yam_cleanup_driver(void)
kfree(p);
}
- proc_net_remove(&init_net, "yam");
+ remove_proc_entry("yam", init_net.proc_net);
}
/* --------------------------------------------------------------------- */
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index d7fa96c..bb07ba9 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -1145,7 +1145,7 @@ static __net_init int pppoe_init_net(struct net *net)
static __net_exit void pppoe_exit_net(struct net *net)
{
- proc_net_remove(net, "pppoe");
+ remove_proc_entry("pppoe", net->proc_net);
}
static struct pernet_operations pppoe_net_ops = {
diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c
index 4de77ea..dc526ec 100644
--- a/net/8021q/vlanproc.c
+++ b/net/8021q/vlanproc.c
@@ -131,7 +131,7 @@ void vlan_proc_cleanup(struct net *net)
remove_proc_entry(name_conf, vn->proc_vlan_dir);
if (vn->proc_vlan_dir)
- proc_net_remove(net, name_root);
+ remove_proc_entry(name_root, net->proc_net);
/* Dynamically added entries should be cleaned up as their vlan_device
* is removed, so we should not have to take care of it here...
diff --git a/net/atm/proc.c b/net/atm/proc.c
index 0d020de..b4e7534 100644
--- a/net/atm/proc.c
+++ b/net/atm/proc.c
@@ -460,7 +460,7 @@ static void atm_proc_dirs_remove(void)
if (e->dirent)
remove_proc_entry(e->name, atm_proc_root);
}
- proc_net_remove(&init_net, "atm");
+ remove_proc_entry("atm", init_net.proc_net);
}
int __init atm_proc_init(void)
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index b6ccbea..69a06c4 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -2009,9 +2009,9 @@ MODULE_ALIAS_NETPROTO(PF_AX25);
static void __exit ax25_exit(void)
{
- proc_net_remove(&init_net, "ax25_route");
- proc_net_remove(&init_net, "ax25");
- proc_net_remove(&init_net, "ax25_calls");
+ remove_proc_entry("ax25_route", init_net.proc_net);
+ remove_proc_entry("ax25", init_net.proc_net);
+ remove_proc_entry("ax25_calls", init_net.proc_net);
unregister_netdevice_notifier(&ax25_dev_notifier);
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 8412b63..d3ee69b 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -652,7 +652,7 @@ int bt_procfs_init(struct module* module, struct net *net, const char *name,
void bt_procfs_cleanup(struct net *net, const char *name)
{
- proc_net_remove(net, name);
+ remove_proc_entry(name, net->proc_net);
}
#else
int bt_procfs_init(struct module* module, struct net *net, const char *name,
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 28e12d1..5dcb200 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1633,7 +1633,7 @@ static void __exit bcm_module_exit(void)
can_proto_unregister(&bcm_can_proto);
if (proc_dir)
- proc_net_remove(&init_net, "can-bcm");
+ remove_proc_entry("can-bcm", init_net.proc_net);
}
module_init(bcm_module_init);
diff --git a/net/can/proc.c b/net/can/proc.c
index ae56690..4973358 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -531,5 +531,5 @@ void can_remove_proc(void)
can_remove_proc_readentry(CAN_PROC_RCVLIST_SFF);
if (can_dir)
- proc_net_remove(&init_net, "can");
+ remove_proc_entry("can", init_net.proc_net);
}
diff --git a/net/core/dev.c b/net/core/dev.c
index 73e0565..37d5b05 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4736,11 +4736,11 @@ static int __net_init dev_proc_net_init(struct net *net)
out:
return rc;
out_ptype:
- proc_net_remove(net, "ptype");
+ remove_proc_entry("ptype", net->proc_net);
out_softnet:
- proc_net_remove(net, "softnet_stat");
+ remove_proc_entry("softnet_stat", net->proc_net);
out_dev:
- proc_net_remove(net, "dev");
+ remove_proc_entry("dev", net->proc_net);
goto out;
}
@@ -4748,9 +4748,9 @@ static void __net_exit dev_proc_net_exit(struct net *net)
{
wext_proc_exit(net);
- proc_net_remove(net, "ptype");
- proc_net_remove(net, "softnet_stat");
- proc_net_remove(net, "dev");
+ remove_proc_entry("ptype", net->proc_net);
+ remove_proc_entry("softnet_stat", net->proc_net);
+ remove_proc_entry("dev", net->proc_net);
}
static struct pernet_operations __net_initdata dev_proc_ops = {
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 7c62ec4..8956252 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -787,7 +787,7 @@ static int __net_init dev_mc_net_init(struct net *net)
static void __net_exit dev_mc_net_exit(struct net *net)
{
- proc_net_remove(net, "dev_mcast");
+ remove_proc_entry("dev_mcast", net->proc_net);
}
static struct pernet_operations __net_initdata dev_mc_net_ops = {
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 2201e69..6048fc1 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3650,7 +3650,7 @@ static int __net_init pg_net_init(struct net *net)
remove_entry:
remove_proc_entry(PGCTRL, pn->proc_dir);
remove:
- proc_net_remove(pn->net, PG_PROC_DIR);
+ remove_proc_entry(PG_PROC_DIR, pn->net->proc_net);
return ret;
}
@@ -3676,7 +3676,7 @@ static void __net_exit pg_net_exit(struct net *net)
}
remove_proc_entry(PGCTRL, pn->proc_dir);
- proc_net_remove(pn->net, PG_PROC_DIR);
+ remove_proc_entry(PG_PROC_DIR, pn->net->proc_net);
}
static struct pernet_operations pg_net_ops = {
diff --git a/net/core/sock.c b/net/core/sock.c
index b4d562ef..fe96c5d 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2844,7 +2844,7 @@ static __net_init int proto_init_net(struct net *net)
static __net_exit void proto_exit_net(struct net *net)
{
- proc_net_remove(net, "protocols");
+ remove_proc_entry("protocols", net->proc_net);
}
diff --git a/net/dccp/probe.c b/net/dccp/probe.c
index d183589..4c6bdf9 100644
--- a/net/dccp/probe.c
+++ b/net/dccp/probe.c
@@ -181,7 +181,7 @@ static __init int dccpprobe_init(void)
pr_info("DCCP watch registered (port=%d)\n", port);
return 0;
err1:
- proc_net_remove(&init_net, procname);
+ remove_proc_entry(procname, init_net.proc_net);
err0:
kfifo_free(&dccpw.fifo);
return ret;
@@ -191,7 +191,7 @@ module_init(dccpprobe_init);
static __exit void dccpprobe_exit(void)
{
kfifo_free(&dccpw.fifo);
- proc_net_remove(&init_net, procname);
+ remove_proc_entry(procname, init_net.proc_net);
unregister_jprobe(&dccp_send_probe);
}
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index f916013..c4a2def 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -2413,7 +2413,7 @@ static void __exit decnet_exit(void)
dn_neigh_cleanup();
dn_fib_cleanup();
- proc_net_remove(&init_net, "decnet");
+ remove_proc_entry("decnet", init_net.proc_net);
proto_unregister(&dn_proto);
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index a04894a..c8da116 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -1433,7 +1433,7 @@ void __exit dn_dev_cleanup(void)
}
#endif /* CONFIG_SYSCTL */
- proc_net_remove(&init_net, "decnet_dev");
+ remove_proc_entry("decnet_dev", init_net.proc_net);
dn_dev_devices_off();
}
diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c
index f3408f3..f8637f9 100644
--- a/net/decnet/dn_neigh.c
+++ b/net/decnet/dn_neigh.c
@@ -596,6 +596,6 @@ void __init dn_neigh_init(void)
void __exit dn_neigh_cleanup(void)
{
- proc_net_remove(&init_net, "decnet_neigh");
+ remove_proc_entry("decnet_neigh", init_net.proc_net);
neigh_table_clear(&dn_neigh_table);
}
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 8afb257..5ac0e15 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1918,7 +1918,7 @@ void __exit dn_route_cleanup(void)
del_timer(&dn_route_timer);
dn_run_flush(0);
- proc_net_remove(&init_net, "decnet_cache");
+ remove_proc_entry("decnet_cache", init_net.proc_net);
dst_entries_destroy(&dn_dst_ops);
}
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index b04c114..fea4929 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1412,7 +1412,7 @@ static int __net_init arp_net_init(struct net *net)
static void __net_exit arp_net_exit(struct net *net)
{
- proc_net_remove(net, "arp");
+ remove_proc_entry("arp", net->proc_net);
}
static struct pernet_operations arp_net_ops = {
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 67c1d4b..61e03da 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2620,18 +2620,18 @@ int __net_init fib_proc_init(struct net *net)
return 0;
out3:
- proc_net_remove(net, "fib_triestat");
+ remove_proc_entry("fib_triestat", net->proc_net);
out2:
- proc_net_remove(net, "fib_trie");
+ remove_proc_entry("fib_trie", net->proc_net);
out1:
return -ENOMEM;
}
void __net_exit fib_proc_exit(struct net *net)
{
- proc_net_remove(net, "fib_trie");
- proc_net_remove(net, "fib_triestat");
- proc_net_remove(net, "route");
+ remove_proc_entry("fib_trie", net->proc_net);
+ remove_proc_entry("fib_triestat", net->proc_net);
+ remove_proc_entry("route", net->proc_net);
}
#endif /* CONFIG_PROC_FS */
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index be85628..d8c2327 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2656,15 +2656,15 @@ static int __net_init igmp_net_init(struct net *net)
return 0;
out_mcfilter:
- proc_net_remove(net, "igmp");
+ remove_proc_entry("igmp", net->proc_net);
out_igmp:
return -ENOMEM;
}
static void __net_exit igmp_net_exit(struct net *net)
{
- proc_net_remove(net, "mcfilter");
- proc_net_remove(net, "igmp");
+ remove_proc_entry("mcfilter", net->proc_net);
+ remove_proc_entry("igmp", net->proc_net);
}
static struct pernet_operations igmp_net_ops = {
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 160a8b8..5f95b3a 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2712,7 +2712,7 @@ static int __net_init ipmr_net_init(struct net *net)
#ifdef CONFIG_PROC_FS
proc_cache_fail:
- proc_net_remove(net, "ip_mr_vif");
+ remove_proc_entry("ip_mr_vif", net->proc_net);
proc_vif_fail:
ipmr_rules_exit(net);
#endif
@@ -2723,8 +2723,8 @@ fail:
static void __net_exit ipmr_net_exit(struct net *net)
{
#ifdef CONFIG_PROC_FS
- proc_net_remove(net, "ip_mr_cache");
- proc_net_remove(net, "ip_mr_vif");
+ remove_proc_entry("ip_mr_cache", net->proc_net);
+ remove_proc_entry("ip_mr_vif", net->proc_net);
#endif
ipmr_rules_exit(net);
}
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index 48bc681..f2ca127 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -433,9 +433,9 @@ static int __net_init ip_conntrack_net_init(struct net *net)
return 0;
err3:
- proc_net_remove(net, "ip_conntrack_expect");
+ remove_proc_entry("ip_conntrack_expect", net->proc_net);
err2:
- proc_net_remove(net, "ip_conntrack");
+ remove_proc_entry("ip_conntrack", net->proc_net);
err1:
return -ENOMEM;
}
@@ -443,8 +443,8 @@ err1:
static void __net_exit ip_conntrack_net_exit(struct net *net)
{
remove_proc_entry("ip_conntrack", net->proc_net_stat);
- proc_net_remove(net, "ip_conntrack_expect");
- proc_net_remove(net, "ip_conntrack");
+ remove_proc_entry("ip_conntrack_expect", net->proc_net);
+ remove_proc_entry("ip_conntrack", net->proc_net);
}
static struct pernet_operations ip_conntrack_net_ops = {
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index fc62a13..55c4ee1 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -897,7 +897,7 @@ static int ping_proc_register(struct net *net)
static void ping_proc_unregister(struct net *net)
{
- proc_net_remove(net, "icmp");
+ remove_proc_entry("icmp", net->proc_net);
}
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 954bcd4..32030a2 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -482,18 +482,18 @@ static __net_init int ip_proc_init_net(struct net *net)
return 0;
out_snmp:
- proc_net_remove(net, "netstat");
+ remove_proc_entry("netstat", net->proc_net);
out_netstat:
- proc_net_remove(net, "sockstat");
+ remove_proc_entry("sockstat", net->proc_net);
out_sockstat:
return -ENOMEM;
}
static __net_exit void ip_proc_exit_net(struct net *net)
{
- proc_net_remove(net, "snmp");
- proc_net_remove(net, "netstat");
- proc_net_remove(net, "sockstat");
+ remove_proc_entry("snmp", net->proc_net);
+ remove_proc_entry("netstat", net->proc_net);
+ remove_proc_entry("sockstat", net->proc_net);
}
static __net_initdata struct pernet_operations ip_proc_ops = {
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 5043a7d..53ddebc 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -1058,7 +1058,7 @@ static __net_init int raw_init_net(struct net *net)
static __net_exit void raw_exit_net(struct net *net)
{
- proc_net_remove(net, "raw");
+ remove_proc_entry("raw", net->proc_net);
}
static __net_initdata struct pernet_operations raw_net_ops = {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 77f5050..145d3bf 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2616,7 +2616,7 @@ EXPORT_SYMBOL(tcp_proc_register);
void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo)
{
- proc_net_remove(net, afinfo->name);
+ remove_proc_entry(afinfo->name, net->proc_net);
}
EXPORT_SYMBOL(tcp_proc_unregister);
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index 1e3a1fb..d4943f6 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -244,7 +244,7 @@ static __init int tcpprobe_init(void)
pr_info("probe registered (port=%d) bufsize=%u\n", port, bufsize);
return 0;
err1:
- proc_net_remove(&init_net, procname);
+ remove_proc_entry(procname, init_net.proc_net);
err0:
kfree(tcp_probe.log);
return ret;
@@ -253,7 +253,7 @@ module_init(tcpprobe_init);
static __exit void tcpprobe_exit(void)
{
- proc_net_remove(&init_net, procname);
+ remove_proc_entry(procname, init_net.proc_net);
unregister_jprobe(&tcp_jprobe);
kfree(tcp_probe.log);
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 39a5e7a..265c42c 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2122,7 +2122,7 @@ EXPORT_SYMBOL(udp_proc_register);
void udp_proc_unregister(struct net *net, struct udp_seq_afinfo *afinfo)
{
- proc_net_remove(net, afinfo->name);
+ remove_proc_entry(afinfo->name, net->proc_net);
}
EXPORT_SYMBOL(udp_proc_unregister);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index bad7108..4dc0d44 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3332,7 +3332,7 @@ static int __net_init if6_proc_net_init(struct net *net)
static void __net_exit if6_proc_net_exit(struct net *net)
{
- proc_net_remove(net, "if_inet6");
+ remove_proc_entry("if_inet6", net->proc_net);
}
static struct pernet_operations if6_proc_net_ops = {
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 5a8c009..5a80f15 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -517,7 +517,7 @@ int __net_init ac6_proc_init(struct net *net)
void ac6_proc_exit(struct net *net)
{
- proc_net_remove(net, "anycast6");
+ remove_proc_entry("anycast6", net->proc_net);
}
#endif
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 900d79e..b973ed3 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -814,7 +814,7 @@ static int __net_init ip6_flowlabel_proc_init(struct net *net)
static void __net_exit ip6_flowlabel_proc_fini(struct net *net)
{
- proc_net_remove(net, "ip6_flowlabel");
+ remove_proc_entry("ip6_flowlabel", net->proc_net);
}
#else
static inline int ip6_flowlabel_proc_init(struct net *net)
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index fdfd96d..96bfb4e 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1369,7 +1369,7 @@ static int __net_init ip6mr_net_init(struct net *net)
#ifdef CONFIG_PROC_FS
proc_cache_fail:
- proc_net_remove(net, "ip6_mr_vif");
+ remove_proc_entry("ip6_mr_vif", net->proc_net);
proc_vif_fail:
ip6mr_rules_exit(net);
#endif
@@ -1380,8 +1380,8 @@ fail:
static void __net_exit ip6mr_net_exit(struct net *net)
{
#ifdef CONFIG_PROC_FS
- proc_net_remove(net, "ip6_mr_cache");
- proc_net_remove(net, "ip6_mr_vif");
+ remove_proc_entry("ip6_mr_cache", net->proc_net);
+ remove_proc_entry("ip6_mr_vif", net->proc_net);
#endif
ip6mr_rules_exit(net);
}
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index de7d4b9..bfa6cc3 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2610,14 +2610,14 @@ out:
return err;
out_proc_net_igmp6:
- proc_net_remove(net, "igmp6");
+ remove_proc_entry("igmp6", net->proc_net);
goto out;
}
static void __net_exit igmp6_proc_exit(struct net *net)
{
- proc_net_remove(net, "mcfilter6");
- proc_net_remove(net, "igmp6");
+ remove_proc_entry("mcfilter6", net->proc_net);
+ remove_proc_entry("igmp6", net->proc_net);
}
#else
static inline int igmp6_proc_init(struct net *net)
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index cf8901d..bbbe53a 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -308,17 +308,17 @@ static int __net_init ipv6_proc_init_net(struct net *net)
return 0;
proc_dev_snmp6_fail:
- proc_net_remove(net, "snmp6");
+ remove_proc_entry("snmp6", net->proc_net);
proc_snmp6_fail:
- proc_net_remove(net, "sockstat6");
+ remove_proc_entry("sockstat6", net->proc_net);
return -ENOMEM;
}
static void __net_exit ipv6_proc_exit_net(struct net *net)
{
- proc_net_remove(net, "sockstat6");
- proc_net_remove(net, "dev_snmp6");
- proc_net_remove(net, "snmp6");
+ remove_proc_entry("sockstat6", net->proc_net);
+ remove_proc_entry("dev_snmp6", net->proc_net);
+ remove_proc_entry("snmp6", net->proc_net);
}
static struct pernet_operations ipv6_proc_ops = {
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index ff42fb3..c65907d 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1300,7 +1300,7 @@ static int __net_init raw6_init_net(struct net *net)
static void __net_exit raw6_exit_net(struct net *net)
{
- proc_net_remove(net, "raw6");
+ remove_proc_entry("raw6", net->proc_net);
}
static struct pernet_operations raw6_net_ops = {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e1228d8..515bb51 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3004,8 +3004,8 @@ static int __net_init ip6_route_net_init_late(struct net *net)
static void __net_exit ip6_route_net_exit_late(struct net *net)
{
#ifdef CONFIG_PROC_FS
- proc_net_remove(net, "ipv6_route");
- proc_net_remove(net, "rt6_stats");
+ remove_proc_entry("ipv6_route", net->proc_net);
+ remove_proc_entry("rt6_stats", net->proc_net);
#endif
}
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 021a429..9ef7985 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3749,7 +3749,7 @@ static int __net_init pfkey_init_proc(struct net *net)
static void __net_exit pfkey_exit_proc(struct net *net)
{
- proc_net_remove(net, "pfkey");
+ remove_proc_entry("pfkey", net->proc_net);
}
#else
static inline int pfkey_init_proc(struct net *net)
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 3ca270b..3f4e3af 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1796,7 +1796,7 @@ out:
static __net_exit void pppol2tp_exit_net(struct net *net)
{
- proc_net_remove(net, "pppol2tp");
+ remove_proc_entry("pppol2tp", net->proc_net);
}
static struct pernet_operations pppol2tp_net_ops = {
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index 1db8a25..0b779d7 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -612,5 +612,5 @@ int __net_init ip_vs_app_net_init(struct net *net)
void __net_exit ip_vs_app_net_cleanup(struct net *net)
{
unregister_ip_vs_app(net, NULL /* all */);
- proc_net_remove(net, "ip_vs_app");
+ remove_proc_entry("ip_vs_app", net->proc_net);
}
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 91ae112..9f00db7 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -1300,8 +1300,8 @@ void __net_exit ip_vs_conn_net_cleanup(struct net *net)
{
/* flush all the connection entries first */
ip_vs_conn_flush(net);
- proc_net_remove(net, "ip_vs_conn");
- proc_net_remove(net, "ip_vs_conn_sync");
+ remove_proc_entry("ip_vs_conn", net->proc_net);
+ remove_proc_entry("ip_vs_conn_sync", net->proc_net);
}
int __init ip_vs_conn_init(void)
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 7d69181..c68198b 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3822,9 +3822,9 @@ void __net_exit ip_vs_control_net_cleanup(struct net *net)
ip_vs_trash_cleanup(net);
ip_vs_stop_estimator(net, &ipvs->tot_stats);
ip_vs_control_net_cleanup_sysctl(net);
- proc_net_remove(net, "ip_vs_stats_percpu");
- proc_net_remove(net, "ip_vs_stats");
- proc_net_remove(net, "ip_vs");
+ remove_proc_entry("ip_vs_stats_percpu", net->proc_net);
+ remove_proc_entry("ip_vs_stats", net->proc_net);
+ remove_proc_entry("ip_vs", net->proc_net);
free_percpu(ipvs->tot_stats.cpustats);
}
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 4c15f8d..3921e5b 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -582,7 +582,7 @@ static int exp_proc_init(struct net *net)
static void exp_proc_remove(struct net *net)
{
#ifdef CONFIG_NF_CONNTRACK_PROCFS
- proc_net_remove(net, "nf_conntrack_expect");
+ remove_proc_entry("nf_conntrack_expect", net->proc_net);
#endif /* CONFIG_NF_CONNTRACK_PROCFS */
}
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index bee9aec..6bcce40 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -377,7 +377,7 @@ static int nf_conntrack_standalone_init_proc(struct net *net)
return 0;
out_stat_nf_conntrack:
- proc_net_remove(net, "nf_conntrack");
+ remove_proc_entry("nf_conntrack", net->proc_net);
out_nf_conntrack:
return -ENOMEM;
}
@@ -385,7 +385,7 @@ out_nf_conntrack:
static void nf_conntrack_standalone_fini_proc(struct net *net)
{
remove_proc_entry("nf_conntrack", net->proc_net_stat);
- proc_net_remove(net, "nf_conntrack");
+ remove_proc_entry("nf_conntrack", net->proc_net);
}
#else
static int nf_conntrack_standalone_init_proc(struct net *net)
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 7b3a9e5..686c771 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1323,12 +1323,12 @@ int xt_proto_init(struct net *net, u_int8_t af)
out_remove_matches:
strlcpy(buf, xt_prefix[af], sizeof(buf));
strlcat(buf, FORMAT_MATCHES, sizeof(buf));
- proc_net_remove(net, buf);
+ remove_proc_entry(buf, net->proc_net);
out_remove_tables:
strlcpy(buf, xt_prefix[af], sizeof(buf));
strlcat(buf, FORMAT_TABLES, sizeof(buf));
- proc_net_remove(net, buf);
+ remove_proc_entry(buf, net->proc_net);
out:
return -1;
#endif
@@ -1342,15 +1342,15 @@ void xt_proto_fini(struct net *net, u_int8_t af)
strlcpy(buf, xt_prefix[af], sizeof(buf));
strlcat(buf, FORMAT_TABLES, sizeof(buf));
- proc_net_remove(net, buf);
+ remove_proc_entry(buf, net->proc_net);
strlcpy(buf, xt_prefix[af], sizeof(buf));
strlcat(buf, FORMAT_TARGETS, sizeof(buf));
- proc_net_remove(net, buf);
+ remove_proc_entry(buf, net->proc_net);
strlcpy(buf, xt_prefix[af], sizeof(buf));
strlcat(buf, FORMAT_MATCHES, sizeof(buf));
- proc_net_remove(net, buf);
+ remove_proc_entry(buf, net->proc_net);
#endif /*CONFIG_PROC_FS*/
}
EXPORT_SYMBOL_GPL(xt_proto_fini);
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index a9d7af9..98218c8 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -867,7 +867,7 @@ static int __net_init hashlimit_proc_net_init(struct net *net)
#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
hashlimit_net->ip6t_hashlimit = proc_mkdir("ip6t_hashlimit", net->proc_net);
if (!hashlimit_net->ip6t_hashlimit) {
- proc_net_remove(net, "ipt_hashlimit");
+ remove_proc_entry("ipt_hashlimit", net->proc_net);
return -ENOMEM;
}
#endif
@@ -897,9 +897,9 @@ static void __net_exit hashlimit_proc_net_exit(struct net *net)
hashlimit_net->ip6t_hashlimit = NULL;
mutex_unlock(&hashlimit_mutex);
- proc_net_remove(net, "ipt_hashlimit");
+ remove_proc_entry("ipt_hashlimit", net->proc_net);
#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
- proc_net_remove(net, "ip6t_hashlimit");
+ remove_proc_entry("ip6t_hashlimit", net->proc_net);
#endif
}
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index 978efc9..31bf233 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -643,7 +643,7 @@ static void __net_exit recent_proc_net_exit(struct net *net)
recent_net->xt_recent = NULL;
spin_unlock_bh(&recent_lock);
- proc_net_remove(net, "xt_recent");
+ remove_proc_entry("xt_recent", net->proc_net);
}
#else
static inline int recent_proc_net_init(struct net *net)
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 50084c4..3d55e0c 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2154,7 +2154,7 @@ static int __net_init netlink_net_init(struct net *net)
static void __net_exit netlink_net_exit(struct net *net)
{
#ifdef CONFIG_PROC_FS
- proc_net_remove(net, "netlink");
+ remove_proc_entry("netlink", net->proc_net);
#endif
}
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 71b8613..297b07a 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1482,9 +1482,9 @@ static void __exit nr_exit(void)
{
int i;
- proc_net_remove(&init_net, "nr");
- proc_net_remove(&init_net, "nr_neigh");
- proc_net_remove(&init_net, "nr_nodes");
+ remove_proc_entry("nr", init_net.proc_net);
+ remove_proc_entry("nr_neigh", init_net.proc_net);
+ remove_proc_entry("nr_nodes", init_net.proc_net);
nr_loopback_clear();
nr_rt_free();
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index b7b2d56..c7bfeff 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3836,7 +3836,7 @@ static int __net_init packet_net_init(struct net *net)
static void __net_exit packet_net_exit(struct net *net)
{
- proc_net_remove(net, "packet");
+ remove_proc_entry("packet", net->proc_net);
}
static struct pernet_operations packet_net_ops = {
diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c
index 0e527c9..45a7df6 100644
--- a/net/phonet/pn_dev.c
+++ b/net/phonet/pn_dev.c
@@ -331,7 +331,7 @@ static int __net_init phonet_init_net(struct net *net)
static void __net_exit phonet_exit_net(struct net *net)
{
- proc_net_remove(net, "phonet");
+ remove_proc_entry("phonet", net->proc_net);
}
static struct pernet_operations phonet_net_ops = {
@@ -361,7 +361,7 @@ void phonet_device_exit(void)
rtnl_unregister_all(PF_PHONET);
unregister_netdevice_notifier(&phonet_device_notifier);
unregister_pernet_subsys(&phonet_net_ops);
- proc_net_remove(&init_net, "pnresource");
+ remove_proc_entry("pnresource", init_net.proc_net);
}
int phonet_route_add(struct net_device *dev, u8 daddr)
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 5fd8aac..b768fe9 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1608,10 +1608,10 @@ static void __exit rose_exit(void)
{
int i;
- proc_net_remove(&init_net, "rose");
- proc_net_remove(&init_net, "rose_neigh");
- proc_net_remove(&init_net, "rose_nodes");
- proc_net_remove(&init_net, "rose_routes");
+ remove_proc_entry("rose", init_net.proc_net);
+ remove_proc_entry("rose_neigh", init_net.proc_net);
+ remove_proc_entry("rose_nodes", init_net.proc_net);
+ remove_proc_entry("rose_routes", init_net.proc_net);
rose_loopback_clear();
rose_rt_free();
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 59c7c7d..e61aa60 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -879,8 +879,8 @@ static void __exit af_rxrpc_exit(void)
_debug("flush scheduled work");
flush_workqueue(rxrpc_workqueue);
- proc_net_remove(&init_net, "rxrpc_conns");
- proc_net_remove(&init_net, "rxrpc_calls");
+ remove_proc_entry("rxrpc_conns", init_net.proc_net);
+ remove_proc_entry("rxrpc_calls", init_net.proc_net);
destroy_workqueue(rxrpc_workqueue);
kmem_cache_destroy(rxrpc_call_jar);
_leave("");
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index d8cf7d3..a181b48 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1777,7 +1777,7 @@ static int __net_init psched_net_init(struct net *net)
static void __net_exit psched_net_exit(struct net *net)
{
- proc_net_remove(net, "psched");
+ remove_proc_entry("psched", net->proc_net);
}
#else
static int __net_init psched_net_init(struct net *net)
diff --git a/net/sctp/probe.c b/net/sctp/probe.c
index dd507f5..ad0dba8 100644
--- a/net/sctp/probe.c
+++ b/net/sctp/probe.c
@@ -208,7 +208,7 @@ static __init int sctpprobe_init(void)
return 0;
remove_proc:
- proc_net_remove(&init_net, procname);
+ remove_proc_entry(procname, init_net.proc_net);
free_kfifo:
kfifo_free(&sctpw.fifo);
return ret;
@@ -217,7 +217,7 @@ free_kfifo:
static __exit void sctpprobe_exit(void)
{
kfifo_free(&sctpw.fifo);
- proc_net_remove(&init_net, procname);
+ remove_proc_entry(procname, init_net.proc_net);
unregister_jprobe(&sctp_recv_probe);
}
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 0c479b6..87d2842 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2415,7 +2415,7 @@ out:
static void __net_exit unix_net_exit(struct net *net)
{
unix_sysctl_unregister(net);
- proc_net_remove(net, "unix");
+ remove_proc_entry("unix", net->proc_net);
}
static struct pernet_operations unix_net_ops = {
diff --git a/net/wireless/wext-proc.c b/net/wireless/wext-proc.c
index 00fc5bb..e98a01c 100644
--- a/net/wireless/wext-proc.c
+++ b/net/wireless/wext-proc.c
@@ -152,5 +152,5 @@ int __net_init wext_proc_init(struct net *net)
void __net_exit wext_proc_exit(struct net *net)
{
- proc_net_remove(net, "wireless");
+ remove_proc_entry("wireless", net->proc_net);
}
diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c
index 9abe14f..c721b0d 100644
--- a/net/xfrm/xfrm_proc.c
+++ b/net/xfrm/xfrm_proc.c
@@ -82,5 +82,5 @@ int __net_init xfrm_proc_init(struct net *net)
void xfrm_proc_fini(struct net *net)
{
- proc_net_remove(net, "xfrm_stat");
+ remove_proc_entry("xfrm_stat", net->proc_net);
}
--
1.7.11.7
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox