aboutsummaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/exit.c2
-rw-r--r--kernel/futex.c2
-rw-r--r--kernel/hrtimer.c10
-rw-r--r--kernel/irq/proc.c2
-rw-r--r--kernel/kexec.c7
-rw-r--r--kernel/perf_event.c12
-rw-r--r--kernel/pid.c5
-rw-r--r--kernel/power/Kconfig6
-rw-r--r--kernel/power/hibernate.c10
-rw-r--r--kernel/power/suspend.c5
-rw-r--r--kernel/ptrace.c17
-rw-r--r--kernel/sched.c20
-rw-r--r--kernel/sched_fair.c14
-rw-r--r--kernel/time/posix-clock.c24
-rw-r--r--kernel/trace/Kconfig2
-rw-r--r--kernel/trace/blktrace.c33
-rw-r--r--kernel/trace/trace.c1
-rw-r--r--kernel/trace/trace_events.c1
-rw-r--r--kernel/watchdog.c5
-rw-r--r--kernel/workqueue.c8
20 files changed, 115 insertions, 71 deletions
diff --git a/kernel/exit.c b/kernel/exit.c
index f5d2f63..8dd8741 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1016,7 +1016,7 @@ NORET_TYPE void do_exit(long code)
/*
* FIXME: do that only when needed, using sched_exit tracepoint
*/
- flush_ptrace_hw_breakpoint(tsk);
+ ptrace_put_breakpoints(tsk);
exit_notify(tsk, group_dead);
#ifdef CONFIG_NUMA
diff --git a/kernel/futex.c b/kernel/futex.c
index dfb924f..fe28dc2 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1886,7 +1886,7 @@ retry:
restart->futex.val = val;
restart->futex.time = abs_time->tv64;
restart->futex.bitset = bitset;
- restart->futex.flags = flags;
+ restart->futex.flags = flags | FLAGS_HAS_TIMEOUT;
ret = -ERESTART_RESTARTBLOCK;
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 9017478..87fdb3f 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -81,7 +81,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
}
};
-static int hrtimer_clock_to_base_table[MAX_CLOCKS];
+static int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
+ [CLOCK_REALTIME] = HRTIMER_BASE_REALTIME,
+ [CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC,
+ [CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME,
+};
static inline int hrtimer_clockid_to_base(clockid_t clock_id)
{
@@ -1722,10 +1726,6 @@ static struct notifier_block __cpuinitdata hrtimers_nb = {
void __init hrtimers_init(void)
{
- hrtimer_clock_to_base_table[CLOCK_REALTIME] = HRTIMER_BASE_REALTIME;
- hrtimer_clock_to_base_table[CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC;
- hrtimer_clock_to_base_table[CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME;
-
hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
(void *)(long)smp_processor_id());
register_cpu_notifier(&hrtimers_nb);
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index dd201bd..834899f 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -419,7 +419,7 @@ int show_interrupts(struct seq_file *p, void *v)
} else {
seq_printf(p, " %8s", "None");
}
-#ifdef CONFIG_GENIRC_IRQ_SHOW_LEVEL
+#ifdef CONFIG_GENERIC_IRQ_SHOW_LEVEL
seq_printf(p, " %-8s", irqd_is_level_type(&desc->irq_data) ? "Level" : "Edge");
#endif
if (desc->name)
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 55936f9..87b77de 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -33,6 +33,7 @@
#include <linux/vmalloc.h>
#include <linux/swap.h>
#include <linux/kmsg_dump.h>
+#include <linux/syscore_ops.h>
#include <asm/page.h>
#include <asm/uaccess.h>
@@ -1532,6 +1533,11 @@ int kernel_kexec(void)
local_irq_disable();
/* Suspend system devices */
error = sysdev_suspend(PMSG_FREEZE);
+ if (!error) {
+ error = syscore_suspend();
+ if (error)
+ sysdev_resume();
+ }
if (error)
goto Enable_irqs;
} else
@@ -1546,6 +1552,7 @@ int kernel_kexec(void)
#ifdef CONFIG_KEXEC_JUMP
if (kexec_image->preserve_context) {
+ syscore_resume();
sysdev_resume();
Enable_irqs:
local_irq_enable();
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 27960f1..8e81a98 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -364,6 +364,7 @@ void perf_cgroup_switch(struct task_struct *task, int mode)
}
if (mode & PERF_CGROUP_SWIN) {
+ WARN_ON_ONCE(cpuctx->cgrp);
/* set cgrp before ctxsw in to
* allow event_filter_match() to not
* have to pass task around
@@ -2423,6 +2424,14 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
if (!ctx || !ctx->nr_events)
goto out;
+ /*
+ * We must ctxsw out cgroup events to avoid conflict
+ * when invoking perf_task_event_sched_in() later on
+ * in this function. Otherwise we end up trying to
+ * ctxswin cgroup events which are already scheduled
+ * in.
+ */
+ perf_cgroup_sched_out(current);
task_ctx_sched_out(ctx, EVENT_ALL);
raw_spin_lock(&ctx->lock);
@@ -2447,6 +2456,9 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
raw_spin_unlock(&ctx->lock);
+ /*
+ * Also calls ctxswin for cgroup events, if any:
+ */
perf_event_context_sched_in(ctx, ctx->task);
out:
local_irq_restore(flags);
diff --git a/kernel/pid.c b/kernel/pid.c
index 02f2212..57a8346 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -217,11 +217,14 @@ static int alloc_pidmap(struct pid_namespace *pid_ns)
return -1;
}
-int next_pidmap(struct pid_namespace *pid_ns, int last)
+int next_pidmap(struct pid_namespace *pid_ns, unsigned int last)
{
int offset;
struct pidmap *map, *end;
+ if (last >= PID_MAX_LIMIT)
+ return -1;
+
offset = (last + 1) & BITS_PER_PAGE_MASK;
map = &pid_ns->pidmap[(last + 1)/BITS_PER_PAGE];
end = &pid_ns->pidmap[PIDMAP_ENTRIES];
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 4603f08..6de9a8f 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -18,9 +18,13 @@ config SUSPEND_FREEZER
Turning OFF this setting is NOT recommended! If in doubt, say Y.
+config HIBERNATE_CALLBACKS
+ bool
+
config HIBERNATION
bool "Hibernation (aka 'suspend to disk')"
depends on SWAP && ARCH_HIBERNATION_POSSIBLE
+ select HIBERNATE_CALLBACKS
select LZO_COMPRESS
select LZO_DECOMPRESS
---help---
@@ -85,7 +89,7 @@ config PM_STD_PARTITION
config PM_SLEEP
def_bool y
- depends on SUSPEND || HIBERNATION || XEN_SAVE_RESTORE
+ depends on SUSPEND || HIBERNATE_CALLBACKS
config PM_SLEEP_SMP
def_bool y
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index aeabd26..50aae66 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -273,8 +273,11 @@ static int create_image(int platform_mode)
local_irq_disable();
error = sysdev_suspend(PMSG_FREEZE);
- if (!error)
+ if (!error) {
error = syscore_suspend();
+ if (error)
+ sysdev_resume();
+ }
if (error) {
printk(KERN_ERR "PM: Some system devices failed to power down, "
"aborting hibernation\n");
@@ -407,8 +410,11 @@ static int resume_target_kernel(bool platform_mode)
local_irq_disable();
error = sysdev_suspend(PMSG_QUIESCE);
- if (!error)
+ if (!error) {
error = syscore_suspend();
+ if (error)
+ sysdev_resume();
+ }
if (error)
goto Enable_irqs;
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 2814c32..8935369 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -164,8 +164,11 @@ static int suspend_enter(suspend_state_t state)
BUG_ON(!irqs_disabled());
error = sysdev_suspend(PMSG_SUSPEND);
- if (!error)
+ if (!error) {
error = syscore_suspend();
+ if (error)
+ sysdev_resume();
+ }
if (!error) {
if (!(suspend_test(TEST_CORE) || pm_wakeup_pending())) {
error = suspend_ops->enter(state);
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 0fc1eed..dc7ab65 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -22,6 +22,7 @@
#include <linux/syscalls.h>
#include <linux/uaccess.h>
#include <linux/regset.h>
+#include <linux/hw_breakpoint.h>
/*
@@ -879,3 +880,19 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
return ret;
}
#endif /* CONFIG_COMPAT */
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+int ptrace_get_breakpoints(struct task_struct *tsk)
+{
+ if (atomic_inc_not_zero(&tsk->ptrace_bp_refcnt))
+ return 0;
+
+ return -1;
+}
+
+void ptrace_put_breakpoints(struct task_struct *tsk)
+{
+ if (atomic_dec_and_test(&tsk->ptrace_bp_refcnt))
+ flush_ptrace_hw_breakpoint(tsk);
+}
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
diff --git a/kernel/sched.c b/kernel/sched.c
index 4801363..312f8b9 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4111,20 +4111,20 @@ need_resched:
try_to_wake_up_local(to_wakeup);
}
deactivate_task(rq, prev, DEQUEUE_SLEEP);
+
+ /*
+ * If we are going to sleep and we have plugged IO queued, make
+ * sure to submit it to avoid deadlocks.
+ */
+ if (blk_needs_flush_plug(prev)) {
+ raw_spin_unlock(&rq->lock);
+ blk_schedule_flush_plug(prev);
+ raw_spin_lock(&rq->lock);
+ }
}
switch_count = &prev->nvcsw;
}
- /*
- * If we are going to sleep and we have plugged IO queued, make
- * sure to submit it to avoid deadlocks.
- */
- if (prev->state != TASK_RUNNING && blk_needs_flush_plug(prev)) {
- raw_spin_unlock(&rq->lock);
- blk_flush_plug(prev);
- raw_spin_lock(&rq->lock);
- }
-
pre_schedule(rq, prev);
if (unlikely(!rq->nr_running))
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 7f00772..6fa833a 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -2104,21 +2104,20 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
enum cpu_idle_type idle, int *all_pinned,
int *this_best_prio, struct cfs_rq *busiest_cfs_rq)
{
- int loops = 0, pulled = 0, pinned = 0;
+ int loops = 0, pulled = 0;
long rem_load_move = max_load_move;
struct task_struct *p, *n;
if (max_load_move == 0)
goto out;
- pinned = 1;
-
list_for_each_entry_safe(p, n, &busiest_cfs_rq->tasks, se.group_node) {
if (loops++ > sysctl_sched_nr_migrate)
break;
if ((p->se.load.weight >> 1) > rem_load_move ||
- !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned))
+ !can_migrate_task(p, busiest, this_cpu, sd, idle,
+ all_pinned))
continue;
pull_task(busiest, p, this_rq, this_cpu);
@@ -2153,9 +2152,6 @@ out:
*/
schedstat_add(sd, lb_gained[idle], pulled);
- if (all_pinned)
- *all_pinned = pinned;
-
return max_load_move - rem_load_move;
}
@@ -3127,6 +3123,8 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
if (!sds.busiest || sds.busiest_nr_running == 0)
goto out_balanced;
+ sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr;
+
/*
* If the busiest group is imbalanced the below checks don't
* work because they assumes all things are equal, which typically
@@ -3151,7 +3149,6 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
* Don't pull any tasks if this group is already above the domain
* average load.
*/
- sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr;
if (sds.this_load >= sds.avg_load)
goto out_balanced;
@@ -3340,6 +3337,7 @@ redo:
* still unbalanced. ld_moved simply stays zero, so it is
* correctly treated as an imbalance.
*/
+ all_pinned = 1;
local_irq_save(flags);
double_rq_lock(this_rq, busiest);
ld_moved = move_tasks(this_rq, this_cpu, busiest,
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index 25028dd..c340ca6 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -19,7 +19,6 @@
*/
#include <linux/device.h>
#include <linux/file.h>
-#include <linux/mutex.h>
#include <linux/posix-clock.h>
#include <linux/slab.h>
#include <linux/syscalls.h>
@@ -34,19 +33,19 @@ static struct posix_clock *get_posix_clock(struct file *fp)
{
struct posix_clock *clk = fp->private_data;
- mutex_lock(&clk->mutex);
+ down_read(&clk->rwsem);
if (!clk->zombie)
return clk;
- mutex_unlock(&clk->mutex);
+ up_read(&clk->rwsem);
return NULL;
}
static void put_posix_clock(struct posix_clock *clk)
{
- mutex_unlock(&clk->mutex);
+ up_read(&clk->rwsem);
}
static ssize_t posix_clock_read(struct file *fp, char __user *buf,
@@ -156,7 +155,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp)
struct posix_clock *clk =
container_of(inode->i_cdev, struct posix_clock, cdev);
- mutex_lock(&clk->mutex);
+ down_read(&clk->rwsem);
if (clk->zombie) {
err = -ENODEV;
@@ -172,7 +171,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp)
fp->private_data = clk;
}
out:
- mutex_unlock(&clk->mutex);
+ up_read(&clk->rwsem);
return err;
}
@@ -211,25 +210,20 @@ int posix_clock_register(struct posix_clock *clk, dev_t devid)
int err;
kref_init(&clk->kref);
- mutex_init(&clk->mutex);
+ init_rwsem(&clk->rwsem);
cdev_init(&clk->cdev, &posix_clock_file_operations);
clk->cdev.owner = clk->ops.owner;
err = cdev_add(&clk->cdev, devid, 1);
- if (err)
- goto no_cdev;
return err;
-no_cdev:
- mutex_destroy(&clk->mutex);
- return err;
}
EXPORT_SYMBOL_GPL(posix_clock_register);
static void delete_clock(struct kref *kref)
{
struct posix_clock *clk = container_of(kref, struct posix_clock, kref);
- mutex_destroy(&clk->mutex);
+
if (clk->release)
clk->release(clk);
}
@@ -238,9 +232,9 @@ void posix_clock_unregister(struct posix_clock *clk)
{
cdev_del(&clk->cdev);
- mutex_lock(&clk->mutex);
+ down_write(&clk->rwsem);
clk->zombie = true;
- mutex_unlock(&clk->mutex);
+ up_write(&clk->rwsem);
kref_put(&clk->kref, delete_clock);
}
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 61d7d59f..2ad39e5 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -141,7 +141,7 @@ if FTRACE
config FUNCTION_TRACER
bool "Kernel Function Tracer"
depends on HAVE_FUNCTION_TRACER
- select FRAME_POINTER if !ARM_UNWIND && !S390
+ select FRAME_POINTER if !ARM_UNWIND && !S390 && !MICROBLAZE
select KALLSYMS
select GENERIC_TRACER
select CONTEXT_SWITCH_TRACER
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 7aa40f8..6957aa2 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -850,29 +850,21 @@ static void blk_add_trace_plug(void *ignore, struct request_queue *q)
__blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL);
}
-static void blk_add_trace_unplug_io(void *ignore, struct request_queue *q)
+static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
+ unsigned int depth, bool explicit)
{
struct blk_trace *bt = q->blk_trace;
if (bt) {
- unsigned int pdu = q->rq.count[READ] + q->rq.count[WRITE];
- __be64 rpdu = cpu_to_be64(pdu);
+ __be64 rpdu = cpu_to_be64(depth);
+ u32 what;
- __blk_add_trace(bt, 0, 0, 0, BLK_TA_UNPLUG_IO, 0,
- sizeof(rpdu), &rpdu);
- }
-}
-
-static void blk_add_trace_unplug_timer(void *ignore, struct request_queue *q)
-{
- struct blk_trace *bt = q->blk_trace;
-
- if (bt) {
- unsigned int pdu = q->rq.count[READ] + q->rq.count[WRITE];
- __be64 rpdu = cpu_to_be64(pdu);
+ if (explicit)
+ what = BLK_TA_UNPLUG_IO;
+ else
+ what = BLK_TA_UNPLUG_TIMER;
- __blk_add_trace(bt, 0, 0, 0, BLK_TA_UNPLUG_TIMER, 0,
- sizeof(rpdu), &rpdu);
+ __blk_add_trace(bt, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu);
}
}
@@ -1015,9 +1007,7 @@ static void blk_register_tracepoints(void)
WARN_ON(ret);
ret = register_trace_block_plug(blk_add_trace_plug, NULL);
WARN_ON(ret);
- ret = register_trace_block_unplug_timer(blk_add_trace_unplug_timer, NULL);
- WARN_ON(ret);
- ret = register_trace_block_unplug_io(blk_add_trace_unplug_io, NULL);
+ ret = register_trace_block_unplug(blk_add_trace_unplug, NULL);
WARN_ON(ret);
ret = register_trace_block_split(blk_add_trace_split, NULL);
WARN_ON(ret);
@@ -1032,8 +1022,7 @@ static void blk_unregister_tracepoints(void)
unregister_trace_block_rq_remap(blk_add_trace_rq_remap, NULL);
unregister_trace_block_bio_remap(blk_add_trace_bio_remap, NULL);
unregister_trace_block_split(blk_add_trace_split, NULL);
- unregister_trace_block_unplug_io(blk_add_trace_unplug_io, NULL);
- unregister_trace_block_unplug_timer(blk_add_trace_unplug_timer, NULL);
+ unregister_trace_block_unplug(blk_add_trace_unplug, NULL);
unregister_trace_block_plug(blk_add_trace_plug, NULL);
unregister_trace_block_sleeprq(blk_add_trace_sleeprq, NULL);
unregister_trace_block_getrq(blk_add_trace_getrq, NULL);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index d38c16a..1cb49be 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1110,6 +1110,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
entry->preempt_count = pc & 0xff;
entry->pid = (tsk) ? tsk->pid : 0;
+ entry->padding = 0;
entry->flags =
#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
(irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index e88f74f..2fe1103 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -116,6 +116,7 @@ static int trace_define_common_fields(void)
__common_field(unsigned char, flags);
__common_field(unsigned char, preempt_count);
__common_field(int, pid);
+ __common_field(int, padding);
return ret;
}
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 140dce7..14733d4 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -430,9 +430,12 @@ static int watchdog_enable(int cpu)
p = kthread_create(watchdog, (void *)(unsigned long)cpu, "watchdog/%d", cpu);
if (IS_ERR(p)) {
printk(KERN_ERR "softlockup watchdog for %i failed\n", cpu);
- if (!err)
+ if (!err) {
/* if hardlockup hasn't already set this */
err = PTR_ERR(p);
+ /* and disable the perf event */
+ watchdog_nmi_disable(cpu);
+ }
goto out;
}
kthread_bind(p, cpu);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 8859a41..e3378e8 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1291,8 +1291,14 @@ __acquires(&gcwq->lock)
return true;
spin_unlock_irq(&gcwq->lock);
- /* CPU has come up in between, retry migration */
+ /*
+ * We've raced with CPU hot[un]plug. Give it a breather
+ * and retry migration. cond_resched() is required here;
+ * otherwise, we might deadlock against cpu_stop trying to
+ * bring down the CPU on non-preemptive kernel.
+ */
cpu_relax();
+ cond_resched();
}
}
generated by cgit v1.1 at 2025-08-17 03:56:06 +0000