WorkStruct: Pass the work_struct pointer instead of context data

Pass the work_struct pointer to the work function rather than context data.
The work function can use container_of() to work out the data.

For the cases where the container of the work_struct may go away the moment the
pending bit is cleared, it is made possible to defer the release of the
structure by deferring the clearing of the pending bit.

To make this work, an extra flag is introduced into the management side of the
work_struct.  This governs auto-release of the structure upon execution.

Ordinarily, the work queue executor would release the work_struct for further
scheduling or deallocation by clearing the pending bit prior to jumping to the
work function.  This means that, unless the driver makes some guarantee itself
that the work_struct won't go away, the work function may not access anything
else in the work_struct or its container lest they be deallocated..  This is a
problem if the auxiliary data is taken away (as done by the last patch).

However, if the pending bit is *not* cleared before jumping to the work
function, then the work function *may* access the work_struct and its container
with no problems.  But then the work function must itself release the
work_struct by calling work_release().

In most cases, automatic release is fine, so this is the default.  Special
initiators exist for the non-auto-release case (ending in _NAR).


Signed-Off-By: David Howells <dhowells@redhat.com>

3 files changed, 12 insertions, 10 deletions

diff --git a/arch/x86_64/kernel/mce.c b/arch/x86_64/kernel/mce.c
index 5306f26..c7587fc 100644
--- a/arch/x86_64/kernel/mce.c
+++ b/arch/x86_64/kernel/mce.c
@@ -306,8 +306,8 @@ void mce_log_therm_throt_event(unsigned int cpu, __u64 status)
  */
 
 static int check_interval = 5 * 60; /* 5 minutes */
-static void mcheck_timer(void *data);
-static DECLARE_DELAYED_WORK(mcheck_work, mcheck_timer, NULL);
+static void mcheck_timer(struct work_struct *work);
+static DECLARE_DELAYED_WORK(mcheck_work, mcheck_timer);
 
 static void mcheck_check_cpu(void *info)
 {
@@ -315,7 +315,7 @@ static void mcheck_check_cpu(void *info)
 		do_machine_check(NULL, 0);
 }
 
-static void mcheck_timer(void *data)
+static void mcheck_timer(struct work_struct *work)
 {
 	on_each_cpu(mcheck_check_cpu, NULL, 1, 1);
 	schedule_delayed_work(&mcheck_work, check_interval * HZ);
diff --git a/arch/x86_64/kernel/smpboot.c b/arch/x86_64/kernel/smpboot.c
index 62c2e74..9800147 100644
--- a/arch/x86_64/kernel/smpboot.c
+++ b/arch/x86_64/kernel/smpboot.c
@@ -753,14 +753,16 @@ static int __cpuinit wakeup_secondary_via_INIT(int phys_apicid, unsigned int sta
 }
 
 struct create_idle {
+	struct work_struct work;
 	struct task_struct *idle;
 	struct completion done;
 	int cpu;
 };
 
-void do_fork_idle(void *_c_idle)
+void do_fork_idle(struct work_struct *work)
 {
-	struct create_idle *c_idle = _c_idle;
+	struct create_idle *c_idle =
+		container_of(work, struct create_idle, work);
 
 	c_idle->idle = fork_idle(c_idle->cpu);
 	complete(&c_idle->done);
@@ -775,10 +777,10 @@ static int __cpuinit do_boot_cpu(int cpu, int apicid)
 	int timeout;
 	unsigned long start_rip;
 	struct create_idle c_idle = {
+		.work = __WORK_INITIALIZER(c_idle.work, do_fork_idle),
 		.cpu = cpu,
 		.done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done),
 	};
-	DECLARE_WORK(work, do_fork_idle, &c_idle);
 
 	/* allocate memory for gdts of secondary cpus. Hotplug is considered */
 	if (!cpu_gdt_descr[cpu].address &&
@@ -825,9 +827,9 @@ static int __cpuinit do_boot_cpu(int cpu, int apicid)
 	 * thread.
 	 */
 	if (!keventd_up() || current_is_keventd())
-		work.func(work.data);
+		c_idle.work.func(&c_idle.work);
 	else {
-		schedule_work(&work);
+		schedule_work(&c_idle.work);
 		wait_for_completion(&c_idle.done);
 	}
 
diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c
index e3ef544..9f05bc9 100644
--- a/arch/x86_64/kernel/time.c
+++ b/arch/x86_64/kernel/time.c
@@ -563,7 +563,7 @@ static unsigned int cpufreq_delayed_issched = 0;
 static unsigned int cpufreq_init = 0;
 static struct work_struct cpufreq_delayed_get_work;
 
-static void handle_cpufreq_delayed_get(void *v)
+static void handle_cpufreq_delayed_get(struct work_struct *v)
 {
 	unsigned int cpu;
 	for_each_online_cpu(cpu) {
@@ -639,7 +639,7 @@ static struct notifier_block time_cpufreq_notifier_block = {
 
 static int __init cpufreq_tsc(void)
 {
-	INIT_WORK(&cpufreq_delayed_get_work, handle_cpufreq_delayed_get, NULL);
+	INIT_WORK(&cpufreq_delayed_get_work, handle_cpufreq_delayed_get);
 	if (!cpufreq_register_notifier(&time_cpufreq_notifier_block,
 				       CPUFREQ_TRANSITION_NOTIFIER))
 		cpufreq_init = 1;