Merge branch 'for-3.15/core' of git://git.kernel.dk/linux-block

Pull core block layer updates from Jens Axboe:
 "This is the pull request for the core block IO bits for the 3.15
  kernel.  It's a smaller round this time, it contains:

   - Various little blk-mq fixes and additions from Christoph and
     myself.

   - Cleanup of the IPI usage from the block layer, and associated
     helper code.  From Frederic Weisbecker and Jan Kara.

   - Duplicate code cleanup in bio-integrity from Gu Zheng.  This will
     give you a merge conflict, but that should be easy to resolve.

   - blk-mq notify spinlock fix for RT from Mike Galbraith.

   - A blktrace partial accounting bug fix from Roman Pen.

   - Missing REQ_SYNC detection fix for blk-mq from Shaohua Li"

* 'for-3.15/core' of git://git.kernel.dk/linux-block: (25 commits)
  blk-mq: add REQ_SYNC early
  rt,blk,mq: Make blk_mq_cpu_notify_lock a raw spinlock
  blk-mq: support partial I/O completions
  blk-mq: merge blk_mq_insert_request and blk_mq_run_request
  blk-mq: remove blk_mq_alloc_rq
  blk-mq: don't dump CPU -> hw queue map on driver load
  blk-mq: fix wrong usage of hctx->state vs hctx->flags
  blk-mq: allow blk_mq_init_commands() to return failure
  block: remove old blk_iopoll_enabled variable
  blktrace: fix accounting of partially completed requests
  smp: Rename __smp_call_function_single() to smp_call_function_single_async()
  smp: Remove wait argument from __smp_call_function_single()
  watchdog: Simplify a little the IPI call
  smp: Move __smp_call_function_single() below its safe version
  smp: Consolidate the various smp_call_function_single() declensions
  smp: Teach __smp_call_function_single() to check for offline cpus
  smp: Remove unused list_head from csd
  smp: Iterate functions through llist_for_each_entry_safe()
  block: Stop abusing rq->csd.list in blk-softirq
  block: Remove useless IPI struct initialization
  ...

6 files changed, 81 insertions, 101 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3c4d096544c..9cae286824b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -432,7 +432,7 @@ void hrtick_start(struct rq *rq, u64 delay)
 	if (rq == this_rq()) {
 		__hrtick_restart(rq);
 	} else if (!rq->hrtick_csd_pending) {
-		__smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0);
+		smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd);
 		rq->hrtick_csd_pending = 1;
 	}
 }
diff --git a/kernel/smp.c b/kernel/smp.c
index ffee35bef17..06d574e42c7 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -117,13 +117,43 @@ static void csd_unlock(struct call_single_data *csd)
 	csd->flags &= ~CSD_FLAG_LOCK;
 }
 
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);
+
 /*
  * Insert a previously allocated call_single_data element
  * for execution on the given CPU. data must already have
  * ->func, ->info, and ->flags set.
  */
-static void generic_exec_single(int cpu, struct call_single_data *csd, int wait)
+static int generic_exec_single(int cpu, struct call_single_data *csd,
+			       smp_call_func_t func, void *info, int wait)
 {
+	struct call_single_data csd_stack = { .flags = 0 };
+	unsigned long flags;
+
+
+	if (cpu == smp_processor_id()) {
+		local_irq_save(flags);
+		func(info);
+		local_irq_restore(flags);
+		return 0;
+	}
+
+
+	if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu))
+		return -ENXIO;
+
+
+	if (!csd) {
+		csd = &csd_stack;
+		if (!wait)
+			csd = &__get_cpu_var(csd_data);
+	}
+
+	csd_lock(csd);
+
+	csd->func = func;
+	csd->info = info;
+
 	if (wait)
 		csd->flags |= CSD_FLAG_WAIT;
 
@@ -143,6 +173,8 @@ static void generic_exec_single(int cpu, struct call_single_data *csd, int wait)
 
 	if (wait)
 		csd_lock_wait(csd);
+
+	return 0;
 }
 
 /*
@@ -151,7 +183,8 @@ static void generic_exec_single(int cpu, struct call_single_data *csd, int wait)
  */
 void generic_smp_call_function_single_interrupt(void)
 {
-	struct llist_node *entry, *next;
+	struct llist_node *entry;
+	struct call_single_data *csd, *csd_next;
 
 	/*
 	 * Shouldn't receive this interrupt on a cpu that is not yet online.
@@ -161,21 +194,12 @@ void generic_smp_call_function_single_interrupt(void)
 	entry = llist_del_all(&__get_cpu_var(call_single_queue));
 	entry = llist_reverse_order(entry);
 
-	while (entry) {
-		struct call_single_data *csd;
-
-		next = entry->next;
-
-		csd = llist_entry(entry, struct call_single_data, llist);
+	llist_for_each_entry_safe(csd, csd_next, entry, llist) {
 		csd->func(csd->info);
 		csd_unlock(csd);
-
-		entry = next;
 	}
 }
 
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);
-
 /*
  * smp_call_function_single - Run a function on a specific CPU
  * @func: The function to run. This must be fast and non-blocking.
@@ -187,12 +211,8 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);
 int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
 			     int wait)
 {
-	struct call_single_data d = {
-		.flags = 0,
-	};
-	unsigned long flags;
 	int this_cpu;
-	int err = 0;
+	int err;
 
 	/*
 	 * prevent preemption and reschedule on another processor,
@@ -209,32 +229,41 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
 	WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled()
 		     && !oops_in_progress);
 
-	if (cpu == this_cpu) {
-		local_irq_save(flags);
-		func(info);
-		local_irq_restore(flags);
-	} else {
-		if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
-			struct call_single_data *csd = &d;
+	err = generic_exec_single(cpu, NULL, func, info, wait);
 
-			if (!wait)
-				csd = &__get_cpu_var(csd_data);
+	put_cpu();
 
-			csd_lock(csd);
+	return err;
+}
+EXPORT_SYMBOL(smp_call_function_single);
 
-			csd->func = func;
-			csd->info = info;
-			generic_exec_single(cpu, csd, wait);
-		} else {
-			err = -ENXIO;	/* CPU not online */
-		}
-	}
+/**
+ * smp_call_function_single_async(): Run an asynchronous function on a
+ * 			         specific CPU.
+ * @cpu: The CPU to run on.
+ * @csd: Pre-allocated and setup data structure
+ *
+ * Like smp_call_function_single(), but the call is asynchonous and
+ * can thus be done from contexts with disabled interrupts.
+ *
+ * The caller passes his own pre-allocated data structure
+ * (ie: embedded in an object) and is responsible for synchronizing it
+ * such that the IPIs performed on the @csd are strictly serialized.
+ *
+ * NOTE: Be careful, there is unfortunately no current debugging facility to
+ * validate the correctness of this serialization.
+ */
+int smp_call_function_single_async(int cpu, struct call_single_data *csd)
+{
+	int err = 0;
 
-	put_cpu();
+	preempt_disable();
+	err = generic_exec_single(cpu, csd, csd->func, csd->info, 0);
+	preempt_enable();
 
 	return err;
 }
-EXPORT_SYMBOL(smp_call_function_single);
+EXPORT_SYMBOL_GPL(smp_call_function_single_async);
 
 /*
  * smp_call_function_any - Run a function on any of the given cpus
@@ -280,44 +309,6 @@ call:
 EXPORT_SYMBOL_GPL(smp_call_function_any);
 
 /**
- * __smp_call_function_single(): Run a function on a specific CPU
- * @cpu: The CPU to run on.
- * @data: Pre-allocated and setup data structure
- * @wait: If true, wait until function has completed on specified CPU.
- *
- * Like smp_call_function_single(), but allow caller to pass in a
- * pre-allocated data structure. Useful for embedding @data inside
- * other structures, for instance.
- */
-void __smp_call_function_single(int cpu, struct call_single_data *csd,
-				int wait)
-{
-	unsigned int this_cpu;
-	unsigned long flags;
-
-	this_cpu = get_cpu();
-	/*
-	 * 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()
-		     && !oops_in_progress);
-
-	if (cpu == this_cpu) {
-		local_irq_save(flags);
-		csd->func(csd->info);
-		local_irq_restore(flags);
-	} else {
-		csd_lock(csd);
-		generic_exec_single(cpu, csd, wait);
-	}
-	put_cpu();
-}
-EXPORT_SYMBOL_GPL(__smp_call_function_single);
-
-/**
  * smp_call_function_many(): Run a function on a set of other CPUs.
  * @mask: The set of cpus to run on (only runs on online subset).
  * @func: The function to run. This must be fast and non-blocking.
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 7754ff16f33..09d2e241360 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -112,9 +112,6 @@ extern int sysctl_nr_open_min, sysctl_nr_open_max;
 #ifndef CONFIG_MMU
 extern int sysctl_nr_trim_pages;
 #endif
-#ifdef CONFIG_BLOCK
-extern int blk_iopoll_enabled;
-#endif
 
 /* Constants used for minimum and  maximum */
 #ifdef CONFIG_LOCKUP_DETECTOR
@@ -1087,15 +1084,6 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-#ifdef CONFIG_BLOCK
-	{
-		.procname	= "blk_iopoll",
-		.data		= &blk_iopoll_enabled,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-#endif
 	{ }
 };
 
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index b418cb0d724..4f3a3c03ead 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -702,6 +702,7 @@ void blk_trace_shutdown(struct request_queue *q)
  * blk_add_trace_rq - Add a trace for a request oriented action
  * @q:		queue the io is for
  * @rq:		the source request
+ * @nr_bytes:	number of completed bytes
  * @what:	the action
  *
  * Description:
@@ -709,7 +710,7 @@ void blk_trace_shutdown(struct request_queue *q)
  *
  **/
 static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
-			     u32 what)
+			     unsigned int nr_bytes, u32 what)
 {
 	struct blk_trace *bt = q->blk_trace;
 
@@ -718,11 +719,11 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
 
 	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
 		what |= BLK_TC_ACT(BLK_TC_PC);
-		__blk_add_trace(bt, 0, blk_rq_bytes(rq), rq->cmd_flags,
+		__blk_add_trace(bt, 0, nr_bytes, rq->cmd_flags,
 				what, rq->errors, rq->cmd_len, rq->cmd);
 	} else  {
 		what |= BLK_TC_ACT(BLK_TC_FS);
-		__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
+		__blk_add_trace(bt, blk_rq_pos(rq), nr_bytes,
 				rq->cmd_flags, what, rq->errors, 0, NULL);
 	}
 }
@@ -730,33 +731,34 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
 static void blk_add_trace_rq_abort(void *ignore,
 				   struct request_queue *q, struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_ABORT);
+	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ABORT);
 }
 
 static void blk_add_trace_rq_insert(void *ignore,
 				    struct request_queue *q, struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_INSERT);
+	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_INSERT);
 }
 
 static void blk_add_trace_rq_issue(void *ignore,
 				   struct request_queue *q, struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
+	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ISSUE);
 }
 
 static void blk_add_trace_rq_requeue(void *ignore,
 				     struct request_queue *q,
 				     struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
+	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_REQUEUE);
 }
 
 static void blk_add_trace_rq_complete(void *ignore,
 				      struct request_queue *q,
-				      struct request *rq)
+				      struct request *rq,
+				      unsigned int nr_bytes)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
+	blk_add_trace_rq(q, rq, nr_bytes, BLK_TA_COMPLETE);
 }
 
 /**
diff --git a/kernel/up.c b/kernel/up.c
index 509403e3fbc..1760bf3d146 100644
--- a/kernel/up.c
+++ b/kernel/up.c
@@ -22,16 +22,16 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 }
 EXPORT_SYMBOL(smp_call_function_single);
 
-void __smp_call_function_single(int cpu, struct call_single_data *csd,
-				int wait)
+int smp_call_function_single_async(int cpu, struct call_single_data *csd)
 {
 	unsigned long flags;
 
 	local_irq_save(flags);
 	csd->func(csd->info);
 	local_irq_restore(flags);
+	return 0;
 }
-EXPORT_SYMBOL(__smp_call_function_single);
+EXPORT_SYMBOL(smp_call_function_single_async);
 
 int on_each_cpu(smp_call_func_t func, void *info, int wait)
 {
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 4431610f049..01c6f979486 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -505,7 +505,6 @@ static void restart_watchdog_hrtimer(void *info)
 
 static void update_timers(int cpu)
 {
-	struct call_single_data data = {.func = restart_watchdog_hrtimer};
 	/*
 	 * Make sure that perf event counter will adopt to a new
 	 * sampling period. Updating the sampling period directly would
@@ -515,7 +514,7 @@ static void update_timers(int cpu)
 	 * might be late already so we have to restart the timer as well.
 	 */
 	watchdog_nmi_disable(cpu);
-	__smp_call_function_single(cpu, &data, 1);
+	smp_call_function_single(cpu, restart_watchdog_hrtimer, NULL, 1);
 	watchdog_nmi_enable(cpu);
 }