block: add blk-iopoll, a NAPI like approach for block devices

This borrows some code from NAPI and implements a polled completion
mode for block devices. The idea is the same as NAPI - instead of
doing the command completion when the irq occurs, schedule a dedicated
softirq in the hopes that we will complete more IO when the iopoll
handler is invoked. Devices have a budget of commands assigned, and will
stay in polled mode as long as they continue to consume their budget
from the iopoll softirq handler. If they do not, the device is set back
to interrupt completion mode.

This patch holds the core bits for blk-iopoll, device driver support
sold separately.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

5 files changed, 272 insertions, 2 deletions

diff --git a/block/Makefile b/block/Makefile
index 6c54ed0..ba74ca6 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -5,7 +5,7 @@
 obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-barrier.o blk-settings.o blk-ioc.o blk-map.o \
 			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
-			ioctl.o genhd.o scsi_ioctl.o
+			blk-iopoll.o ioctl.o genhd.o scsi_ioctl.o
 
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
diff --git a/block/blk-iopoll.c b/block/blk-iopoll.c
new file mode 100644
index 0000000..566db1e
--- /dev/null
+++ b/block/blk-iopoll.c
@@ -0,0 +1,220 @@
+/*
+ * Functions related to interrupt-poll handling in the block layer. This
+ * is similar to NAPI for network devices.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/interrupt.h>
+#include <linux/cpu.h>
+#include <linux/blk-iopoll.h>
+#include <linux/delay.h>
+
+#include "blk.h"
+
+int blk_iopoll_enabled = 1;
+EXPORT_SYMBOL(blk_iopoll_enabled);
+
+static DEFINE_PER_CPU(struct list_head, blk_cpu_iopoll);
+
+/**
+ * blk_iopoll_sched - Schedule a run of the iopoll handler
+ * @iop:      The parent iopoll structure
+ *
+ * Description:
+ *     Add this blk_iopoll structure to the pending poll list and trigger the raise
+ *     of the blk iopoll softirq. The driver must already have gotten a succesful
+ *     return from blk_iopoll_sched_prep() before calling this.
+ **/
+void blk_iopoll_sched(struct blk_iopoll *iop)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	list_add_tail(&iop->list, &__get_cpu_var(blk_cpu_iopoll));
+	__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(blk_iopoll_sched);
+
+/**
+ * __blk_iopoll_complete - Mark this @iop as un-polled again
+ * @iop:      The parent iopoll structure
+ *
+ * Description:
+ *     See blk_iopoll_complete(). This function must be called with interrupts disabled.
+ **/
+void __blk_iopoll_complete(struct blk_iopoll *iop)
+{
+	list_del(&iop->list);
+	smp_mb__before_clear_bit();
+	clear_bit_unlock(IOPOLL_F_SCHED, &iop->state);
+}
+EXPORT_SYMBOL(__blk_iopoll_complete);
+
+/**
+ * blk_iopoll_complete - Mark this @iop as un-polled again
+ * @iop:      The parent iopoll structure
+ *
+ * Description:
+ *     If a driver consumes less than the assigned budget in its run of the iopoll
+ *     handler, it'll end the polled mode by calling this function. The iopoll handler
+ *     will not be invoked again before blk_iopoll_sched_prep() is called.
+ **/
+void blk_iopoll_complete(struct blk_iopoll *iopoll)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__blk_iopoll_complete(iopoll);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(blk_iopoll_complete);
+
+static void blk_iopoll_softirq(struct softirq_action *h)
+{
+	struct list_head *list = &__get_cpu_var(blk_cpu_iopoll);
+	unsigned long start_time = jiffies;
+	int rearm = 0, budget = 64;
+
+	local_irq_disable();
+
+	while (!list_empty(list)) {
+		struct blk_iopoll *iop;
+		int work, weight;
+
+		/*
+		 * If softirq window is exhausted then punt.
+		 */
+		if (budget <= 0 || time_after(jiffies, start_time)) {
+			rearm = 1;
+			break;
+		}
+
+		local_irq_enable();
+
+		/* Even though interrupts have been re-enabled, this
+		 * access is safe because interrupts can only add new
+		 * entries to the tail of this list, and only ->poll()
+		 * calls can remove this head entry from the list.
+		 */
+		iop = list_entry(list->next, struct blk_iopoll, list);
+
+		weight = iop->weight;
+		work = 0;
+		if (test_bit(IOPOLL_F_SCHED, &iop->state))
+			work = iop->poll(iop, weight);
+
+		budget -= work;
+
+		local_irq_disable();
+
+		/* Drivers must not modify the NAPI state if they
+		 * consume the entire weight.  In such cases this code
+		 * still "owns" the NAPI instance and therefore can
+		 * move the instance around on the list at-will.
+		 */
+		if (work >= weight) {
+			if (blk_iopoll_disable_pending(iop))
+				__blk_iopoll_complete(iop);
+			else
+				list_move_tail(&iop->list, list);
+		}
+	}
+
+	if (rearm)
+		__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
+
+	local_irq_enable();
+}
+
+/**
+ * blk_iopoll_disable - Disable iopoll on this @iop
+ * @iop:      The parent iopoll structure
+ *
+ * Description:
+ *     Disable io polling and wait for any pending callbacks to have completed.
+ **/
+void blk_iopoll_disable(struct blk_iopoll *iop)
+{
+	set_bit(IOPOLL_F_DISABLE, &iop->state);
+	while (test_and_set_bit(IOPOLL_F_SCHED, &iop->state))
+		msleep(1);
+	clear_bit(IOPOLL_F_DISABLE, &iop->state);
+}
+EXPORT_SYMBOL(blk_iopoll_disable);
+
+/**
+ * blk_iopoll_enable - Enable iopoll on this @iop
+ * @iop:      The parent iopoll structure
+ *
+ * Description:
+ *     Enable iopoll on this @iop. Note that the handler run will not be scheduled, it
+ *     will only mark it as active.
+ **/
+void blk_iopoll_enable(struct blk_iopoll *iop)
+{
+	BUG_ON(!test_bit(IOPOLL_F_SCHED, &iop->state));
+        smp_mb__before_clear_bit();
+	clear_bit_unlock(IOPOLL_F_SCHED, &iop->state);
+}
+EXPORT_SYMBOL(blk_iopoll_enable);
+
+/**
+ * blk_iopoll_init - Initialize this @iop
+ * @iop:      The parent iopoll structure
+ * @weight:   The default weight (or command completion budget)
+ * @poll_fn:  The handler to invoke
+ *
+ * Description:
+ *     Initialize this blk_iopoll structure. Before being actively used, the driver
+ *     must call blk_iopoll_enable().
+ **/
+void blk_iopoll_init(struct blk_iopoll *iop, int weight, blk_iopoll_fn *poll_fn)
+{
+	memset(iop, 0, sizeof(*iop));
+	INIT_LIST_HEAD(&iop->list);
+	iop->weight = weight;
+	iop->poll = poll_fn;
+	set_bit(IOPOLL_F_SCHED, &iop->state);
+}
+EXPORT_SYMBOL(blk_iopoll_init);
+
+static int __cpuinit blk_iopoll_cpu_notify(struct notifier_block *self,
+					  unsigned long action, void *hcpu)
+{
+	/*
+	 * If a CPU goes away, splice its entries to the current CPU
+	 * and trigger a run of the softirq
+	 */
+	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
+		int cpu = (unsigned long) hcpu;
+
+		local_irq_disable();
+		list_splice_init(&per_cpu(blk_cpu_iopoll, cpu),
+				 &__get_cpu_var(blk_cpu_iopoll));
+		raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
+		local_irq_enable();
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata blk_iopoll_cpu_notifier = {
+	.notifier_call	= blk_iopoll_cpu_notify,
+};
+
+static __init int blk_iopoll_setup(void)
+{
+	int i;
+
+	for_each_possible_cpu(i)
+		INIT_LIST_HEAD(&per_cpu(blk_cpu_iopoll, i));
+
+	open_softirq(BLOCK_IOPOLL_SOFTIRQ, blk_iopoll_softirq);
+	register_hotcpu_notifier(&blk_iopoll_cpu_notifier);
+	return 0;
+}
+subsys_initcall(blk_iopoll_setup);
diff --git a/include/linux/blk-iopoll.h b/include/linux/blk-iopoll.h
new file mode 100644
index 0000000..b2e1739
--- /dev/null
+++ b/include/linux/blk-iopoll.h
@@ -0,0 +1,41 @@
+#ifndef BLK_IOPOLL_H
+#define BLK_IOPOLL_H
+
+struct blk_iopoll;
+typedef int (blk_iopoll_fn)(struct blk_iopoll *, int);
+
+struct blk_iopoll {
+	struct list_head list;
+	unsigned long state;
+	unsigned long data;
+	int weight;
+	int max;
+	blk_iopoll_fn *poll;
+};
+
+enum {
+	IOPOLL_F_SCHED		= 0,
+	IOPOLL_F_DISABLE	= 1,
+};
+
+static inline int blk_iopoll_sched_prep(struct blk_iopoll *iop)
+{
+	return !test_bit(IOPOLL_F_DISABLE, &iop->state) &&
+		!test_and_set_bit(IOPOLL_F_SCHED, &iop->state);
+}
+
+static inline int blk_iopoll_disable_pending(struct blk_iopoll *iop)
+{
+	return test_bit(IOPOLL_F_DISABLE, &iop->state);
+}
+
+extern void blk_iopoll_sched(struct blk_iopoll *);
+extern void blk_iopoll_init(struct blk_iopoll *, int, blk_iopoll_fn *);
+extern void blk_iopoll_complete(struct blk_iopoll *);
+extern void __blk_iopoll_complete(struct blk_iopoll *);
+extern void blk_iopoll_enable(struct blk_iopoll *);
+extern void blk_iopoll_disable(struct blk_iopoll *);
+
+extern int blk_iopoll_enabled;
+
+#endif
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 35e7df1..edd8d5c 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -344,6 +344,7 @@ enum
 	NET_TX_SOFTIRQ,
 	NET_RX_SOFTIRQ,
 	BLOCK_SOFTIRQ,
+	BLOCK_IOPOLL_SOFTIRQ,
 	TASKLET_SOFTIRQ,
 	SCHED_SOFTIRQ,
 	HRTIMER_SOFTIRQ,
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 58be760..0ed9fa6 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -92,6 +92,7 @@ extern int sysctl_nr_trim_pages;
 #ifdef CONFIG_RCU_TORTURE_TEST
 extern int rcutorture_runnable;
 #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
+extern int blk_iopoll_enabled;
 
 /* Constants used for minimum and  maximum */
 #ifdef CONFIG_DETECT_SOFTLOCKUP
@@ -990,7 +991,14 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= &proc_dointvec,
 	},
 #endif
-
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "blk_iopoll",
+		.data		= &blk_iopoll_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt