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>

1 files changed, 41 insertions, 0 deletions

diff --git a/include/linux/blk-iopoll.h b/include/linux/blk-iopoll.h
new file mode 100644
index 000000000000..b2e1739a2e7b
--- /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