Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma

Pull rdma updates from Doug Ledford:
 "Initial roundup of 4.5 merge window patches

   - Remove usage of ib_query_device and instead store attributes in
     ib_device struct

   - Move iopoll out of block and into lib, rename to irqpoll, and use
     in several places in the rdma stack as our new completion queue
     polling library mechanism.  Update the other block drivers that
     already used iopoll to use the new mechanism too.

   - Replace the per-entry GID table locks with a single GID table lock

   - IPoIB multicast cleanup

   - Cleanups to the IB MR facility

   - Add support for 64bit extended IB counters

   - Fix for netlink oops while parsing RDMA nl messages

   - RoCEv2 support for the core IB code

   - mlx4 RoCEv2 support

   - mlx5 RoCEv2 support

   - Cross Channel support for mlx5

   - Timestamp support for mlx5

   - Atomic support for mlx5

   - Raw QP support for mlx5

   - MAINTAINERS update for mlx4/mlx5

   - Misc ocrdma, qib, nes, usNIC, cxgb3, cxgb4, mlx4, mlx5 updates

   - Add support for remote invalidate to the iSER driver (pushed
     through the RDMA tree due to dependencies, acknowledged by nab)

   - Update to NFSoRDMA (pushed through the RDMA tree due to
     dependencies, acknowledged by Bruce)"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (169 commits)
  IB/mlx5: Unify CQ create flags check
  IB/mlx5: Expose Raw Packet QP to user space consumers
  {IB, net}/mlx5: Move the modify QP operation table to mlx5_ib
  IB/mlx5: Support setting Ethernet priority for Raw Packet QPs
  IB/mlx5: Add Raw Packet QP query functionality
  IB/mlx5: Add create and destroy functionality for Raw Packet QP
  IB/mlx5: Refactor mlx5_ib_qp to accommodate other QP types
  IB/mlx5: Allocate a Transport Domain for each ucontext
  net/mlx5_core: Warn on unsupported events of QP/RQ/SQ
  net/mlx5_core: Add RQ and SQ event handling
  net/mlx5_core: Export transport objects
  IB/mlx5: Expose CQE version to user-space
  IB/mlx5: Add CQE version 1 support to user QPs and SRQs
  IB/mlx5: Fix data validation in mlx5_ib_alloc_ucontext
  IB/sa: Fix netlink local service GFP crash
  IB/srpt: Remove redundant wc array
  IB/qib: Improve ipoib UD performance
  IB/mlx4: Advertise RoCE v2 support
  IB/mlx4: Create and use another QP1 for RoCEv2
  IB/mlx4: Enable send of RoCE QP1 packets with IP/UDP headers
  ...

3 files changed, 228 insertions, 0 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index 435f731..133ebc0 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -477,6 +477,11 @@ config DDR
 	  information. This data is useful for drivers handling
 	  DDR SDRAM controllers.
 
+config IRQ_POLL
+	bool "IRQ polling library"
+	help
+	  Helper library to poll interrupt mitigation using polling.
+
 config MPILIB
 	tristate
 	select CLZ_TAB
diff --git a/lib/Makefile b/lib/Makefile
index 2d4bc33..a7c26a4 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -165,6 +165,7 @@ obj-$(CONFIG_GENERIC_NET_UTILS) += net_utils.o
 
 obj-$(CONFIG_SG_SPLIT) += sg_split.o
 obj-$(CONFIG_STMP_DEVICE) += stmp_device.o
+obj-$(CONFIG_IRQ_POLL) += irq_poll.o
 
 libfdt_files = fdt.o fdt_ro.o fdt_wip.o fdt_rw.o fdt_sw.o fdt_strerror.o \
 	       fdt_empty_tree.o
diff --git a/lib/irq_poll.c b/lib/irq_poll.c
new file mode 100644
index 0000000..836f7db
--- /dev/null
+++ b/lib/irq_poll.c
@@ -0,0 +1,222 @@
+/*
+ * 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/interrupt.h>
+#include <linux/cpu.h>
+#include <linux/irq_poll.h>
+#include <linux/delay.h>
+
+static unsigned int irq_poll_budget __read_mostly = 256;
+
+static DEFINE_PER_CPU(struct list_head, blk_cpu_iopoll);
+
+/**
+ * irq_poll_sched - Schedule a run of the iopoll handler
+ * @iop:      The parent iopoll structure
+ *
+ * Description:
+ *     Add this irq_poll structure to the pending poll list and trigger the
+ *     raise of the blk iopoll softirq.
+ **/
+void irq_poll_sched(struct irq_poll *iop)
+{
+	unsigned long flags;
+
+	if (test_bit(IRQ_POLL_F_DISABLE, &iop->state))
+		return;
+	if (test_and_set_bit(IRQ_POLL_F_SCHED, &iop->state))
+		return;
+
+	local_irq_save(flags);
+	list_add_tail(&iop->list, this_cpu_ptr(&blk_cpu_iopoll));
+	__raise_softirq_irqoff(IRQ_POLL_SOFTIRQ);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(irq_poll_sched);
+
+/**
+ * __irq_poll_complete - Mark this @iop as un-polled again
+ * @iop:      The parent iopoll structure
+ *
+ * Description:
+ *     See irq_poll_complete(). This function must be called with interrupts
+ *     disabled.
+ **/
+static void __irq_poll_complete(struct irq_poll *iop)
+{
+	list_del(&iop->list);
+	smp_mb__before_atomic();
+	clear_bit_unlock(IRQ_POLL_F_SCHED, &iop->state);
+}
+
+/**
+ * irq_poll_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 irq_poll_sched()
+ *     is called.
+ **/
+void irq_poll_complete(struct irq_poll *iop)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__irq_poll_complete(iop);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(irq_poll_complete);
+
+static void irq_poll_softirq(struct softirq_action *h)
+{
+	struct list_head *list = this_cpu_ptr(&blk_cpu_iopoll);
+	int rearm = 0, budget = irq_poll_budget;
+	unsigned long start_time = jiffies;
+
+	local_irq_disable();
+
+	while (!list_empty(list)) {
+		struct irq_poll *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 irq_poll, list);
+
+		weight = iop->weight;
+		work = 0;
+		if (test_bit(IRQ_POLL_F_SCHED, &iop->state))
+			work = iop->poll(iop, weight);
+
+		budget -= work;
+
+		local_irq_disable();
+
+		/*
+		 * Drivers must not modify the iopoll state, if they
+		 * consume their assigned weight (or more, some drivers can't
+		 * easily just stop processing, they have to complete an
+		 * entire mask of commands).In such cases this code
+		 * still "owns" the iopoll instance and therefore can
+		 * move the instance around on the list at-will.
+		 */
+		if (work >= weight) {
+			if (test_bit(IRQ_POLL_F_DISABLE, &iop->state))
+				__irq_poll_complete(iop);
+			else
+				list_move_tail(&iop->list, list);
+		}
+	}
+
+	if (rearm)
+		__raise_softirq_irqoff(IRQ_POLL_SOFTIRQ);
+
+	local_irq_enable();
+}
+
+/**
+ * irq_poll_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 irq_poll_disable(struct irq_poll *iop)
+{
+	set_bit(IRQ_POLL_F_DISABLE, &iop->state);
+	while (test_and_set_bit(IRQ_POLL_F_SCHED, &iop->state))
+		msleep(1);
+	clear_bit(IRQ_POLL_F_DISABLE, &iop->state);
+}
+EXPORT_SYMBOL(irq_poll_disable);
+
+/**
+ * irq_poll_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 irq_poll_enable(struct irq_poll *iop)
+{
+	BUG_ON(!test_bit(IRQ_POLL_F_SCHED, &iop->state));
+	smp_mb__before_atomic();
+	clear_bit_unlock(IRQ_POLL_F_SCHED, &iop->state);
+}
+EXPORT_SYMBOL(irq_poll_enable);
+
+/**
+ * irq_poll_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 and enable this irq_poll structure.
+ **/
+void irq_poll_init(struct irq_poll *iop, int weight, irq_poll_fn *poll_fn)
+{
+	memset(iop, 0, sizeof(*iop));
+	INIT_LIST_HEAD(&iop->list);
+	iop->weight = weight;
+	iop->poll = poll_fn;
+}
+EXPORT_SYMBOL(irq_poll_init);
+
+static int irq_poll_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),
+				 this_cpu_ptr(&blk_cpu_iopoll));
+		__raise_softirq_irqoff(IRQ_POLL_SOFTIRQ);
+		local_irq_enable();
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block irq_poll_cpu_notifier = {
+	.notifier_call	= irq_poll_cpu_notify,
+};
+
+static __init int irq_poll_setup(void)
+{
+	int i;
+
+	for_each_possible_cpu(i)
+		INIT_LIST_HEAD(&per_cpu(blk_cpu_iopoll, i));
+
+	open_softirq(IRQ_POLL_SOFTIRQ, irq_poll_softirq);
+	register_hotcpu_notifier(&irq_poll_cpu_notifier);
+	return 0;
+}
+subsys_initcall(irq_poll_setup);