Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending

Pull SCSI target updates from Nicholas Bellinger:
 "Lots of activity again this round for I/O performance optimizations
  (per-cpu IDA pre-allocation for vhost + iscsi/target), and the
  addition of new fabric independent features to target-core
  (COMPARE_AND_WRITE + EXTENDED_COPY).

  The main highlights include:

   - Support for iscsi-target login multiplexing across individual
     network portals
   - Generic Per-cpu IDA logic (kent + akpm + clameter)
   - Conversion of vhost to use per-cpu IDA pre-allocation for
     descriptors, SGLs and userspace page pointer list
   - Conversion of iscsi-target + iser-target to use per-cpu IDA
     pre-allocation for descriptors
   - Add support for generic COMPARE_AND_WRITE (AtomicTestandSet)
     emulation for virtual backend drivers
   - Add support for generic EXTENDED_COPY (CopyOffload) emulation for
     virtual backend drivers.
   - Add support for fast memory registration mode to iser-target (Vu)

  The patches to add COMPARE_AND_WRITE and EXTENDED_COPY support are of
  particular significance, which make us the first and only open source
  target to support the full set of VAAI primitives.

  Currently Linux clients are lacking upstream support to actually
  utilize these primitives.  However, with server side support now in
  place for folks like MKP + ZAB working on the client, this logic once
  reserved for the highest end of storage arrays, can now be run in VMs
  on their laptops"

* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending: (50 commits)
  target/iscsi: Bump versions to v4.1.0
  target: Update copyright ownership/year information to 2013
  iscsi-target: Bump default TCP listen backlog to 256
  target: Fix >= v3.9+ regression in PR APTPL + ALUA metadata write-out
  iscsi-target; Bump default CmdSN Depth to 64
  iscsi-target: Remove unnecessary wait_for_completion in iscsi_get_thread_set
  iscsi-target: Add thread_set->ts_activate_sem + use common deallocate
  iscsi-target: Fix race with thread_pre_handler flush_signals + ISCSI_THREAD_SET_DIE
  target: remove unused including <linux/version.h>
  iser-target: introduce fast memory registration mode (FRWR)
  iser-target: generalize rdma memory registration and cleanup
  iser-target: move rdma wr processing to a shared function
  target: Enable global EXTENDED_COPY setup/release
  target: Add Third Party Copy (3PC) bit in INQUIRY response
  target: Enable EXTENDED_COPY setup in spc_parse_cdb
  target: Add support for EXTENDED_COPY copy offload emulation
  target: Avoid non-existent tg_pt_gp_mem in target_alua_state_check
  target: Add global device list for EXTENDED_COPY
  target: Make helpers non static for EXTENDED_COPY command setup
  target: Make spc_parse_naa_6h_vendor_specific non static
  ...

2 files changed, 338 insertions, 2 deletions

diff --git a/lib/Makefile b/lib/Makefile
index f2cb3082697c..f3bb2cb98adf 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -13,7 +13,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \
 	 proportions.o flex_proportions.o prio_heap.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
-	 earlycpio.o percpu-refcount.o
+	 earlycpio.o percpu-refcount.o percpu_ida.o
 
 obj-$(CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS) += usercopy.o
 lib-$(CONFIG_MMU) += ioremap.o
@@ -25,7 +25,8 @@ obj-y	+= lockref.o
 obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
 	 bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
 	 gcd.o lcm.o list_sort.o uuid.o flex_array.o iovec.o clz_ctz.o \
-	 bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o
+	 bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o \
+	 percpu_ida.o
 obj-y += string_helpers.o
 obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o
 obj-y += kstrtox.o
diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
new file mode 100644
index 000000000000..bab1ba2a4c71
--- /dev/null
+++ b/lib/percpu_ida.c
@@ -0,0 +1,335 @@
+/*
+ * Percpu IDA library
+ *
+ * Copyright (C) 2013 Datera, Inc. Kent Overstreet
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2, or (at
+ * your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/bug.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/hardirq.h>
+#include <linux/idr.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/spinlock.h>
+#include <linux/percpu_ida.h>
+
+/*
+ * Number of tags we move between the percpu freelist and the global freelist at
+ * a time
+ */
+#define IDA_PCPU_BATCH_MOVE	32U
+
+/* Max size of percpu freelist, */
+#define IDA_PCPU_SIZE		((IDA_PCPU_BATCH_MOVE * 3) / 2)
+
+struct percpu_ida_cpu {
+	/*
+	 * Even though this is percpu, we need a lock for tag stealing by remote
+	 * CPUs:
+	 */
+	spinlock_t			lock;
+
+	/* nr_free/freelist form a stack of free IDs */
+	unsigned			nr_free;
+	unsigned			freelist[];
+};
+
+static inline void move_tags(unsigned *dst, unsigned *dst_nr,
+			     unsigned *src, unsigned *src_nr,
+			     unsigned nr)
+{
+	*src_nr -= nr;
+	memcpy(dst + *dst_nr, src + *src_nr, sizeof(unsigned) * nr);
+	*dst_nr += nr;
+}
+
+/*
+ * Try to steal tags from a remote cpu's percpu freelist.
+ *
+ * We first check how many percpu freelists have tags - we don't steal tags
+ * unless enough percpu freelists have tags on them that it's possible more than
+ * half the total tags could be stuck on remote percpu freelists.
+ *
+ * Then we iterate through the cpus until we find some tags - we don't attempt
+ * to find the "best" cpu to steal from, to keep cacheline bouncing to a
+ * minimum.
+ */
+static inline void steal_tags(struct percpu_ida *pool,
+			      struct percpu_ida_cpu *tags)
+{
+	unsigned cpus_have_tags, cpu = pool->cpu_last_stolen;
+	struct percpu_ida_cpu *remote;
+
+	for (cpus_have_tags = cpumask_weight(&pool->cpus_have_tags);
+	     cpus_have_tags * IDA_PCPU_SIZE > pool->nr_tags / 2;
+	     cpus_have_tags--) {
+		cpu = cpumask_next(cpu, &pool->cpus_have_tags);
+
+		if (cpu >= nr_cpu_ids) {
+			cpu = cpumask_first(&pool->cpus_have_tags);
+			if (cpu >= nr_cpu_ids)
+				BUG();
+		}
+
+		pool->cpu_last_stolen = cpu;
+		remote = per_cpu_ptr(pool->tag_cpu, cpu);
+
+		cpumask_clear_cpu(cpu, &pool->cpus_have_tags);
+
+		if (remote == tags)
+			continue;
+
+		spin_lock(&remote->lock);
+
+		if (remote->nr_free) {
+			memcpy(tags->freelist,
+			       remote->freelist,
+			       sizeof(unsigned) * remote->nr_free);
+
+			tags->nr_free = remote->nr_free;
+			remote->nr_free = 0;
+		}
+
+		spin_unlock(&remote->lock);
+
+		if (tags->nr_free)
+			break;
+	}
+}
+
+/*
+ * Pop up to IDA_PCPU_BATCH_MOVE IDs off the global freelist, and push them onto
+ * our percpu freelist:
+ */
+static inline void alloc_global_tags(struct percpu_ida *pool,
+				     struct percpu_ida_cpu *tags)
+{
+	move_tags(tags->freelist, &tags->nr_free,
+		  pool->freelist, &pool->nr_free,
+		  min(pool->nr_free, IDA_PCPU_BATCH_MOVE));
+}
+
+static inline unsigned alloc_local_tag(struct percpu_ida *pool,
+				       struct percpu_ida_cpu *tags)
+{
+	int tag = -ENOSPC;
+
+	spin_lock(&tags->lock);
+	if (tags->nr_free)
+		tag = tags->freelist[--tags->nr_free];
+	spin_unlock(&tags->lock);
+
+	return tag;
+}
+
+/**
+ * percpu_ida_alloc - allocate a tag
+ * @pool: pool to allocate from
+ * @gfp: gfp flags
+ *
+ * Returns a tag - an integer in the range [0..nr_tags) (passed to
+ * tag_pool_init()), or otherwise -ENOSPC on allocation failure.
+ *
+ * Safe to be called from interrupt context (assuming it isn't passed
+ * __GFP_WAIT, of course).
+ *
+ * @gfp indicates whether or not to wait until a free id is available (it's not
+ * used for internal memory allocations); thus if passed __GFP_WAIT we may sleep
+ * however long it takes until another thread frees an id (same semantics as a
+ * mempool).
+ *
+ * Will not fail if passed __GFP_WAIT.
+ */
+int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp)
+{
+	DEFINE_WAIT(wait);
+	struct percpu_ida_cpu *tags;
+	unsigned long flags;
+	int tag;
+
+	local_irq_save(flags);
+	tags = this_cpu_ptr(pool->tag_cpu);
+
+	/* Fastpath */
+	tag = alloc_local_tag(pool, tags);
+	if (likely(tag >= 0)) {
+		local_irq_restore(flags);
+		return tag;
+	}
+
+	while (1) {
+		spin_lock(&pool->lock);
+
+		/*
+		 * prepare_to_wait() must come before steal_tags(), in case
+		 * percpu_ida_free() on another cpu flips a bit in
+		 * cpus_have_tags
+		 *
+		 * global lock held and irqs disabled, don't need percpu lock
+		 */
+		prepare_to_wait(&pool->wait, &wait, TASK_UNINTERRUPTIBLE);
+
+		if (!tags->nr_free)
+			alloc_global_tags(pool, tags);
+		if (!tags->nr_free)
+			steal_tags(pool, tags);
+
+		if (tags->nr_free) {
+			tag = tags->freelist[--tags->nr_free];
+			if (tags->nr_free)
+				cpumask_set_cpu(smp_processor_id(),
+						&pool->cpus_have_tags);
+		}
+
+		spin_unlock(&pool->lock);
+		local_irq_restore(flags);
+
+		if (tag >= 0 || !(gfp & __GFP_WAIT))
+			break;
+
+		schedule();
+
+		local_irq_save(flags);
+		tags = this_cpu_ptr(pool->tag_cpu);
+	}
+
+	finish_wait(&pool->wait, &wait);
+	return tag;
+}
+EXPORT_SYMBOL_GPL(percpu_ida_alloc);
+
+/**
+ * percpu_ida_free - free a tag
+ * @pool: pool @tag was allocated from
+ * @tag: a tag previously allocated with percpu_ida_alloc()
+ *
+ * Safe to be called from interrupt context.
+ */
+void percpu_ida_free(struct percpu_ida *pool, unsigned tag)
+{
+	struct percpu_ida_cpu *tags;
+	unsigned long flags;
+	unsigned nr_free;
+
+	BUG_ON(tag >= pool->nr_tags);
+
+	local_irq_save(flags);
+	tags = this_cpu_ptr(pool->tag_cpu);
+
+	spin_lock(&tags->lock);
+	tags->freelist[tags->nr_free++] = tag;
+
+	nr_free = tags->nr_free;
+	spin_unlock(&tags->lock);
+
+	if (nr_free == 1) {
+		cpumask_set_cpu(smp_processor_id(),
+				&pool->cpus_have_tags);
+		wake_up(&pool->wait);
+	}
+
+	if (nr_free == IDA_PCPU_SIZE) {
+		spin_lock(&pool->lock);
+
+		/*
+		 * Global lock held and irqs disabled, don't need percpu
+		 * lock
+		 */
+		if (tags->nr_free == IDA_PCPU_SIZE) {
+			move_tags(pool->freelist, &pool->nr_free,
+				  tags->freelist, &tags->nr_free,
+				  IDA_PCPU_BATCH_MOVE);
+
+			wake_up(&pool->wait);
+		}
+		spin_unlock(&pool->lock);
+	}
+
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(percpu_ida_free);
+
+/**
+ * percpu_ida_destroy - release a tag pool's resources
+ * @pool: pool to free
+ *
+ * Frees the resources allocated by percpu_ida_init().
+ */
+void percpu_ida_destroy(struct percpu_ida *pool)
+{
+	free_percpu(pool->tag_cpu);
+	free_pages((unsigned long) pool->freelist,
+		   get_order(pool->nr_tags * sizeof(unsigned)));
+}
+EXPORT_SYMBOL_GPL(percpu_ida_destroy);
+
+/**
+ * percpu_ida_init - initialize a percpu tag pool
+ * @pool: pool to initialize
+ * @nr_tags: number of tags that will be available for allocation
+ *
+ * Initializes @pool so that it can be used to allocate tags - integers in the
+ * range [0, nr_tags). Typically, they'll be used by driver code to refer to a
+ * preallocated array of tag structures.
+ *
+ * Allocation is percpu, but sharding is limited by nr_tags - for best
+ * performance, the workload should not span more cpus than nr_tags / 128.
+ */
+int percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags)
+{
+	unsigned i, cpu, order;
+
+	memset(pool, 0, sizeof(*pool));
+
+	init_waitqueue_head(&pool->wait);
+	spin_lock_init(&pool->lock);
+	pool->nr_tags = nr_tags;
+
+	/* Guard against overflow */
+	if (nr_tags > (unsigned) INT_MAX + 1) {
+		pr_err("percpu_ida_init(): nr_tags too large\n");
+		return -EINVAL;
+	}
+
+	order = get_order(nr_tags * sizeof(unsigned));
+	pool->freelist = (void *) __get_free_pages(GFP_KERNEL, order);
+	if (!pool->freelist)
+		return -ENOMEM;
+
+	for (i = 0; i < nr_tags; i++)
+		pool->freelist[i] = i;
+
+	pool->nr_free = nr_tags;
+
+	pool->tag_cpu = __alloc_percpu(sizeof(struct percpu_ida_cpu) +
+				       IDA_PCPU_SIZE * sizeof(unsigned),
+				       sizeof(unsigned));
+	if (!pool->tag_cpu)
+		goto err;
+
+	for_each_possible_cpu(cpu)
+		spin_lock_init(&per_cpu_ptr(pool->tag_cpu, cpu)->lock);
+
+	return 0;
+err:
+	percpu_ida_destroy(pool);
+	return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(percpu_ida_init);