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
  ...

1 files changed, 60 insertions, 0 deletions

diff --git a/include/linux/percpu_ida.h b/include/linux/percpu_ida.h
new file mode 100644
index 000000000000..0b23edbee309
--- /dev/null
+++ b/include/linux/percpu_ida.h
@@ -0,0 +1,60 @@
+#ifndef __PERCPU_IDA_H__
+#define __PERCPU_IDA_H__
+
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/init.h>
+#include <linux/spinlock_types.h>
+#include <linux/wait.h>
+#include <linux/cpumask.h>
+
+struct percpu_ida_cpu;
+
+struct percpu_ida {
+	/*
+	 * number of tags available to be allocated, as passed to
+	 * percpu_ida_init()
+	 */
+	unsigned			nr_tags;
+
+	struct percpu_ida_cpu __percpu	*tag_cpu;
+
+	/*
+	 * Bitmap of cpus that (may) have tags on their percpu freelists:
+	 * steal_tags() uses this to decide when to steal tags, and which cpus
+	 * to try stealing from.
+	 *
+	 * It's ok for a freelist to be empty when its bit is set - steal_tags()
+	 * will just keep looking - but the bitmap _must_ be set whenever a
+	 * percpu freelist does have tags.
+	 */
+	cpumask_t			cpus_have_tags;
+
+	struct {
+		spinlock_t		lock;
+		/*
+		 * When we go to steal tags from another cpu (see steal_tags()),
+		 * we want to pick a cpu at random. Cycling through them every
+		 * time we steal is a bit easier and more or less equivalent:
+		 */
+		unsigned		cpu_last_stolen;
+
+		/* For sleeping on allocation failure */
+		wait_queue_head_t	wait;
+
+		/*
+		 * Global freelist - it's a stack where nr_free points to the
+		 * top
+		 */
+		unsigned		nr_free;
+		unsigned		*freelist;
+	} ____cacheline_aligned_in_smp;
+};
+
+int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp);
+void percpu_ida_free(struct percpu_ida *pool, unsigned tag);
+
+void percpu_ida_destroy(struct percpu_ida *pool);
+int percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags);
+
+#endif /* __PERCPU_IDA_H__ */