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

Pull more rdma updates from Doug Ledford:
 "This is the second group of code for the 4.7 merge window.  It looks
  large, but only in one sense.  I'll get to that in a minute.  The list
  of changes here breaks down as follows:

   - Dynamic counter infrastructure in the IB drivers

     This is a sysfs based code to allow free form access to the
     hardware counters RDMA devices might support so drivers don't need
     to code this up repeatedly themselves

   - SendOnlyFullMember multicast support

   - IB router support

   - A couple misc fixes

   - The big item on the list: hfi1 driver updates, plus moving the hfi1
     driver out of staging

  There was a group of 15 patches in the hfi1 list that I thought I had
  in the first pull request but they weren't.  So that added to the
  length of the hfi1 section here.

  As far as these go, everything but the hfi1 is pretty straight
  forward.

  The hfi1 is, if you recall, the driver that Al had complaints about
  how it used the write/writev interfaces in an overloaded fashion.  The
  write portion of their interface behaved like the write handler in the
  IB stack proper and did bi-directional communications.  The writev
  interface, on the other hand, only accepts SDMA request structures.
  The completions for those structures are sent back via an entirely
  different event mechanism.

  With the security patch, we put security checks on the write
  interface, however, we also knew they would be going away soon.  Now,
  we've converted the write handler in the hfi1 driver to use ioctls
  from the IB reserved magic area for its bidirectional communications.
  With that change, Intel has addressed all of the items originally on
  their TODO when they went into staging (as well as many items added to
  the list later).

  As such, I moved them out, and since they were the last item in the
  staging/rdma directory, and I don't have immediate plans to use the
  staging area again, I removed the staging/rdma area.

  Because of the move out of staging, as well as a series of 5 patches
  in the hfi1 driver that removed code people thought should be done in
  a different way and was optional to begin with (a snoop debug
  interface, an eeprom driver for an eeprom connected directory to their
  hfi1 chip and not via an i2c bus, and a few other things like that),
  the line count, especially the removal count, is high"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (56 commits)
  staging/rdma: Remove the entire rdma subdirectory of staging
  IB/core: Make device counter infrastructure dynamic
  IB/hfi1: Fix pio map initialization
  IB/hfi1: Correct 8051 link parameter settings
  IB/hfi1: Update pkey table properly after link down or FM start
  IB/rdamvt: Fix rdmavt s_ack_queue sizing
  IB/rdmavt: Max atomic value should be a u8
  IB/hfi1: Fix hard lockup due to not using save/restore spin lock
  IB/hfi1: Add tracing support for send with invalidate opcode
  IB/hfi1, qib: Add ieth to the packet header definitions
  IB/hfi1: Move driver out of staging
  IB/hfi1: Do not free hfi1 cdev parent structure early
  IB/hfi1: Add trace message in user IOCTL handling
  IB/hfi1: Remove write(), use ioctl() for user cmds
  IB/hfi1: Add ioctl() interface for user commands
  IB/hfi1: Remove unused user command
  IB/hfi1: Remove snoop/diag interface
  IB/hfi1: Remove EPROM functionality from data device
  IB/hfi1: Remove UI char device
  IB/hfi1: Remove multiple device cdev
  ...

2 files changed, 58 insertions, 32 deletions

diff --git a/include/uapi/rdma/hfi/hfi1_user.h b/include/uapi/rdma/hfi/hfi1_user.h
index a533cecab14f..98bebf8bef55 100644
--- a/include/uapi/rdma/hfi/hfi1_user.h
+++ b/include/uapi/rdma/hfi/hfi1_user.h
@@ -66,7 +66,7 @@
  * The major version changes when data structures change in an incompatible
  * way. The driver must be the same for initialization to succeed.
  */
-#define HFI1_USER_SWMAJOR 5
+#define HFI1_USER_SWMAJOR 6
 
 /*
  * Minor version differences are always compatible
@@ -75,7 +75,12 @@
  * may not be implemented; the user code must deal with this if it
  * cares, or it must abort after initialization reports the difference.
  */
-#define HFI1_USER_SWMINOR 0
+#define HFI1_USER_SWMINOR 1
+
+/*
+ * We will encode the major/minor inside a single 32bit version number.
+ */
+#define HFI1_SWMAJOR_SHIFT 16
 
 /*
  * Set of HW and driver capability/feature bits.
@@ -107,19 +112,6 @@
 #define HFI1_RCVHDR_ENTSIZE_16   (1UL << 1)
 #define HFI1_RCVDHR_ENTSIZE_32   (1UL << 2)
 
-/*
- * If the unit is specified via open, HFI choice is fixed.  If port is
- * specified, it's also fixed.  Otherwise we try to spread contexts
- * across ports and HFIs, using different algorithms.  WITHIN is
- * the old default, prior to this mechanism.
- */
-#define HFI1_ALG_ACROSS 0 /* round robin contexts across HFIs, then
-			  * ports; this is the default */
-#define HFI1_ALG_WITHIN 1 /* use all contexts on an HFI (round robin
-			  * active ports within), then next HFI */
-#define HFI1_ALG_COUNT  2 /* number of algorithm choices */
-
-
 /* User commands. */
 #define HFI1_CMD_ASSIGN_CTXT     1	/* allocate HFI and context */
 #define HFI1_CMD_CTXT_INFO       2	/* find out what resources we got */
@@ -127,7 +119,6 @@
 #define HFI1_CMD_TID_UPDATE      4	/* update expected TID entries */
 #define HFI1_CMD_TID_FREE        5	/* free expected TID entries */
 #define HFI1_CMD_CREDIT_UPD      6	/* force an update of PIO credit */
-#define HFI1_CMD_SDMA_STATUS_UPD 7      /* force update of SDMA status ring */
 
 #define HFI1_CMD_RECV_CTRL       8	/* control receipt of packets */
 #define HFI1_CMD_POLL_TYPE       9	/* set the kind of polling we want */
@@ -135,13 +126,46 @@
 #define HFI1_CMD_SET_PKEY        11     /* set context's pkey */
 #define HFI1_CMD_CTXT_RESET      12     /* reset context's HW send context */
 #define HFI1_CMD_TID_INVAL_READ  13     /* read TID cache invalidations */
-/* separate EPROM commands from normal PSM commands */
-#define HFI1_CMD_EP_INFO         64      /* read EPROM device ID */
-#define HFI1_CMD_EP_ERASE_CHIP   65      /* erase whole EPROM */
-/* range 66-74 no longer used */
-#define HFI1_CMD_EP_ERASE_RANGE  75      /* erase EPROM range */
-#define HFI1_CMD_EP_READ_RANGE   76      /* read EPROM range */
-#define HFI1_CMD_EP_WRITE_RANGE  77      /* write EPROM range */
+#define HFI1_CMD_GET_VERS	 14	/* get the version of the user cdev */
+
+/*
+ * User IOCTLs can not go above 128 if they do then see common.h and change the
+ * base for the snoop ioctl
+ */
+#define IB_IOCTL_MAGIC 0x1b /* See Documentation/ioctl/ioctl-number.txt */
+
+/*
+ * Make the ioctls occupy the last 0xf0-0xff portion of the IB range
+ */
+#define __NUM(cmd) (HFI1_CMD_##cmd + 0xe0)
+
+struct hfi1_cmd;
+#define HFI1_IOCTL_ASSIGN_CTXT \
+	_IOWR(IB_IOCTL_MAGIC, __NUM(ASSIGN_CTXT), struct hfi1_user_info)
+#define HFI1_IOCTL_CTXT_INFO \
+	_IOW(IB_IOCTL_MAGIC, __NUM(CTXT_INFO), struct hfi1_ctxt_info)
+#define HFI1_IOCTL_USER_INFO \
+	_IOW(IB_IOCTL_MAGIC, __NUM(USER_INFO), struct hfi1_base_info)
+#define HFI1_IOCTL_TID_UPDATE \
+	_IOWR(IB_IOCTL_MAGIC, __NUM(TID_UPDATE), struct hfi1_tid_info)
+#define HFI1_IOCTL_TID_FREE \
+	_IOWR(IB_IOCTL_MAGIC, __NUM(TID_FREE), struct hfi1_tid_info)
+#define HFI1_IOCTL_CREDIT_UPD \
+	_IO(IB_IOCTL_MAGIC, __NUM(CREDIT_UPD))
+#define HFI1_IOCTL_RECV_CTRL \
+	_IOW(IB_IOCTL_MAGIC, __NUM(RECV_CTRL), int)
+#define HFI1_IOCTL_POLL_TYPE \
+	_IOW(IB_IOCTL_MAGIC, __NUM(POLL_TYPE), int)
+#define HFI1_IOCTL_ACK_EVENT \
+	_IOW(IB_IOCTL_MAGIC, __NUM(ACK_EVENT), unsigned long)
+#define HFI1_IOCTL_SET_PKEY \
+	_IOW(IB_IOCTL_MAGIC, __NUM(SET_PKEY), __u16)
+#define HFI1_IOCTL_CTXT_RESET \
+	_IO(IB_IOCTL_MAGIC, __NUM(CTXT_RESET))
+#define HFI1_IOCTL_TID_INVAL_READ \
+	_IOWR(IB_IOCTL_MAGIC, __NUM(TID_INVAL_READ), struct hfi1_tid_info)
+#define HFI1_IOCTL_GET_VERS \
+	_IOR(IB_IOCTL_MAGIC, __NUM(GET_VERS), int)
 
 #define _HFI1_EVENT_FROZEN_BIT         0
 #define _HFI1_EVENT_LINKDOWN_BIT       1
@@ -199,9 +223,7 @@ struct hfi1_user_info {
 	 * Should be set to HFI1_USER_SWVERSION.
 	 */
 	__u32 userversion;
-	__u16 pad;
-	/* HFI selection algorithm, if unit has not selected */
-	__u16 hfi1_alg;
+	__u32 pad;
 	/*
 	 * If two or more processes wish to share a context, each process
 	 * must set the subcontext_cnt and subcontext_id to the same
@@ -243,12 +265,6 @@ struct hfi1_tid_info {
 	__u32 length;
 };
 
-struct hfi1_cmd {
-	__u32 type;        /* command type */
-	__u32 len;         /* length of struct pointed to by add */
-	__u64 addr;        /* pointer to user structure */
-};
-
 enum hfi1_sdma_comp_state {
 	FREE = 0,
 	QUEUED,
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 6e373d151cad..02fe8390c18f 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -135,10 +135,12 @@ enum {
  * Local service operations:
  *   RESOLVE - The client requests the local service to resolve a path.
  *   SET_TIMEOUT - The local service requests the client to set the timeout.
+ *   IP_RESOLVE - The client requests the local service to resolve an IP to GID.
  */
 enum {
 	RDMA_NL_LS_OP_RESOLVE = 0,
 	RDMA_NL_LS_OP_SET_TIMEOUT,
+	RDMA_NL_LS_OP_IP_RESOLVE,
 	RDMA_NL_LS_NUM_OPS
 };
 
@@ -176,6 +178,10 @@ struct rdma_ls_resolve_header {
 	__u8 path_use;
 };
 
+struct rdma_ls_ip_resolve_header {
+	__u32 ifindex;
+};
+
 /* Local service attribute type */
 #define RDMA_NLA_F_MANDATORY	(1 << 13)
 #define RDMA_NLA_TYPE_MASK	(~(NLA_F_NESTED | NLA_F_NET_BYTEORDER | \
@@ -193,6 +199,8 @@ struct rdma_ls_resolve_header {
  *   TCLASS          u8
  *   PKEY            u16                        cpu
  *   QOS_CLASS       u16                        cpu
+ *   IPV4            u32                        BE
+ *   IPV6            u8[16]                     BE
  */
 enum {
 	LS_NLA_TYPE_UNSPEC = 0,
@@ -204,6 +212,8 @@ enum {
 	LS_NLA_TYPE_TCLASS,
 	LS_NLA_TYPE_PKEY,
 	LS_NLA_TYPE_QOS_CLASS,
+	LS_NLA_TYPE_IPV4,
+	LS_NLA_TYPE_IPV6,
 	LS_NLA_TYPE_MAX
 };