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
  ...

6 files changed, 161 insertions, 60 deletions

diff --git a/include/rdma/ib_mad.h b/include/rdma/ib_mad.h
index 37dd534cbeab..c8a773ffe23b 100644
--- a/include/rdma/ib_mad.h
+++ b/include/rdma/ib_mad.h
@@ -239,12 +239,15 @@ struct ib_vendor_mad {
 
 #define IB_MGMT_CLASSPORTINFO_ATTR_ID	cpu_to_be16(0x0001)
 
+#define IB_CLASS_PORT_INFO_RESP_TIME_MASK	0x1F
+#define IB_CLASS_PORT_INFO_RESP_TIME_FIELD_SIZE 5
+
 struct ib_class_port_info {
 	u8			base_version;
 	u8			class_version;
 	__be16			capability_mask;
-	u8			reserved[3];
-	u8			resp_time_value;
+	  /* 27 bits for cap_mask2, 5 bits for resp_time */
+	__be32			cap_mask2_resp_time;
 	u8			redirect_gid[16];
 	__be32			redirect_tcslfl;
 	__be16			redirect_lid;
@@ -259,6 +262,59 @@ struct ib_class_port_info {
 	__be32			trap_qkey;
 };
 
+/**
+ * ib_get_cpi_resp_time - Returns the resp_time value from
+ * cap_mask2_resp_time in ib_class_port_info.
+ * @cpi: A struct ib_class_port_info mad.
+ */
+static inline u8 ib_get_cpi_resp_time(struct ib_class_port_info *cpi)
+{
+	return (u8)(be32_to_cpu(cpi->cap_mask2_resp_time) &
+		    IB_CLASS_PORT_INFO_RESP_TIME_MASK);
+}
+
+/**
+ * ib_set_cpi_resptime - Sets the response time in an
+ * ib_class_port_info mad.
+ * @cpi: A struct ib_class_port_info.
+ * @rtime: The response time to set.
+ */
+static inline void ib_set_cpi_resp_time(struct ib_class_port_info *cpi,
+					u8 rtime)
+{
+	cpi->cap_mask2_resp_time =
+		(cpi->cap_mask2_resp_time &
+		 cpu_to_be32(~IB_CLASS_PORT_INFO_RESP_TIME_MASK)) |
+		cpu_to_be32(rtime & IB_CLASS_PORT_INFO_RESP_TIME_MASK);
+}
+
+/**
+ * ib_get_cpi_capmask2 - Returns the capmask2 value from
+ * cap_mask2_resp_time in ib_class_port_info.
+ * @cpi: A struct ib_class_port_info mad.
+ */
+static inline u32 ib_get_cpi_capmask2(struct ib_class_port_info *cpi)
+{
+	return (be32_to_cpu(cpi->cap_mask2_resp_time) >>
+		IB_CLASS_PORT_INFO_RESP_TIME_FIELD_SIZE);
+}
+
+/**
+ * ib_set_cpi_capmask2 - Sets the capmask2 in an
+ * ib_class_port_info mad.
+ * @cpi: A struct ib_class_port_info.
+ * @capmask2: The capmask2 to set.
+ */
+static inline void ib_set_cpi_capmask2(struct ib_class_port_info *cpi,
+				       u32 capmask2)
+{
+	cpi->cap_mask2_resp_time =
+		(cpi->cap_mask2_resp_time &
+		 cpu_to_be32(IB_CLASS_PORT_INFO_RESP_TIME_MASK)) |
+		cpu_to_be32(capmask2 <<
+			    IB_CLASS_PORT_INFO_RESP_TIME_FIELD_SIZE);
+}
+
 struct ib_mad_notice_attr {
 	u8 generic_type;
 	u8 prod_type_msb;
diff --git a/include/rdma/ib_pack.h b/include/rdma/ib_pack.h
index 0f3daae44bf9..b13419ce99ff 100644
--- a/include/rdma/ib_pack.h
+++ b/include/rdma/ib_pack.h
@@ -103,6 +103,9 @@ enum {
 	IB_OPCODE_ATOMIC_ACKNOWLEDGE                = 0x12,
 	IB_OPCODE_COMPARE_SWAP                      = 0x13,
 	IB_OPCODE_FETCH_ADD                         = 0x14,
+	/* opcode 0x15 is reserved */
+	IB_OPCODE_SEND_LAST_WITH_INVALIDATE         = 0x16,
+	IB_OPCODE_SEND_ONLY_WITH_INVALIDATE         = 0x17,
 
 	/* real constants follow -- see comment about above IB_OPCODE()
 	   macro for more details */
@@ -129,6 +132,8 @@ enum {
 	IB_OPCODE(RC, ATOMIC_ACKNOWLEDGE),
 	IB_OPCODE(RC, COMPARE_SWAP),
 	IB_OPCODE(RC, FETCH_ADD),
+	IB_OPCODE(RC, SEND_LAST_WITH_INVALIDATE),
+	IB_OPCODE(RC, SEND_ONLY_WITH_INVALIDATE),
 
 	/* UC */
 	IB_OPCODE(UC, SEND_FIRST),
diff --git a/include/rdma/ib_sa.h b/include/rdma/ib_sa.h
index cdc1c81aa275..384041669489 100644
--- a/include/rdma/ib_sa.h
+++ b/include/rdma/ib_sa.h
@@ -94,6 +94,8 @@ enum ib_sa_selector {
 	IB_SA_BEST = 3
 };
 
+#define IB_SA_CAP_MASK2_SENDONLY_FULL_MEM_SUPPORT	BIT(12)
+
 /*
  * Structures for SA records are named "struct ib_sa_xxx_rec."  No
  * attempt is made to pack structures to match the physical layout of
@@ -439,4 +441,14 @@ int ib_sa_guid_info_rec_query(struct ib_sa_client *client,
 			      void *context,
 			      struct ib_sa_query **sa_query);
 
+/* Support get SA ClassPortInfo */
+int ib_sa_classport_info_rec_query(struct ib_sa_client *client,
+				   struct ib_device *device, u8 port_num,
+				   int timeout_ms, gfp_t gfp_mask,
+				   void (*callback)(int status,
+						    struct ib_class_port_info *resp,
+						    void *context),
+				   void *context,
+				   struct ib_sa_query **sa_query);
+
 #endif /* IB_SA_H */
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index fc0320c004a3..432bed510369 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -403,56 +403,55 @@ enum ib_port_speed {
 	IB_SPEED_EDR	= 32
 };
 
-struct ib_protocol_stats {
-	/* TBD... */
-};
-
-struct iw_protocol_stats {
-	u64	ipInReceives;
-	u64	ipInHdrErrors;
-	u64	ipInTooBigErrors;
-	u64	ipInNoRoutes;
-	u64	ipInAddrErrors;
-	u64	ipInUnknownProtos;
-	u64	ipInTruncatedPkts;
-	u64	ipInDiscards;
-	u64	ipInDelivers;
-	u64	ipOutForwDatagrams;
-	u64	ipOutRequests;
-	u64	ipOutDiscards;
-	u64	ipOutNoRoutes;
-	u64	ipReasmTimeout;
-	u64	ipReasmReqds;
-	u64	ipReasmOKs;
-	u64	ipReasmFails;
-	u64	ipFragOKs;
-	u64	ipFragFails;
-	u64	ipFragCreates;
-	u64	ipInMcastPkts;
-	u64	ipOutMcastPkts;
-	u64	ipInBcastPkts;
-	u64	ipOutBcastPkts;
-
-	u64	tcpRtoAlgorithm;
-	u64	tcpRtoMin;
-	u64	tcpRtoMax;
-	u64	tcpMaxConn;
-	u64	tcpActiveOpens;
-	u64	tcpPassiveOpens;
-	u64	tcpAttemptFails;
-	u64	tcpEstabResets;
-	u64	tcpCurrEstab;
-	u64	tcpInSegs;
-	u64	tcpOutSegs;
-	u64	tcpRetransSegs;
-	u64	tcpInErrs;
-	u64	tcpOutRsts;
-};
-
-union rdma_protocol_stats {
-	struct ib_protocol_stats	ib;
-	struct iw_protocol_stats	iw;
-};
+/**
+ * struct rdma_hw_stats
+ * @timestamp - Used by the core code to track when the last update was
+ * @lifespan - Used by the core code to determine how old the counters
+ *   should be before being updated again.  Stored in jiffies, defaults
+ *   to 10 milliseconds, drivers can override the default be specifying
+ *   their own value during their allocation routine.
+ * @name - Array of pointers to static names used for the counters in
+ *   directory.
+ * @num_counters - How many hardware counters there are.  If name is
+ *   shorter than this number, a kernel oops will result.  Driver authors
+ *   are encouraged to leave BUILD_BUG_ON(ARRAY_SIZE(@name) < num_counters)
+ *   in their code to prevent this.
+ * @value - Array of u64 counters that are accessed by the sysfs code and
+ *   filled in by the drivers get_stats routine
+ */
+struct rdma_hw_stats {
+	unsigned long	timestamp;
+	unsigned long	lifespan;
+	const char * const *names;
+	int		num_counters;
+	u64		value[];
+};
+
+#define RDMA_HW_STATS_DEFAULT_LIFESPAN 10
+/**
+ * rdma_alloc_hw_stats_struct - Helper function to allocate dynamic struct
+ *   for drivers.
+ * @names - Array of static const char *
+ * @num_counters - How many elements in array
+ * @lifespan - How many milliseconds between updates
+ */
+static inline struct rdma_hw_stats *rdma_alloc_hw_stats_struct(
+		const char * const *names, int num_counters,
+		unsigned long lifespan)
+{
+	struct rdma_hw_stats *stats;
+
+	stats = kzalloc(sizeof(*stats) + num_counters * sizeof(u64),
+			GFP_KERNEL);
+	if (!stats)
+		return NULL;
+	stats->names = names;
+	stats->num_counters = num_counters;
+	stats->lifespan = msecs_to_jiffies(lifespan);
+
+	return stats;
+}
+
 
 /* Define bits for the various functionality this port needs to be supported by
  * the core.
@@ -1707,8 +1706,29 @@ struct ib_device {
 
 	struct iw_cm_verbs	     *iwcm;
 
-	int		           (*get_protocol_stats)(struct ib_device *device,
-							 union rdma_protocol_stats *stats);
+	/**
+	 * alloc_hw_stats - Allocate a struct rdma_hw_stats and fill in the
+	 *   driver initialized data.  The struct is kfree()'ed by the sysfs
+	 *   core when the device is removed.  A lifespan of -1 in the return
+	 *   struct tells the core to set a default lifespan.
+	 */
+	struct rdma_hw_stats      *(*alloc_hw_stats)(struct ib_device *device,
+						     u8 port_num);
+	/**
+	 * get_hw_stats - Fill in the counter value(s) in the stats struct.
+	 * @index - The index in the value array we wish to have updated, or
+	 *   num_counters if we want all stats updated
+	 * Return codes -
+	 *   < 0 - Error, no counters updated
+	 *   index - Updated the single counter pointed to by index
+	 *   num_counters - Updated all counters (will reset the timestamp
+	 *     and prevent further calls for lifespan milliseconds)
+	 * Drivers are allowed to update all counters in leiu of just the
+	 *   one given in index at their option
+	 */
+	int		           (*get_hw_stats)(struct ib_device *device,
+						   struct rdma_hw_stats *stats,
+						   u8 port, int index);
 	int		           (*query_device)(struct ib_device *device,
 						   struct ib_device_attr *device_attr,
 						   struct ib_udata *udata);
@@ -1926,6 +1946,8 @@ struct ib_device {
 	u8                           node_type;
 	u8                           phys_port_cnt;
 	struct ib_device_attr        attrs;
+	struct attribute_group	     *hw_stats_ag;
+	struct rdma_hw_stats         *hw_stats;
 
 	/**
 	 * The following mandatory functions are used only at device
diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h
index d57ceee90d26..16274e2133cd 100644
--- a/include/rdma/rdma_vt.h
+++ b/include/rdma/rdma_vt.h
@@ -149,15 +149,15 @@ struct rvt_driver_params {
 	int qpn_res_end;
 	int nports;
 	int npkeys;
-	u8 qos_shift;
 	char cq_name[RVT_CQN_MAX];
 	int node;
-	int max_rdma_atomic;
 	int psn_mask;
 	int psn_shift;
 	int psn_modify_mask;
 	u32 core_cap_flags;
 	u32 max_mad_size;
+	u8 qos_shift;
+	u8 max_rdma_atomic;
 };
 
 /* Protection domain */
@@ -426,6 +426,15 @@ static inline unsigned rvt_get_npkeys(struct rvt_dev_info *rdi)
 }
 
 /*
+ * Return the max atomic suitable for determining
+ * the size of the ack ring buffer in a QP.
+ */
+static inline unsigned int rvt_max_atomic(struct rvt_dev_info *rdi)
+{
+	return rdi->dparms.max_rdma_atomic + 1;
+}
+
+/*
  * Return the indexed PKEY from the port PKEY table.
  */
 static inline u16 rvt_get_pkey(struct rvt_dev_info *rdi,
diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h
index 0e1ff2abfe92..6d23b879416a 100644
--- a/include/rdma/rdmavt_qp.h
+++ b/include/rdma/rdmavt_qp.h
@@ -211,8 +211,6 @@ struct rvt_mmap_info {
 	unsigned size;
 };
 
-#define RVT_MAX_RDMA_ATOMIC	16
-
 /*
  * This structure holds the information that the send tasklet needs
  * to send a RDMA read response or atomic operation.
@@ -282,8 +280,7 @@ struct rvt_qp {
 	atomic_t refcount ____cacheline_aligned_in_smp;
 	wait_queue_head_t wait;
 
-	struct rvt_ack_entry s_ack_queue[RVT_MAX_RDMA_ATOMIC + 1]
-		____cacheline_aligned_in_smp;
+	struct rvt_ack_entry *s_ack_queue;
 	struct rvt_sge_state s_rdma_read_sge;
 
 	spinlock_t r_lock ____cacheline_aligned_in_smp;      /* used for APM */