Merge branch 'for-linus' of master.kernel.org:/pub/scm/linux/kernel/g…

…it/roland/infiniband

* 'for-linus' of master.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband:
  IB/mthca: Fix max_srq_sge returned by ib_query_device for Tavor devices
  IB/cache: Use correct pointer to calculate size
  IPoIB: Use spin_lock_irq() instead of spin_lock_irqsave()
  IPoIB: Close race in ipoib_flush_paths()
  IB/mthca: Disable tuning PCI read burst size
  IPoIB: Make send and receive queue sizes tunable
  IPoIB: Wait for join to finish before freeing mcast struct
  IB: simplify static rate encoding
  IPoIB: Consolidate private neighbour data handling
  IB/srp: Fix memory leak in options parsing
  IB/mthca: Always build debugging code unless CONFIG_EMBEDDED=y
  IPoIB: Always build debugging code unless CONFIG_EMBEDDED=y
  IB/mad: fix oops in cancel_mads

drivers/infiniband/core/cache.c

@@ -302,7 +302,7 @@ static void ib_cache_setup_one(struct ib_device *device)
 		kmalloc(sizeof *device->cache.pkey_cache *
 			(end_port(device) - start_port(device) + 1), GFP_KERNEL);
 	device->cache.gid_cache =
-		kmalloc(sizeof *device->cache.pkey_cache *
+		kmalloc(sizeof *device->cache.gid_cache *
 			(end_port(device) - start_port(device) + 1), GFP_KERNEL);
 
 	if (!device->cache.pkey_cache || !device->cache.gid_cache) {

drivers/infiniband/core/mad.c

@@ -2311,6 +2311,7 @@ static void local_completions(void *data)
 		local = list_entry(mad_agent_priv->local_list.next,
 				   struct ib_mad_local_private,
 				   completion_list);
+		list_del(&local->completion_list);
 		spin_unlock_irqrestore(&mad_agent_priv->lock, flags);
 		if (local->mad_priv) {
 			recv_mad_agent = local->recv_mad_agent;
@@ -2362,7 +2363,6 @@ static void local_completions(void *data)
 						   &mad_send_wc);
 
 		spin_lock_irqsave(&mad_agent_priv->lock, flags);
-		list_del(&local->completion_list);
 		atomic_dec(&mad_agent_priv->refcount);
 		if (!recv)
 			kmem_cache_free(ib_mad_cache, local->mad_priv);

drivers/infiniband/core/verbs.c

@@ -45,6 +45,40 @@
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_cache.h>
 
+int ib_rate_to_mult(enum ib_rate rate)
+{
+	switch (rate) {
+	case IB_RATE_2_5_GBPS: return  1;
+	case IB_RATE_5_GBPS:   return  2;
+	case IB_RATE_10_GBPS:  return  4;
+	case IB_RATE_20_GBPS:  return  8;
+	case IB_RATE_30_GBPS:  return 12;
+	case IB_RATE_40_GBPS:  return 16;
+	case IB_RATE_60_GBPS:  return 24;
+	case IB_RATE_80_GBPS:  return 32;
+	case IB_RATE_120_GBPS: return 48;
+	default:	       return -1;
+	}
+}
+EXPORT_SYMBOL(ib_rate_to_mult);
+
+enum ib_rate mult_to_ib_rate(int mult)
+{
+	switch (mult) {
+	case 1:  return IB_RATE_2_5_GBPS;
+	case 2:  return IB_RATE_5_GBPS;
+	case 4:  return IB_RATE_10_GBPS;
+	case 8:  return IB_RATE_20_GBPS;
+	case 12: return IB_RATE_30_GBPS;
+	case 16: return IB_RATE_40_GBPS;
+	case 24: return IB_RATE_60_GBPS;
+	case 32: return IB_RATE_80_GBPS;
+	case 48: return IB_RATE_120_GBPS;
+	default: return IB_RATE_PORT_CURRENT;
+	}
+}
+EXPORT_SYMBOL(mult_to_ib_rate);
+
 /* Protection domains */
 
 struct ib_pd *ib_alloc_pd(struct ib_device *device)

drivers/infiniband/hw/mthca/Kconfig

@@ -7,10 +7,11 @@ config INFINIBAND_MTHCA
 	  ("Tavor") and the MT25208 PCI Express HCA ("Arbel").
 
 config INFINIBAND_MTHCA_DEBUG
-	bool "Verbose debugging output"
+	bool "Verbose debugging output" if EMBEDDED
 	depends on INFINIBAND_MTHCA
-	default n
+	default y
 	---help---
-	  This option causes the mthca driver produce a bunch of debug
-	  messages.  Select this is you are developing the driver or
-	  trying to diagnose a problem.
+	  This option causes debugging code to be compiled into the
+	  mthca driver.  The output can be turned on via the
+	  debug_level module parameter (which can also be set after
+	  the driver is loaded through sysfs).

drivers/infiniband/hw/mthca/Makefile

@@ -1,7 +1,3 @@
-ifdef CONFIG_INFINIBAND_MTHCA_DEBUG
-EXTRA_CFLAGS += -DDEBUG
-endif
-
 obj-$(CONFIG_INFINIBAND_MTHCA) += ib_mthca.o
 
 ib_mthca-y :=	mthca_main.o mthca_cmd.o mthca_profile.o mthca_reset.o \

drivers/infiniband/hw/mthca/mthca_av.c

@@ -42,6 +42,20 @@
 
 #include "mthca_dev.h"
 
+enum {
+      MTHCA_RATE_TAVOR_FULL   = 0,
+      MTHCA_RATE_TAVOR_1X     = 1,
+      MTHCA_RATE_TAVOR_4X     = 2,
+      MTHCA_RATE_TAVOR_1X_DDR = 3
+};
+
+enum {
+      MTHCA_RATE_MEMFREE_FULL    = 0,
+      MTHCA_RATE_MEMFREE_QUARTER = 1,
+      MTHCA_RATE_MEMFREE_EIGHTH  = 2,
+      MTHCA_RATE_MEMFREE_HALF    = 3
+};
+
 struct mthca_av {
 	__be32 port_pd;
 	u8     reserved1;
@@ -55,6 +69,90 @@ struct mthca_av {
 	__be32 dgid[4];
 };
 
+static enum ib_rate memfree_rate_to_ib(u8 mthca_rate, u8 port_rate)
+{
+	switch (mthca_rate) {
+	case MTHCA_RATE_MEMFREE_EIGHTH:
+		return mult_to_ib_rate(port_rate >> 3);
+	case MTHCA_RATE_MEMFREE_QUARTER:
+		return mult_to_ib_rate(port_rate >> 2);
+	case MTHCA_RATE_MEMFREE_HALF:
+		return mult_to_ib_rate(port_rate >> 1);
+	case MTHCA_RATE_MEMFREE_FULL:
+	default:
+		return mult_to_ib_rate(port_rate);
+	}
+}
+
+static enum ib_rate tavor_rate_to_ib(u8 mthca_rate, u8 port_rate)
+{
+	switch (mthca_rate) {
+	case MTHCA_RATE_TAVOR_1X:     return IB_RATE_2_5_GBPS;
+	case MTHCA_RATE_TAVOR_1X_DDR: return IB_RATE_5_GBPS;
+	case MTHCA_RATE_TAVOR_4X:     return IB_RATE_10_GBPS;
+	default:		      return port_rate;
+	}
+}
+
+enum ib_rate mthca_rate_to_ib(struct mthca_dev *dev, u8 mthca_rate, u8 port)
+{
+	if (mthca_is_memfree(dev)) {
+		/* Handle old Arbel FW */
+		if (dev->limits.stat_rate_support == 0x3 && mthca_rate)
+			return IB_RATE_2_5_GBPS;
+
+		return memfree_rate_to_ib(mthca_rate, dev->rate[port - 1]);
+	} else
+		return tavor_rate_to_ib(mthca_rate, dev->rate[port - 1]);
+}
+
+static u8 ib_rate_to_memfree(u8 req_rate, u8 cur_rate)
+{
+	if (cur_rate <= req_rate)
+		return 0;
+
+	/*
+	 * Inter-packet delay (IPD) to get from rate X down to a rate
+	 * no more than Y is (X - 1) / Y.
+	 */
+	switch ((cur_rate - 1) / req_rate) {
+	case 0:	 return MTHCA_RATE_MEMFREE_FULL;
+	case 1:	 return MTHCA_RATE_MEMFREE_HALF;
+	case 2:	 /* fall through */
+	case 3:	 return MTHCA_RATE_MEMFREE_QUARTER;
+	default: return MTHCA_RATE_MEMFREE_EIGHTH;
+	}
+}
+
+static u8 ib_rate_to_tavor(u8 static_rate)
+{
+	switch (static_rate) {
+	case IB_RATE_2_5_GBPS: return MTHCA_RATE_TAVOR_1X;
+	case IB_RATE_5_GBPS:   return MTHCA_RATE_TAVOR_1X_DDR;
+	case IB_RATE_10_GBPS:  return MTHCA_RATE_TAVOR_4X;
+	default:	       return MTHCA_RATE_TAVOR_FULL;
+	}
+}
+
+u8 mthca_get_rate(struct mthca_dev *dev, int static_rate, u8 port)
+{
+	u8 rate;
+
+	if (!static_rate || ib_rate_to_mult(static_rate) >= dev->rate[port - 1])
+		return 0;
+
+	if (mthca_is_memfree(dev))
+		rate = ib_rate_to_memfree(ib_rate_to_mult(static_rate),
+					  dev->rate[port - 1]);
+	else
+		rate = ib_rate_to_tavor(static_rate);
+
+	if (!(dev->limits.stat_rate_support & (1 << rate)))
+		rate = 1;
+
+	return rate;
+}
+
 int mthca_create_ah(struct mthca_dev *dev,
 		    struct mthca_pd *pd,
 		    struct ib_ah_attr *ah_attr,
@@ -107,7 +205,7 @@ int mthca_create_ah(struct mthca_dev *dev,
 	av->g_slid  = ah_attr->src_path_bits;
 	av->dlid    = cpu_to_be16(ah_attr->dlid);
 	av->msg_sr  = (3 << 4) | /* 2K message */
-		ah_attr->static_rate;
+		mthca_get_rate(dev, ah_attr->static_rate, ah_attr->port_num);
 	av->sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28);
 	if (ah_attr->ah_flags & IB_AH_GRH) {
 		av->g_slid |= 0x80;

drivers/infiniband/hw/mthca/mthca_cmd.c

@@ -965,6 +965,7 @@ int mthca_QUERY_DEV_LIM(struct mthca_dev *dev,
 	u32 *outbox;
 	u8 field;
 	u16 size;
+	u16 stat_rate;
 	int err;
 
 #define QUERY_DEV_LIM_OUT_SIZE             0x100
@@ -995,6 +996,7 @@ int mthca_QUERY_DEV_LIM(struct mthca_dev *dev,
 #define QUERY_DEV_LIM_MTU_WIDTH_OFFSET      0x36
 #define QUERY_DEV_LIM_VL_PORT_OFFSET        0x37
 #define QUERY_DEV_LIM_MAX_GID_OFFSET        0x3b
+#define QUERY_DEV_LIM_RATE_SUPPORT_OFFSET   0x3c
 #define QUERY_DEV_LIM_MAX_PKEY_OFFSET       0x3f
 #define QUERY_DEV_LIM_FLAGS_OFFSET          0x44
 #define QUERY_DEV_LIM_RSVD_UAR_OFFSET       0x48
@@ -1086,6 +1088,8 @@ int mthca_QUERY_DEV_LIM(struct mthca_dev *dev,
 	dev_lim->num_ports = field & 0xf;
 	MTHCA_GET(field, outbox, QUERY_DEV_LIM_MAX_GID_OFFSET);
 	dev_lim->max_gids = 1 << (field & 0xf);
+	MTHCA_GET(stat_rate, outbox, QUERY_DEV_LIM_RATE_SUPPORT_OFFSET);
+	dev_lim->stat_rate_support = stat_rate;
 	MTHCA_GET(field, outbox, QUERY_DEV_LIM_MAX_PKEY_OFFSET);
 	dev_lim->max_pkeys = 1 << (field & 0xf);
 	MTHCA_GET(dev_lim->flags, outbox, QUERY_DEV_LIM_FLAGS_OFFSET);

drivers/infiniband/hw/mthca/mthca_cmd.h

@@ -146,6 +146,7 @@ struct mthca_dev_lim {
 	int max_vl;
 	int num_ports;
 	int max_gids;
+	u16 stat_rate_support;
 	int max_pkeys;
 	u32 flags;
 	int reserved_uars;

drivers/infiniband/hw/mthca/mthca_dev.h

@@ -151,6 +151,7 @@ struct mthca_limits {
 	int      reserved_qps;
 	int      num_srqs;
 	int      max_srq_wqes;
+	int      max_srq_sge;
 	int      reserved_srqs;
 	int      num_eecs;
 	int      reserved_eecs;
@@ -172,6 +173,7 @@ struct mthca_limits {
 	int      reserved_pds;
 	u32      page_size_cap;
 	u32      flags;
+	u16      stat_rate_support;
 	u8       port_width_cap;
 };
 
@@ -353,10 +355,24 @@ struct mthca_dev {
 	struct ib_mad_agent  *send_agent[MTHCA_MAX_PORTS][2];
 	struct ib_ah         *sm_ah[MTHCA_MAX_PORTS];
 	spinlock_t            sm_lock;
+	u8                    rate[MTHCA_MAX_PORTS];
 };
 
-#define mthca_dbg(mdev, format, arg...) \
-	dev_dbg(&mdev->pdev->dev, format, ## arg)
+#ifdef CONFIG_INFINIBAND_MTHCA_DEBUG
+extern int mthca_debug_level;
+
+#define mthca_dbg(mdev, format, arg...)					\
+	do {								\
+		if (mthca_debug_level)					\
+			dev_printk(KERN_DEBUG, &mdev->pdev->dev, format, ## arg); \
+	} while (0)
+
+#else /* CONFIG_INFINIBAND_MTHCA_DEBUG */
+
+#define mthca_dbg(mdev, format, arg...) do { (void) mdev; } while (0)
+
+#endif /* CONFIG_INFINIBAND_MTHCA_DEBUG */
+
 #define mthca_err(mdev, format, arg...) \
 	dev_err(&mdev->pdev->dev, format, ## arg)
 #define mthca_info(mdev, format, arg...) \
@@ -492,6 +508,7 @@ void mthca_free_srq(struct mthca_dev *dev, struct mthca_srq *srq);
 int mthca_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr,
 		     enum ib_srq_attr_mask attr_mask);
 int mthca_query_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr);
+int mthca_max_srq_sge(struct mthca_dev *dev);
 void mthca_srq_event(struct mthca_dev *dev, u32 srqn,
 		     enum ib_event_type event_type);
 void mthca_free_srq_wqe(struct mthca_srq *srq, u32 wqe_addr);
@@ -542,6 +559,8 @@ int mthca_read_ah(struct mthca_dev *dev, struct mthca_ah *ah,
 		  struct ib_ud_header *header);
 int mthca_ah_query(struct ib_ah *ibah, struct ib_ah_attr *attr);
 int mthca_ah_grh_present(struct mthca_ah *ah);
+u8 mthca_get_rate(struct mthca_dev *dev, int static_rate, u8 port);
+enum ib_rate mthca_rate_to_ib(struct mthca_dev *dev, u8 mthca_rate, u8 port);
 
 int mthca_multicast_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid);
 int mthca_multicast_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid);

drivers/infiniband/hw/mthca/mthca_mad.c

@@ -49,6 +49,30 @@ enum {
 	MTHCA_VENDOR_CLASS2 = 0xa
 };
 
+int mthca_update_rate(struct mthca_dev *dev, u8 port_num)
+{
+	struct ib_port_attr *tprops = NULL;
+	int                  ret;
+
+	tprops = kmalloc(sizeof *tprops, GFP_KERNEL);
+	if (!tprops)
+		return -ENOMEM;
+
+	ret = ib_query_port(&dev->ib_dev, port_num, tprops);
+	if (ret) {
+		printk(KERN_WARNING "ib_query_port failed (%d) for %s port %d\n",
+		       ret, dev->ib_dev.name, port_num);
+		goto out;
+	}
+
+	dev->rate[port_num - 1] = tprops->active_speed *
+				  ib_width_enum_to_int(tprops->active_width);
+
+out:
+	kfree(tprops);
+	return ret;
+}
+
 static void update_sm_ah(struct mthca_dev *dev,
 			 u8 port_num, u16 lid, u8 sl)
 {
@@ -90,6 +114,7 @@ static void smp_snoop(struct ib_device *ibdev,
 	     mad->mad_hdr.mgmt_class  == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) &&
 	    mad->mad_hdr.method     == IB_MGMT_METHOD_SET) {
 		if (mad->mad_hdr.attr_id == IB_SMP_ATTR_PORT_INFO) {
+			mthca_update_rate(to_mdev(ibdev), port_num);
 			update_sm_ah(to_mdev(ibdev), port_num,
 				     be16_to_cpup((__be16 *) (mad->data + 58)),
 				     (*(u8 *) (mad->data + 76)) & 0xf);
@@ -246,6 +271,7 @@ int mthca_create_agents(struct mthca_dev *dev)
 {
 	struct ib_mad_agent *agent;
 	int p, q;
+	int ret;
 
 	spin_lock_init(&dev->sm_lock);
 
@@ -255,11 +281,23 @@ int mthca_create_agents(struct mthca_dev *dev)
 						      q ? IB_QPT_GSI : IB_QPT_SMI,
 						      NULL, 0, send_handler,
 						      NULL, NULL);
-			if (IS_ERR(agent))
+			if (IS_ERR(agent)) {
+				ret = PTR_ERR(agent);
 				goto err;
+			}
 			dev->send_agent[p][q] = agent;
 		}
 
+
+	for (p = 1; p <= dev->limits.num_ports; ++p) {
+		ret = mthca_update_rate(dev, p);
+		if (ret) {
+			mthca_err(dev, "Failed to obtain port %d rate."
+				  " aborting.\n", p);
+			goto err;
+		}
+	}
+
 	return 0;
 
 err:
@@ -268,7 +306,7 @@ int mthca_create_agents(struct mthca_dev *dev)
 			if (dev->send_agent[p][q])
 				ib_unregister_mad_agent(dev->send_agent[p][q]);
 
-	return PTR_ERR(agent);
+	return ret;
 }
 
 void __devexit mthca_free_agents(struct mthca_dev *dev)