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

Pull rdma fixes from Doug Ledford:
 "This is the second pull request for the rdma subsystem.  Most of the
  patches are small and obvious.  I took two patches in that are larger
  than I wanted this late in the cycle.

  The first is the hfi1 patch that implements a work queue to test the
  QSFP read state.  I originally rejected the first patch for this
  (which would have place up to 20 seconds worth of udelays in their
  probe routine).  They then rewrote it the way I wanted (use delayed
  work tasks to wait asynchronously up to 20 seconds for the QSFP to
  come alive), so I can't really complain about the size of getting what
  I asked for :-/.

  The second is large because it switches the rcu locking in the debugfs
  code.  Since a locking change like this is done all at once, the size
  it what it is.  It resolves a litany of debug messages from the
  kernel, so I pulled it in for -rc.

  The rest are all typical -rc worthy patches I think.

  There will still be a third -rc pull request from the rdma subsystem
  this release.  I hope to have that one ready to go by the end of this
  week or early next.

  Summary:

   - a smattering of small fixes across the core, ipoib, i40iw, isert,
     cxgb4, and mlx4

   - a slightly larger group of fixes to each of mlx5 and hfi1"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma:
  IB/hfi1: Rework debugfs to use SRCU
  IB/hfi1: Make n_krcvqs be an unsigned long integer
  IB/hfi1: Add QSFP sanity pre-check
  IB/hfi1: Fix AHG KDETH Intr shift
  IB/hfi1: Fix SGE length for misaligned PIO copy
  IB/mlx5: Don't return errors from poll_cq
  IB/mlx5: Use TIR number based on selector
  IB/mlx5: Simplify code by removing return variable
  IB/mlx5: Return EINVAL when caller specifies too many SGEs
  IB/mlx4: Don't return errors from poll_cq
  Revert "IB/mlx4: Return EAGAIN for any error in mlx4_ib_poll_one"
  IB/ipoib: Fix memory corruption in ipoib cm mode connect flow
  IB/core: Fix use after free in send_leave function
  IB/cxgb4: Make _free_qp static to silence build warning
  IB/isert: Properly release resources on DEVICE_REMOVAL
  IB/hfi1: Fix the size parameter to find_first_bit
  IB/mlx5: Fix the size parameter to find_first_bit
  IB/hfi1: Clean up type used and casting
  i40iw: Receive notification events correctly
  i40iw: Update hw_iwarp_state

drivers/infiniband/core/multicast.c

@@ -106,7 +106,6 @@ struct mcast_group {
 	atomic_t		refcount;
 	enum mcast_group_state	state;
 	struct ib_sa_query	*query;
-	int			query_id;
 	u16			pkey_index;
 	u8			leave_state;
 	int			retries;
@@ -340,11 +339,7 @@ static int send_join(struct mcast_group *group, struct mcast_member *member)
 				       member->multicast.comp_mask,
 				       3000, GFP_KERNEL, join_handler, group,
 				       &group->query);
-	if (ret >= 0) {
-		group->query_id = ret;
-		ret = 0;
-	}
-	return ret;
+	return (ret > 0) ? 0 : ret;
 }
 
 static int send_leave(struct mcast_group *group, u8 leave_state)
@@ -364,11 +359,7 @@ static int send_leave(struct mcast_group *group, u8 leave_state)
 				       IB_SA_MCMEMBER_REC_JOIN_STATE,
 				       3000, GFP_KERNEL, leave_handler,
 				       group, &group->query);
-	if (ret >= 0) {
-		group->query_id = ret;
-		ret = 0;
-	}
-	return ret;
+	return (ret > 0) ? 0 : ret;
 }
 
 static void join_group(struct mcast_group *group, struct mcast_member *member,

drivers/infiniband/hw/cxgb4/qp.c

@@ -683,7 +683,7 @@ static int build_inv_stag(union t4_wr *wqe, struct ib_send_wr *wr,
 	return 0;
 }
 
-void _free_qp(struct kref *kref)
+static void _free_qp(struct kref *kref)
 {
 	struct c4iw_qp *qhp;
 

drivers/infiniband/hw/hfi1/chip.c

@@ -9490,6 +9490,78 @@ static void init_lcb(struct hfi1_devdata *dd)
 	write_csr(dd, DC_LCB_CFG_TX_FIFOS_RESET, 0x00);
 }
 
+/*
+ * Perform a test read on the QSFP.  Return 0 on success, -ERRNO
+ * on error.
+ */
+static int test_qsfp_read(struct hfi1_pportdata *ppd)
+{
+	int ret;
+	u8 status;
+
+	/* report success if not a QSFP */
+	if (ppd->port_type != PORT_TYPE_QSFP)
+		return 0;
+
+	/* read byte 2, the status byte */
+	ret = one_qsfp_read(ppd, ppd->dd->hfi1_id, 2, &status, 1);
+	if (ret < 0)
+		return ret;
+	if (ret != 1)
+		return -EIO;
+
+	return 0; /* success */
+}
+
+/*
+ * Values for QSFP retry.
+ *
+ * Give up after 10s (20 x 500ms).  The overall timeout was empirically
+ * arrived at from experience on a large cluster.
+ */
+#define MAX_QSFP_RETRIES 20
+#define QSFP_RETRY_WAIT 500 /* msec */
+
+/*
+ * Try a QSFP read.  If it fails, schedule a retry for later.
+ * Called on first link activation after driver load.
+ */
+static void try_start_link(struct hfi1_pportdata *ppd)
+{
+	if (test_qsfp_read(ppd)) {
+		/* read failed */
+		if (ppd->qsfp_retry_count >= MAX_QSFP_RETRIES) {
+			dd_dev_err(ppd->dd, "QSFP not responding, giving up\n");
+			return;
+		}
+		dd_dev_info(ppd->dd,
+			    "QSFP not responding, waiting and retrying %d\n",
+			    (int)ppd->qsfp_retry_count);
+		ppd->qsfp_retry_count++;
+		queue_delayed_work(ppd->hfi1_wq, &ppd->start_link_work,
+				   msecs_to_jiffies(QSFP_RETRY_WAIT));
+		return;
+	}
+	ppd->qsfp_retry_count = 0;
+
+	/*
+	 * Tune the SerDes to a ballpark setting for optimal signal and bit
+	 * error rate.  Needs to be done before starting the link.
+	 */
+	tune_serdes(ppd);
+	start_link(ppd);
+}
+
+/*
+ * Workqueue function to start the link after a delay.
+ */
+void handle_start_link(struct work_struct *work)
+{
+	struct hfi1_pportdata *ppd = container_of(work, struct hfi1_pportdata,
+						  start_link_work.work);
+	try_start_link(ppd);
+}
+
 int bringup_serdes(struct hfi1_pportdata *ppd)
 {
 	struct hfi1_devdata *dd = ppd->dd;
@@ -9525,14 +9597,8 @@ int bringup_serdes(struct hfi1_pportdata *ppd)
 		set_qsfp_int_n(ppd, 1);
 	}
 
-	/*
-	 * Tune the SerDes to a ballpark setting for
-	 * optimal signal and bit error rate
-	 * Needs to be done before starting the link
-	 */
-	tune_serdes(ppd);
-
-	return start_link(ppd);
+	try_start_link(ppd);
+	return 0;
 }
 
 void hfi1_quiet_serdes(struct hfi1_pportdata *ppd)
@@ -9549,6 +9615,10 @@ void hfi1_quiet_serdes(struct hfi1_pportdata *ppd)
 	ppd->driver_link_ready = 0;
 	ppd->link_enabled = 0;
 
+	ppd->qsfp_retry_count = MAX_QSFP_RETRIES; /* prevent more retries */
+	flush_delayed_work(&ppd->start_link_work);
+	cancel_delayed_work_sync(&ppd->start_link_work);
+
 	ppd->offline_disabled_reason =
 			HFI1_ODR_MASK(OPA_LINKDOWN_REASON_SMA_DISABLED);
 	set_link_down_reason(ppd, OPA_LINKDOWN_REASON_SMA_DISABLED, 0,
@@ -12865,7 +12935,7 @@ fail:
  */
 static int set_up_context_variables(struct hfi1_devdata *dd)
 {
-	int num_kernel_contexts;
+	unsigned long num_kernel_contexts;
 	int total_contexts;
 	int ret;
 	unsigned ngroups;
@@ -12894,9 +12964,9 @@ static int set_up_context_variables(struct hfi1_devdata *dd)
 	 */
 	if (num_kernel_contexts > (dd->chip_send_contexts - num_vls - 1)) {
 		dd_dev_err(dd,
-			   "Reducing # kernel rcv contexts to: %d, from %d\n",
+			   "Reducing # kernel rcv contexts to: %d, from %lu\n",
 			   (int)(dd->chip_send_contexts - num_vls - 1),
-			   (int)num_kernel_contexts);
+			   num_kernel_contexts);
 		num_kernel_contexts = dd->chip_send_contexts - num_vls - 1;
 	}
 	/*

drivers/infiniband/hw/hfi1/chip.h

@@ -706,6 +706,7 @@ void handle_link_up(struct work_struct *work);
 void handle_link_down(struct work_struct *work);
 void handle_link_downgrade(struct work_struct *work);
 void handle_link_bounce(struct work_struct *work);
+void handle_start_link(struct work_struct *work);
 void handle_sma_message(struct work_struct *work);
 void reset_qsfp(struct hfi1_pportdata *ppd);
 void qsfp_event(struct work_struct *work);

drivers/infiniband/hw/hfi1/debugfs.c

@@ -59,6 +59,40 @@
 
 static struct dentry *hfi1_dbg_root;
 
+/* wrappers to enforce srcu in seq file */
+static ssize_t hfi1_seq_read(
+	struct file *file,
+	char __user *buf,
+	size_t size,
+	loff_t *ppos)
+{
+	struct dentry *d = file->f_path.dentry;
+	int srcu_idx;
+	ssize_t r;
+
+	r = debugfs_use_file_start(d, &srcu_idx);
+	if (likely(!r))
+		r = seq_read(file, buf, size, ppos);
+	debugfs_use_file_finish(srcu_idx);
+	return r;
+}
+
+static loff_t hfi1_seq_lseek(
+	struct file *file,
+	loff_t offset,
+	int whence)
+{
+	struct dentry *d = file->f_path.dentry;
+	int srcu_idx;
+	loff_t r;
+
+	r = debugfs_use_file_start(d, &srcu_idx);
+	if (likely(!r))
+		r = seq_lseek(file, offset, whence);
+	debugfs_use_file_finish(srcu_idx);
+	return r;
+}
+
 #define private2dd(file) (file_inode(file)->i_private)
 #define private2ppd(file) (file_inode(file)->i_private)
 
@@ -87,8 +121,8 @@ static int _##name##_open(struct inode *inode, struct file *s) \
 static const struct file_operations _##name##_file_ops = { \
 	.owner   = THIS_MODULE, \
 	.open    = _##name##_open, \
-	.read    = seq_read, \
-	.llseek  = seq_lseek, \
+	.read    = hfi1_seq_read, \
+	.llseek  = hfi1_seq_lseek, \
 	.release = seq_release \
 }
 
@@ -105,11 +139,9 @@ do { \
 	DEBUGFS_FILE_CREATE(#name, parent, data, &_##name##_file_ops, S_IRUGO)
 
 static void *_opcode_stats_seq_start(struct seq_file *s, loff_t *pos)
-__acquires(RCU)
 {
 	struct hfi1_opcode_stats_perctx *opstats;
 
-	rcu_read_lock();
 	if (*pos >= ARRAY_SIZE(opstats->stats))
 		return NULL;
 	return pos;
@@ -126,9 +158,7 @@ static void *_opcode_stats_seq_next(struct seq_file *s, void *v, loff_t *pos)
 }
 
 static void _opcode_stats_seq_stop(struct seq_file *s, void *v)
-__releases(RCU)
 {
-	rcu_read_unlock();
 }
 
 static int _opcode_stats_seq_show(struct seq_file *s, void *v)
@@ -285,12 +315,10 @@ DEBUGFS_SEQ_FILE_OPEN(qp_stats)
 DEBUGFS_FILE_OPS(qp_stats);
 
 static void *_sdes_seq_start(struct seq_file *s, loff_t *pos)
-__acquires(RCU)
 {
 	struct hfi1_ibdev *ibd;
 	struct hfi1_devdata *dd;
 
-	rcu_read_lock();
 	ibd = (struct hfi1_ibdev *)s->private;
 	dd = dd_from_dev(ibd);
 	if (!dd->per_sdma || *pos >= dd->num_sdma)
@@ -310,9 +338,7 @@ static void *_sdes_seq_next(struct seq_file *s, void *v, loff_t *pos)
 }
 
 static void _sdes_seq_stop(struct seq_file *s, void *v)
-__releases(RCU)
 {
-	rcu_read_unlock();
 }
 
 static int _sdes_seq_show(struct seq_file *s, void *v)
@@ -339,11 +365,9 @@ static ssize_t dev_counters_read(struct file *file, char __user *buf,
 	struct hfi1_devdata *dd;
 	ssize_t rval;
 
-	rcu_read_lock();
 	dd = private2dd(file);
 	avail = hfi1_read_cntrs(dd, NULL, &counters);
 	rval =  simple_read_from_buffer(buf, count, ppos, counters, avail);
-	rcu_read_unlock();
 	return rval;
 }
 
@@ -356,11 +380,9 @@ static ssize_t dev_names_read(struct file *file, char __user *buf,
 	struct hfi1_devdata *dd;
 	ssize_t rval;
 
-	rcu_read_lock();
 	dd = private2dd(file);
 	avail = hfi1_read_cntrs(dd, &names, NULL);
 	rval =  simple_read_from_buffer(buf, count, ppos, names, avail);
-	rcu_read_unlock();
 	return rval;
 }
 
@@ -383,11 +405,9 @@ static ssize_t portnames_read(struct file *file, char __user *buf,
 	struct hfi1_devdata *dd;
 	ssize_t rval;
 
-	rcu_read_lock();
 	dd = private2dd(file);
 	avail = hfi1_read_portcntrs(dd->pport, &names, NULL);
 	rval = simple_read_from_buffer(buf, count, ppos, names, avail);
-	rcu_read_unlock();
 	return rval;
 }
 
@@ -400,11 +420,9 @@ static ssize_t portcntrs_debugfs_read(struct file *file, char __user *buf,
 	struct hfi1_pportdata *ppd;
 	ssize_t rval;
 
-	rcu_read_lock();
 	ppd = private2ppd(file);
 	avail = hfi1_read_portcntrs(ppd, NULL, &counters);
 	rval = simple_read_from_buffer(buf, count, ppos, counters, avail);
-	rcu_read_unlock();
 	return rval;
 }
 
@@ -434,16 +452,13 @@ static ssize_t asic_flags_read(struct file *file, char __user *buf,
 	int used;
 	int i;
 
-	rcu_read_lock();
 	ppd = private2ppd(file);
 	dd = ppd->dd;
 	size = PAGE_SIZE;
 	used = 0;
 	tmp = kmalloc(size, GFP_KERNEL);
-	if (!tmp) {
-		rcu_read_unlock();
+	if (!tmp)
 		return -ENOMEM;
-	}
 
 	scratch0 = read_csr(dd, ASIC_CFG_SCRATCH);
 	used += scnprintf(tmp + used, size - used,
@@ -470,7 +485,6 @@ static ssize_t asic_flags_read(struct file *file, char __user *buf,
 	used += scnprintf(tmp + used, size - used, "Write bits to clear\n");
 
 	ret = simple_read_from_buffer(buf, count, ppos, tmp, used);
-	rcu_read_unlock();
 	kfree(tmp);
 	return ret;
 }
@@ -486,15 +500,12 @@ static ssize_t asic_flags_write(struct file *file, const char __user *buf,
 	u64 scratch0;
 	u64 clear;
 
-	rcu_read_lock();
 	ppd = private2ppd(file);
 	dd = ppd->dd;
 
 	buff = kmalloc(count + 1, GFP_KERNEL);
-	if (!buff) {
-		ret = -ENOMEM;
-		goto do_return;
-	}
+	if (!buff)
+		return -ENOMEM;
 
 	ret = copy_from_user(buff, buf, count);
 	if (ret > 0) {
@@ -527,8 +538,6 @@ static ssize_t asic_flags_write(struct file *file, const char __user *buf,
 
  do_free:
 	kfree(buff);
- do_return:
-	rcu_read_unlock();
 	return ret;
 }
 
@@ -542,18 +551,14 @@ static ssize_t qsfp_debugfs_dump(struct file *file, char __user *buf,
 	char *tmp;
 	int ret;
 
-	rcu_read_lock();
 	ppd = private2ppd(file);
 	tmp = kmalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!tmp) {
-		rcu_read_unlock();
+	if (!tmp)
 		return -ENOMEM;
-	}
 
 	ret = qsfp_dump(ppd, tmp, PAGE_SIZE);
 	if (ret > 0)
 		ret = simple_read_from_buffer(buf, count, ppos, tmp, ret);
-	rcu_read_unlock();
 	kfree(tmp);
 	return ret;
 }
@@ -569,7 +574,6 @@ static ssize_t __i2c_debugfs_write(struct file *file, const char __user *buf,
 	int offset;
 	int total_written;
 
-	rcu_read_lock();
 	ppd = private2ppd(file);
 
 	/* byte offset format: [offsetSize][i2cAddr][offsetHigh][offsetLow] */
@@ -577,16 +581,12 @@ static ssize_t __i2c_debugfs_write(struct file *file, const char __user *buf,
 	offset = *ppos & 0xffff;
 
 	/* explicitly reject invalid address 0 to catch cp and cat */
-	if (i2c_addr == 0) {
-		ret = -EINVAL;
-		goto _return;
-	}
+	if (i2c_addr == 0)
+		return -EINVAL;
 
 	buff = kmalloc(count, GFP_KERNEL);
-	if (!buff) {
-		ret = -ENOMEM;
-		goto _return;
-	}
+	if (!buff)
+		return -ENOMEM;
 
 	ret = copy_from_user(buff, buf, count);
 	if (ret > 0) {
@@ -606,8 +606,6 @@ static ssize_t __i2c_debugfs_write(struct file *file, const char __user *buf,
 
  _free:
 	kfree(buff);
- _return:
-	rcu_read_unlock();
 	return ret;
 }
 
@@ -636,7 +634,6 @@ static ssize_t __i2c_debugfs_read(struct file *file, char __user *buf,
 	int offset;
 	int total_read;
 
-	rcu_read_lock();
 	ppd = private2ppd(file);
 
 	/* byte offset format: [offsetSize][i2cAddr][offsetHigh][offsetLow] */
@@ -644,16 +641,12 @@ static ssize_t __i2c_debugfs_read(struct file *file, char __user *buf,
 	offset = *ppos & 0xffff;
 
 	/* explicitly reject invalid address 0 to catch cp and cat */
-	if (i2c_addr == 0) {
-		ret = -EINVAL;
-		goto _return;
-	}
+	if (i2c_addr == 0)
+		return -EINVAL;
 
 	buff = kmalloc(count, GFP_KERNEL);
-	if (!buff) {
-		ret = -ENOMEM;
-		goto _return;
-	}
+	if (!buff)
+		return -ENOMEM;
 
 	total_read = i2c_read(ppd, target, i2c_addr, offset, buff, count);
 	if (total_read < 0) {
@@ -673,8 +666,6 @@ static ssize_t __i2c_debugfs_read(struct file *file, char __user *buf,
 
  _free:
 	kfree(buff);
- _return:
-	rcu_read_unlock();
 	return ret;
 }
 
@@ -701,26 +692,20 @@ static ssize_t __qsfp_debugfs_write(struct file *file, const char __user *buf,
 	int ret;
 	int total_written;
 
-	rcu_read_lock();
-	if (*ppos + count > QSFP_PAGESIZE * 4) { /* base page + page00-page03 */
-		ret = -EINVAL;
-		goto _return;
-	}
+	if (*ppos + count > QSFP_PAGESIZE * 4) /* base page + page00-page03 */
+		return -EINVAL;
 
 	ppd = private2ppd(file);
 
 	buff = kmalloc(count, GFP_KERNEL);
-	if (!buff) {
-		ret = -ENOMEM;
-		goto _return;
-	}
+	if (!buff)
+		return -ENOMEM;
 
 	ret = copy_from_user(buff, buf, count);
 	if (ret > 0) {
 		ret = -EFAULT;
 		goto _free;
 	}
-
 	total_written = qsfp_write(ppd, target, *ppos, buff, count);
 	if (total_written < 0) {
 		ret = total_written;
@@ -733,8 +718,6 @@ static ssize_t __qsfp_debugfs_write(struct file *file, const char __user *buf,
 
  _free:
 	kfree(buff);
- _return:
-	rcu_read_unlock();
 	return ret;
 }
 
@@ -761,7 +744,6 @@ static ssize_t __qsfp_debugfs_read(struct file *file, char __user *buf,
 	int ret;
 	int total_read;
 
-	rcu_read_lock();
 	if (*ppos + count > QSFP_PAGESIZE * 4) { /* base page + page00-page03 */
 		ret = -EINVAL;
 		goto _return;
@@ -794,7 +776,6 @@ static ssize_t __qsfp_debugfs_read(struct file *file, char __user *buf,
  _free:
 	kfree(buff);
  _return:
-	rcu_read_unlock();
 	return ret;
 }
 
@@ -1010,7 +991,6 @@ void hfi1_dbg_ibdev_exit(struct hfi1_ibdev *ibd)
 	debugfs_remove_recursive(ibd->hfi1_ibdev_dbg);
 out:
 	ibd->hfi1_ibdev_dbg = NULL;
-	synchronize_rcu();
 }
 
 /*
@@ -1035,9 +1015,7 @@ static const char * const hfi1_statnames[] = {
 };
 
 static void *_driver_stats_names_seq_start(struct seq_file *s, loff_t *pos)
-__acquires(RCU)
 {
-	rcu_read_lock();
 	if (*pos >= ARRAY_SIZE(hfi1_statnames))
 		return NULL;
 	return pos;
@@ -1055,9 +1033,7 @@ static void *_driver_stats_names_seq_next(
 }
 
 static void _driver_stats_names_seq_stop(struct seq_file *s, void *v)
-__releases(RCU)
 {
-	rcu_read_unlock();
 }
 
 static int _driver_stats_names_seq_show(struct seq_file *s, void *v)
@@ -1073,9 +1049,7 @@ DEBUGFS_SEQ_FILE_OPEN(driver_stats_names)
 DEBUGFS_FILE_OPS(driver_stats_names);
 
 static void *_driver_stats_seq_start(struct seq_file *s, loff_t *pos)
-__acquires(RCU)
 {
-	rcu_read_lock();
 	if (*pos >= ARRAY_SIZE(hfi1_statnames))
 		return NULL;
 	return pos;
@@ -1090,9 +1064,7 @@ static void *_driver_stats_seq_next(struct seq_file *s, void *v, loff_t *pos)
 }
 
 static void _driver_stats_seq_stop(struct seq_file *s, void *v)
-__releases(RCU)
 {
-	rcu_read_unlock();
 }
 
 static u64 hfi1_sps_ints(void)

drivers/infiniband/hw/hfi1/hfi.h

@@ -605,6 +605,7 @@ struct hfi1_pportdata {
 	struct work_struct freeze_work;
 	struct work_struct link_downgrade_work;
 	struct work_struct link_bounce_work;
+	struct delayed_work start_link_work;
 	/* host link state variables */
 	struct mutex hls_lock;
 	u32 host_link_state;
@@ -659,6 +660,7 @@ struct hfi1_pportdata {
 	u8 linkinit_reason;
 	u8 local_tx_rate;	/* rate given to 8051 firmware */
 	u8 last_pstate;		/* info only */
+	u8 qsfp_retry_count;
 
 	/* placeholders for IB MAD packet settings */
 	u8 overrun_threshold;
@@ -1804,7 +1806,7 @@ extern unsigned int hfi1_max_mtu;
 extern unsigned int hfi1_cu;
 extern unsigned int user_credit_return_threshold;
 extern int num_user_contexts;
-extern unsigned n_krcvqs;
+extern unsigned long n_krcvqs;
 extern uint krcvqs[];
 extern int krcvqsset;
 extern uint kdeth_qp;

drivers/infiniband/hw/hfi1/init.c

@@ -94,7 +94,7 @@ module_param_array(krcvqs, uint, &krcvqsset, S_IRUGO);
 MODULE_PARM_DESC(krcvqs, "Array of the number of non-control kernel receive queues by VL");
 
 /* computed based on above array */
-unsigned n_krcvqs;
+unsigned long n_krcvqs;
 
 static unsigned hfi1_rcvarr_split = 25;
 module_param_named(rcvarr_split, hfi1_rcvarr_split, uint, S_IRUGO);
@@ -500,6 +500,7 @@ void hfi1_init_pportdata(struct pci_dev *pdev, struct hfi1_pportdata *ppd,
 	INIT_WORK(&ppd->link_downgrade_work, handle_link_downgrade);
 	INIT_WORK(&ppd->sma_message_work, handle_sma_message);
 	INIT_WORK(&ppd->link_bounce_work, handle_link_bounce);
+	INIT_DELAYED_WORK(&ppd->start_link_work, handle_start_link);
 	INIT_WORK(&ppd->linkstate_active_work, receive_interrupt_work);
 	INIT_WORK(&ppd->qsfp_info.qsfp_work, qsfp_event);
 

drivers/infiniband/hw/hfi1/mad.c

@@ -2604,7 +2604,7 @@ static int pma_get_opa_datacounters(struct opa_pma_mad *pmp,
 	u8 lq, num_vls;
 	u8 res_lli, res_ler;
 	u64 port_mask;
-	unsigned long port_num;
+	u8 port_num;
 	unsigned long vl;
 	u32 vl_select_mask;
 	int vfi;
@@ -2638,9 +2638,9 @@ static int pma_get_opa_datacounters(struct opa_pma_mad *pmp,
 	 */
 	port_mask = be64_to_cpu(req->port_select_mask[3]);
 	port_num = find_first_bit((unsigned long *)&port_mask,
-				  sizeof(port_mask));
+				  sizeof(port_mask) * 8);
 
-	if ((u8)port_num != port) {
+	if (port_num != port) {
 		pmp->mad_hdr.status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)pmp);
 	}
@@ -2842,7 +2842,7 @@ static int pma_get_opa_porterrors(struct opa_pma_mad *pmp,
 	 */
 	port_mask = be64_to_cpu(req->port_select_mask[3]);
 	port_num = find_first_bit((unsigned long *)&port_mask,
-				  sizeof(port_mask));
+				  sizeof(port_mask) * 8);
 
 	if (port_num != port) {
 		pmp->mad_hdr.status |= IB_SMP_INVALID_FIELD;
@@ -3015,7 +3015,7 @@ static int pma_get_opa_errorinfo(struct opa_pma_mad *pmp,
 	 */
 	port_mask = be64_to_cpu(req->port_select_mask[3]);
 	port_num = find_first_bit((unsigned long *)&port_mask,
-				  sizeof(port_mask));
+				  sizeof(port_mask) * 8);
 
 	if (port_num != port) {
 		pmp->mad_hdr.status |= IB_SMP_INVALID_FIELD;
@@ -3252,7 +3252,7 @@ static int pma_set_opa_errorinfo(struct opa_pma_mad *pmp,
 	 */
 	port_mask = be64_to_cpu(req->port_select_mask[3]);
 	port_num = find_first_bit((unsigned long *)&port_mask,
-				  sizeof(port_mask));
+				  sizeof(port_mask) * 8);
 
 	if (port_num != port) {
 		pmp->mad_hdr.status |= IB_SMP_INVALID_FIELD;

drivers/infiniband/hw/hfi1/pio_copy.c

@@ -771,6 +771,9 @@ void seg_pio_copy_mid(struct pio_buf *pbuf, const void *from, size_t nbytes)
 			read_extra_bytes(pbuf, from, to_fill);
 			from += to_fill;
 			nbytes -= to_fill;
+			/* may not be enough valid bytes left to align */
+			if (extra > nbytes)
+				extra = nbytes;
 
 			/* ...now write carry */
 			dest = pbuf->start + (pbuf->qw_written * sizeof(u64));
@@ -798,6 +801,15 @@ void seg_pio_copy_mid(struct pio_buf *pbuf, const void *from, size_t nbytes)
 			read_low_bytes(pbuf, from, extra);
 			from += extra;
 			nbytes -= extra;
+			/*
+			 * If no bytes are left, return early - we are done.
+			 * NOTE: This short-circuit is *required* because
+			 * "extra" may have been reduced in size and "from"
+			 * is not aligned, as required when leaving this
+			 * if block.
+			 */
+			if (nbytes == 0)
+				return;
 		}
 
 		/* at this point, from is QW aligned */

drivers/infiniband/hw/hfi1/user_sdma.c

@@ -114,6 +114,8 @@ MODULE_PARM_DESC(sdma_comp_size, "Size of User SDMA completion ring. Default: 12
 #define KDETH_HCRC_LOWER_SHIFT    24
 #define KDETH_HCRC_LOWER_MASK     0xff
 
+#define AHG_KDETH_INTR_SHIFT 12
+
 #define PBC2LRH(x) ((((x) & 0xfff) << 2) - 4)
 #define LRH2PBC(x) ((((x) >> 2) + 1) & 0xfff)
 
@@ -1480,7 +1482,8 @@ static int set_txreq_header_ahg(struct user_sdma_request *req,
 		/* Clear KDETH.SH on last packet */
 		if (unlikely(tx->flags & TXREQ_FLAGS_REQ_LAST_PKT)) {
 			val |= cpu_to_le16(KDETH_GET(hdr->kdeth.ver_tid_offset,
-								INTR) >> 16);
+						     INTR) <<
+					   AHG_KDETH_INTR_SHIFT);
 			val &= cpu_to_le16(~(1U << 13));
 			AHG_HEADER_SET(req->ahg, diff, 7, 16, 14, val);
 		} else {

drivers/infiniband/hw/i40iw/i40iw_hw.c

@@ -265,6 +265,7 @@ void i40iw_next_iw_state(struct i40iw_qp *iwqp,
 		info.dont_send_fin = false;
 	if (iwqp->sc_qp.term_flags && (state == I40IW_QP_STATE_ERROR))
 		info.reset_tcp_conn = true;
+	iwqp->hw_iwarp_state = state;
 	i40iw_hw_modify_qp(iwqp->iwdev, iwqp, &info, 0);
 }
 

drivers/infiniband/hw/i40iw/i40iw_main.c

@@ -100,7 +100,7 @@ static struct notifier_block i40iw_net_notifier = {
 	.notifier_call = i40iw_net_event
 };
 
-static int i40iw_notifiers_registered;
+static atomic_t i40iw_notifiers_registered;
 
 /**
  * i40iw_find_i40e_handler - find a handler given a client info
@@ -1342,12 +1342,11 @@ exit:
  */
 static void i40iw_register_notifiers(void)
 {
-	if (!i40iw_notifiers_registered) {
+	if (atomic_inc_return(&i40iw_notifiers_registered) == 1) {
 		register_inetaddr_notifier(&i40iw_inetaddr_notifier);
 		register_inet6addr_notifier(&i40iw_inetaddr6_notifier);
 		register_netevent_notifier(&i40iw_net_notifier);
 	}
-	i40iw_notifiers_registered++;
 }
 
 /**
@@ -1429,8 +1428,7 @@ static void i40iw_deinit_device(struct i40iw_device *iwdev, bool reset, bool del
 			i40iw_del_macip_entry(iwdev, (u8)iwdev->mac_ip_table_idx);
 		/* fallthrough */
 	case INET_NOTIFIER:
-		if (i40iw_notifiers_registered > 0) {
-			i40iw_notifiers_registered--;
+		if (!atomic_dec_return(&i40iw_notifiers_registered)) {
 			unregister_netevent_notifier(&i40iw_net_notifier);
 			unregister_inetaddr_notifier(&i40iw_inetaddr_notifier);
 			unregister_inet6addr_notifier(&i40iw_inetaddr6_notifier);

drivers/infiniband/hw/mlx4/cq.c

@@ -687,12 +687,6 @@ repoll:
 	is_error = (cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) ==
 		MLX4_CQE_OPCODE_ERROR;
 
-	if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == MLX4_OPCODE_NOP &&
-		     is_send)) {
-		pr_warn("Completion for NOP opcode detected!\n");
-		return -EAGAIN;
-	}
-
 	/* Resize CQ in progress */
 	if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == MLX4_CQE_OPCODE_RESIZE)) {
 		if (cq->resize_buf) {
@@ -718,12 +712,6 @@ repoll:
 		 */
 		mqp = __mlx4_qp_lookup(to_mdev(cq->ibcq.device)->dev,
 				       be32_to_cpu(cqe->vlan_my_qpn));
-		if (unlikely(!mqp)) {
-			pr_warn("CQ %06x with entry for unknown QPN %06x\n",
-			       cq->mcq.cqn, be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_QPN_MASK);
-			return -EAGAIN;
-		}
-
 		*cur_qp = to_mibqp(mqp);
 	}
 
@@ -736,11 +724,6 @@ repoll:
 		/* SRQ is also in the radix tree */
 		msrq = mlx4_srq_lookup(to_mdev(cq->ibcq.device)->dev,
 				       srq_num);
-		if (unlikely(!msrq)) {
-			pr_warn("CQ %06x with entry for unknown SRQN %06x\n",
-				cq->mcq.cqn, srq_num);
-			return -EAGAIN;
-		}
 	}
 
 	if (is_send) {
@@ -891,7 +874,6 @@ int mlx4_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
 	struct mlx4_ib_qp *cur_qp = NULL;
 	unsigned long flags;
 	int npolled;
-	int err = 0;
 	struct mlx4_ib_dev *mdev = to_mdev(cq->ibcq.device);
 
 	spin_lock_irqsave(&cq->lock, flags);
@@ -901,8 +883,7 @@ int mlx4_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
 	}
 
 	for (npolled = 0; npolled < num_entries; ++npolled) {
-		err = mlx4_ib_poll_one(cq, &cur_qp, wc + npolled);
-		if (err)
+		if (mlx4_ib_poll_one(cq, &cur_qp, wc + npolled))
 			break;
 	}
 
@@ -911,10 +892,7 @@ int mlx4_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
 out:
 	spin_unlock_irqrestore(&cq->lock, flags);
 
-	if (err == 0 || err == -EAGAIN)
-		return npolled;
-	else
-		return err;
+	return npolled;
 }
 
 int mlx4_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)

drivers/infiniband/hw/mlx5/cq.c

@@ -553,12 +553,6 @@ repoll:
 		 * from the table.
 		 */
 		mqp = __mlx5_qp_lookup(dev->mdev, qpn);
-		if (unlikely(!mqp)) {
-			mlx5_ib_warn(dev, "CQE@CQ %06x for unknown QPN %6x\n",
-				     cq->mcq.cqn, qpn);
-			return -EINVAL;
-		}
-
 		*cur_qp = to_mibqp(mqp);
 	}
 
@@ -619,13 +613,6 @@ repoll:
 		read_lock(&dev->mdev->priv.mkey_table.lock);
 		mmkey = __mlx5_mr_lookup(dev->mdev,
 					 mlx5_base_mkey(be32_to_cpu(sig_err_cqe->mkey)));
-		if (unlikely(!mmkey)) {
-			read_unlock(&dev->mdev->priv.mkey_table.lock);
-			mlx5_ib_warn(dev, "CQE@CQ %06x for unknown MR %6x\n",
-				     cq->mcq.cqn, be32_to_cpu(sig_err_cqe->mkey));
-			return -EINVAL;
-		}
-
 		mr = to_mibmr(mmkey);
 		get_sig_err_item(sig_err_cqe, &mr->sig->err_item);
 		mr->sig->sig_err_exists = true;
@@ -676,7 +663,6 @@ int mlx5_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
 	unsigned long flags;
 	int soft_polled = 0;
 	int npolled;
-	int err = 0;
 
 	spin_lock_irqsave(&cq->lock, flags);
 	if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
@@ -688,8 +674,7 @@ int mlx5_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
 		soft_polled = poll_soft_wc(cq, num_entries, wc);
 
 	for (npolled = 0; npolled < num_entries - soft_polled; npolled++) {
-		err = mlx5_poll_one(cq, &cur_qp, wc + soft_polled + npolled);
-		if (err)
+		if (mlx5_poll_one(cq, &cur_qp, wc + soft_polled + npolled))
 			break;
 	}
 
@@ -698,10 +683,7 @@ int mlx5_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
 out:
 	spin_unlock_irqrestore(&cq->lock, flags);
 
-	if (err == 0 || err == -EAGAIN)
-		return soft_polled + npolled;
-	else
-		return err;
+	return soft_polled + npolled;
 }
 
 int mlx5_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)

drivers/infiniband/hw/mlx5/main.c

@@ -1849,6 +1849,7 @@ static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp,
 					   int domain)
 {
 	struct mlx5_ib_dev *dev = to_mdev(qp->device);
+	struct mlx5_ib_qp *mqp = to_mqp(qp);
 	struct mlx5_ib_flow_handler *handler = NULL;
 	struct mlx5_flow_destination *dst = NULL;
 	struct mlx5_ib_flow_prio *ft_prio;
@@ -1875,7 +1876,10 @@ static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp,
 	}
 
 	dst->type = MLX5_FLOW_DESTINATION_TYPE_TIR;
-	dst->tir_num = to_mqp(qp)->raw_packet_qp.rq.tirn;
+	if (mqp->flags & MLX5_IB_QP_RSS)
+		dst->tir_num = mqp->rss_qp.tirn;
+	else
+		dst->tir_num = mqp->raw_packet_qp.rq.tirn;
 
 	if (flow_attr->type == IB_FLOW_ATTR_NORMAL) {
 		if (flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP)  {

drivers/infiniband/hw/mlx5/mem.c

@@ -71,7 +71,7 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift,
 
 	addr = addr >> page_shift;
 	tmp = (unsigned long)addr;
-	m = find_first_bit(&tmp, sizeof(tmp));
+	m = find_first_bit(&tmp, BITS_PER_LONG);
 	skip = 1 << m;
 	mask = skip - 1;
 	i = 0;
@@ -81,7 +81,7 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift,
 		for (k = 0; k < len; k++) {
 			if (!(i & mask)) {
 				tmp = (unsigned long)pfn;
-				m = min_t(unsigned long, m, find_first_bit(&tmp, sizeof(tmp)));
+				m = min_t(unsigned long, m, find_first_bit(&tmp, BITS_PER_LONG));
 				skip = 1 << m;
 				mask = skip - 1;
 				base = pfn;
@@ -89,7 +89,7 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift,
 			} else {
 				if (base + p != pfn) {
 					tmp = (unsigned long)p;
-					m = find_first_bit(&tmp, sizeof(tmp));
+					m = find_first_bit(&tmp, BITS_PER_LONG);
 					skip = 1 << m;
 					mask = skip - 1;
 					base = pfn;

drivers/infiniband/hw/mlx5/mlx5_ib.h

@@ -402,6 +402,7 @@ enum mlx5_ib_qp_flags {
 	/* QP uses 1 as its source QP number */
 	MLX5_IB_QP_SQPN_QP1			= 1 << 6,
 	MLX5_IB_QP_CAP_SCATTER_FCS		= 1 << 7,
+	MLX5_IB_QP_RSS				= 1 << 8,
 };
 
 struct mlx5_umr_wr {

drivers/infiniband/hw/mlx5/qp.c

@@ -1449,6 +1449,7 @@ create_tir:
 	kvfree(in);
 	/* qpn is reserved for that QP */
 	qp->trans_qp.base.mqp.qpn = 0;
+	qp->flags |= MLX5_IB_QP_RSS;
 	return 0;
 
 err:
@@ -3658,12 +3659,8 @@ static int begin_wqe(struct mlx5_ib_qp *qp, void **seg,
 		     struct ib_send_wr *wr, unsigned *idx,
 		     int *size, int nreq)
 {
-	int err = 0;
-
-	if (unlikely(mlx5_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq))) {
-		err = -ENOMEM;
-		return err;
-	}
+	if (unlikely(mlx5_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq)))
+		return -ENOMEM;
 
 	*idx = qp->sq.cur_post & (qp->sq.wqe_cnt - 1);
 	*seg = mlx5_get_send_wqe(qp, *idx);
@@ -3679,7 +3676,7 @@ static int begin_wqe(struct mlx5_ib_qp *qp, void **seg,
 	*seg += sizeof(**ctrl);
 	*size = sizeof(**ctrl) / 16;
 
-	return err;
+	return 0;
 }
 
 static void finish_wqe(struct mlx5_ib_qp *qp,
@@ -3758,7 +3755,7 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		num_sge = wr->num_sge;
 		if (unlikely(num_sge > qp->sq.max_gs)) {
 			mlx5_ib_warn(dev, "\n");
-			err = -ENOMEM;
+			err = -EINVAL;
 			*bad_wr = wr;
 			goto out;
 		}

drivers/infiniband/ulp/ipoib/ipoib.h

@@ -478,6 +478,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb,
 		struct ipoib_ah *address, u32 qpn);
 void ipoib_reap_ah(struct work_struct *work);
 
+struct ipoib_path *__path_find(struct net_device *dev, void *gid);
 void ipoib_mark_paths_invalid(struct net_device *dev);
 void ipoib_flush_paths(struct net_device *dev);
 int ipoib_check_sm_sendonly_fullmember_support(struct ipoib_dev_priv *priv);

drivers/infiniband/ulp/ipoib/ipoib_cm.c

@@ -1318,6 +1318,8 @@ void ipoib_cm_destroy_tx(struct ipoib_cm_tx *tx)
 	}
 }
 
+#define QPN_AND_OPTIONS_OFFSET	4
+
 static void ipoib_cm_tx_start(struct work_struct *work)
 {
 	struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv,
@@ -1326,6 +1328,7 @@ static void ipoib_cm_tx_start(struct work_struct *work)
 	struct ipoib_neigh *neigh;
 	struct ipoib_cm_tx *p;
 	unsigned long flags;
+	struct ipoib_path *path;
 	int ret;
 
 	struct ib_sa_path_rec pathrec;
@@ -1338,7 +1341,19 @@ static void ipoib_cm_tx_start(struct work_struct *work)
 		p = list_entry(priv->cm.start_list.next, typeof(*p), list);
 		list_del_init(&p->list);
 		neigh = p->neigh;
+
 		qpn = IPOIB_QPN(neigh->daddr);
+		/*
+		 * As long as the search is with these 2 locks,
+		 * path existence indicates its validity.
+		 */
+		path = __path_find(dev, neigh->daddr + QPN_AND_OPTIONS_OFFSET);
+		if (!path) {
+			pr_info("%s ignore not valid path %pI6\n",
+				__func__,
+				neigh->daddr + QPN_AND_OPTIONS_OFFSET);
+			goto free_neigh;
+		}
 		memcpy(&pathrec, &p->path->pathrec, sizeof pathrec);
 
 		spin_unlock_irqrestore(&priv->lock, flags);
@@ -1350,6 +1365,7 @@ static void ipoib_cm_tx_start(struct work_struct *work)
 		spin_lock_irqsave(&priv->lock, flags);
 
 		if (ret) {
+free_neigh:
 			neigh = p->neigh;
 			if (neigh) {
 				neigh->cm = NULL;

drivers/infiniband/ulp/ipoib/ipoib_main.c

@@ -485,7 +485,7 @@ int ipoib_set_mode(struct net_device *dev, const char *buf)
 	return -EINVAL;
 }
 
-static struct ipoib_path *__path_find(struct net_device *dev, void *gid)
+struct ipoib_path *__path_find(struct net_device *dev, void *gid)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct rb_node *n = priv->path_tree.rb_node;

drivers/infiniband/ulp/isert/ib_isert.c

@@ -403,6 +403,7 @@ isert_init_conn(struct isert_conn *isert_conn)
 	INIT_LIST_HEAD(&isert_conn->node);
 	init_completion(&isert_conn->login_comp);
 	init_completion(&isert_conn->login_req_comp);
+	init_waitqueue_head(&isert_conn->rem_wait);
 	kref_init(&isert_conn->kref);
 	mutex_init(&isert_conn->mutex);
 	INIT_WORK(&isert_conn->release_work, isert_release_work);
@@ -578,7 +579,8 @@ isert_connect_release(struct isert_conn *isert_conn)
 	BUG_ON(!device);
 
 	isert_free_rx_descriptors(isert_conn);
-	if (isert_conn->cm_id)
+	if (isert_conn->cm_id &&
+	    !isert_conn->dev_removed)
 		rdma_destroy_id(isert_conn->cm_id);
 
 	if (isert_conn->qp) {
@@ -593,7 +595,10 @@ isert_connect_release(struct isert_conn *isert_conn)
 
 	isert_device_put(device);
 
-	kfree(isert_conn);
+	if (isert_conn->dev_removed)
+		wake_up_interruptible(&isert_conn->rem_wait);
+	else
+		kfree(isert_conn);
 }
 
 static void
@@ -753,6 +758,7 @@ static int
 isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 {
 	struct isert_np *isert_np = cma_id->context;
+	struct isert_conn *isert_conn;
 	int ret = 0;
 
 	isert_info("%s (%d): status %d id %p np %p\n",
@@ -773,10 +779,21 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 		break;
 	case RDMA_CM_EVENT_ADDR_CHANGE:    /* FALLTHRU */
 	case RDMA_CM_EVENT_DISCONNECTED:   /* FALLTHRU */
-	case RDMA_CM_EVENT_DEVICE_REMOVAL: /* FALLTHRU */
 	case RDMA_CM_EVENT_TIMEWAIT_EXIT:  /* FALLTHRU */
 		ret = isert_disconnected_handler(cma_id, event->event);
 		break;
+	case RDMA_CM_EVENT_DEVICE_REMOVAL:
+		isert_conn = cma_id->qp->qp_context;
+		isert_conn->dev_removed = true;
+		isert_disconnected_handler(cma_id, event->event);
+		wait_event_interruptible(isert_conn->rem_wait,
+					 isert_conn->state == ISER_CONN_DOWN);
+		kfree(isert_conn);
+		/*
+		 * return non-zero from the callback to destroy
+		 * the rdma cm id
+		 */
+		return 1;
 	case RDMA_CM_EVENT_REJECTED:       /* FALLTHRU */
 	case RDMA_CM_EVENT_UNREACHABLE:    /* FALLTHRU */
 	case RDMA_CM_EVENT_CONNECT_ERROR:

drivers/infiniband/ulp/isert/ib_isert.h

@@ -158,6 +158,8 @@ struct isert_conn {
 	struct work_struct	release_work;
 	bool                    logout_posted;
 	bool                    snd_w_inv;
+	wait_queue_head_t	rem_wait;
+	bool			dev_removed;
 };
 
 #define ISERT_MAX_CQ 64