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

Pull rdma fixes from Jason Gunthorpe:
 "This is the next batch of for-rc patches from RDMA. It includes the
  fix for the ipoib regression I mentioned last time, and the result of
  a fairly major debugging effort to get iser working reliably on cxgb4
  hardware - it turns out the cxgb4 driver was not handling QP error
  flushing properly causing iser to fail.

   - cxgb4 fix for an iser testing failure as debugged by Steve and
     Sagi. The problem was a driver bug in the handling of shutting down
     a QP.

   - Various vmw_pvrdma fixes for bogus WARN_ON, missed resource free on
     error unwind and a use after free bug

   - Improper congestion counter values on mlx5 when link aggregation is
     enabled

   - ipoib lockdep regression introduced in this merge window

   - hfi1 regression supporting the device in a VM introduced in a
     recent patch

   - Typo that breaks future uAPI compatibility in the verbs core

   - More SELinux related oops fixing

   - Fix an oops during error unwind in mlx5"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  IB/mlx5: Fix mlx5_ib_alloc_mr error flow
  IB/core: Verify that QP is security enabled in create and destroy
  IB/uverbs: Fix command checking as part of ib_uverbs_ex_modify_qp()
  IB/mlx5: Serialize access to the VMA list
  IB/hfi: Only read capability registers if the capability exists
  IB/ipoib: Fix lockdep issue found on ipoib_ib_dev_heavy_flush
  IB/mlx5: Fix congestion counters in LAG mode
  RDMA/vmw_pvrdma: Avoid use after free due to QP/CQ/SRQ destroy
  RDMA/vmw_pvrdma: Use refcount_dec_and_test to avoid warning
  RDMA/vmw_pvrdma: Call ib_umem_release on destroy QP path
  iw_cxgb4: when flushing, complete all wrs in a chain
  iw_cxgb4: reflect the original WR opcode in drain cqes
  iw_cxgb4: Only validate the MSN for successful completions

1 files changed, 56 insertions, 0 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index f26f97fe4666..582b2f18010a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -137,6 +137,17 @@ int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev)
 }
 EXPORT_SYMBOL(mlx5_cmd_destroy_vport_lag);
 
+static int mlx5_cmd_query_cong_counter(struct mlx5_core_dev *dev,
+				       bool reset, void *out, int out_size)
+{
+	u32 in[MLX5_ST_SZ_DW(query_cong_statistics_in)] = { };
+
+	MLX5_SET(query_cong_statistics_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_CONG_STATISTICS);
+	MLX5_SET(query_cong_statistics_in, in, clear, reset);
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size);
+}
+
 static struct mlx5_lag *mlx5_lag_dev_get(struct mlx5_core_dev *dev)
 {
 	return dev->priv.lag;
@@ -633,3 +644,48 @@ bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv)
 	/* If bonded, we do not add an IB device for PF1. */
 	return false;
 }
+
+int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
+				 u64 *values,
+				 int num_counters,
+				 size_t *offsets)
+{
+	int outlen = MLX5_ST_SZ_BYTES(query_cong_statistics_out);
+	struct mlx5_core_dev *mdev[MLX5_MAX_PORTS];
+	struct mlx5_lag *ldev;
+	int num_ports;
+	int ret, i, j;
+	void *out;
+
+	out = kvzalloc(outlen, GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+
+	memset(values, 0, sizeof(*values) * num_counters);
+
+	mutex_lock(&lag_mutex);
+	ldev = mlx5_lag_dev_get(dev);
+	if (ldev && mlx5_lag_is_bonded(ldev)) {
+		num_ports = MLX5_MAX_PORTS;
+		mdev[0] = ldev->pf[0].dev;
+		mdev[1] = ldev->pf[1].dev;
+	} else {
+		num_ports = 1;
+		mdev[0] = dev;
+	}
+
+	for (i = 0; i < num_ports; ++i) {
+		ret = mlx5_cmd_query_cong_counter(mdev[i], false, out, outlen);
+		if (ret)
+			goto unlock;
+
+		for (j = 0; j < num_counters; ++j)
+			values[j] += be64_to_cpup((__be64 *)(out + offsets[j]));
+	}
+
+unlock:
+	mutex_unlock(&lag_mutex);
+	kvfree(out);
+	return ret;
+}
+EXPORT_SYMBOL(mlx5_lag_query_cong_counters);