From 97989356af0ec8b1b1658d804892abb354127330 Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Thu, 6 Mar 2014 18:28:17 +0200 Subject: [PATCH] net/mlx4_core: mlx4_init_slave() shouldn't access comm channel before PF is ready Currently, the PF call to pci_enable_sriov from the PF probe function stalls for 10 seconds times the number of VFs probed on the host. This happens because the way for such VFs to determine of the PF initialization finished, is by attempting to issue reset on the comm-channel and get timeout (after 10s). The PF probe function is called from a kenernel workqueue, and therefore during that time, rcu lock is being held and kernel's workqueue is stalled. This blocks other processes that try to use the workqueue or rcu lock. For example, interface renaming which is calling rcu_synchronize is blocked, and timedout by systemd. Changed mlx4_init_slave() to allow VF probed on the host to immediatly detect that the PF is not ready, and return EPROBE_DEFER instantly. Only when the PF finishes the initialization, allow such VFs to access the comm channel. This issue and fix are relevant only for probed VFs on the hypervisor, there is no way to pass this information to a VM until comm channel is ready, so in a VM, if PF is not ready, the first command will be timedout after 10 seconds and return EPROBE_DEFER. Signed-off-by: Amir Vadai Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/main.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 5a6105f1ba6d..30a08a60f059 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -150,6 +150,8 @@ struct mlx4_port_config { struct pci_dev *pdev; }; +static atomic_t pf_loading = ATOMIC_INIT(0); + int mlx4_check_port_params(struct mlx4_dev *dev, enum mlx4_port_type *port_type) { @@ -1407,6 +1409,11 @@ static int mlx4_init_slave(struct mlx4_dev *dev) u32 slave_read; u32 cmd_channel_ver; + if (atomic_read(&pf_loading)) { + mlx4_warn(dev, "PF is not ready. Deferring probe\n"); + return -EPROBE_DEFER; + } + mutex_lock(&priv->cmd.slave_cmd_mutex); priv->cmd.max_cmds = 1; mlx4_warn(dev, "Sending reset\n"); @@ -2319,7 +2326,11 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data) if (num_vfs) { mlx4_warn(dev, "Enabling SR-IOV with %d VFs\n", num_vfs); + + atomic_inc(&pf_loading); err = pci_enable_sriov(pdev, num_vfs); + atomic_dec(&pf_loading); + if (err) { mlx4_err(dev, "Failed to enable SR-IOV, continuing without SR-IOV (err = %d).\n", err); -- 2.11.0