Merge tag 'mlx5e-failsafe' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5e-failsafe 27-03-2017

This series provides a fail-safe mechanism to allow safely re-configuring
mlx5e netdevice and provides a resiliency against sporadic
configuration failures.

To enable this we do some refactoring and code reorganizing to allow
breaking the drivers open/close flows to stages:
      open -> activate -> deactivate -> close.

In addition we need to allow creating fresh HW ring resources
(mlx5e_channels) with their own "new" set of parameters, while keeping
the current ones running and active until the new channels are
successfully created with the new configuration, and only then we can
safly replace (switch) old channels with new ones.

For that we introduce mlx5e_channels object and an API to manage it:
 - channels = open_channels(new_params):
   open fresh TX/RX channels
 - activate_channels(channels):
   redirect traffic to them and attach them to the netdev
 - deactivate_channes(channels)
   stop traffic and detach from netdev
 - close(channels)
   Free the TX/RX HW resources of those channels

With the above strategy it is straightforward to achieve the desired
behavior of fail-safe configuration.  In pseudo code:

make_new_config(new_params)
{
	old_channels = current_active_channels;
	new_channels = create_channels(new_params);
	if (!new_channels)
		return "Failed, but current channels are still active :)"

	deactivate_channels(old_channels); /* Can't fail */
	set_hw_new_state();                /* If needed  */
	activate_channels(new_channels);   /* Can't fail */
	close_channels(old_channels);
	current_active_channels = new_channels;

        return "SUCCESS";
}

At the top of this series, we change the following flows to be fail-safe:
ethtool:
   - ring parameters
   - coalesce parameters
   - tx copy break parameters
   - cqe compressing/moderation mode setting (priv flags)
ndos:
   - tc setup
   - set features: LRO
   - change mtu
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -182,15 +182,15 @@ enum mlx5e_priv_flag {
 	MLX5E_PFLAG_RX_CQE_COMPRESS = (1 << 1),
 };
 
-#define MLX5E_SET_PFLAG(priv, pflag, enable)			\
+#define MLX5E_SET_PFLAG(params, pflag, enable)			\
 	do {							\
 		if (enable)					\
-			(priv)->params.pflags |= (pflag);	\
+			(params)->pflags |= (pflag);		\
 		else						\
-			(priv)->params.pflags &= ~(pflag);	\
+			(params)->pflags &= ~(pflag);		\
 	} while (0)
 
-#define MLX5E_GET_PFLAG(priv, pflag) (!!((priv)->params.pflags & (pflag)))
+#define MLX5E_GET_PFLAG(params, pflag) (!!((params)->pflags & (pflag)))
 
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 #define MLX5E_MAX_BW_ALLOC 100 /* Max percentage of BW allocation */
@@ -213,7 +213,6 @@ struct mlx5e_params {
 	bool rx_cqe_compress_def;
 	struct mlx5e_cq_moder rx_cq_moderation;
 	struct mlx5e_cq_moder tx_cq_moderation;
-	u16 min_rx_wqes;
 	bool lro_en;
 	u32 lro_wqe_sz;
 	u16 tx_max_inline;
@@ -225,6 +224,7 @@ struct mlx5e_params {
 	bool rx_am_enabled;
 	u32 lro_timeout;
 	u32 pflags;
+	struct bpf_prog *xdp_prog;
 };
 
 #ifdef CONFIG_MLX5_CORE_EN_DCB
@@ -280,7 +280,6 @@ struct mlx5e_cq {
 	struct napi_struct        *napi;
 	struct mlx5_core_cq        mcq;
 	struct mlx5e_channel      *channel;
-	struct mlx5e_priv         *priv;
 
 	/* cqe decompression */
 	struct mlx5_cqe64          title;
@@ -290,6 +289,7 @@ struct mlx5e_cq {
 	u16                        decmprs_wqe_counter;
 
 	/* control */
+	struct mlx5_core_dev      *mdev;
 	struct mlx5_frag_wq_ctrl   wq_ctrl;
 } ____cacheline_aligned_in_smp;
 
@@ -357,7 +357,7 @@ struct mlx5e_txqsq {
 	/* control path */
 	struct mlx5_wq_ctrl        wq_ctrl;
 	struct mlx5e_channel      *channel;
-	int                        tc;
+	int                        txq_ix;
 	u32                        rate_limit;
 } ____cacheline_aligned_in_smp;
 
@@ -533,7 +533,7 @@ struct mlx5e_rq {
 	u32                    mpwqe_num_strides;
 	u32                    rqn;
 	struct mlx5e_channel  *channel;
-	struct mlx5e_priv     *priv;
+	struct mlx5_core_dev  *mdev;
 	struct mlx5_core_mkey  umr_mkey;
 } ____cacheline_aligned_in_smp;
 
@@ -556,10 +556,18 @@ struct mlx5e_channel {
 
 	/* control */
 	struct mlx5e_priv         *priv;
+	struct mlx5_core_dev      *mdev;
+	struct mlx5e_tstamp       *tstamp;
 	int                        ix;
 	int                        cpu;
 };
 
+struct mlx5e_channels {
+	struct mlx5e_channel **c;
+	unsigned int           num;
+	struct mlx5e_params    params;
+};
+
 enum mlx5e_traffic_types {
 	MLX5E_TT_IPV4_TCP,
 	MLX5E_TT_IPV6_TCP,
@@ -709,34 +717,17 @@ enum {
 	MLX5E_NIC_PRIO
 };
 
-struct mlx5e_profile {
-	void	(*init)(struct mlx5_core_dev *mdev,
-			struct net_device *netdev,
-			const struct mlx5e_profile *profile, void *ppriv);
-	void	(*cleanup)(struct mlx5e_priv *priv);
-	int	(*init_rx)(struct mlx5e_priv *priv);
-	void	(*cleanup_rx)(struct mlx5e_priv *priv);
-	int	(*init_tx)(struct mlx5e_priv *priv);
-	void	(*cleanup_tx)(struct mlx5e_priv *priv);
-	void	(*enable)(struct mlx5e_priv *priv);
-	void	(*disable)(struct mlx5e_priv *priv);
-	void	(*update_stats)(struct mlx5e_priv *priv);
-	int	(*max_nch)(struct mlx5_core_dev *mdev);
-	int	max_tc;
-};
-
 struct mlx5e_priv {
 	/* priv data path fields - start */
-	struct mlx5e_txqsq         **txq_to_sq_map;
-	int channeltc_to_txq_map[MLX5E_MAX_NUM_CHANNELS][MLX5E_MAX_NUM_TC];
-	struct bpf_prog *xdp_prog;
+	struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC];
+	int channel_tc2txq[MLX5E_MAX_NUM_CHANNELS][MLX5E_MAX_NUM_TC];
 	/* priv data path fields - end */
 
 	unsigned long              state;
 	struct mutex               state_lock; /* Protects Interface state */
 	struct mlx5e_rq            drop_rq;
 
-	struct mlx5e_channel     **channel;
+	struct mlx5e_channels      channels;
 	u32                        tisn[MLX5E_MAX_NUM_TC];
 	struct mlx5e_rqt           indir_rqt;
 	struct mlx5e_tir           indir_tir[MLX5E_NUM_INDIR_TIRS];
@@ -746,7 +737,6 @@ struct mlx5e_priv {
 	struct mlx5e_flow_steering fs;
 	struct mlx5e_vxlan_db      vxlan;
 
-	struct mlx5e_params        params;
 	struct workqueue_struct    *wq;
 	struct work_struct         update_carrier_work;
 	struct work_struct         set_rx_mode_work;
@@ -766,6 +756,22 @@ struct mlx5e_priv {
 	void                      *ppriv;
 };
 
+struct mlx5e_profile {
+	void	(*init)(struct mlx5_core_dev *mdev,
+			struct net_device *netdev,
+			const struct mlx5e_profile *profile, void *ppriv);
+	void	(*cleanup)(struct mlx5e_priv *priv);
+	int	(*init_rx)(struct mlx5e_priv *priv);
+	void	(*cleanup_rx)(struct mlx5e_priv *priv);
+	int	(*init_tx)(struct mlx5e_priv *priv);
+	void	(*cleanup_tx)(struct mlx5e_priv *priv);
+	void	(*enable)(struct mlx5e_priv *priv);
+	void	(*disable)(struct mlx5e_priv *priv);
+	void	(*update_stats)(struct mlx5e_priv *priv);
+	int	(*max_nch)(struct mlx5_core_dev *mdev);
+	int	max_tc;
+};
+
 void mlx5e_build_ptys2ethtool_map(void);
 
 u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
@@ -827,7 +833,7 @@ void mlx5e_pps_event_handler(struct mlx5e_priv *priv,
 			     struct ptp_clock_event *event);
 int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr);
 int mlx5e_hwstamp_get(struct net_device *dev, struct ifreq *ifr);
-void mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val);
+int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val);
 
 int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto,
 			  u16 vid);
@@ -836,22 +842,49 @@ int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto,
 void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv);
 void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv);
 
-int mlx5e_modify_rqs_vsd(struct mlx5e_priv *priv, bool vsd);
+int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd);
+
+struct mlx5e_redirect_rqt_param {
+	bool is_rss;
+	union {
+		u32 rqn; /* Direct RQN (Non-RSS) */
+		struct {
+			u8 hfunc;
+			struct mlx5e_channels *channels;
+		} rss; /* RSS data */
+	};
+};
 
-int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz, int ix);
-void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_priv *priv, void *tirc,
-				    enum mlx5e_traffic_types tt);
+int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz,
+		       struct mlx5e_redirect_rqt_param rrp);
+void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params,
+				    enum mlx5e_traffic_types tt,
+				    void *tirc);
 
 int mlx5e_open_locked(struct net_device *netdev);
 int mlx5e_close_locked(struct net_device *netdev);
+
+int mlx5e_open_channels(struct mlx5e_priv *priv,
+			struct mlx5e_channels *chs);
+void mlx5e_close_channels(struct mlx5e_channels *chs);
+
+/* Function pointer to be used to modify WH settings while
+ * switching channels
+ */
+typedef int (*mlx5e_fp_hw_modify)(struct mlx5e_priv *priv);
+void mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
+				struct mlx5e_channels *new_chs,
+				mlx5e_fp_hw_modify hw_modify);
+
 void mlx5e_build_default_indir_rqt(struct mlx5_core_dev *mdev,
 				   u32 *indirection_rqt, int len,
 				   int num_channels);
 int mlx5e_get_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
 
 void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params,
 				 u8 cq_period_mode);
-void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type);
+void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev,
+			      struct mlx5e_params *params, u8 rq_type);
 
 static inline
 struct mlx5e_tx_wqe *mlx5e_post_nop(struct mlx5_wq_cyc *wq, u32 sqn, u16 *pc)
@@ -942,8 +975,7 @@ void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
 		       struct mlx5e_tir *tir);
 int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev);
 void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev);
-int mlx5e_refresh_tirs_self_loopback(struct mlx5_core_dev *mdev,
-				     bool enable_uc_lb);
+int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb);
 
 struct mlx5_eswitch_rep;
 int mlx5e_vport_rep_load(struct mlx5_eswitch *esw,

drivers/net/ethernet/mellanox/mlx5/core/en_clock.c

@@ -90,6 +90,7 @@ int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct hwtstamp_config config;
+	int err;
 
 	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz))
 		return -EOPNOTSUPP;
@@ -111,7 +112,7 @@ int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr)
 	switch (config.rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		/* Reset CQE compression to Admin default */
-		mlx5e_modify_rx_cqe_compression_locked(priv, priv->params.rx_cqe_compress_def);
+		mlx5e_modify_rx_cqe_compression_locked(priv, priv->channels.params.rx_cqe_compress_def);
 		break;
 	case HWTSTAMP_FILTER_ALL:
 	case HWTSTAMP_FILTER_SOME:
@@ -129,7 +130,12 @@ int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 		/* Disable CQE compression */
 		netdev_warn(dev, "Disabling cqe compression");
-		mlx5e_modify_rx_cqe_compression_locked(priv, false);
+		err = mlx5e_modify_rx_cqe_compression_locked(priv, false);
+		if (err) {
+			netdev_err(dev, "Failed disabling cqe compression err=%d\n", err);
+			mutex_unlock(&priv->state_lock);
+			return err;
+		}
 		config.rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	default:

drivers/net/ethernet/mellanox/mlx5/core/en_common.c

@@ -136,18 +136,20 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev)
 	mlx5_core_dealloc_pd(mdev, res->pdn);
 }
 
-int mlx5e_refresh_tirs_self_loopback(struct mlx5_core_dev *mdev,
-				     bool enable_uc_lb)
+int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
 {
+	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_tir *tir;
-	void *in;
+	int err  = -ENOMEM;
+	u32 tirn = 0;
 	int inlen;
-	int err = 0;
+	void *in;
+
 
 	inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
 	in = mlx5_vzalloc(inlen);
 	if (!in)
-		return -ENOMEM;
+		goto out;
 
 	if (enable_uc_lb)
 		MLX5_SET(modify_tir_in, in, ctx.self_lb_block,
@@ -156,13 +158,16 @@ int mlx5e_refresh_tirs_self_loopback(struct mlx5_core_dev *mdev,
 	MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);
 
 	list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) {
-		err = mlx5_core_modify_tir(mdev, tir->tirn, in, inlen);
+		tirn = tir->tirn;
+		err = mlx5_core_modify_tir(mdev, tirn, in, inlen);
 		if (err)
 			goto out;
 	}
 
 out:
 	kvfree(in);
+	if (err)
+		netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err);
 
 	return err;
 }