[dpdk-dev] [PATCH v3 3/4] bond mode 4: allow external state machine

[Neil Horman]

On Wed, Apr 22, 2015 at 09:27:42AM -0700, Eric Kinzie wrote:
> From: Eric Kinzie <ekinzie at brocade.com>
> 
>   Provide functions to allow an external 802.3ad state machine to transmit
>   and recieve LACPDUs and to set the collection/distribution flags on
>   slave interfaces.
> 
> Signed-off-by: Eric Kinzie <ehkinzie at gmail.com>
> ---
>  lib/librte_pmd_bond/rte_eth_bond_8023ad.c         |  173 +++++++++++++++++++++
>  lib/librte_pmd_bond/rte_eth_bond_8023ad.h         |   44 ++++++
>  lib/librte_pmd_bond/rte_eth_bond_8023ad_private.h |    2 +
>  lib/librte_pmd_bond/rte_eth_bond_version.map      |    3 +
>  4 files changed, 222 insertions(+)
> 
> diff --git a/lib/librte_pmd_bond/rte_eth_bond_8023ad.c b/lib/librte_pmd_bond/rte_eth_bond_8023ad.c
> index 1009d5b..326e899 100644
> --- a/lib/librte_pmd_bond/rte_eth_bond_8023ad.c
> +++ b/lib/librte_pmd_bond/rte_eth_bond_8023ad.c
> @@ -42,6 +42,8 @@
>  
>  #include "rte_eth_bond_private.h"
>  
> +static void bond_mode_8023ad_ext_periodic_cb(void *arg);
> +
>  #ifdef RTE_LIBRTE_BOND_DEBUG_8023AD
>  #define MODE4_DEBUG(fmt, ...) RTE_LOG(DEBUG, PMD, "%6u [Port %u: %s] " fmt, \
>  			bond_dbg_get_time_diff_ms(), slave_id, \
> @@ -1014,6 +1016,7 @@ bond_mode_8023ad_conf_get(struct rte_eth_dev *dev,
>  	conf->tx_period_ms = mode4->tx_period_timeout / ms_ticks;
>  	conf->update_timeout_ms = mode4->update_timeout_us / 1000;
>  	conf->rx_marker_period_ms = mode4->rx_marker_timeout / ms_ticks;
> +	conf->slowrx_cb = mode4->slowrx_cb;
>  }
>  
>  void
> @@ -1035,8 +1038,11 @@ bond_mode_8023ad_setup(struct rte_eth_dev *dev,
>  		conf->tx_period_ms = BOND_8023AD_TX_MACHINE_PERIOD_MS;
>  		conf->rx_marker_period_ms = BOND_8023AD_RX_MARKER_PERIOD_MS;
>  		conf->update_timeout_ms = BOND_MODE_8023AX_UPDATE_TIMEOUT_MS;
> +		conf->slowrx_cb = NULL;
>  	}
>  
> +	bond_mode_8023ad_stop(dev);
> +
>  	mode4->fast_periodic_timeout = conf->fast_periodic_ms * ms_ticks;
>  	mode4->slow_periodic_timeout = conf->slow_periodic_ms * ms_ticks;
>  	mode4->short_timeout = conf->short_timeout_ms * ms_ticks;
> @@ -1045,6 +1051,10 @@ bond_mode_8023ad_setup(struct rte_eth_dev *dev,
>  	mode4->tx_period_timeout = conf->tx_period_ms * ms_ticks;
>  	mode4->rx_marker_timeout = conf->rx_marker_period_ms * ms_ticks;
>  	mode4->update_timeout_us = conf->update_timeout_ms * 1000;
> +	mode4->slowrx_cb = conf->slowrx_cb;
> +
> +	if (dev->data->dev_started)
> +		bond_mode_8023ad_start(dev);
>  }
>  
>  int
> @@ -1062,6 +1072,13 @@ bond_mode_8023ad_enable(struct rte_eth_dev *bond_dev)
>  int
>  bond_mode_8023ad_start(struct rte_eth_dev *bond_dev)
>  {
> +	struct bond_dev_private *internals = bond_dev->data->dev_private;
> +	struct mode8023ad_private *mode4 = &internals->mode4;
> +
> +	if (mode4->slowrx_cb)
> +		return rte_eal_alarm_set(BOND_MODE_8023AX_UPDATE_TIMEOUT_MS * 1000,
> +			&bond_mode_8023ad_ext_periodic_cb, bond_dev);
> +
>  	return rte_eal_alarm_set(BOND_MODE_8023AX_UPDATE_TIMEOUT_MS * 1000,
>  			&bond_mode_8023ad_periodic_cb, bond_dev);
>  }
> @@ -1069,6 +1086,13 @@ bond_mode_8023ad_start(struct rte_eth_dev *bond_dev)
>  void
>  bond_mode_8023ad_stop(struct rte_eth_dev *bond_dev)
>  {
> +	struct bond_dev_private *internals = bond_dev->data->dev_private;
> +	struct mode8023ad_private *mode4 = &internals->mode4;
> +
> +	if (mode4->slowrx_cb) {
> +		rte_eal_alarm_cancel(&bond_mode_8023ad_ext_periodic_cb, bond_dev);
> +		return;
> +	}
>  	rte_eal_alarm_cancel(&bond_mode_8023ad_periodic_cb, bond_dev);
>  }
>  
> @@ -1215,3 +1239,152 @@ rte_eth_bond_8023ad_slave_info(uint8_t port_id, uint8_t slave_id,
>  	info->agg_port_id = port->aggregator_port_id;
>  	return 0;
>  }
> +
> +int
> +rte_eth_bond_8023ad_ext_collect(uint8_t port_id, uint8_t slave_id, int enabled)
> +{
> +	struct rte_eth_dev *bond_dev;
> +	struct bond_dev_private *internals;
> +	struct mode8023ad_private *mode4;
> +	struct port *port;
> +
> +	if (rte_eth_bond_mode_get(port_id) != BONDING_MODE_8023AD)
> +		return -EINVAL;
> +
> +	bond_dev = &rte_eth_devices[port_id];
> +
> +	if (!bond_dev->data->dev_started)
> +		return -EINVAL;
> +
> +	internals = bond_dev->data->dev_private;
> +	if (find_slave_by_id(internals->active_slaves,
> +			internals->active_slave_count, slave_id) ==
> +				internals->active_slave_count)
> +		return -EINVAL;
> +
> +	mode4 = &internals->mode4;
> +	if (mode4->slowrx_cb == NULL)
> +		return -EINVAL;
> +
> +	port = &mode_8023ad_ports[slave_id];
> +
> +	if (enabled)
> +		ACTOR_STATE_SET(port, COLLECTING);
> +	else
> +		ACTOR_STATE_CLR(port, COLLECTING);
> +
> +	return 0;
> +}
> +
> +int
> +rte_eth_bond_8023ad_ext_distrib(uint8_t port_id, uint8_t slave_id, int enabled)
> +{
> +	struct rte_eth_dev *bond_dev;
> +	struct bond_dev_private *internals;
> +	struct mode8023ad_private *mode4;
> +	struct port *port;
> +
> +	if (rte_eth_bond_mode_get(port_id) != BONDING_MODE_8023AD)
> +		return -EINVAL;
> +
> +	bond_dev = &rte_eth_devices[port_id];
> +
> +	if (!bond_dev->data->dev_started)
> +		return -EINVAL;
> +
> +	internals = bond_dev->data->dev_private;
> +	if (find_slave_by_id(internals->active_slaves,
> +			internals->active_slave_count, slave_id) ==
> +				internals->active_slave_count)
> +		return -EINVAL;
> +
> +	mode4 = &internals->mode4;
> +	if (mode4->slowrx_cb == NULL)
> +		return -EINVAL;
> +
> +	port = &mode_8023ad_ports[slave_id];
> +
> +	if (enabled)
> +		ACTOR_STATE_SET(port, DISTRIBUTING);
> +	else
> +		ACTOR_STATE_CLR(port, DISTRIBUTING);
> +
> +	return 0;
> +}
> +
> +int
> +rte_eth_bond_8023ad_ext_slowtx(uint8_t port_id, uint8_t slave_id,
> +		struct rte_mbuf *lacp_pkt)
> +{
> +	struct rte_eth_dev *bond_dev;
> +	struct bond_dev_private *internals;
> +	struct mode8023ad_private *mode4;
> +	struct port *port;
> +
> +	if (rte_eth_bond_mode_get(port_id) != BONDING_MODE_8023AD)
> +		return -EINVAL;
> +
> +	bond_dev = &rte_eth_devices[port_id];
> +
> +	if (!bond_dev->data->dev_started)
> +		return -EINVAL;
> +
> +	internals = bond_dev->data->dev_private;
> +	if (find_slave_by_id(internals->active_slaves,
> +			internals->active_slave_count, slave_id) ==
> +				internals->active_slave_count)
> +		return -EINVAL;
> +
> +	mode4 = &internals->mode4;
> +	if (mode4->slowrx_cb == NULL)
> +		return -EINVAL;
> +
> +	port = &mode_8023ad_ports[slave_id];
> +
> +	if (rte_pktmbuf_pkt_len(lacp_pkt) < sizeof(struct lacpdu_header))
> +		return -EINVAL;
> +
> +	struct lacpdu_header *lacp;
> +
> +	/* only enqueue LACPDUs */
> +	lacp = rte_pktmbuf_mtod(lacp_pkt, struct lacpdu_header *);
> +	if (lacp->lacpdu.subtype != SLOW_SUBTYPE_LACP)
> +		return -EINVAL;
> +
> +	MODE4_DEBUG("sending LACP frame\n");
> +
> +	return rte_ring_enqueue(port->tx_ring, lacp_pkt);
> +}
> +
> +static void
> +bond_mode_8023ad_ext_periodic_cb(void *arg)
> +{
> +	struct rte_eth_dev *bond_dev = arg;
> +	struct bond_dev_private *internals = bond_dev->data->dev_private;
> +	struct mode8023ad_private *mode4 = &internals->mode4;
> +	struct port *port;
> +	void *pkt = NULL;
> +	uint16_t i, slave_id;
> +
> +	for (i = 0; i < internals->active_slave_count; i++) {
> +		slave_id = internals->active_slaves[i];
> +		port = &mode_8023ad_ports[slave_id];
> +
> +		if (rte_ring_dequeue(port->rx_ring, &pkt) == 0) {
> +			struct rte_mbuf *lacp_pkt = pkt;
> +			struct lacpdu_header *lacp;
> +
> +			lacp = rte_pktmbuf_mtod(lacp_pkt,
> +						struct lacpdu_header *);
> +			RTE_VERIFY(lacp->lacpdu.subtype == SLOW_SUBTYPE_LACP);
> +
> +			/* This is LACP frame so pass it to rx callback.
> +			 * Callback is responsible for freeing mbuf.
> +			 */
> +			mode4->slowrx_cb(slave_id, lacp_pkt);
> +		}
> +	}
> +
> +	rte_eal_alarm_set(internals->mode4.update_timeout_us,
> +			bond_mode_8023ad_ext_periodic_cb, arg);
> +}
> diff --git a/lib/librte_pmd_bond/rte_eth_bond_8023ad.h b/lib/librte_pmd_bond/rte_eth_bond_8023ad.h
> index ebd0e93..8cfa3d3 100644
> --- a/lib/librte_pmd_bond/rte_eth_bond_8023ad.h
> +++ b/lib/librte_pmd_bond/rte_eth_bond_8023ad.h
> @@ -64,6 +64,8 @@ extern "C" {
>  #define MARKER_TLV_TYPE_INFO                0x01
>  #define MARKER_TLV_TYPE_RESP                0x02
>  
> +typedef void (*rte_eth_bond_8023ad_ext_slowrx_fn)(uint8_t slave_id, struct rte_mbuf *lacp_pkt);
> +
>  enum rte_bond_8023ad_selection {
>  	UNSELECTED,
>  	STANDBY,
> @@ -157,6 +159,7 @@ struct rte_eth_bond_8023ad_conf {
>  	uint32_t tx_period_ms;
>  	uint32_t rx_marker_period_ms;
>  	uint32_t update_timeout_ms;
> +	rte_eth_bond_8023ad_ext_slowrx_fn slowrx_cb;
>  };
>  

This is dangerous.  While it doesn't break ABI, it does create a situation in
which you will be prone to writing to invalid memory. By the examples that you
provide in the test application, you declare rte_eth_bond_8023ad_conf statically
within an application, so if someone is using the DPDK built as a shared
library, they may have less allocated space in the .data section then you think
with this new extended structure.  As a result in that situation you will read
from and write to unallocated memory when you access slowrx_cb.  I recommend
that you version the setup routine, so that the older version is modified to not
touch slowrx_cb.

Neil