[dpdk-dev] [PATCH v2 0/4] Memory corruption due to HW rings allocation

[dpdk-dev] [PATCH v2 0/4] Memory corruption due to HW rings allocation

[Renata Saiakhova]

igb and ixgbe and some other drivers allocate HW rings using rte_eth_dma_zone_reserve(),
which checks first if the memzone exists for a given name, consisting of port
id, queue_id, rx/tx direction, but not for the size, alignment, and socket_id.
If the memzone with a given name exists it is returned, otherwise it is
allocated.
Disconnecting dpdk port from one type of interface (igb) and connecting it
to another type of interface (ixgbe) for the same port id, potentially creates
memory overlap and corruption, because it may require memzone of bigger size.
That's what is happening from switching from igb to ixgbe having the same port
id.


Renata Saiakhova (4):
  librte_ethdev: Introduce a function to release HW rings
  drivers/net: Fix in igb and ixgbe HW rings memory
  drivers/net: Fix in i40e HW rings memory overlap
  drivers/net: Fix in em and ice HW rings memory overlap

 drivers/net/e1000/em_rxtx.c              |  2 ++
 drivers/net/e1000/igb_rxtx.c             |  2 ++
 drivers/net/i40e/i40e_rxtx.c             |  2 ++
 drivers/net/ice/ice_rxtx.c               |  2 ++
 drivers/net/ixgbe/ixgbe_rxtx.c           |  2 ++
 lib/librte_ethdev/rte_ethdev.c           | 30 ++++++++++++++++++++++--
 lib/librte_ethdev/rte_ethdev_driver.h    | 19 +++++++++++++++
 lib/librte_ethdev/rte_ethdev_version.map |  1 +
 8 files changed, 58 insertions(+), 2 deletions(-)

-- 
2.17.2

[dpdk-dev] [PATCH v2 1/4] librte_ethdev: Introduce a function to release HW rings

[Renata Saiakhova]

Free previously allocated memzone for HW rings

Signed-off-by: Renata Saiakhova <Renata.Saiakhova@ekinops.com>
---
 lib/librte_ethdev/rte_ethdev.c           | 30 ++++++++++++++++++++++--
 lib/librte_ethdev/rte_ethdev_driver.h    | 19 +++++++++++++++
 lib/librte_ethdev/rte_ethdev_version.map |  1 +
 3 files changed, 48 insertions(+), 2 deletions(-)

diff --git a/lib/librte_ethdev/rte_ethdev.c b/lib/librte_ethdev/rte_ethdev.c
index 72aed59a5..7200ef48c 100644
--- a/lib/librte_ethdev/rte_ethdev.c
+++ b/lib/librte_ethdev/rte_ethdev.c
@@ -4181,6 +4181,10 @@ rte_eth_dev_rx_intr_ctl_q_get_fd(uint16_t port_id, uint16_t queue_id)
 	return fd;
 }
 
+#define ETH_DMA_MZONE_NAME(_name, _port_id, _queue_id, _ring_name) \
+	snprintf(_name, sizeof(_name), "eth_p%d_q%d_%s", \
+			_port_id, _queue_id, _ring_name)
+
 const struct rte_memzone *
 rte_eth_dma_zone_reserve(const struct rte_eth_dev *dev, const char *ring_name,
 			 uint16_t queue_id, size_t size, unsigned align,
@@ -4190,8 +4194,7 @@ rte_eth_dma_zone_reserve(const struct rte_eth_dev *dev, const char *ring_name,
 	const struct rte_memzone *mz;
 	int rc;
 
-	rc = snprintf(z_name, sizeof(z_name), "eth_p%d_q%d_%s",
-		      dev->data->port_id, queue_id, ring_name);
+	rc = ETH_DMA_MZONE_NAME(z_name, dev->data->port_id, queue_id, ring_name);
 	if (rc >= RTE_MEMZONE_NAMESIZE) {
 		RTE_ETHDEV_LOG(ERR, "ring name too long\n");
 		rte_errno = ENAMETOOLONG;
@@ -4206,6 +4209,29 @@ rte_eth_dma_zone_reserve(const struct rte_eth_dev *dev, const char *ring_name,
 			RTE_MEMZONE_IOVA_CONTIG, align);
 }
 
+int __rte_experimental
+rte_eth_dma_zone_free(const struct rte_eth_dev *dev, const char *ring_name,
+		uint16_t queue_id)
+{
+	char z_name[RTE_MEMZONE_NAMESIZE];
+	const struct rte_memzone *mz;
+	int rc = 0;
+
+	rc = ETH_DMA_MZONE_NAME(z_name, dev->data->port_id, queue_id, ring_name);
+	if (rc >= RTE_MEMZONE_NAMESIZE) {
+		RTE_ETHDEV_LOG(ERR, "ring name too long\n");
+		return -ENAMETOOLONG;
+	}
+
+	mz = rte_memzone_lookup(z_name);
+	if (mz)
+		rc = rte_memzone_free(mz);
+
+	return rc;
+}
+
+#undef ETH_DMA_MZONE_NAME
+
 int
 rte_eth_dev_create(struct rte_device *device, const char *name,
 	size_t priv_data_size,
diff --git a/lib/librte_ethdev/rte_ethdev_driver.h b/lib/librte_ethdev/rte_ethdev_driver.h
index 99d4cd6cd..f32d55720 100644
--- a/lib/librte_ethdev/rte_ethdev_driver.h
+++ b/lib/librte_ethdev/rte_ethdev_driver.h
@@ -180,6 +180,25 @@ rte_eth_dma_zone_reserve(const struct rte_eth_dev *eth_dev, const char *name,
 			 uint16_t queue_id, size_t size,
 			 unsigned align, int socket_id);
 
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Free previously allocated memzone for HW rings.
+ *
+ * @param eth_dev
+ *   The *eth_dev* pointer is the address of the *rte_eth_dev* structure
+ * @param name
+ *   The name of the memory zone
+ * @param queue_id
+ *   The index of the queue to add to name
+ * @return
+ *   Negative errno value on error, 0 on success.
+ */
+int __rte_experimental
+rte_eth_dma_zone_free(const struct rte_eth_dev *dev, const char *ring_name,
+		 uint16_t queue_id);
+
 /**
  * @internal
  * Atomically set the link status for the specific device.
diff --git a/lib/librte_ethdev/rte_ethdev_version.map b/lib/librte_ethdev/rte_ethdev_version.map
index 715505604..139a81302 100644
--- a/lib/librte_ethdev/rte_ethdev_version.map
+++ b/lib/librte_ethdev/rte_ethdev_version.map
@@ -241,4 +241,5 @@ EXPERIMENTAL {
 	__rte_ethdev_trace_rx_burst;
 	__rte_ethdev_trace_tx_burst;
 	rte_flow_get_aged_flows;
+	rte_eth_dma_zone_free;
 };
-- 
2.17.2

Re: [dpdk-dev] [PATCH v2 1/4] librte_ethdev: Introduce a function to release HW rings

[Burakov, Anatoly]

On 13-May-20 10:15 AM, Renata Saiakhova wrote:
> Free previously allocated memzone for HW rings
> 
> Signed-off-by: Renata Saiakhova <Renata.Saiakhova@ekinops.com>
> ---
>   lib/librte_ethdev/rte_ethdev.c           | 30 ++++++++++++++++++++++--
>   lib/librte_ethdev/rte_ethdev_driver.h    | 19 +++++++++++++++
>   lib/librte_ethdev/rte_ethdev_version.map |  1 +
>   3 files changed, 48 insertions(+), 2 deletions(-)
> 
> diff --git a/lib/librte_ethdev/rte_ethdev.c b/lib/librte_ethdev/rte_ethdev.c
> index 72aed59a5..7200ef48c 100644
> --- a/lib/librte_ethdev/rte_ethdev.c
> +++ b/lib/librte_ethdev/rte_ethdev.c
> @@ -4181,6 +4181,10 @@ rte_eth_dev_rx_intr_ctl_q_get_fd(uint16_t port_id, uint16_t queue_id)
>   	return fd;
>   }
>   
> +#define ETH_DMA_MZONE_NAME(_name, _port_id, _queue_id, _ring_name) \
> +	snprintf(_name, sizeof(_name), "eth_p%d_q%d_%s", \
> +			_port_id, _queue_id, _ring_name)
> +
>   const struct rte_memzone *
>   rte_eth_dma_zone_reserve(const struct rte_eth_dev *dev, const char *ring_name,
>   			 uint16_t queue_id, size_t size, unsigned align,
> @@ -4190,8 +4194,7 @@ rte_eth_dma_zone_reserve(const struct rte_eth_dev *dev, const char *ring_name,
>   	const struct rte_memzone *mz;
>   	int rc;
>   
> -	rc = snprintf(z_name, sizeof(z_name), "eth_p%d_q%d_%s",
> -		      dev->data->port_id, queue_id, ring_name);
> +	rc = ETH_DMA_MZONE_NAME(z_name, dev->data->port_id, queue_id, ring_name);
>   	if (rc >= RTE_MEMZONE_NAMESIZE) {
>   		RTE_ETHDEV_LOG(ERR, "ring name too long\n");
>   		rte_errno = ENAMETOOLONG;
> @@ -4206,6 +4209,29 @@ rte_eth_dma_zone_reserve(const struct rte_eth_dev *dev, const char *ring_name,
>   			RTE_MEMZONE_IOVA_CONTIG, align);
>   }
>   
> +int __rte_experimental
> +rte_eth_dma_zone_free(const struct rte_eth_dev *dev, const char *ring_name,
> +		uint16_t queue_id)
> +{
> +	char z_name[RTE_MEMZONE_NAMESIZE];
> +	const struct rte_memzone *mz;
> +	int rc = 0;
> +
> +	rc = ETH_DMA_MZONE_NAME(z_name, dev->data->port_id, queue_id, ring_name);
> +	if (rc >= RTE_MEMZONE_NAMESIZE) {
> +		RTE_ETHDEV_LOG(ERR, "ring name too long\n");
> +		return -ENAMETOOLONG;
> +	}
> +
> +	mz = rte_memzone_lookup(z_name);
> +	if (mz)
> +		rc = rte_memzone_free(mz);
> +
> +	return rc;
> +}
> +
> +#undef ETH_DMA_MZONE_NAME

Not sure #undef is necessary in a .c file :)

Otherwise LGTM

Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>

-- 
Thanks,
Anatoly

Re: [dpdk-dev] [PATCH v2 1/4] librte_ethdev: Introduce a function to release HW rings

[Neil Horman]

On Wed, May 13, 2020 at 11:15:44AM +0200, Renata Saiakhova wrote:
> Free previously allocated memzone for HW rings
> 
> Signed-off-by: Renata Saiakhova <Renata.Saiakhova@ekinops.com>
> ---
>  lib/librte_ethdev/rte_ethdev.c           | 30 ++++++++++++++++++++++--
>  lib/librte_ethdev/rte_ethdev_driver.h    | 19 +++++++++++++++
>  lib/librte_ethdev/rte_ethdev_version.map |  1 +
>  3 files changed, 48 insertions(+), 2 deletions(-)
> 
> diff --git a/lib/librte_ethdev/rte_ethdev.c b/lib/librte_ethdev/rte_ethdev.c
> index 72aed59a5..7200ef48c 100644
> --- a/lib/librte_ethdev/rte_ethdev.c
> +++ b/lib/librte_ethdev/rte_ethdev.c
> @@ -4181,6 +4181,10 @@ rte_eth_dev_rx_intr_ctl_q_get_fd(uint16_t port_id, uint16_t queue_id)
>  	return fd;
>  }
>  
> +#define ETH_DMA_MZONE_NAME(_name, _port_id, _queue_id, _ring_name) \
> +	snprintf(_name, sizeof(_name), "eth_p%d_q%d_%s", \
> +			_port_id, _queue_id, _ring_name)
> +
>  const struct rte_memzone *
>  rte_eth_dma_zone_reserve(const struct rte_eth_dev *dev, const char *ring_name,
>  			 uint16_t queue_id, size_t size, unsigned align,
> @@ -4190,8 +4194,7 @@ rte_eth_dma_zone_reserve(const struct rte_eth_dev *dev, const char *ring_name,
>  	const struct rte_memzone *mz;
>  	int rc;
>  
> -	rc = snprintf(z_name, sizeof(z_name), "eth_p%d_q%d_%s",
> -		      dev->data->port_id, queue_id, ring_name);
> +	rc = ETH_DMA_MZONE_NAME(z_name, dev->data->port_id, queue_id, ring_name);
>  	if (rc >= RTE_MEMZONE_NAMESIZE) {
>  		RTE_ETHDEV_LOG(ERR, "ring name too long\n");
>  		rte_errno = ENAMETOOLONG;
> @@ -4206,6 +4209,29 @@ rte_eth_dma_zone_reserve(const struct rte_eth_dev *dev, const char *ring_name,
>  			RTE_MEMZONE_IOVA_CONTIG, align);
>  }
>  
> +int __rte_experimental
> +rte_eth_dma_zone_free(const struct rte_eth_dev *dev, const char *ring_name,
> +		uint16_t queue_id)
> +{
> +	char z_name[RTE_MEMZONE_NAMESIZE];
> +	const struct rte_memzone *mz;
> +	int rc = 0;
> +
> +	rc = ETH_DMA_MZONE_NAME(z_name, dev->data->port_id, queue_id, ring_name);
> +	if (rc >= RTE_MEMZONE_NAMESIZE) {
> +		RTE_ETHDEV_LOG(ERR, "ring name too long\n");
> +		return -ENAMETOOLONG;
> +	}
> +
> +	mz = rte_memzone_lookup(z_name);
> +	if (mz)
> +		rc = rte_memzone_free(mz);
> +
> +	return rc;
> +}
> +
> +#undef ETH_DMA_MZONE_NAME
Agree with Anatoly, this isn't needed, and will cause confusion if more
functions are added using this macro later


Otherwise, looks good.
Neil

> +
>  int
>  rte_eth_dev_create(struct rte_device *device, const char *name,
>  	size_t priv_data_size,
> diff --git a/lib/librte_ethdev/rte_ethdev_driver.h b/lib/librte_ethdev/rte_ethdev_driver.h
> index 99d4cd6cd..f32d55720 100644
> --- a/lib/librte_ethdev/rte_ethdev_driver.h
> +++ b/lib/librte_ethdev/rte_ethdev_driver.h
> @@ -180,6 +180,25 @@ rte_eth_dma_zone_reserve(const struct rte_eth_dev *eth_dev, const char *name,
>  			 uint16_t queue_id, size_t size,
>  			 unsigned align, int socket_id);
>  
> +/**
> + * @warning
> + * @b EXPERIMENTAL: this API may change without prior notice.
> + *
> + * Free previously allocated memzone for HW rings.
> + *
> + * @param eth_dev
> + *   The *eth_dev* pointer is the address of the *rte_eth_dev* structure
> + * @param name
> + *   The name of the memory zone
> + * @param queue_id
> + *   The index of the queue to add to name
> + * @return
> + *   Negative errno value on error, 0 on success.
> + */
> +int __rte_experimental
> +rte_eth_dma_zone_free(const struct rte_eth_dev *dev, const char *ring_name,
> +		 uint16_t queue_id);
> +
>  /**
>   * @internal
>   * Atomically set the link status for the specific device.
> diff --git a/lib/librte_ethdev/rte_ethdev_version.map b/lib/librte_ethdev/rte_ethdev_version.map
> index 715505604..139a81302 100644
> --- a/lib/librte_ethdev/rte_ethdev_version.map
> +++ b/lib/librte_ethdev/rte_ethdev_version.map
> @@ -241,4 +241,5 @@ EXPERIMENTAL {
>  	__rte_ethdev_trace_rx_burst;
>  	__rte_ethdev_trace_tx_burst;
>  	rte_flow_get_aged_flows;
> +	rte_eth_dma_zone_free;
>  };
> -- 
> 2.17.2
> 
> 

Re: [dpdk-dev] [PATCH v2 1/4] librte_ethdev: Introduce a function to release HW rings

[Ray Kinsella]

On 13/05/2020 10:15, Renata Saiakhova wrote:
> diff --git a/lib/librte_ethdev/rte_ethdev_version.map b/lib/librte_ethdev/rte_ethdev_version.map
> index 715505604..139a81302 100644
> --- a/lib/librte_ethdev/rte_ethdev_version.map
> +++ b/lib/librte_ethdev/rte_ethdev_version.map
> @@ -241,4 +241,5 @@ EXPERIMENTAL {
>  	__rte_ethdev_trace_rx_burst;
>  	__rte_ethdev_trace_tx_burst;
>  	rte_flow_get_aged_flows;
> +	rte_eth_dma_zone_free;
>  };

Minor niggle rte_eth is alphabetically before rte_flow_get_aged_flows.
Although I note that not all additions to EXPERIMENTAL, have been consistent in this regard.

Ray K

[dpdk-dev] [PATCH v2 2/4] drivers/net: Fix in igb and ixgbe HW rings memory

[Renata Saiakhova]

Delete memzones for HW rings in igb and ixgbe while freeing queues

Signed-off-by: Renata Saiakhova <Renata.Saiakhova@ekinops.com>
---
 drivers/net/e1000/igb_rxtx.c   | 2 ++
 drivers/net/ixgbe/ixgbe_rxtx.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/net/e1000/igb_rxtx.c b/drivers/net/e1000/igb_rxtx.c
index 684fa4ad8..fe80c0f0d 100644
--- a/drivers/net/e1000/igb_rxtx.c
+++ b/drivers/net/e1000/igb_rxtx.c
@@ -1884,12 +1884,14 @@ igb_dev_free_queues(struct rte_eth_dev *dev)
 	for (i = 0; i < dev->data->nb_rx_queues; i++) {
 		eth_igb_rx_queue_release(dev->data->rx_queues[i]);
 		dev->data->rx_queues[i] = NULL;
+		rte_eth_dma_zone_free(dev, "rx_ring", i);
 	}
 	dev->data->nb_rx_queues = 0;
 
 	for (i = 0; i < dev->data->nb_tx_queues; i++) {
 		eth_igb_tx_queue_release(dev->data->tx_queues[i]);
 		dev->data->tx_queues[i] = NULL;
+		rte_eth_dma_zone_free(dev, "tx_ring", i);
 	}
 	dev->data->nb_tx_queues = 0;
 }
diff --git a/drivers/net/ixgbe/ixgbe_rxtx.c b/drivers/net/ixgbe/ixgbe_rxtx.c
index 2e20e18c7..977ecf513 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx.c
+++ b/drivers/net/ixgbe/ixgbe_rxtx.c
@@ -3368,12 +3368,14 @@ ixgbe_dev_free_queues(struct rte_eth_dev *dev)
 	for (i = 0; i < dev->data->nb_rx_queues; i++) {
 		ixgbe_dev_rx_queue_release(dev->data->rx_queues[i]);
 		dev->data->rx_queues[i] = NULL;
+		rte_eth_dma_zone_free(dev, "rx_ring", i);
 	}
 	dev->data->nb_rx_queues = 0;
 
 	for (i = 0; i < dev->data->nb_tx_queues; i++) {
 		ixgbe_dev_tx_queue_release(dev->data->tx_queues[i]);
 		dev->data->tx_queues[i] = NULL;
+		rte_eth_dma_zone_free(dev, "tx_ring", i);
 	}
 	dev->data->nb_tx_queues = 0;
 }
-- 
2.17.2

[dpdk-dev] [PATCH v2 3/4] drivers/net: Fix in i40e HW rings memory overlap

[Renata Saiakhova]

Delete memzones for HW rings in i40e while freeing queues

Signed-off-by: Renata Saiakhova <Renata.Saiakhova@ekinops.com>
---
 drivers/net/i40e/i40e_rxtx.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/i40e/i40e_rxtx.c b/drivers/net/i40e/i40e_rxtx.c
index 5e7c86ed8..99cec9b99 100644
--- a/drivers/net/i40e/i40e_rxtx.c
+++ b/drivers/net/i40e/i40e_rxtx.c
@@ -2900,6 +2900,7 @@ i40e_dev_free_queues(struct rte_eth_dev *dev)
 			continue;
 		i40e_dev_rx_queue_release(dev->data->rx_queues[i]);
 		dev->data->rx_queues[i] = NULL;
+		rte_eth_dma_zone_free(dev, "rx_ring", i);
 	}
 
 	for (i = 0; i < dev->data->nb_tx_queues; i++) {
@@ -2907,6 +2908,7 @@ i40e_dev_free_queues(struct rte_eth_dev *dev)
 			continue;
 		i40e_dev_tx_queue_release(dev->data->tx_queues[i]);
 		dev->data->tx_queues[i] = NULL;
+		rte_eth_dma_zone_free(dev, "tx_ring", i);
 	}
 }
 
-- 
2.17.2

[dpdk-dev] [PATCH v2 4/4] drivers/net: Fix in em and ice HW rings memory overlap

[Renata Saiakhova]

Delete memzones for HW rings in em and ice while freeing queues

Signed-off-by: Renata Saiakhova <Renata.Saiakhova@ekinops.com>
---
 drivers/net/e1000/em_rxtx.c | 2 ++
 drivers/net/ice/ice_rxtx.c  | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/net/e1000/em_rxtx.c b/drivers/net/e1000/em_rxtx.c
index 49c53712a..67a271e8c 100644
--- a/drivers/net/e1000/em_rxtx.c
+++ b/drivers/net/e1000/em_rxtx.c
@@ -1611,12 +1611,14 @@ em_dev_free_queues(struct rte_eth_dev *dev)
 	for (i = 0; i < dev->data->nb_rx_queues; i++) {
 		eth_em_rx_queue_release(dev->data->rx_queues[i]);
 		dev->data->rx_queues[i] = NULL;
+		rte_eth_dma_zone_free(dev, "rx_ring", i);
 	}
 	dev->data->nb_rx_queues = 0;
 
 	for (i = 0; i < dev->data->nb_tx_queues; i++) {
 		eth_em_tx_queue_release(dev->data->tx_queues[i]);
 		dev->data->tx_queues[i] = NULL;
+		rte_eth_dma_zone_free(dev, "tx_ring", i);
 	}
 	dev->data->nb_tx_queues = 0;
 }
diff --git a/drivers/net/ice/ice_rxtx.c b/drivers/net/ice/ice_rxtx.c
index 1c9f31efd..7c2dad9d6 100644
--- a/drivers/net/ice/ice_rxtx.c
+++ b/drivers/net/ice/ice_rxtx.c
@@ -1905,6 +1905,7 @@ ice_free_queues(struct rte_eth_dev *dev)
 			continue;
 		ice_rx_queue_release(dev->data->rx_queues[i]);
 		dev->data->rx_queues[i] = NULL;
+		rte_eth_dma_zone_free(dev, "rx_ring", i);
 	}
 	dev->data->nb_rx_queues = 0;
 
@@ -1913,6 +1914,7 @@ ice_free_queues(struct rte_eth_dev *dev)
 			continue;
 		ice_tx_queue_release(dev->data->tx_queues[i]);
 		dev->data->tx_queues[i] = NULL;
+		rte_eth_dma_zone_free(dev, "tx_ring", i);
 	}
 	dev->data->nb_tx_queues = 0;
 }
-- 
2.17.2