[dpdk-dev,1/2] net/failsafe: fix removed sub-device cleanup
Checks
Commit Message
The fail-safe PMD registers to RMV event for each removable sub-device
port in order to cleanup the sub-device resources and switch the Tx
sub-device directly when it is plugged-out.
In the removal time, the fail-safe PMD stops and closes the sub-device
but it doesn't unregister the LSC and RMV callbacks of the sub-device
port.
It can lead the callbacks to be called for a port which is no more
associated to the fail-safe sub-device, because there is not a
guaranty that a sub-device gets the same port ID for each plug-in
process. This port, for example, may belong to another sub-device of a
different fail-safe device.
Unregister the LSC and RMV callbacks for sub-devices which are not
used.
Fixes: 598fb8aec6f6 ("net/failsafe: support device removal")
Cc: stable@dpdk.org
Signed-off-by: Matan Azrad <matan@mellanox.com>
---
drivers/net/failsafe/failsafe_ether.c | 22 ++++++++++++++++++++++
drivers/net/failsafe/failsafe_ops.c | 5 +++++
drivers/net/failsafe/failsafe_private.h | 3 +++
3 files changed, 30 insertions(+)
Comments
Hi,
Please find comments inline.
> -----Original Message-----
> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Matan Azrad
> Sent: Thursday, May 17, 2018 9:52 PM
> To: Gaetan Rivet <gaetan.rivet@6wind.com>
> Cc: dev@dpdk.org; stable@dpdk.org
> Subject: [dpdk-dev] [PATCH 1/2] net/failsafe: fix removed sub-device cleanup
>
> The fail-safe PMD registers to RMV event for each removable sub-device
> port in order to cleanup the sub-device resources and switch the Tx sub-
> device directly when it is plugged-out.
>
> In the removal time, the fail-safe PMD stops and closes the sub-device but it
During removal time...
> doesn't unregister the LSC and RMV callbacks of the sub-device port.
>
> It can lead the callbacks to be called for a port which is no more associated
> to the fail-safe sub-device, because there is not a guaranty that a sub-device
associated with........ guarantee that
> gets the same port ID for each plug-in process. This port, for example, may
> belong to another sub-device of a different fail-safe device.
>
> Unregister the LSC and RMV callbacks for sub-devices which are not used.
>
> Fixes: 598fb8aec6f6 ("net/failsafe: support device removal")
> Cc: stable@dpdk.org
>
> Signed-off-by: Matan Azrad <matan@mellanox.com>
> ---
> drivers/net/failsafe/failsafe_ether.c | 22 ++++++++++++++++++++++
> drivers/net/failsafe/failsafe_ops.c | 5 +++++
> drivers/net/failsafe/failsafe_private.h | 3 +++
> 3 files changed, 30 insertions(+)
>
> diff --git a/drivers/net/failsafe/failsafe_ether.c
> b/drivers/net/failsafe/failsafe_ether.c
> index 733e95d..2bbee82 100644
> --- a/drivers/net/failsafe/failsafe_ether.c
> +++ b/drivers/net/failsafe/failsafe_ether.c
> @@ -260,6 +260,7 @@
> sdev->state = DEV_ACTIVE;
> /* fallthrough */
> case DEV_ACTIVE:
> + failsafe_eth_dev_unregister_callbacks(sdev);
> rte_eth_dev_close(PORT_ID(sdev));
> sdev->state = DEV_PROBED;
> /* fallthrough */
> @@ -321,6 +322,27 @@
> }
>
> void
> +failsafe_eth_dev_unregister_callbacks(struct sub_device *sdev) {
> + if (sdev == NULL)
> + return;
> + if (sdev->rmv_callback) {
> + rte_eth_dev_callback_unregister(PORT_ID(sdev),
> + RTE_ETH_EVENT_INTR_RMV,
> + failsafe_eth_rmv_event_callback,
> + sdev);
Please justify ignoring returned error from rte_eth_dev_callback_unregister call.
I have noticed that this call returned error is ignored in other places in code (failsafe.c)...but if for example the callback returns with -EAGAIN shouldn't you try again to unregister?
Need to avoid a case where the callback is still registered, while rmv_callback is assigned to 0
> + sdev->rmv_callback = 0;
> + }
> + if (sdev->lsc_callback) {
> + rte_eth_dev_callback_unregister(PORT_ID(sdev),
> + RTE_ETH_EVENT_INTR_LSC,
> + failsafe_eth_lsc_event_callback,
> + sdev);
Same comment here regarding the returned error from rte_eth_dev_callback_unregister call and lsc_event_callback.
> + sdev->lsc_callback = 0;
> + }
> +}
> +
> +void
> failsafe_dev_remove(struct rte_eth_dev *dev) {
> struct sub_device *sdev;
> diff --git a/drivers/net/failsafe/failsafe_ops.c
> b/drivers/net/failsafe/failsafe_ops.c
> index d04277b..e0570b6 100644
> --- a/drivers/net/failsafe/failsafe_ops.c
> +++ b/drivers/net/failsafe/failsafe_ops.c
> @@ -146,6 +146,8 @@
> if (ret)
> WARN("Failed to register RMV callback for
> sub_device %d",
> SUB_ID(sdev));
> + else
> + sdev->rmv_callback = 1;
> }
> dev->data->dev_conf.intr_conf.rmv = 0;
> if (lsc_interrupt) {
> @@ -156,6 +158,8 @@
> if (ret)
> WARN("Failed to register LSC callback for
> sub_device %d",
> SUB_ID(sdev));
> + else
> + sdev->lsc_callback = 1;
> }
> dev->data->dev_conf.intr_conf.lsc = lsc_enabled;
> sdev->state = DEV_ACTIVE;
> @@ -282,6 +286,7 @@
> PRIV(dev)->state = DEV_ACTIVE - 1;
> FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE) {
> DEBUG("Closing sub_device %d", i);
> + failsafe_eth_dev_unregister_callbacks(sdev);
DEBUG("Closing...") message should be in its right place just before closing sdev (next line).
> rte_eth_dev_close(PORT_ID(sdev));
> sdev->state = DEV_ACTIVE - 1;
> }
> diff --git a/drivers/net/failsafe/failsafe_private.h
> b/drivers/net/failsafe/failsafe_private.h
> index 7e6a3f8..3222653 100644
> --- a/drivers/net/failsafe/failsafe_private.h
> +++ b/drivers/net/failsafe/failsafe_private.h
> @@ -119,6 +119,8 @@ struct sub_device {
> volatile unsigned int remove:1;
> /* flow isolation state */
> int flow_isolated:1;
> + unsigned int rmv_callback:1;
> + unsigned int lsc_callback:1;
Nit-pick: please consider adding a description for rmv_callback and lsc_callback similar to the other fields in this struct.
> };
>
> struct fs_priv {
> @@ -211,6 +213,7 @@ uint16_t failsafe_tx_burst_fast(void *txq,
> /* ETH_DEV */
>
> int failsafe_eth_dev_state_sync(struct rte_eth_dev *dev);
> +void failsafe_eth_dev_unregister_callbacks(struct sub_device *sdev);
> void failsafe_dev_remove(struct rte_eth_dev *dev); void
> failsafe_stats_increment(struct rte_eth_stats *to,
> struct rte_eth_stats *from);
> --
> 1.9.5
@@ -260,6 +260,7 @@
sdev->state = DEV_ACTIVE;
/* fallthrough */
case DEV_ACTIVE:
+ failsafe_eth_dev_unregister_callbacks(sdev);
rte_eth_dev_close(PORT_ID(sdev));
sdev->state = DEV_PROBED;
/* fallthrough */
@@ -321,6 +322,27 @@
}
void
+failsafe_eth_dev_unregister_callbacks(struct sub_device *sdev)
+{
+ if (sdev == NULL)
+ return;
+ if (sdev->rmv_callback) {
+ rte_eth_dev_callback_unregister(PORT_ID(sdev),
+ RTE_ETH_EVENT_INTR_RMV,
+ failsafe_eth_rmv_event_callback,
+ sdev);
+ sdev->rmv_callback = 0;
+ }
+ if (sdev->lsc_callback) {
+ rte_eth_dev_callback_unregister(PORT_ID(sdev),
+ RTE_ETH_EVENT_INTR_LSC,
+ failsafe_eth_lsc_event_callback,
+ sdev);
+ sdev->lsc_callback = 0;
+ }
+}
+
+void
failsafe_dev_remove(struct rte_eth_dev *dev)
{
struct sub_device *sdev;
@@ -146,6 +146,8 @@
if (ret)
WARN("Failed to register RMV callback for sub_device %d",
SUB_ID(sdev));
+ else
+ sdev->rmv_callback = 1;
}
dev->data->dev_conf.intr_conf.rmv = 0;
if (lsc_interrupt) {
@@ -156,6 +158,8 @@
if (ret)
WARN("Failed to register LSC callback for sub_device %d",
SUB_ID(sdev));
+ else
+ sdev->lsc_callback = 1;
}
dev->data->dev_conf.intr_conf.lsc = lsc_enabled;
sdev->state = DEV_ACTIVE;
@@ -282,6 +286,7 @@
PRIV(dev)->state = DEV_ACTIVE - 1;
FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE) {
DEBUG("Closing sub_device %d", i);
+ failsafe_eth_dev_unregister_callbacks(sdev);
rte_eth_dev_close(PORT_ID(sdev));
sdev->state = DEV_ACTIVE - 1;
}
@@ -119,6 +119,8 @@ struct sub_device {
volatile unsigned int remove:1;
/* flow isolation state */
int flow_isolated:1;
+ unsigned int rmv_callback:1;
+ unsigned int lsc_callback:1;
};
struct fs_priv {
@@ -211,6 +213,7 @@ uint16_t failsafe_tx_burst_fast(void *txq,
/* ETH_DEV */
int failsafe_eth_dev_state_sync(struct rte_eth_dev *dev);
+void failsafe_eth_dev_unregister_callbacks(struct sub_device *sdev);
void failsafe_dev_remove(struct rte_eth_dev *dev);
void failsafe_stats_increment(struct rte_eth_stats *to,
struct rte_eth_stats *from);