[v6] net/ice: fix ice dcf control thread crash
Checks
Commit Message
The control thread accesses the hardware resources after the
resources were released, which results in a segment error.
The 'ice-reset' threads are detached, so thread resources cannot be
reclaimed by `pthread_join` calls.
This commit synchronizes the number of "ice-reset" threads by adding a
variable ("vsi_update_thread_num") to the "struct ice_dcf_hw" and
performing an atomic operation on this variable. When releasing HW
resources, we wait for the number of "ice-reset" threads to be reduced
to 0 before releasing the resources.
Fixes: c7e1a1a3bfeb ("net/ice: refactor DCF VLAN handling")
Fixes: 7564d5509611 ("net/ice: add DCF hardware initialization")
Fixes: 0b02c9519432 ("net/ice: handle PF initialization by DCF")
Cc: stable@dpdk.org
Signed-off-by: Ke Zhang <ke1x.zhang@intel.com>
Signed-off-by: Mingjin Ye <mingjinx.ye@intel.com>
---
v2: add pthread_exit() for windows
---
v3: Optimization. It is unsafe for a thread to forcibly exit, which
will cause the spin lock to not be released correctly
---
v4: Safely wait for all event threads to end
---
v5: Spinlock moved to struct ice_dcf_hw
---
v6: Spinlock changed to atomic
---
drivers/net/ice/ice_dcf.c | 9 +++++++++
drivers/net/ice/ice_dcf.h | 2 ++
drivers/net/ice/ice_dcf_parent.c | 6 ++++++
3 files changed, 17 insertions(+)
Comments
> -----Original Message-----
> From: Ye, MingjinX <mingjinx.ye@intel.com>
> Sent: Wednesday, March 22, 2023 1:56 PM
> To: dev@dpdk.org
> Cc: Yang, Qiming <qiming.yang@intel.com>; stable@dpdk.org; Zhou, YidingX
> <yidingx.zhou@intel.com>; Ye, MingjinX <mingjinx.ye@intel.com>; Zhang,
> Ke1X <ke1x.zhang@intel.com>; Zhang, Qi Z <qi.z.zhang@intel.com>
> Subject: [PATCH v6] net/ice: fix ice dcf control thread crash
>
> The control thread accesses the hardware resources after the resources were
> released, which results in a segment error.
>
> The 'ice-reset' threads are detached, so thread resources cannot be
> reclaimed by `pthread_join` calls.
>
> This commit synchronizes the number of "ice-reset" threads by adding a
> variable ("vsi_update_thread_num") to the "struct ice_dcf_hw" and
> performing an atomic operation on this variable. When releasing HW
> resources, we wait for the number of "ice-reset" threads to be reduced to 0
> before releasing the resources.
>
> Fixes: c7e1a1a3bfeb ("net/ice: refactor DCF VLAN handling")
> Fixes: 7564d5509611 ("net/ice: add DCF hardware initialization")
> Fixes: 0b02c9519432 ("net/ice: handle PF initialization by DCF")
> Cc: stable@dpdk.org
>
> Signed-off-by: Ke Zhang <ke1x.zhang@intel.com>
> Signed-off-by: Mingjin Ye <mingjinx.ye@intel.com>
> ---
> v2: add pthread_exit() for windows
> ---
> v3: Optimization. It is unsafe for a thread to forcibly exit, which will cause the
> spin lock to not be released correctly
> ---
> v4: Safely wait for all event threads to end
> ---
> v5: Spinlock moved to struct ice_dcf_hw
> ---
> v6: Spinlock changed to atomic
> ---
> drivers/net/ice/ice_dcf.c | 9 +++++++++
> drivers/net/ice/ice_dcf.h | 2 ++
> drivers/net/ice/ice_dcf_parent.c | 6 ++++++
> 3 files changed, 17 insertions(+)
>
> diff --git a/drivers/net/ice/ice_dcf.c b/drivers/net/ice/ice_dcf.c index
> 1c3d22ae0f..adf2cf2cb6 100644
> --- a/drivers/net/ice/ice_dcf.c
> +++ b/drivers/net/ice/ice_dcf.c
> @@ -32,6 +32,8 @@
> #define ICE_DCF_ARQ_MAX_RETRIES 200
> #define ICE_DCF_ARQ_CHECK_TIME 2 /* msecs */
>
> +#define ICE_DCF_CHECK_INTERVAL 100 /* 100ms */
> +
> #define ICE_DCF_VF_RES_BUF_SZ \
> (sizeof(struct virtchnl_vf_resource) + \
> IAVF_MAX_VF_VSI * sizeof(struct virtchnl_vsi_resource)) @@
> -639,6 +641,8 @@ ice_dcf_init_hw(struct rte_eth_dev *eth_dev, struct
> ice_dcf_hw *hw)
> rte_spinlock_init(&hw->vc_cmd_queue_lock);
> TAILQ_INIT(&hw->vc_cmd_queue);
>
> + __atomic_store_n(&hw->vsi_update_thread_num, 0,
> __ATOMIC_RELAXED);
> +
> hw->arq_buf = rte_zmalloc("arq_buf", ICE_DCF_AQ_BUF_SZ, 0);
> if (hw->arq_buf == NULL) {
> PMD_INIT_LOG(ERR, "unable to allocate AdminQ buffer
> memory"); @@ -760,6 +764,11 @@ ice_dcf_uninit_hw(struct rte_eth_dev
> *eth_dev, struct ice_dcf_hw *hw)
> rte_intr_callback_unregister(intr_handle,
> ice_dcf_dev_interrupt_handler, hw);
>
> + /* Wait for all `ice-thread` threads to exit. */
> + while (__atomic_load_n(&hw->vsi_update_thread_num,
> + __ATOMIC_ACQUIRE) != 0)
> + rte_delay_ms(ICE_DCF_CHECK_INTERVAL);
> +
> ice_dcf_mode_disable(hw);
> iavf_shutdown_adminq(&hw->avf);
>
> diff --git a/drivers/net/ice/ice_dcf.h b/drivers/net/ice/ice_dcf.h index
> 7f42ebabe9..7becf6d187 100644
> --- a/drivers/net/ice/ice_dcf.h
> +++ b/drivers/net/ice/ice_dcf.h
> @@ -105,6 +105,8 @@ struct ice_dcf_hw {
> void (*vc_event_msg_cb)(struct ice_dcf_hw *dcf_hw,
> uint8_t *msg, uint16_t msglen);
>
> + int vsi_update_thread_num;
> +
> uint8_t *arq_buf;
>
> uint16_t num_vfs;
> diff --git a/drivers/net/ice/ice_dcf_parent.c
> b/drivers/net/ice/ice_dcf_parent.c
> index 01e390ddda..6ee0fbcd2b 100644
> --- a/drivers/net/ice/ice_dcf_parent.c
> +++ b/drivers/net/ice/ice_dcf_parent.c
> @@ -154,6 +154,9 @@ ice_dcf_vsi_update_service_handler(void *param)
>
> free(param);
>
> + __atomic_fetch_sub(&hw->vsi_update_thread_num, 1,
> + __ATOMIC_RELEASE);
> +
> return NULL;
> }
>
> @@ -183,6 +186,9 @@ start_vsi_reset_thread(struct ice_dcf_hw *dcf_hw,
> bool vfr, uint16_t vf_id)
> PMD_DRV_LOG(ERR, "Failed to start the thread for reset
> handling");
> free(param);
> }
> +
> + __atomic_fetch_add(&dcf_hw->vsi_update_thread_num, 1,
> + __ATOMIC_RELAXED);
Is this correct? you increment the counter after you start the new thread with rte_ctrl_thread_create,
It is possible, __atomic_fetch_sub in ice_dcf_vsi_update_service_handler will be executed before __atomic_fetch_add?
Why not moving __atomic_fetch_add to the service_handler thread? So the order of "add" and "sub" can be guaranteed ?
> }
>
> static uint32_t
> --
> 2.25.1
@@ -32,6 +32,8 @@
#define ICE_DCF_ARQ_MAX_RETRIES 200
#define ICE_DCF_ARQ_CHECK_TIME 2 /* msecs */
+#define ICE_DCF_CHECK_INTERVAL 100 /* 100ms */
+
#define ICE_DCF_VF_RES_BUF_SZ \
(sizeof(struct virtchnl_vf_resource) + \
IAVF_MAX_VF_VSI * sizeof(struct virtchnl_vsi_resource))
@@ -639,6 +641,8 @@ ice_dcf_init_hw(struct rte_eth_dev *eth_dev, struct ice_dcf_hw *hw)
rte_spinlock_init(&hw->vc_cmd_queue_lock);
TAILQ_INIT(&hw->vc_cmd_queue);
+ __atomic_store_n(&hw->vsi_update_thread_num, 0, __ATOMIC_RELAXED);
+
hw->arq_buf = rte_zmalloc("arq_buf", ICE_DCF_AQ_BUF_SZ, 0);
if (hw->arq_buf == NULL) {
PMD_INIT_LOG(ERR, "unable to allocate AdminQ buffer memory");
@@ -760,6 +764,11 @@ ice_dcf_uninit_hw(struct rte_eth_dev *eth_dev, struct ice_dcf_hw *hw)
rte_intr_callback_unregister(intr_handle,
ice_dcf_dev_interrupt_handler, hw);
+ /* Wait for all `ice-thread` threads to exit. */
+ while (__atomic_load_n(&hw->vsi_update_thread_num,
+ __ATOMIC_ACQUIRE) != 0)
+ rte_delay_ms(ICE_DCF_CHECK_INTERVAL);
+
ice_dcf_mode_disable(hw);
iavf_shutdown_adminq(&hw->avf);
@@ -105,6 +105,8 @@ struct ice_dcf_hw {
void (*vc_event_msg_cb)(struct ice_dcf_hw *dcf_hw,
uint8_t *msg, uint16_t msglen);
+ int vsi_update_thread_num;
+
uint8_t *arq_buf;
uint16_t num_vfs;
@@ -154,6 +154,9 @@ ice_dcf_vsi_update_service_handler(void *param)
free(param);
+ __atomic_fetch_sub(&hw->vsi_update_thread_num, 1,
+ __ATOMIC_RELEASE);
+
return NULL;
}
@@ -183,6 +186,9 @@ start_vsi_reset_thread(struct ice_dcf_hw *dcf_hw, bool vfr, uint16_t vf_id)
PMD_DRV_LOG(ERR, "Failed to start the thread for reset handling");
free(param);
}
+
+ __atomic_fetch_add(&dcf_hw->vsi_update_thread_num, 1,
+ __ATOMIC_RELAXED);
}
static uint32_t