mlx5e_hv_vhca_stats_create() registers the stats agent through
mlx5_hv_vhca_agent_create(). The helper publishes the agent in
hv_vhca->agents[type] under agents_lock and immediately schedules an
asynchronous control invalidation on the HV VHCA workqueue before
returning to mlx5e.
The asynchronous invalidation invokes the control agent's invalidate
callback, which reads the hypervisor control block and forwards the
command to mlx5e_hv_vhca_stats_control(). That callback may either:
- call cancel_delayed_work_sync(&priv->stats_agent.work), or
- call queue_delayed_work(priv->wq, &sagent->work, sagent->delay).
However, the delayed_work and priv->stats_agent.agent are only
initialized after mlx5_hv_vhca_agent_create() returns to mlx5e:
agent = mlx5_hv_vhca_agent_create(...); /* publish + invalidate */
...
priv->stats_agent.agent = agent; /* too late */
INIT_DELAYED_WORK(&priv->stats_agent.work, ...); /* too late */
If the asynchronous control path runs before the two assignments
above, it can:
- Operate on an uninitialized delayed_work whose timer.function is
NULL. queue_delayed_work() calls add_timer() unconditionally, so
when the timer expires the timer softirq invokes a NULL function
pointer.
- Re-initialize the timer later through INIT_DELAYED_WORK() while
the timer is already enqueued in the timer wheel, corrupting the
hlist (entry.pprev cleared while the previous bucket node still
points at this entry).
- When the worker eventually runs, mlx5e_hv_vhca_stats_work() reads
sagent->agent (NULL) and dereferences it inside
mlx5_hv_vhca_agent_write().
Fix this by:
- Initializing priv->stats_agent.work before invoking
mlx5_hv_vhca_agent_create(), so the work is always in a valid
state when the control callback observes it.
- Adding a struct mlx5_hv_vhca_agent **ctx_update out-parameter
to mlx5_hv_vhca_agent_create(). The helper writes the agent
pointer to *ctx_update before publishing into hv_vhca->agents[]
and triggering the agents_update flow, so any callback
subsequently invoked from that flow already sees a valid
priv->stats_agent.agent. This avoids having the control
callback participate in agent initialization.
While at it, access priv->stats_agent.agent with
READ_ONCE()/WRITE_ONCE() for the cross-CPU access with the worker, and
clear priv->stats_agent.buf on the agent_create() failure path.
Fixes: cef35af34d6d ("net/mlx5e: Add mlx5e HV VHCA stats agent")
Signed-off-by: Feng Liu <feliu@nvidia.com>
Reviewed-by: Eran Ben Elisha <eranbe@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260630115151.729219-3-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
sagent = container_of(dwork, struct mlx5e_hv_vhca_stats_agent, work);
priv = container_of(sagent, struct mlx5e_priv, stats_agent);
buf_len = mlx5e_hv_vhca_stats_buf_size(priv);
- agent = sagent->agent;
+ agent = READ_ONCE(sagent->agent);
buf = sagent->buf;
memset(buf, 0, buf_len);
if (!priv->stats_agent.buf)
return;
+ INIT_DELAYED_WORK(&priv->stats_agent.work, mlx5e_hv_vhca_stats_work);
+
agent = mlx5_hv_vhca_agent_create(priv->mdev->hv_vhca,
MLX5_HV_VHCA_AGENT_STATS,
mlx5e_hv_vhca_stats_control, NULL,
mlx5e_hv_vhca_stats_cleanup,
- priv);
+ priv,
+ &priv->stats_agent.agent);
if (IS_ERR_OR_NULL(agent)) {
if (IS_ERR(agent))
agent);
kvfree(priv->stats_agent.buf);
- return;
+ priv->stats_agent.buf = NULL;
}
-
- priv->stats_agent.agent = agent;
- INIT_DELAYED_WORK(&priv->stats_agent.work, mlx5e_hv_vhca_stats_work);
}
void mlx5e_hv_vhca_stats_destroy(struct mlx5e_priv *priv)
{
- if (IS_ERR_OR_NULL(priv->stats_agent.agent))
+ struct mlx5_hv_vhca_agent *agent;
+
+ agent = READ_ONCE(priv->stats_agent.agent);
+ if (IS_ERR_OR_NULL(agent))
return;
- mlx5_hv_vhca_agent_destroy(priv->stats_agent.agent);
- priv->stats_agent.agent = NULL;
+ mlx5_hv_vhca_agent_destroy(agent);
+ WRITE_ONCE(priv->stats_agent.agent, NULL);
kvfree(priv->stats_agent.buf);
priv->stats_agent.buf = NULL;
}
return mlx5_hv_vhca_agent_create(hv_vhca, MLX5_HV_VHCA_AGENT_CONTROL,
NULL,
mlx5_hv_vhca_control_agent_invalidate,
- NULL, NULL);
+ NULL, NULL, NULL);
}
static void mlx5_hv_vhca_control_agent_destroy(struct mlx5_hv_vhca_agent *agent)
void (*invalidate)(struct mlx5_hv_vhca_agent*,
u64 block_mask),
void (*cleaup)(struct mlx5_hv_vhca_agent *agent),
- void *priv)
+ void *priv,
+ struct mlx5_hv_vhca_agent **ctx_update)
{
struct mlx5_hv_vhca_agent *agent;
agent->invalidate = invalidate;
agent->cleanup = cleaup;
+ if (ctx_update)
+ WRITE_ONCE(*ctx_update, agent);
+
mutex_lock(&hv_vhca->agents_lock);
hv_vhca->agents[type] = agent;
mutex_unlock(&hv_vhca->agents_lock);
void (*invalidate)(struct mlx5_hv_vhca_agent*,
u64 block_mask),
void (*cleanup)(struct mlx5_hv_vhca_agent *agent),
- void *context);
+ void *context,
+ struct mlx5_hv_vhca_agent **ctx_update);
void mlx5_hv_vhca_agent_destroy(struct mlx5_hv_vhca_agent *agent);
int mlx5_hv_vhca_agent_write(struct mlx5_hv_vhca_agent *agent,
void (*invalidate)(struct mlx5_hv_vhca_agent*,
u64 block_mask),
void (*cleanup)(struct mlx5_hv_vhca_agent *agent),
- void *context)
+ void *context,
+ struct mlx5_hv_vhca_agent **ctx_update)
{
return NULL;
}
projects / thirdparty / kernel / linux.git / commitdiff
