From: Petr Machata <petrm@nvidia.com>
To: Andrew Lunn <andrew+netdev@lunn.ch>,
"David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@kernel.org>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
<netdev@vger.kernel.org>
Cc: Ido Schimmel <idosch@nvidia.com>, Petr Machata <petrm@nvidia.com>,
<mlxsw@nvidia.com>, Myeonghun Pak <mhun512@gmail.com>,
Ijae Kim <ae878000@gmail.com>, Jiale Yao <yaojiale02@163.com>
Subject: [PATCH net-next 2/2] mlxsw: pci: Fix teardown order of CQ NAPI instances
Date: Mon, 16 Nov 2026 11:16:47 +0100 [thread overview]
Message-ID: <3a1a078f21028851b04ba4987fae490362b59cd4.1794823524.git.petrm@nvidia.com> (raw)
In-Reply-To: <cover.1794823524.git.petrm@nvidia.com>
In his report (see the link below), Myeonghun Pak <mhun512@gmail.com>
writes:
> mlxsw_pci_eq_irq_handler() schedules the EQ tasklet. The tasklet reads
> the EQ ring and schedules CQ NAPI instances. The CQ poll callbacks, in
> turn, dereference the RDQ or SDQ associated with the CQ.
>
> mlxsw_pci_fini() unregisters the IRQ and immediately tears down the
> asynchronous queues in RDQ, SDQ, CQ, EQ order. free_irq() waits for IRQ
> handlers, but not for a tasklet already scheduled by one. In addition,
> mlxsw_pci_cq_fini() disables each CQ NAPI only after all RDQs and SDQs
> have been freed. A pending tasklet or NAPI poll can therefore access
> freed queue storage.
The previous patch folded the tasklet into the IRQ handler, which takes
care of the first half of the problem: free_irq() in mlxsw_pci_fini() now
guarantees that nothing schedules CQ NAPI instances anymore. The second
half remains. A NAPI poll that was scheduled right before free_irq(), or
is currently running, can still dereference the RDQ or SDQ of its CQ, which
mlxsw_pci_aqs_fini() frees before the CQ, and where napi_disable() is
currently called.
In this patch, introduce a process-related duals to init / fini per-queue
callbacks: start and stop. Only CQ needs them for now, to manage the NAPI
instances. Invoke them at the end of mlxsw_pci_aqs_init() and at the
beginning of mlxsw_pci_aqs_fini(), respectively, so that NAPI is enabled
only once all queues are set up, and disabled before any of them is
destroyed. This also keeps napi_enable() and napi_disable() paired on error
paths of mlxsw_pci_aqs_init().
In his report, Myeonghun Pak notes that the issue was originally discovered
by static analysis.
Cc: Myeonghun Pak <mhun512@gmail.com>
Cc: Ijae Kim <ae878000@gmail.com>
Cc: Jiale Yao <yaojiale02@163.com>
Reported-by: Myeonghun Pak <mhun512@gmail.com>
Link: https://lore.kernel.org/netdev/20260721125753.35944-1-mhun512@gmail.com/
Reported-by: Jiale Yao <yaojiale02@163.com>
Link: https://lore.kernel.org/netdev/20261018040653.534066-1-yaojiale02@163.com/
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlxsw/pci.c | 46 ++++++++++++++++++++++-
1 file changed, 44 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index b2a7f568c74a..dc6cad5637d6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -1059,7 +1059,6 @@ static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
if (err)
goto err_page_pool_init;
- napi_enable(&q->u.cq.napi);
mlxsw_pci_queue_doorbell_consumer_ring(mlxsw_pci, q);
mlxsw_pci_queue_doorbell_arm_consumer_ring(mlxsw_pci, q);
return 0;
@@ -1074,12 +1073,23 @@ static void mlxsw_pci_cq_fini(struct mlxsw_pci *mlxsw_pci,
{
enum mlxsw_pci_cq_type cq_type = mlxsw_pci_cq_type(mlxsw_pci, q);
- napi_disable(&q->u.cq.napi);
mlxsw_pci_cq_page_pool_fini(q, cq_type);
mlxsw_pci_cq_napi_teardown(q);
mlxsw_cmd_hw2sw_cq(mlxsw_pci->core, q->num);
}
+static void mlxsw_pci_cq_start(struct mlxsw_pci *mlxsw_pci,
+ struct mlxsw_pci_queue *q)
+{
+ napi_enable(&q->u.cq.napi);
+}
+
+static void mlxsw_pci_cq_stop(struct mlxsw_pci *mlxsw_pci,
+ struct mlxsw_pci_queue *q)
+{
+ napi_disable(&q->u.cq.napi);
+}
+
static u16 mlxsw_pci_cq_elem_count(const struct mlxsw_pci_queue *q)
{
return q->u.cq.v == MLXSW_PCI_CQE_V2 ? MLXSW_PCI_CQE2_COUNT :
@@ -1198,6 +1208,10 @@ struct mlxsw_pci_queue_ops {
struct mlxsw_pci_queue *q);
void (*fini)(struct mlxsw_pci *mlxsw_pci,
struct mlxsw_pci_queue *q);
+ void (*start)(struct mlxsw_pci *mlxsw_pci,
+ struct mlxsw_pci_queue *q);
+ void (*stop)(struct mlxsw_pci *mlxsw_pci,
+ struct mlxsw_pci_queue *q);
u16 (*elem_count_f)(const struct mlxsw_pci_queue *q);
u8 (*elem_size_f)(const struct mlxsw_pci_queue *q);
u16 elem_count;
@@ -1225,6 +1239,8 @@ static const struct mlxsw_pci_queue_ops mlxsw_pci_cq_ops = {
.pre_init = mlxsw_pci_cq_pre_init,
.init = mlxsw_pci_cq_init,
.fini = mlxsw_pci_cq_fini,
+ .start = mlxsw_pci_cq_start,
+ .stop = mlxsw_pci_cq_stop,
.elem_count_f = mlxsw_pci_cq_elem_count,
.elem_size_f = mlxsw_pci_cq_elem_size
};
@@ -1349,6 +1365,28 @@ static void mlxsw_pci_queue_group_fini(struct mlxsw_pci *mlxsw_pci,
kfree(queue_group->q);
}
+static void mlxsw_pci_queue_group_start(struct mlxsw_pci *mlxsw_pci,
+ const struct mlxsw_pci_queue_ops *q_ops)
+{
+ struct mlxsw_pci_queue_type_group *queue_group;
+ int i;
+
+ queue_group = mlxsw_pci_queue_type_group_get(mlxsw_pci, q_ops->type);
+ for (i = 0; i < queue_group->count; i++)
+ q_ops->start(mlxsw_pci, &queue_group->q[i]);
+}
+
+static void mlxsw_pci_queue_group_stop(struct mlxsw_pci *mlxsw_pci,
+ const struct mlxsw_pci_queue_ops *q_ops)
+{
+ struct mlxsw_pci_queue_type_group *queue_group;
+ int i;
+
+ queue_group = mlxsw_pci_queue_type_group_get(mlxsw_pci, q_ops->type);
+ for (i = 0; i < queue_group->count; i++)
+ q_ops->stop(mlxsw_pci, &queue_group->q[i]);
+}
+
static int mlxsw_pci_aqs_init(struct mlxsw_pci *mlxsw_pci, char *mbox)
{
struct pci_dev *pdev = mlxsw_pci->pdev;
@@ -1426,6 +1464,8 @@ static int mlxsw_pci_aqs_init(struct mlxsw_pci *mlxsw_pci, char *mbox)
goto err_rdqs_init;
}
+ mlxsw_pci_queue_group_start(mlxsw_pci, &mlxsw_pci_cq_ops);
+
return 0;
err_rdqs_init:
@@ -1439,6 +1479,8 @@ static int mlxsw_pci_aqs_init(struct mlxsw_pci *mlxsw_pci, char *mbox)
static void mlxsw_pci_aqs_fini(struct mlxsw_pci *mlxsw_pci)
{
+ mlxsw_pci_queue_group_stop(mlxsw_pci, &mlxsw_pci_cq_ops);
+
mlxsw_pci_queue_group_fini(mlxsw_pci, &mlxsw_pci_rdq_ops);
mlxsw_pci_queue_group_fini(mlxsw_pci, &mlxsw_pci_sdq_ops);
mlxsw_pci_queue_group_fini(mlxsw_pci, &mlxsw_pci_cq_ops);
--
2.56.1
next prev parent reply other threads:[~2026-11-16 10:19 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-16 10:16 [PATCH net-next 0/2] mlxsw: Fix teardown order of CQ NAPI instances Petr Machata
2026-11-16 10:16 ` [PATCH net-next 1/2] mlxsw: pci: Process EQ in the IRQ handler instead of a tasklet Petr Machata
2026-11-16 10:16 ` Petr Machata [this message]
2026-11-16 10:21 ` [PATCH net-next 0/2] mlxsw: Fix teardown order of CQ NAPI instances netdev-bot+sinfo
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=3a1a078f21028851b04ba4987fae490362b59cd4.1794823524.git.petrm@nvidia.com \
--to=petrm@nvidia.com \
--cc=ae878000@gmail.com \
--cc=andrew+netdev@lunn.ch \
--cc=davem@davemloft.net \
--cc=edumazet@kernel.org \
--cc=idosch@nvidia.com \
--cc=kuba@kernel.org \
--cc=mhun512@gmail.com \
--cc=mlxsw@nvidia.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=yaojiale02@163.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox