diff mbox series

[V4,net] net: mana: Fix error handling in mana_create_txq/rxq's NAPI cleanup

Message ID 1725281027-29331-1-git-send-email-schakrabarti@linux.microsoft.com (mailing list archive)
State Not Applicable
Headers show
Series [V4,net] net: mana: Fix error handling in mana_create_txq/rxq's NAPI cleanup | expand

Commit Message

Souradeep Chakrabarti Sept. 2, 2024, 12:43 p.m. UTC
Currently napi_disable() gets called during rxq and txq cleanup,
even before napi is enabled and hrtimer is initialized. It causes
kernel panic.

? page_fault_oops+0x136/0x2b0
  ? page_counter_cancel+0x2e/0x80
  ? do_user_addr_fault+0x2f2/0x640
  ? refill_obj_stock+0xc4/0x110
  ? exc_page_fault+0x71/0x160
  ? asm_exc_page_fault+0x27/0x30
  ? __mmdrop+0x10/0x180
  ? __mmdrop+0xec/0x180
  ? hrtimer_active+0xd/0x50
  hrtimer_try_to_cancel+0x2c/0xf0
  hrtimer_cancel+0x15/0x30
  napi_disable+0x65/0x90
  mana_destroy_rxq+0x4c/0x2f0
  mana_create_rxq.isra.0+0x56c/0x6d0
  ? mana_uncfg_vport+0x50/0x50
  mana_alloc_queues+0x21b/0x320
  ? skb_dequeue+0x5f/0x80

Cc: stable@vger.kernel.org
Fixes: e1b5683ff62e ("net: mana: Move NAPI from EQ to CQ")
Signed-off-by: Souradeep Chakrabarti <schakrabarti@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
---
V4 -> V3:
Made napi_initialized from atomic_t to bool in txq, as per review comment.
Also used validate_state for rxq as a check.

V3 -> V2:
Instead of using napi internal attribute, using an atomic
attribute to verify napi is initialized for a particular txq / rxq.

V2 -> V1:
Addressed the comment on cleaning up napi for the queues,
where queue creation was successful.
---
 drivers/net/ethernet/microsoft/mana/mana_en.c | 22 +++++++++++--------
 include/net/mana/mana.h                       |  2 ++
 2 files changed, 15 insertions(+), 9 deletions(-)

Comments

patchwork-bot+netdevbpf@kernel.org Sept. 4, 2024, 11 a.m. UTC | #1
Hello:

This patch was applied to netdev/net.git (main)
by David S. Miller <davem@davemloft.net>:

On Mon,  2 Sep 2024 05:43:47 -0700 you wrote:
> Currently napi_disable() gets called during rxq and txq cleanup,
> even before napi is enabled and hrtimer is initialized. It causes
> kernel panic.
> 
> ? page_fault_oops+0x136/0x2b0
>   ? page_counter_cancel+0x2e/0x80
>   ? do_user_addr_fault+0x2f2/0x640
>   ? refill_obj_stock+0xc4/0x110
>   ? exc_page_fault+0x71/0x160
>   ? asm_exc_page_fault+0x27/0x30
>   ? __mmdrop+0x10/0x180
>   ? __mmdrop+0xec/0x180
>   ? hrtimer_active+0xd/0x50
>   hrtimer_try_to_cancel+0x2c/0xf0
>   hrtimer_cancel+0x15/0x30
>   napi_disable+0x65/0x90
>   mana_destroy_rxq+0x4c/0x2f0
>   mana_create_rxq.isra.0+0x56c/0x6d0
>   ? mana_uncfg_vport+0x50/0x50
>   mana_alloc_queues+0x21b/0x320
>   ? skb_dequeue+0x5f/0x80
> 
> [...]

Here is the summary with links:
  - [V4,net] net: mana: Fix error handling in mana_create_txq/rxq's NAPI cleanup
    https://git.kernel.org/netdev/net/c/b6ecc6620376

You are awesome, thank you!
diff mbox series

Patch

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 39f56973746d..3d151700f658 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1872,10 +1872,12 @@  static void mana_destroy_txq(struct mana_port_context *apc)
 
 	for (i = 0; i < apc->num_queues; i++) {
 		napi = &apc->tx_qp[i].tx_cq.napi;
-		napi_synchronize(napi);
-		napi_disable(napi);
-		netif_napi_del(napi);
-
+		if (apc->tx_qp[i].txq.napi_initialized) {
+			napi_synchronize(napi);
+			napi_disable(napi);
+			netif_napi_del(napi);
+			apc->tx_qp[i].txq.napi_initialized = false;
+		}
 		mana_destroy_wq_obj(apc, GDMA_SQ, apc->tx_qp[i].tx_object);
 
 		mana_deinit_cq(apc, &apc->tx_qp[i].tx_cq);
@@ -1931,6 +1933,7 @@  static int mana_create_txq(struct mana_port_context *apc,
 		txq->ndev = net;
 		txq->net_txq = netdev_get_tx_queue(net, i);
 		txq->vp_offset = apc->tx_vp_offset;
+		txq->napi_initialized = false;
 		skb_queue_head_init(&txq->pending_skbs);
 
 		memset(&spec, 0, sizeof(spec));
@@ -1997,6 +2000,7 @@  static int mana_create_txq(struct mana_port_context *apc,
 
 		netif_napi_add_tx(net, &cq->napi, mana_poll);
 		napi_enable(&cq->napi);
+		txq->napi_initialized = true;
 
 		mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT);
 	}
@@ -2008,7 +2012,7 @@  static int mana_create_txq(struct mana_port_context *apc,
 }
 
 static void mana_destroy_rxq(struct mana_port_context *apc,
-			     struct mana_rxq *rxq, bool validate_state)
+			     struct mana_rxq *rxq, bool napi_initialized)
 
 {
 	struct gdma_context *gc = apc->ac->gdma_dev->gdma_context;
@@ -2023,15 +2027,15 @@  static void mana_destroy_rxq(struct mana_port_context *apc,
 
 	napi = &rxq->rx_cq.napi;
 
-	if (validate_state)
+	if (napi_initialized) {
 		napi_synchronize(napi);
 
-	napi_disable(napi);
+		napi_disable(napi);
 
+		netif_napi_del(napi);
+	}
 	xdp_rxq_info_unreg(&rxq->xdp_rxq);
 
-	netif_napi_del(napi);
-
 	mana_destroy_wq_obj(apc, GDMA_RQ, rxq->rxobj);
 
 	mana_deinit_cq(apc, &rxq->rx_cq);
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 7caa334f4888..b8a6c7504ee1 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -98,6 +98,8 @@  struct mana_txq {
 
 	atomic_t pending_sends;
 
+	bool napi_initialized;
+
 	struct mana_stats_tx stats;
 };