[PATCH v1] i40e: Lock VF cloud filter list operations

[PATCH v1] i40e: Lock VF cloud filter list operations

[Binbin Deng]

A VF's cloud-filter hlist is modified by the virtchnl add and delete
handlers and by i40e_del_all_cloud_filters(), which runs when ADq is
disabled or when the VF loses trusted status.  These paths do not share a
lock.  In particular, the PF's async VF-message handler can process
VIRTCHNL_OP_DEL_CLOUD_FILTER while host-side ndo_set_vf_trust() removes
every cloud filter for that VF.

The race is reachable from a guest by issuing cloud-filter virtchnl
requests while the host revokes VF trust or disables ADq.  The VF-message
handler can traverse nodes that the bulk-delete path has already freed, or
both paths can remove the same node.  The result can be a KASAN
use-after-free, hlist corruption, incorrect filter accounting, or a panic.
The virtchnl operation-pending bit does not serialize this host-side trust
path.

Serialize cloud-filter control operations with a mutex.  Hold it across
the firmware add or delete, hlist update, and free, so bulk deletion and
individual add/delete operations cannot observe a partially removed list.
The lock is file-local and slow-path only.

Found during a static-analysis-assisted audit: candidate sites were
surfaced by a Coccinelle rule, and the reader/writer paths were
confirmed by LLM-assisted (GLM-5.3) code inspection. Due to a lack 
of hardware infrastructureThe issue was not observed at runtime.
It is identified by code inspection only.

Fixes: e284fc280473 ("i40e: Add and delete cloud filter")
Assisted-by: GLM-5.3 coccinelle
Signed-off-by: Binbin Deng <18983559317@163.com>
---
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index a26c3d47ec15..f73a710f42f1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -3740,6 +3740,8 @@ static struct i40e_vsi *i40e_find_vsi_from_seid(struct i40e_vf *vf, u16 seid)
  *
  * This function deletes all cloud filters
  **/
+static DEFINE_MUTEX(i40e_vf_cloud_filter_lock);
+
 static void i40e_del_all_cloud_filters(struct i40e_vf *vf)
 {
 	struct i40e_cloud_filter *cfilter = NULL;
@@ -3748,6 +3750,7 @@ static void i40e_del_all_cloud_filters(struct i40e_vf *vf)
 	struct hlist_node *node;
 	int ret;
 
+	mutex_lock(&i40e_vf_cloud_filter_lock);
 	hlist_for_each_entry_safe(cfilter, node,
 				  &vf->cloud_filter_list, cloud_node) {
 		vsi = i40e_find_vsi_from_seid(vf, cfilter->seid);
@@ -3773,6 +3776,7 @@ static void i40e_del_all_cloud_filters(struct i40e_vf *vf)
 		kfree(cfilter);
 		vf->num_cloud_filters--;
 	}
+	mutex_unlock(&i40e_vf_cloud_filter_lock);
 }
 
 /**
@@ -3856,6 +3860,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg)
 	}
 
 	/* get the vsi to which the tc belongs to */
+	mutex_lock(&i40e_vf_cloud_filter_lock);
 	vsi = pf->vsi[vf->ch[vcf->action_meta].vsi_idx];
 	cfilter.seid = vsi->seid;
 	cfilter.flags = vcf->field_flags;
@@ -3870,6 +3875,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg)
 			"VF %d: Failed to delete cloud filter, err %pe aq_err %s\n",
 			vf->vf_id, ERR_PTR(ret),
 			libie_aq_str(pf->hw.aq.asq_last_status));
+		mutex_unlock(&i40e_vf_cloud_filter_lock);
 		goto err;
 	}
 
@@ -3901,6 +3907,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg)
 		kfree(cf);
 		vf->num_cloud_filters--;
 	}
+	mutex_unlock(&i40e_vf_cloud_filter_lock);
 
 err:
 	return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DEL_CLOUD_FILTER,
@@ -4002,6 +4009,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 	}
 
 	/* get the VSI to which the TC belongs to */
+	mutex_lock(&i40e_vf_cloud_filter_lock);
 	vsi = pf->vsi[vf->ch[vcf->action_meta].vsi_idx];
 	cfilter->seid = vsi->seid;
 	cfilter->flags = vcf->field_flags;
@@ -4016,6 +4024,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 			"VF %d: Failed to add cloud filter, err %pe aq_err %s\n",
 			vf->vf_id, ERR_PTR(aq_ret),
 			libie_aq_str(pf->hw.aq.asq_last_status));
+		mutex_unlock(&i40e_vf_cloud_filter_lock);
 		goto err_free;
 	}
 
@@ -4024,6 +4033,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 	/* release the pointer passing it to the collection */
 	cfilter = NULL;
 	vf->num_cloud_filters++;
+	mutex_unlock(&i40e_vf_cloud_filter_lock);
 err_free:
 	kfree(cfilter);
 err_out:
-- 
2.43.0

Re: [PATCH v1] i40e: Lock VF cloud filter list operations

[kernel test robot]

Hi Binbin,

kernel test robot noticed the following build warnings:

[auto build test WARNING on tnguy-next-queue/dev-queue]
[also build test WARNING on tnguy-net-queue/dev-queue linus/master v7.3 next-20261019]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Binbin-Deng/i40e-Lock-VF-cloud-filter-list-operations/20261020-105856
base:   https://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue.git dev-queue
patch link:    https://lore.kernel.org/r/20261020025856.519623-1-18983559317%40163.com
patch subject: [PATCH v1] i40e: Lock VF cloud filter list operations
config: loongarch-defconfig (https://download.01.org/0day-ci/archive/20261021/202610210619.K13qhCpp-lkp@intel.com/config)
compiler: clang version 24.0.0git (https://github.com/llvm/llvm-project 2c419645e808a6667eee9dbb16c828f77e2fd2f0)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20261021/202610210619.K13qhCpp-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202610210619.K13qhCpp-lkp@intel.com/

All warnings (new ones prefixed by >>):

>> Warning: drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:3739 function parameter 'i40e_vf_cloud_filter_lock' not described in 'DEFINE_MUTEX'
>> Warning: drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:3739 expecting prototype for i40e_del_all_cloud_filters(). Prototype was for DEFINE_MUTEX() instead

--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH v1] i40e: Lock VF cloud filter list operations

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [High] i40e: TOCTOU race and VSI UAF in i40e_vc_add_cloud_filter() and reset
- [Low] i40e: mutex definition breaks kernel-doc for i40e_del_all_cloud_filters()
--

commit 03ab6f762cec8d24f3f9bbef8a127d3ed4ca9ef7
Author: Binbin Deng <18983559317@163.com>

i40e: Lock VF cloud filter list operations

This commit adds a file-local mutex, i40e_vf_cloud_filter_lock, to serialize
VF cloud filter additions, deletions, and bulk removals across
i40e_vc_add_cloud_filter(), i40e_vc_del_cloud_filter(), and
i40e_del_all_cloud_filters().

> diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
> index c6732a24b6400..d62e59c7ac814 100644
> --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
> +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
> @@ -3740,6 +3740,8 @@ static struct i40e_vsi *i40e_find_vsi_from_seid(struct i40e_vf *vf, u16 seid)
>   *
>   * This function deletes all cloud filters
>   **/
> +static DEFINE_MUTEX(i40e_vf_cloud_filter_lock);
> +
>  static void i40e_del_all_cloud_filters(struct i40e_vf *vf)

[Severity: Low]
Will placing DEFINE_MUTEX(i40e_vf_cloud_filter_lock) between the kernel-doc
comment block and i40e_del_all_cloud_filters() cause scripts/kernel-doc to
emit a warning?

 Because DEFINE_MUTEX() sits immediately after the closing **/ of the comment,
kernel-doc parses DEFINE_MUTEX() as the documented prototype instead of
i40e_del_all_cloud_filters().

[ ... ]

> @@ -3856,6 +3860,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg)
>  	}
>  
>  	/* get the vsi to which the tc belongs to */
> +	mutex_lock(&i40e_vf_cloud_filter_lock);
>  	vsi = pf->vsi[vf->ch[vcf->action_meta].vsi_idx];
>  	cfilter.seid = vsi->seid;
>  	cfilter.flags = vcf->field_flags;

[ ... ]

> @@ -4002,6 +4009,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
>  	}
>  
>  	/* get the VSI to which the TC belongs to */
> +	mutex_lock(&i40e_vf_cloud_filter_lock);
>  	vsi = pf->vsi[vf->ch[vcf->action_meta].vsi_idx];
>  	cfilter->seid = vsi->seid;
>  	cfilter->flags = vcf->field_flags;

[Severity: High]
Can i40e_vc_add_cloud_filter() and i40e_vc_del_cloud_filter() still race with
i40e_ndo_set_vf_trust() and dereference a NULL or freed struct i40e_vsi, or
install a cloud filter after trust has been revoked?

In both i40e_vc_add_cloud_filter() and i40e_vc_del_cloud_filter(), the checks
for i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE), vf->adq_enabled,
i40e_validate_cloud_filter(vf, vcf), and vf->num_cloud_filters run before
acquiring i40e_vf_cloud_filter_lock.

Meanwhile, when host-side trust is revoked, i40e_ndo_set_vf_trust() resets the
VF outside i40e_vf_cloud_filter_lock before calling
i40e_del_all_cloud_filters():

drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:i40e_ndo_set_vf_trust() {
	...
	if (!setting &&
	    (vf->adq_enabled || vf->num_cloud_filters > 0 ||
	     test_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states) ||
	     test_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states))) {
		i40e_vc_reset_vf(vf, true);
		i40e_del_all_cloud_filters(vf);
	}
	...
}

During i40e_vc_reset_vf() -> i40e_reset_vf() -> i40e_cleanup_reset_vf() ->
i40e_free_vf_res(), the ADq channel VSIs are released and their indices are
cleared without holding i40e_vf_cloud_filter_lock:

drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:i40e_free_vf_res() {
	...
	if (vf->adq_enabled && vf->ch[0].vsi_idx) {
		for (j = 0; j < vf->num_tc; j++) {
			if (j)
				i40e_vsi_release(pf->vsi[vf->ch[j].vsi_idx]);
			vf->ch[j].vsi_idx = 0;
			vf->ch[j].vsi_id = 0;
		}
	}
	...
}

If i40e_vc_add_cloud_filter() or i40e_vc_del_cloud_filter() passes the initial
unlocked validation checks and then executes:

	mutex_lock(&i40e_vf_cloud_filter_lock);
	vsi = pf->vsi[vf->ch[vcf->action_meta].vsi_idx];
	cfilter->seid = vsi->seid;

concurrently with i40e_vc_reset_vf(), vsi can be NULL or already freed by
i40e_vsi_release(), or vf->ch[vcf->action_meta].vsi_idx can be zeroed so that
pf->vsi[0] (the PF main VSI) is used instead.

Additionally, if i40e_vc_add_cloud_filter() passes
i40e_validate_cloud_filter() before trust is revoked and acquires
i40e_vf_cloud_filter_lock after both i40e_vc_reset_vf() and
i40e_del_all_cloud_filters() have finished, wouldn't it program the filter into
hardware and append cfilter to vf->cloud_filter_list for an untrusted VF?

[ ... ]

>

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20261020025856.519623-1-18983559317@163.com?part=1

RE: [PATCH v1] i40e: Lock VF cloud filter list operations

[Loktionov, Aleksandr]

> -----Original Message-----
> From: Binbin Deng <18983559317@163.com>
> Sent: Tuesday, October 20, 2026 4:59 AM
> To: Nguyen, Anthony L <anthony.l.nguyen@intel.com>; Kitszel, Przemyslaw
> <przemyslaw.kitszel@intel.com>; andrew+netdev@lunn.ch;
> davem@davemloft.net; edumazet@google.com; kuba@kernel.org;
> pabeni@redhat.com
> Cc: intel-wired-lan@lists.osuosl.org; netdev@vger.kernel.org; linux-
> kernel@vger.kernel.org; Binbin Deng <18983559317@163.com>
> Subject: [PATCH v1] i40e: Lock VF cloud filter list operations
> 
> A VF's cloud-filter hlist is modified by the virtchnl add and delete
> handlers and by i40e_del_all_cloud_filters(), which runs when ADq is
> disabled or when the VF loses trusted status.  These paths do not share
> a lock.  In particular, the PF's async VF-message handler can process
> VIRTCHNL_OP_DEL_CLOUD_FILTER while host-side ndo_set_vf_trust() removes
> every cloud filter for that VF.
> 
> The race is reachable from a guest by issuing cloud-filter virtchnl
> requests while the host revokes VF trust or disables ADq.  The VF-
> message handler can traverse nodes that the bulk-delete path has already
> freed, or both paths can remove the same node.  The result can be a
> KASAN use-after-free, hlist corruption, incorrect filter accounting, or
> a panic.
> The virtchnl operation-pending bit does not serialize this host-side
> trust path.
> 
> Serialize cloud-filter control operations with a mutex.  Hold it across
> the firmware add or delete, hlist update, and free, so bulk deletion and
> individual add/delete operations cannot observe a partially removed
> list.
> The lock is file-local and slow-path only.
> 
> Found during a static-analysis-assisted audit: candidate sites were
> surfaced by a Coccinelle rule, and the reader/writer paths were
> confirmed by LLM-assisted (GLM-5.3) code inspection. Due to a lack of
> hardware infrastructureThe issue was not observed at runtime.
> It is identified by code inspection only.
> 
> Fixes: e284fc280473 ("i40e: Add and delete cloud filter")
> Assisted-by: GLM-5.3 coccinelle
> Signed-off-by: Binbin Deng <18983559317@163.com>
> ---
>  drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 10 ++++++++++
>  1 file changed, 10 insertions(+)
> 
> diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
> b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
> index a26c3d47ec15..f73a710f42f1 100644
> --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
> +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
> @@ -3740,6 +3740,8 @@ static struct i40e_vsi
> *i40e_find_vsi_from_seid(struct i40e_vf *vf, u16 seid)
>   *
>   * This function deletes all cloud filters
>   **/
> +static DEFINE_MUTEX(i40e_vf_cloud_filter_lock);
> +
>  static void i40e_del_all_cloud_filters(struct i40e_vf *vf)  {
>  	struct i40e_cloud_filter *cfilter = NULL; @@ -3748,6 +3750,7 @@
> static void i40e_del_all_cloud_filters(struct i40e_vf *vf)
>  	struct hlist_node *node;
>  	int ret;
> 
> +	mutex_lock(&i40e_vf_cloud_filter_lock);
>  	hlist_for_each_entry_safe(cfilter, node,
>  				  &vf->cloud_filter_list, cloud_node) {
>  		vsi = i40e_find_vsi_from_seid(vf, cfilter->seid); @@ -
> 3773,6 +3776,7 @@ static void i40e_del_all_cloud_filters(struct i40e_vf
> *vf)
>  		kfree(cfilter);
>  		vf->num_cloud_filters--;
>  	}
> +	mutex_unlock(&i40e_vf_cloud_filter_lock);
>  }
> 
>  /**
> @@ -3856,6 +3860,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf
> *vf, u8 *msg)
>  	}
> 
>  	/* get the vsi to which the tc belongs to */
> +	mutex_lock(&i40e_vf_cloud_filter_lock);
>  	vsi = pf->vsi[vf->ch[vcf->action_meta].vsi_idx];
>  	cfilter.seid = vsi->seid;
>  	cfilter.flags = vcf->field_flags;
> @@ -3870,6 +3875,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf
> *vf, u8 *msg)
>  			"VF %d: Failed to delete cloud filter, err %pe
> aq_err %s\n",
>  			vf->vf_id, ERR_PTR(ret),
>  			libie_aq_str(pf->hw.aq.asq_last_status));
> +		mutex_unlock(&i40e_vf_cloud_filter_lock);
>  		goto err;
>  	}
> 
> @@ -3901,6 +3907,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf
> *vf, u8 *msg)
>  		kfree(cf);
>  		vf->num_cloud_filters--;
>  	}
> +	mutex_unlock(&i40e_vf_cloud_filter_lock);
> 
>  err:
>  	return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DEL_CLOUD_FILTER,
> @@ -4002,6 +4009,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf
> *vf, u8 *msg)
>  	}
> 
>  	/* get the VSI to which the TC belongs to */
> +	mutex_lock(&i40e_vf_cloud_filter_lock);
>  	vsi = pf->vsi[vf->ch[vcf->action_meta].vsi_idx];
>  	cfilter->seid = vsi->seid;
>  	cfilter->flags = vcf->field_flags;
> @@ -4016,6 +4024,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf
> *vf, u8 *msg)
>  			"VF %d: Failed to add cloud filter, err %pe aq_err
> %s\n",
>  			vf->vf_id, ERR_PTR(aq_ret),
>  			libie_aq_str(pf->hw.aq.asq_last_status));
> +		mutex_unlock(&i40e_vf_cloud_filter_lock);
>  		goto err_free;
>  	}
> 
> @@ -4024,6 +4033,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf
> *vf, u8 *msg)
>  	/* release the pointer passing it to the collection */
>  	cfilter = NULL;
>  	vf->num_cloud_filters++;
> +	mutex_unlock(&i40e_vf_cloud_filter_lock);
>  err_free:
>  	kfree(cfilter);
>  err_out:
> --
> 2.43.0

I'm afraid one more global lock shared among all cards on server will make things worse.
@Jakub Kicinski can you comment?