From ac28b1ec6135649b5d78b028e47264cb3ebca5ea Mon Sep 17 00:00:00 2001
From: Liu Jian <liujian56@huawei.com>
Date: Thu, 7 Sep 2023 10:57:09 +0800
Subject: net: ipv4: fix one memleak in __inet_del_ifa()

I got the below warning when do fuzzing test:
unregister_netdevice: waiting for bond0 to become free. Usage count = 2

It can be repoduced via:

ip link add bond0 type bond
sysctl -w net.ipv4.conf.bond0.promote_secondaries=1
ip addr add 4.117.174.103/0 scope 0x40 dev bond0
ip addr add 192.168.100.111/255.255.255.254 scope 0 dev bond0
ip addr add 0.0.0.4/0 scope 0x40 secondary dev bond0
ip addr del 4.117.174.103/0 scope 0x40 dev bond0
ip link delete bond0 type bond

In this reproduction test case, an incorrect 'last_prim' is found in
__inet_del_ifa(), as a result, the secondary address(0.0.0.4/0 scope 0x40)
is lost. The memory of the secondary address is leaked and the reference of
in_device and net_device is leaked.

Fix this problem:
Look for 'last_prim' starting at location of the deleted IP and inserting
the promoted IP into the location of 'last_prim'.

Fixes: 0ff60a45678e ("[IPV4]: Fix secondary IP addresses after promotion")
Signed-off-by: Liu Jian <liujian56@huawei.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/devinet.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 9cf64ee47dd2..ca0ff15dc8fa 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -355,14 +355,14 @@ static void __inet_del_ifa(struct in_device *in_dev,
 {
 	struct in_ifaddr *promote = NULL;
 	struct in_ifaddr *ifa, *ifa1;
-	struct in_ifaddr *last_prim;
+	struct in_ifaddr __rcu **last_prim;
 	struct in_ifaddr *prev_prom = NULL;
 	int do_promote = IN_DEV_PROMOTE_SECONDARIES(in_dev);
 
 	ASSERT_RTNL();
 
 	ifa1 = rtnl_dereference(*ifap);
-	last_prim = rtnl_dereference(in_dev->ifa_list);
+	last_prim = ifap;
 	if (in_dev->dead)
 		goto no_promotions;
 
@@ -376,7 +376,7 @@ static void __inet_del_ifa(struct in_device *in_dev,
 		while ((ifa = rtnl_dereference(*ifap1)) != NULL) {
 			if (!(ifa->ifa_flags & IFA_F_SECONDARY) &&
 			    ifa1->ifa_scope <= ifa->ifa_scope)
-				last_prim = ifa;
+				last_prim = &ifa->ifa_next;
 
 			if (!(ifa->ifa_flags & IFA_F_SECONDARY) ||
 			    ifa1->ifa_mask != ifa->ifa_mask ||
@@ -440,9 +440,9 @@ no_promotions:
 
 			rcu_assign_pointer(prev_prom->ifa_next, next_sec);
 
-			last_sec = rtnl_dereference(last_prim->ifa_next);
+			last_sec = rtnl_dereference(*last_prim);
 			rcu_assign_pointer(promote->ifa_next, last_sec);
-			rcu_assign_pointer(last_prim->ifa_next, promote);
+			rcu_assign_pointer(*last_prim, promote);
 		}
 
 		promote->ifa_flags &= ~IFA_F_SECONDARY;
-- 
cgit v1.2.3


From ced33ca07d8d99435ca3320c740ea947843005ca Mon Sep 17 00:00:00 2001
From: Juntong Deng <juntong.deng@outlook.com>
Date: Thu, 7 Sep 2023 00:26:03 +0800
Subject: selftests/net: Improve bind_bhash.sh to accommodate predictable
 network interface names

Starting with v197, systemd uses predictable interface network names,
the traditional interface naming scheme (eth0) is deprecated, therefore
it cannot be assumed that the eth0 interface exists on the host.

This modification makes the bind_bhash test program run in a separate
network namespace and no longer needs to consider the name of the
network interface on the host.

Signed-off-by: Juntong Deng <juntong.deng@outlook.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/bind_bhash.sh | 26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/net/bind_bhash.sh b/tools/testing/selftests/net/bind_bhash.sh
index ca0292d4b441..a28563bdaae0 100755
--- a/tools/testing/selftests/net/bind_bhash.sh
+++ b/tools/testing/selftests/net/bind_bhash.sh
@@ -2,7 +2,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
 NR_FILES=32768
-SAVED_NR_FILES=$(ulimit -n)
+readonly NETNS="ns-$(mktemp -u XXXXXX)"
 
 # default values
 port=443
@@ -36,21 +36,21 @@ while getopts "ha:p:64" opt; do
 done
 
 setup() {
+    ip netns add "${NETNS}"
+    ip -netns "${NETNS}" link add veth0 type veth peer name veth1
+    ip -netns "${NETNS}" link set lo up
+    ip -netns "${NETNS}" link set veth0 up
+    ip -netns "${NETNS}" link set veth1 up
+
     if [[ "$use_v6" == true ]]; then
-	ip addr add $addr_v6 nodad dev eth0
+        ip -netns "${NETNS}" addr add $addr_v6 nodad dev veth0
     else
-	ip addr add $addr_v4 dev lo
+        ip -netns "${NETNS}" addr add $addr_v4 dev lo
     fi
-	ulimit -n $NR_FILES
 }
 
 cleanup() {
-    if [[ "$use_v6" == true ]]; then
-	ip addr del $addr_v6 dev eth0
-    else
-	ip addr del $addr_v4/32 dev lo
-    fi
-    ulimit -n $SAVED_NR_FILES
+    ip netns del "${NETNS}"
 }
 
 if [[ "$addr" != "" ]]; then
@@ -59,8 +59,10 @@ if [[ "$addr" != "" ]]; then
 fi
 setup
 if [[ "$use_v6" == true ]] ; then
-    ./bind_bhash $port "ipv6" $addr_v6
+    ip netns exec "${NETNS}" sh -c \
+        "ulimit -n ${NR_FILES};./bind_bhash ${port} ipv6 ${addr_v6}"
 else
-    ./bind_bhash $port "ipv4" $addr_v4
+    ip netns exec "${NETNS}" sh -c \
+        "ulimit -n ${NR_FILES};./bind_bhash ${port} ipv4 ${addr_v4}"
 fi
 cleanup
-- 
cgit v1.2.3


From e73d1ab6cd7e7190bd891e521d270cd26ad8e40d Mon Sep 17 00:00:00 2001
From: Julia Lawall <Julia.Lawall@inria.fr>
Date: Thu, 7 Sep 2023 11:55:12 +0200
Subject: net: bcmasp: add missing of_node_put

for_each_available_child_of_node performs an of_node_get
on each iteration, so a break out of the loop requires an
of_node_put.

This was done using the Coccinelle semantic patch
iterators/for_each_child.cocci

Signed-off-by: Julia Lawall <Julia.Lawall@inria.fr>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/asp2/bcmasp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
index d63d321f3e7b..f048e3d45119 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
@@ -1300,6 +1300,7 @@ static int bcmasp_probe(struct platform_device *pdev)
 		if (!intf) {
 			dev_err(dev, "Cannot create eth interface %d\n", i);
 			bcmasp_remove_intfs(priv);
+			of_node_put(intf_node);
 			goto of_put_exit;
 		}
 		list_add_tail(&intf->list, &priv->intfs);
-- 
cgit v1.2.3


From 281f65d29d6da1a9b6907fb0b145aaf34f4e4822 Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Thu, 7 Sep 2023 22:03:58 +0800
Subject: net: microchip: vcap api: Fix possible memory leak for
 vcap_dup_rule()

Inject fault When select CONFIG_VCAP_KUNIT_TEST, the below memory leak
occurs. If kzalloc() for duprule succeeds, but the following
kmemdup() fails, the duprule, ckf and caf memory will be leaked. So kfree
them in the error path.

unreferenced object 0xffff122744c50600 (size 192):
  comm "kunit_try_catch", pid 346, jiffies 4294896122 (age 911.812s)
  hex dump (first 32 bytes):
    10 27 00 00 04 00 00 00 1e 00 00 00 2c 01 00 00  .'..........,...
    00 00 00 00 00 00 00 00 18 06 c5 44 27 12 ff ff  ...........D'...
  backtrace:
    [<00000000394b0db8>] __kmem_cache_alloc_node+0x274/0x2f8
    [<0000000001bedc67>] kmalloc_trace+0x38/0x88
    [<00000000b0612f98>] vcap_dup_rule+0x50/0x460
    [<000000005d2d3aca>] vcap_add_rule+0x8cc/0x1038
    [<00000000eef9d0f8>] test_vcap_xn_rule_creator.constprop.0.isra.0+0x238/0x494
    [<00000000cbda607b>] vcap_api_rule_remove_in_front_test+0x1ac/0x698
    [<00000000c8766299>] kunit_try_run_case+0xe0/0x20c
    [<00000000c4fe9186>] kunit_generic_run_threadfn_adapter+0x50/0x94
    [<00000000f6864acf>] kthread+0x2e8/0x374
    [<0000000022e639b3>] ret_from_fork+0x10/0x20

Fixes: 814e7693207f ("net: microchip: vcap api: Add a storage state to a VCAP rule")
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/vcap/vcap_api.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.c b/drivers/net/ethernet/microchip/vcap/vcap_api.c
index 300fe1a93dce..ef980e4e5bc2 100644
--- a/drivers/net/ethernet/microchip/vcap/vcap_api.c
+++ b/drivers/net/ethernet/microchip/vcap/vcap_api.c
@@ -1021,18 +1021,32 @@ static struct vcap_rule_internal *vcap_dup_rule(struct vcap_rule_internal *ri,
 	list_for_each_entry(ckf, &ri->data.keyfields, ctrl.list) {
 		newckf = kmemdup(ckf, sizeof(*newckf), GFP_KERNEL);
 		if (!newckf)
-			return ERR_PTR(-ENOMEM);
+			goto err;
 		list_add_tail(&newckf->ctrl.list, &duprule->data.keyfields);
 	}
 
 	list_for_each_entry(caf, &ri->data.actionfields, ctrl.list) {
 		newcaf = kmemdup(caf, sizeof(*newcaf), GFP_KERNEL);
 		if (!newcaf)
-			return ERR_PTR(-ENOMEM);
+			goto err;
 		list_add_tail(&newcaf->ctrl.list, &duprule->data.actionfields);
 	}
 
 	return duprule;
+
+err:
+	list_for_each_entry_safe(ckf, newckf, &duprule->data.keyfields, ctrl.list) {
+		list_del(&ckf->ctrl.list);
+		kfree(ckf);
+	}
+
+	list_for_each_entry_safe(caf, newcaf, &duprule->data.actionfields, ctrl.list) {
+		list_del(&caf->ctrl.list);
+		kfree(caf);
+	}
+
+	kfree(duprule);
+	return ERR_PTR(-ENOMEM);
 }
 
 static void vcap_apply_width(u8 *dst, int width, int bytes)
-- 
cgit v1.2.3


From 88e69af061f2e061a68751ef9cad47a674527a1b Mon Sep 17 00:00:00 2001
From: Ratheesh Kannoth <rkannoth@marvell.com>
Date: Fri, 8 Sep 2023 08:23:09 +0530
Subject: octeontx2-pf: Fix page pool cache index corruption.

The access to page pool `cache' array and the `count' variable
is not locked. Page pool cache access is fine as long as there
is only one consumer per pool.

octeontx2 driver fills in rx buffers from page pool in NAPI context.
If system is stressed and could not allocate buffers, refiiling work
will be delegated to a delayed workqueue. This means that there are
two cosumers to the page pool cache.

Either workqueue or IRQ/NAPI can be run on other CPU. This will lead
to lock less access, hence corruption of cache pool indexes.

To fix this issue, NAPI is rescheduled from workqueue context to refill
rx buffers.

Fixes: b2e3406a38f0 ("octeontx2-pf: Add support for page pool")
Signed-off-by: Ratheesh Kannoth <rkannoth@marvell.com>
Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c |  6 ++-
 drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h |  2 +-
 .../ethernet/marvell/octeontx2/nic/otx2_common.c   | 43 +++-------------------
 .../ethernet/marvell/octeontx2/nic/otx2_common.h   |  3 +-
 .../net/ethernet/marvell/octeontx2/nic/otx2_pf.c   |  7 ++--
 .../net/ethernet/marvell/octeontx2/nic/otx2_txrx.c | 30 ++++++++++++---
 .../net/ethernet/marvell/octeontx2/nic/otx2_txrx.h |  4 +-
 7 files changed, 44 insertions(+), 51 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
index 826f691de259..a4a258da8dd5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
@@ -107,12 +107,13 @@ int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura)
 }
 
 #define NPA_MAX_BURST 16
-void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
+int cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
 {
 	struct otx2_nic *pfvf = dev;
+	int cnt = cq->pool_ptrs;
 	u64 ptrs[NPA_MAX_BURST];
-	int num_ptrs = 1;
 	dma_addr_t bufptr;
+	int num_ptrs = 1;
 
 	/* Refill pool with new buffers */
 	while (cq->pool_ptrs) {
@@ -131,6 +132,7 @@ void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
 			num_ptrs = 1;
 		}
 	}
+	return cnt - cq->pool_ptrs;
 }
 
 void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h
index 8ae96815865e..c1861f7de254 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h
@@ -24,7 +24,7 @@ static inline int mtu_to_dwrr_weight(struct otx2_nic *pfvf, int mtu)
 	return weight;
 }
 
-void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq);
+int cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq);
 void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx);
 int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura);
 int cn10k_lmtst_init(struct otx2_nic *pfvf);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 8511906cb4e2..997fedac3a98 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -574,20 +574,8 @@ int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
 int otx2_alloc_buffer(struct otx2_nic *pfvf, struct otx2_cq_queue *cq,
 		      dma_addr_t *dma)
 {
-	if (unlikely(__otx2_alloc_rbuf(pfvf, cq->rbpool, dma))) {
-		struct refill_work *work;
-		struct delayed_work *dwork;
-
-		work = &pfvf->refill_wrk[cq->cq_idx];
-		dwork = &work->pool_refill_work;
-		/* Schedule a task if no other task is running */
-		if (!cq->refill_task_sched) {
-			cq->refill_task_sched = true;
-			schedule_delayed_work(dwork,
-					      msecs_to_jiffies(100));
-		}
+	if (unlikely(__otx2_alloc_rbuf(pfvf, cq->rbpool, dma)))
 		return -ENOMEM;
-	}
 	return 0;
 }
 
@@ -1082,39 +1070,20 @@ static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx)
 static void otx2_pool_refill_task(struct work_struct *work)
 {
 	struct otx2_cq_queue *cq;
-	struct otx2_pool *rbpool;
 	struct refill_work *wrk;
-	int qidx, free_ptrs = 0;
 	struct otx2_nic *pfvf;
-	dma_addr_t bufptr;
+	int qidx;
 
 	wrk = container_of(work, struct refill_work, pool_refill_work.work);
 	pfvf = wrk->pf;
 	qidx = wrk - pfvf->refill_wrk;
 	cq = &pfvf->qset.cq[qidx];
-	rbpool = cq->rbpool;
-	free_ptrs = cq->pool_ptrs;
 
-	while (cq->pool_ptrs) {
-		if (otx2_alloc_rbuf(pfvf, rbpool, &bufptr)) {
-			/* Schedule a WQ if we fails to free atleast half of the
-			 * pointers else enable napi for this RQ.
-			 */
-			if (!((free_ptrs - cq->pool_ptrs) > free_ptrs / 2)) {
-				struct delayed_work *dwork;
-
-				dwork = &wrk->pool_refill_work;
-				schedule_delayed_work(dwork,
-						      msecs_to_jiffies(100));
-			} else {
-				cq->refill_task_sched = false;
-			}
-			return;
-		}
-		pfvf->hw_ops->aura_freeptr(pfvf, qidx, bufptr + OTX2_HEAD_ROOM);
-		cq->pool_ptrs--;
-	}
 	cq->refill_task_sched = false;
+
+	local_bh_disable();
+	napi_schedule(wrk->napi);
+	local_bh_enable();
 }
 
 int otx2_config_nix_queues(struct otx2_nic *pfvf)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index 4c6032ee7800..c04a8ee53a82 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -302,6 +302,7 @@ struct flr_work {
 struct refill_work {
 	struct delayed_work pool_refill_work;
 	struct otx2_nic *pf;
+	struct napi_struct *napi;
 };
 
 /* PTPv2 originTimestamp structure */
@@ -370,7 +371,7 @@ struct dev_hw_ops {
 	int	(*sq_aq_init)(void *dev, u16 qidx, u16 sqb_aura);
 	void	(*sqe_flush)(void *dev, struct otx2_snd_queue *sq,
 			     int size, int qidx);
-	void	(*refill_pool_ptrs)(void *dev, struct otx2_cq_queue *cq);
+	int	(*refill_pool_ptrs)(void *dev, struct otx2_cq_queue *cq);
 	void	(*aura_freeptr)(void *dev, int aura, u64 buf);
 };
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index 70b9065f7d10..6daf4d58c25d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -1943,6 +1943,10 @@ int otx2_stop(struct net_device *netdev)
 
 	netif_tx_disable(netdev);
 
+	for (wrk = 0; wrk < pf->qset.cq_cnt; wrk++)
+		cancel_delayed_work_sync(&pf->refill_wrk[wrk].pool_refill_work);
+	devm_kfree(pf->dev, pf->refill_wrk);
+
 	otx2_free_hw_resources(pf);
 	otx2_free_cints(pf, pf->hw.cint_cnt);
 	otx2_disable_napi(pf);
@@ -1950,9 +1954,6 @@ int otx2_stop(struct net_device *netdev)
 	for (qidx = 0; qidx < netdev->num_tx_queues; qidx++)
 		netdev_tx_reset_queue(netdev_get_tx_queue(netdev, qidx));
 
-	for (wrk = 0; wrk < pf->qset.cq_cnt; wrk++)
-		cancel_delayed_work_sync(&pf->refill_wrk[wrk].pool_refill_work);
-	devm_kfree(pf->dev, pf->refill_wrk);
 
 	kfree(qset->sq);
 	kfree(qset->cq);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index e369baf11530..e77d43848955 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -424,9 +424,10 @@ process_cqe:
 	return processed_cqe;
 }
 
-void otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
+int otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
 {
 	struct otx2_nic *pfvf = dev;
+	int cnt = cq->pool_ptrs;
 	dma_addr_t bufptr;
 
 	while (cq->pool_ptrs) {
@@ -435,6 +436,8 @@ void otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
 		otx2_aura_freeptr(pfvf, cq->cq_idx, bufptr + OTX2_HEAD_ROOM);
 		cq->pool_ptrs--;
 	}
+
+	return cnt - cq->pool_ptrs;
 }
 
 static int otx2_tx_napi_handler(struct otx2_nic *pfvf,
@@ -521,6 +524,7 @@ int otx2_napi_handler(struct napi_struct *napi, int budget)
 	struct otx2_cq_queue *cq;
 	struct otx2_qset *qset;
 	struct otx2_nic *pfvf;
+	int filled_cnt = -1;
 
 	cq_poll = container_of(napi, struct otx2_cq_poll, napi);
 	pfvf = (struct otx2_nic *)cq_poll->dev;
@@ -541,7 +545,7 @@ int otx2_napi_handler(struct napi_struct *napi, int budget)
 	}
 
 	if (rx_cq && rx_cq->pool_ptrs)
-		pfvf->hw_ops->refill_pool_ptrs(pfvf, rx_cq);
+		filled_cnt = pfvf->hw_ops->refill_pool_ptrs(pfvf, rx_cq);
 	/* Clear the IRQ */
 	otx2_write64(pfvf, NIX_LF_CINTX_INT(cq_poll->cint_idx), BIT_ULL(0));
 
@@ -561,9 +565,25 @@ int otx2_napi_handler(struct napi_struct *napi, int budget)
 				otx2_config_irq_coalescing(pfvf, i);
 		}
 
-		/* Re-enable interrupts */
-		otx2_write64(pfvf, NIX_LF_CINTX_ENA_W1S(cq_poll->cint_idx),
-			     BIT_ULL(0));
+		if (unlikely(!filled_cnt)) {
+			struct refill_work *work;
+			struct delayed_work *dwork;
+
+			work = &pfvf->refill_wrk[cq->cq_idx];
+			dwork = &work->pool_refill_work;
+			/* Schedule a task if no other task is running */
+			if (!cq->refill_task_sched) {
+				work->napi = napi;
+				cq->refill_task_sched = true;
+				schedule_delayed_work(dwork,
+						      msecs_to_jiffies(100));
+			}
+		} else {
+			/* Re-enable interrupts */
+			otx2_write64(pfvf,
+				     NIX_LF_CINTX_ENA_W1S(cq_poll->cint_idx),
+				     BIT_ULL(0));
+		}
 	}
 	return workdone;
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
index 9e3bfbe5c480..a82ffca8ce1b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
@@ -170,6 +170,6 @@ void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq,
 		     int size, int qidx);
 void otx2_sqe_flush(void *dev, struct otx2_snd_queue *sq,
 		    int size, int qidx);
-void otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq);
-void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq);
+int otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq);
+int cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq);
 #endif /* OTX2_TXRX_H */
-- 
cgit v1.2.3


From 6912e724832c47bb381eb1bd1e483ec8df0d0f0f Mon Sep 17 00:00:00 2001
From: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Date: Fri, 8 Sep 2023 11:31:42 +0800
Subject: net/smc: bugfix for smcr v2 server connect success statistic

In the macro SMC_STAT_SERV_SUCC_INC, the smcd_version is used
to determin whether to increase the v1 statistic or the v2
statistic. It is correct for SMCD. But for SMCR, smcr_version
should be used.

Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_stats.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h
index b60fe1eb37ab..aa8928975cc6 100644
--- a/net/smc/smc_stats.h
+++ b/net/smc/smc_stats.h
@@ -243,8 +243,9 @@ while (0)
 #define SMC_STAT_SERV_SUCC_INC(net, _ini) \
 do { \
 	typeof(_ini) i = (_ini); \
-	bool is_v2 = (i->smcd_version & SMC_V2); \
 	bool is_smcd = (i->is_smcd); \
+	u8 version = is_smcd ? i->smcd_version : i->smcr_version; \
+	bool is_v2 = (version & SMC_V2); \
 	typeof(net->smc.smc_stats) smc_stats = (net)->smc.smc_stats; \
 	if (is_v2 && is_smcd) \
 		this_cpu_inc(smc_stats->smc[SMC_TYPE_D].srv_v2_succ_cnt); \
-- 
cgit v1.2.3


From f5146e3ef0a9eea405874b36178c19a4863b8989 Mon Sep 17 00:00:00 2001
From: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Date: Fri, 8 Sep 2023 11:31:43 +0800
Subject: net/smc: use smc_lgr_list.lock to protect smc_lgr_list.list iterate
 in smcr_port_add

While doing smcr_port_add, there maybe linkgroup add into or delete
from smc_lgr_list.list at the same time, which may result kernel crash.
So, use smc_lgr_list.lock to protect smc_lgr_list.list iterate in
smcr_port_add.

The crash calltrace show below:
BUG: kernel NULL pointer dereference, address: 0000000000000000
PGD 0 P4D 0
Oops: 0000 [#1] SMP NOPTI
CPU: 0 PID: 559726 Comm: kworker/0:92 Kdump: loaded Tainted: G
Hardware name: Alibaba Cloud Alibaba Cloud ECS, BIOS 449e491 04/01/2014
Workqueue: events smc_ib_port_event_work [smc]
RIP: 0010:smcr_port_add+0xa6/0xf0 [smc]
RSP: 0000:ffffa5a2c8f67de0 EFLAGS: 00010297
RAX: 0000000000000001 RBX: ffff9935e0650000 RCX: 0000000000000000
RDX: 0000000000000010 RSI: ffff9935e0654290 RDI: ffff9935c8560000
RBP: 0000000000000000 R08: 0000000000000000 R09: ffff9934c0401918
R10: 0000000000000000 R11: ffffffffb4a5c278 R12: ffff99364029aae4
R13: ffff99364029aa00 R14: 00000000ffffffed R15: ffff99364029ab08
FS:  0000000000000000(0000) GS:ffff994380600000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000000 CR3: 0000000f06a10003 CR4: 0000000002770ef0
PKRU: 55555554
Call Trace:
 smc_ib_port_event_work+0x18f/0x380 [smc]
 process_one_work+0x19b/0x340
 worker_thread+0x30/0x370
 ? process_one_work+0x340/0x340
 kthread+0x114/0x130
 ? __kthread_cancel_work+0x50/0x50
 ret_from_fork+0x1f/0x30

Fixes: 1f90a05d9ff9 ("net/smc: add smcr_port_add() and smcr_link_up() processing")
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index bd01dd31e4bd..d520ee62c8ec 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1662,6 +1662,7 @@ void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport)
 {
 	struct smc_link_group *lgr, *n;
 
+	spin_lock_bh(&smc_lgr_list.lock);
 	list_for_each_entry_safe(lgr, n, &smc_lgr_list.list, list) {
 		struct smc_link *link;
 
@@ -1680,6 +1681,7 @@ void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport)
 		if (link)
 			smc_llc_add_link_local(link);
 	}
+	spin_unlock_bh(&smc_lgr_list.lock);
 }
 
 /* link is down - switch connections to alternate link,
-- 
cgit v1.2.3


From fa60b8163816f194786f3ee334c9a458da7699c6 Mon Sep 17 00:00:00 2001
From: Vincent Whitchurch <vincent.whitchurch@axis.com>
Date: Thu, 7 Sep 2023 12:46:31 +0200
Subject: net: stmmac: fix handling of zero coalescing tx-usecs

Setting ethtool -C eth0 tx-usecs 0 is supposed to disable the use of the
coalescing timer but currently it gets programmed with zero delay
instead.

Disable the use of the coalescing timer if tx-usecs is zero by
preventing it from being restarted.  Note that to keep things simple we
don't start/stop the timer when the coalescing settings are changed, but
just let that happen on the next transmit or timer expiry.

Fixes: 8fce33317023 ("net: stmmac: Rework coalesce timer and fix multi-queue races")
Signed-off-by: Vincent Whitchurch <vincent.whitchurch@axis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 9a3182b9e767..2206789802bf 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2704,9 +2704,7 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue)
 
 	/* We still have pending packets, let's call for a new scheduling */
 	if (tx_q->dirty_tx != tx_q->cur_tx)
-		hrtimer_start(&tx_q->txtimer,
-			      STMMAC_COAL_TIMER(priv->tx_coal_timer[queue]),
-			      HRTIMER_MODE_REL);
+		stmmac_tx_timer_arm(priv, queue);
 
 	flags = u64_stats_update_begin_irqsave(&tx_q->txq_stats.syncp);
 	tx_q->txq_stats.tx_packets += tx_packets;
@@ -2995,9 +2993,13 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 static void stmmac_tx_timer_arm(struct stmmac_priv *priv, u32 queue)
 {
 	struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue];
+	u32 tx_coal_timer = priv->tx_coal_timer[queue];
+
+	if (!tx_coal_timer)
+		return;
 
 	hrtimer_start(&tx_q->txtimer,
-		      STMMAC_COAL_TIMER(priv->tx_coal_timer[queue]),
+		      STMMAC_COAL_TIMER(tx_coal_timer),
 		      HRTIMER_MODE_REL);
 }
 
-- 
cgit v1.2.3


From 9b90aca97f6d5255ca41e716720d138b878cd034 Mon Sep 17 00:00:00 2001
From: Hangyu Hua <hbh25y@gmail.com>
Date: Fri, 8 Sep 2023 14:19:48 +0800
Subject: net: ethernet: bcmasp: fix possible OOB write in
 bcmasp_netfilt_get_all_active()

rule_locs is allocated in ethtool_get_rxnfc and the size is determined by
rule_cnt from user space. So rule_cnt needs to be check before using
rule_locs to avoid OOB writing or NULL pointer dereference.

Fixes: c5d511c49587 ("net: bcmasp: Add support for wake on net filters")
Signed-off-by: Hangyu Hua <hbh25y@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/asp2/bcmasp.c         | 9 +++++++--
 drivers/net/ethernet/broadcom/asp2/bcmasp.h         | 4 ++--
 drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c | 2 +-
 3 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
index f048e3d45119..41a6098eb0c2 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
@@ -528,13 +528,16 @@ void bcmasp_netfilt_suspend(struct bcmasp_intf *intf)
 				  ASP_RX_FILTER_BLK_CTRL);
 }
 
-void bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs,
-				   u32 *rule_cnt)
+int bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs,
+				  u32 *rule_cnt)
 {
 	struct bcmasp_priv *priv = intf->parent;
 	int j = 0, i;
 
 	for (i = 0; i < NUM_NET_FILTERS; i++) {
+		if (j == *rule_cnt)
+			return -EMSGSIZE;
+
 		if (!priv->net_filters[i].claimed ||
 		    priv->net_filters[i].port != intf->port)
 			continue;
@@ -548,6 +551,8 @@ void bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs,
 	}
 
 	*rule_cnt = j;
+
+	return 0;
 }
 
 int bcmasp_netfilt_get_active(struct bcmasp_intf *intf)
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.h b/drivers/net/ethernet/broadcom/asp2/bcmasp.h
index 5b512f7f5e94..ec90add6b03e 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.h
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.h
@@ -577,8 +577,8 @@ void bcmasp_netfilt_release(struct bcmasp_intf *intf,
 
 int bcmasp_netfilt_get_active(struct bcmasp_intf *intf);
 
-void bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs,
-				   u32 *rule_cnt);
+int bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs,
+				  u32 *rule_cnt);
 
 void bcmasp_netfilt_suspend(struct bcmasp_intf *intf);
 
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
index c4f1604d5ab3..ce6a3d56fb23 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
@@ -335,7 +335,7 @@ static int bcmasp_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 		err = bcmasp_flow_get(intf, cmd);
 		break;
 	case ETHTOOL_GRXCLSRLALL:
-		bcmasp_netfilt_get_all_active(intf, rule_locs, &cmd->rule_cnt);
+		err = bcmasp_netfilt_get_all_active(intf, rule_locs, &cmd->rule_cnt);
 		cmd->data = NUM_NET_FILTERS;
 		break;
 	default:
-- 
cgit v1.2.3


From 51fe0a470543f345e3c62b6798929de3ddcedc1d Mon Sep 17 00:00:00 2001
From: Hangyu Hua <hbh25y@gmail.com>
Date: Fri, 8 Sep 2023 14:19:49 +0800
Subject: net: ethernet: mvpp2_main: fix possible OOB write in
 mvpp2_ethtool_get_rxnfc()

rules is allocated in ethtool_get_rxnfc and the size is determined by
rule_cnt from user space. So rule_cnt needs to be check before using
rules to avoid OOB writing or NULL pointer dereference.

Fixes: 90b509b39ac9 ("net: mvpp2: cls: Add Classification offload support")
Signed-off-by: Hangyu Hua <hbh25y@gmail.com>
Reviewed-by: Marcin Wojtas <mw@semihalf.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index eb74ccddb440..21c3f9b015c8 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -5586,6 +5586,11 @@ static int mvpp2_ethtool_get_rxnfc(struct net_device *dev,
 		break;
 	case ETHTOOL_GRXCLSRLALL:
 		for (i = 0; i < MVPP2_N_RFS_ENTRIES_PER_FLOW; i++) {
+			if (loc == info->rule_cnt) {
+				ret = -EMSGSIZE;
+				break;
+			}
+
 			if (port->rfs_rules[i])
 				rules[loc++] = i;
 		}
-- 
cgit v1.2.3


From e4c79810755f66c9a933ca810da2724133b1165a Mon Sep 17 00:00:00 2001
From: Hangyu Hua <hbh25y@gmail.com>
Date: Fri, 8 Sep 2023 14:19:50 +0800
Subject: net: ethernet: mtk_eth_soc: fix possible NULL pointer dereference in
 mtk_hwlro_get_fdir_all()

rule_locs is allocated in ethtool_get_rxnfc and the size is determined by
rule_cnt from user space. So rule_cnt needs to be check before using
rule_locs to avoid NULL pointer dereference.

Fixes: 7aab747e5563 ("net: ethernet: mediatek: add ethtool functions to configure RX flows of HW LRO")
Signed-off-by: Hangyu Hua <hbh25y@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 6ad42e3b488f..2372ce8c2580 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -2994,6 +2994,9 @@ static int mtk_hwlro_get_fdir_all(struct net_device *dev,
 	int i;
 
 	for (i = 0; i < MTK_MAX_LRO_IP_CNT; i++) {
+		if (cnt == cmd->rule_cnt)
+			return -EMSGSIZE;
+
 		if (mac->hwlro_ip[i]) {
 			rule_locs[cnt] = i;
 			cnt++;
-- 
cgit v1.2.3


From 484b4833c604c0adcf19eac1ca14b60b757355b5 Mon Sep 17 00:00:00 2001
From: Ziyang Xuan <william.xuanziyang@huawei.com>
Date: Fri, 8 Sep 2023 18:17:52 +0800
Subject: hsr: Fix uninit-value access in fill_frame_info()

Syzbot reports the following uninit-value access problem.

=====================================================
BUG: KMSAN: uninit-value in fill_frame_info net/hsr/hsr_forward.c:601 [inline]
BUG: KMSAN: uninit-value in hsr_forward_skb+0x9bd/0x30f0 net/hsr/hsr_forward.c:616
 fill_frame_info net/hsr/hsr_forward.c:601 [inline]
 hsr_forward_skb+0x9bd/0x30f0 net/hsr/hsr_forward.c:616
 hsr_dev_xmit+0x192/0x330 net/hsr/hsr_device.c:223
 __netdev_start_xmit include/linux/netdevice.h:4889 [inline]
 netdev_start_xmit include/linux/netdevice.h:4903 [inline]
 xmit_one net/core/dev.c:3544 [inline]
 dev_hard_start_xmit+0x247/0xa10 net/core/dev.c:3560
 __dev_queue_xmit+0x34d0/0x52a0 net/core/dev.c:4340
 dev_queue_xmit include/linux/netdevice.h:3082 [inline]
 packet_xmit+0x9c/0x6b0 net/packet/af_packet.c:276
 packet_snd net/packet/af_packet.c:3087 [inline]
 packet_sendmsg+0x8b1d/0x9f30 net/packet/af_packet.c:3119
 sock_sendmsg_nosec net/socket.c:730 [inline]
 sock_sendmsg net/socket.c:753 [inline]
 __sys_sendto+0x781/0xa30 net/socket.c:2176
 __do_sys_sendto net/socket.c:2188 [inline]
 __se_sys_sendto net/socket.c:2184 [inline]
 __ia32_sys_sendto+0x11f/0x1c0 net/socket.c:2184
 do_syscall_32_irqs_on arch/x86/entry/common.c:112 [inline]
 __do_fast_syscall_32+0xa2/0x100 arch/x86/entry/common.c:178
 do_fast_syscall_32+0x37/0x80 arch/x86/entry/common.c:203
 do_SYSENTER_32+0x1f/0x30 arch/x86/entry/common.c:246
 entry_SYSENTER_compat_after_hwframe+0x70/0x82

Uninit was created at:
 slab_post_alloc_hook+0x12f/0xb70 mm/slab.h:767
 slab_alloc_node mm/slub.c:3478 [inline]
 kmem_cache_alloc_node+0x577/0xa80 mm/slub.c:3523
 kmalloc_reserve+0x148/0x470 net/core/skbuff.c:559
 __alloc_skb+0x318/0x740 net/core/skbuff.c:644
 alloc_skb include/linux/skbuff.h:1286 [inline]
 alloc_skb_with_frags+0xc8/0xbd0 net/core/skbuff.c:6299
 sock_alloc_send_pskb+0xa80/0xbf0 net/core/sock.c:2794
 packet_alloc_skb net/packet/af_packet.c:2936 [inline]
 packet_snd net/packet/af_packet.c:3030 [inline]
 packet_sendmsg+0x70e8/0x9f30 net/packet/af_packet.c:3119
 sock_sendmsg_nosec net/socket.c:730 [inline]
 sock_sendmsg net/socket.c:753 [inline]
 __sys_sendto+0x781/0xa30 net/socket.c:2176
 __do_sys_sendto net/socket.c:2188 [inline]
 __se_sys_sendto net/socket.c:2184 [inline]
 __ia32_sys_sendto+0x11f/0x1c0 net/socket.c:2184
 do_syscall_32_irqs_on arch/x86/entry/common.c:112 [inline]
 __do_fast_syscall_32+0xa2/0x100 arch/x86/entry/common.c:178
 do_fast_syscall_32+0x37/0x80 arch/x86/entry/common.c:203
 do_SYSENTER_32+0x1f/0x30 arch/x86/entry/common.c:246
 entry_SYSENTER_compat_after_hwframe+0x70/0x82

It is because VLAN not yet supported in hsr driver. Return error
when protocol is ETH_P_8021Q in fill_frame_info() now to fix it.

Fixes: 451d8123f897 ("net: prp: add packet handling support")
Reported-by: syzbot+bf7e6250c7ce248f3ec9@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=bf7e6250c7ce248f3ec9
Signed-off-by: Ziyang Xuan <william.xuanziyang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_forward.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c
index 629daacc9607..b71dab630a87 100644
--- a/net/hsr/hsr_forward.c
+++ b/net/hsr/hsr_forward.c
@@ -594,6 +594,7 @@ static int fill_frame_info(struct hsr_frame_info *frame,
 		proto = vlan_hdr->vlanhdr.h_vlan_encapsulated_proto;
 		/* FIXME: */
 		netdev_warn_once(skb->dev, "VLAN not yet supported");
+		return -EINVAL;
 	}
 
 	frame->is_from_san = false;
-- 
cgit v1.2.3


From 32530dba1bd48da4437d18d9a8dbc9d2826938a6 Mon Sep 17 00:00:00 2001
From: Ciprian Regus <ciprian.regus@analog.com>
Date: Fri, 8 Sep 2023 15:58:08 +0300
Subject: net:ethernet:adi:adin1110: Fix forwarding offload

Currently, when a new fdb entry is added (with both ports of the
ADIN2111 bridged), the driver configures the MAC filters for the wrong
port, which results in the forwarding being done by the host, and not
actually hardware offloaded.

The ADIN2111 offloads the forwarding by setting filters on the
destination MAC address of incoming frames. Based on these, they may be
routed to the other port. Thus, if a frame has to be forwarded from port
1 to port 2, the required configuration for the ADDR_FILT_UPRn register
should set the APPLY2PORT1 bit (instead of APPLY2PORT2, as it's
currently the case).

Fixes: bc93e19d088b ("net: ethernet: adi: Add ADIN1110 support")
Signed-off-by: Ciprian Regus <ciprian.regus@analog.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/adi/adin1110.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c
index 1c009b485188..ca66b747b7c5 100644
--- a/drivers/net/ethernet/adi/adin1110.c
+++ b/drivers/net/ethernet/adi/adin1110.c
@@ -1385,7 +1385,7 @@ static int adin1110_fdb_add(struct adin1110_port_priv *port_priv,
 		return -ENOMEM;
 
 	other_port = priv->ports[!port_priv->nr];
-	port_rules = adin1110_port_rules(port_priv, false, true);
+	port_rules = adin1110_port_rules(other_port, false, true);
 	eth_broadcast_addr(mask);
 
 	return adin1110_write_mac_address(other_port, mac_nr, (u8 *)fdb->addr,
-- 
cgit v1.2.3


From 02c652f5465011126152bbd93b6a582a1d0c32f1 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Fri, 8 Sep 2023 16:33:48 +0300
Subject: net: dsa: sja1105: hide all multicast addresses from "bridge fdb
 show"

Commit 4d9423549501 ("net: dsa: sja1105: offload bridge port flags to
device") has partially hidden some multicast entries from showing up in
the "bridge fdb show" output, but it wasn't enough. Addresses which are
added through "bridge mdb add" still show up. Hide them all.

Fixes: 291d1e72b756 ("net: dsa: sja1105: Add support for FDB and MDB management")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index a23d980d28f5..11c917d5ce43 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -1868,13 +1868,14 @@ static int sja1105_fdb_dump(struct dsa_switch *ds, int port,
 		if (!(l2_lookup.destports & BIT(port)))
 			continue;
 
-		/* We need to hide the FDB entry for unknown multicast */
-		if (l2_lookup.macaddr == SJA1105_UNKNOWN_MULTICAST &&
-		    l2_lookup.mask_macaddr == SJA1105_UNKNOWN_MULTICAST)
-			continue;
-
 		u64_to_ether_addr(l2_lookup.macaddr, macaddr);
 
+		/* Hardware FDB is shared for fdb and mdb, "bridge fdb show"
+		 * only wants to see unicast
+		 */
+		if (is_multicast_ether_addr(macaddr))
+			continue;
+
 		/* We need to hide the dsa_8021q VLANs from the user. */
 		if (vid_is_dsa_8021q(l2_lookup.vlanid))
 			l2_lookup.vlanid = 0;
-- 
cgit v1.2.3


From c956798062b5a308db96e75157747291197f0378 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Fri, 8 Sep 2023 16:33:49 +0300
Subject: net: dsa: sja1105: propagate exact error code from
 sja1105_dynamic_config_poll_valid()

Currently, sja1105_dynamic_config_wait_complete() returns either 0 or
-ETIMEDOUT, because it just looks at the read_poll_timeout() return code.

There will be future changes which move some more checks to
sja1105_dynamic_config_poll_valid(). It is important that we propagate
their exact return code (-ENOENT, -EINVAL), because callers of
sja1105_dynamic_config_read() depend on them.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_dynamic_config.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c
index 7729d3f8b7f5..93d47dab8d3e 100644
--- a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c
+++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c
@@ -1211,13 +1211,14 @@ sja1105_dynamic_config_wait_complete(struct sja1105_private *priv,
 				     struct sja1105_dyn_cmd *cmd,
 				     const struct sja1105_dynamic_table_ops *ops)
 {
-	int rc;
-
-	return read_poll_timeout(sja1105_dynamic_config_poll_valid,
-				 rc, rc != -EAGAIN,
-				 SJA1105_DYNAMIC_CONFIG_SLEEP_US,
-				 SJA1105_DYNAMIC_CONFIG_TIMEOUT_US,
-				 false, priv, cmd, ops);
+	int err, rc;
+
+	err = read_poll_timeout(sja1105_dynamic_config_poll_valid,
+				rc, rc != -EAGAIN,
+				SJA1105_DYNAMIC_CONFIG_SLEEP_US,
+				SJA1105_DYNAMIC_CONFIG_TIMEOUT_US,
+				false, priv, cmd, ops);
+	return err < 0 ? err : rc;
 }
 
 /* Provides read access to the settings through the dynamic interface
-- 
cgit v1.2.3


From 7cef293b9a634a05fcce9e1df4aee3aeed023345 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Fri, 8 Sep 2023 16:33:50 +0300
Subject: net: dsa: sja1105: fix multicast forwarding working only for last
 added mdb entry

The commit cited in Fixes: did 2 things: it refactored the read-back
polling from sja1105_dynamic_config_read() into a new function,
sja1105_dynamic_config_wait_complete(), and it called that from
sja1105_dynamic_config_write() too.

What is problematic is the refactoring.

The refactored code from sja1105_dynamic_config_poll_valid() works like
the previous one, but the problem is that it uses another packed_buf[]
SPI buffer, and there was code at the end of sja1105_dynamic_config_read()
which was relying on the read-back packed_buf[]:

	/* Don't dereference possibly NULL pointer - maybe caller
	 * only wanted to see whether the entry existed or not.
	 */
	if (entry)
		ops->entry_packing(packed_buf, entry, UNPACK);

After the change, the packed_buf[] that this code sees is no longer the
entry read back from hardware, but the original entry that the caller
passed to the sja1105_dynamic_config_read(), packed into this buffer.

This difference is the most notable with the SJA1105_SEARCH uses from
sja1105pqrs_fdb_add() - used for both fdb and mdb. There, we have logic
added by commit 728db843df88 ("net: dsa: sja1105: ignore the FDB entry
for unknown multicast when adding a new address") to figure out whether
the address we're trying to add matches on any existing hardware entry,
with the exception of the catch-all multicast address.

That logic was broken, because with sja1105_dynamic_config_read() not
working properly, it doesn't return us the entry read back from
hardware, but the entry that we passed to it. And, since for multicast,
a match will always exist, it will tell us that any mdb entry already
exists at index=0 L2 Address Lookup table. It is index=0 because the
caller doesn't know the index - it wants to find it out, and
sja1105_dynamic_config_read() does:

	if (index < 0) { // SJA1105_SEARCH
		/* Avoid copying a signed negative number to an u64 */
		cmd.index = 0; // <- this
		cmd.search = true;
	} else {
		cmd.index = index;
		cmd.search = false;
	}

So, to the caller of sja1105_dynamic_config_read(), the returned info
looks entirely legit, and it will add all mdb entries to FDB index 0.
There, they will always overwrite each other (not to mention,
potentially they can also overwrite a pre-existing bridge fdb entry),
and the user-visible impact will be that only the last mdb entry will be
forwarded as it should. The others won't (will be flooded or dropped,
depending on the egress flood settings).

Fixing is a bit more complicated, and involves either passing the same
packed_buf[] to sja1105_dynamic_config_wait_complete(), or moving all
the extra processing on the packed_buf[] to
sja1105_dynamic_config_wait_complete(). I've opted for the latter,
because it makes sja1105_dynamic_config_wait_complete() a bit more
self-contained.

Fixes: df405910ab9f ("net: dsa: sja1105: wait for dynamic config command completion on writes too")
Reported-by: Yanan Yang <yanan.yang@nxp.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_dynamic_config.c | 80 +++++++++++-------------
 1 file changed, 37 insertions(+), 43 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c
index 93d47dab8d3e..984c0e604e8d 100644
--- a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c
+++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c
@@ -1175,18 +1175,15 @@ const struct sja1105_dynamic_table_ops sja1110_dyn_ops[BLK_IDX_MAX_DYN] = {
 
 static int
 sja1105_dynamic_config_poll_valid(struct sja1105_private *priv,
-				  struct sja1105_dyn_cmd *cmd,
-				  const struct sja1105_dynamic_table_ops *ops)
+				  const struct sja1105_dynamic_table_ops *ops,
+				  void *entry, bool check_valident,
+				  bool check_errors)
 {
 	u8 packed_buf[SJA1105_MAX_DYN_CMD_SIZE] = {};
+	struct sja1105_dyn_cmd cmd = {};
 	int rc;
 
-	/* We don't _need_ to read the full entry, just the command area which
-	 * is a fixed SJA1105_SIZE_DYN_CMD. But our cmd_packing() API expects a
-	 * buffer that contains the full entry too. Additionally, our API
-	 * doesn't really know how many bytes into the buffer does the command
-	 * area really begin. So just read back the whole entry.
-	 */
+	/* Read back the whole entry + command structure. */
 	rc = sja1105_xfer_buf(priv, SPI_READ, ops->addr, packed_buf,
 			      ops->packed_size);
 	if (rc)
@@ -1195,11 +1192,25 @@ sja1105_dynamic_config_poll_valid(struct sja1105_private *priv,
 	/* Unpack the command structure, and return it to the caller in case it
 	 * needs to perform further checks on it (VALIDENT).
 	 */
-	memset(cmd, 0, sizeof(*cmd));
-	ops->cmd_packing(packed_buf, cmd, UNPACK);
+	ops->cmd_packing(packed_buf, &cmd, UNPACK);
 
 	/* Hardware hasn't cleared VALID => still working on it */
-	return cmd->valid ? -EAGAIN : 0;
+	if (cmd.valid)
+		return -EAGAIN;
+
+	if (check_valident && !cmd.valident && !(ops->access & OP_VALID_ANYWAY))
+		return -ENOENT;
+
+	if (check_errors && cmd.errors)
+		return -EINVAL;
+
+	/* Don't dereference possibly NULL pointer - maybe caller
+	 * only wanted to see whether the entry existed or not.
+	 */
+	if (entry)
+		ops->entry_packing(packed_buf, entry, UNPACK);
+
+	return 0;
 }
 
 /* Poll the dynamic config entry's control area until the hardware has
@@ -1208,8 +1219,9 @@ sja1105_dynamic_config_poll_valid(struct sja1105_private *priv,
  */
 static int
 sja1105_dynamic_config_wait_complete(struct sja1105_private *priv,
-				     struct sja1105_dyn_cmd *cmd,
-				     const struct sja1105_dynamic_table_ops *ops)
+				     const struct sja1105_dynamic_table_ops *ops,
+				     void *entry, bool check_valident,
+				     bool check_errors)
 {
 	int err, rc;
 
@@ -1217,7 +1229,8 @@ sja1105_dynamic_config_wait_complete(struct sja1105_private *priv,
 				rc, rc != -EAGAIN,
 				SJA1105_DYNAMIC_CONFIG_SLEEP_US,
 				SJA1105_DYNAMIC_CONFIG_TIMEOUT_US,
-				false, priv, cmd, ops);
+				false, priv, ops, entry, check_valident,
+				check_errors);
 	return err < 0 ? err : rc;
 }
 
@@ -1287,25 +1300,14 @@ int sja1105_dynamic_config_read(struct sja1105_private *priv,
 	mutex_lock(&priv->dynamic_config_lock);
 	rc = sja1105_xfer_buf(priv, SPI_WRITE, ops->addr, packed_buf,
 			      ops->packed_size);
-	if (rc < 0) {
-		mutex_unlock(&priv->dynamic_config_lock);
-		return rc;
-	}
-
-	rc = sja1105_dynamic_config_wait_complete(priv, &cmd, ops);
-	mutex_unlock(&priv->dynamic_config_lock);
 	if (rc < 0)
-		return rc;
+		goto out;
 
-	if (!cmd.valident && !(ops->access & OP_VALID_ANYWAY))
-		return -ENOENT;
+	rc = sja1105_dynamic_config_wait_complete(priv, ops, entry, true, false);
+out:
+	mutex_unlock(&priv->dynamic_config_lock);
 
-	/* Don't dereference possibly NULL pointer - maybe caller
-	 * only wanted to see whether the entry existed or not.
-	 */
-	if (entry)
-		ops->entry_packing(packed_buf, entry, UNPACK);
-	return 0;
+	return rc;
 }
 
 int sja1105_dynamic_config_write(struct sja1105_private *priv,
@@ -1357,22 +1359,14 @@ int sja1105_dynamic_config_write(struct sja1105_private *priv,
 	mutex_lock(&priv->dynamic_config_lock);
 	rc = sja1105_xfer_buf(priv, SPI_WRITE, ops->addr, packed_buf,
 			      ops->packed_size);
-	if (rc < 0) {
-		mutex_unlock(&priv->dynamic_config_lock);
-		return rc;
-	}
-
-	rc = sja1105_dynamic_config_wait_complete(priv, &cmd, ops);
-	mutex_unlock(&priv->dynamic_config_lock);
 	if (rc < 0)
-		return rc;
+		goto out;
 
-	cmd = (struct sja1105_dyn_cmd) {0};
-	ops->cmd_packing(packed_buf, &cmd, UNPACK);
-	if (cmd.errors)
-		return -EINVAL;
+	rc = sja1105_dynamic_config_wait_complete(priv, ops, NULL, false, true);
+out:
+	mutex_unlock(&priv->dynamic_config_lock);
 
-	return 0;
+	return rc;
 }
 
 static u8 sja1105_crc8_add(u8 crc, u8 byte, u8 poly)
-- 
cgit v1.2.3


From ea32690daf4fa525dc5a4d164bd00ed8c756e1c6 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Fri, 8 Sep 2023 16:33:51 +0300
Subject: net: dsa: sja1105: serialize sja1105_port_mcast_flood() with other
 FDB accesses

sja1105_fdb_add() runs from the dsa_owq, and sja1105_port_mcast_flood()
runs from switchdev_deferred_process_work(). Prior to the blamed commit,
they used to be indirectly serialized through the rtnl_lock(), which
no longer holds true because dsa_owq dropped that.

So, it is now possible that we traverse the static config BLK_IDX_L2_LOOKUP
elements concurrently compared to when we change them, in
sja1105_static_fdb_change(). That is not ideal, since it might result in
data corruption.

Introduce a mutex which serializes accesses to the hardware FDB and to
the static config elements for the L2 Address Lookup table.

I can't find a good reason to add locking around sja1105_fdb_dump().
I'll add it later if needed.

Fixes: 0faf890fc519 ("net: dsa: drop rtnl_lock from dsa_slave_switchdev_event_work")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105.h      |  2 ++
 drivers/net/dsa/sja1105/sja1105_main.c | 56 ++++++++++++++++++++++++++--------
 2 files changed, 45 insertions(+), 13 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h
index 0617d5ccd3ff..8c66d3bf61f0 100644
--- a/drivers/net/dsa/sja1105/sja1105.h
+++ b/drivers/net/dsa/sja1105/sja1105.h
@@ -266,6 +266,8 @@ struct sja1105_private {
 	 * the switch doesn't confuse them with one another.
 	 */
 	struct mutex mgmt_lock;
+	/* Serializes accesses to the FDB */
+	struct mutex fdb_lock;
 	/* PTP two-step TX timestamp ID, and its serialization lock */
 	spinlock_t ts_id_lock;
 	u8 ts_id;
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 11c917d5ce43..cefd72617af4 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -1798,6 +1798,7 @@ static int sja1105_fdb_add(struct dsa_switch *ds, int port,
 			   struct dsa_db db)
 {
 	struct sja1105_private *priv = ds->priv;
+	int rc;
 
 	if (!vid) {
 		switch (db.type) {
@@ -1812,12 +1813,16 @@ static int sja1105_fdb_add(struct dsa_switch *ds, int port,
 		}
 	}
 
-	return priv->info->fdb_add_cmd(ds, port, addr, vid);
+	mutex_lock(&priv->fdb_lock);
+	rc = priv->info->fdb_add_cmd(ds, port, addr, vid);
+	mutex_unlock(&priv->fdb_lock);
+
+	return rc;
 }
 
-static int sja1105_fdb_del(struct dsa_switch *ds, int port,
-			   const unsigned char *addr, u16 vid,
-			   struct dsa_db db)
+static int __sja1105_fdb_del(struct dsa_switch *ds, int port,
+			     const unsigned char *addr, u16 vid,
+			     struct dsa_db db)
 {
 	struct sja1105_private *priv = ds->priv;
 
@@ -1837,6 +1842,20 @@ static int sja1105_fdb_del(struct dsa_switch *ds, int port,
 	return priv->info->fdb_del_cmd(ds, port, addr, vid);
 }
 
+static int sja1105_fdb_del(struct dsa_switch *ds, int port,
+			   const unsigned char *addr, u16 vid,
+			   struct dsa_db db)
+{
+	struct sja1105_private *priv = ds->priv;
+	int rc;
+
+	mutex_lock(&priv->fdb_lock);
+	rc = __sja1105_fdb_del(ds, port, addr, vid, db);
+	mutex_unlock(&priv->fdb_lock);
+
+	return rc;
+}
+
 static int sja1105_fdb_dump(struct dsa_switch *ds, int port,
 			    dsa_fdb_dump_cb_t *cb, void *data)
 {
@@ -1899,6 +1918,8 @@ static void sja1105_fast_age(struct dsa_switch *ds, int port)
 	};
 	int i;
 
+	mutex_lock(&priv->fdb_lock);
+
 	for (i = 0; i < SJA1105_MAX_L2_LOOKUP_COUNT; i++) {
 		struct sja1105_l2_lookup_entry l2_lookup = {0};
 		u8 macaddr[ETH_ALEN];
@@ -1912,7 +1933,7 @@ static void sja1105_fast_age(struct dsa_switch *ds, int port)
 		if (rc) {
 			dev_err(ds->dev, "Failed to read FDB: %pe\n",
 				ERR_PTR(rc));
-			return;
+			break;
 		}
 
 		if (!(l2_lookup.destports & BIT(port)))
@@ -1924,14 +1945,16 @@ static void sja1105_fast_age(struct dsa_switch *ds, int port)
 
 		u64_to_ether_addr(l2_lookup.macaddr, macaddr);
 
-		rc = sja1105_fdb_del(ds, port, macaddr, l2_lookup.vlanid, db);
+		rc = __sja1105_fdb_del(ds, port, macaddr, l2_lookup.vlanid, db);
 		if (rc) {
 			dev_err(ds->dev,
 				"Failed to delete FDB entry %pM vid %lld: %pe\n",
 				macaddr, l2_lookup.vlanid, ERR_PTR(rc));
-			return;
+			break;
 		}
 	}
+
+	mutex_unlock(&priv->fdb_lock);
 }
 
 static int sja1105_mdb_add(struct dsa_switch *ds, int port,
@@ -2955,7 +2978,9 @@ static int sja1105_port_mcast_flood(struct sja1105_private *priv, int to,
 {
 	struct sja1105_l2_lookup_entry *l2_lookup;
 	struct sja1105_table *table;
-	int match;
+	int match, rc;
+
+	mutex_lock(&priv->fdb_lock);
 
 	table = &priv->static_config.tables[BLK_IDX_L2_LOOKUP];
 	l2_lookup = table->entries;
@@ -2968,7 +2993,8 @@ static int sja1105_port_mcast_flood(struct sja1105_private *priv, int to,
 	if (match == table->entry_count) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Could not find FDB entry for unknown multicast");
-		return -ENOSPC;
+		rc = -ENOSPC;
+		goto out;
 	}
 
 	if (flags.val & BR_MCAST_FLOOD)
@@ -2976,10 +3002,13 @@ static int sja1105_port_mcast_flood(struct sja1105_private *priv, int to,
 	else
 		l2_lookup[match].destports &= ~BIT(to);
 
-	return sja1105_dynamic_config_write(priv, BLK_IDX_L2_LOOKUP,
-					    l2_lookup[match].index,
-					    &l2_lookup[match],
-					    true);
+	rc = sja1105_dynamic_config_write(priv, BLK_IDX_L2_LOOKUP,
+					  l2_lookup[match].index,
+					  &l2_lookup[match], true);
+out:
+	mutex_unlock(&priv->fdb_lock);
+
+	return rc;
 }
 
 static int sja1105_port_pre_bridge_flags(struct dsa_switch *ds, int port,
@@ -3349,6 +3378,7 @@ static int sja1105_probe(struct spi_device *spi)
 	mutex_init(&priv->ptp_data.lock);
 	mutex_init(&priv->dynamic_config_lock);
 	mutex_init(&priv->mgmt_lock);
+	mutex_init(&priv->fdb_lock);
 	spin_lock_init(&priv->ts_id_lock);
 
 	rc = sja1105_parse_dt(priv);
-- 
cgit v1.2.3


From 86899e9e1e29e854b5f6dcc24ba4f75f792c89aa Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Fri, 8 Sep 2023 16:33:52 +0300
Subject: net: dsa: sja1105: block FDB accesses that are concurrent with a
 switch reset

Currently, when we add the first sja1105 port to a bridge with
vlan_filtering 1, then we sometimes see this output:

sja1105 spi2.2: port 4 failed to read back entry for be:79:b4:9e:9e:96 vid 3088: -ENOENT
sja1105 spi2.2: Reset switch and programmed static config. Reason: VLAN filtering
sja1105 spi2.2: port 0 failed to add be:79:b4:9e:9e:96 vid 0 to fdb: -2

It is because sja1105_fdb_add() runs from the dsa_owq which is no longer
serialized with switch resets since it dropped the rtnl_lock() in the
blamed commit.

Either performing the FDB accesses before the reset, or after the reset,
is equally fine, because sja1105_static_fdb_change() backs up those
changes in the static config, but FDB access during reset isn't ok.

Make sja1105_static_config_reload() take the fdb_lock to fix that.

Fixes: 0faf890fc519 ("net: dsa: drop rtnl_lock from dsa_slave_switchdev_event_work")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index cefd72617af4..1a367e64bc3b 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -2297,6 +2297,7 @@ int sja1105_static_config_reload(struct sja1105_private *priv,
 	int rc, i;
 	s64 now;
 
+	mutex_lock(&priv->fdb_lock);
 	mutex_lock(&priv->mgmt_lock);
 
 	mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries;
@@ -2409,6 +2410,7 @@ int sja1105_static_config_reload(struct sja1105_private *priv,
 		goto out;
 out:
 	mutex_unlock(&priv->mgmt_lock);
+	mutex_unlock(&priv->fdb_lock);
 
 	return rc;
 }
-- 
cgit v1.2.3


From a7b8d60b37237680009dd0b025fe8c067aba0ee3 Mon Sep 17 00:00:00 2001
From: Hayes Wang <hayeswang@realtek.com>
Date: Fri, 8 Sep 2023 15:01:52 +0800
Subject: r8152: check budget for r8152_poll()

According to the document of napi, there is no rx process when the
budget is 0. Therefore, r8152_poll() has to return 0 directly when the
budget is equal to 0.

Fixes: d2187f8e4454 ("r8152: divide the tx and rx bottom functions")
Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 332c853ca99b..0c13d9950cd8 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -2636,6 +2636,9 @@ static int r8152_poll(struct napi_struct *napi, int budget)
 	struct r8152 *tp = container_of(napi, struct r8152, napi);
 	int work_done;
 
+	if (!budget)
+		return 0;
+
 	work_done = rx_bottom(tp, budget);
 
 	if (work_done < budget) {
-- 
cgit v1.2.3


From c821a88bd720b0046433173185fd841a100d44ad Mon Sep 17 00:00:00 2001
From: Shigeru Yoshida <syoshida@redhat.com>
Date: Sun, 10 Sep 2023 02:03:10 +0900
Subject: kcm: Fix memory leak in error path of kcm_sendmsg()

syzbot reported a memory leak like below:

BUG: memory leak
unreferenced object 0xffff88810b088c00 (size 240):
  comm "syz-executor186", pid 5012, jiffies 4294943306 (age 13.680s)
  hex dump (first 32 bytes):
    00 89 08 0b 81 88 ff ff 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<ffffffff83e5d5ff>] __alloc_skb+0x1ef/0x230 net/core/skbuff.c:634
    [<ffffffff84606e59>] alloc_skb include/linux/skbuff.h:1289 [inline]
    [<ffffffff84606e59>] kcm_sendmsg+0x269/0x1050 net/kcm/kcmsock.c:815
    [<ffffffff83e479c6>] sock_sendmsg_nosec net/socket.c:725 [inline]
    [<ffffffff83e479c6>] sock_sendmsg+0x56/0xb0 net/socket.c:748
    [<ffffffff83e47f55>] ____sys_sendmsg+0x365/0x470 net/socket.c:2494
    [<ffffffff83e4c389>] ___sys_sendmsg+0xc9/0x130 net/socket.c:2548
    [<ffffffff83e4c536>] __sys_sendmsg+0xa6/0x120 net/socket.c:2577
    [<ffffffff84ad7bb8>] do_syscall_x64 arch/x86/entry/common.c:50 [inline]
    [<ffffffff84ad7bb8>] do_syscall_64+0x38/0xb0 arch/x86/entry/common.c:80
    [<ffffffff84c0008b>] entry_SYSCALL_64_after_hwframe+0x63/0xcd

In kcm_sendmsg(), kcm_tx_msg(head)->last_skb is used as a cursor to append
newly allocated skbs to 'head'. If some bytes are copied, an error occurred,
and jumped to out_error label, 'last_skb' is left unmodified. A later
kcm_sendmsg() will use an obsoleted 'last_skb' reference, corrupting the
'head' frag_list and causing the leak.

This patch fixes this issue by properly updating the last allocated skb in
'last_skb'.

Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module")
Reported-and-tested-by: syzbot+6f98de741f7dbbfc4ccb@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=6f98de741f7dbbfc4ccb
Signed-off-by: Shigeru Yoshida <syoshida@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/kcm/kcmsock.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 4580f61426bb..740539a218b7 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -939,6 +939,8 @@ out_error:
 
 	if (head != kcm->seq_skb)
 		kfree_skb(head);
+	else if (copied)
+		kcm_tx_msg(head)->last_skb = skb;
 
 	err = sk_stream_error(sk, msg->msg_flags, err);
 
-- 
cgit v1.2.3


From e10a35abb3da12b812cfb6fc6137926a0c81e39a Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Sun, 10 Sep 2023 22:40:30 +0100
Subject: net: ethernet: mtk_eth_soc: fix uninitialized variable

Variable dma_addr in function mtk_poll_rx can be uninitialized on
some of the error paths. In practise this doesn't matter, even random
data present in uninitialized stack memory can safely be used in the
way it happens in the error path.

However, in order to make Smatch happy make sure the variable is
always initialized.

Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 2372ce8c2580..3cffd1bd3067 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -2005,11 +2005,11 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 	u8 *data, *new_data;
 	struct mtk_rx_dma_v2 *rxd, trxd;
 	int done = 0, bytes = 0;
+	dma_addr_t dma_addr = DMA_MAPPING_ERROR;
 
 	while (done < budget) {
 		unsigned int pktlen, *rxdcsum;
 		struct net_device *netdev;
-		dma_addr_t dma_addr;
 		u32 hash, reason;
 		int mac = 0;
 
@@ -2186,7 +2186,8 @@ release_desc:
 		else
 			rxd->rxd2 = RX_DMA_PREP_PLEN0(ring->buf_size);
 
-		if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA))
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA) &&
+		    likely(dma_addr != DMA_MAPPING_ERROR))
 			rxd->rxd2 |= RX_DMA_PREP_ADDR64(dma_addr);
 
 		ring->calc_idx = idx;
-- 
cgit v1.2.3


From 5a124b1fd3e6cb15a943f0cdfe96aa8f6d3d2f39 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Sat, 9 Sep 2023 20:41:56 +0200
Subject: net: ethernet: mtk_eth_soc: fix pse_port configuration for MT7988

MT7988 SoC support 3 NICs. Fix pse_port configuration in
mtk_flow_set_output_device routine if the traffic is offloaded to eth2.
Rely on mtk_pse_port definitions.

Fixes: 88efedf517e6 ("net: ethernet: mtk_eth_soc: enable nft hw flowtable_offload for MT7988 SoC")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_ppe_offload.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
index a70a5417c173..a4efbeb16208 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
+++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
@@ -214,9 +214,11 @@ mtk_flow_set_output_device(struct mtk_eth *eth, struct mtk_foe_entry *foe,
 	dsa_port = mtk_flow_get_dsa_port(&dev);
 
 	if (dev == eth->netdev[0])
-		pse_port = 1;
+		pse_port = PSE_GDM1_PORT;
 	else if (dev == eth->netdev[1])
-		pse_port = 2;
+		pse_port = PSE_GDM2_PORT;
+	else if (dev == eth->netdev[2])
+		pse_port = PSE_GDM3_PORT;
 	else
 		return -EOPNOTSUPP;
 
-- 
cgit v1.2.3


From 5ca636d927a106780451d957734f02589b972e2b Mon Sep 17 00:00:00 2001
From: Andrii Staikov <andrii.staikov@intel.com>
Date: Fri, 8 Sep 2023 14:42:01 +0200
Subject: i40e: fix potential memory leaks in i40e_remove()

Instead of freeing memory of a single VSI, make sure
the memory for all VSIs is cleared before releasing VSIs.
Add releasing of their resources in a loop with the iteration
number equal to the number of allocated VSIs.

Fixes: 41c445ff0f48 ("i40e: main driver core")
Signed-off-by: Andrii Staikov <andrii.staikov@intel.com>
Signed-off-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index de7fd43dc11c..00ca2b88165c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -16320,11 +16320,15 @@ static void i40e_remove(struct pci_dev *pdev)
 			i40e_switch_branch_release(pf->veb[i]);
 	}
 
-	/* Now we can shutdown the PF's VSI, just before we kill
+	/* Now we can shutdown the PF's VSIs, just before we kill
 	 * adminq and hmc.
 	 */
-	if (pf->vsi[pf->lan_vsi])
-		i40e_vsi_release(pf->vsi[pf->lan_vsi]);
+	for (i = pf->num_alloc_vsi; i--;)
+		if (pf->vsi[i]) {
+			i40e_vsi_close(pf->vsi[i]);
+			i40e_vsi_release(pf->vsi[i]);
+			pf->vsi[i] = NULL;
+		}
 
 	i40e_cloud_filter_exit(pf);
 
-- 
cgit v1.2.3


From 221465de6bd8090ab61267f019866e8d2dd4ea3d Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Mon, 21 Aug 2023 17:01:44 -0600
Subject: iavf: Fix promiscuous mode configuration flow messages

Currently when configuring promiscuous mode on the AVF we detect a
change in the netdev->flags. We use IFF_PROMISC and IFF_ALLMULTI to
determine whether or not we need to request/release promiscuous mode
and/or multicast promiscuous mode. The problem is that the AQ calls for
setting/clearing promiscuous/multicast mode are treated separately. This
leads to a case where we can trigger two promiscuous mode AQ calls in
a row with the incorrect state. To fix this make a few changes.

Use IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE instead of the previous
IAVF_FLAG_AQ_[REQUEST|RELEASE]_[PROMISC|ALLMULTI] flags.

In iavf_set_rx_mode() detect if there is a change in the
netdev->flags in comparison with adapter->flags and set the
IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE aq_required bit. Then in
iavf_process_aq_command() only check for IAVF_FLAG_CONFIGURE_PROMISC_MODE
and call iavf_set_promiscuous() if it's set.

In iavf_set_promiscuous() check again to see which (if any) promiscuous
mode bits have changed when comparing the netdev->flags with the
adapter->flags. Use this to set the flags which get sent to the PF
driver.

Add a spinlock that is used for updating current_netdev_promisc_flags
and only allows one promiscuous mode AQ at a time.

[1] Fixes the fact that we will only have one AQ call in the aq_required
queue at any one time.

[2] Streamlines the change in promiscuous mode to only set one AQ
required bit.

[3] This allows us to keep track of the current state of the flags and
also makes it so we can take the most recent netdev->flags promiscuous
mode state.

[4] This fixes the problem where a change in the netdev->flags can cause
IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE to be set in iavf_set_rx_mode(),
but cleared in iavf_set_promiscuous() before the change is ever made via
AQ call.

Fixes: 47d3483988f6 ("i40evf: Add driver support for promiscuous mode")
Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf.h          | 16 +++---
 drivers/net/ethernet/intel/iavf/iavf_main.c     | 43 ++++++--------
 drivers/net/ethernet/intel/iavf/iavf_virtchnl.c | 75 ++++++++++++++++---------
 3 files changed, 74 insertions(+), 60 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index 85fba85fbb23..738e25657c6b 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -298,8 +298,6 @@ struct iavf_adapter {
 #define IAVF_FLAG_CLIENT_NEEDS_OPEN		BIT(10)
 #define IAVF_FLAG_CLIENT_NEEDS_CLOSE		BIT(11)
 #define IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS	BIT(12)
-#define IAVF_FLAG_PROMISC_ON			BIT(13)
-#define IAVF_FLAG_ALLMULTI_ON			BIT(14)
 #define IAVF_FLAG_LEGACY_RX			BIT(15)
 #define IAVF_FLAG_REINIT_ITR_NEEDED		BIT(16)
 #define IAVF_FLAG_QUEUES_DISABLED		BIT(17)
@@ -325,10 +323,7 @@ struct iavf_adapter {
 #define IAVF_FLAG_AQ_SET_HENA			BIT_ULL(12)
 #define IAVF_FLAG_AQ_SET_RSS_KEY		BIT_ULL(13)
 #define IAVF_FLAG_AQ_SET_RSS_LUT		BIT_ULL(14)
-#define IAVF_FLAG_AQ_REQUEST_PROMISC		BIT_ULL(15)
-#define IAVF_FLAG_AQ_RELEASE_PROMISC		BIT_ULL(16)
-#define IAVF_FLAG_AQ_REQUEST_ALLMULTI		BIT_ULL(17)
-#define IAVF_FLAG_AQ_RELEASE_ALLMULTI		BIT_ULL(18)
+#define IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE	BIT_ULL(15)
 #define IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING	BIT_ULL(19)
 #define IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING	BIT_ULL(20)
 #define IAVF_FLAG_AQ_ENABLE_CHANNELS		BIT_ULL(21)
@@ -365,6 +360,12 @@ struct iavf_adapter {
 	(IAVF_EXTENDED_CAP_SEND_VLAN_V2 |		\
 	 IAVF_EXTENDED_CAP_RECV_VLAN_V2)
 
+	/* Lock to prevent possible clobbering of
+	 * current_netdev_promisc_flags
+	 */
+	spinlock_t current_netdev_promisc_flags_lock;
+	netdev_features_t current_netdev_promisc_flags;
+
 	/* OS defined structs */
 	struct net_device *netdev;
 	struct pci_dev *pdev;
@@ -551,7 +552,8 @@ void iavf_add_ether_addrs(struct iavf_adapter *adapter);
 void iavf_del_ether_addrs(struct iavf_adapter *adapter);
 void iavf_add_vlans(struct iavf_adapter *adapter);
 void iavf_del_vlans(struct iavf_adapter *adapter);
-void iavf_set_promiscuous(struct iavf_adapter *adapter, int flags);
+void iavf_set_promiscuous(struct iavf_adapter *adapter);
+bool iavf_promiscuous_mode_changed(struct iavf_adapter *adapter);
 void iavf_request_stats(struct iavf_adapter *adapter);
 int iavf_request_reset(struct iavf_adapter *adapter);
 void iavf_get_hena(struct iavf_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 7b300c86ceda..36b94ee44211 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -1188,6 +1188,16 @@ static int iavf_addr_unsync(struct net_device *netdev, const u8 *addr)
 	return 0;
 }
 
+/**
+ * iavf_promiscuous_mode_changed - check if promiscuous mode bits changed
+ * @adapter: device specific adapter
+ */
+bool iavf_promiscuous_mode_changed(struct iavf_adapter *adapter)
+{
+	return (adapter->current_netdev_promisc_flags ^ adapter->netdev->flags) &
+		(IFF_PROMISC | IFF_ALLMULTI);
+}
+
 /**
  * iavf_set_rx_mode - NDO callback to set the netdev filters
  * @netdev: network interface device structure
@@ -1201,19 +1211,10 @@ static void iavf_set_rx_mode(struct net_device *netdev)
 	__dev_mc_sync(netdev, iavf_addr_sync, iavf_addr_unsync);
 	spin_unlock_bh(&adapter->mac_vlan_list_lock);
 
-	if (netdev->flags & IFF_PROMISC &&
-	    !(adapter->flags & IAVF_FLAG_PROMISC_ON))
-		adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_PROMISC;
-	else if (!(netdev->flags & IFF_PROMISC) &&
-		 adapter->flags & IAVF_FLAG_PROMISC_ON)
-		adapter->aq_required |= IAVF_FLAG_AQ_RELEASE_PROMISC;
-
-	if (netdev->flags & IFF_ALLMULTI &&
-	    !(adapter->flags & IAVF_FLAG_ALLMULTI_ON))
-		adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_ALLMULTI;
-	else if (!(netdev->flags & IFF_ALLMULTI) &&
-		 adapter->flags & IAVF_FLAG_ALLMULTI_ON)
-		adapter->aq_required |= IAVF_FLAG_AQ_RELEASE_ALLMULTI;
+	spin_lock_bh(&adapter->current_netdev_promisc_flags_lock);
+	if (iavf_promiscuous_mode_changed(adapter))
+		adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE;
+	spin_unlock_bh(&adapter->current_netdev_promisc_flags_lock);
 }
 
 /**
@@ -2163,19 +2164,8 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter)
 		return 0;
 	}
 
-	if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_PROMISC) {
-		iavf_set_promiscuous(adapter, FLAG_VF_UNICAST_PROMISC |
-				       FLAG_VF_MULTICAST_PROMISC);
-		return 0;
-	}
-
-	if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_ALLMULTI) {
-		iavf_set_promiscuous(adapter, FLAG_VF_MULTICAST_PROMISC);
-		return 0;
-	}
-	if ((adapter->aq_required & IAVF_FLAG_AQ_RELEASE_PROMISC) ||
-	    (adapter->aq_required & IAVF_FLAG_AQ_RELEASE_ALLMULTI)) {
-		iavf_set_promiscuous(adapter, 0);
+	if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE) {
+		iavf_set_promiscuous(adapter);
 		return 0;
 	}
 
@@ -4971,6 +4961,7 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	spin_lock_init(&adapter->cloud_filter_list_lock);
 	spin_lock_init(&adapter->fdir_fltr_lock);
 	spin_lock_init(&adapter->adv_rss_lock);
+	spin_lock_init(&adapter->current_netdev_promisc_flags_lock);
 
 	INIT_LIST_HEAD(&adapter->mac_filter_list);
 	INIT_LIST_HEAD(&adapter->vlan_filter_list);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index f9727e9c3d63..0b97b424e487 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -936,14 +936,14 @@ void iavf_del_vlans(struct iavf_adapter *adapter)
 /**
  * iavf_set_promiscuous
  * @adapter: adapter structure
- * @flags: bitmask to control unicast/multicast promiscuous.
  *
  * Request that the PF enable promiscuous mode for our VSI.
  **/
-void iavf_set_promiscuous(struct iavf_adapter *adapter, int flags)
+void iavf_set_promiscuous(struct iavf_adapter *adapter)
 {
+	struct net_device *netdev = adapter->netdev;
 	struct virtchnl_promisc_info vpi;
-	int promisc_all;
+	unsigned int flags;
 
 	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -952,36 +952,57 @@ void iavf_set_promiscuous(struct iavf_adapter *adapter, int flags)
 		return;
 	}
 
-	promisc_all = FLAG_VF_UNICAST_PROMISC |
-		      FLAG_VF_MULTICAST_PROMISC;
-	if ((flags & promisc_all) == promisc_all) {
-		adapter->flags |= IAVF_FLAG_PROMISC_ON;
-		adapter->aq_required &= ~IAVF_FLAG_AQ_REQUEST_PROMISC;
-		dev_info(&adapter->pdev->dev, "Entering promiscuous mode\n");
-	}
+	/* prevent changes to promiscuous flags */
+	spin_lock_bh(&adapter->current_netdev_promisc_flags_lock);
 
-	if (flags & FLAG_VF_MULTICAST_PROMISC) {
-		adapter->flags |= IAVF_FLAG_ALLMULTI_ON;
-		adapter->aq_required &= ~IAVF_FLAG_AQ_REQUEST_ALLMULTI;
-		dev_info(&adapter->pdev->dev, "%s is entering multicast promiscuous mode\n",
-			 adapter->netdev->name);
+	/* sanity check to prevent duplicate AQ calls */
+	if (!iavf_promiscuous_mode_changed(adapter)) {
+		adapter->aq_required &= ~IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE;
+		dev_dbg(&adapter->pdev->dev, "No change in promiscuous mode\n");
+		/* allow changes to promiscuous flags */
+		spin_unlock_bh(&adapter->current_netdev_promisc_flags_lock);
+		return;
 	}
 
-	if (!flags) {
-		if (adapter->flags & IAVF_FLAG_PROMISC_ON) {
-			adapter->flags &= ~IAVF_FLAG_PROMISC_ON;
-			adapter->aq_required &= ~IAVF_FLAG_AQ_RELEASE_PROMISC;
-			dev_info(&adapter->pdev->dev, "Leaving promiscuous mode\n");
-		}
+	/* there are 2 bits, but only 3 states */
+	if (!(netdev->flags & IFF_PROMISC) &&
+	    netdev->flags & IFF_ALLMULTI) {
+		/* State 1  - only multicast promiscuous mode enabled
+		 * - !IFF_PROMISC && IFF_ALLMULTI
+		 */
+		flags = FLAG_VF_MULTICAST_PROMISC;
+		adapter->current_netdev_promisc_flags |= IFF_ALLMULTI;
+		adapter->current_netdev_promisc_flags &= ~IFF_PROMISC;
+		dev_info(&adapter->pdev->dev, "Entering multicast promiscuous mode\n");
+	} else if (!(netdev->flags & IFF_PROMISC) &&
+		   !(netdev->flags & IFF_ALLMULTI)) {
+		/* State 2 - unicast/multicast promiscuous mode disabled
+		 * - !IFF_PROMISC && !IFF_ALLMULTI
+		 */
+		flags = 0;
+		adapter->current_netdev_promisc_flags &=
+			~(IFF_PROMISC | IFF_ALLMULTI);
+		dev_info(&adapter->pdev->dev, "Leaving promiscuous mode\n");
+	} else {
+		/* State 3 - unicast/multicast promiscuous mode enabled
+		 * - IFF_PROMISC && IFF_ALLMULTI
+		 * - IFF_PROMISC && !IFF_ALLMULTI
+		 */
+		flags = FLAG_VF_UNICAST_PROMISC | FLAG_VF_MULTICAST_PROMISC;
+		adapter->current_netdev_promisc_flags |= IFF_PROMISC;
+		if (netdev->flags & IFF_ALLMULTI)
+			adapter->current_netdev_promisc_flags |= IFF_ALLMULTI;
+		else
+			adapter->current_netdev_promisc_flags &= ~IFF_ALLMULTI;
 
-		if (adapter->flags & IAVF_FLAG_ALLMULTI_ON) {
-			adapter->flags &= ~IAVF_FLAG_ALLMULTI_ON;
-			adapter->aq_required &= ~IAVF_FLAG_AQ_RELEASE_ALLMULTI;
-			dev_info(&adapter->pdev->dev, "%s is leaving multicast promiscuous mode\n",
-				 adapter->netdev->name);
-		}
+		dev_info(&adapter->pdev->dev, "Entering promiscuous mode\n");
 	}
 
+	adapter->aq_required &= ~IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE;
+
+	/* allow changes to promiscuous flags */
+	spin_unlock_bh(&adapter->current_netdev_promisc_flags_lock);
+
 	adapter->current_op = VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE;
 	vpi.vsi_id = adapter->vsi_res->vsi_id;
 	vpi.flags = flags;
-- 
cgit v1.2.3