Merge tag 'net-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from CAN, netfilter, wireguard and IPsec.

  I'd like to highlight [ lowlight? - Linus ] Florian W stepping down as
  a netfilter maintainer due to constant stream of bug reports. Not sure
  what we can do but IIUC this is not the first such case.

  Current release - regressions:

   - rxrpc: fix use of page_frag_alloc_align(), it changed semantics and
     we added a new caller in a different subtree

   - xfrm: allow UDP encapsulation only in offload modes

  Current release - new code bugs:

   - tcp: fix refcnt handling in __inet_hash_connect()

   - Revert "net: Re-use and set mono_delivery_time bit for userspace
     tstamp packets", conflicted with some expectations in BPF uAPI

  Previous releases - regressions:

   - ipv4: raw: fix sending packets from raw sockets via IPsec tunnels

   - devlink: fix devlink's parallel command processing

   - veth: do not manipulate GRO when using XDP

   - esp: fix bad handling of pages from page_pool

  Previous releases - always broken:

   - report RCU QS for busy network kthreads (with Paul McK's blessing)

   - tcp/rds: fix use-after-free on netns with kernel TCP reqsk

   - virt: vmxnet3: fix missing reserved tailroom with XDP

  Misc:

   - couple of build fixes for Documentation"

* tag 'net-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (59 commits)
  selftests: forwarding: Fix ping failure due to short timeout
  MAINTAINERS: step down as netfilter maintainer
  netfilter: nf_tables: Fix a memory leak in nf_tables_updchain
  net: dsa: mt7530: fix handling of all link-local frames
  net: dsa: mt7530: fix link-local frames that ingress vlan filtering ports
  bpf: report RCU QS in cpumap kthread
  net: report RCU QS on threaded NAPI repolling
  rcu: add a helper to report consolidated flavor QS
  ionic: update documentation for XDP support
  lib/bitmap: Fix bitmap_scatter() and bitmap_gather() kernel doc
  netfilter: nf_tables: do not compare internal table flags on updates
  netfilter: nft_set_pipapo: release elements in clone only from destroy path
  octeontx2-af: Use separate handlers for interrupts
  octeontx2-pf: Send UP messages to VF only when VF is up.
  octeontx2-pf: Use default max_active works instead of one
  octeontx2-pf: Wait till detach_resources msg is complete
  octeontx2: Detect the mbox up or down message via register
  devlink: fix port new reply cmd type
  tcp: Clear req->syncookie in reqsk_alloc().
  net/bnx2x: Prevent access to a freed page in page_pool
  ...

26 files changed, 345 insertions, 177 deletions

diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c
index f81b598147b3..7b5028b67cd5 100644
--- a/drivers/net/can/kvaser_pciefd.c
+++ b/drivers/net/can/kvaser_pciefd.c
@@ -370,8 +370,8 @@ static const struct kvaser_pciefd_irq_mask kvaser_pciefd_sf2_irq_mask = {
 
 static const struct kvaser_pciefd_irq_mask kvaser_pciefd_xilinx_irq_mask = {
 	.kcan_rx0 = BIT(4),
-	.kcan_tx = { BIT(16), BIT(17), BIT(18), BIT(19) },
-	.all = GENMASK(19, 16) | BIT(4),
+	.kcan_tx = { BIT(16), BIT(17), BIT(18), BIT(19), BIT(20), BIT(21), BIT(22), BIT(23) },
+	.all = GENMASK(23, 16) | BIT(4),
 };
 
 static const struct kvaser_pciefd_dev_ops kvaser_pciefd_altera_dev_ops = {
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 678b51f9cea6..767f66c37f6b 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -950,20 +950,56 @@ static void mt7530_setup_port5(struct dsa_switch *ds, phy_interface_t interface)
 	mutex_unlock(&priv->reg_mutex);
 }
 
+/* On page 205, section "8.6.3 Frame filtering" of the active standard, IEEE Std
+ * 802.1Q™-2022, it is stated that frames with 01:80:C2:00:00:00-0F as MAC DA
+ * must only be propagated to C-VLAN and MAC Bridge components. That means
+ * VLAN-aware and VLAN-unaware bridges. On the switch designs with CPU ports,
+ * these frames are supposed to be processed by the CPU (software). So we make
+ * the switch only forward them to the CPU port. And if received from a CPU
+ * port, forward to a single port. The software is responsible of making the
+ * switch conform to the latter by setting a single port as destination port on
+ * the special tag.
+ *
+ * This switch intellectual property cannot conform to this part of the standard
+ * fully. Whilst the REV_UN frame tag covers the remaining :04-0D and :0F MAC
+ * DAs, it also includes :22-FF which the scope of propagation is not supposed
+ * to be restricted for these MAC DAs.
+ */
 static void
 mt753x_trap_frames(struct mt7530_priv *priv)
 {
-	/* Trap BPDUs to the CPU port(s) */
-	mt7530_rmw(priv, MT753X_BPC, MT753X_BPDU_PORT_FW_MASK,
+	/* Trap 802.1X PAE frames and BPDUs to the CPU port(s) and egress them
+	 * VLAN-untagged.
+	 */
+	mt7530_rmw(priv, MT753X_BPC, MT753X_PAE_EG_TAG_MASK |
+		   MT753X_PAE_PORT_FW_MASK | MT753X_BPDU_EG_TAG_MASK |
+		   MT753X_BPDU_PORT_FW_MASK,
+		   MT753X_PAE_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+		   MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY) |
+		   MT753X_BPDU_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
 		   MT753X_BPDU_CPU_ONLY);
 
-	/* Trap 802.1X PAE frames to the CPU port(s) */
-	mt7530_rmw(priv, MT753X_BPC, MT753X_PAE_PORT_FW_MASK,
-		   MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY));
+	/* Trap frames with :01 and :02 MAC DAs to the CPU port(s) and egress
+	 * them VLAN-untagged.
+	 */
+	mt7530_rmw(priv, MT753X_RGAC1, MT753X_R02_EG_TAG_MASK |
+		   MT753X_R02_PORT_FW_MASK | MT753X_R01_EG_TAG_MASK |
+		   MT753X_R01_PORT_FW_MASK,
+		   MT753X_R02_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+		   MT753X_R02_PORT_FW(MT753X_BPDU_CPU_ONLY) |
+		   MT753X_R01_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+		   MT753X_BPDU_CPU_ONLY);
 
-	/* Trap LLDP frames with :0E MAC DA to the CPU port(s) */
-	mt7530_rmw(priv, MT753X_RGAC2, MT753X_R0E_PORT_FW_MASK,
-		   MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY));
+	/* Trap frames with :03 and :0E MAC DAs to the CPU port(s) and egress
+	 * them VLAN-untagged.
+	 */
+	mt7530_rmw(priv, MT753X_RGAC2, MT753X_R0E_EG_TAG_MASK |
+		   MT753X_R0E_PORT_FW_MASK | MT753X_R03_EG_TAG_MASK |
+		   MT753X_R03_PORT_FW_MASK,
+		   MT753X_R0E_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+		   MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY) |
+		   MT753X_R03_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+		   MT753X_BPDU_CPU_ONLY);
 }
 
 static void
@@ -2192,22 +2228,16 @@ mt7530_setup(struct dsa_switch *ds)
 		}
 	}
 
-	/* Disable LEDs before reset to prevent the MT7530 sampling a
-	 * potentially incorrect HT_XTAL_FSEL value.
-	 */
-	mt7530_write(priv, MT7530_LED_EN, 0);
-	usleep_range(1000, 1100);
-
 	/* Reset whole chip through gpio pin or memory-mapped registers for
 	 * different type of hardware
 	 */
 	if (priv->mcm) {
 		reset_control_assert(priv->rstc);
-		usleep_range(1000, 1100);
+		usleep_range(5000, 5100);
 		reset_control_deassert(priv->rstc);
 	} else {
 		gpiod_set_value_cansleep(priv->reset, 0);
-		usleep_range(1000, 1100);
+		usleep_range(5000, 5100);
 		gpiod_set_value_cansleep(priv->reset, 1);
 	}
 
@@ -2420,11 +2450,11 @@ mt7531_setup(struct dsa_switch *ds)
 	 */
 	if (priv->mcm) {
 		reset_control_assert(priv->rstc);
-		usleep_range(1000, 1100);
+		usleep_range(5000, 5100);
 		reset_control_deassert(priv->rstc);
 	} else {
 		gpiod_set_value_cansleep(priv->reset, 0);
-		usleep_range(1000, 1100);
+		usleep_range(5000, 5100);
 		gpiod_set_value_cansleep(priv->reset, 1);
 	}
 
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index a71166e0a7fc..d17b318e6ee4 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -65,14 +65,33 @@ enum mt753x_id {
 
 /* Registers for BPDU and PAE frame control*/
 #define MT753X_BPC			0x24
-#define  MT753X_BPDU_PORT_FW_MASK	GENMASK(2, 0)
+#define  MT753X_PAE_EG_TAG_MASK		GENMASK(24, 22)
+#define  MT753X_PAE_EG_TAG(x)		FIELD_PREP(MT753X_PAE_EG_TAG_MASK, x)
 #define  MT753X_PAE_PORT_FW_MASK	GENMASK(18, 16)
 #define  MT753X_PAE_PORT_FW(x)		FIELD_PREP(MT753X_PAE_PORT_FW_MASK, x)
+#define  MT753X_BPDU_EG_TAG_MASK	GENMASK(8, 6)
+#define  MT753X_BPDU_EG_TAG(x)		FIELD_PREP(MT753X_BPDU_EG_TAG_MASK, x)
+#define  MT753X_BPDU_PORT_FW_MASK	GENMASK(2, 0)
+
+/* Register for :01 and :02 MAC DA frame control */
+#define MT753X_RGAC1			0x28
+#define  MT753X_R02_EG_TAG_MASK		GENMASK(24, 22)
+#define  MT753X_R02_EG_TAG(x)		FIELD_PREP(MT753X_R02_EG_TAG_MASK, x)
+#define  MT753X_R02_PORT_FW_MASK	GENMASK(18, 16)
+#define  MT753X_R02_PORT_FW(x)		FIELD_PREP(MT753X_R02_PORT_FW_MASK, x)
+#define  MT753X_R01_EG_TAG_MASK		GENMASK(8, 6)
+#define  MT753X_R01_EG_TAG(x)		FIELD_PREP(MT753X_R01_EG_TAG_MASK, x)
+#define  MT753X_R01_PORT_FW_MASK	GENMASK(2, 0)
 
 /* Register for :03 and :0E MAC DA frame control */
 #define MT753X_RGAC2			0x2c
+#define  MT753X_R0E_EG_TAG_MASK		GENMASK(24, 22)
+#define  MT753X_R0E_EG_TAG(x)		FIELD_PREP(MT753X_R0E_EG_TAG_MASK, x)
 #define  MT753X_R0E_PORT_FW_MASK	GENMASK(18, 16)
 #define  MT753X_R0E_PORT_FW(x)		FIELD_PREP(MT753X_R0E_PORT_FW_MASK, x)
+#define  MT753X_R03_EG_TAG_MASK		GENMASK(8, 6)
+#define  MT753X_R03_EG_TAG(x)		FIELD_PREP(MT753X_R03_EG_TAG_MASK, x)
+#define  MT753X_R03_PORT_FW_MASK	GENMASK(2, 0)
 
 enum mt753x_bpdu_port_fw {
 	MT753X_BPDU_FOLLOW_MFC,
@@ -253,6 +272,7 @@ enum mt7530_port_mode {
 enum mt7530_vlan_port_eg_tag {
 	MT7530_VLAN_EG_DISABLED = 0,
 	MT7530_VLAN_EG_CONSISTENT = 1,
+	MT7530_VLAN_EG_UNTAGGED = 4,
 };
 
 enum mt7530_vlan_port_attr {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index d8b1824c334d..0bc1367fd649 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -1002,9 +1002,6 @@ static inline void bnx2x_set_fw_mac_addr(__le16 *fw_hi, __le16 *fw_mid,
 static inline void bnx2x_free_rx_mem_pool(struct bnx2x *bp,
 					  struct bnx2x_alloc_pool *pool)
 {
-	if (!pool->page)
-		return;
-
 	put_page(pool->page);
 
 	pool->page = NULL;
@@ -1015,6 +1012,9 @@ static inline void bnx2x_free_rx_sge_range(struct bnx2x *bp,
 {
 	int i;
 
+	if (!fp->page_pool.page)
+		return;
+
 	if (fp->mode == TPA_MODE_DISABLED)
 		return;
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 6c70c8498690..3c0f55b3e48e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -1338,7 +1338,7 @@ static irqreturn_t cgx_fwi_event_handler(int irq, void *data)
 
 		/* Release thread waiting for completion  */
 		lmac->cmd_pend = false;
-		wake_up_interruptible(&lmac->wq_cmd_cmplt);
+		wake_up(&lmac->wq_cmd_cmplt);
 		break;
 	case CGX_EVT_ASYNC:
 		if (cgx_event_is_linkevent(event))
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
index b92264d0a77e..1e5aa5397504 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
@@ -214,11 +214,12 @@ int otx2_mbox_busy_poll_for_rsp(struct otx2_mbox *mbox, int devid)
 }
 EXPORT_SYMBOL(otx2_mbox_busy_poll_for_rsp);
 
-void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid)
+static void otx2_mbox_msg_send_data(struct otx2_mbox *mbox, int devid, u64 data)
 {
 	struct otx2_mbox_dev *mdev = &mbox->dev[devid];
 	struct mbox_hdr *tx_hdr, *rx_hdr;
 	void *hw_mbase = mdev->hwbase;
+	u64 intr_val;
 
 	tx_hdr = hw_mbase + mbox->tx_start;
 	rx_hdr = hw_mbase + mbox->rx_start;
@@ -254,14 +255,52 @@ void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid)
 
 	spin_unlock(&mdev->mbox_lock);
 
+	/* Check if interrupt pending */
+	intr_val = readq((void __iomem *)mbox->reg_base +
+		     (mbox->trigger | (devid << mbox->tr_shift)));
+
+	intr_val |= data;
 	/* The interrupt should be fired after num_msgs is written
 	 * to the shared memory
 	 */
-	writeq(1, (void __iomem *)mbox->reg_base +
+	writeq(intr_val, (void __iomem *)mbox->reg_base +
 	       (mbox->trigger | (devid << mbox->tr_shift)));
 }
+
+void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid)
+{
+	otx2_mbox_msg_send_data(mbox, devid, MBOX_DOWN_MSG);
+}
 EXPORT_SYMBOL(otx2_mbox_msg_send);
 
+void otx2_mbox_msg_send_up(struct otx2_mbox *mbox, int devid)
+{
+	otx2_mbox_msg_send_data(mbox, devid, MBOX_UP_MSG);
+}
+EXPORT_SYMBOL(otx2_mbox_msg_send_up);
+
+bool otx2_mbox_wait_for_zero(struct otx2_mbox *mbox, int devid)
+{
+	u64 data;
+
+	data = readq((void __iomem *)mbox->reg_base +
+		     (mbox->trigger | (devid << mbox->tr_shift)));
+
+	/* If data is non-zero wait for ~1ms and return to caller
+	 * whether data has changed to zero or not after the wait.
+	 */
+	if (!data)
+		return true;
+
+	usleep_range(950, 1000);
+
+	data = readq((void __iomem *)mbox->reg_base +
+		     (mbox->trigger | (devid << mbox->tr_shift)));
+
+	return data == 0;
+}
+EXPORT_SYMBOL(otx2_mbox_wait_for_zero);
+
 struct mbox_msghdr *otx2_mbox_alloc_msg_rsp(struct otx2_mbox *mbox, int devid,
 					    int size, int size_rsp)
 {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 61ab7f66f053..eb2a20b5a0d0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -16,6 +16,9 @@
 
 #define MBOX_SIZE		SZ_64K
 
+#define MBOX_DOWN_MSG		1
+#define MBOX_UP_MSG		2
+
 /* AF/PF: PF initiated, PF/VF VF initiated */
 #define MBOX_DOWN_RX_START	0
 #define MBOX_DOWN_RX_SIZE	(46 * SZ_1K)
@@ -101,6 +104,7 @@ int otx2_mbox_regions_init(struct otx2_mbox *mbox, void __force **hwbase,
 			   struct pci_dev *pdev, void __force *reg_base,
 			   int direction, int ndevs, unsigned long *bmap);
 void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid);
+void otx2_mbox_msg_send_up(struct otx2_mbox *mbox, int devid);
 int otx2_mbox_wait_for_rsp(struct otx2_mbox *mbox, int devid);
 int otx2_mbox_busy_poll_for_rsp(struct otx2_mbox *mbox, int devid);
 struct mbox_msghdr *otx2_mbox_alloc_msg_rsp(struct otx2_mbox *mbox, int devid,
@@ -118,6 +122,8 @@ static inline struct mbox_msghdr *otx2_mbox_alloc_msg(struct otx2_mbox *mbox,
 	return otx2_mbox_alloc_msg_rsp(mbox, devid, size, 0);
 }
 
+bool otx2_mbox_wait_for_zero(struct otx2_mbox *mbox, int devid);
+
 /* Mailbox message types */
 #define MBOX_MSG_MASK				0xFFFF
 #define MBOX_MSG_INVALID			0xFFFE
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c
index dfd23580e3b8..d39d86e694cc 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c
@@ -121,13 +121,17 @@ int mcs_add_intr_wq_entry(struct mcs *mcs, struct mcs_intr_event *event)
 static int mcs_notify_pfvf(struct mcs_intr_event *event, struct rvu *rvu)
 {
 	struct mcs_intr_info *req;
-	int err, pf;
+	int pf;
 
 	pf = rvu_get_pf(event->pcifunc);
 
+	mutex_lock(&rvu->mbox_lock);
+
 	req = otx2_mbox_alloc_msg_mcs_intr_notify(rvu, pf);
-	if (!req)
+	if (!req) {
+		mutex_unlock(&rvu->mbox_lock);
 		return -ENOMEM;
+	}
 
 	req->mcs_id = event->mcs_id;
 	req->intr_mask = event->intr_mask;
@@ -135,10 +139,11 @@ static int mcs_notify_pfvf(struct mcs_intr_event *event, struct rvu *rvu)
 	req->hdr.pcifunc = event->pcifunc;
 	req->lmac_id = event->lmac_id;
 
-	otx2_mbox_msg_send(&rvu->afpf_wq_info.mbox_up, pf);
-	err = otx2_mbox_wait_for_rsp(&rvu->afpf_wq_info.mbox_up, pf);
-	if (err)
-		dev_warn(rvu->dev, "MCS notification to pf %d failed\n", pf);
+	otx2_mbox_wait_for_zero(&rvu->afpf_wq_info.mbox_up, pf);
+
+	otx2_mbox_msg_send_up(&rvu->afpf_wq_info.mbox_up, pf);
+
+	mutex_unlock(&rvu->mbox_lock);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 07d4859de53a..ff78251f92d4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -2119,7 +2119,7 @@ bad_message:
 	}
 }
 
-static void __rvu_mbox_handler(struct rvu_work *mwork, int type)
+static void __rvu_mbox_handler(struct rvu_work *mwork, int type, bool poll)
 {
 	struct rvu *rvu = mwork->rvu;
 	int offset, err, id, devid;
@@ -2186,6 +2186,9 @@ static void __rvu_mbox_handler(struct rvu_work *mwork, int type)
 	}
 	mw->mbox_wrk[devid].num_msgs = 0;
 
+	if (poll)
+		otx2_mbox_wait_for_zero(mbox, devid);
+
 	/* Send mbox responses to VF/PF */
 	otx2_mbox_msg_send(mbox, devid);
 }
@@ -2193,15 +2196,18 @@ static void __rvu_mbox_handler(struct rvu_work *mwork, int type)
 static inline void rvu_afpf_mbox_handler(struct work_struct *work)
 {
 	struct rvu_work *mwork = container_of(work, struct rvu_work, work);
+	struct rvu *rvu = mwork->rvu;
 
-	__rvu_mbox_handler(mwork, TYPE_AFPF);
+	mutex_lock(&rvu->mbox_lock);
+	__rvu_mbox_handler(mwork, TYPE_AFPF, true);
+	mutex_unlock(&rvu->mbox_lock);
 }
 
 static inline void rvu_afvf_mbox_handler(struct work_struct *work)
 {
 	struct rvu_work *mwork = container_of(work, struct rvu_work, work);
 
-	__rvu_mbox_handler(mwork, TYPE_AFVF);
+	__rvu_mbox_handler(mwork, TYPE_AFVF, false);
 }
 
 static void __rvu_mbox_up_handler(struct rvu_work *mwork, int type)
@@ -2376,6 +2382,8 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw,
 		}
 	}
 
+	mutex_init(&rvu->mbox_lock);
+
 	mbox_regions = kcalloc(num, sizeof(void *), GFP_KERNEL);
 	if (!mbox_regions) {
 		err = -ENOMEM;
@@ -2525,10 +2533,9 @@ static void rvu_queue_work(struct mbox_wq_info *mw, int first,
 	}
 }
 
-static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq)
+static irqreturn_t rvu_mbox_pf_intr_handler(int irq, void *rvu_irq)
 {
 	struct rvu *rvu = (struct rvu *)rvu_irq;
-	int vfs = rvu->vfs;
 	u64 intr;
 
 	intr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT);
@@ -2542,6 +2549,18 @@ static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq)
 
 	rvu_queue_work(&rvu->afpf_wq_info, 0, rvu->hw->total_pfs, intr);
 
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq)
+{
+	struct rvu *rvu = (struct rvu *)rvu_irq;
+	int vfs = rvu->vfs;
+	u64 intr;
+
+	/* Sync with mbox memory region */
+	rmb();
+
 	/* Handle VF interrupts */
 	if (vfs > 64) {
 		intr = rvupf_read64(rvu, RVU_PF_VFPF_MBOX_INTX(1));
@@ -2886,7 +2905,7 @@ static int rvu_register_interrupts(struct rvu *rvu)
 	/* Register mailbox interrupt handler */
 	sprintf(&rvu->irq_name[RVU_AF_INT_VEC_MBOX * NAME_SIZE], "RVUAF Mbox");
 	ret = request_irq(pci_irq_vector(rvu->pdev, RVU_AF_INT_VEC_MBOX),
-			  rvu_mbox_intr_handler, 0,
+			  rvu_mbox_pf_intr_handler, 0,
 			  &rvu->irq_name[RVU_AF_INT_VEC_MBOX * NAME_SIZE], rvu);
 	if (ret) {
 		dev_err(rvu->dev,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index f390525a6217..35834687e40f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -591,6 +591,8 @@ struct rvu {
 	spinlock_t		mcs_intrq_lock;
 	/* CPT interrupt lock */
 	spinlock_t		cpt_intr_lock;
+
+	struct mutex		mbox_lock; /* Serialize mbox up and down msgs */
 };
 
 static inline void rvu_write64(struct rvu *rvu, u64 block, u64 offset, u64 val)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index 38acdc7a73bb..72e060cf6b61 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -232,7 +232,7 @@ static void cgx_notify_pfs(struct cgx_link_event *event, struct rvu *rvu)
 	struct cgx_link_user_info *linfo;
 	struct cgx_link_info_msg *msg;
 	unsigned long pfmap;
-	int err, pfid;
+	int pfid;
 
 	linfo = &event->link_uinfo;
 	pfmap = cgxlmac_to_pfmap(rvu, event->cgx_id, event->lmac_id);
@@ -255,16 +255,22 @@ static void cgx_notify_pfs(struct cgx_link_event *event, struct rvu *rvu)
 			continue;
 		}
 
+		mutex_lock(&rvu->mbox_lock);
+
 		/* Send mbox message to PF */
 		msg = otx2_mbox_alloc_msg_cgx_link_event(rvu, pfid);
-		if (!msg)
+		if (!msg) {
+			mutex_unlock(&rvu->mbox_lock);
 			continue;
+		}
+
 		msg->link_info = *linfo;
-		otx2_mbox_msg_send(&rvu->afpf_wq_info.mbox_up, pfid);
-		err = otx2_mbox_wait_for_rsp(&rvu->afpf_wq_info.mbox_up, pfid);
-		if (err)
-			dev_warn(rvu->dev, "notification to pf %d failed\n",
-				 pfid);
+
+		otx2_mbox_wait_for_zero(&rvu->afpf_wq_info.mbox_up, pfid);
+
+		otx2_mbox_msg_send_up(&rvu->afpf_wq_info.mbox_up, pfid);
+
+		mutex_unlock(&rvu->mbox_lock);
 	} while (pfmap);
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 02d0b707aea5..a85ac039d779 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -1592,7 +1592,7 @@ int otx2_detach_resources(struct mbox *mbox)
 	detach->partial = false;
 
 	/* Send detach request to AF */
-	otx2_mbox_msg_send(&mbox->mbox, 0);
+	otx2_sync_mbox_msg(mbox);
 	mutex_unlock(&mbox->lock);
 	return 0;
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index 06910307085e..7e16a341ec58 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -815,7 +815,7 @@ static inline int otx2_sync_mbox_up_msg(struct mbox *mbox, int devid)
 
 	if (!otx2_mbox_nonempty(&mbox->mbox_up, devid))
 		return 0;
-	otx2_mbox_msg_send(&mbox->mbox_up, devid);
+	otx2_mbox_msg_send_up(&mbox->mbox_up, devid);
 	err = otx2_mbox_wait_for_rsp(&mbox->mbox_up, devid);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index e5fe67e73865..b40bd0e46751 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -292,8 +292,8 @@ static int otx2_pf_flr_init(struct otx2_nic *pf, int num_vfs)
 	return 0;
 }
 
-static void otx2_queue_work(struct mbox *mw, struct workqueue_struct *mbox_wq,
-			    int first, int mdevs, u64 intr, int type)
+static void otx2_queue_vf_work(struct mbox *mw, struct workqueue_struct *mbox_wq,
+			       int first, int mdevs, u64 intr)
 {
 	struct otx2_mbox_dev *mdev;
 	struct otx2_mbox *mbox;
@@ -307,40 +307,26 @@ static void otx2_queue_work(struct mbox *mw, struct workqueue_struct *mbox_wq,
 
 		mbox = &mw->mbox;
 		mdev = &mbox->dev[i];
-		if (type == TYPE_PFAF)
-			otx2_sync_mbox_bbuf(mbox, i);
 		hdr = mdev->mbase + mbox->rx_start;
 		/* The hdr->num_msgs is set to zero immediately in the interrupt
-		 * handler to  ensure that it holds a correct value next time
-		 * when the interrupt handler is called.
-		 * pf->mbox.num_msgs holds the data for use in pfaf_mbox_handler
-		 * pf>mbox.up_num_msgs holds the data for use in
-		 * pfaf_mbox_up_handler.
+		 * handler to ensure that it holds a correct value next time
+		 * when the interrupt handler is called. pf->mw[i].num_msgs
+		 * holds the data for use in otx2_pfvf_mbox_handler and
+		 * pf->mw[i].up_num_msgs holds the data for use in
+		 * otx2_pfvf_mbox_up_handler.
 		 */
 		if (hdr->num_msgs) {
 			mw[i].num_msgs = hdr->num_msgs;
 			hdr->num_msgs = 0;
-			if (type == TYPE_PFAF)
-				memset(mbox->hwbase + mbox->rx_start, 0,
-				       ALIGN(sizeof(struct mbox_hdr),
-					     sizeof(u64)));
-
 			queue_work(mbox_wq, &mw[i].mbox_wrk);
 		}
 
 		mbox = &mw->mbox_up;
 		mdev = &mbox->dev[i];
-		if (type == TYPE_PFAF)
-			otx2_sync_mbox_bbuf(mbox, i);
 		hdr = mdev->mbase + mbox->rx_start;
 		if (hdr->num_msgs) {
 			mw[i].up_num_msgs = hdr->num_msgs;
 			hdr->num_msgs = 0;
-			if (type == TYPE_PFAF)
-				memset(mbox->hwbase + mbox->rx_start, 0,
-				       ALIGN(sizeof(struct mbox_hdr),
-					     sizeof(u64)));
-
 			queue_work(mbox_wq, &mw[i].mbox_up_wrk);
 		}
 	}
@@ -356,8 +342,10 @@ static void otx2_forward_msg_pfvf(struct otx2_mbox_dev *mdev,
 	/* Msgs are already copied, trigger VF's mbox irq */
 	smp_wmb();
 
+	otx2_mbox_wait_for_zero(pfvf_mbox, devid);
+
 	offset = pfvf_mbox->trigger | (devid << pfvf_mbox->tr_shift);
-	writeq(1, (void __iomem *)pfvf_mbox->reg_base + offset);
+	writeq(MBOX_DOWN_MSG, (void __iomem *)pfvf_mbox->reg_base + offset);
 
 	/* Restore VF's mbox bounce buffer region address */
 	src_mdev->mbase = bbuf_base;
@@ -547,7 +535,7 @@ static void otx2_pfvf_mbox_up_handler(struct work_struct *work)
 end:
 		offset = mbox->rx_start + msg->next_msgoff;
 		if (mdev->msgs_acked == (vf_mbox->up_num_msgs - 1))
-			__otx2_mbox_reset(mbox, 0);
+			__otx2_mbox_reset(mbox, vf_idx);
 		mdev->msgs_acked++;
 	}
 }
@@ -564,8 +552,7 @@ static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq)
 	if (vfs > 64) {
 		intr = otx2_read64(pf, RVU_PF_VFPF_MBOX_INTX(1));
 		otx2_write64(pf, RVU_PF_VFPF_MBOX_INTX(1), intr);
-		otx2_queue_work(mbox, pf->mbox_pfvf_wq, 64, vfs, intr,
-				TYPE_PFVF);
+		otx2_queue_vf_work(mbox, pf->mbox_pfvf_wq, 64, vfs, intr);
 		if (intr)
 			trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr);
 		vfs = 64;
@@ -574,7 +561,7 @@ static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq)
 	intr = otx2_read64(pf, RVU_PF_VFPF_MBOX_INTX(0));
 	otx2_write64(pf, RVU_PF_VFPF_MBOX_INTX(0), intr);
 
-	otx2_queue_work(mbox, pf->mbox_pfvf_wq, 0, vfs, intr, TYPE_PFVF);
+	otx2_queue_vf_work(mbox, pf->mbox_pfvf_wq, 0, vfs, intr);
 
 	if (intr)
 		trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr);
@@ -597,8 +584,9 @@ static int otx2_pfvf_mbox_init(struct otx2_nic *pf, int numvfs)
 	if (!pf->mbox_pfvf)
 		return -ENOMEM;
 
-	pf->mbox_pfvf_wq = alloc_ordered_workqueue("otx2_pfvf_mailbox",
-						   WQ_HIGHPRI | WQ_MEM_RECLAIM);
+	pf->mbox_pfvf_wq = alloc_workqueue("otx2_pfvf_mailbox",
+					   WQ_UNBOUND | WQ_HIGHPRI |
+					   WQ_MEM_RECLAIM, 0);
 	if (!pf->mbox_pfvf_wq)
 		return -ENOMEM;
 
@@ -821,20 +809,22 @@ static void otx2_pfaf_mbox_handler(struct work_struct *work)
 	struct mbox *af_mbox;
 	struct otx2_nic *pf;
 	int offset, id;
+	u16 num_msgs;
 
 	af_mbox = container_of(work, struct mbox, mbox_wrk);
 	mbox = &af_mbox->mbox;
 	mdev = &mbox->dev[0];
 	rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
+	num_msgs = rsp_hdr->num_msgs;
 
 	offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN);
 	pf = af_mbox->pfvf;
 
-	for (id = 0; id < af_mbox->num_msgs; id++) {
+	for (id = 0; id < num_msgs; id++) {
 		msg = (struct mbox_msghdr *)(mdev->mbase + offset);
 		otx2_process_pfaf_mbox_msg(pf, msg);
 		offset = mbox->rx_start + msg->next_msgoff;
-		if (mdev->msgs_acked == (af_mbox->num_msgs - 1))
+		if (mdev->msgs_acked == (num_msgs - 1))
 			__otx2_mbox_reset(mbox, 0);
 		mdev->msgs_acked++;
 	}
@@ -945,12 +935,14 @@ static void otx2_pfaf_mbox_up_handler(struct work_struct *work)
 	int offset, id, devid = 0;
 	struct mbox_hdr *rsp_hdr;
 	struct mbox_msghdr *msg;
+	u16 num_msgs;
 
 	rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
+	num_msgs = rsp_hdr->num_msgs;
 
 	offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN);
 
-	for (id = 0; id < af_mbox->up_num_msgs; id++) {
+	for (id = 0; id < num_msgs; id++) {
 		msg = (struct mbox_msghdr *)(mdev->mbase + offset);
 
 		devid = msg->pcifunc & RVU_PFVF_FUNC_MASK;
@@ -959,10 +951,11 @@ static void otx2_pfaf_mbox_up_handler(struct work_struct *work)
 			otx2_process_mbox_msg_up(pf, msg);
 		offset = mbox->rx_start + msg->next_msgoff;
 	}
-	if (devid) {
+	/* Forward to VF iff VFs are really present */
+	if (devid && pci_num_vf(pf->pdev)) {
 		otx2_forward_vf_mbox_msgs(pf, &pf->mbox.mbox_up,
 					  MBOX_DIR_PFVF_UP, devid - 1,
-