* [PATCH net-next v8 00/10] net: airoha: Support multiple net_devices connected to the same GDM port
@ 2026-05-19 8:57 Lorenzo Bianconi
2026-05-19 8:57 ` [PATCH net-next v8 01/10] dt-bindings: net: airoha: Add GDM port ethernet child node Lorenzo Bianconi
` (9 more replies)
0 siblings, 10 replies; 22+ messages in thread
From: Lorenzo Bianconi @ 2026-05-19 8:57 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Lorenzo Bianconi
Cc: Christian Marangi, Benjamin Larsson, linux-arm-kernel,
linux-mediatek, netdev, devicetree, Xuegang Lu, Madhur Agrawal
EN7581 or AN7583 SoCs support connecting multiple external SerDes (e.g.
Ethernet or USB SerDes) to GDM3 or GDM4 ports via a hw arbiter that
manages the traffic in a TDM manner. As a result multiple net_devices can
connect to the same GDM{3,4} port and there is a theoretical "1:n"
relation between GDM ports and net_devices.
┌─────────────────────────────────┐
│ │ ┌──────┐
│ P1 GDM1 ├────►MT7530│
│ │ └──────┘
│ │ ETH0 (DSA conduit)
│ │
│ PSE/FE │
│ │
│ │
│ │ ┌─────┐
│ P0 CDM1 ├────►QDMA0│
│ P4 P9 GDM4 │ └─────┘
└──┬─────────────────────────┬────┘
│ │
┌──▼──┐ ┌────▼────┐
│ PPE │ │ ARB │
└─────┘ └─┬─────┬─┘
│ │
┌──▼──┐┌─▼───┐
│ ETH ││ USB │
└─────┘└─────┘
ETH1 ETH2
This series introduces support for multiple net_devices connected to the
same Frame Engine (FE) GDM port (GDM3 or GDM4) via an external hw
arbiter. Please note GDM1 or GDM2 does not support the connection with
the external arbiter.
---
Changes in v8:
- Fix dts schema issues reported by sashiko.
- Fix possible NULL-pointer dereference in patch 2/10.
- Fix max mtu computation in airoha_dev_change_mtu().
- Link to v7: https://lore.kernel.org/r/20260516-airoha-eth-multi-serdes-v7-0-99e0093303e2@kernel.org
Changes in v7:
- Fix dma_sync_single_for_cpu() size in airoha_qdma_rx_process().
- Fix hw stats reset.
- Fix typos.
- Add fix for airoha_tc_remove_htb_queue queue index.
- Fix dts schema issues.
- Remove hw stats patch from the series.
- Link to v6: https://lore.kernel.org/r/20260511-airoha-eth-multi-serdes-v6-0-c899462c4f75@kernel.org
Changes in v6:
- Reconfigure REG_GDM_LEN_CFG() whit max 'running' MTU in
airoha_dev_stop().
- Fix port staring MIB counters in airoha_update_hw_stats().
- Fix regression in TC_HTB_NODE_MODIFY command.
- Fix length check in airoha_qdma_rx_process().
- Fix dts schema.
- Link to v5: https://lore.kernel.org/r/20260509-airoha-eth-multi-serdes-v5-0-805e38edc2aa@kernel.org
Changes in v5:
- Move qos_sq_bmap bitmap in airoha_gdm_dev struct.
- Unregister netdevice before running of_node_put().
- Move stat MIB counters in airoha_gdm_dev struct.
- Fix airoha_ppe_init_upd_mem() mac address configuration.
- Do not return -EBUSY if we try to decrease configured MTU of a shared
GDM port, just skip hw configuration.
- use int instead of atomic_t for GDM port users.
- Add patch "net: airoha: Reserve RX headroom to avoid skb reallocation"
- Fix typos.
- Link to v4: https://lore.kernel.org/r/20260507-airoha-eth-multi-serdes-v4-0-af613b61ae02@kernel.org
Changes in v4:
- Make ethernet-port property available just for GDM3 and GDM4 in DTS
specification
- Move cpu_tx_packets, fwd_tx_packets qos_sq_bmap fields in airoha_qdma
struct
- Fix of_node leak removing the net_device in airoha_remove() or
airoha_probe() error path
- Fix nbq backward compatibility
- Link to v3: https://lore.kernel.org/r/20260406-airoha-eth-multi-serdes-v3-0-ab6ea49d59ff@kernel.org
Changes in v3:
- Fix MTU and VIP configuration when the GDM port is shared between
multiple net_devices.
- Add sanity check for nbq parameter.
- Add missing of_node_get() for net_device np node.
- Check if GDM port is shared before decresing device MTU.
- Move port forward configuration in airoha_dev_stop() before
configuring DMA tx/rx engine.
- Introduce PRIV_FLAG_WAN parameter.
- Link to v2: https://lore.kernel.org/r/20260401-airoha-eth-multi-serdes-v2-0-ac427ae4beeb@kernel.org
Changes in v2:
- Rename multiplexer in arbiter in the commit logs.
- Rebase on top of net-next main branch.
- Add missing PPE cpu port configuration for GDM2 when loopback is
enabled.
- Link to v1: https://lore.kernel.org/r/20260329-airoha-eth-multi-serdes-v1-0-00f52dc360ca@kernel.org
---
Lorenzo Bianconi (10):
dt-bindings: net: airoha: Add GDM port ethernet child node
net: airoha: Introduce airoha_gdm_dev struct
net: airoha: Move airoha_qdma pointer in airoha_gdm_dev struct
net: airoha: Rely on airoha_gdm_dev pointer in airoha_is_lan_gdm_port()
net: airoha: Move qos_sq_bmap in airoha_gdm_dev struct
net: airoha: Move {cpu,fwd}_tx_packets in airoha_gdm_dev struct
net: airoha: Support multiple net_devices for a single FE GDM port
net: airoha: Do not stop GDM port if it is shared
net: airoha: Introduce WAN device flag
net: airoha: Support multiple LAN/WAN interfaces for hw MAC address configuration
.../devicetree/bindings/net/airoha,en7581-eth.yaml | 56 +-
drivers/net/ethernet/airoha/airoha_eth.c | 833 +++++++++++++++------
drivers/net/ethernet/airoha/airoha_eth.h | 47 +-
drivers/net/ethernet/airoha/airoha_ppe.c | 43 +-
4 files changed, 702 insertions(+), 277 deletions(-)
---
base-commit: 7a348a95f696d20f15c776de4df8b4415bcf3d77
change-id: 20260324-airoha-eth-multi-serdes-fb4b556ee756
Best regards,
--
Lorenzo Bianconi <lorenzo@kernel.org>
^ permalink raw reply [flat|nested] 22+ messages in thread
* [PATCH net-next v8 01/10] dt-bindings: net: airoha: Add GDM port ethernet child node
2026-05-19 8:57 [PATCH net-next v8 00/10] net: airoha: Support multiple net_devices connected to the same GDM port Lorenzo Bianconi
@ 2026-05-19 8:57 ` Lorenzo Bianconi
2026-05-19 8:57 ` [PATCH net-next v8 02/10] net: airoha: Introduce airoha_gdm_dev struct Lorenzo Bianconi
` (8 subsequent siblings)
9 siblings, 0 replies; 22+ messages in thread
From: Lorenzo Bianconi @ 2026-05-19 8:57 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Lorenzo Bianconi
Cc: Christian Marangi, Benjamin Larsson, linux-arm-kernel,
linux-mediatek, netdev, devicetree
EN7581 and AN7583 SoCs support connecting multiple external SerDes to GDM3
or GDM4 ports via a hw arbiter that manages the traffic in a TDM manner.
As a result multiple net_devices can connect to the same GDM{3,4} port
and there is a theoretical "1:n" relation between GDM ports and
net_devices.
Introduce the ethernet node child of a specific GDM port in order to model
a given net_device that is connected via the external arbiter to the
GDM{3,4} port. This new ethernet node is defined by the "airoha,eth-port"
compatible string. Please note GDM1 and GDM2 does not support the
connection with the external arbiter and they are represented by an
ethernet node defined by the "airoha,eth-mac" compatible string.
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
.../devicetree/bindings/net/airoha,en7581-eth.yaml | 56 +++++++++++++++++++++-
1 file changed, 55 insertions(+), 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/net/airoha,en7581-eth.yaml b/Documentation/devicetree/bindings/net/airoha,en7581-eth.yaml
index fbe2ddcdd909..17fe2edf4886 100644
--- a/Documentation/devicetree/bindings/net/airoha,en7581-eth.yaml
+++ b/Documentation/devicetree/bindings/net/airoha,en7581-eth.yaml
@@ -130,6 +130,42 @@ patternProperties:
maximum: 4
description: GMAC port identifier
+ allOf:
+ - if:
+ properties:
+ reg:
+ contains:
+ items:
+ - enum:
+ - 3
+ - 4
+ then:
+ properties:
+ '#address-cells':
+ const: 1
+
+ '#size-cells':
+ const: 0
+
+ patternProperties:
+ "^ethernet@[0-5]$":
+ type: object
+ unevaluatedProperties: false
+ $ref: ethernet-controller.yaml#
+ description: External ethernet port ID available on the GDM port
+
+ properties:
+ compatible:
+ const: airoha,eth-port
+
+ reg:
+ maximum: 5
+ description: External ethernet port identifier
+
+ required:
+ - reg
+ - compatible
+
required:
- reg
- compatible
@@ -191,9 +227,27 @@ examples:
#address-cells = <1>;
#size-cells = <0>;
- mac: ethernet@1 {
+ ethernet@1 {
compatible = "airoha,eth-mac";
reg = <1>;
};
+
+ ethernet@4 {
+ compatible = "airoha,eth-mac";
+ reg = <4>;
+
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ ethernet@0 {
+ compatible = "airoha,eth-port";
+ reg = <0>;
+ };
+
+ ethernet@1 {
+ compatible = "airoha,eth-port";
+ reg = <1>;
+ };
+ };
};
};
--
2.54.0
^ permalink raw reply related [flat|nested] 22+ messages in thread
* [PATCH net-next v8 02/10] net: airoha: Introduce airoha_gdm_dev struct
2026-05-19 8:57 [PATCH net-next v8 00/10] net: airoha: Support multiple net_devices connected to the same GDM port Lorenzo Bianconi
2026-05-19 8:57 ` [PATCH net-next v8 01/10] dt-bindings: net: airoha: Add GDM port ethernet child node Lorenzo Bianconi
@ 2026-05-19 8:57 ` Lorenzo Bianconi
2026-05-20 8:59 ` sashiko-bot
2026-05-19 8:57 ` [PATCH net-next v8 03/10] net: airoha: Move airoha_qdma pointer in " Lorenzo Bianconi
` (7 subsequent siblings)
9 siblings, 1 reply; 22+ messages in thread
From: Lorenzo Bianconi @ 2026-05-19 8:57 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Lorenzo Bianconi
Cc: Christian Marangi, Benjamin Larsson, linux-arm-kernel,
linux-mediatek, netdev, devicetree, Xuegang Lu
EN7581 and AN7583 SoCs support connecting multiple external SerDes to GDM3
or GDM4 ports via a hw arbiter that manages the traffic in a TDM manner.
As a result multiple net_devices can connect to the same GDM{3,4} port
and there is a theoretical "1:n" relation between GDM port and
net_devices.
Introduce airoha_gdm_dev struct to collect net_device related info (e.g.
net_device and external phy pointer). Please note this is just a
preliminary patch and we are still supporting a single net_device for
each GDM port. Subsequent patches will add support for multiple net_devices
connected to the same GDM port.
Tested-by: Xuegang Lu <xuegang.lu@airoha.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
drivers/net/ethernet/airoha/airoha_eth.c | 312 ++++++++++++++++++-------------
drivers/net/ethernet/airoha/airoha_eth.h | 13 +-
drivers/net/ethernet/airoha/airoha_ppe.c | 17 +-
3 files changed, 206 insertions(+), 136 deletions(-)
diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 5a027cc7ffcb..5335271ea865 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -600,6 +600,7 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
struct airoha_qdma_desc *desc = &q->desc[q->tail];
u32 hash, reason, msg1, desc_ctrl;
struct airoha_gdm_port *port;
+ struct net_device *netdev;
int data_len, len, p;
struct page *page;
@@ -626,6 +627,10 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
goto free_frag;
port = eth->ports[p];
+ if (!port->dev)
+ goto free_frag;
+
+ netdev = port->dev->dev;
if (!q->skb) { /* first buffer */
q->skb = napi_build_skb(e->buf - AIROHA_RX_HEADROOM,
q->buf_size);
@@ -635,8 +640,8 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
skb_reserve(q->skb, AIROHA_RX_HEADROOM);
__skb_put(q->skb, len);
skb_mark_for_recycle(q->skb);
- q->skb->dev = port->dev;
- q->skb->protocol = eth_type_trans(q->skb, port->dev);
+ q->skb->dev = netdev;
+ q->skb->protocol = eth_type_trans(q->skb, netdev);
q->skb->ip_summed = CHECKSUM_UNNECESSARY;
skb_record_rx_queue(q->skb, qid);
} else { /* scattered frame */
@@ -654,7 +659,7 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
if (FIELD_GET(QDMA_DESC_MORE_MASK, desc_ctrl))
continue;
- if (netdev_uses_dsa(port->dev)) {
+ if (netdev_uses_dsa(netdev)) {
/* PPE module requires untagged packets to work
* properly and it provides DSA port index via the
* DMA descriptor. Report DSA tag to the DSA stack
@@ -848,6 +853,7 @@ static void airoha_qdma_wake_netdev_txqs(struct airoha_queue *q)
for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
struct airoha_gdm_port *port = eth->ports[i];
+ struct airoha_gdm_dev *dev;
int j;
if (!port)
@@ -856,11 +862,12 @@ static void airoha_qdma_wake_netdev_txqs(struct airoha_queue *q)
if (port->qdma != qdma)
continue;
- for (j = 0; j < port->dev->num_tx_queues; j++) {
+ dev = port->dev;
+ for (j = 0; j < dev->dev->num_tx_queues; j++) {
if (airoha_qdma_get_txq(qdma, j) != qid)
continue;
- netif_wake_subqueue(port->dev, j);
+ netif_wake_subqueue(dev->dev, j);
}
}
q->txq_stopped = false;
@@ -1700,19 +1707,20 @@ static void airoha_update_hw_stats(struct airoha_gdm_port *port)
spin_unlock(&port->stats.lock);
}
-static int airoha_dev_open(struct net_device *dev)
+static int airoha_dev_open(struct net_device *netdev)
{
- int err, len = ETH_HLEN + dev->mtu + ETH_FCS_LEN;
- struct airoha_gdm_port *port = netdev_priv(dev);
+ int err, len = ETH_HLEN + netdev->mtu + ETH_FCS_LEN;
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
struct airoha_qdma *qdma = port->qdma;
u32 pse_port = FE_PSE_PORT_PPE1;
- netif_tx_start_all_queues(dev);
+ netif_tx_start_all_queues(netdev);
err = airoha_set_vip_for_gdm_port(port, true);
if (err)
return err;
- if (netdev_uses_dsa(dev))
+ if (netdev_uses_dsa(netdev))
airoha_fe_set(qdma->eth, REG_GDM_INGRESS_CFG(port->id),
GDM_STAG_EN_MASK);
else
@@ -1740,16 +1748,17 @@ static int airoha_dev_open(struct net_device *dev)
return 0;
}
-static int airoha_dev_stop(struct net_device *dev)
+static int airoha_dev_stop(struct net_device *netdev)
{
- struct airoha_gdm_port *port = netdev_priv(dev);
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
struct airoha_qdma *qdma = port->qdma;
int i;
- netif_tx_disable(dev);
+ netif_tx_disable(netdev);
airoha_set_vip_for_gdm_port(port, false);
- for (i = 0; i < dev->num_tx_queues; i++)
- netdev_tx_reset_subqueue(dev, i);
+ for (i = 0; i < netdev->num_tx_queues; i++)
+ netdev_tx_reset_subqueue(netdev, i);
airoha_set_gdm_port_fwd_cfg(qdma->eth, REG_GDM_FWD_CFG(port->id),
FE_PSE_PORT_DROP);
@@ -1770,16 +1779,17 @@ static int airoha_dev_stop(struct net_device *dev)
return 0;
}
-static int airoha_dev_set_macaddr(struct net_device *dev, void *p)
+static int airoha_dev_set_macaddr(struct net_device *netdev, void *p)
{
- struct airoha_gdm_port *port = netdev_priv(dev);
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
int err;
- err = eth_mac_addr(dev, p);
+ err = eth_mac_addr(netdev, p);
if (err)
return err;
- airoha_set_macaddr(port, dev->dev_addr);
+ airoha_set_macaddr(port, netdev->dev_addr);
return 0;
}
@@ -1843,16 +1853,17 @@ static int airoha_set_gdm2_loopback(struct airoha_gdm_port *port)
return 0;
}
-static int airoha_dev_init(struct net_device *dev)
+static int airoha_dev_init(struct net_device *netdev)
{
- struct airoha_gdm_port *port = netdev_priv(dev);
- struct airoha_eth *eth = port->eth;
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
+ struct airoha_eth *eth = dev->eth;
int i;
/* QDMA0 is used for lan ports while QDMA1 is used for WAN ports */
port->qdma = ð->qdma[!airoha_is_lan_gdm_port(port)];
- port->dev->irq = port->qdma->irq_banks[0].irq;
- airoha_set_macaddr(port, dev->dev_addr);
+ dev->dev->irq = port->qdma->irq_banks[0].irq;
+ airoha_set_macaddr(port, netdev->dev_addr);
switch (port->id) {
case AIROHA_GDM3_IDX:
@@ -1877,10 +1888,11 @@ static int airoha_dev_init(struct net_device *dev)
return 0;
}
-static void airoha_dev_get_stats64(struct net_device *dev,
+static void airoha_dev_get_stats64(struct net_device *netdev,
struct rtnl_link_stats64 *storage)
{
- struct airoha_gdm_port *port = netdev_priv(dev);
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
unsigned int start;
airoha_update_hw_stats(port);
@@ -1899,36 +1911,39 @@ static void airoha_dev_get_stats64(struct net_device *dev,
} while (u64_stats_fetch_retry(&port->stats.syncp, start));
}
-static int airoha_dev_change_mtu(struct net_device *dev, int mtu)
+static int airoha_dev_change_mtu(struct net_device *netdev, int mtu)
{
- struct airoha_gdm_port *port = netdev_priv(dev);
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
struct airoha_eth *eth = port->qdma->eth;
u32 len = ETH_HLEN + mtu + ETH_FCS_LEN;
airoha_fe_rmw(eth, REG_GDM_LEN_CFG(port->id),
GDM_LONG_LEN_MASK,
FIELD_PREP(GDM_LONG_LEN_MASK, len));
- WRITE_ONCE(dev->mtu, mtu);
+ WRITE_ONCE(netdev->mtu, mtu);
return 0;
}
-static u16 airoha_dev_select_queue(struct net_device *dev, struct sk_buff *skb,
+static u16 airoha_dev_select_queue(struct net_device *netdev,
+ struct sk_buff *skb,
struct net_device *sb_dev)
{
- struct airoha_gdm_port *port = netdev_priv(dev);
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
int queue, channel;
/* For dsa device select QoS channel according to the dsa user port
* index, rely on port id otherwise. Select QoS queue based on the
* skb priority.
*/
- channel = netdev_uses_dsa(dev) ? skb_get_queue_mapping(skb) : port->id;
+ channel = netdev_uses_dsa(netdev) ? skb_get_queue_mapping(skb) : port->id;
channel = channel % AIROHA_NUM_QOS_CHANNELS;
queue = (skb->priority - 1) % AIROHA_NUM_QOS_QUEUES; /* QoS queue */
queue = channel * AIROHA_NUM_QOS_QUEUES + queue;
- return queue < dev->num_tx_queues ? queue : 0;
+ return queue < netdev->num_tx_queues ? queue : 0;
}
static u32 airoha_get_dsa_tag(struct sk_buff *skb, struct net_device *dev)
@@ -1992,9 +2007,10 @@ int airoha_get_fe_port(struct airoha_gdm_port *port)
}
static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
- struct net_device *dev)
+ struct net_device *netdev)
{
- struct airoha_gdm_port *port = netdev_priv(dev);
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
struct airoha_qdma *qdma = port->qdma;
u32 nr_frags, tag, msg0, msg1, len;
struct airoha_queue_entry *e;
@@ -2007,7 +2023,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
u8 fport;
qid = airoha_qdma_get_txq(qdma, skb_get_queue_mapping(skb));
- tag = airoha_get_dsa_tag(skb, dev);
+ tag = airoha_get_dsa_tag(skb, netdev);
msg0 = FIELD_PREP(QDMA_ETH_TXMSG_CHAN_MASK,
qid / AIROHA_NUM_QOS_QUEUES) |
@@ -2043,7 +2059,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
spin_lock_bh(&q->lock);
- txq = skb_get_tx_queue(dev, skb);
+ txq = skb_get_tx_queue(netdev, skb);
nr_frags = 1 + skb_shinfo(skb)->nr_frags;
if (q->queued + nr_frags >= q->ndesc) {
@@ -2067,9 +2083,9 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
dma_addr_t addr;
u32 val;
- addr = dma_map_single(dev->dev.parent, data, len,
+ addr = dma_map_single(netdev->dev.parent, data, len,
DMA_TO_DEVICE);
- if (unlikely(dma_mapping_error(dev->dev.parent, addr)))
+ if (unlikely(dma_mapping_error(netdev->dev.parent, addr)))
goto error_unmap;
list_move_tail(&e->list, &tx_list);
@@ -2118,7 +2134,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
error_unmap:
list_for_each_entry(e, &tx_list, list) {
- dma_unmap_single(dev->dev.parent, e->dma_addr, e->dma_len,
+ dma_unmap_single(netdev->dev.parent, e->dma_addr, e->dma_len,
DMA_TO_DEVICE);
e->dma_addr = 0;
}
@@ -2127,25 +2143,27 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
spin_unlock_bh(&q->lock);
error:
dev_kfree_skb_any(skb);
- dev->stats.tx_dropped++;
+ netdev->stats.tx_dropped++;
return NETDEV_TX_OK;
}
-static void airoha_ethtool_get_drvinfo(struct net_device *dev,
+static void airoha_ethtool_get_drvinfo(struct net_device *netdev,
struct ethtool_drvinfo *info)
{
- struct airoha_gdm_port *port = netdev_priv(dev);
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
struct airoha_eth *eth = port->qdma->eth;
strscpy(info->driver, eth->dev->driver->name, sizeof(info->driver));
strscpy(info->bus_info, dev_name(eth->dev), sizeof(info->bus_info));
}
-static void airoha_ethtool_get_mac_stats(struct net_device *dev,
+static void airoha_ethtool_get_mac_stats(struct net_device *netdev,
struct ethtool_eth_mac_stats *stats)
{
- struct airoha_gdm_port *port = netdev_priv(dev);
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
unsigned int start;
airoha_update_hw_stats(port);
@@ -2173,11 +2191,12 @@ static const struct ethtool_rmon_hist_range airoha_ethtool_rmon_ranges[] = {
};
static void
-airoha_ethtool_get_rmon_stats(struct net_device *dev,
+airoha_ethtool_get_rmon_stats(struct net_device *netdev,
struct ethtool_rmon_stats *stats,
const struct ethtool_rmon_hist_range **ranges)
{
- struct airoha_gdm_port *port = netdev_priv(dev);
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
struct airoha_hw_stats *hw_stats = &port->stats;
unsigned int start;
@@ -2202,11 +2221,12 @@ airoha_ethtool_get_rmon_stats(struct net_device *dev,
} while (u64_stats_fetch_retry(&port->stats.syncp, start));
}
-static int airoha_qdma_set_chan_tx_sched(struct net_device *dev,
+static int airoha_qdma_set_chan_tx_sched(struct net_device *netdev,
int channel, enum tx_sched_mode mode,
const u16 *weights, u8 n_weights)
{
- struct airoha_gdm_port *port = netdev_priv(dev);
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
int i;
for (i = 0; i < AIROHA_NUM_TX_RING; i++)
@@ -2291,10 +2311,12 @@ static int airoha_qdma_set_tx_ets_sched(struct net_device *dev, int channel,
ARRAY_SIZE(w));
}
-static int airoha_qdma_get_tx_ets_stats(struct net_device *dev, int channel,
+static int airoha_qdma_get_tx_ets_stats(struct net_device *netdev, int channel,
struct tc_ets_qopt_offload *opt)
{
- struct airoha_gdm_port *port = netdev_priv(dev);
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
+
u64 cpu_tx_packets = airoha_qdma_rr(port->qdma,
REG_CNTR_VAL(channel << 1));
u64 fwd_tx_packets = airoha_qdma_rr(port->qdma,
@@ -2556,11 +2578,12 @@ static int airoha_qdma_set_trtcm_token_bucket(struct airoha_qdma *qdma,
mode, val);
}
-static int airoha_qdma_set_tx_rate_limit(struct net_device *dev,
+static int airoha_qdma_set_tx_rate_limit(struct net_device *netdev,
int channel, u32 rate,
u32 bucket_size)
{
- struct airoha_gdm_port *port = netdev_priv(dev);
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
int i, err;
for (i = 0; i <= TRTCM_PEAK_MODE; i++) {
@@ -2580,20 +2603,22 @@ static int airoha_qdma_set_tx_rate_limit(struct net_device *dev,
return 0;
}
-static int airoha_tc_htb_alloc_leaf_queue(struct net_device *dev,
+static int airoha_tc_htb_alloc_leaf_queue(struct net_device *netdev,
struct tc_htb_qopt_offload *opt)
{
u32 channel = TC_H_MIN(opt->classid) % AIROHA_NUM_QOS_CHANNELS;
u32 rate = div_u64(opt->rate, 1000) << 3; /* kbps */
- int err, num_tx_queues = dev->real_num_tx_queues;
- struct airoha_gdm_port *port = netdev_priv(dev);
+ int err, num_tx_queues = netdev->real_num_tx_queues;
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
if (opt->parent_classid != TC_HTB_CLASSID_ROOT) {
NL_SET_ERR_MSG_MOD(opt->extack, "invalid parent classid");
return -EINVAL;
}
- err = airoha_qdma_set_tx_rate_limit(dev, channel, rate, opt->quantum);
+ err = airoha_qdma_set_tx_rate_limit(netdev, channel, rate,
+ opt->quantum);
if (err) {
NL_SET_ERR_MSG_MOD(opt->extack,
"failed configuring htb offload");
@@ -2603,9 +2628,10 @@ static int airoha_tc_htb_alloc_leaf_queue(struct net_device *dev,
if (opt->command == TC_HTB_NODE_MODIFY)
return 0;
- err = netif_set_real_num_tx_queues(dev, num_tx_queues + 1);
+ err = netif_set_real_num_tx_queues(netdev, num_tx_queues + 1);
if (err) {
- airoha_qdma_set_tx_rate_limit(dev, channel, 0, opt->quantum);
+ airoha_qdma_set_tx_rate_limit(netdev, channel, 0,
+ opt->quantum);
NL_SET_ERR_MSG_MOD(opt->extack,
"failed setting real_num_tx_queues");
return err;
@@ -2695,11 +2721,12 @@ static int airoha_tc_matchall_act_validate(struct tc_cls_matchall_offload *f)
return 0;
}
-static int airoha_dev_tc_matchall(struct net_device *dev,
+static int airoha_dev_tc_matchall(struct net_device *netdev,
struct tc_cls_matchall_offload *f)
{
enum trtcm_unit_type unit_type = TRTCM_BYTE_UNIT;
- struct airoha_gdm_port *port = netdev_priv(dev);
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
u32 rate = 0, bucket_size = 0;
switch (f->command) {
@@ -2734,18 +2761,19 @@ static int airoha_dev_tc_matchall(struct net_device *dev,
static int airoha_dev_setup_tc_block_cb(enum tc_setup_type type,
void *type_data, void *cb_priv)
{
- struct net_device *dev = cb_priv;
- struct airoha_gdm_port *port = netdev_priv(dev);
+ struct net_device *netdev = cb_priv;
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
struct airoha_eth *eth = port->qdma->eth;
- if (!tc_can_offload(dev))
+ if (!tc_can_offload(netdev))
return -EOPNOTSUPP;
switch (type) {
case TC_SETUP_CLSFLOWER:
return airoha_ppe_setup_tc_block_cb(ð->ppe->dev, type_data);
case TC_SETUP_CLSMATCHALL:
- return airoha_dev_tc_matchall(dev, type_data);
+ return airoha_dev_tc_matchall(netdev, type_data);
default:
return -EOPNOTSUPP;
}
@@ -2792,47 +2820,51 @@ static int airoha_dev_setup_tc_block(struct net_device *dev,
}
}
-static void airoha_tc_remove_htb_queue(struct net_device *dev, int queue)
+static void airoha_tc_remove_htb_queue(struct net_device *netdev, int queue)
{
- struct airoha_gdm_port *port = netdev_priv(dev);
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
- netif_set_real_num_tx_queues(dev, dev->real_num_tx_queues - 1);
- airoha_qdma_set_tx_rate_limit(dev, queue + 1, 0, 0);
+ netif_set_real_num_tx_queues(netdev, netdev->real_num_tx_queues - 1);
+ airoha_qdma_set_tx_rate_limit(netdev, queue + 1, 0, 0);
clear_bit(queue, port->qos_sq_bmap);
}
-static int airoha_tc_htb_delete_leaf_queue(struct net_device *dev,
+static int airoha_tc_htb_delete_leaf_queue(struct net_device *netdev,
struct tc_htb_qopt_offload *opt)
{
u32 channel = TC_H_MIN(opt->classid) % AIROHA_NUM_QOS_CHANNELS;
- struct airoha_gdm_port *port = netdev_priv(dev);
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
if (!test_bit(channel, port->qos_sq_bmap)) {
NL_SET_ERR_MSG_MOD(opt->extack, "invalid queue id");
return -EINVAL;
}
- airoha_tc_remove_htb_queue(dev, channel);
+ airoha_tc_remove_htb_queue(netdev, channel);
return 0;
}
-static int airoha_tc_htb_destroy(struct net_device *dev)
+static int airoha_tc_htb_destroy(struct net_device *netdev)
{
- struct airoha_gdm_port *port = netdev_priv(dev);
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
int q;
for_each_set_bit(q, port->qos_sq_bmap, AIROHA_NUM_QOS_CHANNELS)
- airoha_tc_remove_htb_queue(dev, q);
+ airoha_tc_remove_htb_queue(netdev, q);
return 0;
}
-static int airoha_tc_get_htb_get_leaf_queue(struct net_device *dev,
+static int airoha_tc_get_htb_get_leaf_queue(struct net_device *netdev,
struct tc_htb_qopt_offload *opt)
{
u32 channel = TC_H_MIN(opt->classid) % AIROHA_NUM_QOS_CHANNELS;
- struct airoha_gdm_port *port = netdev_priv(dev);
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
if (!test_bit(channel, port->qos_sq_bmap)) {
NL_SET_ERR_MSG_MOD(opt->extack, "invalid queue id");
@@ -2868,8 +2900,8 @@ static int airoha_tc_setup_qdisc_htb(struct net_device *dev,
return 0;
}
-static int airoha_dev_tc_setup(struct net_device *dev, enum tc_setup_type type,
- void *type_data)
+static int airoha_dev_tc_setup(struct net_device *dev,
+ enum tc_setup_type type, void *type_data)
{
switch (type) {
case TC_SETUP_QDISC_ETS:
@@ -2935,25 +2967,81 @@ static void airoha_metadata_dst_free(struct airoha_gdm_port *port)
}
}
-bool airoha_is_valid_gdm_port(struct airoha_eth *eth,
- struct airoha_gdm_port *port)
+bool airoha_is_valid_gdm_dev(struct airoha_eth *eth,
+ struct airoha_gdm_dev *dev)
{
int i;
for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
- if (eth->ports[i] == port)
+ struct airoha_gdm_port *port = eth->ports[i];
+
+ if (!port)
+ continue;
+
+ if (port->dev == dev)
return true;
}
return false;
}
+static int airoha_alloc_gdm_device(struct airoha_eth *eth,
+ struct airoha_gdm_port *port,
+ struct device_node *np)
+{
+ struct airoha_gdm_dev *dev;
+ struct net_device *netdev;
+ int err;
+
+ netdev = devm_alloc_etherdev_mqs(eth->dev, sizeof(*dev),
+ AIROHA_NUM_NETDEV_TX_RINGS,
+ AIROHA_NUM_RX_RING);
+ if (!netdev) {
+ dev_err(eth->dev, "alloc_etherdev failed\n");
+ return -ENOMEM;
+ }
+
+ netdev->netdev_ops = &airoha_netdev_ops;
+ netdev->ethtool_ops = &airoha_ethtool_ops;
+ netdev->max_mtu = AIROHA_MAX_MTU;
+ netdev->watchdog_timeo = 5 * HZ;
+ netdev->hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM | NETIF_F_TSO6 |
+ NETIF_F_IPV6_CSUM | NETIF_F_SG | NETIF_F_TSO |
+ NETIF_F_HW_TC;
+ netdev->features |= netdev->hw_features;
+ netdev->vlan_features = netdev->hw_features;
+ netdev->dev.of_node = np;
+ SET_NETDEV_DEV(netdev, eth->dev);
+
+ /* reserve hw queues for HTB offloading */
+ err = netif_set_real_num_tx_queues(netdev, AIROHA_NUM_TX_RING);
+ if (err)
+ return err;
+
+ err = of_get_ethdev_address(np, netdev);
+ if (err) {
+ if (err == -EPROBE_DEFER)
+ return err;
+
+ eth_hw_addr_random(netdev);
+ dev_info(eth->dev, "generated random MAC address %pM\n",
+ netdev->dev_addr);
+ }
+
+ dev = netdev_priv(netdev);
+ dev->dev = netdev;
+ dev->port = port;
+ port->dev = dev;
+ dev->eth = eth;
+
+ return 0;
+}
+
static int airoha_alloc_gdm_port(struct airoha_eth *eth,
struct device_node *np)
{
const __be32 *id_ptr = of_get_property(np, "reg", NULL);
struct airoha_gdm_port *port;
- struct net_device *dev;
int err, p;
u32 id;
@@ -2975,53 +3063,22 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth,
return -EINVAL;
}
- dev = devm_alloc_etherdev_mqs(eth->dev, sizeof(*port),
- AIROHA_NUM_NETDEV_TX_RINGS,
- AIROHA_NUM_RX_RING);
- if (!dev) {
- dev_err(eth->dev, "alloc_etherdev failed\n");
+ port = devm_kzalloc(eth->dev, sizeof(*port), GFP_KERNEL);
+ if (!port)
return -ENOMEM;
- }
-
- dev->netdev_ops = &airoha_netdev_ops;
- dev->ethtool_ops = &airoha_ethtool_ops;
- dev->max_mtu = AIROHA_MAX_MTU;
- dev->watchdog_timeo = 5 * HZ;
- dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
- NETIF_F_TSO6 | NETIF_F_IPV6_CSUM |
- NETIF_F_SG | NETIF_F_TSO |
- NETIF_F_HW_TC;
- dev->features |= dev->hw_features;
- dev->vlan_features = dev->hw_features;
- dev->dev.of_node = np;
- SET_NETDEV_DEV(dev, eth->dev);
- /* reserve hw queues for HTB offloading */
- err = netif_set_real_num_tx_queues(dev, AIROHA_NUM_TX_RING);
- if (err)
- return err;
-
- err = of_get_ethdev_address(np, dev);
- if (err) {
- if (err == -EPROBE_DEFER)
- return err;
-
- eth_hw_addr_random(dev);
- dev_info(eth->dev, "generated random MAC address %pM\n",
- dev->dev_addr);
- }
-
- port = netdev_priv(dev);
u64_stats_init(&port->stats.syncp);
spin_lock_init(&port->stats.lock);
- port->eth = eth;
- port->dev = dev;
port->id = id;
/* XXX: Read nbq from DTS */
port->nbq = id == AIROHA_GDM3_IDX && airoha_is_7581(eth) ? 4 : 0;
eth->ports[p] = port;
- return airoha_metadata_dst_alloc(port);
+ err = airoha_metadata_dst_alloc(port);
+ if (err)
+ return err;
+
+ return airoha_alloc_gdm_device(eth, port, np);
}
static int airoha_register_gdm_devices(struct airoha_eth *eth)
@@ -3035,7 +3092,7 @@ static int airoha_register_gdm_devices(struct airoha_eth *eth)
if (!port)
continue;
- err = register_netdev(port->dev);
+ err = register_netdev(port->dev->dev);
if (err)
return err;
}
@@ -3144,12 +3201,14 @@ static int airoha_probe(struct platform_device *pdev)
for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
struct airoha_gdm_port *port = eth->ports[i];
+ struct airoha_gdm_dev *dev;
if (!port)
continue;
- if (port->dev->reg_state == NETREG_REGISTERED)
- unregister_netdev(port->dev);
+ dev = port->dev;
+ if (dev && dev->dev->reg_state == NETREG_REGISTERED)
+ unregister_netdev(dev->dev);
airoha_metadata_dst_free(port);
}
airoha_hw_cleanup(eth);
@@ -3170,11 +3229,14 @@ static void airoha_remove(struct platform_device *pdev)
for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
struct airoha_gdm_port *port = eth->ports[i];
+ struct airoha_gdm_dev *dev;
if (!port)
continue;
- unregister_netdev(port->dev);
+ dev = port->dev;
+ if (dev)
+ unregister_netdev(dev->dev);
airoha_metadata_dst_free(port);
}
airoha_hw_cleanup(eth);
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index d3781103abb5..c78cabbec753 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -535,10 +535,15 @@ struct airoha_qdma {
struct airoha_queue q_rx[AIROHA_NUM_RX_RING];
};
+struct airoha_gdm_dev {
+ struct airoha_gdm_port *port;
+ struct net_device *dev;
+ struct airoha_eth *eth;
+};
+
struct airoha_gdm_port {
struct airoha_qdma *qdma;
- struct airoha_eth *eth;
- struct net_device *dev;
+ struct airoha_gdm_dev *dev;
int id;
int nbq;
@@ -662,8 +667,8 @@ static inline bool airoha_is_7583(struct airoha_eth *eth)
}
int airoha_get_fe_port(struct airoha_gdm_port *port);
-bool airoha_is_valid_gdm_port(struct airoha_eth *eth,
- struct airoha_gdm_port *port);
+bool airoha_is_valid_gdm_dev(struct airoha_eth *eth,
+ struct airoha_gdm_dev *dev);
void airoha_ppe_set_cpu_port(struct airoha_gdm_port *port, u8 ppe_id,
u8 fport);
diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
index 26da519236bf..af7af4097b98 100644
--- a/drivers/net/ethernet/airoha/airoha_ppe.c
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -298,12 +298,12 @@ static void airoha_ppe_foe_set_bridge_addrs(struct airoha_foe_bridge *br,
static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth,
struct airoha_foe_entry *hwe,
- struct net_device *dev, int type,
+ struct net_device *netdev, int type,
struct airoha_flow_data *data,
int l4proto)
{
u32 qdata = FIELD_PREP(AIROHA_FOE_SHAPER_ID, 0x7f), ports_pad, val;
- int wlan_etype = -EINVAL, dsa_port = airoha_get_dsa_port(&dev);
+ int wlan_etype = -EINVAL, dsa_port = airoha_get_dsa_port(&netdev);
struct airoha_foe_mac_info_common *l2;
u8 smac_id = 0xf;
@@ -319,10 +319,11 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth,
hwe->ib1 = val;
val = FIELD_PREP(AIROHA_FOE_IB2_PORT_AG, 0x1f);
- if (dev) {
+ if (netdev) {
struct airoha_wdma_info info = {};
- if (!airoha_ppe_get_wdma_info(dev, data->eth.h_dest, &info)) {
+ if (!airoha_ppe_get_wdma_info(netdev, data->eth.h_dest,
+ &info)) {
val |= FIELD_PREP(AIROHA_FOE_IB2_NBQ, info.idx) |
FIELD_PREP(AIROHA_FOE_IB2_PSE_PORT,
FE_PSE_PORT_CDM4);
@@ -332,12 +333,14 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth,
FIELD_PREP(AIROHA_FOE_MAC_WDMA_WCID,
info.wcid);
} else {
- struct airoha_gdm_port *port = netdev_priv(dev);
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port;
u8 pse_port, channel;
- if (!airoha_is_valid_gdm_port(eth, port))
+ if (!airoha_is_valid_gdm_dev(eth, dev))
return -EINVAL;
+ port = dev->port;
if (dsa_port >= 0 || eth->ports[1])
pse_port = port->id == 4 ? FE_PSE_PORT_GDM4
: port->id;
@@ -1473,7 +1476,7 @@ void airoha_ppe_check_skb(struct airoha_ppe_dev *dev, struct sk_buff *skb,
void airoha_ppe_init_upd_mem(struct airoha_gdm_port *port)
{
struct airoha_eth *eth = port->qdma->eth;
- struct net_device *dev = port->dev;
+ struct net_device *dev = port->dev->dev;
const u8 *addr = dev->dev_addr;
u32 val;
--
2.54.0
^ permalink raw reply related [flat|nested] 22+ messages in thread
* [PATCH net-next v8 03/10] net: airoha: Move airoha_qdma pointer in airoha_gdm_dev struct
2026-05-19 8:57 [PATCH net-next v8 00/10] net: airoha: Support multiple net_devices connected to the same GDM port Lorenzo Bianconi
2026-05-19 8:57 ` [PATCH net-next v8 01/10] dt-bindings: net: airoha: Add GDM port ethernet child node Lorenzo Bianconi
2026-05-19 8:57 ` [PATCH net-next v8 02/10] net: airoha: Introduce airoha_gdm_dev struct Lorenzo Bianconi
@ 2026-05-19 8:57 ` Lorenzo Bianconi
2026-05-19 8:57 ` [PATCH net-next v8 04/10] net: airoha: Rely on airoha_gdm_dev pointer in airoha_is_lan_gdm_port() Lorenzo Bianconi
` (6 subsequent siblings)
9 siblings, 0 replies; 22+ messages in thread
From: Lorenzo Bianconi @ 2026-05-19 8:57 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Lorenzo Bianconi
Cc: Christian Marangi, Benjamin Larsson, linux-arm-kernel,
linux-mediatek, netdev, devicetree, Xuegang Lu
Move airoha_qdma pointer from airoha_gdm_port struct to airoha_gdm_dev
one since the QDMA block used depends on the particular net_device
WAN/LAN configuration and in the current codebase net_device pointer is
associated to airoha_gdm_dev struct.
This is a preliminary patch to support multiple net_devices connected
to the same GDM{3,4} port via an external hw arbiter.
Tested-by: Xuegang Lu <xuegang.lu@airoha.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
drivers/net/ethernet/airoha/airoha_eth.c | 105 +++++++++++++++----------------
drivers/net/ethernet/airoha/airoha_eth.h | 9 ++-
drivers/net/ethernet/airoha/airoha_ppe.c | 17 ++---
3 files changed, 64 insertions(+), 67 deletions(-)
diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 5335271ea865..9f93a1f28c89 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -71,9 +71,10 @@ static void airoha_qdma_irq_disable(struct airoha_irq_bank *irq_bank,
airoha_qdma_set_irqmask(irq_bank, index, mask, 0);
}
-static void airoha_set_macaddr(struct airoha_gdm_port *port, const u8 *addr)
+static void airoha_set_macaddr(struct airoha_gdm_dev *dev, const u8 *addr)
{
- struct airoha_eth *eth = port->qdma->eth;
+ struct airoha_gdm_port *port = dev->port;
+ struct airoha_eth *eth = dev->eth;
u32 val, reg;
reg = airoha_is_lan_gdm_port(port) ? REG_FE_LAN_MAC_H
@@ -85,7 +86,7 @@ static void airoha_set_macaddr(struct airoha_gdm_port *port, const u8 *addr)
airoha_fe_wr(eth, REG_FE_MAC_LMIN(reg), val);
airoha_fe_wr(eth, REG_FE_MAC_LMAX(reg), val);
- airoha_ppe_init_upd_mem(port);
+ airoha_ppe_init_upd_mem(dev);
}
static void airoha_set_gdm_port_fwd_cfg(struct airoha_eth *eth, u32 addr,
@@ -101,10 +102,10 @@ static void airoha_set_gdm_port_fwd_cfg(struct airoha_eth *eth, u32 addr,
FIELD_PREP(GDM_UCFQ_MASK, val));
}
-static int airoha_set_vip_for_gdm_port(struct airoha_gdm_port *port,
- bool enable)
+static int airoha_set_vip_for_gdm_port(struct airoha_gdm_dev *dev, bool enable)
{
- struct airoha_eth *eth = port->qdma->eth;
+ struct airoha_gdm_port *port = dev->port;
+ struct airoha_eth *eth = dev->eth;
u32 vip_port;
vip_port = eth->soc->ops.get_vip_port(port, port->nbq);
@@ -859,10 +860,13 @@ static void airoha_qdma_wake_netdev_txqs(struct airoha_queue *q)
if (!port)
continue;
- if (port->qdma != qdma)
+ dev = port->dev;
+ if (!dev)
+ continue;
+
+ if (dev->qdma != qdma)
continue;
- dev = port->dev;
for (j = 0; j < dev->dev->num_tx_queues; j++) {
if (airoha_qdma_get_txq(qdma, j) != qid)
continue;
@@ -1563,9 +1567,10 @@ static void airoha_qdma_stop_napi(struct airoha_qdma *qdma)
}
}
-static void airoha_update_hw_stats(struct airoha_gdm_port *port)
+static void airoha_update_hw_stats(struct airoha_gdm_dev *dev)
{
- struct airoha_eth *eth = port->qdma->eth;
+ struct airoha_gdm_port *port = dev->port;
+ struct airoha_eth *eth = dev->eth;
u32 val, i = 0;
spin_lock(&port->stats.lock);
@@ -1712,11 +1717,11 @@ static int airoha_dev_open(struct net_device *netdev)
int err, len = ETH_HLEN + netdev->mtu + ETH_FCS_LEN;
struct airoha_gdm_dev *dev = netdev_priv(netdev);
struct airoha_gdm_port *port = dev->port;
- struct airoha_qdma *qdma = port->qdma;
+ struct airoha_qdma *qdma = dev->qdma;
u32 pse_port = FE_PSE_PORT_PPE1;
netif_tx_start_all_queues(netdev);
- err = airoha_set_vip_for_gdm_port(port, true);
+ err = airoha_set_vip_for_gdm_port(dev, true);
if (err)
return err;
@@ -1752,11 +1757,11 @@ static int airoha_dev_stop(struct net_device *netdev)
{
struct airoha_gdm_dev *dev = netdev_priv(netdev);
struct airoha_gdm_port *port = dev->port;
- struct airoha_qdma *qdma = port->qdma;
+ struct airoha_qdma *qdma = dev->qdma;
int i;
netif_tx_disable(netdev);
- airoha_set_vip_for_gdm_port(port, false);
+ airoha_set_vip_for_gdm_port(dev, false);
for (i = 0; i < netdev->num_tx_queues; i++)
netdev_tx_reset_subqueue(netdev, i);
@@ -1782,21 +1787,21 @@ static int airoha_dev_stop(struct net_device *netdev)
static int airoha_dev_set_macaddr(struct net_device *netdev, void *p)
{
struct airoha_gdm_dev *dev = netdev_priv(netdev);
- struct airoha_gdm_port *port = dev->port;
int err;
err = eth_mac_addr(netdev, p);
if (err)
return err;
- airoha_set_macaddr(port, netdev->dev_addr);
+ airoha_set_macaddr(dev, netdev->dev_addr);
return 0;
}
-static int airoha_set_gdm2_loopback(struct airoha_gdm_port *port)
+static int airoha_set_gdm2_loopback(struct airoha_gdm_dev *dev)
{
- struct airoha_eth *eth = port->qdma->eth;
+ struct airoha_gdm_port *port = dev->port;
+ struct airoha_eth *eth = dev->eth;
u32 val, pse_port, chan;
int i, src_port;
@@ -1841,7 +1846,7 @@ static int airoha_set_gdm2_loopback(struct airoha_gdm_port *port)
__field_prep(SP_CPORT_MASK(val), FE_PSE_PORT_CDM2));
for (i = 0; i < eth->soc->num_ppe; i++)
- airoha_ppe_set_cpu_port(port, i, AIROHA_GDM2_IDX);
+ airoha_ppe_set_cpu_port(dev, i, AIROHA_GDM2_IDX);
if (port->id == AIROHA_GDM4_IDX && airoha_is_7581(eth)) {
u32 mask = FC_ID_OF_SRC_PORT_MASK(port->nbq);
@@ -1861,9 +1866,9 @@ static int airoha_dev_init(struct net_device *netdev)
int i;
/* QDMA0 is used for lan ports while QDMA1 is used for WAN ports */
- port->qdma = ð->qdma[!airoha_is_lan_gdm_port(port)];
- dev->dev->irq = port->qdma->irq_banks[0].irq;
- airoha_set_macaddr(port, netdev->dev_addr);
+ dev->qdma = ð->qdma[!airoha_is_lan_gdm_port(port)];
+ dev->dev->irq = dev->qdma->irq_banks[0].irq;
+ airoha_set_macaddr(dev, netdev->dev_addr);
switch (port->id) {
case AIROHA_GDM3_IDX:
@@ -1872,7 +1877,7 @@ static int airoha_dev_init(struct net_device *netdev)
if (!eth->ports[1]) {
int err;
- err = airoha_set_gdm2_loopback(port);
+ err = airoha_set_gdm2_loopback(dev);
if (err)
return err;
}
@@ -1882,8 +1887,7 @@ static int airoha_dev_init(struct net_device *netdev)
}
for (i = 0; i < eth->soc->num_ppe; i++)
- airoha_ppe_set_cpu_port(port, i,
- airoha_get_fe_port(port));
+ airoha_ppe_set_cpu_port(dev, i, airoha_get_fe_port(dev));
return 0;
}
@@ -1895,7 +1899,7 @@ static void airoha_dev_get_stats64(struct net_device *netdev,
struct airoha_gdm_port *port = dev->port;
unsigned int start;
- airoha_update_hw_stats(port);
+ airoha_update_hw_stats(dev);
do {
start = u64_stats_fetch_begin(&port->stats.syncp);
storage->rx_packets = port->stats.rx_ok_pkts;
@@ -1915,8 +1919,8 @@ static int airoha_dev_change_mtu(struct net_device *netdev, int mtu)
{
struct airoha_gdm_dev *dev = netdev_priv(netdev);
struct airoha_gdm_port *port = dev->port;
- struct airoha_eth *eth = port->qdma->eth;
u32 len = ETH_HLEN + mtu + ETH_FCS_LEN;
+ struct airoha_eth *eth = dev->eth;
airoha_fe_rmw(eth, REG_GDM_LEN_CFG(port->id),
GDM_LONG_LEN_MASK,
@@ -1990,10 +1994,10 @@ static u32 airoha_get_dsa_tag(struct sk_buff *skb, struct net_device *dev)
#endif
}
-int airoha_get_fe_port(struct airoha_gdm_port *port)
+int airoha_get_fe_port(struct airoha_gdm_dev *dev)
{
- struct airoha_qdma *qdma = port->qdma;
- struct airoha_eth *eth = qdma->eth;
+ struct airoha_gdm_port *port = dev->port;
+ struct airoha_eth *eth = dev->eth;
switch (eth->soc->version) {
case 0x7583:
@@ -2010,8 +2014,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
struct net_device *netdev)
{
struct airoha_gdm_dev *dev = netdev_priv(netdev);
- struct airoha_gdm_port *port = dev->port;
- struct airoha_qdma *qdma = port->qdma;
+ struct airoha_qdma *qdma = dev->qdma;
u32 nr_frags, tag, msg0, msg1, len;
struct airoha_queue_entry *e;
struct netdev_queue *txq;
@@ -2049,7 +2052,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
}
}
- fport = airoha_get_fe_port(port);
+ fport = airoha_get_fe_port(dev);
msg1 = FIELD_PREP(QDMA_ETH_TXMSG_FPORT_MASK, fport) |
FIELD_PREP(QDMA_ETH_TXMSG_METER_MASK, 0x7f);
@@ -2152,8 +2155,7 @@ static void airoha_ethtool_get_drvinfo(struct net_device *netdev,
struct ethtool_drvinfo *info)
{
struct airoha_gdm_dev *dev = netdev_priv(netdev);
- struct airoha_gdm_port *port = dev->port;
- struct airoha_eth *eth = port->qdma->eth;
+ struct airoha_eth *eth = dev->eth;
strscpy(info->driver, eth->dev->driver->name, sizeof(info->driver));
strscpy(info->bus_info, dev_name(eth->dev), sizeof(info->bus_info));
@@ -2166,7 +2168,7 @@ static void airoha_ethtool_get_mac_stats(struct net_device *netdev,
struct airoha_gdm_port *port = dev->port;
unsigned int start;
- airoha_update_hw_stats(port);
+ airoha_update_hw_stats(dev);
do {
start = u64_stats_fetch_begin(&port->stats.syncp);
stats->FramesTransmittedOK = port->stats.tx_ok_pkts;
@@ -2206,7 +2208,7 @@ airoha_ethtool_get_rmon_stats(struct net_device *netdev,
ARRAY_SIZE(hw_stats->rx_len) + 1);
*ranges = airoha_ethtool_rmon_ranges;
- airoha_update_hw_stats(port);
+ airoha_update_hw_stats(dev);
do {
int i;
@@ -2226,18 +2228,17 @@ static int airoha_qdma_set_chan_tx_sched(struct net_device *netdev,
const u16 *weights, u8 n_weights)
{
struct airoha_gdm_dev *dev = netdev_priv(netdev);
- struct airoha_gdm_port *port = dev->port;
int i;
for (i = 0; i < AIROHA_NUM_TX_RING; i++)
- airoha_qdma_clear(port->qdma, REG_QUEUE_CLOSE_CFG(channel),
+ airoha_qdma_clear(dev->qdma, REG_QUEUE_CLOSE_CFG(channel),
TXQ_DISABLE_CHAN_QUEUE_MASK(channel, i));
for (i = 0; i < n_weights; i++) {
u32 status;
int err;
- airoha_qdma_wr(port->qdma, REG_TXWRR_WEIGHT_CFG,
+ airoha_qdma_wr(dev->qdma, REG_TXWRR_WEIGHT_CFG,
TWRR_RW_CMD_MASK |
FIELD_PREP(TWRR_CHAN_IDX_MASK, channel) |
FIELD_PREP(TWRR_QUEUE_IDX_MASK, i) |
@@ -2245,13 +2246,12 @@ static int airoha_qdma_set_chan_tx_sched(struct net_device *netdev,
err = read_poll_timeout(airoha_qdma_rr, status,
status & TWRR_RW_CMD_DONE,
USEC_PER_MSEC, 10 * USEC_PER_MSEC,
- true, port->qdma,
- REG_TXWRR_WEIGHT_CFG);
+ true, dev->qdma, REG_TXWRR_WEIGHT_CFG);
if (err)
return err;
}
- airoha_qdma_rmw(port->qdma, REG_CHAN_QOS_MODE(channel >> 3),
+ airoha_qdma_rmw(dev->qdma, REG_CHAN_QOS_MODE(channel >> 3),
CHAN_QOS_MODE_MASK(channel),
__field_prep(CHAN_QOS_MODE_MASK(channel), mode));
@@ -2317,9 +2317,9 @@ static int airoha_qdma_get_tx_ets_stats(struct net_device *netdev, int channel,
struct airoha_gdm_dev *dev = netdev_priv(netdev);
struct airoha_gdm_port *port = dev->port;
- u64 cpu_tx_packets = airoha_qdma_rr(port->qdma,
+ u64 cpu_tx_packets = airoha_qdma_rr(dev->qdma,
REG_CNTR_VAL(channel << 1));
- u64 fwd_tx_packets = airoha_qdma_rr(port->qdma,
+ u64 fwd_tx_packets = airoha_qdma_rr(dev->qdma,
REG_CNTR_VAL((channel << 1) + 1));
u64 tx_packets = (cpu_tx_packets - port->cpu_tx_packets) +
(fwd_tx_packets - port->fwd_tx_packets);
@@ -2583,17 +2583,16 @@ static int airoha_qdma_set_tx_rate_limit(struct net_device *netdev,
u32 bucket_size)
{
struct airoha_gdm_dev *dev = netdev_priv(netdev);
- struct airoha_gdm_port *port = dev->port;
int i, err;
for (i = 0; i <= TRTCM_PEAK_MODE; i++) {
- err = airoha_qdma_set_trtcm_config(port->qdma, channel,
+ err = airoha_qdma_set_trtcm_config(dev->qdma, channel,
REG_EGRESS_TRTCM_CFG, i,
!!rate, TRTCM_METER_MODE);
if (err)
return err;
- err = airoha_qdma_set_trtcm_token_bucket(port->qdma, channel,
+ err = airoha_qdma_set_trtcm_token_bucket(dev->qdma, channel,
REG_EGRESS_TRTCM_CFG,
i, rate, bucket_size);
if (err)
@@ -2643,11 +2642,11 @@ static int airoha_tc_htb_alloc_leaf_queue(struct net_device *netdev,
return 0;
}
-static int airoha_qdma_set_rx_meter(struct airoha_gdm_port *port,
+static int airoha_qdma_set_rx_meter(struct airoha_gdm_dev *dev,
u32 rate, u32 bucket_size,
enum trtcm_unit_type unit_type)
{
- struct airoha_qdma *qdma = port->qdma;
+ struct airoha_qdma *qdma = dev->qdma;
int i;
for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) {
@@ -2726,7 +2725,6 @@ static int airoha_dev_tc_matchall(struct net_device *netdev,
{
enum trtcm_unit_type unit_type = TRTCM_BYTE_UNIT;
struct airoha_gdm_dev *dev = netdev_priv(netdev);
- struct airoha_gdm_port *port = dev->port;
u32 rate = 0, bucket_size = 0;
switch (f->command) {
@@ -2751,7 +2749,7 @@ static int airoha_dev_tc_matchall(struct net_device *netdev,
fallthrough;
}
case TC_CLSMATCHALL_DESTROY:
- return airoha_qdma_set_rx_meter(port, rate, bucket_size,
+ return airoha_qdma_set_rx_meter(dev, rate, bucket_size,
unit_type);
default:
return -EOPNOTSUPP;
@@ -2763,8 +2761,7 @@ static int airoha_dev_setup_tc_block_cb(enum tc_setup_type type,
{
struct net_device *netdev = cb_priv;
struct airoha_gdm_dev *dev = netdev_priv(netdev);
- struct airoha_gdm_port *port = dev->port;
- struct airoha_eth *eth = port->qdma->eth;
+ struct airoha_eth *eth = dev->eth;
if (!tc_can_offload(netdev))
return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index c78cabbec753..f1eea492217c 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -537,12 +537,12 @@ struct airoha_qdma {
struct airoha_gdm_dev {
struct airoha_gdm_port *port;
+ struct airoha_qdma *qdma;
struct net_device *dev;
struct airoha_eth *eth;
};
struct airoha_gdm_port {
- struct airoha_qdma *qdma;
struct airoha_gdm_dev *dev;
int id;
int nbq;
@@ -666,19 +666,18 @@ static inline bool airoha_is_7583(struct airoha_eth *eth)
return eth->soc->version == 0x7583;
}
-int airoha_get_fe_port(struct airoha_gdm_port *port);
+int airoha_get_fe_port(struct airoha_gdm_dev *dev);
bool airoha_is_valid_gdm_dev(struct airoha_eth *eth,
struct airoha_gdm_dev *dev);
-void airoha_ppe_set_cpu_port(struct airoha_gdm_port *port, u8 ppe_id,
- u8 fport);
+void airoha_ppe_set_cpu_port(struct airoha_gdm_dev *dev, u8 ppe_id, u8 fport);
bool airoha_ppe_is_enabled(struct airoha_eth *eth, int index);
void airoha_ppe_check_skb(struct airoha_ppe_dev *dev, struct sk_buff *skb,
u16 hash, bool rx_wlan);
int airoha_ppe_setup_tc_block_cb(struct airoha_ppe_dev *dev, void *type_data);
int airoha_ppe_init(struct airoha_eth *eth);
void airoha_ppe_deinit(struct airoha_eth *eth);
-void airoha_ppe_init_upd_mem(struct airoha_gdm_port *port);
+void airoha_ppe_init_upd_mem(struct airoha_gdm_dev *dev);
u32 airoha_ppe_get_total_num_entries(struct airoha_ppe *ppe);
struct airoha_foe_entry *airoha_ppe_foe_get_entry(struct airoha_ppe *ppe,
u32 hash);
diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
index af7af4097b98..22f5f1bae730 100644
--- a/drivers/net/ethernet/airoha/airoha_ppe.c
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -84,9 +84,9 @@ static u32 airoha_ppe_get_timestamp(struct airoha_ppe *ppe)
AIROHA_FOE_IB1_BIND_TIMESTAMP);
}
-void airoha_ppe_set_cpu_port(struct airoha_gdm_port *port, u8 ppe_id, u8 fport)
+void airoha_ppe_set_cpu_port(struct airoha_gdm_dev *dev, u8 ppe_id, u8 fport)
{
- struct airoha_qdma *qdma = port->qdma;
+ struct airoha_qdma *qdma = dev->qdma;
struct airoha_eth *eth = qdma->eth;
u8 qdma_id = qdma - ð->qdma[0];
u32 fe_cpu_port;
@@ -180,8 +180,8 @@ static void airoha_ppe_hw_init(struct airoha_ppe *ppe)
if (!port)
continue;
- airoha_ppe_set_cpu_port(port, i,
- airoha_get_fe_port(port));
+ airoha_ppe_set_cpu_port(port->dev, i,
+ airoha_get_fe_port(port->dev));
}
}
}
@@ -1473,11 +1473,12 @@ void airoha_ppe_check_skb(struct airoha_ppe_dev *dev, struct sk_buff *skb,
airoha_ppe_foe_insert_entry(ppe, skb, hash, rx_wlan);
}
-void airoha_ppe_init_upd_mem(struct airoha_gdm_port *port)
+void airoha_ppe_init_upd_mem(struct airoha_gdm_dev *dev)
{
- struct airoha_eth *eth = port->qdma->eth;
- struct net_device *dev = port->dev->dev;
- const u8 *addr = dev->dev_addr;
+ struct airoha_gdm_port *port = dev->port;
+ struct net_device *netdev = dev->dev;
+ struct airoha_eth *eth = dev->eth;
+ const u8 *addr = netdev->dev_addr;
u32 val;
val = (addr[2] << 24) | (addr[3] << 16) | (addr[4] << 8) | addr[5];
--
2.54.0
^ permalink raw reply related [flat|nested] 22+ messages in thread
* [PATCH net-next v8 04/10] net: airoha: Rely on airoha_gdm_dev pointer in airoha_is_lan_gdm_port()
2026-05-19 8:57 [PATCH net-next v8 00/10] net: airoha: Support multiple net_devices connected to the same GDM port Lorenzo Bianconi
` (2 preceding siblings ...)
2026-05-19 8:57 ` [PATCH net-next v8 03/10] net: airoha: Move airoha_qdma pointer in " Lorenzo Bianconi
@ 2026-05-19 8:57 ` Lorenzo Bianconi
2026-05-19 8:57 ` [PATCH net-next v8 05/10] net: airoha: Move qos_sq_bmap in airoha_gdm_dev struct Lorenzo Bianconi
` (5 subsequent siblings)
9 siblings, 0 replies; 22+ messages in thread
From: Lorenzo Bianconi @ 2026-05-19 8:57 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Lorenzo Bianconi
Cc: Christian Marangi, Benjamin Larsson, linux-arm-kernel,
linux-mediatek, netdev, devicetree, Xuegang Lu
Rename airoha_is_lan_gdm_port in airoha_is_lan_gdm_dev. Moreover, rely
on airoha_gdm_dev pointer in airoha_is_lan_gdm_dev() instead of
airoha_gdm_port one.
This is a preliminary patch to support multiple net_devices connected to
the same GDM{3,4} port via an external hw arbiter.
Tested-by: Xuegang Lu <xuegang.lu@airoha.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
drivers/net/ethernet/airoha/airoha_eth.c | 6 ++----
drivers/net/ethernet/airoha/airoha_eth.h | 4 +++-
drivers/net/ethernet/airoha/airoha_ppe.c | 2 +-
3 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 9f93a1f28c89..847f432b0a2b 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -73,12 +73,10 @@ static void airoha_qdma_irq_disable(struct airoha_irq_bank *irq_bank,
static void airoha_set_macaddr(struct airoha_gdm_dev *dev, const u8 *addr)
{
- struct airoha_gdm_port *port = dev->port;
struct airoha_eth *eth = dev->eth;
u32 val, reg;
- reg = airoha_is_lan_gdm_port(port) ? REG_FE_LAN_MAC_H
- : REG_FE_WAN_MAC_H;
+ reg = airoha_is_lan_gdm_dev(dev) ? REG_FE_LAN_MAC_H : REG_FE_WAN_MAC_H;
val = (addr[0] << 16) | (addr[1] << 8) | addr[2];
airoha_fe_wr(eth, reg, val);
@@ -1866,7 +1864,7 @@ static int airoha_dev_init(struct net_device *netdev)
int i;
/* QDMA0 is used for lan ports while QDMA1 is used for WAN ports */
- dev->qdma = ð->qdma[!airoha_is_lan_gdm_port(port)];
+ dev->qdma = ð->qdma[!airoha_is_lan_gdm_dev(dev)];
dev->dev->irq = dev->qdma->irq_banks[0].irq;
airoha_set_macaddr(dev, netdev->dev_addr);
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index f1eea492217c..f6f59d25abd9 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -647,8 +647,10 @@ static inline u16 airoha_qdma_get_txq(struct airoha_qdma *qdma, u16 qid)
return qid % ARRAY_SIZE(qdma->q_tx);
}
-static inline bool airoha_is_lan_gdm_port(struct airoha_gdm_port *port)
+static inline bool airoha_is_lan_gdm_dev(struct airoha_gdm_dev *dev)
{
+ struct airoha_gdm_port *port = dev->port;
+
/* GDM1 port on EN7581 SoC is connected to the lan dsa switch.
* GDM{2,3,4} can be used as wan port connected to an external
* phy module.
diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
index 22f5f1bae730..047141b2d6d8 100644
--- a/drivers/net/ethernet/airoha/airoha_ppe.c
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -362,7 +362,7 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth,
/* For downlink traffic consume SRAM memory for hw
* forwarding descriptors queue.
*/
- if (airoha_is_lan_gdm_port(port))
+ if (airoha_is_lan_gdm_dev(dev))
val |= AIROHA_FOE_IB2_FAST_PATH;
if (dsa_port >= 0)
val |= FIELD_PREP(AIROHA_FOE_IB2_NBQ,
--
2.54.0
^ permalink raw reply related [flat|nested] 22+ messages in thread
* [PATCH net-next v8 05/10] net: airoha: Move qos_sq_bmap in airoha_gdm_dev struct
2026-05-19 8:57 [PATCH net-next v8 00/10] net: airoha: Support multiple net_devices connected to the same GDM port Lorenzo Bianconi
` (3 preceding siblings ...)
2026-05-19 8:57 ` [PATCH net-next v8 04/10] net: airoha: Rely on airoha_gdm_dev pointer in airoha_is_lan_gdm_port() Lorenzo Bianconi
@ 2026-05-19 8:57 ` Lorenzo Bianconi
2026-05-20 8:59 ` sashiko-bot
2026-05-19 8:57 ` [PATCH net-next v8 06/10] net: airoha: Move {cpu,fwd}_tx_packets " Lorenzo Bianconi
` (4 subsequent siblings)
9 siblings, 1 reply; 22+ messages in thread
From: Lorenzo Bianconi @ 2026-05-19 8:57 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Lorenzo Bianconi
Cc: Christian Marangi, Benjamin Larsson, linux-arm-kernel,
linux-mediatek, netdev, devicetree
Since now multiple net_devices connected to different QDMA blocks can
share the same GDM port, qos_sq_bmap field can be overwritten with the
configuration obtained from a net_device connected to a different QDMA
block. In order to fix the issue move qos_sq_bmap field from
airoha_gdm_port struct to airoha_gdm_dev one.
Add qos_channel_map bitmap in airoha_qdma struct to track if a shared
QDMA channel is already in use by another net_device.
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
drivers/net/ethernet/airoha/airoha_eth.c | 58 ++++++++++++++++++++------------
drivers/net/ethernet/airoha/airoha_eth.h | 6 ++--
2 files changed, 40 insertions(+), 24 deletions(-)
diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 847f432b0a2b..594fbebcb12c 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -2600,30 +2600,40 @@ static int airoha_qdma_set_tx_rate_limit(struct net_device *netdev,
return 0;
}
-static int airoha_tc_htb_alloc_leaf_queue(struct net_device *netdev,
- struct tc_htb_qopt_offload *opt)
+static int airoha_tc_htb_modify_queue(struct net_device *dev,
+ struct tc_htb_qopt_offload *opt)
{
u32 channel = TC_H_MIN(opt->classid) % AIROHA_NUM_QOS_CHANNELS;
u32 rate = div_u64(opt->rate, 1000) << 3; /* kbps */
- int err, num_tx_queues = netdev->real_num_tx_queues;
- struct airoha_gdm_dev *dev = netdev_priv(netdev);
- struct airoha_gdm_port *port = dev->port;
if (opt->parent_classid != TC_HTB_CLASSID_ROOT) {
NL_SET_ERR_MSG_MOD(opt->extack, "invalid parent classid");
return -EINVAL;
}
- err = airoha_qdma_set_tx_rate_limit(netdev, channel, rate,
- opt->quantum);
- if (err) {
+ return airoha_qdma_set_tx_rate_limit(dev, channel, rate, opt->quantum);
+}
+
+static int airoha_tc_htb_alloc_leaf_queue(struct net_device *netdev,
+ struct tc_htb_qopt_offload *opt)
+{
+ u32 channel = TC_H_MIN(opt->classid) % AIROHA_NUM_QOS_CHANNELS;
+ int err, num_tx_queues = netdev->real_num_tx_queues;
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_qdma *qdma = dev->qdma;
+
+ /* Here we need to check the requested QDMA channel is not already
+ * in use by another net_device running on the same QDMA block.
+ */
+ if (test_and_set_bit(channel, qdma->qos_channel_map)) {
NL_SET_ERR_MSG_MOD(opt->extack,
- "failed configuring htb offload");
- return err;
+ "qdma qos channel already in use");
+ return -EBUSY;
}
- if (opt->command == TC_HTB_NODE_MODIFY)
- return 0;
+ err = airoha_tc_htb_modify_queue(netdev, opt);
+ if (err)
+ goto error;
err = netif_set_real_num_tx_queues(netdev, num_tx_queues + 1);
if (err) {
@@ -2631,13 +2641,17 @@ static int airoha_tc_htb_alloc_leaf_queue(struct net_device *netdev,
opt->quantum);
NL_SET_ERR_MSG_MOD(opt->extack,
"failed setting real_num_tx_queues");
- return err;
+ goto error;
}
- set_bit(channel, port->qos_sq_bmap);
+ set_bit(channel, dev->qos_sq_bmap);
opt->qid = AIROHA_NUM_TX_RING + channel;
return 0;
+error:
+ clear_bit(channel, qdma->qos_channel_map);
+
+ return err;
}
static int airoha_qdma_set_rx_meter(struct airoha_gdm_dev *dev,
@@ -2818,11 +2832,13 @@ static int airoha_dev_setup_tc_block(struct net_device *dev,
static void airoha_tc_remove_htb_queue(struct net_device *netdev, int queue)
{
struct airoha_gdm_dev *dev = netdev_priv(netdev);
- struct airoha_gdm_port *port = dev->port;
+ struct airoha_qdma *qdma = dev->qdma;
netif_set_real_num_tx_queues(netdev, netdev->real_num_tx_queues - 1);
airoha_qdma_set_tx_rate_limit(netdev, queue + 1, 0, 0);
- clear_bit(queue, port->qos_sq_bmap);
+
+ clear_bit(queue, qdma->qos_channel_map);
+ clear_bit(queue, dev->qos_sq_bmap);
}
static int airoha_tc_htb_delete_leaf_queue(struct net_device *netdev,
@@ -2830,9 +2846,8 @@ static int airoha_tc_htb_delete_leaf_queue(struct net_device *netdev,
{
u32 channel = TC_H_MIN(opt->classid) % AIROHA_NUM_QOS_CHANNELS;
struct airoha_gdm_dev *dev = netdev_priv(netdev);
- struct airoha_gdm_port *port = dev->port;
- if (!test_bit(channel, port->qos_sq_bmap)) {
+ if (!test_bit(channel, dev->qos_sq_bmap)) {
NL_SET_ERR_MSG_MOD(opt->extack, "invalid queue id");
return -EINVAL;
}
@@ -2845,10 +2860,9 @@ static int airoha_tc_htb_delete_leaf_queue(struct net_device *netdev,
static int airoha_tc_htb_destroy(struct net_device *netdev)
{
struct airoha_gdm_dev *dev = netdev_priv(netdev);
- struct airoha_gdm_port *port = dev->port;
int q;
- for_each_set_bit(q, port->qos_sq_bmap, AIROHA_NUM_QOS_CHANNELS)
+ for_each_set_bit(q, dev->qos_sq_bmap, AIROHA_NUM_QOS_CHANNELS)
airoha_tc_remove_htb_queue(netdev, q);
return 0;
@@ -2859,9 +2873,8 @@ static int airoha_tc_get_htb_get_leaf_queue(struct net_device *netdev,
{
u32 channel = TC_H_MIN(opt->classid) % AIROHA_NUM_QOS_CHANNELS;
struct airoha_gdm_dev *dev = netdev_priv(netdev);
- struct airoha_gdm_port *port = dev->port;
- if (!test_bit(channel, port->qos_sq_bmap)) {
+ if (!test_bit(channel, dev->qos_sq_bmap)) {
NL_SET_ERR_MSG_MOD(opt->extack, "invalid queue id");
return -EINVAL;
}
@@ -2880,6 +2893,7 @@ static int airoha_tc_setup_qdisc_htb(struct net_device *dev,
case TC_HTB_DESTROY:
return airoha_tc_htb_destroy(dev);
case TC_HTB_NODE_MODIFY:
+ return airoha_tc_htb_modify_queue(dev, opt);
case TC_HTB_LEAF_ALLOC_QUEUE:
return airoha_tc_htb_alloc_leaf_queue(dev, opt);
case TC_HTB_LEAF_DEL:
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index f6f59d25abd9..a308a770116b 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -533,6 +533,8 @@ struct airoha_qdma {
struct airoha_queue q_tx[AIROHA_NUM_TX_RING];
struct airoha_queue q_rx[AIROHA_NUM_RX_RING];
+
+ DECLARE_BITMAP(qos_channel_map, AIROHA_NUM_QOS_CHANNELS);
};
struct airoha_gdm_dev {
@@ -540,6 +542,8 @@ struct airoha_gdm_dev {
struct airoha_qdma *qdma;
struct net_device *dev;
struct airoha_eth *eth;
+
+ DECLARE_BITMAP(qos_sq_bmap, AIROHA_NUM_QOS_CHANNELS);
};
struct airoha_gdm_port {
@@ -549,8 +553,6 @@ struct airoha_gdm_port {
struct airoha_hw_stats stats;
- DECLARE_BITMAP(qos_sq_bmap, AIROHA_NUM_QOS_CHANNELS);
-
/* qos stats counters */
u64 cpu_tx_packets;
u64 fwd_tx_packets;
--
2.54.0
^ permalink raw reply related [flat|nested] 22+ messages in thread
* [PATCH net-next v8 06/10] net: airoha: Move {cpu,fwd}_tx_packets in airoha_gdm_dev struct
2026-05-19 8:57 [PATCH net-next v8 00/10] net: airoha: Support multiple net_devices connected to the same GDM port Lorenzo Bianconi
` (4 preceding siblings ...)
2026-05-19 8:57 ` [PATCH net-next v8 05/10] net: airoha: Move qos_sq_bmap in airoha_gdm_dev struct Lorenzo Bianconi
@ 2026-05-19 8:57 ` Lorenzo Bianconi
2026-05-19 8:57 ` [PATCH net-next v8 07/10] net: airoha: Support multiple net_devices for a single FE GDM port Lorenzo Bianconi
` (3 subsequent siblings)
9 siblings, 0 replies; 22+ messages in thread
From: Lorenzo Bianconi @ 2026-05-19 8:57 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Lorenzo Bianconi
Cc: Christian Marangi, Benjamin Larsson, linux-arm-kernel,
linux-mediatek, netdev, devicetree
Since now multiple net_devices connected to different QDMA blocks can
share the same GDM port, cpu_tx_packets and fwd_tx_packets fields can
be overwritten with the value from a different QDMA block. In order to
fix the issue move cpu_tx_packets and fwd_tx_packets fields from
airoha_gdm_port struct to airoha_gdm_dev one.
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
drivers/net/ethernet/airoha/airoha_eth.c | 16 +++++++---------
drivers/net/ethernet/airoha/airoha_eth.h | 7 +++----
2 files changed, 10 insertions(+), 13 deletions(-)
diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 594fbebcb12c..27b214ce2a4e 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -2313,19 +2313,17 @@ static int airoha_qdma_get_tx_ets_stats(struct net_device *netdev, int channel,
struct tc_ets_qopt_offload *opt)
{
struct airoha_gdm_dev *dev = netdev_priv(netdev);
- struct airoha_gdm_port *port = dev->port;
+ struct airoha_qdma *qdma = dev->qdma;
- u64 cpu_tx_packets = airoha_qdma_rr(dev->qdma,
- REG_CNTR_VAL(channel << 1));
- u64 fwd_tx_packets = airoha_qdma_rr(dev->qdma,
+ u64 cpu_tx_packets = airoha_qdma_rr(qdma, REG_CNTR_VAL(channel << 1));
+ u64 fwd_tx_packets = airoha_qdma_rr(qdma,
REG_CNTR_VAL((channel << 1) + 1));
- u64 tx_packets = (cpu_tx_packets - port->cpu_tx_packets) +
- (fwd_tx_packets - port->fwd_tx_packets);
+ u64 tx_packets = (cpu_tx_packets - dev->cpu_tx_packets) +
+ (fwd_tx_packets - dev->fwd_tx_packets);
_bstats_update(opt->stats.bstats, 0, tx_packets);
-
- port->cpu_tx_packets = cpu_tx_packets;
- port->fwd_tx_packets = fwd_tx_packets;
+ dev->cpu_tx_packets = cpu_tx_packets;
+ dev->fwd_tx_packets = fwd_tx_packets;
return 0;
}
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index a308a770116b..fbb50dc73af8 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -544,6 +544,9 @@ struct airoha_gdm_dev {
struct airoha_eth *eth;
DECLARE_BITMAP(qos_sq_bmap, AIROHA_NUM_QOS_CHANNELS);
+ /* qos stats counters */
+ u64 cpu_tx_packets;
+ u64 fwd_tx_packets;
};
struct airoha_gdm_port {
@@ -553,10 +556,6 @@ struct airoha_gdm_port {
struct airoha_hw_stats stats;
- /* qos stats counters */
- u64 cpu_tx_packets;
- u64 fwd_tx_packets;
-
struct metadata_dst *dsa_meta[AIROHA_MAX_DSA_PORTS];
};
--
2.54.0
^ permalink raw reply related [flat|nested] 22+ messages in thread
* [PATCH net-next v8 07/10] net: airoha: Support multiple net_devices for a single FE GDM port
2026-05-19 8:57 [PATCH net-next v8 00/10] net: airoha: Support multiple net_devices connected to the same GDM port Lorenzo Bianconi
` (5 preceding siblings ...)
2026-05-19 8:57 ` [PATCH net-next v8 06/10] net: airoha: Move {cpu,fwd}_tx_packets " Lorenzo Bianconi
@ 2026-05-19 8:57 ` Lorenzo Bianconi
2026-05-20 8:59 ` sashiko-bot
2026-05-19 8:57 ` [PATCH net-next v8 08/10] net: airoha: Do not stop GDM port if it is shared Lorenzo Bianconi
` (2 subsequent siblings)
9 siblings, 1 reply; 22+ messages in thread
From: Lorenzo Bianconi @ 2026-05-19 8:57 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Lorenzo Bianconi
Cc: Christian Marangi, Benjamin Larsson, linux-arm-kernel,
linux-mediatek, netdev, devicetree, Xuegang Lu
EN7581 or AN7583 SoCs support connecting multiple external SerDes (e.g.
Ethernet or USB SerDes) to GDM3 or GDM4 ports via a hw arbiter that
manages the traffic in a TDM manner. As a result multiple net_devices can
connect to the same GDM{3,4} port and there is a theoretical "1:n"
relation between GDM ports and net_devices.
┌─────────────────────────────────┐
│ │ ┌──────┐
│ P1 GDM1 ├────►MT7530│
│ │ └──────┘
│ │ ETH0 (DSA conduit)
│ │
│ PSE/FE │
│ │
│ │
│ │ ┌─────┐
│ P0 CDM1 ├────►QDMA0│
│ P4 P9 GDM4 │ └─────┘
└──┬─────────────────────────┬────┘
│ │
┌──▼──┐ ┌────▼────┐
│ PPE │ │ ARB │
└─────┘ └─┬─────┬─┘
│ │
┌──▼──┐┌─▼───┐
│ ETH ││ USB │
└─────┘└─────┘
ETH1 ETH2
Introduce support for multiple net_devices connected to the same Frame
Engine (FE) GDM port (GDM3 or GDM4) via an external hw arbiter.
Please note GDM1 or GDM2 does not support the connection with the external
arbiter.
Add get_dev_from_sport callback since EN7581 and AN7583 have different
logics for the net_device type connected to GDM3 or GDM4.
Tested-by: Xuegang Lu <xuegang.lu@airoha.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
drivers/net/ethernet/airoha/airoha_eth.c | 274 +++++++++++++++++++++++--------
drivers/net/ethernet/airoha/airoha_eth.h | 10 +-
drivers/net/ethernet/airoha/airoha_ppe.c | 13 +-
3 files changed, 228 insertions(+), 69 deletions(-)
diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 27b214ce2a4e..8d36ab6cd785 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -106,7 +106,7 @@ static int airoha_set_vip_for_gdm_port(struct airoha_gdm_dev *dev, bool enable)
struct airoha_eth *eth = dev->eth;
u32 vip_port;
- vip_port = eth->soc->ops.get_vip_port(port, port->nbq);
+ vip_port = eth->soc->ops.get_vip_port(port, dev->nbq);
if (enable) {
airoha_fe_set(eth, REG_FE_VIP_PORT_EN, vip_port);
airoha_fe_set(eth, REG_FE_IFC_PORT_EN, vip_port);
@@ -566,24 +566,26 @@ static int airoha_qdma_fill_rx_queue(struct airoha_queue *q)
return nframes;
}
-static int airoha_qdma_get_gdm_port(struct airoha_eth *eth,
- struct airoha_qdma_desc *desc)
+static struct airoha_gdm_dev *
+airoha_qdma_get_gdm_dev(struct airoha_eth *eth, struct airoha_qdma_desc *desc)
{
- u32 port, sport, msg1 = le32_to_cpu(READ_ONCE(desc->msg1));
+ struct airoha_gdm_port *port;
+ u16 p, d;
- sport = FIELD_GET(QDMA_ETH_RXMSG_SPORT_MASK, msg1);
- switch (sport) {
- case 0x10 ... 0x14:
- port = 0;
- break;
- case 0x2 ... 0x4:
- port = sport - 1;
- break;
- default:
- return -EINVAL;
- }
+ if (eth->soc->ops.get_dev_from_sport(desc, &p, &d))
+ return ERR_PTR(-ENODEV);
- return port >= ARRAY_SIZE(eth->ports) ? -EINVAL : port;
+ if (p >= ARRAY_SIZE(eth->ports))
+ return ERR_PTR(-ENODEV);
+
+ port = eth->ports[p];
+ if (!port)
+ return ERR_PTR(-ENODEV);
+
+ if (d >= ARRAY_SIZE(port->devs))
+ return ERR_PTR(-ENODEV);
+
+ return port->devs[d] ? port->devs[d] : ERR_PTR(-ENODEV);
}
static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
@@ -598,9 +600,8 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
struct airoha_queue_entry *e = &q->entry[q->tail];
struct airoha_qdma_desc *desc = &q->desc[q->tail];
u32 hash, reason, msg1, desc_ctrl;
- struct airoha_gdm_port *port;
- struct net_device *netdev;
- int data_len, len, p;
+ struct airoha_gdm_dev *dev;
+ int data_len, len;
struct page *page;
desc_ctrl = le32_to_cpu(READ_ONCE(desc->ctrl));
@@ -621,15 +622,10 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
if (!len || data_len < len)
goto free_frag;
- p = airoha_qdma_get_gdm_port(eth, desc);
- if (p < 0 || !eth->ports[p])
+ dev = airoha_qdma_get_gdm_dev(eth, desc);
+ if (IS_ERR(dev))
goto free_frag;
- port = eth->ports[p];
- if (!port->dev)
- goto free_frag;
-
- netdev = port->dev->dev;
if (!q->skb) { /* first buffer */
q->skb = napi_build_skb(e->buf - AIROHA_RX_HEADROOM,
q->buf_size);
@@ -639,8 +635,8 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
skb_reserve(q->skb, AIROHA_RX_HEADROOM);
__skb_put(q->skb, len);
skb_mark_for_recycle(q->skb);
- q->skb->dev = netdev;
- q->skb->protocol = eth_type_trans(q->skb, netdev);
+ q->skb->dev = dev->dev;
+ q->skb->protocol = eth_type_trans(q->skb, dev->dev);
q->skb->ip_summed = CHECKSUM_UNNECESSARY;
skb_record_rx_queue(q->skb, qid);
} else { /* scattered frame */
@@ -658,7 +654,9 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
if (FIELD_GET(QDMA_DESC_MORE_MASK, desc_ctrl))
continue;
- if (netdev_uses_dsa(netdev)) {
+ if (netdev_uses_dsa(dev->dev)) {
+ struct airoha_gdm_port *port = dev->port;
+
/* PPE module requires untagged packets to work
* properly and it provides DSA port index via the
* DMA descriptor. Report DSA tag to the DSA stack
@@ -852,24 +850,27 @@ static void airoha_qdma_wake_netdev_txqs(struct airoha_queue *q)
for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
struct airoha_gdm_port *port = eth->ports[i];
- struct airoha_gdm_dev *dev;
- int j;
+ int d;
if (!port)
continue;
- dev = port->dev;
- if (!dev)
- continue;
+ for (d = 0; d < ARRAY_SIZE(port->devs); d++) {
+ struct airoha_gdm_dev *dev = port->devs[d];
+ int j;
- if (dev->qdma != qdma)
- continue;
+ if (!dev)
+ continue;
- for (j = 0; j < dev->dev->num_tx_queues; j++) {
- if (airoha_qdma_get_txq(qdma, j) != qid)
+ if (dev->qdma != qdma)
continue;
- netif_wake_subqueue(dev->dev, j);
+ for (j = 0; j < dev->dev->num_tx_queues; j++) {
+ if (airoha_qdma_get_txq(qdma, j) != qid)
+ continue;
+
+ netif_wake_subqueue(dev->dev, j);
+ }
}
}
q->txq_stopped = false;
@@ -1830,7 +1831,7 @@ static int airoha_set_gdm2_loopback(struct airoha_gdm_dev *dev)
airoha_fe_clear(eth, REG_FE_VIP_PORT_EN, BIT(AIROHA_GDM2_IDX));
airoha_fe_clear(eth, REG_FE_IFC_PORT_EN, BIT(AIROHA_GDM2_IDX));
- src_port = eth->soc->ops.get_sport(port, port->nbq);
+ src_port = eth->soc->ops.get_sport(port, dev->nbq);
if (src_port < 0)
return src_port;
@@ -1847,7 +1848,7 @@ static int airoha_set_gdm2_loopback(struct airoha_gdm_dev *dev)
airoha_ppe_set_cpu_port(dev, i, AIROHA_GDM2_IDX);
if (port->id == AIROHA_GDM4_IDX && airoha_is_7581(eth)) {
- u32 mask = FC_ID_OF_SRC_PORT_MASK(port->nbq);
+ u32 mask = FC_ID_OF_SRC_PORT_MASK(dev->nbq);
airoha_fe_rmw(eth, REG_SRC_PORT_FC_MAP6, mask,
__field_prep(mask, AIROHA_GDM2_IDX));
@@ -2051,7 +2052,8 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
}
fport = airoha_get_fe_port(dev);
- msg1 = FIELD_PREP(QDMA_ETH_TXMSG_FPORT_MASK, fport) |
+ msg1 = FIELD_PREP(QDMA_ETH_TXMSG_NBOQ_MASK, dev->nbq) |
+ FIELD_PREP(QDMA_ETH_TXMSG_FPORT_MASK, fport) |
FIELD_PREP(QDMA_ETH_TXMSG_METER_MASK, 0x7f);
q = &qdma->q_tx[qid];
@@ -2981,12 +2983,15 @@ bool airoha_is_valid_gdm_dev(struct airoha_eth *eth,
for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
struct airoha_gdm_port *port = eth->ports[i];
+ int j;
if (!port)
continue;
- if (port->dev == dev)
- return true;
+ for (j = 0; j < ARRAY_SIZE(port->devs); j++) {
+ if (port->devs[j] == dev)
+ return true;
+ }
}
return false;
@@ -2994,10 +2999,11 @@ bool airoha_is_valid_gdm_dev(struct airoha_eth *eth,
static int airoha_alloc_gdm_device(struct airoha_eth *eth,
struct airoha_gdm_port *port,
- struct device_node *np)
+ int nbq, struct device_node *np)
{
- struct airoha_gdm_dev *dev;
struct net_device *netdev;
+ struct airoha_gdm_dev *dev;
+ u8 index;
int err;
netdev = devm_alloc_etherdev_mqs(eth->dev, sizeof(*dev),
@@ -3017,7 +3023,6 @@ static int airoha_alloc_gdm_device(struct airoha_eth *eth,
NETIF_F_HW_TC;
netdev->features |= netdev->hw_features;
netdev->vlan_features = netdev->hw_features;
- netdev->dev.of_node = np;
SET_NETDEV_DEV(netdev, eth->dev);
/* reserve hw queues for HTB offloading */
@@ -3035,11 +3040,25 @@ static int airoha_alloc_gdm_device(struct airoha_eth *eth,
netdev->dev_addr);
}
+ /* Allowed nbq for EN7581 on GDM3 port are 4 and 5 for PCIE0
+ * and PCIE1 respectively.
+ */
+ index = nbq;
+ if (index && airoha_is_7581(eth) && port->id == AIROHA_GDM3_IDX)
+ index -= 4;
+
+ if (index >= ARRAY_SIZE(port->devs) || port->devs[index]) {
+ dev_err(eth->dev, "invalid nbq id: %d\n", nbq);
+ return -EINVAL;
+ }
+
+ netdev->dev.of_node = of_node_get(np);
dev = netdev_priv(netdev);
dev->dev = netdev;
dev->port = port;
- port->dev = dev;
dev->eth = eth;
+ dev->nbq = nbq;
+ port->devs[index] = dev;
return 0;
}
@@ -3049,7 +3068,8 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth,
{
const __be32 *id_ptr = of_get_property(np, "reg", NULL);
struct airoha_gdm_port *port;
- int err, p;
+ struct device_node *node;
+ int err, nbq, p, d = 0;
u32 id;
if (!id_ptr) {
@@ -3077,15 +3097,51 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth,
u64_stats_init(&port->stats.syncp);
spin_lock_init(&port->stats.lock);
port->id = id;
- /* XXX: Read nbq from DTS */
- port->nbq = id == AIROHA_GDM3_IDX && airoha_is_7581(eth) ? 4 : 0;
eth->ports[p] = port;
err = airoha_metadata_dst_alloc(port);
if (err)
return err;
- return airoha_alloc_gdm_device(eth, port, np);
+ /* Default nbq value to ensure backward compatibility */
+ nbq = id == AIROHA_GDM3_IDX && airoha_is_7581(eth) ? 4 : 0;
+
+ for_each_child_of_node(np, node) {
+ /* Multiple external serdes connected to the FE GDM port via an
+ * external arbiter.
+ */
+ const __be32 *nbq_ptr;
+
+ if (!of_device_is_compatible(node, "airoha,eth-port"))
+ continue;
+
+ d++;
+ if (!of_device_is_available(node))
+ continue;
+
+ nbq_ptr = of_get_property(node, "reg", NULL);
+ if (!nbq_ptr) {
+ dev_err(eth->dev, "missing nbq id\n");
+ of_node_put(node);
+ return -EINVAL;
+ }
+
+ /* Verify the provided nbq parameter is valid */
+ nbq = be32_to_cpup(nbq_ptr);
+ err = eth->soc->ops.get_sport(port, nbq);
+ if (err < 0) {
+ of_node_put(node);
+ return err;
+ }
+
+ err = airoha_alloc_gdm_device(eth, port, nbq, node);
+ if (err) {
+ of_node_put(node);
+ return err;
+ }
+ }
+
+ return !d ? airoha_alloc_gdm_device(eth, port, nbq, np) : 0;
}
static int airoha_register_gdm_devices(struct airoha_eth *eth)
@@ -3094,14 +3150,22 @@ static int airoha_register_gdm_devices(struct airoha_eth *eth)
for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
struct airoha_gdm_port *port = eth->ports[i];
- int err;
+ int j;
if (!port)
continue;
- err = register_netdev(port->dev->dev);
- if (err)
- return err;
+ for (j = 0; j < ARRAY_SIZE(port->devs); j++) {
+ struct airoha_gdm_dev *dev = port->devs[j];
+ int err;
+
+ if (!dev)
+ continue;
+
+ err = register_netdev(dev->dev);
+ if (err)
+ return err;
+ }
}
set_bit(DEV_STATE_REGISTERED, ð->state);
@@ -3208,14 +3272,23 @@ static int airoha_probe(struct platform_device *pdev)
for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
struct airoha_gdm_port *port = eth->ports[i];
- struct airoha_gdm_dev *dev;
+ int j;
if (!port)
continue;
- dev = port->dev;
- if (dev && dev->dev->reg_state == NETREG_REGISTERED)
- unregister_netdev(dev->dev);
+ for (j = 0; j < ARRAY_SIZE(port->devs); j++) {
+ struct airoha_gdm_dev *dev = port->devs[j];
+ struct net_device *netdev;
+
+ if (!dev)
+ continue;
+
+ netdev = dev->dev;
+ if (netdev->reg_state == NETREG_REGISTERED)
+ unregister_netdev(netdev);
+ of_node_put(netdev->dev.of_node);
+ }
airoha_metadata_dst_free(port);
}
airoha_hw_cleanup(eth);
@@ -3236,14 +3309,22 @@ static void airoha_remove(struct platform_device *pdev)
for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
struct airoha_gdm_port *port = eth->ports[i];
- struct airoha_gdm_dev *dev;
+ int j;
if (!port)
continue;
- dev = port->dev;
- if (dev)
- unregister_netdev(dev->dev);
+ for (j = 0; j < ARRAY_SIZE(port->devs); j++) {
+ struct airoha_gdm_dev *dev = port->devs[j];
+ struct net_device *netdev;
+
+ if (!dev)
+ continue;
+
+ netdev = dev->dev;
+ unregister_netdev(netdev);
+ of_node_put(netdev->dev.of_node);
+ }
airoha_metadata_dst_free(port);
}
airoha_hw_cleanup(eth);
@@ -3306,6 +3387,39 @@ static u32 airoha_en7581_get_vip_port(struct airoha_gdm_port *port, int nbq)
return 0;
}
+static int airoha_en7581_get_dev_from_sport(struct airoha_qdma_desc *desc,
+ u16 *port, u16 *dev)
+{
+ u32 sport = FIELD_GET(QDMA_ETH_RXMSG_SPORT_MASK,
+ le32_to_cpu(READ_ONCE(desc->msg1)));
+
+ *dev = 0;
+ switch (sport) {
+ case 0x10 ... 0x14:
+ *port = 0; /* GDM1 */
+ break;
+ case 0x2 ... 0x4:
+ *port = sport - 1;
+ break;
+ case HSGMII_LAN_7581_PCIE1_SRCPORT:
+ *dev = 1;
+ fallthrough;
+ case HSGMII_LAN_7581_PCIE0_SRCPORT:
+ *port = 2; /* GDM3 */
+ break;
+ case HSGMII_LAN_7581_USB_SRCPORT:
+ *dev = 1;
+ fallthrough;
+ case HSGMII_LAN_7581_ETH_SRCPORT:
+ *port = 3; /* GDM4 */
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static const char * const an7583_xsi_rsts_names[] = {
"xsi-mac",
"hsi0-mac",
@@ -3355,6 +3469,36 @@ static u32 airoha_an7583_get_vip_port(struct airoha_gdm_port *port, int nbq)
return 0;
}
+static int airoha_an7583_get_dev_from_sport(struct airoha_qdma_desc *desc,
+ u16 *port, u16 *dev)
+{
+ u32 sport = FIELD_GET(QDMA_ETH_RXMSG_SPORT_MASK,
+ le32_to_cpu(READ_ONCE(desc->msg1)));
+
+ *dev = 0;
+ switch (sport) {
+ case 0x10 ... 0x14:
+ *port = 0; /* GDM1 */
+ break;
+ case 0x2 ... 0x4:
+ *port = sport - 1;
+ break;
+ case HSGMII_LAN_7583_ETH_SRCPORT:
+ *port = 2; /* GDM3 */
+ break;
+ case HSGMII_LAN_7583_USB_SRCPORT:
+ *dev = 1;
+ fallthrough;
+ case HSGMII_LAN_7583_PCIE_SRCPORT:
+ *port = 3; /* GDM4 */
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static const struct airoha_eth_soc_data en7581_soc_data = {
.version = 0x7581,
.xsi_rsts_names = en7581_xsi_rsts_names,
@@ -3363,6 +3507,7 @@ static const struct airoha_eth_soc_data en7581_soc_data = {
.ops = {
.get_sport = airoha_en7581_get_sport,
.get_vip_port = airoha_en7581_get_vip_port,
+ .get_dev_from_sport = airoha_en7581_get_dev_from_sport,
},
};
@@ -3374,6 +3519,7 @@ static const struct airoha_eth_soc_data an7583_soc_data = {
.ops = {
.get_sport = airoha_an7583_get_sport,
.get_vip_port = airoha_an7583_get_vip_port,
+ .get_dev_from_sport = airoha_an7583_get_dev_from_sport,
},
};
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index fbb50dc73af8..fc49f0049983 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -17,6 +17,7 @@
#include <net/dsa.h>
#define AIROHA_MAX_NUM_GDM_PORTS 4
+#define AIROHA_MAX_NUM_GDM_DEVS 2
#define AIROHA_MAX_NUM_QDMA 2
#define AIROHA_MAX_NUM_IRQ_BANKS 4
#define AIROHA_MAX_DSA_PORTS 7
@@ -540,19 +541,20 @@ struct airoha_qdma {
struct airoha_gdm_dev {
struct airoha_gdm_port *port;
struct airoha_qdma *qdma;
- struct net_device *dev;
struct airoha_eth *eth;
+ struct net_device *dev;
DECLARE_BITMAP(qos_sq_bmap, AIROHA_NUM_QOS_CHANNELS);
/* qos stats counters */
u64 cpu_tx_packets;
u64 fwd_tx_packets;
+
+ int nbq;
};
struct airoha_gdm_port {
- struct airoha_gdm_dev *dev;
+ struct airoha_gdm_dev *devs[AIROHA_MAX_NUM_GDM_DEVS];
int id;
- int nbq;
struct airoha_hw_stats stats;
@@ -588,6 +590,8 @@ struct airoha_eth_soc_data {
struct {
int (*get_sport)(struct airoha_gdm_port *port, int nbq);
u32 (*get_vip_port)(struct airoha_gdm_port *port, int nbq);
+ int (*get_dev_from_sport)(struct airoha_qdma_desc *desc,
+ u16 *port, u16 *dev);
} ops;
};
diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
index 047141b2d6d8..c4086d29d984 100644
--- a/drivers/net/ethernet/airoha/airoha_ppe.c
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -169,6 +169,7 @@ static void airoha_ppe_hw_init(struct airoha_ppe *ppe)
for (p = 0; p < ARRAY_SIZE(eth->ports); p++) {
struct airoha_gdm_port *port = eth->ports[p];
+ int j;
airoha_fe_rmw(eth, REG_PPE_MTU(i, p),
FP0_EGRESS_MTU_MASK |
@@ -180,8 +181,16 @@ static void airoha_ppe_hw_init(struct airoha_ppe *ppe)
if (!port)
continue;
- airoha_ppe_set_cpu_port(port->dev, i,
- airoha_get_fe_port(port->dev));
+ for (j = 0; j < ARRAY_SIZE(port->devs); j++) {
+ struct airoha_gdm_dev *dev = port->devs[j];
+ u8 fport;
+
+ if (!dev)
+ continue;
+
+ fport = airoha_get_fe_port(dev);
+ airoha_ppe_set_cpu_port(dev, i, fport);
+ }
}
}
}
--
2.54.0
^ permalink raw reply related [flat|nested] 22+ messages in thread
* [PATCH net-next v8 08/10] net: airoha: Do not stop GDM port if it is shared
2026-05-19 8:57 [PATCH net-next v8 00/10] net: airoha: Support multiple net_devices connected to the same GDM port Lorenzo Bianconi
` (6 preceding siblings ...)
2026-05-19 8:57 ` [PATCH net-next v8 07/10] net: airoha: Support multiple net_devices for a single FE GDM port Lorenzo Bianconi
@ 2026-05-19 8:57 ` Lorenzo Bianconi
2026-05-19 8:57 ` [PATCH net-next v8 09/10] net: airoha: Introduce WAN device flag Lorenzo Bianconi
2026-05-19 8:57 ` [PATCH net-next v8 10/10] net: airoha: Support multiple LAN/WAN interfaces for hw MAC address configuration Lorenzo Bianconi
9 siblings, 0 replies; 22+ messages in thread
From: Lorenzo Bianconi @ 2026-05-19 8:57 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Lorenzo Bianconi
Cc: Christian Marangi, Benjamin Larsson, linux-arm-kernel,
linux-mediatek, netdev, devicetree, Xuegang Lu
Theoretically, in the current codebase, two independent net_devices can
be connected to the same GDM port so we need to check the GDM port is not
used by any other running net_device before setting the forward
configuration to FE_PSE_PORT_DROP.
Moreover, always set in GDM_LONG_LEN_MASK field of REG_GDM_LEN_CFG
register the maximum MTU of all running net_devices connected to the same
GDM port.
Tested-by: Xuegang Lu <xuegang.lu@airoha.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
drivers/net/ethernet/airoha/airoha_eth.c | 59 +++++++++++++++++++++++++-------
drivers/net/ethernet/airoha/airoha_eth.h | 1 +
2 files changed, 48 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 8d36ab6cd785..15ad5a7edd43 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -1716,8 +1716,8 @@ static int airoha_dev_open(struct net_device *netdev)
int err, len = ETH_HLEN + netdev->mtu + ETH_FCS_LEN;
struct airoha_gdm_dev *dev = netdev_priv(netdev);
struct airoha_gdm_port *port = dev->port;
+ u32 cur_len, pse_port = FE_PSE_PORT_PPE1;
struct airoha_qdma *qdma = dev->qdma;
- u32 pse_port = FE_PSE_PORT_PPE1;
netif_tx_start_all_queues(netdev);
err = airoha_set_vip_for_gdm_port(dev, true);
@@ -1731,10 +1731,20 @@ static int airoha_dev_open(struct net_device *netdev)
airoha_fe_clear(qdma->eth, REG_GDM_INGRESS_CFG(port->id),
GDM_STAG_EN_MASK);
- airoha_fe_rmw(qdma->eth, REG_GDM_LEN_CFG(port->id),
- GDM_SHORT_LEN_MASK | GDM_LONG_LEN_MASK,
- FIELD_PREP(GDM_SHORT_LEN_MASK, 60) |
- FIELD_PREP(GDM_LONG_LEN_MASK, len));
+ cur_len = airoha_fe_get(qdma->eth, REG_GDM_LEN_CFG(port->id),
+ GDM_LONG_LEN_MASK);
+ if (!port->users || len > cur_len) {
+ /* Opening a sibling net_device with a larger MTU updates the
+ * MTU of already running devices. This is required to allow
+ * multiple net_devices with different MTUs to share the same
+ * GDM port.
+ */
+ airoha_fe_rmw(qdma->eth, REG_GDM_LEN_CFG(port->id),
+ GDM_SHORT_LEN_MASK | GDM_LONG_LEN_MASK,
+ FIELD_PREP(GDM_SHORT_LEN_MASK, 60) |
+ FIELD_PREP(GDM_LONG_LEN_MASK, len));
+ }
+ port->users++;
airoha_qdma_set(qdma, REG_QDMA_GLOBAL_CFG,
GLOBAL_CFG_TX_DMA_EN_MASK |
@@ -1752,6 +1762,30 @@ static int airoha_dev_open(struct net_device *netdev)
return 0;
}
+static void airoha_set_port_mtu(struct airoha_eth *eth,
+ struct airoha_gdm_port *port)
+{
+ u32 len = 0;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(port->devs); i++) {
+ struct airoha_gdm_dev *dev = port->devs[i];
+ struct net_device *netdev;
+
+ if (!dev)
+ continue;
+
+ netdev = dev->dev;
+ if (netif_running(netdev))
+ len = max_t(u32, len, netdev->mtu);
+ }
+ len += ETH_HLEN + ETH_FCS_LEN;
+
+ airoha_fe_rmw(eth, REG_GDM_LEN_CFG(port->id),
+ GDM_LONG_LEN_MASK,
+ FIELD_PREP(GDM_LONG_LEN_MASK, len));
+}
+
static int airoha_dev_stop(struct net_device *netdev)
{
struct airoha_gdm_dev *dev = netdev_priv(netdev);
@@ -1764,8 +1798,12 @@ static int airoha_dev_stop(struct net_device *netdev)
for (i = 0; i < netdev->num_tx_queues; i++)
netdev_tx_reset_subqueue(netdev, i);
- airoha_set_gdm_port_fwd_cfg(qdma->eth, REG_GDM_FWD_CFG(port->id),
- FE_PSE_PORT_DROP);
+ if (--port->users)
+ airoha_set_port_mtu(dev->eth, port);
+ else
+ airoha_set_gdm_port_fwd_cfg(qdma->eth,
+ REG_GDM_FWD_CFG(port->id),
+ FE_PSE_PORT_DROP);
if (atomic_dec_and_test(&qdma->users)) {
airoha_qdma_clear(qdma, REG_QDMA_GLOBAL_CFG,
@@ -1918,13 +1956,10 @@ static int airoha_dev_change_mtu(struct net_device *netdev, int mtu)
{
struct airoha_gdm_dev *dev = netdev_priv(netdev);
struct airoha_gdm_port *port = dev->port;
- u32 len = ETH_HLEN + mtu + ETH_FCS_LEN;
- struct airoha_eth *eth = dev->eth;
- airoha_fe_rmw(eth, REG_GDM_LEN_CFG(port->id),
- GDM_LONG_LEN_MASK,
- FIELD_PREP(GDM_LONG_LEN_MASK, len));
WRITE_ONCE(netdev->mtu, mtu);
+ if (port->users)
+ airoha_set_port_mtu(dev->eth, port);
return 0;
}
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index fc49f0049983..32633d84f7d2 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -555,6 +555,7 @@ struct airoha_gdm_dev {
struct airoha_gdm_port {
struct airoha_gdm_dev *devs[AIROHA_MAX_NUM_GDM_DEVS];
int id;
+ int users;
struct airoha_hw_stats stats;
--
2.54.0
^ permalink raw reply related [flat|nested] 22+ messages in thread
* [PATCH net-next v8 09/10] net: airoha: Introduce WAN device flag
2026-05-19 8:57 [PATCH net-next v8 00/10] net: airoha: Support multiple net_devices connected to the same GDM port Lorenzo Bianconi
` (7 preceding siblings ...)
2026-05-19 8:57 ` [PATCH net-next v8 08/10] net: airoha: Do not stop GDM port if it is shared Lorenzo Bianconi
@ 2026-05-19 8:57 ` Lorenzo Bianconi
2026-05-20 8:59 ` sashiko-bot
2026-05-19 8:57 ` [PATCH net-next v8 10/10] net: airoha: Support multiple LAN/WAN interfaces for hw MAC address configuration Lorenzo Bianconi
9 siblings, 1 reply; 22+ messages in thread
From: Lorenzo Bianconi @ 2026-05-19 8:57 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Lorenzo Bianconi
Cc: Christian Marangi, Benjamin Larsson, linux-arm-kernel,
linux-mediatek, netdev, devicetree, Xuegang Lu
Introduce WAN flag to specify if a given device is used to transmit/receive
WAN or LAN traffic. Current codebase supports specifying LAN/WAN device
configuration in ndo_init() callback during device bootstrap.
In order to consider setups where LAN configuration is used even for
GDM3/GDM4 devices, check airoha_is_lan_gdm_dev() to select pse_port in
airoha_ppe_foe_entry_prepare().
Please note after this patch, it will be possible to specify multiple LAN
devices but just a single WAN one. Please note this change is not visible
to the user since airoha_eth driver currently supports just the internal
phy available via the MT7530 DSA switch and there are no WAN interfaces
officially supported since PCS/external phy is not merged mainline yet
(it will be posted with following patches).
Tested-by: Xuegang Lu <xuegang.lu@airoha.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
drivers/net/ethernet/airoha/airoha_eth.c | 72 +++++++++++++++++++++++++-------
drivers/net/ethernet/airoha/airoha_eth.h | 13 +++---
drivers/net/ethernet/airoha/airoha_ppe.c | 2 +-
3 files changed, 65 insertions(+), 22 deletions(-)
diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 15ad5a7edd43..328f94fef2e2 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -1895,36 +1895,80 @@ static int airoha_set_gdm2_loopback(struct airoha_gdm_dev *dev)
return 0;
}
-static int airoha_dev_init(struct net_device *netdev)
+static struct airoha_gdm_dev *
+airoha_get_wan_gdm_dev(struct airoha_eth *eth)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
+ struct airoha_gdm_port *port = eth->ports[i];
+ int j;
+
+ if (!port)
+ continue;
+
+ for (j = 0; j < ARRAY_SIZE(port->devs); j++) {
+ struct airoha_gdm_dev *dev = port->devs[j];
+
+ if (dev && !airoha_is_lan_gdm_dev(dev))
+ return dev;
+ }
+ }
+
+ return NULL;
+}
+
+static void airoha_dev_set_qdma(struct airoha_gdm_dev *dev)
{
- struct airoha_gdm_dev *dev = netdev_priv(netdev);
- struct airoha_gdm_port *port = dev->port;
struct airoha_eth *eth = dev->eth;
int i;
/* QDMA0 is used for lan ports while QDMA1 is used for WAN ports */
dev->qdma = ð->qdma[!airoha_is_lan_gdm_dev(dev)];
dev->dev->irq = dev->qdma->irq_banks[0].irq;
- airoha_set_macaddr(dev, netdev->dev_addr);
+
+ for (i = 0; i < eth->soc->num_ppe; i++)
+ airoha_ppe_set_cpu_port(dev, i, airoha_get_fe_port(dev));
+}
+
+static int airoha_dev_init(struct net_device *netdev)
+{
+ struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct airoha_gdm_port *port = dev->port;
switch (port->id) {
case AIROHA_GDM3_IDX:
- case AIROHA_GDM4_IDX:
- /* If GDM2 is active we can't enable loopback */
- if (!eth->ports[1]) {
- int err;
+ case AIROHA_GDM4_IDX: {
+ struct airoha_eth *eth = dev->eth;
- err = airoha_set_gdm2_loopback(dev);
- if (err)
- return err;
- }
+ /* GDM2 supports a single net_device */
+ if (eth->ports[1] && eth->ports[1]->devs[0])
+ break;
+
+ if (airoha_get_wan_gdm_dev(eth))
+ break;
+
+ fallthrough;
+ }
+ case AIROHA_GDM2_IDX:
+ /* GDM2 is always used as wan */
+ dev->flags |= AIROHA_PRIV_F_WAN;
break;
default:
break;
}
- for (i = 0; i < eth->soc->num_ppe; i++)
- airoha_ppe_set_cpu_port(dev, i, airoha_get_fe_port(dev));
+ airoha_dev_set_qdma(dev);
+ airoha_set_macaddr(dev, netdev->dev_addr);
+
+ if (!airoha_is_lan_gdm_dev(dev) &&
+ (port->id == AIROHA_GDM3_IDX || port->id == AIROHA_GDM4_IDX)) {
+ int err;
+
+ err = airoha_set_gdm2_loopback(dev);
+ if (err)
+ return err;
+ }
return 0;
}
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index 32633d84f7d2..a2241520f2e2 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -538,6 +538,10 @@ struct airoha_qdma {
DECLARE_BITMAP(qos_channel_map, AIROHA_NUM_QOS_CHANNELS);
};
+enum airoha_priv_flags {
+ AIROHA_PRIV_F_WAN = BIT(0),
+};
+
struct airoha_gdm_dev {
struct airoha_gdm_port *port;
struct airoha_qdma *qdma;
@@ -549,6 +553,7 @@ struct airoha_gdm_dev {
u64 cpu_tx_packets;
u64 fwd_tx_packets;
+ u32 flags;
int nbq;
};
@@ -655,13 +660,7 @@ static inline u16 airoha_qdma_get_txq(struct airoha_qdma *qdma, u16 qid)
static inline bool airoha_is_lan_gdm_dev(struct airoha_gdm_dev *dev)
{
- struct airoha_gdm_port *port = dev->port;
-
- /* GDM1 port on EN7581 SoC is connected to the lan dsa switch.
- * GDM{2,3,4} can be used as wan port connected to an external
- * phy module.
- */
- return port->id == 1;
+ return !(dev->flags & AIROHA_PRIV_F_WAN);
}
static inline bool airoha_is_7581(struct airoha_eth *eth)
diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
index c4086d29d984..194cd50b2c74 100644
--- a/drivers/net/ethernet/airoha/airoha_ppe.c
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -350,7 +350,7 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth,
return -EINVAL;
port = dev->port;
- if (dsa_port >= 0 || eth->ports[1])
+ if (dsa_port >= 0 || airoha_is_lan_gdm_dev(dev))
pse_port = port->id == 4 ? FE_PSE_PORT_GDM4
: port->id;
else
--
2.54.0
^ permalink raw reply related [flat|nested] 22+ messages in thread
* [PATCH net-next v8 10/10] net: airoha: Support multiple LAN/WAN interfaces for hw MAC address configuration
2026-05-19 8:57 [PATCH net-next v8 00/10] net: airoha: Support multiple net_devices connected to the same GDM port Lorenzo Bianconi
` (8 preceding siblings ...)
2026-05-19 8:57 ` [PATCH net-next v8 09/10] net: airoha: Introduce WAN device flag Lorenzo Bianconi
@ 2026-05-19 8:57 ` Lorenzo Bianconi
2026-05-20 8:59 ` sashiko-bot
9 siblings, 1 reply; 22+ messages in thread
From: Lorenzo Bianconi @ 2026-05-19 8:57 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Lorenzo Bianconi
Cc: Christian Marangi, Benjamin Larsson, linux-arm-kernel,
linux-mediatek, netdev, devicetree, Madhur Agrawal
The EN7581 and AN7583 SoCs provide registers to configure hardware LAN/WAN
MAC addresses, used to determine whether received traffic is destined for
this host or should be forwarded to another device.
The SoC hardware design assumes all interfaces configured as LAN (or WAN)
share a common upper MAC address, which is programmed into the
REG_FE_{LAN,WAN}_MAC_H register. The lower bytes of 'local' addresses can
be expressed as a range via the REG_FE_MAC_LMIN and REG_FE_MAC_LMAX
registers.
Previously, only a single interface was considered when programming these
registers. Extend the logic to derive the correct minimum and maximum
values for REG_FE_MAC_LMIN/REG_FE_MAC_LMAX when two or more interfaces are
configured as LAN or WAN.
Tested-by: Madhur Agrawal <madhur.agrawal@airoha.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
drivers/net/ethernet/airoha/airoha_eth.c | 77 +++++++++++++++++++++++++++-----
drivers/net/ethernet/airoha/airoha_eth.h | 2 +-
drivers/net/ethernet/airoha/airoha_ppe.c | 4 +-
3 files changed, 68 insertions(+), 15 deletions(-)
diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 328f94fef2e2..9ae1ba433309 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -71,20 +71,69 @@ static void airoha_qdma_irq_disable(struct airoha_irq_bank *irq_bank,
airoha_qdma_set_irqmask(irq_bank, index, mask, 0);
}
-static void airoha_set_macaddr(struct airoha_gdm_dev *dev, const u8 *addr)
+static int airoha_set_macaddr(struct airoha_gdm_dev *dev, const u8 *addr)
{
+ u8 ref_addr[ETH_ALEN] __aligned(2);
struct airoha_eth *eth = dev->eth;
- u32 val, reg;
+ u32 reg, val, lmin, lmax;
+ int i;
+
+ eth_zero_addr(ref_addr);
+ lmin = (addr[3] << 16) | (addr[4] << 8) | addr[5];
+ lmax = lmin;
+
+ for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
+ struct airoha_gdm_port *port = eth->ports[i];
+ int j;
+
+ if (!port)
+ continue;
+
+ for (j = 0; j < ARRAY_SIZE(port->devs); j++) {
+ struct airoha_gdm_dev *iter_dev;
+ struct net_device *netdev;
+
+ iter_dev = port->devs[j];
+ if (!iter_dev || iter_dev == dev)
+ continue;
+
+ if (airoha_is_lan_gdm_dev(iter_dev) !=
+ airoha_is_lan_gdm_dev(dev))
+ continue;
+
+ netdev = iter_dev->dev;
+ if (netdev->reg_state != NETREG_REGISTERED)
+ continue;
+
+ ether_addr_copy(ref_addr, netdev->dev_addr);
+ val = (netdev->dev_addr[3] << 16) |
+ (netdev->dev_addr[4] << 8) | netdev->dev_addr[5];
+ if (val < lmin)
+ lmin = val;
+ if (val > lmax)
+ lmax = val;
+ }
+ }
+
+ if (!is_zero_ether_addr(ref_addr) && memcmp(ref_addr, addr, 3)) {
+ /* According to the HW design, hw mac address MS bits
+ * must be the same for each net_device with the same
+ * LAN/WAN configuration.
+ */
+ netdev_err(dev->dev, "wrong mac addr for shared GDM port\n");
+ return -EINVAL;
+ }
reg = airoha_is_lan_gdm_dev(dev) ? REG_FE_LAN_MAC_H : REG_FE_WAN_MAC_H;
val = (addr[0] << 16) | (addr[1] << 8) | addr[2];
airoha_fe_wr(eth, reg, val);
- val = (addr[3] << 16) | (addr[4] << 8) | addr[5];
- airoha_fe_wr(eth, REG_FE_MAC_LMIN(reg), val);
- airoha_fe_wr(eth, REG_FE_MAC_LMAX(reg), val);
+ airoha_fe_wr(eth, REG_FE_MAC_LMIN(reg), lmin);
+ airoha_fe_wr(eth, REG_FE_MAC_LMAX(reg), lmax);
- airoha_ppe_init_upd_mem(dev);
+ airoha_ppe_init_upd_mem(dev, addr);
+
+ return 0;
}
static void airoha_set_gdm_port_fwd_cfg(struct airoha_eth *eth, u32 addr,
@@ -1824,13 +1873,18 @@ static int airoha_dev_stop(struct net_device *netdev)
static int airoha_dev_set_macaddr(struct net_device *netdev, void *p)
{
struct airoha_gdm_dev *dev = netdev_priv(netdev);
+ struct sockaddr *addr = p;
int err;
- err = eth_mac_addr(netdev, p);
+ err = eth_prepare_mac_addr_change(netdev, p);
if (err)
return err;
- airoha_set_macaddr(dev, netdev->dev_addr);
+ err = airoha_set_macaddr(dev, addr->sa_data);
+ if (err)
+ return err;
+
+ eth_commit_mac_addr_change(netdev, p);
return 0;
}
@@ -1935,6 +1989,7 @@ static int airoha_dev_init(struct net_device *netdev)
{
struct airoha_gdm_dev *dev = netdev_priv(netdev);
struct airoha_gdm_port *port = dev->port;
+ int err;
switch (port->id) {
case AIROHA_GDM3_IDX:
@@ -1959,12 +2014,12 @@ static int airoha_dev_init(struct net_device *netdev)
}
airoha_dev_set_qdma(dev);
- airoha_set_macaddr(dev, netdev->dev_addr);
+ err = airoha_set_macaddr(dev, netdev->dev_addr);
+ if (err)
+ return err;
if (!airoha_is_lan_gdm_dev(dev) &&
(port->id == AIROHA_GDM3_IDX || port->id == AIROHA_GDM4_IDX)) {
- int err;
-
err = airoha_set_gdm2_loopback(dev);
if (err)
return err;
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index a2241520f2e2..364ca76eb3a6 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -684,7 +684,7 @@ void airoha_ppe_check_skb(struct airoha_ppe_dev *dev, struct sk_buff *skb,
int airoha_ppe_setup_tc_block_cb(struct airoha_ppe_dev *dev, void *type_data);
int airoha_ppe_init(struct airoha_eth *eth);
void airoha_ppe_deinit(struct airoha_eth *eth);
-void airoha_ppe_init_upd_mem(struct airoha_gdm_dev *dev);
+void airoha_ppe_init_upd_mem(struct airoha_gdm_dev *dev, const u8 *addr);
u32 airoha_ppe_get_total_num_entries(struct airoha_ppe *ppe);
struct airoha_foe_entry *airoha_ppe_foe_get_entry(struct airoha_ppe *ppe,
u32 hash);
diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
index 194cd50b2c74..531ce33528b9 100644
--- a/drivers/net/ethernet/airoha/airoha_ppe.c
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -1482,12 +1482,10 @@ void airoha_ppe_check_skb(struct airoha_ppe_dev *dev, struct sk_buff *skb,
airoha_ppe_foe_insert_entry(ppe, skb, hash, rx_wlan);
}
-void airoha_ppe_init_upd_mem(struct airoha_gdm_dev *dev)
+void airoha_ppe_init_upd_mem(struct airoha_gdm_dev *dev, const u8 *addr)
{
struct airoha_gdm_port *port = dev->port;
- struct net_device *netdev = dev->dev;
struct airoha_eth *eth = dev->eth;
- const u8 *addr = netdev->dev_addr;
u32 val;
val = (addr[2] << 24) | (addr[3] << 16) | (addr[4] << 8) | addr[5];
--
2.54.0
^ permalink raw reply related [flat|nested] 22+ messages in thread
* Re: [PATCH net-next v8 05/10] net: airoha: Move qos_sq_bmap in airoha_gdm_dev struct
2026-05-19 8:57 ` [PATCH net-next v8 05/10] net: airoha: Move qos_sq_bmap in airoha_gdm_dev struct Lorenzo Bianconi
@ 2026-05-20 8:59 ` sashiko-bot
2026-05-20 12:24 ` Lorenzo Bianconi
0 siblings, 1 reply; 22+ messages in thread
From: sashiko-bot @ 2026-05-20 8:59 UTC (permalink / raw)
To: Lorenzo Bianconi; +Cc: conor+dt, robh, devicetree
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [High] Off-by-one in airoha_tc_remove_htb_queue() clears the hardware rate limit of the wrong QDMA channel, corrupting cross-device shared state.
- [High] Dynamic real_num_tx_queues accounting causes out-of-bounds queue indices and bypasses hardware QoS entirely.
--
commit cfd982e85e1dc0ffc8dc017589e1128ecce7248e
Author: Lorenzo Bianconi <lorenzo@kernel.org>
net: airoha: Move qos_sq_bmap in airoha_gdm_dev struct
This commit moves the qos_sq_bmap field from airoha_gdm_port to
airoha_gdm_dev to prevent overwriting configurations from multiple
net_devices sharing the same GDM port. It also introduces
qos_channel_map in airoha_qdma to track shared QDMA channel usage.
> diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
> index 847f432b0a2b0..594fbebcb12ce 100644
> --- a/drivers/net/ethernet/airoha/airoha_eth.c
> +++ b/drivers/net/ethernet/airoha/airoha_eth.c
[ ... ]
> +static int airoha_tc_htb_alloc_leaf_queue(struct net_device *netdev,
> + struct tc_htb_qopt_offload *opt)
> +{
> + u32 channel = TC_H_MIN(opt->classid) % AIROHA_NUM_QOS_CHANNELS;
> + int err, num_tx_queues = netdev->real_num_tx_queues;
[ ... ]
> err = netif_set_real_num_tx_queues(netdev, num_tx_queues + 1);
> if (err) {
[ ... ]
> - set_bit(channel, port->qos_sq_bmap);
> + set_bit(channel, dev->qos_sq_bmap);
> opt->qid = AIROHA_NUM_TX_RING + channel;
Can this dynamic real_num_tx_queues accounting cause out-of-bounds queue
indices?
The driver tracks allocated QoS leaf queues by incrementing
dev->real_num_tx_queues by 1. However, the assigned hardware queue index is
derived from a sparse hash of the user-provided classid.
If a user allocates a non-sequential classid that hashes to a higher channel
number while having only a few queues active, won't opt->qid exceed the
incremented dev->real_num_tx_queues?
During transmission, would netdev_core_pick_tx() then detect this
out-of-bounds queue mapping, reset the queue index, and route the traffic to
the default ring 0, silently bypassing the hardware HTB rate limits?
[ ... ]
> static void airoha_tc_remove_htb_queue(struct net_device *netdev, int queue)
> {
> struct airoha_gdm_dev *dev = netdev_priv(netdev);
> - struct airoha_gdm_port *port = dev->port;
> + struct airoha_qdma *qdma = dev->qdma;
>
> netif_set_real_num_tx_queues(netdev, netdev->real_num_tx_queues - 1);
> airoha_qdma_set_tx_rate_limit(netdev, queue + 1, 0, 0);
Is there an off-by-one error when clearing the hardware rate limit here?
The queue + 1 offset causes it to clear the configuration of the adjacent
channel instead of the one actually being deleted, as the allocation path
uses channel without the offset.
Since this patch enables multiple net_devices to share the same QDMA block,
could clearing queue + 1 silently destroy the active hardware QoS
configuration belonging to a completely different net_device?
Does this also leave the rate limit for the actual deleted queue active,
and potentially cause an out-of-bounds register write if the deleted queue is
the maximum channel index (15)?
> - clear_bit(queue, port->qos_sq_bmap);
> +
> + clear_bit(queue, qdma->qos_channel_map);
> + clear_bit(queue, dev->qos_sq_bmap);
> }
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260519-airoha-eth-multi-serdes-v8-0-6bd70e329df6@kernel.org?part=5
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH net-next v8 02/10] net: airoha: Introduce airoha_gdm_dev struct
2026-05-19 8:57 ` [PATCH net-next v8 02/10] net: airoha: Introduce airoha_gdm_dev struct Lorenzo Bianconi
@ 2026-05-20 8:59 ` sashiko-bot
2026-05-20 12:25 ` Lorenzo Bianconi
0 siblings, 1 reply; 22+ messages in thread
From: sashiko-bot @ 2026-05-20 8:59 UTC (permalink / raw)
To: Lorenzo Bianconi; +Cc: conor+dt, devicetree, robh
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Potential deadlock in `airoha_update_hw_stats()` due to using `spin_lock()` instead of `spin_lock_bh()`.
--
commit 6823c137925a562390270eb1ce7967caaa011b7b
Author: Lorenzo Bianconi <lorenzo@kernel.org>
net: airoha: Introduce airoha_gdm_dev struct
This commit introduces the airoha_gdm_dev struct to collect net_device related
info, accommodating future support for connecting multiple external SerDes to
GDM3 or GDM4 ports via a hardware arbiter.
> diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
> index 5a027cc7ffcb1..5335271ea8654 100644
> --- a/drivers/net/ethernet/airoha/airoha_eth.c
> +++ b/drivers/net/ethernet/airoha/airoha_eth.c
[ ... ]
> @@ -1877,10 +1888,11 @@ static int airoha_dev_init(struct net_device *dev)
> return 0;
> }
>
> -static void airoha_dev_get_stats64(struct net_device *dev,
> +static void airoha_dev_get_stats64(struct net_device *netdev,
> struct rtnl_link_stats64 *storage)
> {
> - struct airoha_gdm_port *port = netdev_priv(dev);
> + struct airoha_gdm_dev *dev = netdev_priv(netdev);
> + struct airoha_gdm_port *port = dev->port;
> unsigned int start;
>
> airoha_update_hw_stats(port);
This isn't a bug introduced by this patch, but could this lead to a deadlock?
Because airoha_dev_get_stats64() is registered as the ndo_get_stats64 callback,
it can be called from both process context (e.g., via user-space netlink dumps)
and software interrupt context (BH) (e.g., via bonding or teaming drivers).
Looking at airoha_update_hw_stats(), it uses spin_lock() to protect the
hardware statistics update:
drivers/net/ethernet/airoha/airoha_eth.c:airoha_update_hw_stats() {
...
spin_lock(&port->stats.lock);
u64_stats_update_begin(&port->stats.syncp);
...
}
Because spin_lock() disables preemption but not softirqs, if a process context
call is interrupted by a BH call on the same CPU, the BH handler will attempt
to acquire the already-held lock.
Should this be upgraded to spin_lock_bh() to prevent a potential deadlock?
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260519-airoha-eth-multi-serdes-v8-0-6bd70e329df6@kernel.org?part=2
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH net-next v8 07/10] net: airoha: Support multiple net_devices for a single FE GDM port
2026-05-19 8:57 ` [PATCH net-next v8 07/10] net: airoha: Support multiple net_devices for a single FE GDM port Lorenzo Bianconi
@ 2026-05-20 8:59 ` sashiko-bot
2026-05-20 12:28 ` Lorenzo Bianconi
2026-05-20 12:33 ` Lorenzo Bianconi
0 siblings, 2 replies; 22+ messages in thread
From: sashiko-bot @ 2026-05-20 8:59 UTC (permalink / raw)
To: Lorenzo Bianconi; +Cc: robh, conor+dt, devicetree
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [High] Port-wide hardware configuration is improperly modified via per-net_device callbacks, breaking the newly introduced 1:N relationship.
- [High] Sequential initialization of multiple net_devices sharing a GDM port silently overwrites singleton hardware loopback and WAN configuration registers.
--
commit d922e17d3b113696fc139ac4b2b3ef81e2b9ad50
Author: Lorenzo Bianconi <lorenzo@kernel.org>
net: airoha: Support multiple net_devices for a single FE GDM port
This commit introduces support for multiple net_devices connected to the
same Frame Engine (FE) GDM port (GDM3 or GDM4) via an external hw arbiter.
It updates the airoha_gdm_port structure to hold an array of devices instead
of a single device.
> diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
> index fbb50dc73af84..fc49f0049983e 100644
> --- a/drivers/net/ethernet/airoha/airoha_eth.h
> +++ b/drivers/net/ethernet/airoha/airoha_eth.h
[ ... ]
> @@ -540,19 +541,20 @@ struct airoha_qdma {
> struct airoha_gdm_dev {
> struct airoha_gdm_port *port;
> struct airoha_qdma *qdma;
> - struct net_device *dev;
> struct airoha_eth *eth;
> + struct net_device *dev;
>
> DECLARE_BITMAP(qos_sq_bmap, AIROHA_NUM_QOS_CHANNELS);
> /* qos stats counters */
> u64 cpu_tx_packets;
> u64 fwd_tx_packets;
> +
> + int nbq;
> };
>
> struct airoha_gdm_port {
> - struct airoha_gdm_dev *dev;
> + struct airoha_gdm_dev *devs[AIROHA_MAX_NUM_GDM_DEVS];
> int id;
> - int nbq;
This introduces a 1:N relationship between a GDM port and net_devices, but
are the net_device lifecycle and MTU callbacks updated to account for shared
ports?
Looking at airoha_dev_stop(), the driver unconditionally drops all traffic
for the port:
airoha_dev_stop()
airoha_set_gdm_port_fwd_cfg(qdma->eth, REG_GDM_FWD_CFG(port->id), FE_PSE_PORT_DROP);
Since this modifies the forwarding configuration for the entire GDM port,
does stopping just one net_device silently drop all traffic for the port,
breaking any other active net_devices sharing it?
Similarly, airoha_dev_change_mtu() overwrites port-wide hardware registers
such as REG_GDM_LEN_CFG. Could this lower the port MTU while another device
still requires a larger MTU?
I note this regression is addressed later in the series by commit
646f1e7bb6021 (net: airoha: Do not stop GDM port if it is shared).
> diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
> index 27b214ce2a4ed..8d36ab6cd7854 100644
> --- a/drivers/net/ethernet/airoha/airoha_eth.c
> +++ b/drivers/net/ethernet/airoha/airoha_eth.c
[ ... ]
> @@ -1830,7 +1831,7 @@ static int airoha_set_gdm2_loopback(struct airoha_gdm_dev *dev)
> airoha_fe_clear(eth, REG_FE_VIP_PORT_EN, BIT(AIROHA_GDM2_IDX));
> airoha_fe_clear(eth, REG_FE_IFC_PORT_EN, BIT(AIROHA_GDM2_IDX));
>
> - src_port = eth->soc->ops.get_sport(port, port->nbq);
> + src_port = eth->soc->ops.get_sport(port, dev->nbq);
> if (src_port < 0)
> return src_port;
>
When multiple net_devices sharing a GDM port are sequentially initialized
via ndo_init (airoha_dev_init()), they unconditionally call
airoha_set_gdm2_loopback().
Inside this function, global singleton hardware registers are modified:
airoha_set_gdm2_loopback()
airoha_fe_rmw(eth, REG_FE_WAN_PORT,
WAN1_EN_MASK | WAN1_MASK | WAN0_MASK,
FIELD_PREP(WAN0_MASK, src_port));
Does initializing the second device on the same port silently overwrite
the hardware loopback and WAN configuration of the previously initialized
device?
I see this regression is resolved later in the series by commit
8a565b44990bb (net: airoha: Introduce WAN device flag).
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260519-airoha-eth-multi-serdes-v8-0-6bd70e329df6@kernel.org?part=7
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH net-next v8 09/10] net: airoha: Introduce WAN device flag
2026-05-19 8:57 ` [PATCH net-next v8 09/10] net: airoha: Introduce WAN device flag Lorenzo Bianconi
@ 2026-05-20 8:59 ` sashiko-bot
2026-05-20 12:46 ` Lorenzo Bianconi
0 siblings, 1 reply; 22+ messages in thread
From: sashiko-bot @ 2026-05-20 8:59 UTC (permalink / raw)
To: Lorenzo Bianconi; +Cc: conor+dt, robh, devicetree
Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
- [High] Hardware CPU port mapping overwrite when multiple devices share a GDM port.
- [High] Strict probe-order dependency leads to hardware misconfiguration and multiple WAN devices.
- [Medium] Global hardware MAC filter overwrite for multiple LAN devices.
--
commit 8a565b44990bb31355dea04fc03116c38aa783db
Author: Lorenzo Bianconi <lorenzo@kernel.org>
net: airoha: Introduce WAN device flag
This commit introduces a WAN flag to specify if a given device is used to
transmit or receive WAN or LAN traffic. It updates the initialization path
to select the proper QDMA and MAC address registers based on this role.
> diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
> index 15ad5a7edd439..328f94fef2e28 100644
> --- a/drivers/net/ethernet/airoha/airoha_eth.c
> +++ b/drivers/net/ethernet/airoha/airoha_eth.c
[ ... ]
> +static void airoha_dev_set_qdma(struct airoha_gdm_dev *dev)
> {
> struct airoha_eth *eth = dev->eth;
> int i;
>
> /* QDMA0 is used for lan ports while QDMA1 is used for WAN ports */
> dev->qdma = ð->qdma[!airoha_is_lan_gdm_dev(dev)];
> dev->dev->irq = dev->qdma->irq_banks[0].irq;
> +
> + for (i = 0; i < eth->soc->num_ppe; i++)
> + airoha_ppe_set_cpu_port(dev, i, airoha_get_fe_port(dev));
> +}
If multiple devices share a physical GDM port, and the first initialized
device assumes the WAN role, it will set the hardware per-physical-port
register to route inbound traffic to the WAN QDMA.
If a second device then initializes on the same physical port, it will
default to the LAN role.
Could this second initialization silently overwrite the previous hardware
mapping since the physical port is shared, effectively routing all traffic
to the LAN QDMA and starving the WAN device?
[ ... ]
> +static int airoha_dev_init(struct net_device *netdev)
> +{
> + struct airoha_gdm_dev *dev = netdev_priv(netdev);
> + struct airoha_gdm_port *port = dev->port;
>
> switch (port->id) {
> case AIROHA_GDM3_IDX:
> + case AIROHA_GDM4_IDX: {
> + struct airoha_eth *eth = dev->eth;
>
> + /* GDM2 supports a single net_device */
> + if (eth->ports[1] && eth->ports[1]->devs[0])
> + break;
Is there a strict probe-order dependency for these interfaces?
If GDM3 or GDM4 is probed before GDM2, eth->ports[1]->devs[0] will be NULL.
This leads GDM3/GDM4 to assume GDM2 is inactive, take the WAN role, and force
GDM2 into loopback mode.
Later, when GDM2 initializes:
> + case AIROHA_GDM2_IDX:
> + /* GDM2 is always used as wan */
> + dev->flags |= AIROHA_PRIV_F_WAN;
> break;
It unconditionally assigns itself the WAN role.
Does this probe ordering create multiple WAN devices and leave GDM2's
hardware silently misconfigured since its routing capabilities were disabled
by GDM3's loopback configuration?
> default:
> break;
> }
>
> + airoha_dev_set_qdma(dev);
> + airoha_set_macaddr(dev, netdev->dev_addr);
When setting the MAC address, airoha_set_macaddr() does the following:
static void airoha_set_macaddr(struct airoha_gdm_dev *dev, const u8 *addr)
{
...
reg = airoha_is_lan_gdm_dev(dev) ? REG_FE_LAN_MAC_H : REG_FE_WAN_MAC_H;
...
airoha_fe_wr(eth, reg, val);
}
Since REG_FE_LAN_MAC_H is a global forwarding engine register rather than
per-port, will initializing subsequent LAN devices overwrite the hardware
MAC filter configured by the first LAN device?
Might this cause the hardware to drop packets for LAN interfaces that do not
match the single overwritten MAC address?
(Note: This was observed to be fixed later in the series by commit "net:
airoha: Support multiple LAN/WAN interfaces for hw MAC address configuration",
but is mentioned here as it appears to introduce a regression in this commit.)
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260519-airoha-eth-multi-serdes-v8-0-6bd70e329df6@kernel.org?part=9
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH net-next v8 10/10] net: airoha: Support multiple LAN/WAN interfaces for hw MAC address configuration
2026-05-19 8:57 ` [PATCH net-next v8 10/10] net: airoha: Support multiple LAN/WAN interfaces for hw MAC address configuration Lorenzo Bianconi
@ 2026-05-20 8:59 ` sashiko-bot
2026-05-20 12:49 ` Lorenzo Bianconi
0 siblings, 1 reply; 22+ messages in thread
From: sashiko-bot @ 2026-05-20 8:59 UTC (permalink / raw)
To: Lorenzo Bianconi; +Cc: robh, devicetree, conor+dt
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [High] Driver probe fails on systems where MAC addresses are randomly generated.
- [High] Configuration deadlock prevents users from changing the MAC address OUI.
--
commit dbc4f298ffd475d67c32eeea98f201059b73194a
Author: Lorenzo Bianconi <lorenzo@kernel.org>
net: airoha: Support multiple LAN/WAN interfaces for hw MAC address configuration
The EN7581 and AN7583 SoCs provide registers to configure hardware LAN/WAN
MAC addresses. The hardware design assumes all interfaces configured as LAN
(or WAN) share a common upper MAC address. This patch extends the logic to
derive the correct minimum and maximum values when two or more interfaces
are configured.
> diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
> index 328f94fef2e28..9ae1ba4333097 100644
> --- a/drivers/net/ethernet/airoha/airoha_eth.c
> +++ b/drivers/net/ethernet/airoha/airoha_eth.c
> @@ -71,20 +71,69 @@ static void airoha_qdma_irq_disable(struct airoha_irq_bank *irq_bank,
> airoha_qdma_set_irqmask(irq_bank, index, mask, 0);
> }
>
> -static void airoha_set_macaddr(struct airoha_gdm_dev *dev, const u8 *addr)
> +static int airoha_set_macaddr(struct airoha_gdm_dev *dev, const u8 *addr)
> {
[ ... ]
> + if (netdev->reg_state != NETREG_REGISTERED)
> + continue;
> +
> + ether_addr_copy(ref_addr, netdev->dev_addr);
> + val = (netdev->dev_addr[3] << 16) |
> + (netdev->dev_addr[4] << 8) | netdev->dev_addr[5];
> + if (val < lmin)
> + lmin = val;
> + if (val > lmax)
> + lmax = val;
> + }
> + }
> +
> + if (!is_zero_ether_addr(ref_addr) && memcmp(ref_addr, addr, 3)) {
Does this strict OUI validation cause the driver probe to fail when MAC addresses
are randomly generated?
If a MAC address is not provided in the device tree, the driver generates a random
one via eth_hw_addr_random(). For multi-port configurations, each port receives an
independently generated random MAC address.
Since the upper 3 bytes of these random addresses will almost certainly differ,
when register_netdev() is called for the second port, its ndo_init callback
(airoha_dev_init) will invoke airoha_set_macaddr() and hit this check. Returning
-EINVAL will fail register_netdev() and abort the entire driver probe, leaving
the system without networking.
Does this also prevent users from changing the MAC address OUI?
When an administrator attempts to change the MAC address via standard userspace
tools, only one interface can be modified at a time. The driver will compare the
new MAC against the existing MAC of the other port.
If the MSBs differ, the change is rejected. This makes it impossible to atomically
change the OUI of both interfaces simultaneously, locking the MAC address OUI
to its initial probe-time value.
> + /* According to the HW design, hw mac address MS bits
> + * must be the same for each net_device with the same
> + * LAN/WAN configuration.
> + */
> + netdev_err(dev->dev, "wrong mac addr for shared GDM port\n");
> + return -EINVAL;
> + }
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260519-airoha-eth-multi-serdes-v8-0-6bd70e329df6@kernel.org?part=10
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH net-next v8 05/10] net: airoha: Move qos_sq_bmap in airoha_gdm_dev struct
2026-05-20 8:59 ` sashiko-bot
@ 2026-05-20 12:24 ` Lorenzo Bianconi
0 siblings, 0 replies; 22+ messages in thread
From: Lorenzo Bianconi @ 2026-05-20 12:24 UTC (permalink / raw)
To: sashiko-reviews; +Cc: conor+dt, robh, devicetree, netdev
[-- Attachment #1: Type: text/plain, Size: 3945 bytes --]
> Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
> - [High] Off-by-one in airoha_tc_remove_htb_queue() clears the hardware rate limit of the wrong QDMA channel, corrupting cross-device shared state.
> - [High] Dynamic real_num_tx_queues accounting causes out-of-bounds queue indices and bypasses hardware QoS entirely.
> --
>
> commit cfd982e85e1dc0ffc8dc017589e1128ecce7248e
> Author: Lorenzo Bianconi <lorenzo@kernel.org>
>
> net: airoha: Move qos_sq_bmap in airoha_gdm_dev struct
>
> This commit moves the qos_sq_bmap field from airoha_gdm_port to
> airoha_gdm_dev to prevent overwriting configurations from multiple
> net_devices sharing the same GDM port. It also introduces
> qos_channel_map in airoha_qdma to track shared QDMA channel usage.
>
> > diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
> > index 847f432b0a2b0..594fbebcb12ce 100644
> > --- a/drivers/net/ethernet/airoha/airoha_eth.c
> > +++ b/drivers/net/ethernet/airoha/airoha_eth.c
> [ ... ]
> > +static int airoha_tc_htb_alloc_leaf_queue(struct net_device *netdev,
> > + struct tc_htb_qopt_offload *opt)
> > +{
> > + u32 channel = TC_H_MIN(opt->classid) % AIROHA_NUM_QOS_CHANNELS;
> > + int err, num_tx_queues = netdev->real_num_tx_queues;
> [ ... ]
> > err = netif_set_real_num_tx_queues(netdev, num_tx_queues + 1);
> > if (err) {
> [ ... ]
> > - set_bit(channel, port->qos_sq_bmap);
> > + set_bit(channel, dev->qos_sq_bmap);
> > opt->qid = AIROHA_NUM_TX_RING + channel;
>
> Can this dynamic real_num_tx_queues accounting cause out-of-bounds queue
> indices?
>
> The driver tracks allocated QoS leaf queues by incrementing
> dev->real_num_tx_queues by 1. However, the assigned hardware queue index is
> derived from a sparse hash of the user-provided classid.
>
> If a user allocates a non-sequential classid that hashes to a higher channel
> number while having only a few queues active, won't opt->qid exceed the
> incremented dev->real_num_tx_queues?
>
> During transmission, would netdev_core_pick_tx() then detect this
> out-of-bounds queue mapping, reset the queue index, and route the traffic to
> the default ring 0, silently bypassing the hardware HTB rate limits?
As pointed out before this issue has not been introduced by this series and I
will fix it with a dedicated patch.
>
> [ ... ]
> > static void airoha_tc_remove_htb_queue(struct net_device *netdev, int queue)
> > {
> > struct airoha_gdm_dev *dev = netdev_priv(netdev);
> > - struct airoha_gdm_port *port = dev->port;
> > + struct airoha_qdma *qdma = dev->qdma;
> >
> > netif_set_real_num_tx_queues(netdev, netdev->real_num_tx_queues - 1);
> > airoha_qdma_set_tx_rate_limit(netdev, queue + 1, 0, 0);
>
> Is there an off-by-one error when clearing the hardware rate limit here?
>
> The queue + 1 offset causes it to clear the configuration of the adjacent
> channel instead of the one actually being deleted, as the allocation path
> uses channel without the offset.
>
> Since this patch enables multiple net_devices to share the same QDMA block,
> could clearing queue + 1 silently destroy the active hardware QoS
> configuration belonging to a completely different net_device?
>
> Does this also leave the rate limit for the actual deleted queue active,
> and potentially cause an out-of-bounds register write if the deleted queue is
> the maximum channel index (15)?
As pointed out before this issue has not been introduced by this series and I
will fix it with a dedicated patch.
Regards,
Lorenzo
>
> > - clear_bit(queue, port->qos_sq_bmap);
> > +
> > + clear_bit(queue, qdma->qos_channel_map);
> > + clear_bit(queue, dev->qos_sq_bmap);
> > }
>
> --
> Sashiko AI review · https://sashiko.dev/#/patchset/20260519-airoha-eth-multi-serdes-v8-0-6bd70e329df6@kernel.org?part=5
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH net-next v8 02/10] net: airoha: Introduce airoha_gdm_dev struct
2026-05-20 8:59 ` sashiko-bot
@ 2026-05-20 12:25 ` Lorenzo Bianconi
0 siblings, 0 replies; 22+ messages in thread
From: Lorenzo Bianconi @ 2026-05-20 12:25 UTC (permalink / raw)
To: sashiko-reviews; +Cc: conor+dt, devicetree, robh, netdev
[-- Attachment #1: Type: text/plain, Size: 2624 bytes --]
> Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
> - [High] Potential deadlock in `airoha_update_hw_stats()` due to using `spin_lock()` instead of `spin_lock_bh()`.
> --
>
> commit 6823c137925a562390270eb1ce7967caaa011b7b
> Author: Lorenzo Bianconi <lorenzo@kernel.org>
>
> net: airoha: Introduce airoha_gdm_dev struct
>
> This commit introduces the airoha_gdm_dev struct to collect net_device related
> info, accommodating future support for connecting multiple external SerDes to
> GDM3 or GDM4 ports via a hardware arbiter.
>
> > diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
> > index 5a027cc7ffcb1..5335271ea8654 100644
> > --- a/drivers/net/ethernet/airoha/airoha_eth.c
> > +++ b/drivers/net/ethernet/airoha/airoha_eth.c
>
> [ ... ]
>
> > @@ -1877,10 +1888,11 @@ static int airoha_dev_init(struct net_device *dev)
> > return 0;
> > }
> >
> > -static void airoha_dev_get_stats64(struct net_device *dev,
> > +static void airoha_dev_get_stats64(struct net_device *netdev,
> > struct rtnl_link_stats64 *storage)
> > {
> > - struct airoha_gdm_port *port = netdev_priv(dev);
> > + struct airoha_gdm_dev *dev = netdev_priv(netdev);
> > + struct airoha_gdm_port *port = dev->port;
> > unsigned int start;
> >
> > airoha_update_hw_stats(port);
>
> This isn't a bug introduced by this patch, but could this lead to a deadlock?
>
> Because airoha_dev_get_stats64() is registered as the ndo_get_stats64 callback,
> it can be called from both process context (e.g., via user-space netlink dumps)
> and software interrupt context (BH) (e.g., via bonding or teaming drivers).
>
> Looking at airoha_update_hw_stats(), it uses spin_lock() to protect the
> hardware statistics update:
>
> drivers/net/ethernet/airoha/airoha_eth.c:airoha_update_hw_stats() {
> ...
> spin_lock(&port->stats.lock);
> u64_stats_update_begin(&port->stats.syncp);
> ...
> }
>
> Because spin_lock() disables preemption but not softirqs, if a process context
> call is interrupted by a BH call on the same CPU, the BH handler will attempt
> to acquire the already-held lock.
>
> Should this be upgraded to spin_lock_bh() to prevent a potential deadlock?
As pointed out before, according to my understanding, ndo_get_stats64()
callback can't run from software interrupt context (BH), so this is not a real
issue.
Regards,
Lorenzo
>
> --
> Sashiko AI review · https://sashiko.dev/#/patchset/20260519-airoha-eth-multi-serdes-v8-0-6bd70e329df6@kernel.org?part=2
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH net-next v8 07/10] net: airoha: Support multiple net_devices for a single FE GDM port
2026-05-20 8:59 ` sashiko-bot
@ 2026-05-20 12:28 ` Lorenzo Bianconi
2026-05-20 12:33 ` Lorenzo Bianconi
1 sibling, 0 replies; 22+ messages in thread
From: Lorenzo Bianconi @ 2026-05-20 12:28 UTC (permalink / raw)
To: sashiko-reviews; +Cc: robh, conor+dt, devicetree, netdev
[-- Attachment #1: Type: text/plain, Size: 4379 bytes --]
> Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
> - [High] Port-wide hardware configuration is improperly modified via per-net_device callbacks, breaking the newly introduced 1:N relationship.
> - [High] Sequential initialization of multiple net_devices sharing a GDM port silently overwrites singleton hardware loopback and WAN configuration registers.
> --
>
> commit d922e17d3b113696fc139ac4b2b3ef81e2b9ad50
> Author: Lorenzo Bianconi <lorenzo@kernel.org>
>
> net: airoha: Support multiple net_devices for a single FE GDM port
>
> This commit introduces support for multiple net_devices connected to the
> same Frame Engine (FE) GDM port (GDM3 or GDM4) via an external hw arbiter.
> It updates the airoha_gdm_port structure to hold an array of devices instead
> of a single device.
>
> > diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
> > index fbb50dc73af84..fc49f0049983e 100644
> > --- a/drivers/net/ethernet/airoha/airoha_eth.h
> > +++ b/drivers/net/ethernet/airoha/airoha_eth.h
> [ ... ]
> > @@ -540,19 +541,20 @@ struct airoha_qdma {
> > struct airoha_gdm_dev {
> > struct airoha_gdm_port *port;
> > struct airoha_qdma *qdma;
> > - struct net_device *dev;
> > struct airoha_eth *eth;
> > + struct net_device *dev;
> >
> > DECLARE_BITMAP(qos_sq_bmap, AIROHA_NUM_QOS_CHANNELS);
> > /* qos stats counters */
> > u64 cpu_tx_packets;
> > u64 fwd_tx_packets;
> > +
> > + int nbq;
> > };
> >
> > struct airoha_gdm_port {
> > - struct airoha_gdm_dev *dev;
> > + struct airoha_gdm_dev *devs[AIROHA_MAX_NUM_GDM_DEVS];
> > int id;
> > - int nbq;
>
> This introduces a 1:N relationship between a GDM port and net_devices, but
> are the net_device lifecycle and MTU callbacks updated to account for shared
> ports?
>
> Looking at airoha_dev_stop(), the driver unconditionally drops all traffic
> for the port:
>
> airoha_dev_stop()
> airoha_set_gdm_port_fwd_cfg(qdma->eth, REG_GDM_FWD_CFG(port->id), FE_PSE_PORT_DROP);
>
> Since this modifies the forwarding configuration for the entire GDM port,
> does stopping just one net_device silently drop all traffic for the port,
> breaking any other active net_devices sharing it?
>
> Similarly, airoha_dev_change_mtu() overwrites port-wide hardware registers
> such as REG_GDM_LEN_CFG. Could this lower the port MTU while another device
> still requires a larger MTU?
>
> I note this regression is addressed later in the series by commit
> 646f1e7bb6021 (net: airoha: Do not stop GDM port if it is shared).
as pointed out here, this is resolved from a patch in the same series.
>
> > diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
> > index 27b214ce2a4ed..8d36ab6cd7854 100644
> > --- a/drivers/net/ethernet/airoha/airoha_eth.c
> > +++ b/drivers/net/ethernet/airoha/airoha_eth.c
> [ ... ]
> > @@ -1830,7 +1831,7 @@ static int airoha_set_gdm2_loopback(struct airoha_gdm_dev *dev)
> > airoha_fe_clear(eth, REG_FE_VIP_PORT_EN, BIT(AIROHA_GDM2_IDX));
> > airoha_fe_clear(eth, REG_FE_IFC_PORT_EN, BIT(AIROHA_GDM2_IDX));
> >
> > - src_port = eth->soc->ops.get_sport(port, port->nbq);
> > + src_port = eth->soc->ops.get_sport(port, dev->nbq);
> > if (src_port < 0)
> > return src_port;
> >
>
> When multiple net_devices sharing a GDM port are sequentially initialized
> via ndo_init (airoha_dev_init()), they unconditionally call
> airoha_set_gdm2_loopback().
>
> Inside this function, global singleton hardware registers are modified:
>
> airoha_set_gdm2_loopback()
> airoha_fe_rmw(eth, REG_FE_WAN_PORT,
> WAN1_EN_MASK | WAN1_MASK | WAN0_MASK,
> FIELD_PREP(WAN0_MASK, src_port));
>
> Does initializing the second device on the same port silently overwrite
> the hardware loopback and WAN configuration of the previously initialized
> device?
>
> I see this regression is resolved later in the series by commit
> 8a565b44990bb (net: airoha: Introduce WAN device flag).
as pointed out here, this is resolved from a patch in the same series.
Regards,
Lorenzo
>
> --
> Sashiko AI review · https://sashiko.dev/#/patchset/20260519-airoha-eth-multi-serdes-v8-0-6bd70e329df6@kernel.org?part=7
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH net-next v8 07/10] net: airoha: Support multiple net_devices for a single FE GDM port
2026-05-20 8:59 ` sashiko-bot
2026-05-20 12:28 ` Lorenzo Bianconi
@ 2026-05-20 12:33 ` Lorenzo Bianconi
1 sibling, 0 replies; 22+ messages in thread
From: Lorenzo Bianconi @ 2026-05-20 12:33 UTC (permalink / raw)
To: sashiko-reviews; +Cc: robh, conor+dt, devicetree, netdev
[-- Attachment #1: Type: text/plain, Size: 4970 bytes --]
On May 20, sashiko-bot@kernel.org wrote:
> Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
> - [High] Port-wide hardware configuration is improperly modified via per-net_device callbacks, breaking the newly introduced 1:N relationship.
> - [High] Sequential initialization of multiple net_devices sharing a GDM port silently overwrites singleton hardware loopback and WAN configuration registers.
> --
>
> commit d922e17d3b113696fc139ac4b2b3ef81e2b9ad50
> Author: Lorenzo Bianconi <lorenzo@kernel.org>
>
> net: airoha: Support multiple net_devices for a single FE GDM port
>
> This commit introduces support for multiple net_devices connected to the
> same Frame Engine (FE) GDM port (GDM3 or GDM4) via an external hw arbiter.
> It updates the airoha_gdm_port structure to hold an array of devices instead
> of a single device.
>
> > diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
> > index fbb50dc73af84..fc49f0049983e 100644
> > --- a/drivers/net/ethernet/airoha/airoha_eth.h
> > +++ b/drivers/net/ethernet/airoha/airoha_eth.h
> [ ... ]
> > @@ -540,19 +541,20 @@ struct airoha_qdma {
> > struct airoha_gdm_dev {
> > struct airoha_gdm_port *port;
> > struct airoha_qdma *qdma;
> > - struct net_device *dev;
> > struct airoha_eth *eth;
> > + struct net_device *dev;
> >
> > DECLARE_BITMAP(qos_sq_bmap, AIROHA_NUM_QOS_CHANNELS);
> > /* qos stats counters */
> > u64 cpu_tx_packets;
> > u64 fwd_tx_packets;
> > +
> > + int nbq;
> > };
> >
> > struct airoha_gdm_port {
> > - struct airoha_gdm_dev *dev;
> > + struct airoha_gdm_dev *devs[AIROHA_MAX_NUM_GDM_DEVS];
> > int id;
> > - int nbq;
>
> This introduces a 1:N relationship between a GDM port and net_devices, but
> are the net_device lifecycle and MTU callbacks updated to account for shared
> ports?
>
> Looking at airoha_dev_stop(), the driver unconditionally drops all traffic
> for the port:
>
> airoha_dev_stop()
> airoha_set_gdm_port_fwd_cfg(qdma->eth, REG_GDM_FWD_CFG(port->id), FE_PSE_PORT_DROP);
>
> Since this modifies the forwarding configuration for the entire GDM port,
> does stopping just one net_device silently drop all traffic for the port,
> breaking any other active net_devices sharing it?
>
> Similarly, airoha_dev_change_mtu() overwrites port-wide hardware registers
> such as REG_GDM_LEN_CFG. Could this lower the port MTU while another device
> still requires a larger MTU?
>
> I note this regression is addressed later in the series by commit
> 646f1e7bb6021 (net: airoha: Do not stop GDM port if it is shared).
>
> > diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
> > index 27b214ce2a4ed..8d36ab6cd7854 100644
> > --- a/drivers/net/ethernet/airoha/airoha_eth.c
> > +++ b/drivers/net/ethernet/airoha/airoha_eth.c
> [ ... ]
> > @@ -1830,7 +1831,7 @@ static int airoha_set_gdm2_loopback(struct airoha_gdm_dev *dev)
> > airoha_fe_clear(eth, REG_FE_VIP_PORT_EN, BIT(AIROHA_GDM2_IDX));
> > airoha_fe_clear(eth, REG_FE_IFC_PORT_EN, BIT(AIROHA_GDM2_IDX));
> >
> > - src_port = eth->soc->ops.get_sport(port, port->nbq);
> > + src_port = eth->soc->ops.get_sport(port, dev->nbq);
> > if (src_port < 0)
> > return src_port;
> >
>
> When multiple net_devices sharing a GDM port are sequentially initialized
> via ndo_init (airoha_dev_init()), they unconditionally call
> airoha_set_gdm2_loopback().
>
> Inside this function, global singleton hardware registers are modified:
>
> airoha_set_gdm2_loopback()
> airoha_fe_rmw(eth, REG_FE_WAN_PORT,
> WAN1_EN_MASK | WAN1_MASK | WAN0_MASK,
> FIELD_PREP(WAN0_MASK, src_port));
>
> Does initializing the second device on the same port silently overwrite
> the hardware loopback and WAN configuration of the previously initialized
> device?
>
> I see this regression is resolved later in the series by commit
> 8a565b44990bb (net: airoha: Introduce WAN device flag).
>
> --
> Sashiko AI review · https://sashiko.dev/#/patchset/20260519-airoha-eth-multi-serdes-v8-0-6bd70e329df6@kernel.org?part=7
Commenting on sashiko's report:
https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20260519-airoha-eth-multi-serdes-v8-0-6bd70e329df6%40kernel.org
- The per-port hardware MIB counters live on the GDM port, but
airoha_dev_get_stats64() returns dev->port->stats and
airoha_update_hw_stats() reads REG_FE_GDM_*_CNT_*(port->id) into that
shared structure followed by REG_FE_GDM_MIB_CLEAR. With two netdevs now
sharing a single GDM3 or GDM4 port, would both siblings report identical
combined byte/packet counters via ip -s link show, since there is no
per-dev SW counter to disambiguate the shared HW MIB?
- This issue will be fixed with a dedicated patch not in the series.
Regards,
Lorenzo
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH net-next v8 09/10] net: airoha: Introduce WAN device flag
2026-05-20 8:59 ` sashiko-bot
@ 2026-05-20 12:46 ` Lorenzo Bianconi
0 siblings, 0 replies; 22+ messages in thread
From: Lorenzo Bianconi @ 2026-05-20 12:46 UTC (permalink / raw)
To: sashiko-reviews; +Cc: conor+dt, robh, devicetree, netdev
[-- Attachment #1: Type: text/plain, Size: 2460 bytes --]
[...]
>
> [ ... ]
> > +static int airoha_dev_init(struct net_device *netdev)
> > +{
> > + struct airoha_gdm_dev *dev = netdev_priv(netdev);
> > + struct airoha_gdm_port *port = dev->port;
> >
> > switch (port->id) {
> > case AIROHA_GDM3_IDX:
> > + case AIROHA_GDM4_IDX: {
> > + struct airoha_eth *eth = dev->eth;
> >
> > + /* GDM2 supports a single net_device */
> > + if (eth->ports[1] && eth->ports[1]->devs[0])
> > + break;
>
> Is there a strict probe-order dependency for these interfaces?
>
> If GDM3 or GDM4 is probed before GDM2, eth->ports[1]->devs[0] will be NULL.
> This leads GDM3/GDM4 to assume GDM2 is inactive, take the WAN role, and force
> GDM2 into loopback mode.
>
> Later, when GDM2 initializes:
>
> > + case AIROHA_GDM2_IDX:
> > + /* GDM2 is always used as wan */
> > + dev->flags |= AIROHA_PRIV_F_WAN;
> > break;
>
> It unconditionally assigns itself the WAN role.
>
> Does this probe ordering create multiple WAN devices and leave GDM2's
> hardware silently misconfigured since its routing capabilities were disabled
> by GDM3's loopback configuration?
This is not a real issue since GDM2 is always registered before GDM3/GDM4.
>
> > default:
> > break;
> > }
> >
> > + airoha_dev_set_qdma(dev);
> > + airoha_set_macaddr(dev, netdev->dev_addr);
>
> When setting the MAC address, airoha_set_macaddr() does the following:
>
> static void airoha_set_macaddr(struct airoha_gdm_dev *dev, const u8 *addr)
> {
> ...
> reg = airoha_is_lan_gdm_dev(dev) ? REG_FE_LAN_MAC_H : REG_FE_WAN_MAC_H;
> ...
> airoha_fe_wr(eth, reg, val);
> }
>
> Since REG_FE_LAN_MAC_H is a global forwarding engine register rather than
> per-port, will initializing subsequent LAN devices overwrite the hardware
> MAC filter configured by the first LAN device?
>
> Might this cause the hardware to drop packets for LAN interfaces that do not
> match the single overwritten MAC address?
>
> (Note: This was observed to be fixed later in the series by commit "net:
> airoha: Support multiple LAN/WAN interfaces for hw MAC address configuration",
> but is mentioned here as it appears to introduce a regression in this commit.)
As pointed out here, this is resolved in a subsequent patch in the series.
Regards,
Lorenzo
>
> --
> Sashiko AI review · https://sashiko.dev/#/patchset/20260519-airoha-eth-multi-serdes-v8-0-6bd70e329df6@kernel.org?part=9
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH net-next v8 10/10] net: airoha: Support multiple LAN/WAN interfaces for hw MAC address configuration
2026-05-20 8:59 ` sashiko-bot
@ 2026-05-20 12:49 ` Lorenzo Bianconi
0 siblings, 0 replies; 22+ messages in thread
From: Lorenzo Bianconi @ 2026-05-20 12:49 UTC (permalink / raw)
To: sashiko-reviews; +Cc: robh, devicetree, conor+dt, netdev
[-- Attachment #1: Type: text/plain, Size: 3601 bytes --]
> Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
> - [High] Driver probe fails on systems where MAC addresses are randomly generated.
> - [High] Configuration deadlock prevents users from changing the MAC address OUI.
> --
>
> commit dbc4f298ffd475d67c32eeea98f201059b73194a
> Author: Lorenzo Bianconi <lorenzo@kernel.org>
>
> net: airoha: Support multiple LAN/WAN interfaces for hw MAC address configuration
>
> The EN7581 and AN7583 SoCs provide registers to configure hardware LAN/WAN
> MAC addresses. The hardware design assumes all interfaces configured as LAN
> (or WAN) share a common upper MAC address. This patch extends the logic to
> derive the correct minimum and maximum values when two or more interfaces
> are configured.
>
> > diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
> > index 328f94fef2e28..9ae1ba4333097 100644
> > --- a/drivers/net/ethernet/airoha/airoha_eth.c
> > +++ b/drivers/net/ethernet/airoha/airoha_eth.c
> > @@ -71,20 +71,69 @@ static void airoha_qdma_irq_disable(struct airoha_irq_bank *irq_bank,
> > airoha_qdma_set_irqmask(irq_bank, index, mask, 0);
> > }
> >
> > -static void airoha_set_macaddr(struct airoha_gdm_dev *dev, const u8 *addr)
> > +static int airoha_set_macaddr(struct airoha_gdm_dev *dev, const u8 *addr)
> > {
>
> [ ... ]
>
> > + if (netdev->reg_state != NETREG_REGISTERED)
> > + continue;
> > +
> > + ether_addr_copy(ref_addr, netdev->dev_addr);
> > + val = (netdev->dev_addr[3] << 16) |
> > + (netdev->dev_addr[4] << 8) | netdev->dev_addr[5];
> > + if (val < lmin)
> > + lmin = val;
> > + if (val > lmax)
> > + lmax = val;
> > + }
> > + }
> > +
> > + if (!is_zero_ether_addr(ref_addr) && memcmp(ref_addr, addr, 3)) {
>
> Does this strict OUI validation cause the driver probe to fail when MAC addresses
> are randomly generated?
>
> If a MAC address is not provided in the device tree, the driver generates a random
> one via eth_hw_addr_random(). For multi-port configurations, each port receives an
> independently generated random MAC address.
>
> Since the upper 3 bytes of these random addresses will almost certainly differ,
> when register_netdev() is called for the second port, its ndo_init callback
> (airoha_dev_init) will invoke airoha_set_macaddr() and hit this check. Returning
> -EINVAL will fail register_netdev() and abort the entire driver probe, leaving
> the system without networking.
>
> Does this also prevent users from changing the MAC address OUI?
>
> When an administrator attempts to change the MAC address via standard userspace
> tools, only one interface can be modified at a time. The driver will compare the
> new MAC against the existing MAC of the other port.
>
> If the MSBs differ, the change is rejected. This makes it impossible to atomically
> change the OUI of both interfaces simultaneously, locking the MAC address OUI
> to its initial probe-time value.
As pointed out before, this is a hw design requirement when multiple
net_devices are configured as LAN.
Regards,
Lorenzo
>
> > + /* According to the HW design, hw mac address MS bits
> > + * must be the same for each net_device with the same
> > + * LAN/WAN configuration.
> > + */
> > + netdev_err(dev->dev, "wrong mac addr for shared GDM port\n");
> > + return -EINVAL;
> > + }
>
> --
> Sashiko AI review · https://sashiko.dev/#/patchset/20260519-airoha-eth-multi-serdes-v8-0-6bd70e329df6@kernel.org?part=10
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]
^ permalink raw reply [flat|nested] 22+ messages in thread
end of thread, other threads:[~2026-05-20 12:49 UTC | newest]
Thread overview: 22+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-05-19 8:57 [PATCH net-next v8 00/10] net: airoha: Support multiple net_devices connected to the same GDM port Lorenzo Bianconi
2026-05-19 8:57 ` [PATCH net-next v8 01/10] dt-bindings: net: airoha: Add GDM port ethernet child node Lorenzo Bianconi
2026-05-19 8:57 ` [PATCH net-next v8 02/10] net: airoha: Introduce airoha_gdm_dev struct Lorenzo Bianconi
2026-05-20 8:59 ` sashiko-bot
2026-05-20 12:25 ` Lorenzo Bianconi
2026-05-19 8:57 ` [PATCH net-next v8 03/10] net: airoha: Move airoha_qdma pointer in " Lorenzo Bianconi
2026-05-19 8:57 ` [PATCH net-next v8 04/10] net: airoha: Rely on airoha_gdm_dev pointer in airoha_is_lan_gdm_port() Lorenzo Bianconi
2026-05-19 8:57 ` [PATCH net-next v8 05/10] net: airoha: Move qos_sq_bmap in airoha_gdm_dev struct Lorenzo Bianconi
2026-05-20 8:59 ` sashiko-bot
2026-05-20 12:24 ` Lorenzo Bianconi
2026-05-19 8:57 ` [PATCH net-next v8 06/10] net: airoha: Move {cpu,fwd}_tx_packets " Lorenzo Bianconi
2026-05-19 8:57 ` [PATCH net-next v8 07/10] net: airoha: Support multiple net_devices for a single FE GDM port Lorenzo Bianconi
2026-05-20 8:59 ` sashiko-bot
2026-05-20 12:28 ` Lorenzo Bianconi
2026-05-20 12:33 ` Lorenzo Bianconi
2026-05-19 8:57 ` [PATCH net-next v8 08/10] net: airoha: Do not stop GDM port if it is shared Lorenzo Bianconi
2026-05-19 8:57 ` [PATCH net-next v8 09/10] net: airoha: Introduce WAN device flag Lorenzo Bianconi
2026-05-20 8:59 ` sashiko-bot
2026-05-20 12:46 ` Lorenzo Bianconi
2026-05-19 8:57 ` [PATCH net-next v8 10/10] net: airoha: Support multiple LAN/WAN interfaces for hw MAC address configuration Lorenzo Bianconi
2026-05-20 8:59 ` sashiko-bot
2026-05-20 12:49 ` Lorenzo Bianconi
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox