* [PATCH v12 nf-next 5/7] netfilter: nft_flow_offload: nft_flow_offload_eval: check thoff==0
From: Eric Woudstra @ 2026-07-07 9:10 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Pablo Neira Ayuso, Florian Westphal,
Phil Sutter, Nikolay Aleksandrov, Ido Schimmel, Kuniyuki Iwashima,
Stanislav Fomichev, Samiullah Khawaja, Hangbin Liu, Krishna Kumar,
Martin Karsten
Cc: netdev, netfilter-devel, bridge, Eric Woudstra
In-Reply-To: <20260707091045.967678-1-ericwouds@gmail.com>
In case of flow through bridge, when evaluating traffic with double vlan,
pppoe and pppoe-in-q. In this case thoff will be valid only when meta has
been processed. If meta was not processed in nftables, thoff is zero.
Signed-off-by: Eric Woudstra <ericwouds@gmail.com>
---
net/netfilter/nft_flow_offload.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index f8c7f9f631e48..4f68fb64f1657 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -59,7 +59,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
struct flow_offload *flow;
enum ip_conntrack_dir dir;
struct nf_conn *ct;
- int ret;
+ int ret, thoff;
if (nft_flow_offload_skip(pkt->skb, nft_pf(pkt)))
goto out;
@@ -70,8 +70,11 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) {
case IPPROTO_TCP:
- tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt),
- sizeof(_tcph), &_tcph);
+ thoff = nft_thoff(pkt);
+ if (thoff == 0)
+ goto out;
+ tcph = skb_header_pointer(pkt->skb, thoff, sizeof(_tcph),
+ &_tcph);
if (unlikely(!tcph || tcph->fin || tcph->rst ||
!nf_conntrack_tcp_established(ct)))
goto out;
--
2.53.0
^ permalink raw reply related
* [PATCH v12 nf-next 4/7] netfilter: nf_flow_table_inet: Add nf_flowtable_type flowtable_bridge
From: Eric Woudstra @ 2026-07-07 9:10 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Pablo Neira Ayuso, Florian Westphal,
Phil Sutter, Nikolay Aleksandrov, Ido Schimmel, Kuniyuki Iwashima,
Stanislav Fomichev, Samiullah Khawaja, Hangbin Liu, Krishna Kumar,
Martin Karsten
Cc: netdev, netfilter-devel, bridge, Eric Woudstra
In-Reply-To: <20260707091045.967678-1-ericwouds@gmail.com>
This will allow a flowtable to be added to the nft bridge family.
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Eric Woudstra <ericwouds@gmail.com>
---
net/netfilter/nf_flow_table_inet.c | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c
index b0f1991719324..80b238196f29b 100644
--- a/net/netfilter/nf_flow_table_inet.c
+++ b/net/netfilter/nf_flow_table_inet.c
@@ -65,6 +65,16 @@ static int nf_flow_rule_route_inet(struct net *net,
return err;
}
+static struct nf_flowtable_type flowtable_bridge = {
+ .family = NFPROTO_BRIDGE,
+ .init = nf_flow_table_init,
+ .setup = nf_flow_table_offload_setup,
+ .action = nf_flow_rule_bridge,
+ .free = nf_flow_table_free,
+ .hook = nf_flow_offload_inet_hook,
+ .owner = THIS_MODULE,
+};
+
static struct nf_flowtable_type flowtable_inet = {
.family = NFPROTO_INET,
.init = nf_flow_table_init,
@@ -97,6 +107,7 @@ static struct nf_flowtable_type flowtable_ipv6 = {
static int __init nf_flow_inet_module_init(void)
{
+ nft_register_flowtable_type(&flowtable_bridge);
nft_register_flowtable_type(&flowtable_ipv4);
nft_register_flowtable_type(&flowtable_ipv6);
nft_register_flowtable_type(&flowtable_inet);
@@ -109,6 +120,7 @@ static void __exit nf_flow_inet_module_exit(void)
nft_unregister_flowtable_type(&flowtable_inet);
nft_unregister_flowtable_type(&flowtable_ipv6);
nft_unregister_flowtable_type(&flowtable_ipv4);
+ nft_unregister_flowtable_type(&flowtable_bridge);
}
module_init(nf_flow_inet_module_init);
@@ -118,5 +130,6 @@ MODULE_LICENSE("GPL");
MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
MODULE_ALIAS_NF_FLOWTABLE(AF_INET);
MODULE_ALIAS_NF_FLOWTABLE(AF_INET6);
+MODULE_ALIAS_NF_FLOWTABLE(AF_BRIDGE);
MODULE_ALIAS_NF_FLOWTABLE(1); /* NFPROTO_INET */
MODULE_DESCRIPTION("Netfilter flow table mixed IPv4/IPv6 module");
--
2.53.0
^ permalink raw reply related
* [PATCH v12 nf-next 3/7] netfilter: nf_flow_table_offload: Add nf_flow_rule_bridge()
From: Eric Woudstra @ 2026-07-07 9:10 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Pablo Neira Ayuso, Florian Westphal,
Phil Sutter, Nikolay Aleksandrov, Ido Schimmel, Kuniyuki Iwashima,
Stanislav Fomichev, Samiullah Khawaja, Hangbin Liu, Krishna Kumar,
Martin Karsten
Cc: netdev, netfilter-devel, bridge, Eric Woudstra
In-Reply-To: <20260707091045.967678-1-ericwouds@gmail.com>
Add nf_flow_rule_bridge().
It only calls the common rule and adds the redirect.
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Eric Woudstra <ericwouds@gmail.com>
---
include/net/netfilter/nf_flow_table.h | 3 +++
net/netfilter/nf_flow_table_offload.c | 13 +++++++++++++
2 files changed, 16 insertions(+)
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 7b23b245a5a86..5c6e3b65ae85b 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -368,6 +368,9 @@ void nf_flow_table_offload_flush_cleanup(struct nf_flowtable *flowtable);
int nf_flow_table_offload_setup(struct nf_flowtable *flowtable,
struct net_device *dev,
enum flow_block_command cmd);
+int nf_flow_rule_bridge(struct net *net, struct flow_offload *flow,
+ enum flow_offload_tuple_dir dir,
+ struct nf_flow_rule *flow_rule);
int nf_flow_rule_route_ipv4(struct net *net, struct flow_offload *flow,
enum flow_offload_tuple_dir dir,
struct nf_flow_rule *flow_rule);
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index 002ec15d988bd..5566ebda7b7d3 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -740,6 +740,19 @@ nf_flow_rule_route_common(struct net *net, const struct flow_offload *flow,
return 0;
}
+int nf_flow_rule_bridge(struct net *net, struct flow_offload *flow,
+ enum flow_offload_tuple_dir dir,
+ struct nf_flow_rule *flow_rule)
+{
+ if (nf_flow_rule_route_common(net, flow, dir, flow_rule) < 0)
+ return -1;
+
+ flow_offload_redirect(net, flow, dir, flow_rule);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(nf_flow_rule_bridge);
+
int nf_flow_rule_route_ipv4(struct net *net, struct flow_offload *flow,
enum flow_offload_tuple_dir dir,
struct nf_flow_rule *flow_rule)
--
2.53.0
^ permalink raw reply related
* [PATCH v12 nf-next 2/7] net: core: dev: Add dev_fill_bridge_path()
From: Eric Woudstra @ 2026-07-07 9:10 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Pablo Neira Ayuso, Florian Westphal,
Phil Sutter, Nikolay Aleksandrov, Ido Schimmel, Kuniyuki Iwashima,
Stanislav Fomichev, Samiullah Khawaja, Hangbin Liu, Krishna Kumar,
Martin Karsten
Cc: netdev, netfilter-devel, bridge, Eric Woudstra
In-Reply-To: <20260707091045.967678-1-ericwouds@gmail.com>
New function dev_fill_bridge_path(), similar to dev_fill_forward_path().
It handles starting from a bridge port instead of the bridge master.
The structures ctx and nft_forward_info need to be already filled in with
the (vlan) encaps.
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Eric Woudstra <ericwouds@gmail.com>
---
include/linux/netdevice.h | 2 ++
net/core/dev.c | 66 +++++++++++++++++++++++++++++++--------
2 files changed, 55 insertions(+), 13 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 982b6e65a4be4..69b499ddefda0 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3421,6 +3421,8 @@ void dev_remove_offload(struct packet_offload *po);
int dev_get_iflink(const struct net_device *dev);
int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb);
+int dev_fill_bridge_path(struct net_device_path_ctx *ctx,
+ struct net_device_path_stack *stack);
int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
struct net_device_path_stack *stack);
struct net_device *dev_get_by_name(struct net *net, const char *name);
diff --git a/net/core/dev.c b/net/core/dev.c
index 4b3d5cfdf6e00..f6685c1e47860 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -750,44 +750,84 @@ static struct net_device_path *dev_fwd_path(struct net_device_path_stack *stack)
return &stack->path[k];
}
-int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
- struct net_device_path_stack *stack)
+static int dev_fill_forward_path_common(struct net_device_path_ctx *ctx,
+ struct net_device_path_stack *stack)
{
const struct net_device *last_dev;
- struct net_device_path_ctx ctx = {
- .dev = dev,
- };
struct net_device_path *path;
int ret = 0;
- memcpy(ctx.daddr, daddr, sizeof(ctx.daddr));
- stack->num_paths = 0;
- while (ctx.dev && ctx.dev->netdev_ops->ndo_fill_forward_path) {
- last_dev = ctx.dev;
+ while (ctx->dev && ctx->dev->netdev_ops->ndo_fill_forward_path) {
+ last_dev = ctx->dev;
path = dev_fwd_path(stack);
if (!path)
return -1;
memset(path, 0, sizeof(struct net_device_path));
- ret = ctx.dev->netdev_ops->ndo_fill_forward_path(&ctx, path);
+ ret = ctx->dev->netdev_ops->ndo_fill_forward_path(ctx, path);
if (ret < 0)
return -1;
- if (WARN_ON_ONCE(last_dev == ctx.dev))
+ if (WARN_ON_ONCE(last_dev == ctx->dev))
return -1;
}
- if (!ctx.dev)
+ if (!ctx->dev)
return ret;
path = dev_fwd_path(stack);
if (!path)
return -1;
path->type = DEV_PATH_ETHERNET;
- path->dev = ctx.dev;
+ path->dev = ctx->dev;
return ret;
}
+
+int dev_fill_bridge_path(struct net_device_path_ctx *ctx,
+ struct net_device_path_stack *stack)
+{
+ const struct net_device *last_dev, *br_dev;
+ struct net_device_path *path;
+
+ stack->num_paths = 0;
+
+ if (!ctx->dev || !netif_is_bridge_port(ctx->dev))
+ return -1;
+
+ br_dev = netdev_master_upper_dev_get_rcu((struct net_device *)ctx->dev);
+ if (!br_dev || !br_dev->netdev_ops->ndo_fill_forward_path)
+ return -1;
+
+ last_dev = ctx->dev;
+ path = dev_fwd_path(stack);
+ if (!path)
+ return -1;
+
+ memset(path, 0, sizeof(struct net_device_path));
+ if (br_dev->netdev_ops->ndo_fill_forward_path(ctx, path) < 0)
+ return -1;
+
+ if (!ctx->dev || WARN_ON_ONCE(last_dev == ctx->dev))
+ return -1;
+
+ return dev_fill_forward_path_common(ctx, stack);
+}
+EXPORT_SYMBOL_GPL(dev_fill_bridge_path);
+
+int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
+ struct net_device_path_stack *stack)
+{
+ struct net_device_path_ctx ctx = {
+ .dev = dev,
+ };
+
+ memcpy(ctx.daddr, daddr, sizeof(ctx.daddr));
+
+ stack->num_paths = 0;
+
+ return dev_fill_forward_path_common(&ctx, stack);
+}
EXPORT_SYMBOL_GPL(dev_fill_forward_path);
/* must be called under rcu_read_lock(), as we dont take a reference */
--
2.53.0
^ permalink raw reply related
* [PATCH v12 nf-next 1/7] bridge: Add filling forward path from port to port
From: Eric Woudstra @ 2026-07-07 9:10 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Pablo Neira Ayuso, Florian Westphal,
Phil Sutter, Nikolay Aleksandrov, Ido Schimmel, Kuniyuki Iwashima,
Stanislav Fomichev, Samiullah Khawaja, Hangbin Liu, Krishna Kumar,
Martin Karsten
Cc: netdev, netfilter-devel, bridge, Eric Woudstra
In-Reply-To: <20260707091045.967678-1-ericwouds@gmail.com>
If a port is passed as argument instead of the master, then:
At br_fill_forward_path(): find the master and use it to fill the
forward path.
At br_vlan_fill_forward_path_pvid(): lookup vlan group from port
instead.
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Eric Woudstra <ericwouds@gmail.com>
---
net/bridge/br_device.c | 19 ++++++++++++++-----
net/bridge/br_private.h | 2 ++
net/bridge/br_vlan.c | 6 +++++-
3 files changed, 21 insertions(+), 6 deletions(-)
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 3b9fc86293fdb..56fc80d2f5215 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -385,16 +385,25 @@ static int br_del_slave(struct net_device *dev, struct net_device *slave_dev)
static int br_fill_forward_path(struct net_device_path_ctx *ctx,
struct net_device_path *path)
{
+ struct net_bridge_port *src, *dst;
struct net_bridge_fdb_entry *f;
- struct net_bridge_port *dst;
struct net_bridge *br;
- if (netif_is_bridge_port(ctx->dev))
- return -1;
+ if (netif_is_bridge_port(ctx->dev)) {
+ struct net_device *br_dev;
+
+ br_dev = netdev_master_upper_dev_get_rcu((struct net_device *)ctx->dev);
+ if (!br_dev)
+ return -1;
- br = netdev_priv(ctx->dev);
+ src = br_port_get_rcu(ctx->dev);
+ br = netdev_priv(br_dev);
+ } else {
+ src = NULL;
+ br = netdev_priv(ctx->dev);
+ }
- br_vlan_fill_forward_path_pvid(br, ctx, path);
+ br_vlan_fill_forward_path_pvid(br, src, ctx, path);
f = br_fdb_find_rcu(br, ctx->daddr, path->bridge.vlan_id);
if (!f)
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index d55ea9516e3e3..00f5b72ff42de 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -1630,6 +1630,7 @@ bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr,
const struct net_bridge_vlan *range_end);
void br_vlan_fill_forward_path_pvid(struct net_bridge *br,
+ struct net_bridge_port *p,
struct net_device_path_ctx *ctx,
struct net_device_path *path);
int br_vlan_fill_forward_path_mode(struct net_bridge *br,
@@ -1799,6 +1800,7 @@ static inline int nbp_get_num_vlan_infos(struct net_bridge_port *p,
}
static inline void br_vlan_fill_forward_path_pvid(struct net_bridge *br,
+ struct net_bridge_port *p,
struct net_device_path_ctx *ctx,
struct net_device_path *path)
{
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index a248ce70f919f..f4a82e107ec7d 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -1450,6 +1450,7 @@ int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid)
EXPORT_SYMBOL_GPL(br_vlan_get_pvid_rcu);
void br_vlan_fill_forward_path_pvid(struct net_bridge *br,
+ struct net_bridge_port *p,
struct net_device_path_ctx *ctx,
struct net_device_path *path)
{
@@ -1462,7 +1463,10 @@ void br_vlan_fill_forward_path_pvid(struct net_bridge *br,
if (!br_opt_get(br, BROPT_VLAN_ENABLED))
return;
- vg = br_vlan_group_rcu(br);
+ if (p)
+ vg = nbp_vlan_group_rcu(p);
+ else
+ vg = br_vlan_group_rcu(br);
if (idx >= 0 &&
ctx->vlan[idx].proto == br->vlan_proto) {
--
2.53.0
^ permalink raw reply related
* [PATCH v12 nf-next 0/7] netfilter: Add bridge-fastpath
From: Eric Woudstra @ 2026-07-07 9:10 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Pablo Neira Ayuso, Florian Westphal,
Phil Sutter, Nikolay Aleksandrov, Ido Schimmel, Kuniyuki Iwashima,
Stanislav Fomichev, Samiullah Khawaja, Hangbin Liu, Krishna Kumar,
Martin Karsten
Cc: netdev, netfilter-devel, bridge, Eric Woudstra
This patchset makes it possible to set up a software fastpath between
bridged interfaces. One patch adds the flow rule for the hardware
fastpath. This creates the possibility to have a hardware offloaded
fastpath between bridged interfaces. More patches are added to solve
issues found with the existing code.
To set up the fastpath, add this extra flowtable (with or
without 'flags offload'):
table bridge filter {
flowtable fb {
hook ingress priority filter
devices = { lan0, lan1, lan2, lan3, lan4, wlan0, wlan1 }
flags offload
}
chain forward {
type filter hook forward priority filter; policy accept;
ct state established flow add @fb
}
}
Creating a separate fastpath for bridges.
forward fastpath bypass
.----------------------------------------.
/ \
| IP - forwarding |
| / \ v
| / wan ...
| /
| |
| |
| brlan.1
| |
| +-------------------------------+
| | vlan 1 |
| | |
| | brlan (vlan-filtering) |
| +---------------+ |
| | DSA-SWITCH | |
| | | vlan 1 |
| | | to |
| | vlan 1 | untagged |
| +---------------+---------------+
. / \
------>lan0 wlan1
. ^ ^
. | |
. \_________________/
. bridge fastpath bypass
.
^
vlan 1 tagged packets
Note: While testing direct transmit in the software forward-fastpath,
without the capability of setting the offload flag, it is sometimes useful
to enslave the wan interface to another bridge, brwan. This will make
sure both directions of the software forward-fastpath use direct transmit,
which also happens when the offload flag is set.
Note 2: For complete testing this patch-set, see:
[PATCH v5 nf-next] selftests: netfilter: Add bridge_fastpath.sh
This mail also mentions other patches involved in this, some patches
already applied, some patches are not.
Changes in v12:
- Added Note 2, refer to selftest script
- Added patch: nft_flow_offload_eval() check thoff==0.
- flow_offload_bridge_init() removed unnecessary call to memset().
Changes in v11:
- Dropped "Introduce DEV_PATH_BR_VLAN_KEEP_HW for bridge-fastpath" from
this patch-set, it has moved to another patch-set.
- Updated nft_flow_offload_bridge_init() changing the way of accessing
headers after fixing nft_do_chain_bridge().
v10 split from patch-set: bridge-fastpath and related improvements v9
Eric Woudstra (7):
bridge: Add filling forward path from port to port
net: core: dev: Add dev_fill_bridge_path()
netfilter: nf_flow_table_offload: Add nf_flow_rule_bridge()
netfilter: nf_flow_table_inet: Add nf_flowtable_type flowtable_bridge
netfilter: nft_flow_offload: nft_flow_offload_eval: check thoff==0
netfilter: nft_flow_offload: Add NFPROTO_BRIDGE to validate
netfilter: nft_flow_offload: Add bridgeflow to nft_flow_offload_eval()
include/linux/netdevice.h | 2 +
include/net/netfilter/nf_flow_table.h | 8 ++
net/bridge/br_device.c | 19 +++-
net/bridge/br_private.h | 2 +
net/bridge/br_vlan.c | 6 +-
net/core/dev.c | 66 +++++++++++---
net/netfilter/nf_flow_table_inet.c | 13 +++
net/netfilter/nf_flow_table_offload.c | 13 +++
net/netfilter/nf_flow_table_path.c | 126 ++++++++++++++++++++++++++
net/netfilter/nft_flow_offload.c | 32 +++++--
10 files changed, 259 insertions(+), 28 deletions(-)
--
2.53.0
^ permalink raw reply
* Re: [PATCH v3] net/liquidio: drop cached VF pci_dev LUT
From: patchwork-bot+netdevbpf @ 2026-07-07 9:10 UTC (permalink / raw)
To: Yuho Choi
Cc: andrew+netdev, davem, edumazet, kuba, pabeni, netdev,
kory.maincent, zilin, arend.vanspriel, marco.crivellari,
u.kleine-koenig, vadim.fedorenko, linux-kernel
In-Reply-To: <20260701040847.1897845-1-dbgh9129@gmail.com>
Hello:
This patch was applied to netdev/net.git (main)
by Paolo Abeni <pabeni@redhat.com>:
On Wed, 1 Jul 2026 00:08:47 -0400 you wrote:
> The PF SR-IOV enable path caches VF pci_dev pointers in
> dpiring_to_vfpcidev_lut[] by iterating with pci_get_device(). Those
> entries do not own a reference, because the iterator drops the previous
> device reference on each step. The cached pointer is then dereferenced
> later when handling OCTEON_VF_FLR_REQUEST.
>
> Replace the cached VF mapping with runtime lookup on the mailbox DPI
> ring: derive the VF index from q_no, resolve the VF via exported PCI
> IOV helpers, validate it with the PF pointer and VF ID, then issue
> pcie_flr() and drop the reference with pci_dev_put(). Remove the
> unused VF lookup table initialization and cleanup.
>
> [...]
Here is the summary with links:
- [v3] net/liquidio: drop cached VF pci_dev LUT
https://git.kernel.org/netdev/net/c/5c0e3ba4f500
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
^ permalink raw reply
* RE: Ethtool : PRBS feature
From: Das, Shubham @ 2026-07-07 9:06 UTC (permalink / raw)
To: Srinivasan, Vijay, Lee Trager, Andrew Lunn
Cc: Alexander Duyck, Maxime Chevallier, netdev@vger.kernel.org,
mkubecek@suse.cz, D H, Siddaraju, Chintalapalle, Balaji,
Lindberg, Magnus, niklas.damberg@ericsson.com, Wirandi, Jonas
In-Reply-To: <BL3PR11MB6385468A86BACA1D8EFEF2BE88F62@BL3PR11MB6385.namprd11.prod.outlook.com>
Thanks Andrew, Lee for the feedback.
Lee,
I don't see prbs11.0, prbs11.1, prbs11.2, prbs11.3, prbs13.0, prbs13.1, prbs13.2, prbs13.3, prbs16 and prbs32 in IEEE 802.3 2022 standard.
Is this specific to fnic based on base PRBS pattern or it is mentioned in some other standard ?
Each lane and each direction is a completely separate test with its own test of
> statistics. The test is actually verified on the Rx side, Tx is your generator so you
> won't have data to collect. So when you run PRBS testing on a 2 lane NIC you are
> actually running 4 independent tests.
> While its fine to have a shortcut to run the same test on all lanes we absolutely
> need a way to run tests per lane and the ability to choose Rx, Tx, or both.
- Agree, we need lane parameter in commands, Updated command.
> I wouldn't consider stats a phy-test action. It shouldn't change the state of the
> NIC at all. I would just add phy-test-stats as set of standard ethtool statistics.
Yes moved under separate command.
Below are the updated UAPI, data structures, and Netlink messages to support PRBS/BERT and test pattern configuration.
diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 5e9135e3774f..113005a5f80a 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -30,6 +30,35 @@ definitions:
+ -
+ name: phy-test-pattern
+ enum-name: phy-test-pattern
+ type: enum
+ name-prefix: phy-test-pattern-
+ doc: PRBS and other PHY test patterns
+ entries:
+ - off
+ - prbs7
+ - prbs9
+ - prbs11
+ - prbs13
+ - prbs15
+ - prbs23
+ - prbs31
+ - ssprq
+ - prbs13q
+ - prbs31q
+ - square8
+ name: phy-test-action
+ enum-name: phy-test-action
+ type: enum
+ name-prefix: phy-test-action-
+ doc: Actions for PHY BERT test control
+ entries:
+ - none
+ - start
+ - stop
+ name: phy-test
+ attr-cnt-name: __ethtool-a-phy-test-cnt
+ doc: |
+ PHY test configuration for pattern generation/checking,
+ BERT (Bit Error Rate Test), and statistics.
+ attributes:
+ -
+ name: unspec
+ type: unused
+ value: 0
+ -
+ name: header
+ type: nest
+ nested-attributes: header
+ -
+ name: lane
+ type: u32
+ doc: PHY lane index to target for the test operation
+ -
+ name: tx-pattern
+ type: u32
+ doc: TX test pattern type (PRBS or square8 wave)
+ enum: phy-test-pattern
+ -
+ name: rx-pattern
+ type: u32
+ doc: RX checker pattern type (PRBS or square8 wave)
+ enum: phy-test-pattern
+ -
+ name: bert-action
+ type: u32
+ doc: BERT test start/stop
+ enum: phy-test-action
+ -
+ name: inject-error-count
+ type: u32
+ doc: |
+ Inject a specified number of bit errors into the PHY transmit data
+ stream for diagnostic verification purposes.
+
+ Context and Purpose:
+ When performing Bit Error Ratio Testing (BERT), the receiving side
+ runs a PRBS checker that monitors for bit errors. Before relying
+ on a zero-error BERT result, operators need to confirm Checker
+ state and configuration to qualify result as TRUE.
+ A checker that is broken or misconfigured would also report
+ zero errors, giving a FALSE pass. Error injection provides this
+ confirmation by deliberately introducing a known number of errors
+ on the transmit side and verifying they appear on the receive side.
+
+ Note:
+ Receiver under test maybe in the same port as the transmitter
+ (loopback mode) or a different port in the same device or another
+ device connected to the transmitting port (non-loopback mode).
+
+ Layer and Mechanism:
+ Error injection operates at the PMA/PMD boundary. This is
+ bit-level injection in the serial data stream, not frame-level.
+ The SerDes Built-In Self Test (BIST) block inverts the specified
+ number of bits in the outgoing serial stream. The injection does
+ not distinguish between data frames and test patterns; it
+ corrupts raw bits at the physical layer regardless of what the
+ stream carries.
+
+ Mode of Operation:
+ This command implements "one-shot" injection: a single burst of
+ N bit errors injected immediately. The PHY inverts exactly N
+ consecutive bits in the serial transmit stream at the PMA/PMD
+ layer, then resumes clean transmission. No continuous/fixed-rate
+ injection mode is provided.
+
+ Prerequisites:
+ - A PRBS test pattern must be active on the transmitting port
+ (tx-pattern != off).
+ - The receiving port must have the matching rx-pattern configured
+ and ber-lock-status must be "locked" (indicating the checker
+ has synchronized to the incoming pattern).
+ - BERT must be running on the receiving port (bert start issued).
+
+ Note:
+ Availability of BIST mode test pattern generator, checker and
+ lock indication is IP dependent.
+
+ Semantics:
+ - Fire-and-forget: the command completes immediately. No
+ persistent state is created. Each invocation is an independent
+ injection event.
+ - The command may be issued multiple times. Each invocation
+ injects an additional burst of errors (counts accumulate on
+ the receiver's ber-error-count across invocations).
+ - If no test pattern is active, the behaviour is
+ implementation-defined (hardware may silently ignore the
+ request or return an error).
+
+ Expected Outcome:
+ After injecting N errors on the TX port, the far-end receiver's
+ ber-error-count (read via --show-phy-test) should increment by
+ exactly N (within hardware counter precision). This confirms:
+ 1. The PRBS checker is locked and actively counting errors.
+ 2. The data path between TX and RX is intact.
+ 3. The BERT counters are functioning correctly.
+
+ Example Workflow:
+ # Configure TX pattern on port A
+ ethtool --phy-test eth1 lane 0 tx-pattern prbs31
+ # Configure RX checker on port B, start BERT
+ ethtool --phy-test eth2 lane 0 rx-pattern prbs31
+ ethtool --phy-test eth2 lane 0 bert start
+ # Verify lock
+ ethtool --show-phy-test eth2 lane 0
+ # -> ber-lock-status: locked, ber-error-count: 0
+ # Inject 5 errors from TX side
+ ethtool --phy-test eth1 lane 0 inject-errors 5
+ # Confirm errors were detected
+ ethtool --show-phy-test eth2 lane 0
+ # -> ber-error-count: 5
+ -
+ name: ber-lock-status
+ type: u8
+ doc: PRBS lock status (1=locked, 0=not locked)
+ -
+ name: ber-error-count
+ type: u64
+ doc: BERT bit error count
+ -
+ name: ber-total-bits-sent
+ type: u64
+ doc: BERT total bits sent
+ -
+ name: supported-test-patterns
+ type: u32
+ doc: Bitmask of supported test patterns
+ -
+ name: phy-test-act
+ doc: |
+ Configure PHY test parameters. Each attribute is optional and only
+ specified attributes are applied. TX/RX patterns are set on the
+ local port. BERT and error injection operate on the receiver port.
+ Typical workflow:
+ ethtool --phy-test eth1 lane 0 tx-pattern prbs7 (TX side)
+ ethtool --phy-test eth2 lane 0 rx-pattern prbs7 (RX side)
+ ethtool --phy-test eth2 lane 0 bert start (start BERT on RX)
+ ethtool --phy-test eth1 lane 0 inject-errors 10 (inject 10 errors on TX)
+ ethtool --show-phy-test eth2 lane 0 (read counters, expect +10)
+ ethtool --phy-test eth2 lane 0 bert stop (stop BERT)
+
+ attribute-set: phy-test
+
+ do:
+ request:
+ attributes:
+ - header
+ - lane
+ - tx-pattern
+ - rx-pattern
+ - bert-action
+ - inject-error-count
+ -
+ name: phy-test-get
+ doc: |
+ Get PHY test configuration status, supported patterns, and BERT
+ statistics (lock status, error count, total bits).
+
+ attribute-set: phy-test
+
+ do:
+ request:
+ attributes:
+ - header
+ - lane
+ reply:
+ attributes:
+ - header
+ - lane
+ - tx-pattern
+ - rx-pattern
+ - supported-test-patterns
+ - ber-lock-status
+ - ber-error-count
+ - ber-total-bits-sent
mcast-groups:
list:
- Shubham D
From: Srinivasan, Vijay <vijay.srinivasan@intel.com>
Sent: 02 July 2026 05:19
To: Lee Trager <lee@trager.us>; Andrew Lunn <andrew@lunn.ch>
Cc: Das, Shubham <shubham.das@intel.com>; Alexander Duyck <alexander.duyck@gmail.com>; Maxime Chevallier <maxime.chevallier@bootlin.com>; netdev@vger.kernel.org; mkubecek@suse.cz; D H, Siddaraju <siddaraju.dh@intel.com>; Chintalapalle, Balaji <balaji.chintalapalle@intel.com>; Lindberg, Magnus <magnus.k.lindberg@ericsson.com>; niklas.damberg@ericsson.com; Wirandi, Jonas <jonas.wirandi@ericsson.com>
Subject: Re: Ethtool : PRBS feature
All good points and noted.
Will write the specification in general terms with full description of context, usage, configuration, expected outcome etc.
Vijay
________________________________________
From: Lee Trager <mailto:lee@trager.us>
Sent: Wednesday, July 1, 2026 4:28 PM
To: Andrew Lunn <mailto:andrew@lunn.ch>; Srinivasan, Vijay <mailto:vijay.srinivasan@intel.com>
Cc: Das, Shubham <mailto:shubham.das@intel.com>; Alexander Duyck <mailto:alexander.duyck@gmail.com>; Maxime Chevallier <mailto:maxime.chevallier@bootlin.com>; mailto:netdev@vger.kernel.org <mailto:netdev@vger.kernel.org>; mailto:mkubecek@suse.cz <mailto:mkubecek@suse.cz>; D H, Siddaraju <mailto:siddaraju.dh@intel.com>; Chintalapalle, Balaji <mailto:balaji.chintalapalle@intel.com>; Lindberg, Magnus <mailto:magnus.k.lindberg@ericsson.com>; mailto:niklas.damberg@ericsson.com <mailto:niklas.damberg@ericsson.com>; Wirandi, Jonas <mailto:jonas.wirandi@ericsson.com>
Subject: Re: Ethtool : PRBS feature
On 7/1/26 3:02 PM, Andrew Lunn wrote:
> On Wed, Jul 01, 2026 at 09:38:08PM +0000, Srinivasan, Vijay wrote:
>> Hi Andrew,
>> I think there is a disconnect here.
> Which proves my point. The specification is not sufficient if you have
> to keep correcting me.
>
> The kAPI should be understandable by somebody who has a general
> networking background. Please write a specification with that
> assumption in mind. Don't assume the reader is a test engineer who has
> used PRBS for half his life. Assume it is a brand new test engineer
> who is hearing PRBS for the first time. That is what most engineers on
> the netdev list are. Me included.
I think part of the disconnect is that PRBS testing is a signal
integrity test, not a network test. In this case the phy happens to be
Ethernet but it could just as easily be PCIE or USB. That is why it was
heavily suggested to me at netdev 0x19 that this should be done on the
generic phy layer, not netdev.
Lee
^ permalink raw reply related
* Re: [PATCH net-next 3/6] net: stmmac: mediatek: rename MT2712 and MT8195 variant methods
From: Maxime Chevallier @ 2026-07-07 9:05 UTC (permalink / raw)
To: Louis-Alexis Eyraud, Andrew Lunn, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Richard Cochran, Matthias Brugger,
AngeloGioacchino Del Regno, Biao Huang, Maxime Coquelin,
Alexandre Torgue
Cc: rmk+kernel, kernel, netdev, devicetree, linux-kernel,
linux-arm-kernel, linux-mediatek, linux-stm32
In-Reply-To: <20260707-dwmac-mediatek-mt8189-v1-3-17f345eaaca3@collabora.com>
On 7/7/26 10:21, Louis-Alexis Eyraud wrote:
> In preparation of newer SoC support, rename MT2712 and MT8195 variant
> methods and sub functions to more generic names.
>
> Signed-off-by: Louis-Alexis Eyraud <louisalexis.eyraud@collabora.com>
> ---
> .../net/ethernet/stmicro/stmmac/dwmac-mediatek.c | 32 +++++++++++-----------
> 1 file changed, 16 insertions(+), 16 deletions(-)
>
> diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
> index 0cabab4fd89a..28e87990b0a1 100644
> --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
> +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
> @@ -110,7 +110,7 @@ static const char * const mt8195_dwmac_clk_l[] = {
> "axi", "apb", "mac_cg", "mac_main", "ptp_ref"
> };
>
> -static int mt2712_set_interface(struct mediatek_dwmac_plat_data *plat,
> +static int set_phy_interface_v1(struct mediatek_dwmac_plat_data *plat,
> u8 phy_intf_sel)
What does this naming of "v1 / v2" refer to ?
I personally don't find it much better than the current one prefixed by the SoC
name. You still end-up using registers that have the "MT8195_" prefix in their
names in the 'v2' variants of these functions, so it still sound SoC-family specific :)
I'd say you can keep the original names as-is, or if you really want a rename,
maybe use the mt81xx_ prefix for MT8195 and MT8189 ?
Maxime
^ permalink raw reply
* Re: [PATCH net-next v2] ipv4: hold a consistent view of rt->dst.dev under RCU
From: Paolo Abeni @ 2026-07-07 9:02 UTC (permalink / raw)
To: luoxuanqiang, Ido Schimmel
Cc: David S . Miller, Eric Dumazet, Jakub Kicinski, David Ahern,
Simon Horman, Kuniyuki Iwashima, netdev, linux-kernel,
Xuanqiang Luo
In-Reply-To: <5e2119f1-3c1c-43eb-984e-a8eeab2896e0@linux.dev>
On 7/7/26 3:26 AM, luoxuanqiang wrote:
> 在 2026/7/6 00:46, Ido Schimmel 写道:
>> On Wed, Jul 01, 2026 at 11:24:34AM +0800,xuanqiang.luo@linux.dev wrote:
>>> From: Xuanqiang Luo<luoxuanqiang@kylinos.cn>
>>>
>>> rt_flush_dev() walks the per-CPU uncached route list and rewrites
>>> rt->dst.dev in-place to blackhole_netdev under spin_lock_bh().
>>> This lock does not exclude RCU readers, which may load rt->dst.dev
>>> multiple times within a single rcu_read_lock() region.
>>>
>>> ip_rt_send_redirect() is a typical example: it reads rt->dst.dev
>>> three times to obtain in_dev, the L3 master ifindex, and net.
>>> A concurrent device unregistration can repoint rt->dst.dev to
>>> blackhole_netdev between those reads, making the reader combine
>>> state from two different net_devices — for instance, an in_dev
>>> from the real device but a netns and peer lookup from the blackhole
>>> device. ip_rt_get_source() has the same problem: it reads
>>> rt->dst.dev four times to obtain the output ifindex, the netns,
>>> and the source address, so a concurrent flush can cause the source
>>> selection to mix state from different devices.
>> Why only change ip_rt_send_redirect() and ip_rt_get_source() when the
>> patch is titled "ipv4: hold a consistent view of rt->dst.dev under RCU"?
>> What is the criterion?
>
> Thanks! You are right, the subject is too broad. I will make them
> more accurate in the next version.
>
>>> Take a single dst_dev_rcu() snapshot of rt->dst.dev at the start
>>> of each affected RCU reader and use that snapshot throughout, so
>>> concurrent flushes cannot cause mid-function inconsistency.
>>> Publish the in-place write in rt_flush_dev() with rcu_assign_pointer()
>>> to match the readers.
>> The rt_flush_dev() change should be a separate change. Note that
>> dst_dev_put() was already converted to use rcu_assign_pointer().
>>
> I will split the rt_flush_dev() change into a separate patch.
>
>>> Fixes: caacf05e5ad1a ("ipv4: Properly purge netdev references on uncached routes.")
>> Please remove the Fixes tag given you are targeting net-next.
>
> Just to clarify: is the suggestion to drop the Fixes tag here solely
> because this patch is targeted at net-next? Or are there any other
> reasons?
Generally speaking, yes: net-next patches should not include a fixes tag
unless the blamed commit is on net-next only.
More specifically, this patch is really a behavior improvement and not a
vertical fix, as such we want to avoid it propagating on stable trees,
as the fixes tag sometimes does.
/P
^ permalink raw reply
* Re: [PATCH v1 net-next 0/2] net: Misc follow-up on RTNL-less fib_rules series.
From: patchwork-bot+netdevbpf @ 2026-07-07 9:00 UTC (permalink / raw)
To: Kuniyuki Iwashima
Cc: dsahern, idosch, davem, edumazet, kuba, pabeni, horms, kuni1840,
netdev
In-Reply-To: <20260702044437.591864-1-kuniyu@google.com>
Hello:
This series was applied to netdev/net-next.git (main)
by Paolo Abeni <pabeni@redhat.com>:
On Thu, 2 Jul 2026 04:44:13 +0000 you wrote:
> Patch 1 moves net->ipv4.fib_table_hash_lock under
> CONFIG_IP_MULTIPLE_TABLES.
>
> Patch 2 adds mutex_destroy() for fib_rules_ops.lock.
>
>
> Kuniyuki Iwashima (2):
> ipv4: fib: Define fib_table_hash_lock under CONFIG_IP_MULTIPLE_TABLES.
> net: fib_rules: Destroy ops->lock in fib_rules_unregister().
>
> [...]
Here is the summary with links:
- [v1,net-next,1/2] ipv4: fib: Define fib_table_hash_lock under CONFIG_IP_MULTIPLE_TABLES.
https://git.kernel.org/netdev/net-next/c/6041421dd087
- [v1,net-next,2/2] net: fib_rules: Destroy ops->lock in fib_rules_unregister().
https://git.kernel.org/netdev/net-next/c/99c13f8020df
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
^ permalink raw reply
* [PATCH nf] ipvs: make destination flags atomic
From: Yizhou Zhao @ 2026-07-07 8:57 UTC (permalink / raw)
To: Simon Horman, Julian Anastasov, David Ahern, Ido Schimmel,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Pablo Neira Ayuso, Florian Westphal, Phil Sutter,
Alexander Frolkin
Cc: Yizhou Zhao, netdev, lvs-devel, linux-kernel, netfilter-devel,
coreteam, stable, Yuxiang Yang, Ao Wang, Xuewei Feng, Qi Li,
Ke Xu
is_unavailable() in the SH scheduler reads dest->flags from the packet
scheduling path while holding only the RCU read lock. The same word is
updated by read-modify-write operations from connection accounting and
destination update paths, for example ip_vs_bind_dest(),
ip_vs_unbind_dest(), and __ip_vs_update_dest().
The RCU read lock only protects the destination lifetime; it does not
serialize accesses to dest->flags. A racing plain load or RMW update can
therefore observe stale state or lose an AVAILABLE/OVERLOAD bit update,
which can make the scheduler choose an overloaded destination or report no
available destination even though one should be usable.
KCSAN reports the race with a standard IPVS configuration using the SH
scheduler and a destination with u_threshold set:
BUG: KCSAN: data-race in __ip_vs_update_dest / ip_vs_sh_schedule
write to ... of 4 bytes by task ipvs_cfg:
__ip_vs_update_dest
ip_vs_edit_dest
do_ip_vs_set_ctl
__x64_sys_setsockopt
read to ... of 4 bytes by task ipvs_churn:
ip_vs_sh_schedule
ip_vs_schedule
tcp_conn_schedule
ip_vs_in_hook
tcp_connect
__x64_sys_connect
value changed: 0x00000003 -> 0x00000001
Convert dest->flags to atomic_t and use atomic_read(), atomic_or(), and
atomic_and() for all destination flag tests and updates. This preserves
the existing 32-bit field size while making the flag updates atomic RMW
operations and making readers use atomic accesses. Valid minimum-sized
IPVS configuration and scheduling paths are unchanged; only the
synchronization of the destination status flags changes.
Fixes: eba3b5a78799d ("ipvs: SH fallback and L4 hashing")
Cc: stable@vger.kernel.org
Reported-by: Yizhou Zhao <zhaoyz24@mails.tsinghua.edu.cn>
Reported-by: Yuxiang Yang <yangyx22@mails.tsinghua.edu.cn>
Reported-by: Ao Wang <wangao@seu.edu.cn>
Reported-by: Xuewei Feng <fengxw06@126.com>
Reported-by: Qi Li <qli01@tsinghua.edu.cn>
Reported-by: Ke Xu <xuke@tsinghua.edu.cn>
Assisted-by: Claude-Code:GLM-5.2
Signed-off-by: Yizhou Zhao <zhaoyz24@mails.tsinghua.edu.cn>
---
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 49297fec448a..bb969738ed73 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -972,7 +972,7 @@ struct ip_vs_dest {
u16 af; /* address family */
__be16 port; /* port number of the server */
union nf_inet_addr addr; /* IP address of the server */
- volatile unsigned int flags; /* dest status flags */
+ atomic_t flags; /* dest status flags */
atomic_t conn_flags; /* flags to copy to conn */
atomic_t weight; /* server weight */
atomic_t last_weight; /* server latest weight */
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index cb36641f8d1c..539f603f38b7 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -1055,7 +1055,7 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
if (dest->u_threshold != 0 &&
ip_vs_dest_totalconns(dest) >= dest->u_threshold)
- dest->flags |= IP_VS_DEST_F_OVERLOAD;
+ atomic_or(IP_VS_DEST_F_OVERLOAD, &dest->flags);
}
@@ -1151,13 +1151,13 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp)
if (dest->l_threshold != 0) {
if (ip_vs_dest_totalconns(dest) < dest->l_threshold)
- dest->flags &= ~IP_VS_DEST_F_OVERLOAD;
+ atomic_and(~IP_VS_DEST_F_OVERLOAD, &dest->flags);
} else if (dest->u_threshold != 0) {
if (ip_vs_dest_totalconns(dest) * 4 < dest->u_threshold * 3)
- dest->flags &= ~IP_VS_DEST_F_OVERLOAD;
+ atomic_and(~IP_VS_DEST_F_OVERLOAD, &dest->flags);
} else {
- if (dest->flags & IP_VS_DEST_F_OVERLOAD)
- dest->flags &= ~IP_VS_DEST_F_OVERLOAD;
+ if (atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD)
+ atomic_and(~IP_VS_DEST_F_OVERLOAD, &dest->flags);
}
ip_vs_dest_put(dest);
@@ -1188,7 +1188,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct, struct ip_vs_dest *cdest)
* Checking the dest server status.
*/
if ((dest == NULL) ||
- !(dest->flags & IP_VS_DEST_F_AVAILABLE) ||
+ !(atomic_read(&dest->flags) & IP_VS_DEST_F_AVAILABLE) ||
expire_quiescent_template(ipvs, dest) ||
(cdest && (dest != cdest))) {
IP_VS_DBG_BUF(9, "check_template: dest not available for "
@@ -1929,7 +1929,7 @@ void ip_vs_expire_nodest_conn_flush(struct netns_ipvs *ipvs)
cp = ip_vs_hn0_to_conn(hn);
resched_score++;
dest = cp->dest;
- if (!dest || (dest->flags & IP_VS_DEST_F_AVAILABLE))
+ if (!dest || (atomic_read(&dest->flags) & IP_VS_DEST_F_AVAILABLE))
continue;
if (atomic_read(&cp->n_control))
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index d40b404c1bf6..ca778937facf 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -302,7 +302,7 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
struct ip_vs_dest *dest = cp->dest;
struct netns_ipvs *ipvs = cp->ipvs;
- if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
+ if (dest && (atomic_read(&dest->flags) & IP_VS_DEST_F_AVAILABLE)) {
struct ip_vs_cpu_stats *s;
struct ip_vs_service *svc;
@@ -338,7 +338,7 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
struct ip_vs_dest *dest = cp->dest;
struct netns_ipvs *ipvs = cp->ipvs;
- if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
+ if (dest && (atomic_read(&dest->flags) & IP_VS_DEST_F_AVAILABLE)) {
struct ip_vs_cpu_stats *s;
struct ip_vs_service *svc;
@@ -2204,7 +2204,7 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state
}
/* Check the server status */
- if (cp && cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
+ if (cp && cp->dest && !(atomic_read(&cp->dest->flags) & IP_VS_DEST_F_AVAILABLE)) {
/* the destination server is not available */
if (sysctl_expire_nodest_conn(ipvs)) {
bool old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index bcf40b8c41cf..685b2675b6e0 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1368,10 +1368,10 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
}
/* set the dest status flags */
- dest->flags |= IP_VS_DEST_F_AVAILABLE;
+ atomic_or(IP_VS_DEST_F_AVAILABLE, &dest->flags);
if (udest->u_threshold == 0 || udest->u_threshold > dest->u_threshold)
- dest->flags &= ~IP_VS_DEST_F_OVERLOAD;
+ atomic_and(~IP_VS_DEST_F_OVERLOAD, &dest->flags);
dest->u_threshold = udest->u_threshold;
dest->l_threshold = udest->l_threshold;
@@ -1613,7 +1613,7 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc,
struct ip_vs_dest *dest,
int svcupd)
{
- dest->flags &= ~IP_VS_DEST_F_AVAILABLE;
+ atomic_and(~IP_VS_DEST_F_AVAILABLE, &dest->flags);
spin_lock_bh(&dest->dst_lock);
__ip_vs_dst_cache_reset(dest);
diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c
index e1f62f6b25e2..82492e824f02 100644
--- a/net/netfilter/ipvs/ip_vs_dh.c
+++ b/net/netfilter/ipvs/ip_vs_dh.c
@@ -201,7 +201,7 @@ static int ip_vs_dh_dest_changed(struct ip_vs_service *svc,
*/
static inline int is_overloaded(struct ip_vs_dest *dest)
{
- return dest->flags & IP_VS_DEST_F_OVERLOAD;
+ return atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD;
}
@@ -219,10 +219,10 @@ ip_vs_dh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
s = (struct ip_vs_dh_state *) svc->sched_data;
dest = ip_vs_dh_get(svc->af, s, &iph->daddr);
- if (!dest
- || !(dest->flags & IP_VS_DEST_F_AVAILABLE)
- || atomic_read(&dest->weight) <= 0
- || is_overloaded(dest)) {
+ if (!dest
+ || !(atomic_read(&dest->flags) & IP_VS_DEST_F_AVAILABLE)
+ || atomic_read(&dest->weight) <= 0
+ || is_overloaded(dest)) {
ip_vs_scheduler_err(svc, "no destination available");
return NULL;
}
diff --git a/net/netfilter/ipvs/ip_vs_fo.c b/net/netfilter/ipvs/ip_vs_fo.c
index d657b47c6511..5231e518c07c 100644
--- a/net/netfilter/ipvs/ip_vs_fo.c
+++ b/net/netfilter/ipvs/ip_vs_fo.c
@@ -29,7 +29,7 @@ ip_vs_fo_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
* Find virtual server with highest weight and send it traffic
*/
list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
- if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) &&
+ if (!(atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD) &&
atomic_read(&dest->weight) > hw) {
hweight = dest;
hw = atomic_read(&dest->weight);
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 15ccb2b2fa1f..d2eb5dda5b68 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -414,7 +414,7 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc)
* new connection.
*/
list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
- if (dest->flags & IP_VS_DEST_F_OVERLOAD)
+ if (atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD)
continue;
if (atomic_read(&dest->weight) > 0) {
least = dest;
@@ -429,7 +429,7 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc)
*/
nextstage:
list_for_each_entry_continue_rcu(dest, &svc->destinations, n_list) {
- if (dest->flags & IP_VS_DEST_F_OVERLOAD)
+ if (atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD)
continue;
doh = ip_vs_dest_conn_overhead(dest);
@@ -502,7 +502,7 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
*/
dest = en->dest;
- if ((dest->flags & IP_VS_DEST_F_AVAILABLE) &&
+ if ((atomic_read(&dest->flags) & IP_VS_DEST_F_AVAILABLE) &&
atomic_read(&dest->weight) > 0 && !is_overloaded(dest, svc))
goto out;
}
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index c90ea897c3f7..48f02453a5be 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -166,11 +166,11 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set)
/* select the first destination server, whose weight > 0 */
list_for_each_entry_rcu(e, &set->list, list) {
least = e->dest;
- if (least->flags & IP_VS_DEST_F_OVERLOAD)
+ if (atomic_read(&least->flags) & IP_VS_DEST_F_OVERLOAD)
continue;
- if ((atomic_read(&least->weight) > 0)
- && (least->flags & IP_VS_DEST_F_AVAILABLE)) {
+ if ((atomic_read(&least->weight) > 0)
+ && (atomic_read(&least->flags) & IP_VS_DEST_F_AVAILABLE)) {
loh = ip_vs_dest_conn_overhead(least);
goto nextstage;
}
@@ -181,13 +181,13 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set)
nextstage:
list_for_each_entry_continue_rcu(e, &set->list, list) {
dest = e->dest;
- if (dest->flags & IP_VS_DEST_F_OVERLOAD)
+ if (atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD)
continue;
doh = ip_vs_dest_conn_overhead(dest);
if (((__s64)loh * atomic_read(&dest->weight) >
- (__s64)doh * atomic_read(&least->weight))
- && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
+ (__s64)doh * atomic_read(&least->weight))
+ && (atomic_read(&dest->flags) & IP_VS_DEST_F_AVAILABLE)) {
least = dest;
loh = doh;
}
@@ -577,7 +577,7 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc)
* new connection.
*/
list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
- if (dest->flags & IP_VS_DEST_F_OVERLOAD)
+ if (atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD)
continue;
if (atomic_read(&dest->weight) > 0) {
@@ -593,7 +593,7 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc)
*/
nextstage:
list_for_each_entry_continue_rcu(dest, &svc->destinations, n_list) {
- if (dest->flags & IP_VS_DEST_F_OVERLOAD)
+ if (atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD)
continue;
doh = ip_vs_dest_conn_overhead(dest);
diff --git a/net/netfilter/ipvs/ip_vs_lc.c b/net/netfilter/ipvs/ip_vs_lc.c
index 38cc38c5d8bb..6acb3c904af5 100644
--- a/net/netfilter/ipvs/ip_vs_lc.c
+++ b/net/netfilter/ipvs/ip_vs_lc.c
@@ -38,7 +38,7 @@ ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
*/
list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
- if ((dest->flags & IP_VS_DEST_F_OVERLOAD) ||
+ if ((atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD) ||
atomic_read(&dest->weight) == 0)
continue;
doh = ip_vs_dest_conn_overhead(dest);
diff --git a/net/netfilter/ipvs/ip_vs_mh.c b/net/netfilter/ipvs/ip_vs_mh.c
index 020863047562..c322ed1754b7 100644
--- a/net/netfilter/ipvs/ip_vs_mh.c
+++ b/net/netfilter/ipvs/ip_vs_mh.c
@@ -80,7 +80,7 @@ static inline void generate_hash_secret(hsiphash_key_t *hash1,
static inline bool is_unavailable(struct ip_vs_dest *dest)
{
return atomic_read(&dest->weight) <= 0 ||
- dest->flags & IP_VS_DEST_F_OVERLOAD;
+ atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD;
}
/* Returns hash value for IPVS MH entry */
diff --git a/net/netfilter/ipvs/ip_vs_nq.c b/net/netfilter/ipvs/ip_vs_nq.c
index ada158c610ce..ffa4bfeb21d9 100644
--- a/net/netfilter/ipvs/ip_vs_nq.c
+++ b/net/netfilter/ipvs/ip_vs_nq.c
@@ -72,7 +72,7 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
- if (dest->flags & IP_VS_DEST_F_OVERLOAD ||
+ if (atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD ||
!atomic_read(&dest->weight))
continue;
diff --git a/net/netfilter/ipvs/ip_vs_ovf.c b/net/netfilter/ipvs/ip_vs_ovf.c
index c5c67df80a0b..f7f17dddbb05 100644
--- a/net/netfilter/ipvs/ip_vs_ovf.c
+++ b/net/netfilter/ipvs/ip_vs_ovf.c
@@ -33,7 +33,7 @@ ip_vs_ovf_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
*/
list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
w = atomic_read(&dest->weight);
- if ((dest->flags & IP_VS_DEST_F_OVERLOAD) ||
+ if ((atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD) ||
atomic_read(&dest->activeconns) > w ||
w == 0)
continue;
diff --git a/net/netfilter/ipvs/ip_vs_rr.c b/net/netfilter/ipvs/ip_vs_rr.c
index 4125ee561cdc..98453d205d6f 100644
--- a/net/netfilter/ipvs/ip_vs_rr.c
+++ b/net/netfilter/ipvs/ip_vs_rr.c
@@ -66,7 +66,7 @@ ip_vs_rr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
list_for_each_entry_continue_rcu(dest,
&svc->destinations,
n_list) {
- if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) &&
+ if (!(atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD) &&
atomic_read(&dest->weight) > 0)
/* HIT */
goto out;
diff --git a/net/netfilter/ipvs/ip_vs_sed.c b/net/netfilter/ipvs/ip_vs_sed.c
index 245a323c84cd..0249062d1360 100644
--- a/net/netfilter/ipvs/ip_vs_sed.c
+++ b/net/netfilter/ipvs/ip_vs_sed.c
@@ -75,7 +75,7 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
*/
list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
- if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) &&
+ if (!(atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD) &&
atomic_read(&dest->weight) > 0) {
least = dest;
loh = ip_vs_sed_dest_overhead(least);
@@ -90,7 +90,7 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
*/
nextstage:
list_for_each_entry_continue_rcu(dest, &svc->destinations, n_list) {
- if (dest->flags & IP_VS_DEST_F_OVERLOAD)
+ if (atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD)
continue;
doh = ip_vs_sed_dest_overhead(dest);
if ((__s64)loh * atomic_read(&dest->weight) >
diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c
index cd67066e3b26..343780b82c95 100644
--- a/net/netfilter/ipvs/ip_vs_sh.c
+++ b/net/netfilter/ipvs/ip_vs_sh.c
@@ -73,7 +73,7 @@ struct ip_vs_sh_state {
static inline bool is_unavailable(struct ip_vs_dest *dest)
{
return atomic_read(&dest->weight) <= 0 ||
- dest->flags & IP_VS_DEST_F_OVERLOAD;
+ atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD;
}
/*
diff --git a/net/netfilter/ipvs/ip_vs_twos.c b/net/netfilter/ipvs/ip_vs_twos.c
index dbb7f5fd4688..35fa4c6dc5cf 100644
--- a/net/netfilter/ipvs/ip_vs_twos.c
+++ b/net/netfilter/ipvs/ip_vs_twos.c
@@ -52,7 +52,7 @@ static struct ip_vs_dest *ip_vs_twos_schedule(struct ip_vs_service *svc,
/* Generate a random weight between [0,sum of all weights) */
list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
- if (!(dest->flags & IP_VS_DEST_F_OVERLOAD)) {
+ if (!(atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD)) {
weight = atomic_read(&dest->weight);
if (weight > 0) {
total_weight += weight;
@@ -75,7 +75,7 @@ static struct ip_vs_dest *ip_vs_twos_schedule(struct ip_vs_service *svc,
/* Pick two weighted servers */
list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
- if (dest->flags & IP_VS_DEST_F_OVERLOAD)
+ if (atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD)
continue;
weight = atomic_read(&dest->weight);
diff --git a/net/netfilter/ipvs/ip_vs_wlc.c b/net/netfilter/ipvs/ip_vs_wlc.c
index 9da445ca09a1..c2d09ac96fe8 100644
--- a/net/netfilter/ipvs/ip_vs_wlc.c
+++ b/net/netfilter/ipvs/ip_vs_wlc.c
@@ -47,7 +47,7 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
*/
list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
- if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) &&
+ if (!(atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD) &&
atomic_read(&dest->weight) > 0) {
least = dest;
loh = ip_vs_dest_conn_overhead(least);
@@ -62,7 +62,7 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
*/
nextstage:
list_for_each_entry_continue_rcu(dest, &svc->destinations, n_list) {
- if (dest->flags & IP_VS_DEST_F_OVERLOAD)
+ if (atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD)
continue;
doh = ip_vs_dest_conn_overhead(dest);
if ((__s64)loh * atomic_read(&dest->weight) >
diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c
index 2dcff1040da5..f21a75284971 100644
--- a/net/netfilter/ipvs/ip_vs_wrr.c
+++ b/net/netfilter/ipvs/ip_vs_wrr.c
@@ -176,7 +176,7 @@ ip_vs_wrr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
list_for_each_entry_continue_rcu(dest,
&svc->destinations,
n_list) {
- if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) &&
+ if (!(atomic_read(&dest->flags) & IP_VS_DEST_F_OVERLOAD) &&
atomic_read(&dest->weight) >= mark->cw)
goto found;
if (dest == stop)
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index ce542ed4b013..37b9671e4960 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -351,7 +351,7 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
* stored in dest_trash.
*/
if (!rt_dev_is_down(dst_dev_rcu(&rt->dst)) &&
- dest->flags & IP_VS_DEST_F_AVAILABLE)
+ atomic_read(&dest->flags) & IP_VS_DEST_F_AVAILABLE)
__ip_vs_dst_set(dest, dest_dst, &rt->dst, 0);
else
noref = 0;
@@ -530,7 +530,7 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
* stored in dest_trash.
*/
if (!rt_dev_is_down(dst_dev_rcu(&rt->dst)) &&
- dest->flags & IP_VS_DEST_F_AVAILABLE)
+ atomic_read(&dest->flags) & IP_VS_DEST_F_AVAILABLE)
__ip_vs_dst_set(dest, dest_dst, &rt->dst, cookie);
else
noref = 0;
^ permalink raw reply related
* Re: [PATCH net-next 2/6] net: stmmac: mediatek: add PERI_ETH_CTRLx register offset in platform data
From: Maxime Chevallier @ 2026-07-07 8:55 UTC (permalink / raw)
To: Louis-Alexis Eyraud, Andrew Lunn, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Richard Cochran, Matthias Brugger,
AngeloGioacchino Del Regno, Biao Huang, Maxime Coquelin,
Alexandre Torgue
Cc: rmk+kernel, kernel, netdev, devicetree, linux-kernel,
linux-arm-kernel, linux-mediatek, linux-stm32
In-Reply-To: <20260707-dwmac-mediatek-mt8189-v1-2-17f345eaaca3@collabora.com>
Hi,
On 7/7/26 10:21, Louis-Alexis Eyraud wrote:
> In preparation of newer SoC support, that use like MT8195 the Ethernet
> control registers from the peripheral configuration syscon but at a
> different base offset, add a new base offset in the variant platform
> data to access the PERI_ETH_CTRLx registers and use it in implemented
> methods.
>
> Signed-off-by: Louis-Alexis Eyraud <louisalexis.eyraud@collabora.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Maxime
^ permalink raw reply
* Re: [PATCH net-next v2 0/1] net: rnpgbe: fix mailbox endianness
From: patchwork-bot+netdevbpf @ 2026-07-07 8:50 UTC (permalink / raw)
To: Dong Yibo
Cc: andrew+netdev, davem, edumazet, kuba, pabeni, vadim.fedorenko,
netdev, linux-kernel, yaojun
In-Reply-To: <20260701032208.1843156-1-dong100@mucse.com>
Hello:
This patch was applied to netdev/net.git (main)
by Paolo Abeni <pabeni@redhat.com>:
On Wed, 1 Jul 2026 11:22:07 +0800 you wrote:
> The rnpgbe mailbox exchanges data through 32-bit MMIO registers in
> little-endian wire format. The original code had two problems:
>
> 1. FW structs with __le16/__le32 fields were cast to (u32 *) before
> reaching the transport, hiding the endian annotations from sparse.
>
> 2. No cpu_to_le32()/le32_to_cpu() conversion was performed between
> the CPU-endian MMIO values and the little-endian payload, causing
> data corruption on big-endian systems.
>
> [...]
Here is the summary with links:
- [net-next,v2,1/1] net: rnpgbe: fix mailbox endianness and remove pointer casts
https://git.kernel.org/netdev/net/c/d9d6d67f4c08
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
^ permalink raw reply
* [PATCH v4 net-next 14/14] net: enetc: use kzalloc_flex() for enetc_psfp_gate allocation
From: wei.fang @ 2026-07-07 8:18 UTC (permalink / raw)
To: claudiu.manoil, vladimir.oltean, xiaoning.wang, andrew+netdev,
davem, edumazet, kuba, pabeni, linux, wei.fang, chleroy,
maxime.chevallier
Cc: imx, netdev, linux-kernel, linuxppc-dev, linux-arm-kernel
In-Reply-To: <20260707081834.710730-1-wei.fang@oss.nxp.com>
From: Wei Fang <wei.fang@nxp.com>
Replace the open-coded struct_size() + kzalloc() pattern with the
kzalloc_flex() helper when allocating struct enetc_psfp_gate. This
removes the intermediate entries_size local variable and makes the
allocation site more concise.
Signed-off-by: Wei Fang <wei.fang@nxp.com>
---
drivers/net/ethernet/freescale/enetc/enetc_qos.c | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c
index 7b17bca24f26..2aa0fcaafcd2 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c
@@ -1135,7 +1135,6 @@ static int enetc_psfp_parse_clsflower(struct enetc_ndev_priv *priv,
struct flow_action_entry *entry;
struct action_gate_entry *e;
u8 sfi_overwrite = 0;
- int entries_size;
int i, err;
if (f->common.chain_index >= priv->psfp_cap.max_streamid) {
@@ -1242,8 +1241,7 @@ static int enetc_psfp_parse_clsflower(struct enetc_ndev_priv *priv,
goto free_filter;
}
- entries_size = struct_size(sgi, entries, entryg->gate.num_entries);
- sgi = kzalloc(entries_size, GFP_KERNEL);
+ sgi = kzalloc_flex(*sgi, entries, entryg->gate.num_entries);
if (!sgi) {
err = -ENOMEM;
goto free_filter;
--
2.34.1
^ permalink raw reply related
* [PATCH v4 net-next 13/14] net: enetc: use alloc_etherdev_mqs() to create netdev for VF driver
From: wei.fang @ 2026-07-07 8:18 UTC (permalink / raw)
To: claudiu.manoil, vladimir.oltean, xiaoning.wang, andrew+netdev,
davem, edumazet, kuba, pabeni, linux, wei.fang, chleroy,
maxime.chevallier
Cc: imx, netdev, linux-kernel, linuxppc-dev, linux-arm-kernel
In-Reply-To: <20260707081834.710730-1-wei.fang@oss.nxp.com>
From: Wei Fang <wei.fang@nxp.com>
The VF driver uses alloc_etherdev_mq() with ENETC_MAX_NUM_TXQS as the
queue count, which forces the TX and RX queue counts to be equal and
uses a compile-time constant rather than the actual hardware capability.
After enetc_get_si_caps() is called, si->num_tx_rings and
si->num_rx_rings reflect the actual number of rings assigned to the VF
by the PF. For the ENETC VF on LS1028A and the upcoming i.MX95/94, their
SoCs have no more than 6 CPUs, and the number of TX/RX rings allocated
to the VF is less than 8.
Therefore, switch to alloc_etherdev_mqs() so that the TX and RX queue
counts are set independently, each capped at ENETC_MAX_NUM_TXQS, based
on the actual number of rings assigned to the VF by the PF.
Note that if future SoCs have more than 6 CPUs and more than 6 RX rings
allocated to VFs, the size of the int_vector array in struct
enetc_ndev_priv will need to be modified. Similarly, if more than 8 TX
rings are allocated to each int_vector, ENETC_MAX_NUM_TXQS will also
need to be modified.
Signed-off-by: Wei Fang <wei.fang@nxp.com>
---
drivers/net/ethernet/freescale/enetc/enetc_vf.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
index 9cdb0a4d6baf..7dcb4a0246f5 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
@@ -317,7 +317,14 @@ static int enetc_vf_probe(struct pci_dev *pdev,
enetc_get_si_caps(si);
- ndev = alloc_etherdev_mq(sizeof(*priv), ENETC_MAX_NUM_TXQS);
+ /* Currently, the supported SoCs have a max of 6 CPUs and the VFs
+ * have less than 6 RX/TX rings. So no issues for these supported
+ * SoCs, but for future SoCs which have more CPUs or more TX/RX
+ * rings, all the related logic needs to be improved.
+ */
+ ndev = alloc_etherdev_mqs(sizeof(*priv),
+ min(si->num_tx_rings, ENETC_MAX_NUM_TXQS),
+ min(si->num_rx_rings, ENETC_MAX_NUM_TXQS));
if (!ndev) {
err = -ENOMEM;
dev_err(&pdev->dev, "netdev creation failed\n");
--
2.34.1
^ permalink raw reply related
* [PATCH v4 net-next 12/14] net: enetc: remove redundant num_vsi field from enetc_port_caps
From: wei.fang @ 2026-07-07 8:18 UTC (permalink / raw)
To: claudiu.manoil, vladimir.oltean, xiaoning.wang, andrew+netdev,
davem, edumazet, kuba, pabeni, linux, wei.fang, chleroy,
maxime.chevallier
Cc: imx, netdev, linux-kernel, linuxppc-dev, linux-arm-kernel
In-Reply-To: <20260707081834.710730-1-wei.fang@oss.nxp.com>
From: Wei Fang <wei.fang@nxp.com>
The num_vsi field in struct enetc_port_caps is populated by reading the
NUM_VSI field of the ECAPR1 register, which reports the number of VSIs
supported by the ENETC4 port. When CONFIG_PCI_IOV is enabled, this value
always matches pf->total_vfs, which is obtained from the read-only
PCI_SRIOV_TOTAL_VF register via pci_sriov_get_totalvfs() during probe.
Both ECAPR1[NUM_VSI] and PCI_SRIOV_TOTAL_VF are derived from the same
IERB register EaVFRIDAR[NUM_VF] (a 4-bit field), so they are guaranteed
to be equal. When CONFIG_PCI_IOV is disabled, pci_sriov_get_totalvfs()
returns 0, but this is benign since pci_enable_sriov() is also stubbed
to return -ENODEV, so no VF can be created, and enetc4_enable_all_si()
only enables the PF SI (PSI).
Since pf->total_vfs already reflects the number of VFs that can actually
be used, and is the established convention in the sibling FSL_ENETC PF
driver, there is no need to read and cache num_vsi separately in the port
capabilities structure. Remove the num_vsi field from enetc_port_caps,
and replace all uses of pf->caps.num_vsi with pf->total_vfs in the ring
allocation, MSI-X configuration, SI enable, and debugfs code paths.
Signed-off-by: Wei Fang <wei.fang@nxp.com>
---
.../ethernet/freescale/enetc/enetc4_debugfs.c | 13 ++-
.../net/ethernet/freescale/enetc/enetc4_pf.c | 86 ++++++++++++++-----
.../net/ethernet/freescale/enetc/enetc_pf.h | 1 -
3 files changed, 68 insertions(+), 32 deletions(-)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c b/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c
index be378bf8f74d..5029038bf99f 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c
@@ -28,17 +28,14 @@ static void enetc_show_si_mac_hash_filter(struct seq_file *s, int i)
static int enetc_mac_filter_show(struct seq_file *s, void *data)
{
- struct enetc_si *si = s->private;
- struct enetc_hw *hw = &si->hw;
+ struct enetc_pf *pf = enetc_si_priv(s->private);
+ struct enetc_hw *hw = &pf->si->hw;
+ int num_si = pf->total_vfs + 1;
struct maft_entry_data maft;
struct ntmp_user *user;
- struct enetc_pf *pf;
u32 val, entry_id;
- int i, num_si;
int err = 0;
-
- pf = enetc_si_priv(si);
- num_si = pf->caps.num_vsi + 1;
+ int i;
val = enetc_port_rd(hw, ENETC4_PSIPMMR);
for (i = 0; i < num_si; i++) {
@@ -52,7 +49,7 @@ static int enetc_mac_filter_show(struct seq_file *s, void *data)
for (i = 0; i < num_si; i++)
enetc_show_si_mac_hash_filter(s, i);
- user = &si->ntmp_user;
+ user = &pf->si->ntmp_user;
rtnl_lock();
if (bitmap_empty(user->maft_eid_bitmap, user->maft_num_entries))
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
index cab79f81d6fe..fcfbabb29d22 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
@@ -23,7 +23,6 @@ static void enetc4_get_port_caps(struct enetc_pf *pf)
u32 val;
val = enetc_port_rd(hw, ENETC4_ECAPR1);
- pf->caps.num_vsi = (val & ECAPR1_NUM_VSI) >> 24;
pf->caps.num_msix = ((val & ECAPR1_NUM_MSIX) >> 12) + 1;
val = enetc_port_rd(hw, ENETC4_ECAPR2);
@@ -255,34 +254,35 @@ static void enetc4_default_rings_allocation(struct enetc_pf *pf)
{
struct enetc_hw *hw = &pf->si->hw;
u32 num_rx_bdr, num_tx_bdr, val;
+ int num_vfs = pf->total_vfs;
u32 vf_tx_bdr, vf_rx_bdr;
int i, rx_rem, tx_rem;
- if (pf->caps.num_rx_bdr < ENETC_SI_MAX_RING_NUM + pf->caps.num_vsi)
- num_rx_bdr = pf->caps.num_rx_bdr - pf->caps.num_vsi;
+ if (pf->caps.num_rx_bdr < ENETC_SI_MAX_RING_NUM + num_vfs)
+ num_rx_bdr = pf->caps.num_rx_bdr - num_vfs;
else
num_rx_bdr = ENETC_SI_MAX_RING_NUM;
- if (pf->caps.num_tx_bdr < ENETC_SI_MAX_RING_NUM + pf->caps.num_vsi)
- num_tx_bdr = pf->caps.num_tx_bdr - pf->caps.num_vsi;
+ if (pf->caps.num_tx_bdr < ENETC_SI_MAX_RING_NUM + num_vfs)
+ num_tx_bdr = pf->caps.num_tx_bdr - num_vfs;
else
num_tx_bdr = ENETC_SI_MAX_RING_NUM;
val = enetc4_psicfgr0_val_construct(false, num_tx_bdr, num_rx_bdr);
enetc_port_wr(hw, ENETC4_PSICFGR0(0), val);
- if (!pf->caps.num_vsi)
+ if (!num_vfs)
return;
num_rx_bdr = pf->caps.num_rx_bdr - num_rx_bdr;
- rx_rem = num_rx_bdr % pf->caps.num_vsi;
- num_rx_bdr = num_rx_bdr / pf->caps.num_vsi;
+ rx_rem = num_rx_bdr % num_vfs;
+ num_rx_bdr = num_rx_bdr / num_vfs;
num_tx_bdr = pf->caps.num_tx_bdr - num_tx_bdr;
- tx_rem = num_tx_bdr % pf->caps.num_vsi;
- num_tx_bdr = num_tx_bdr / pf->caps.num_vsi;
+ tx_rem = num_tx_bdr % num_vfs;
+ num_tx_bdr = num_tx_bdr / num_vfs;
- for (i = 0; i < pf->caps.num_vsi; i++) {
+ for (i = 0; i < num_vfs; i++) {
vf_tx_bdr = (i < tx_rem) ? num_tx_bdr + 1 : num_tx_bdr;
vf_rx_bdr = (i < rx_rem) ? num_rx_bdr + 1 : num_rx_bdr;
val = enetc4_psicfgr0_val_construct(true, vf_tx_bdr, vf_rx_bdr);
@@ -298,27 +298,67 @@ static void enetc4_allocate_si_rings(struct enetc_pf *pf)
/* Allocate the number of MSI-X vectors for per SI. */
static void enetc4_set_si_msix_num(struct enetc_pf *pf)
{
+ int valid_num_si = pf->total_vfs + 1;
struct enetc_hw *hw = &pf->si->hw;
- int i, num_msix, total_si;
+ int i, num_msix, num_vsi;
u32 val;
- total_si = pf->caps.num_vsi + 1;
+ val = enetc_port_rd(hw, ENETC4_ECAPR1);
+ num_vsi = FIELD_GET(ECAPR1_NUM_VSI, val);
+
+ /* The PSIaCFGR2[NUM_MSIX] indicates the number of MSI-X allocated to
+ * the SI is NUM_MSIX + 1, so the minimum number of MSI-X allocated to
+ * each SI is 1. The total number of MSI-X allocated to PSI and VSIs
+ * cannot exceed the total number of MSI-X owned by this ENETC, which
+ * is ECAPR1[NUM_MSIX]. Otherwise, when multiple ENETC instances exist,
+ * it will affect other ENETCs whose MSI-X interrupts cannot be
+ * generated. This is similar to out-of-bounds array access: the array
+ * itself is not affected, but adjacent arrays will be corrupted.
+ *
+ * pf->total_vfs is 0 if CONFIG_PCI_IOV is disabled. If the hardware
+ * itself supports SR-IOV, then when allocating the number of MSIXs to
+ * the SI, it must be taken into account that the VSI has at least 1
+ * MSIX, and the total number of MSIXs of all SIs cannot exceed
+ * ECAPR1[NUM_MSIX].
+ */
+ if (!pf->total_vfs && num_vsi) {
+ /* Because each SI has at least one MSIX, and from the hardware
+ * perspective, pf->caps.num_msix will always be greater than
+ * num_vsi. So num_msix is always greater than or equal to 0.
+ */
+ num_msix = pf->caps.num_msix - num_vsi - 1;
+ if (num_msix > PSICFGR2_NUM_MSIX)
+ num_msix = PSICFGR2_NUM_MSIX;
+ enetc_port_wr(hw, ENETC4_PSICFGR2(0), num_msix);
- num_msix = pf->caps.num_msix / total_si +
- pf->caps.num_msix % total_si - 1;
- val = num_msix & PSICFGR2_NUM_MSIX;
- enetc_port_wr(hw, ENETC4_PSICFGR2(0), val);
+ for (i = 0; i < num_vsi; i++)
+ enetc_port_wr(hw, ENETC4_PSICFGR2(i + 1), 0);
- num_msix = pf->caps.num_msix / total_si - 1;
- val = num_msix & PSICFGR2_NUM_MSIX;
- for (i = 0; i < pf->caps.num_vsi; i++)
- enetc_port_wr(hw, ENETC4_PSICFGR2(i + 1), val);
+ return;
+ }
+
+ /* Likewise, from the hardware perspective pf->caps.num_msix is always
+ * greater than valid_num_si. So num_msix is always greater than or
+ * equal to 0.
+ */
+ num_msix = pf->caps.num_msix / valid_num_si +
+ pf->caps.num_msix % valid_num_si - 1;
+ if (num_msix > PSICFGR2_NUM_MSIX)
+ num_msix = PSICFGR2_NUM_MSIX;
+ enetc_port_wr(hw, ENETC4_PSICFGR2(0), num_msix);
+
+ num_msix = pf->caps.num_msix / valid_num_si - 1;
+ if (num_msix > PSICFGR2_NUM_MSIX)
+ num_msix = PSICFGR2_NUM_MSIX;
+
+ for (i = 0; i < pf->total_vfs; i++)
+ enetc_port_wr(hw, ENETC4_PSICFGR2(i + 1), num_msix);
}
static void enetc4_enable_all_si(struct enetc_pf *pf)
{
struct enetc_hw *hw = &pf->si->hw;
- int num_si = pf->caps.num_vsi + 1;
+ int num_si = pf->total_vfs + 1;
u32 si_bitmap = 0;
int i;
@@ -339,7 +379,7 @@ static void enetc4_configure_port_si(struct enetc_pf *pf)
enetc_port_wr(hw, ENETC4_PSIVLANFMR, PSIVLANFMR_VS);
/* Enforce VLAN promiscuous mode for all SIs */
- for (int i = 0; i < pf->caps.num_vsi + 1; i++)
+ for (int i = 0; i < pf->total_vfs + 1; i++)
enetc_set_si_vlan_promisc(pf->si, i, true);
/* Disable SI MAC multicast & unicast promiscuous */
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.h b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
index 1bd3063a3be3..56d23a8a11a0 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
@@ -17,7 +17,6 @@ struct enetc_vf_state {
};
struct enetc_port_caps {
- int num_vsi;
int num_msix;
int num_rx_bdr;
int num_tx_bdr;
--
2.34.1
^ permalink raw reply related
* [PATCH v4 net-next 11/14] net: enetc: move enetc_set_si_vlan_promisc() to enetc_pf_common.c
From: wei.fang @ 2026-07-07 8:18 UTC (permalink / raw)
To: claudiu.manoil, vladimir.oltean, xiaoning.wang, andrew+netdev,
davem, edumazet, kuba, pabeni, linux, wei.fang, chleroy,
maxime.chevallier
Cc: imx, netdev, linux-kernel, linuxppc-dev, linux-arm-kernel
In-Reply-To: <20260707081834.710730-1-wei.fang@oss.nxp.com>
From: Wei Fang <wei.fang@nxp.com>
The PSIPVMR in ENETC v4 has the same bit layout and functionality as the
PSIPVMR register in ENETC v1: bit n (n <= 15) controls VLAN promiscuous
mode for SI n. The only difference between the two hardware generations
is the register address offset.
Since the register functionality is identical, the VLAN promiscuous mode
setting code can be shared between ENETC v1 and v4 drivers.
Move enetc_set_si_vlan_promisc() from enetc_pf.c to enetc_pf_common.c
and export it so that it can be shared between the two drivers. Add a
revision check using is_enetc_rev1() to select the correct register
offset (ENETC_PSIPVMR for v1 and ENETC4_PSIPVMR for v4) while keeping
the same logic.
Remove the v4-specific enetc4_pf_set_si_vlan_promisc() from enetc4_pf.c
and replace its call site with the new common enetc_set_si_vlan_promisc()
to eliminate code duplication.
Signed-off-by: Wei Fang <wei.fang@nxp.com>
---
.../net/ethernet/freescale/enetc/enetc4_pf.c | 17 ++------------
.../net/ethernet/freescale/enetc/enetc_pf.c | 16 --------------
.../freescale/enetc/enetc_pf_common.c | 22 +++++++++++++++++++
.../freescale/enetc/enetc_pf_common.h | 1 +
4 files changed, 25 insertions(+), 31 deletions(-)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
index 505e4abf6c37..cab79f81d6fe 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
@@ -295,18 +295,6 @@ static void enetc4_allocate_si_rings(struct enetc_pf *pf)
enetc4_default_rings_allocation(pf);
}
-static void enetc4_pf_set_si_vlan_promisc(struct enetc_hw *hw, int si, bool en)
-{
- u32 val = enetc_port_rd(hw, ENETC4_PSIPVMR);
-
- if (en)
- val |= BIT(si);
- else
- val &= ~BIT(si);
-
- enetc_port_wr(hw, ENETC4_PSIPVMR, val);
-}
-
/* Allocate the number of MSI-X vectors for per SI. */
static void enetc4_set_si_msix_num(struct enetc_pf *pf)
{
@@ -352,7 +340,7 @@ static void enetc4_configure_port_si(struct enetc_pf *pf)
/* Enforce VLAN promiscuous mode for all SIs */
for (int i = 0; i < pf->caps.num_vsi + 1; i++)
- enetc4_pf_set_si_vlan_promisc(hw, i, true);
+ enetc_set_si_vlan_promisc(pf->si, i, true);
/* Disable SI MAC multicast & unicast promiscuous */
enetc_port_wr(hw, ENETC4_PSIPMMR, 0);
@@ -518,12 +506,11 @@ static int enetc4_pf_set_features(struct net_device *ndev,
{
netdev_features_t changed = ndev->features ^ features;
struct enetc_ndev_priv *priv = netdev_priv(ndev);
- struct enetc_hw *hw = &priv->si->hw;
if (changed & NETIF_F_HW_VLAN_CTAG_FILTER) {
bool promisc_en = !(features & NETIF_F_HW_VLAN_CTAG_FILTER);
- enetc4_pf_set_si_vlan_promisc(hw, 0, promisc_en);
+ enetc_set_si_vlan_promisc(priv->si, 0, promisc_en);
}
if (changed & NETIF_F_LOOPBACK)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index afc02ed62c77..a509929f89f2 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -42,22 +42,6 @@ static void enetc_pf_destroy_pcs(struct phylink_pcs *pcs)
lynx_pcs_destroy(pcs);
}
-static void enetc_set_si_vlan_promisc(struct enetc_si *si, int si_id,
- bool promisc)
-{
- struct enetc_hw *hw = &si->hw;
- u32 val;
-
- val = enetc_port_rd(hw, ENETC_PSIPVMR);
-
- if (promisc)
- val |= PSIPVMR_SI_VLAN_P(si_id);
- else
- val &= ~PSIPVMR_SI_VLAN_P(si_id);
-
- enetc_port_wr(hw, ENETC_PSIPVMR, val);
-}
-
static void enetc_set_isol_vlan(struct enetc_hw *hw, int si, u16 vlan, u8 qos)
{
u32 val = 0;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
index 781b22198ca8..d32a195a04c9 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
@@ -171,6 +171,28 @@ void enetc_set_si_mc_hash_filter(struct enetc_si *si, int si_id, u64 hash)
}
EXPORT_SYMBOL_GPL(enetc_set_si_mc_hash_filter);
+void enetc_set_si_vlan_promisc(struct enetc_si *si, int si_id, bool promisc)
+{
+ struct enetc_hw *hw = &si->hw;
+ int psipvmr_off;
+ u32 val;
+
+ if (is_enetc_rev1(si))
+ psipvmr_off = ENETC_PSIPVMR;
+ else
+ psipvmr_off = ENETC4_PSIPVMR;
+
+ val = enetc_port_rd(hw, psipvmr_off);
+
+ if (promisc)
+ val |= PSIPVMR_SI_VLAN_P(si_id);
+ else
+ val &= ~PSIPVMR_SI_VLAN_P(si_id);
+
+ enetc_port_wr(hw, psipvmr_off, val);
+}
+EXPORT_SYMBOL_GPL(enetc_set_si_vlan_promisc);
+
void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
const struct net_device_ops *ndev_ops)
{
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h
index bf9029b0a017..8243ce0de57f 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h
@@ -21,6 +21,7 @@ void enetc_set_si_uc_promisc(struct enetc_si *si, int si_id, bool promisc);
void enetc_set_si_mc_promisc(struct enetc_si *si, int si_id, bool promisc);
void enetc_set_si_uc_hash_filter(struct enetc_si *si, int si_id, u64 hash);
void enetc_set_si_mc_hash_filter(struct enetc_si *si, int si_id, u64 hash);
+void enetc_set_si_vlan_promisc(struct enetc_si *si, int si_id, bool promisc);
static inline u16 enetc_get_ip_revision(struct enetc_hw *hw)
{
--
2.34.1
^ permalink raw reply related
* [PATCH v4 net-next 10/14] net: enetc: refactor SI VLAN promiscuous mode configuration
From: wei.fang @ 2026-07-07 8:18 UTC (permalink / raw)
To: claudiu.manoil, vladimir.oltean, xiaoning.wang, andrew+netdev,
davem, edumazet, kuba, pabeni, linux, wei.fang, chleroy,
maxime.chevallier
Cc: imx, netdev, linux-kernel, linuxppc-dev, linux-arm-kernel
In-Reply-To: <20260707081834.710730-1-wei.fang@oss.nxp.com>
From: Wei Fang <wei.fang@nxp.com>
Remove the enetc_set_vlan_promisc(), enetc_enable_si_vlan_promisc() and
enetc_disable_si_vlan_promisc() functions, and introduce a new unified
function enetc_set_si_vlan_promisc() to enable or disable VLAN
promiscuous mode for a specific SI. This simplifies the logic and makes
the interface more straightforward. The vlan_promisc_simap field in
struct enetc_pf is no longer needed to track the current state.
As ENETC V4 only changes the address offset of PSIPVMR register compared
to V1 without any functional difference, enetc_set_si_vlan_promisc() can
be moved to enetc_pf_common.c in the future with minor adjustments to be
reused by the ENETC V4 driver
Signed-off-by: Wei Fang <wei.fang@nxp.com>
---
.../net/ethernet/freescale/enetc/enetc_hw.h | 5 ++-
.../net/ethernet/freescale/enetc/enetc_pf.c | 36 ++++++++-----------
.../net/ethernet/freescale/enetc/enetc_pf.h | 1 -
3 files changed, 16 insertions(+), 26 deletions(-)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index 66bfda60da9c..16da732dc5de 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -185,9 +185,8 @@ enum enetc_bdr_type {TX, RX};
#define PSIPMMR_SI_MAC_MP(n) BIT((n) + 16)
#define ENETC_PSIPVMR 0x001c
-#define ENETC_VLAN_PROMISC_MAP_ALL 0x7
-#define ENETC_PSIPVMR_SET_VP(simap) ((simap) & 0x7)
-#define ENETC_PSIPVMR_SET_VUTA(simap) (((simap) & 0x7) << 16)
+#define PSIPVMR_SI_VLAN_P(n) BIT(n) /* n = SI index */
+
#define ENETC_PSIPMAR0(n) (0x0100 + (n) * 0x8) /* n = SI index */
#define ENETC_PSIPMAR1(n) (0x0104 + (n) * 0x8)
#define ENETC_PVCLCTR 0x0208
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index db2a800a7aaf..afc02ed62c77 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -42,24 +42,20 @@ static void enetc_pf_destroy_pcs(struct phylink_pcs *pcs)
lynx_pcs_destroy(pcs);
}
-static void enetc_set_vlan_promisc(struct enetc_hw *hw, char si_map)
+static void enetc_set_si_vlan_promisc(struct enetc_si *si, int si_id,
+ bool promisc)
{
- u32 val = enetc_port_rd(hw, ENETC_PSIPVMR);
+ struct enetc_hw *hw = &si->hw;
+ u32 val;
- val &= ~ENETC_PSIPVMR_SET_VP(ENETC_VLAN_PROMISC_MAP_ALL);
- enetc_port_wr(hw, ENETC_PSIPVMR, ENETC_PSIPVMR_SET_VP(si_map) | val);
-}
+ val = enetc_port_rd(hw, ENETC_PSIPVMR);
-static void enetc_enable_si_vlan_promisc(struct enetc_pf *pf, int si_idx)
-{
- pf->vlan_promisc_simap |= BIT(si_idx);
- enetc_set_vlan_promisc(&pf->si->hw, pf->vlan_promisc_simap);
-}
+ if (promisc)
+ val |= PSIPVMR_SI_VLAN_P(si_id);
+ else
+ val &= ~PSIPVMR_SI_VLAN_P(si_id);
-static void enetc_disable_si_vlan_promisc(struct enetc_pf *pf, int si_idx)
-{
- pf->vlan_promisc_simap &= ~BIT(si_idx);
- enetc_set_vlan_promisc(&pf->si->hw, pf->vlan_promisc_simap);
+ enetc_port_wr(hw, ENETC_PSIPVMR, val);
}
static void enetc_set_isol_vlan(struct enetc_hw *hw, int si, u16 vlan, u8 qos)
@@ -441,10 +437,9 @@ static void enetc_configure_port(struct enetc_pf *pf)
/* split up RFS entries */
enetc_port_assign_rfs_entries(pf->si);
-
/* enforce VLAN promisc mode for all SIs */
- pf->vlan_promisc_simap = ENETC_VLAN_PROMISC_MAP_ALL;
- enetc_set_vlan_promisc(hw, pf->vlan_promisc_simap);
+ for (int i = 0; i < pf->total_vfs + 1; i++)
+ enetc_set_si_vlan_promisc(pf->si, i, true);
enetc_port_wr(hw, ENETC_PSIPMMR, 0);
@@ -466,12 +461,9 @@ static int enetc_pf_set_features(struct net_device *ndev,
}
if (changed & NETIF_F_HW_VLAN_CTAG_FILTER) {
- struct enetc_pf *pf = enetc_si_priv(priv->si);
+ bool promisc = !(features & NETIF_F_HW_VLAN_CTAG_FILTER);
- if (!!(features & NETIF_F_HW_VLAN_CTAG_FILTER))
- enetc_disable_si_vlan_promisc(pf, 0);
- else
- enetc_enable_si_vlan_promisc(pf, 0);
+ enetc_set_si_vlan_promisc(priv->si, 0, promisc);
}
if (changed & NETIF_F_LOOPBACK)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.h b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
index 7e886dc49997..1bd3063a3be3 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
@@ -45,7 +45,6 @@ struct enetc_pf {
struct work_struct msg_task;
char msg_int_name[ENETC_INT_NAME_MAX];
- char vlan_promisc_simap; /* bitmap of SIs in VLAN promisc mode */
DECLARE_BITMAP(vlan_ht_filter, ENETC_VLAN_HT_SIZE);
DECLARE_BITMAP(active_vlans, VLAN_N_VID);
--
2.34.1
^ permalink raw reply related
* [PATCH v4 net-next 09/14] net: enetc: open-code enetc4_set_default_si_vlan_promisc()
From: wei.fang @ 2026-07-07 8:18 UTC (permalink / raw)
To: claudiu.manoil, vladimir.oltean, xiaoning.wang, andrew+netdev,
davem, edumazet, kuba, pabeni, linux, wei.fang, chleroy,
maxime.chevallier
Cc: imx, netdev, linux-kernel, linuxppc-dev, linux-arm-kernel
In-Reply-To: <20260707081834.710730-1-wei.fang@oss.nxp.com>
From: Wei Fang <wei.fang@nxp.com>
The function enetc4_set_default_si_vlan_promisc() is only called once,
from enetc4_configure_port_si(). Open-code the loop at the call site
and remove the single-use wrapper.
Signed-off-by: Wei Fang <wei.fang@nxp.com>
---
drivers/net/ethernet/freescale/enetc/enetc4_pf.c | 15 +++------------
1 file changed, 3 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
index 859b02f5170a..505e4abf6c37 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
@@ -307,17 +307,6 @@ static void enetc4_pf_set_si_vlan_promisc(struct enetc_hw *hw, int si, bool en)
enetc_port_wr(hw, ENETC4_PSIPVMR, val);
}
-static void enetc4_set_default_si_vlan_promisc(struct enetc_pf *pf)
-{
- struct enetc_hw *hw = &pf->si->hw;
- int num_si = pf->caps.num_vsi + 1;
- int i;
-
- /* enforce VLAN promiscuous mode for all SIs */
- for (i = 0; i < num_si; i++)
- enetc4_pf_set_si_vlan_promisc(hw, i, true);
-}
-
/* Allocate the number of MSI-X vectors for per SI. */
static void enetc4_set_si_msix_num(struct enetc_pf *pf)
{
@@ -361,7 +350,9 @@ static void enetc4_configure_port_si(struct enetc_pf *pf)
/* Outer VLAN tag will be used for VLAN filtering */
enetc_port_wr(hw, ENETC4_PSIVLANFMR, PSIVLANFMR_VS);
- enetc4_set_default_si_vlan_promisc(pf);
+ /* Enforce VLAN promiscuous mode for all SIs */
+ for (int i = 0; i < pf->caps.num_vsi + 1; i++)
+ enetc4_pf_set_si_vlan_promisc(hw, i, true);
/* Disable SI MAC multicast & unicast promiscuous */
enetc_port_wr(hw, ENETC4_PSIPMMR, 0);
--
2.34.1
^ permalink raw reply related
* [PATCH v4 net-next 08/14] net: enetc: remove invalid code from enetc4_pl_mac_link_up()
From: wei.fang @ 2026-07-07 8:18 UTC (permalink / raw)
To: claudiu.manoil, vladimir.oltean, xiaoning.wang, andrew+netdev,
davem, edumazet, kuba, pabeni, linux, wei.fang, chleroy,
maxime.chevallier
Cc: imx, netdev, linux-kernel, linuxppc-dev, linux-arm-kernel
In-Reply-To: <20260707081834.710730-1-wei.fang@oss.nxp.com>
From: Wei Fang <wei.fang@nxp.com>
When adding phylink MAC operations support to the NETC switch driver,
Russell King pointed out several pieces of invalid logic in the
.mac_link_up() implementation (see [1] and [2]):
1) Half-duplex backpressure is not supported by the kernel, Ethernet
relies on packet dropping for congestion management.
2) phylink_autoneg_inband() is unnecessary, as RGMII in-band status is
not supported.
3) TX and RX pause are disabled in half-duplex mode, so there is no
need to override them in .mac_link_up().
The same invalid logic is also present in enetc4_pl_mac_link_up(), so
remove the invalid code from it.
Given enetc4_set_hd_flow_control() is removed, pf->caps.half_duplex has
also become useless and should therefore be removed as well.
Link: https://lore.kernel.org/imx/acEIQqI-_oyCym8O@shell.armlinux.org.uk/ # 1
Link: https://lore.kernel.org/imx/acEFwqmAvWls_9Ef@shell.armlinux.org.uk/ # 2
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
---
.../net/ethernet/freescale/enetc/enetc4_hw.h | 2 -
.../net/ethernet/freescale/enetc/enetc4_pf.c | 38 +------------------
.../net/ethernet/freescale/enetc/enetc_pf.h | 1 -
3 files changed, 1 insertion(+), 40 deletions(-)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
index dea1fd0b8175..09025e7a2a3a 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
@@ -135,7 +135,6 @@
#define ENETC4_PSIVHFR1(a) ((a) * 0x80 + 0x2064)
#define ENETC4_PMCAPR 0x4004
-#define PMCAPR_HD BIT(8)
#define PMCAPR_FP GENMASK(10, 9)
/* Port capability register */
@@ -198,7 +197,6 @@
#define PM_CMD_CFG_CNT_FRM_EN BIT(13)
#define PM_CMD_CFG_TXP BIT(15)
#define PM_CMD_CFG_SEND_IDLE BIT(16)
-#define PM_CMD_CFG_HD_FCEN BIT(18)
#define PM_CMD_CFG_SFD BIT(21)
#define PM_CMD_CFG_TX_FLUSH BIT(22)
#define PM_CMD_CFG_TX_LOWP_EN BIT(23)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
index 75ee117e9b1d..859b02f5170a 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
@@ -29,9 +29,6 @@ static void enetc4_get_port_caps(struct enetc_pf *pf)
val = enetc_port_rd(hw, ENETC4_ECAPR2);
pf->caps.num_rx_bdr = (val & ECAPR2_NUM_RX_BDR) >> 16;
pf->caps.num_tx_bdr = val & ECAPR2_NUM_TX_BDR;
-
- val = enetc_port_rd(hw, ENETC4_PMCAPR);
- pf->caps.half_duplex = (val & PMCAPR_HD) ? 1 : 0;
}
static void enetc4_get_psi_hw_features(struct enetc_si *si)
@@ -588,11 +585,6 @@ static void enetc4_mac_config(struct enetc_pf *pf, unsigned int mode,
case PHY_INTERFACE_MODE_RGMII_RXID:
case PHY_INTERFACE_MODE_RGMII_TXID:
val |= IFMODE_RGMII;
- /* We need to enable auto-negotiation for the MAC
- * if its RGMII interface support In-Band status.
- */
- if (phylink_autoneg_inband(mode))
- val |= PM_IF_MODE_ENA;
break;
case PHY_INTERFACE_MODE_RMII:
val |= IFMODE_RMII;
@@ -695,22 +687,6 @@ static void enetc4_set_rmii_mac(struct enetc_pf *pf, int speed, int duplex)
enetc_port_mac_wr(si, ENETC4_PM_IF_MODE(0), val);
}
-static void enetc4_set_hd_flow_control(struct enetc_pf *pf, bool enable)
-{
- struct enetc_si *si = pf->si;
- u32 old_val, val;
-
- if (!pf->caps.half_duplex)
- return;
-
- old_val = enetc_port_mac_rd(si, ENETC4_PM_CMD_CFG(0));
- val = u32_replace_bits(old_val, enable ? 1 : 0, PM_CMD_CFG_HD_FCEN);
- if (val == old_val)
- return;
-
- enetc_port_mac_wr(si, ENETC4_PM_CMD_CFG(0), val);
-}
-
static void enetc4_set_rx_pause(struct enetc_pf *pf, bool rx_pause)
{
struct enetc_si *si = pf->si;
@@ -886,13 +862,11 @@ static void enetc4_pl_mac_link_up(struct phylink_config *config,
struct enetc_pf *pf = phylink_to_enetc_pf(config);
struct enetc_si *si = pf->si;
struct enetc_ndev_priv *priv;
- bool hd_fc = false;
priv = netdev_priv(si->ndev);
enetc4_set_port_speed(priv, speed);
- if (!phylink_autoneg_inband(mode) &&
- phy_interface_mode_is_rgmii(interface))
+ if (phy_interface_mode_is_rgmii(interface))
enetc4_set_rgmii_mac(pf, speed, duplex);
if (interface == PHY_INTERFACE_MODE_RMII)
@@ -904,18 +878,8 @@ static void enetc4_pl_mac_link_up(struct phylink_config *config,
*/
if (priv->active_offloads & ENETC_F_QBU)
tx_pause = false;
- } else { /* DUPLEX_HALF */
- if (tx_pause || rx_pause)
- hd_fc = true;
-
- /* As per 802.3 annex 31B, PAUSE frames are only supported
- * when the link is configured for full duplex operation.
- */
- tx_pause = false;
- rx_pause = false;
}
- enetc4_set_hd_flow_control(pf, hd_fc);
enetc4_set_tx_pause(pf, priv->num_rx_rings, tx_pause);
enetc4_set_rx_pause(pf, rx_pause);
enetc4_mac_tx_enable(pf);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.h b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
index 6f15f9ea1664..7e886dc49997 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
@@ -17,7 +17,6 @@ struct enetc_vf_state {
};
struct enetc_port_caps {
- u32 half_duplex:1;
int num_vsi;
int num_msix;
int num_rx_bdr;
--
2.34.1
^ permalink raw reply related
* [PATCH v4 net-next 07/14] net: enetc: differentiate phylink capabilities for pseudo-MAC and standalone MAC
From: wei.fang @ 2026-07-07 8:18 UTC (permalink / raw)
To: claudiu.manoil, vladimir.oltean, xiaoning.wang, andrew+netdev,
davem, edumazet, kuba, pabeni, linux, wei.fang, chleroy,
maxime.chevallier
Cc: imx, netdev, linux-kernel, linuxppc-dev, linux-arm-kernel
In-Reply-To: <20260707081834.710730-1-wei.fang@oss.nxp.com>
From: Claudiu Manoil <claudiu.manoil@nxp.com>
The ENETC pseudo-MACs are proprietary internal links that do not
implement any standard MII interface, so restrict their supported PHY
interface modes to PHY_INTERFACE_MODE_INTERNAL only.
Since pseudo-MACs can operate at any speed between 10Mbps and 25Gbps
in multiples of 10Mbps, set their MAC capabilities to cover the full
range of standard full-duplex speeds: 10/100/1000/2500/5000/10000/
20000/25000 Mbps.
For standalone ENETC (v4), expand the supported interface modes to
include 10GBASER in addition to the existing RGMII, SGMII, 1000BASEX,
2500BASEX and USXGMII modes, with MAC capabilities up to 10G. MAC_1000
is replaced with MAC_1000FD to explicitly exclude 1000M half-duplex,
which is not supported.
Note that 10GBASE-R mode of ENETC v4 has not supported yet, the current
patch adds PHY_INTERFACE_MODE_10GBASER simply as preparation for the
upcoming support of the 10GBASE-R mode.
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
---
drivers/net/ethernet/freescale/enetc/enetc.h | 2 +-
.../net/ethernet/freescale/enetc/enetc4_pf.c | 1 -
.../freescale/enetc/enetc_pf_common.c | 44 +++++++++++++------
3 files changed, 32 insertions(+), 15 deletions(-)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index 06a9f1ee0970..8839cfb49bcf 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
-/* Copyright 2017-2019 NXP */
+/* Copyright 2017-2019, 2025-2026 NXP */
#include <linux/timer.h>
#include <linux/pci.h>
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
index f24269a48c26..75ee117e9b1d 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
@@ -602,7 +602,6 @@ static void enetc4_mac_config(struct enetc_pf *pf, unsigned int mode,
val |= IFMODE_SGMII;
break;
case PHY_INTERFACE_MODE_10GBASER:
- case PHY_INTERFACE_MODE_XGMII:
case PHY_INTERFACE_MODE_USXGMII:
val |= IFMODE_XGMII;
break;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
index 3597cb81a7cc..781b22198ca8 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
-/* Copyright 2024 NXP */
+/* Copyright 2024-2026 NXP */
#include <linux/fsl/enetc_mdio.h>
#include <linux/of_mdio.h>
@@ -359,7 +359,8 @@ static bool enetc_port_has_pcs(struct enetc_pf *pf)
return (pf->if_mode == PHY_INTERFACE_MODE_SGMII ||
pf->if_mode == PHY_INTERFACE_MODE_1000BASEX ||
pf->if_mode == PHY_INTERFACE_MODE_2500BASEX ||
- pf->if_mode == PHY_INTERFACE_MODE_USXGMII);
+ pf->if_mode == PHY_INTERFACE_MODE_USXGMII ||
+ pf->if_mode == PHY_INTERFACE_MODE_10GBASER);
}
int enetc_mdiobus_create(struct enetc_pf *pf, struct device_node *node)
@@ -400,25 +401,42 @@ int enetc_phylink_create(struct enetc_ndev_priv *priv, struct device_node *node,
{
struct enetc_pf *pf = enetc_si_priv(priv->si);
struct phylink *phylink;
+ unsigned long mac_caps;
int err;
pf->phylink_config.dev = &priv->ndev->dev;
pf->phylink_config.type = PHYLINK_NETDEV;
- pf->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
- MAC_10 | MAC_100 | MAC_1000 | MAC_2500FD;
__set_bit(PHY_INTERFACE_MODE_INTERNAL,
pf->phylink_config.supported_interfaces);
- __set_bit(PHY_INTERFACE_MODE_SGMII,
- pf->phylink_config.supported_interfaces);
- __set_bit(PHY_INTERFACE_MODE_1000BASEX,
- pf->phylink_config.supported_interfaces);
- __set_bit(PHY_INTERFACE_MODE_2500BASEX,
- pf->phylink_config.supported_interfaces);
- __set_bit(PHY_INTERFACE_MODE_USXGMII,
- pf->phylink_config.supported_interfaces);
- phy_interface_set_rgmii(pf->phylink_config.supported_interfaces);
+ mac_caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE;
+ if (!enetc_is_pseudo_mac(priv->si)) {
+ mac_caps |= MAC_10 | MAC_100 | MAC_1000FD | MAC_2500FD;
+
+ __set_bit(PHY_INTERFACE_MODE_SGMII,
+ pf->phylink_config.supported_interfaces);
+ __set_bit(PHY_INTERFACE_MODE_1000BASEX,
+ pf->phylink_config.supported_interfaces);
+ __set_bit(PHY_INTERFACE_MODE_2500BASEX,
+ pf->phylink_config.supported_interfaces);
+ __set_bit(PHY_INTERFACE_MODE_USXGMII,
+ pf->phylink_config.supported_interfaces);
+
+ if (!is_enetc_rev1(priv->si)) {
+ mac_caps |= MAC_5000FD | MAC_10000FD;
+ __set_bit(PHY_INTERFACE_MODE_10GBASER,
+ pf->phylink_config.supported_interfaces);
+ }
+
+ phy_interface_set_rgmii(pf->phylink_config.supported_interfaces);
+ } else {
+ mac_caps |= MAC_10FD | MAC_100FD | MAC_1000FD | MAC_2500FD |
+ MAC_5000FD | MAC_10000FD | MAC_20000FD |
+ MAC_25000FD;
+ }
+
+ pf->phylink_config.mac_capabilities = mac_caps;
phylink = phylink_create(&pf->phylink_config, of_fwnode_handle(node),
pf->if_mode, ops);
if (IS_ERR(phylink)) {
--
2.34.1
^ permalink raw reply related
* [PATCH v4 net-next 06/14] net: enetc: simplify enetc4_set_port_speed()
From: wei.fang @ 2026-07-07 8:18 UTC (permalink / raw)
To: claudiu.manoil, vladimir.oltean, xiaoning.wang, andrew+netdev,
davem, edumazet, kuba, pabeni, linux, wei.fang, chleroy,
maxime.chevallier
Cc: imx, netdev, linux-kernel, linuxppc-dev, linux-arm-kernel
In-Reply-To: <20260707081834.710730-1-wei.fang@oss.nxp.com>
From: Wei Fang <wei.fang@nxp.com>
Since phylink may pass SPEED_UNKNOWN to mac_link_up, handle it
explicitly by defaulting to SPEED_10, then replace the switch statement
with a direct call to PCR_PSPEED_VAL(). Also update PCR_PSPEED_VAL() to
use FIELD_PREP() for proper field masking instead of an open-coded shift.
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
---
.../net/ethernet/freescale/enetc/enetc4_hw.h | 2 +-
.../net/ethernet/freescale/enetc/enetc4_pf.c | 25 +++++++------------
2 files changed, 10 insertions(+), 17 deletions(-)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
index 6a8f2ed56017..dea1fd0b8175 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
@@ -148,7 +148,7 @@
#define PCR_L2DOSE BIT(4)
#define PCR_TIMER_CS BIT(8)
#define PCR_PSPEED GENMASK(29, 16)
-#define PCR_PSPEED_VAL(speed) (((speed) / 10 - 1) << 16)
+#define PCR_PSPEED_VAL(s) FIELD_PREP(PCR_PSPEED, ((s) / 10 - 1))
/* Port MAC address register 0/1 */
#define ENETC4_PMAR0 0x4020
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
index b966637572a7..f24269a48c26 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
@@ -628,26 +628,19 @@ static void enetc4_set_port_speed(struct enetc_ndev_priv *priv, int speed)
u32 old_speed = priv->speed;
u32 val;
+ /* If the speed is unknown, use the minimum value */
+ if (speed == SPEED_UNKNOWN) {
+ speed = SPEED_10;
+ dev_warn(priv->dev, "Speed unknown, default is 10Mbps\n");
+ }
+
if (speed == old_speed)
return;
- val = enetc_port_rd(&priv->si->hw, ENETC4_PCR);
- val &= ~PCR_PSPEED;
-
- switch (speed) {
- case SPEED_100:
- case SPEED_1000:
- case SPEED_2500:
- case SPEED_10000:
- val |= (PCR_PSPEED & PCR_PSPEED_VAL(speed));
- break;
- case SPEED_10:
- default:
- val |= (PCR_PSPEED & PCR_PSPEED_VAL(SPEED_10));
- }
-
- priv->speed = speed;
+ val = enetc_port_rd(&priv->si->hw, ENETC4_PCR) & (~PCR_PSPEED);
+ val |= PCR_PSPEED_VAL(speed);
enetc_port_wr(&priv->si->hw, ENETC4_PCR, val);
+ priv->speed = speed;
}
static void enetc4_set_rgmii_mac(struct enetc_pf *pf, int speed, int duplex)
--
2.34.1
^ permalink raw reply related
* [PATCH v4 net-next 05/14] net: enetc: use PCI device name for debugfs directory
From: wei.fang @ 2026-07-07 8:18 UTC (permalink / raw)
To: claudiu.manoil, vladimir.oltean, xiaoning.wang, andrew+netdev,
davem, edumazet, kuba, pabeni, linux, wei.fang, chleroy,
maxime.chevallier
Cc: imx, netdev, linux-kernel, linuxppc-dev, linux-arm-kernel
In-Reply-To: <20260707081834.710730-1-wei.fang@oss.nxp.com>
From: Wei Fang <wei.fang@nxp.com>
enetc_create_debugfs() is called right after register_netdev(), at which
point ndev->name still holds the format "eth%d" (e.g., eth0) rather than
the final assigned name (e.g., via udev rules).
Use pci_name() instead of netdev_name() to name the debugfs directory.
The PCI device name is unique, stable, and available from the start,
making it a more reliable identifier for the debugfs entry. Therefore,
the observable debugfs path from something like
/sys/kernel/debug/eth0/mac_filter to a PCI BDF-style path such as
/sys/kernel/debug/0002:00:00.0/mac_filter.
Signed-off-by: Wei Fang <wei.fang@nxp.com>
---
drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c b/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c
index 4a769d9e5679..be378bf8f74d 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c
@@ -81,10 +81,9 @@ DEFINE_SHOW_ATTRIBUTE(enetc_mac_filter);
void enetc_create_debugfs(struct enetc_si *si)
{
- struct net_device *ndev = si->ndev;
struct dentry *root;
- root = debugfs_create_dir(netdev_name(ndev), NULL);
+ root = debugfs_create_dir(pci_name(si->pdev), NULL);
if (IS_ERR(root))
return;
--
2.34.1
^ permalink raw reply related
* [PATCH v4 net-next 04/14] net: enetc: improve MAFT entry management with bitmap tracking
From: wei.fang @ 2026-07-07 8:18 UTC (permalink / raw)
To: claudiu.manoil, vladimir.oltean, xiaoning.wang, andrew+netdev,
davem, edumazet, kuba, pabeni, linux, wei.fang, chleroy,
maxime.chevallier
Cc: imx, netdev, linux-kernel, linuxppc-dev, linux-arm-kernel
In-Reply-To: <20260707081834.710730-1-wei.fang@oss.nxp.com>
From: Wei Fang <wei.fang@nxp.com>
Replace the counter-based MAFT entry tracking (num_mfe/mac_filter_num)
with a bitmap (maft_eid_bitmap) stored in struct ntmp_user, which is a
more appropriate place for NTMP resource management.
The bitmap approach brings two improvements. First, the entry deletion
in enetc4_pf_clear_maft_entries() now checks the return value of
ntmp_maft_delete_entry() and only clears the corresponding bit on
success, keeping hardware and software state in sync. Previously, the
counter was reset unconditionally regardless of whether the hardware
deletion actually succeeded.
Second, entry allocation in enetc4_pf_add_maft_entries() uses
ntmp_lookup_free_eid() to find available IDs dynamically, with an
upfront capacity check via bitmap_weight() to avoid partial failures.
The MAFT entry count is moved into ntmp_user.maft_num_entries and
initialized once during enetc4_init_ntmp_user(). Helper functions
enetc4_ntmp_bitmap_init() and enetc4_ntmp_bitmap_free() manage the
bitmap lifetime. The debugfs show function is updated accordingly to
iterate over set bits under rtnl_lock().
Signed-off-by: Wei Fang <wei.fang@nxp.com>
---
.../ethernet/freescale/enetc/enetc4_debugfs.c | 30 ++++--
.../net/ethernet/freescale/enetc/enetc4_pf.c | 97 ++++++++++++++-----
.../net/ethernet/freescale/enetc/enetc_pf.h | 3 -
include/linux/fsl/ntmp.h | 2 +
4 files changed, 96 insertions(+), 36 deletions(-)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c b/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c
index 1b1591dce73d..4a769d9e5679 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c
@@ -31,9 +31,11 @@ static int enetc_mac_filter_show(struct seq_file *s, void *data)
struct enetc_si *si = s->private;
struct enetc_hw *hw = &si->hw;
struct maft_entry_data maft;
+ struct ntmp_user *user;
struct enetc_pf *pf;
- int i, err, num_si;
- u32 val;
+ u32 val, entry_id;
+ int i, num_si;
+ int err = 0;
pf = enetc_si_priv(si);
num_si = pf->caps.num_vsi + 1;
@@ -50,22 +52,30 @@ static int enetc_mac_filter_show(struct seq_file *s, void *data)
for (i = 0; i < num_si; i++)
enetc_show_si_mac_hash_filter(s, i);
- if (!pf->num_mfe)
- return 0;
+ user = &si->ntmp_user;
+ rtnl_lock();
+
+ if (bitmap_empty(user->maft_eid_bitmap, user->maft_num_entries))
+ goto unlock_rtnl;
/* MAC address filter table */
seq_puts(s, "MAC address filter table\n");
- for (i = 0; i < pf->num_mfe; i++) {
+ for_each_set_bit(entry_id, user->maft_eid_bitmap,
+ user->maft_num_entries) {
memset(&maft, 0, sizeof(maft));
- err = ntmp_maft_query_entry(&si->ntmp_user, i, &maft);
+ err = ntmp_maft_query_entry(user, entry_id, &maft);
if (err)
- return err;
+ goto unlock_rtnl;
- seq_printf(s, "Entry %d, MAC: %pM, SI bitmap: 0x%04x\n", i,
- maft.keye.mac_addr, le16_to_cpu(maft.cfge.si_bitmap));
+ seq_printf(s, "Entry %d, MAC: %pM, SI bitmap: 0x%04x\n",
+ entry_id, maft.keye.mac_addr,
+ le16_to_cpu(maft.cfge.si_bitmap));
}
- return 0;
+unlock_rtnl:
+ rtnl_unlock();
+
+ return err;
}
DEFINE_SHOW_ATTRIBUTE(enetc_mac_filter);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
index a02b01753ff2..b966637572a7 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
@@ -32,9 +32,6 @@ static void enetc4_get_port_caps(struct enetc_pf *pf)
val = enetc_port_rd(hw, ENETC4_PMCAPR);
pf->caps.half_duplex = (val & PMCAPR_HD) ? 1 : 0;
-
- val = enetc_port_rd(hw, ENETC4_PSIMAFCAPR);
- pf->caps.mac_filter_num = val & PSIMAFCAPR_NUM_MAC_AFTE;
}
static void enetc4_get_psi_hw_features(struct enetc_si *si)
@@ -92,31 +89,45 @@ static void enetc4_pf_set_loopback(struct net_device *ndev, bool en)
static void enetc4_pf_clear_maft_entries(struct enetc_pf *pf)
{
- int i;
+ struct ntmp_user *user = &pf->si->ntmp_user;
+ u32 entry_id;
- for (i = 0; i < pf->num_mfe; i++)
- ntmp_maft_delete_entry(&pf->si->ntmp_user, i);
-
- pf->num_mfe = 0;
+ for_each_set_bit(entry_id, user->maft_eid_bitmap,
+ user->maft_num_entries) {
+ if (!ntmp_maft_delete_entry(user, entry_id))
+ ntmp_clear_eid_bitmap(user->maft_eid_bitmap, entry_id);
+ }
}
static int enetc4_pf_add_maft_entries(struct enetc_pf *pf,
struct netdev_hw_addr_list *uc)
{
+ struct ntmp_user *user = &pf->si->ntmp_user;
+ int mac_cnt = netdev_hw_addr_list_count(uc);
struct maft_entry_data maft = {};
struct netdev_hw_addr *ha;
+ u32 available_entries;
u16 si_bit = BIT(0);
+ u32 entry_id;
int err;
+ available_entries = user->maft_num_entries -
+ bitmap_weight(user->maft_eid_bitmap,
+ user->maft_num_entries);
+
+ if (mac_cnt > available_entries)
+ return -ENOSPC;
+
maft.cfge.si_bitmap = cpu_to_le16(si_bit);
netdev_hw_addr_list_for_each(ha, uc) {
+ entry_id = ntmp_lookup_free_eid(user->maft_eid_bitmap,
+ user->maft_num_entries);
ether_addr_copy(maft.keye.mac_addr, ha->addr);
- err = ntmp_maft_add_entry(&pf->si->ntmp_user, pf->num_mfe,
- &maft);
- if (unlikely(err))
+ err = ntmp_maft_add_entry(user, entry_id, &maft);
+ if (unlikely(err)) {
+ ntmp_clear_eid_bitmap(user->maft_eid_bitmap, entry_id);
goto clear_maft_entries;
-
- pf->num_mfe++;
+ }
}
return 0;
@@ -146,10 +157,10 @@ static void enetc4_pf_set_uc_hash_filter(struct enetc_pf *pf,
static int enetc4_pf_set_uc_exact_filter(struct enetc_pf *pf,
struct netdev_hw_addr_list *uc)
{
- int mac_cnt = netdev_hw_addr_list_count(uc);
struct enetc_si *si = pf->si;
+ int err;
- if (!mac_cnt) {
+ if (netdev_hw_addr_list_empty(uc)) {
/* clear both MAC hash and exact filters */
enetc_set_si_uc_hash_filter(si, 0, 0);
enetc4_pf_clear_maft_entries(pf);
@@ -157,21 +168,19 @@ static int enetc4_pf_set_uc_exact_filter(struct enetc_pf *pf,
return 0;
}
- if (mac_cnt > pf->caps.mac_filter_num)
- return -ENOSPC;
-
- /* Set temporary unicast hash filters in case of Rx loss when
+ /* Set temporary unicast hash filter in case of Rx loss when
* updating MAC address filter table
*/
enetc4_pf_set_uc_hash_filter(pf, uc);
enetc4_pf_clear_maft_entries(pf);
- if (!enetc4_pf_add_maft_entries(pf, uc)) {
+ err = enetc4_pf_add_maft_entries(pf, uc);
+ if (!err) {
enetc_reset_mac_addr_filter(&pf->mac_filter[UC]);
enetc_set_si_uc_hash_filter(si, 0, 0);
}
- return 0;
+ return err;
}
static void enetc4_pf_set_mc_hash_filter(struct enetc_pf *pf,
@@ -393,18 +402,60 @@ static void enetc4_configure_port(struct enetc_pf *pf)
enetc_set_default_rss_key(pf);
}
+static void enetc4_get_ntmp_caps(struct enetc_si *si)
+{
+ struct ntmp_user *user = &si->ntmp_user;
+ struct enetc_hw *hw = &si->hw;
+ u32 val;
+
+ val = enetc_port_rd(hw, ENETC4_PSIMAFCAPR);
+ user->maft_num_entries = FIELD_GET(PSIMAFCAPR_NUM_MAC_AFTE, val);
+}
+
+static int enetc4_ntmp_bitmap_init(struct ntmp_user *user)
+{
+ user->maft_eid_bitmap = bitmap_zalloc(user->maft_num_entries,
+ GFP_KERNEL);
+ if (!user->maft_eid_bitmap)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void enetc4_ntmp_bitmap_free(struct ntmp_user *user)
+{
+ bitmap_free(user->maft_eid_bitmap);
+ user->maft_eid_bitmap = NULL;
+}
+
static int enetc4_init_ntmp_user(struct enetc_si *si)
{
struct ntmp_user *user = &si->ntmp_user;
+ int err;
/* For ENETC 4.1, all table versions are 0 */
memset(&user->tbl, 0, sizeof(user->tbl));
- return enetc4_setup_cbdr(si);
+ err = enetc4_setup_cbdr(si);
+ if (err)
+ return err;
+
+ enetc4_get_ntmp_caps(si);
+ err = enetc4_ntmp_bitmap_init(user);
+ if (err)
+ goto teardown_cbdr;
+
+ return 0;
+
+teardown_cbdr:
+ enetc4_teardown_cbdr(si);
+
+ return err;
}
static void enetc4_free_ntmp_user(struct enetc_si *si)
{
+ enetc4_ntmp_bitmap_free(&si->ntmp_user);
enetc4_teardown_cbdr(si);
}
@@ -422,7 +473,7 @@ static int enetc4_pf_init(struct enetc_pf *pf)
err = enetc4_init_ntmp_user(pf->si);
if (err) {
- dev_err(dev, "Failed to init CBDR\n");
+ dev_err(dev, "Failed to init NTMP user\n");
return err;
}
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.h b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
index 285b7e5c48fd..6f15f9ea1664 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
@@ -22,7 +22,6 @@ struct enetc_port_caps {
int num_msix;
int num_rx_bdr;
int num_tx_bdr;
- int mac_filter_num;
};
struct enetc_pf;
@@ -60,8 +59,6 @@ struct enetc_pf {
struct enetc_port_caps caps;
const struct enetc_pf_ops *ops;
-
- int num_mfe; /* number of mac address filter table entries */
};
#define phylink_to_enetc_pf(config) \
diff --git a/include/linux/fsl/ntmp.h b/include/linux/fsl/ntmp.h
index d3b6c476b91a..764ef2892608 100644
--- a/include/linux/fsl/ntmp.h
+++ b/include/linux/fsl/ntmp.h
@@ -75,8 +75,10 @@ struct ntmp_user {
/* NTMP table bitmaps for resource management */
u32 ett_bitmap_size;
u32 ect_bitmap_size;
+ u16 maft_num_entries;
unsigned long *ett_gid_bitmap; /* only valid for switch */
unsigned long *ect_gid_bitmap; /* only valid for switch */
+ unsigned long *maft_eid_bitmap; /* only valid for ENETC */
};
struct maft_entry_data {
--
2.34.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox