Merge branch 'devlink-introduce-shared-devlink-instance-for-pfs-on-same-chip'

Jiri Pirko says:

====================
devlink: introduce shared devlink instance for PFs on same chip

Multiple PFs on a network adapter often reside on the same physical
chip, running a single firmware. Some resources and configurations
are inherently shared among these PFs - PTP clocks, VF group rates,
firmware parameters, and others. Today there is no good object in
the devlink model to attach these chip-wide configuration knobs to.
Drivers resort to workarounds like pinning shared state to PF0 or
maintaining ad-hoc internal structures (e.g., ice_adapter) that are
invisible to userspace.

This problem was discussed extensively starting with Przemek Kitszel's
"whole device devlink instance" RFC for the ice driver [1]. Several
approaches for representing the parent instance were considered:
using a partial PCI BDF as the dev_name (breaks when PFs have different
BDFs in VMs), creating a per-driver bus, using auxiliary devices, or
using faux devices. All of these required a backing struct device for
the parent devlink instance, which does not naturally exist - there is
no PCI device that represents the chip as a whole.

This patchset takes a different approach: allow devlink instances to
exist without any backing struct device. The instance is identified
purely by its internal index, exposed over devlin netlink. This avoids
fabricating fake devices and keeps the devlink handle semantics clean.

The first ten patches prepare the devlink core for device-less
instances by decoupling the handle from the parent device. The last
three introduce the shared devlink infrastructure and its first user
in the mlx5 driver.

Example output showing the shared instance and nesting:

  pci/0000:08:00.0: index 0
    nested_devlink:
      auxiliary/mlx5_core.eth.0
  devlink_index/1: index 1
    nested_devlink:
      pci/0000:08:00.0
      pci/0000:08:00.1
  auxiliary/mlx5_core.eth.0: index 2
  pci/0000:08:00.1: index 3
    nested_devlink:
      auxiliary/mlx5_core.eth.1
  auxiliary/mlx5_core.eth.1: index 4

[1] https://lore.kernel.org/netdev/20250219164410.35665-1-przemyslaw.kitszel@intel.com/
---
Decoupled from "devlink and mlx5: Support cross-function rate scheduling"
patchset to maintain 15-patches limit.

See individual patches for changelog.
====================

Link: https://patch.msgid.link/20260312100407.551173-1-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 33 insertions, 18 deletions

diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 04dcd09f7517..1268fcf35ec7 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -798,6 +798,7 @@ struct mlx5_core_dev {
 	enum mlx5_wc_state wc_state;
 	/* sync write combining state */
 	struct mutex wc_state_lock;
+	struct devlink *shd;
 };
 
 struct mlx5_db {
diff --git a/include/net/devlink.h b/include/net/devlink.h
index cb839e0435a1..3038af6ec017 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -1611,6 +1611,9 @@ struct devlink_ops {
 void *devlink_priv(struct devlink *devlink);
 struct devlink *priv_to_devlink(void *priv);
 struct device *devlink_to_dev(const struct devlink *devlink);
+const char *devlink_bus_name(const struct devlink *devlink);
+const char *devlink_dev_name(const struct devlink *devlink);
+const char *devlink_dev_driver_name(const struct devlink *devlink);
 
 /* Devlink instance explicit locking */
 void devl_lock(struct devlink *devlink);
@@ -1644,6 +1647,13 @@ void devlink_register(struct devlink *devlink);
 void devlink_unregister(struct devlink *devlink);
 void devlink_free(struct devlink *devlink);
 
+struct devlink *devlink_shd_get(const char *id,
+				const struct devlink_ops *ops,
+				size_t priv_size,
+				const struct device_driver *driver);
+void devlink_shd_put(struct devlink *devlink);
+void *devlink_shd_get_priv(struct devlink *devlink);
+
 /**
  * struct devlink_port_ops - Port operations
  * @port_split: Callback used to split the port into multiple ones.
diff --git a/include/trace/events/devlink.h b/include/trace/events/devlink.h
index f241e204fe6b..4f8edf77dfbe 100644
--- a/include/trace/events/devlink.h
+++ b/include/trace/events/devlink.h
@@ -21,9 +21,9 @@ TRACE_EVENT(devlink_hwmsg,
 	TP_ARGS(devlink, incoming, type, buf, len),
 
 	TP_STRUCT__entry(
-		__string(bus_name, devlink_to_dev(devlink)->bus->name)
-		__string(dev_name, dev_name(devlink_to_dev(devlink)))
-		__string(driver_name, devlink_to_dev(devlink)->driver->name)
+		__string(bus_name, devlink_bus_name(devlink))
+		__string(dev_name, devlink_dev_name(devlink))
+		__string(driver_name, devlink_dev_driver_name(devlink))
 		__field(bool, incoming)
 		__field(unsigned long, type)
 		__dynamic_array(u8, buf, len)
@@ -55,9 +55,9 @@ TRACE_EVENT(devlink_hwerr,
 	TP_ARGS(devlink, err, msg),
 
 	TP_STRUCT__entry(
-		__string(bus_name, devlink_to_dev(devlink)->bus->name)
-		__string(dev_name, dev_name(devlink_to_dev(devlink)))
-		__string(driver_name, devlink_to_dev(devlink)->driver->name)
+		__string(bus_name, devlink_bus_name(devlink))
+		__string(dev_name, devlink_dev_name(devlink))
+		__string(driver_name, devlink_dev_driver_name(devlink))
 		__field(int, err)
 		__string(msg, msg)
 		),
@@ -85,9 +85,9 @@ TRACE_EVENT(devlink_health_report,
 	TP_ARGS(devlink, reporter_name, msg),
 
 	TP_STRUCT__entry(
-		__string(bus_name, devlink_to_dev(devlink)->bus->name)
-		__string(dev_name, dev_name(devlink_to_dev(devlink)))
-		__string(driver_name, devlink_to_dev(devlink)->driver->name)
+		__string(bus_name, devlink_bus_name(devlink))
+		__string(dev_name, devlink_dev_name(devlink))
+		__string(driver_name, devlink_dev_driver_name(devlink))
 		__string(reporter_name, reporter_name)
 		__string(msg, msg)
 	),
@@ -116,9 +116,9 @@ TRACE_EVENT(devlink_health_recover_aborted,
 	TP_ARGS(devlink, reporter_name, health_state, time_since_last_recover),
 
 	TP_STRUCT__entry(
-		__string(bus_name, devlink_to_dev(devlink)->bus->name)
-		__string(dev_name, dev_name(devlink_to_dev(devlink)))
-		__string(driver_name, devlink_to_dev(devlink)->driver->name)
+		__string(bus_name, devlink_bus_name(devlink))
+		__string(dev_name, devlink_dev_name(devlink))
+		__string(driver_name, devlink_dev_driver_name(devlink))
 		__string(reporter_name, reporter_name)
 		__field(bool, health_state)
 		__field(u64, time_since_last_recover)
@@ -150,9 +150,9 @@ TRACE_EVENT(devlink_health_reporter_state_update,
 	TP_ARGS(devlink, reporter_name, new_state),
 
 	TP_STRUCT__entry(
-		__string(bus_name, devlink_to_dev(devlink)->bus->name)
-		__string(dev_name, dev_name(devlink_to_dev(devlink)))
-		__string(driver_name, devlink_to_dev(devlink)->driver->name)
+		__string(bus_name, devlink_bus_name(devlink))
+		__string(dev_name, devlink_dev_name(devlink))
+		__string(driver_name, devlink_dev_driver_name(devlink))
 		__string(reporter_name, reporter_name)
 		__field(u8, new_state)
 	),
@@ -181,9 +181,9 @@ TRACE_EVENT(devlink_trap_report,
 	TP_ARGS(devlink, skb, metadata),
 
 	TP_STRUCT__entry(
-		__string(bus_name, devlink_to_dev(devlink)->bus->name)
-		__string(dev_name, dev_name(devlink_to_dev(devlink)))
-		__string(driver_name, devlink_to_dev(devlink)->driver->name)
+		__string(bus_name, devlink_bus_name(devlink))
+		__string(dev_name, devlink_dev_name(devlink))
+		__string(driver_name, devlink_dev_driver_name(devlink))
 		__string(trap_name, metadata->trap_name)
 		__string(trap_group_name, metadata->trap_group_name)
 		__array(char, input_dev_name, IFNAMSIZ)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index e7d6b6d13470..7de2d8cc862f 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -19,6 +19,8 @@
 #define DEVLINK_GENL_VERSION 0x1
 #define DEVLINK_GENL_MCGRP_CONFIG_NAME "config"
 
+#define DEVLINK_INDEX_BUS_NAME "devlink_index"
+
 enum devlink_command {
 	/* don't change the order or add anything between, this is ABI! */
 	DEVLINK_CMD_UNSPEC,
@@ -642,6 +644,8 @@ enum devlink_attr {
 	DEVLINK_ATTR_PARAM_VALUE_DEFAULT,	/* dynamic */
 	DEVLINK_ATTR_PARAM_RESET_DEFAULT,	/* flag */
 
+	DEVLINK_ATTR_INDEX,			/* uint */
+
 	/* Add new attributes above here, update the spec in
 	 * Documentation/netlink/specs/devlink.yaml and re-generate
 	 * net/devlink/netlink_gen.c.