# Re: \[PATCH net-next v4 13/13\] net/mlx5: Add a shared devlink instance for PFs on same chip - From: Adam Young \ - Date: 2026-03-20 23:16:28 - List: netdev - Page: https://ratatoskr.run/netdev/2026/03/8535728 - Thread: https://ratatoskr.run/netdev/2026/03/8535651/t.md ```text This breaks on my system: On 7.0.0 It boots fine.  With net-next/main currently at this commit commit 8737d7194d6d5947c3d7d8813895b44a25b84477 (net-next/main, net-next/HEAD) Author: Lorenzo Bianconi [ref] Date:   Fri Mar 13 17:28:36 2026 +0100 I get: [   21.859081] mlx5_core 0005:01:00.0: probe_one:2017:(pid 10): mlx5_shd_init failed with error code -2 [   21.863266] mlx5_core 0005:01:00.0: probe with driver mlx5_core failed with error -2 [   21.866360] mlx5_core 0005:01:00.1: probe_one:2017:(pid 10): mlx5_shd_init failed with error code -2 [   21.869937] mlx5_core 0005:01:00.1: probe with driver mlx5_core failed with error -2 I am happy to help debug:   what do you need from me? On 3/12/26 06:04, Jiri Pirko wrote: > From: Jiri Pirko > > Use the previously introduced shared devlink infrastructure to create > a shared devlink instance for mlx5 PFs that reside on the same physical > chip. The shared instance is identified by the chip's serial number > extracted from PCI VPD (V3 keyword, with fallback to serial number > for older devices). > > Each PF that probes calls mlx5_shd_init() which extracts the chip serial > number and uses devlink_shd_get() to get or create the shared instance. > When a PF is removed, mlx5_shd_uninit() calls devlink_shd_put() > to release the reference. The shared instance is automatically destroyed > when the last PF is removed. > > Make the PF devlink instances nested in this shared devlink instance, > allowing userspace to identify which PFs belong to the same physical > chip. > > Example: > > 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 > > Signed-off-by: Jiri Pirko > --- > v2->v3: > - removed "const" from "sn" > - passing driver pointer to devlink_shd_get() > --- > .../net/ethernet/mellanox/mlx5/core/Makefile | 5 +- > .../net/ethernet/mellanox/mlx5/core/main.c | 17 ++++++ > .../ethernet/mellanox/mlx5/core/sh_devlink.c | 61 +++++++++++++++++++ > .../ethernet/mellanox/mlx5/core/sh_devlink.h | 12 ++++ > include/linux/mlx5/driver.h | 1 + > 5 files changed, 94 insertions(+), 2 deletions(-) > create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/sh_devlink.c > create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/sh_devlink.h > > diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile > index 8ffa286a18f5..d39fe9c4a87c 100644 > --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile > +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile > @@ -16,8 +16,9 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ > transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \ > fs_counters.o fs_ft_pool.o rl.o lag/debugfs.o lag/lag.o dev.o events.o wq.o lib/gid.o \ > lib/devcom.o lib/pci_vsc.o lib/dm.o lib/fs_ttc.o diag/fs_tracepoint.o \ > - diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o diag/reporter_vnic.o \ > - fw_reset.o qos.o lib/tout.o lib/aso.o wc.o fs_pool.o lib/nv_param.o > + diag/fw_tracer.o diag/crdump.o devlink.o sh_devlink.o diag/rsc_dump.o \ > + diag/reporter_vnic.o fw_reset.o qos.o lib/tout.o lib/aso.o wc.o fs_pool.o \ > + lib/nv_param.o > > # > # Netdev basic > diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c > index fdc3ba20912e..1c35c3fc3bb3 100644 > --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c > +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c > @@ -74,6 +74,7 @@ > #include "mlx5_irq.h" > #include "hwmon.h" > #include "lag/lag.h" > +#include "sh_devlink.h" > > MODULE_AUTHOR("Eli Cohen [ref]"); > MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver"); > @@ -1520,10 +1521,16 @@ int mlx5_init_one(struct mlx5_core_dev *dev) > int err; > > devl_lock(devlink); > + if (dev->shd) { > + err = devl_nested_devlink_set(dev->shd, devlink); > + if (err) > + goto unlock; > + } > devl_register(devlink); > err = mlx5_init_one_devl_locked(dev); > if (err) > devl_unregister(devlink); > +unlock: > devl_unlock(devlink); > return err; > } > @@ -2005,6 +2012,13 @@ static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id) > goto pci_init_err; > } > > + err = mlx5_shd_init(dev); > + if (err) { > + mlx5_core_err(dev, "mlx5_shd_init failed with error code %d\n", > + err); > + goto shd_init_err; > + } > + > err = mlx5_init_one(dev); > if (err) { > mlx5_core_err(dev, "mlx5_init_one failed with error code %d\n", > @@ -2018,6 +2032,8 @@ static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id) > return 0; > > err_init_one: > + mlx5_shd_uninit(dev); > +shd_init_err: > mlx5_pci_close(dev); > pci_init_err: > mlx5_mdev_uninit(dev); > @@ -2039,6 +2055,7 @@ static void remove_one(struct pci_dev *pdev) > mlx5_drain_health_wq(dev); > mlx5_sriov_disable(pdev, false); > mlx5_uninit_one(dev); > + mlx5_shd_uninit(dev); > mlx5_pci_close(dev); > mlx5_mdev_uninit(dev); > mlx5_adev_idx_free(dev->priv.adev_idx); > diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sh_devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sh_devlink.c > new file mode 100644 > index 000000000000..bc33f95302df > --- /dev/null > +++ b/drivers/net/ethernet/mellanox/mlx5/core/sh_devlink.c > @@ -0,0 +1,61 @@ > +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB > +/* Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ > + > +#include > +#include > + > +#include "sh_devlink.h" > + > +static const struct devlink_ops mlx5_shd_ops = { > +}; > + > +int mlx5_shd_init(struct mlx5_core_dev *dev) > +{ > + u8 *vpd_data __free(kfree) = NULL; > + struct pci_dev *pdev = dev->pdev; > + unsigned int vpd_size, kw_len; > + struct devlink *devlink; > + char *sn, *end; > + int start; > + int err; > + > + if (!mlx5_core_is_pf(dev)) > + return 0; > + > + vpd_data = pci_vpd_alloc(pdev, &vpd_size); > + if (IS_ERR(vpd_data)) { > + err = PTR_ERR(vpd_data); > + return err == -ENODEV ? 0 : err; > + } > + start = pci_vpd_find_ro_info_keyword(vpd_data, vpd_size, "V3", &kw_len); > + if (start < 0) { > + /* Fall-back to SN for older devices. */ > + start = pci_vpd_find_ro_info_keyword(vpd_data, vpd_size, > + PCI_VPD_RO_KEYWORD_SERIALNO, &kw_len); > + if (start < 0) > + return -ENOENT; > + } > + sn = kstrndup(vpd_data + start, kw_len, GFP_KERNEL); > + if (!sn) > + return -ENOMEM; > + /* Firmware may return spaces at the end of the string, strip it. */ > + end = strchrnul(sn, ' '); > + *end = '\0'; > + > + /* Get or create shared devlink instance */ > + devlink = devlink_shd_get(sn, &mlx5_shd_ops, 0, pdev->dev.driver); > + kfree(sn); > + if (!devlink) > + return -ENOMEM; > + > + dev->shd = devlink; > + return 0; > +} > + > +void mlx5_shd_uninit(struct mlx5_core_dev *dev) > +{ > + if (!dev->shd) > + return; > + > + devlink_shd_put(dev->shd); > +} > diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sh_devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/sh_devlink.h > new file mode 100644 > index 000000000000..8ab8d6940227 > --- /dev/null > +++ b/drivers/net/ethernet/mellanox/mlx5/core/sh_devlink.h > @@ -0,0 +1,12 @@ > +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ > +/* Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ > + > +#ifndef __MLX5_SH_DEVLINK_H__ > +#define __MLX5_SH_DEVLINK_H__ > + > +#include > + > +int mlx5_shd_init(struct mlx5_core_dev *dev); > +void mlx5_shd_uninit(struct mlx5_core_dev *dev); > + > +#endif /* __MLX5_SH_DEVLINK_H__ */ > 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 { ```