On 3/18/25 23:05, Keller, Jacob E wrote:
quoted
-----Original Message-----
From: Jiri Pirko <jiri@resnulli.us>
quoted
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sh_devlink.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include <linux/device/faux.h>
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/vport.h>
+
+#include "sh_devlink.h"
+
+static LIST_HEAD(shd_list);
+static DEFINE_MUTEX(shd_mutex); /* Protects shd_list and shd->list */
I essentially agree that faux_device could be used as-is, without any
devlink changes, works for me.
That does not remove the need to invent the name at some point ;)
we have resolved this in similar manner, that's fine, given my
understanding that you cannot let faux to dispatch for you, like:
faux_get_instance(serial_number_equivalent)
quoted
+
+/* This structure represents a shared devlink instance,
+ * there is one created for PF group of the same chip.
+ */
+struct mlx5_shd {
+ /* Node in shd list */
+ struct list_head list;
+ /* Serial number of the chip */
+ const char *sn;
+ /* List of per-PF dev instances. */
+ struct list_head dev_list;
+ /* Related faux device */
+ struct faux_device *faux_dev;
+};
+
For ice, the equivalent of this would essentially replace ice_adapter I imagine.
or "ice_adapter will be the ice equivalent"
quoted
+static const struct devlink_ops mlx5_shd_ops = {
please double check if there is no crash for:
$ devlink dev info the/faux/thing
quoted
+};
+
+static int mlx5_shd_faux_probe(struct faux_device *faux_dev)
+{
+ struct devlink *devlink;
+ struct mlx5_shd *shd;
+
+ devlink = devlink_alloc(&mlx5_shd_ops, sizeof(struct mlx5_shd),
sizeof(*shd)
I like that you reuse devlink_alloc(), with allocation of priv data,
that suits also our needs
quoted
&faux_dev->dev);
+ if (!devlink)
+ return -ENOMEM;
+ shd = devlink_priv(devlink);
+ faux_device_set_drvdata(faux_dev, shd);
+
+ devl_lock(devlink);
+ devl_register(devlink);
+ devl_unlock(devlink);
+ return 0;
+}
[...]
quoted
+int mlx5_shd_init(struct mlx5_core_dev *dev)
+{
+ u8 *vpd_data __free(kfree) = NULL;
so bad that netdev mainainers discourage __free() :(
perhaps I should propose higher abstraction wrapper for it
on April 1st
quoted
+ struct pci_dev *pdev = dev->pdev;
+ unsigned int vpd_size, kw_len;
+ struct mlx5_shd *shd;
+ const char *sn;
I would extract name retrieval, perhaps mlx5_shd_get_name()?
quoted
+ char *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;
what? that means the shared devlink instance is something you will
work properly without?
quoted
+ }
+ 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;
+ end = strchrnul(sn, ' ');
+ *end = '\0';
+
+ guard(mutex)(&shd_mutex);
guard()() is a no-no too, per "discouraged by netdev maintainers",
and here I'm on board with discouraging ;)
quoted
+ list_for_each_entry(shd, &shd_list, list) {
+ if (!strcmp(shd->sn, sn)) {
+ kfree(sn);
+ goto found;
+ }
+ }
+ shd = mlx5_shd_create(sn);
+ if (!shd) {
+ kfree(sn);
+ return -ENOMEM;
+ }
How is the faux device kept in memory? I guess its reference counted somewhere?
get_device()/put_device() with faxu_dev->dev as argument
But I don't see that reference being incremented in the list_for_each.
Jiri keeps "the counter" as the implicit observation of shd list size :)
which is protected by mutex