Merge branch 'mlxsw-new-reset-flow'

Petr Machata says:

====================
mlxsw: Add support for new reset flow

Ido Schimmel writes:

This patchset changes mlxsw to issue a PCI reset during probe and
devlink reload so that the PCI firmware could be upgraded without a
reboot.

Unlike the old version of this patchset [1], in this version the driver
no longer tries to issue a PCI reset by triggering a PCI link toggle on
its own, but instead calls the PCI core to issue the reset.

The PCI APIs require the device lock to be held which is why patches

Patches #7 adds reset method quirk for NVIDIA Spectrum devices.

Patch #8 adds a debug level print in PCI core so that device ready delay
will be printed even if it is shorter than one second.

Patches #9-#11 are straightforward preparations in mlxsw.

Patch #12 finally implements the new reset flow in mlxsw.

Patch #13 adds PCI reset handlers in mlxsw to avoid user space from
resetting the device from underneath an unaware driver. Instead, the
driver is gracefully de-initialized before the PCI reset and then
initialized again after it.

Patch #14 adds a PCI reset selftest to make sure this code path does not
regress.

[1] https://lore.kernel.org/netdev/cover.1679502371.git.petrm@nvidia.com/
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 74 insertions, 19 deletions

diff --git a/net/devlink/core.c b/net/devlink/core.c
index 6984877e9f10..4275a2bc6d8e 100644
--- a/net/devlink/core.c
+++ b/net/devlink/core.c
@@ -503,14 +503,14 @@ static void __net_exit devlink_pernet_pre_exit(struct net *net)
 	 * all devlink instances from this namespace into init_net.
 	 */
 	devlinks_xa_for_each_registered_get(net, index, devlink) {
-		devl_lock(devlink);
+		devl_dev_lock(devlink, true);
 		err = 0;
 		if (devl_is_registered(devlink))
 			err = devlink_reload(devlink, &init_net,
 					     DEVLINK_RELOAD_ACTION_DRIVER_REINIT,
 					     DEVLINK_RELOAD_LIMIT_UNSPEC,
 					     &actions_performed, NULL);
-		devl_unlock(devlink);
+		devl_dev_unlock(devlink, true);
 		devlink_put(devlink);
 		if (err && err != -EOPNOTSUPP)
 			pr_warn("Failed to reload devlink instance into init_net\n");
diff --git a/net/devlink/dev.c b/net/devlink/dev.c
index 4fc7adb32663..ea6a92f2e6a2 100644
--- a/net/devlink/dev.c
+++ b/net/devlink/dev.c
@@ -4,6 +4,7 @@
  * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
  */
 
+#include <linux/device.h>
 #include <net/genetlink.h>
 #include <net/sock.h>
 #include "devl_internal.h"
@@ -433,6 +434,13 @@ int devlink_reload(struct devlink *devlink, struct net *dest_net,
 	struct net *curr_net;
 	int err;
 
+	/* Make sure the reload operations are invoked with the device lock
+	 * held to allow drivers to trigger functionality that expects it
+	 * (e.g., PCI reset) and to close possible races between these
+	 * operations and probe/remove.
+	 */
+	device_lock_assert(devlink->dev);
+
 	memcpy(remote_reload_stats, devlink->stats.remote_reload_stats,
 	       sizeof(remote_reload_stats));
 
diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index 183dbe3807ab..5ea2e2012e93 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -3,6 +3,7 @@
  * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
  */
 
+#include <linux/device.h>
 #include <linux/etherdevice.h>
 #include <linux/mutex.h>
 #include <linux/netdevice.h>
@@ -96,6 +97,20 @@ static inline bool devl_is_registered(struct devlink *devlink)
 	return xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED);
 }
 
+static inline void devl_dev_lock(struct devlink *devlink, bool dev_lock)
+{
+	if (dev_lock)
+		device_lock(devlink->dev);
+	devl_lock(devlink);
+}
+
+static inline void devl_dev_unlock(struct devlink *devlink, bool dev_lock)
+{
+	devl_unlock(devlink);
+	if (dev_lock)
+		device_unlock(devlink->dev);
+}
+
 typedef void devlink_rel_notify_cb_t(struct devlink *devlink, u32 obj_index);
 typedef void devlink_rel_cleanup_cb_t(struct devlink *devlink, u32 obj_index,
 				      u32 rel_index);
@@ -111,9 +126,6 @@ int devlink_rel_devlink_handle_put(struct sk_buff *msg, struct devlink *devlink,
 				   bool *msg_updated);
 
 /* Netlink */
-#define DEVLINK_NL_FLAG_NEED_PORT		BIT(0)
-#define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT	BIT(1)
-
 enum devlink_multicast_groups {
 	DEVLINK_MCGRP_CONFIG,
 };
@@ -140,7 +152,8 @@ typedef int devlink_nl_dump_one_func_t(struct sk_buff *msg,
 				       int flags);
 
 struct devlink *
-devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs);
+devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs,
+			    bool dev_lock);
 
 int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb,
 		      devlink_nl_dump_one_func_t *dump_one);
diff --git a/net/devlink/health.c b/net/devlink/health.c
index 695df61f8ac2..71ae121dc739 100644
--- a/net/devlink/health.c
+++ b/net/devlink/health.c
@@ -1151,7 +1151,8 @@ devlink_health_reporter_get_from_cb_lock(struct netlink_callback *cb)
 	struct nlattr **attrs = info->attrs;
 	struct devlink *devlink;
 
-	devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs);
+	devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs,
+					      false);
 	if (IS_ERR(devlink))
 		return NULL;
 
diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c
index d0b90ebc8b15..fa9afe3e6d9b 100644
--- a/net/devlink/netlink.c
+++ b/net/devlink/netlink.c
@@ -9,6 +9,10 @@
 
 #include "devl_internal.h"
 
+#define DEVLINK_NL_FLAG_NEED_PORT		BIT(0)
+#define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT	BIT(1)
+#define DEVLINK_NL_FLAG_NEED_DEV_LOCK		BIT(2)
+
 static const struct genl_multicast_group devlink_nl_mcgrps[] = {
 	[DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME },
 };
@@ -61,7 +65,8 @@ int devlink_nl_msg_reply_and_new(struct sk_buff **msg, struct genl_info *info)
 }
 
 struct devlink *
-devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs)
+devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs,
+			    bool dev_lock)
 {
 	struct devlink *devlink;
 	unsigned long index;
@@ -75,12 +80,12 @@ devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs)
 	devname = nla_data(attrs[DEVLINK_ATTR_DEV_NAME]);
 
 	devlinks_xa_for_each_registered_get(net, index, devlink) {
-		devl_lock(devlink);
+		devl_dev_lock(devlink, dev_lock);
 		if (devl_is_registered(devlink) &&
 		    strcmp(devlink->dev->bus->name, busname) == 0 &&
 		    strcmp(dev_name(devlink->dev), devname) == 0)
 			return devlink;
-		devl_unlock(devlink);
+		devl_dev_unlock(devlink, dev_lock);
 		devlink_put(devlink);
 	}
 
@@ -90,11 +95,13 @@ devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs)
 static int __devlink_nl_pre_doit(struct sk_buff *skb, struct genl_info *info,
 				 u8 flags)
 {
+	bool dev_lock = flags & DEVLINK_NL_FLAG_NEED_DEV_LOCK;
 	struct devlink_port *devlink_port;
 	struct devlink *devlink;
 	int err;
 
-	devlink = devlink_get_from_attrs_lock(genl_info_net(info), info->attrs);
+	devlink = devlink_get_from_attrs_lock(genl_info_net(info), info->attrs,
+					      dev_lock);
 	if (IS_ERR(devlink))
 		return PTR_ERR(devlink);
 
@@ -114,7 +121,7 @@ static int __devlink_nl_pre_doit(struct sk_buff *skb, struct genl_info *info,
 	return 0;
 
 unlock:
-	devl_unlock(devlink);
+	devl_dev_unlock(devlink, dev_lock);
 	devlink_put(devlink);
 	return err;
 }
@@ -131,6 +138,12 @@ int devlink_nl_pre_doit_port(const struct genl_split_ops *ops,
 	return __devlink_nl_pre_doit(skb, info, DEVLINK_NL_FLAG_NEED_PORT);
 }
 
+int devlink_nl_pre_doit_dev_lock(const struct genl_split_ops *ops,
+				 struct sk_buff *skb, struct genl_info *info)
+{
+	return __devlink_nl_pre_doit(skb, info, DEVLINK_NL_FLAG_NEED_DEV_LOCK);
+}
+
 int devlink_nl_pre_doit_port_optional(const struct genl_split_ops *ops,
 				      struct sk_buff *skb,
 				      struct genl_info *info)
@@ -138,16 +151,30 @@ int devlink_nl_pre_doit_port_optional(const struct genl_split_ops *ops,
 	return __devlink_nl_pre_doit(skb, info, DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT);
 }
 
-void devlink_nl_post_doit(const struct genl_split_ops *ops,
-			  struct sk_buff *skb, struct genl_info *info)
+static void __devlink_nl_post_doit(struct sk_buff *skb, struct genl_info *info,
+				   u8 flags)
 {
+	bool dev_lock = flags & DEVLINK_NL_FLAG_NEED_DEV_LOCK;
 	struct devlink *devlink;
 
 	devlink = info->user_ptr[0];
-	devl_unlock(devlink);
+	devl_dev_unlock(devlink, dev_lock);
 	devlink_put(devlink);
 }
 
+void devlink_nl_post_doit(const struct genl_split_ops *ops,
+			  struct sk_buff *skb, struct genl_info *info)
+{
+	__devlink_nl_post_doit(skb, info, 0);
+}
+
+void
+devlink_nl_post_doit_dev_lock(const struct genl_split_ops *ops,
+			      struct sk_buff *skb, struct genl_info *info)
+{
+	__devlink_nl_post_doit(skb, info, DEVLINK_NL_FLAG_NEED_DEV_LOCK);
+}
+
 static int devlink_nl_inst_single_dumpit(struct sk_buff *msg,
 					 struct netlink_callback *cb, int flags,
 					 devlink_nl_dump_one_func_t *dump_one,
@@ -156,7 +183,7 @@ static int devlink_nl_inst_single_dumpit(struct sk_buff *msg,
 	struct devlink *devlink;
 	int err;
 
-	devlink = devlink_get_from_attrs_lock(sock_net(msg->sk), attrs);
+	devlink = devlink_get_from_attrs_lock(sock_net(msg->sk), attrs, false);
 	if (IS_ERR(devlink))
 		return PTR_ERR(devlink);
 	err = dump_one(msg, devlink, cb, flags | NLM_F_DUMP_FILTERED);
diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c
index 788dfdc498a9..95f9b4350ab7 100644
--- a/net/devlink/netlink_gen.c
+++ b/net/devlink/netlink_gen.c
@@ -846,9 +846,9 @@ const struct genl_split_ops devlink_nl_ops[73] = {
 	{
 		.cmd		= DEVLINK_CMD_RELOAD,
 		.validate	= GENL_DONT_VALIDATE_STRICT,
-		.pre_doit	= devlink_nl_pre_doit,
+		.pre_doit	= devlink_nl_pre_doit_dev_lock,
 		.doit		= devlink_nl_reload_doit,
-		.post_doit	= devlink_nl_post_doit,
+		.post_doit	= devlink_nl_post_doit_dev_lock,
 		.policy		= devlink_reload_nl_policy,
 		.maxattr	= DEVLINK_ATTR_RELOAD_LIMITS,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
diff --git a/net/devlink/netlink_gen.h b/net/devlink/netlink_gen.h
index 0e9e89c31c31..02f3c0bfae0e 100644
--- a/net/devlink/netlink_gen.h
+++ b/net/devlink/netlink_gen.h
@@ -22,12 +22,17 @@ int devlink_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 			struct genl_info *info);
 int devlink_nl_pre_doit_port(const struct genl_split_ops *ops,
 			     struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_pre_doit_dev_lock(const struct genl_split_ops *ops,
+				 struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_pre_doit_port_optional(const struct genl_split_ops *ops,
 				      struct sk_buff *skb,
 				      struct genl_info *info);
 void
 devlink_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 		     struct genl_info *info);
+void
+devlink_nl_post_doit_dev_lock(const struct genl_split_ops *ops,
+			      struct sk_buff *skb, struct genl_info *info);
 
 int devlink_nl_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
diff --git a/net/devlink/region.c b/net/devlink/region.c
index 0aab7b82d678..e3bab458db94 100644
--- a/net/devlink/region.c
+++ b/net/devlink/region.c
@@ -883,7 +883,8 @@ int devlink_nl_region_read_dumpit(struct sk_buff *skb,
 
 	start_offset = state->start_offset;
 
-	devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs);
+	devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs,
+					      false);
 	if (IS_ERR(devlink))
 		return PTR_ERR(devlink);