All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jiri Pirko <jiri@resnulli.us>
To: Moshe Shemesh <moshe@mellanox.com>
Cc: "David S. Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>, Jiri Pirko <jiri@mellanox.com>,
	netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH net-next RFC v4 10/15] net/mlx5: Add support for devlink reload action fw activate
Date: Mon, 14 Sep 2020 15:52:51 +0200	[thread overview]
Message-ID: <20200914135251.GI2236@nanopsycho.orion> (raw)
In-Reply-To: <1600063682-17313-11-git-send-email-moshe@mellanox.com>

Mon, Sep 14, 2020 at 08:07:57AM CEST, moshe@mellanox.com wrote:
>Add support for devlink reload action fw_activate. To activate firmware
>image the mlx5 driver resets the firmware and reloads it from flash. If
>a new image was stored on flash it will be loaded. Once this reload
>command is executed the driver initiates fw sync reset flow, where the
>firmware synchronizes all PFs on coming reset and driver reload.
>
>Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
>---
>v3 -> v4:
>- Renamed actions_done to actions_performed
>v2 -> v3:
>- Return the reload actions done
>- Update reload action counters if reset initiated by remote host
>v1 -> v2:
>- Have fw_activate action instead of fw_reset level
>---
> .../net/ethernet/mellanox/mlx5/core/devlink.c | 62 ++++++++++++++++---
> .../ethernet/mellanox/mlx5/core/fw_reset.c    | 60 ++++++++++++++++--
> .../ethernet/mellanox/mlx5/core/fw_reset.h    |  1 +
> 3 files changed, 109 insertions(+), 14 deletions(-)
>
>diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
>index f6b29deaf02e..fa8f6abbea4e 100644
>--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
>+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
>@@ -4,6 +4,7 @@
> #include <devlink.h>
> 
> #include "mlx5_core.h"
>+#include "fw_reset.h"
> #include "fs_core.h"
> #include "eswitch.h"
> 
>@@ -88,6 +89,32 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
> 	return 0;
> }
> 
>+static int mlx5_devlink_reload_fw_activate(struct devlink *devlink, struct netlink_ext_ack *extack)
>+{
>+	struct mlx5_core_dev *dev = devlink_priv(devlink);
>+	u8 reset_level, reset_type, net_port_alive;
>+	int err;
>+
>+	err = mlx5_reg_mfrl_query(dev, &reset_level, &reset_type);
>+	if (err)
>+		return err;
>+	if (!(reset_level & MLX5_MFRL_REG_RESET_LEVEL3)) {
>+		NL_SET_ERR_MSG_MOD(extack, "FW activate requires reboot");
>+		return -EINVAL;
>+	}
>+
>+	net_port_alive = !!(reset_type & MLX5_MFRL_REG_RESET_TYPE_NET_PORT_ALIVE);
>+	err = mlx5_fw_set_reset_sync(dev, net_port_alive);
>+	if (err)
>+		goto out;
>+
>+	err = mlx5_fw_wait_fw_reset_done(dev);
>+out:
>+	if (err)
>+		NL_SET_ERR_MSG_MOD(extack, "FW activate command failed");
>+	return err;
>+}
>+
> static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change,
> 				    enum devlink_reload_action action,
> 				    enum devlink_reload_action_limit_level limit_level,
>@@ -95,8 +122,17 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change,
> {
> 	struct mlx5_core_dev *dev = devlink_priv(devlink);
> 
>-	mlx5_unload_one(dev, false);
>-	return 0;
>+	switch (action) {
>+	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT:
>+		mlx5_unload_one(dev, false);
>+		return 0;
>+	case DEVLINK_RELOAD_ACTION_FW_ACTIVATE:
>+		return mlx5_devlink_reload_fw_activate(devlink, extack);
>+	default:
>+		/* Unsupported action should not get to this function */
>+		WARN_ON(1);
>+		return -EOPNOTSUPP;
>+	}
> }
> 
> static int mlx5_devlink_reload_up(struct devlink *devlink, enum devlink_reload_action action,
>@@ -104,13 +140,22 @@ static int mlx5_devlink_reload_up(struct devlink *devlink, enum devlink_reload_a
> 				  struct netlink_ext_ack *extack, unsigned long *actions_performed)
> {
> 	struct mlx5_core_dev *dev = devlink_priv(devlink);
>-	int err;
> 
>-	err = mlx5_load_one(dev, false);
>-	if (err)
>-		return err;
> 	if (actions_performed)
>-		*actions_performed = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT);
>+		*actions_performed = BIT(action);
>+
>+	switch (action) {
>+	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT:
>+	case DEVLINK_RELOAD_ACTION_FW_ACTIVATE:
>+		/* On fw_activate action, also driver is reloaded and reinit performed */
>+		if (actions_performed)
>+			*actions_performed |= BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT);

You should set DEVLINK_RELOAD_ACTION_FW_ACTIVATE bit in actions_performed
upon activation.


>+		return mlx5_load_one(dev, false);
>+	default:
>+		/* Unsupported action should not get to this function */
>+		WARN_ON(1);
>+		return -EOPNOTSUPP;
>+	}
> 
> 	return 0;
> }
>@@ -128,7 +173,8 @@ static const struct devlink_ops mlx5_devlink_ops = {
> #endif
> 	.flash_update = mlx5_devlink_flash_update,
> 	.info_get = mlx5_devlink_info_get,
>-	.supported_reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT),
>+	.supported_reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) |
>+				    BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE),
> 	.supported_reload_action_limit_levels = BIT(DEVLINK_RELOAD_ACTION_LIMIT_LEVEL_NONE),
> 	.reload_down = mlx5_devlink_reload_down,
> 	.reload_up = mlx5_devlink_reload_up,
>diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
>index 61237f4836cc..550f67b00473 100644
>--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
>+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
>@@ -5,6 +5,7 @@
> 
> enum {
> 	MLX5_FW_RESET_FLAGS_RESET_REQUESTED,
>+	MLX5_FW_RESET_FLAGS_PENDING_COMP
> };
> 
> struct mlx5_fw_reset {
>@@ -17,6 +18,8 @@ struct mlx5_fw_reset {
> 	struct work_struct reset_abort_work;
> 	unsigned long reset_flags;
> 	struct timer_list timer;
>+	struct completion done;
>+	int ret;
> };
> 
> static int mlx5_reg_mfrl_set(struct mlx5_core_dev *dev, u8 reset_level,
>@@ -53,7 +56,14 @@ int mlx5_reg_mfrl_query(struct mlx5_core_dev *dev, u8 *reset_level, u8 *reset_ty
> 
> int mlx5_fw_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel)
> {
>-	return mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL3, reset_type_sel, 0, true);
>+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
>+	int err;
>+
>+	set_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags);
>+	err =  mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL3, reset_type_sel, 0, true);
>+	if (err)
>+		clear_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags);
>+	return err;
> }
> 
> int mlx5_fw_set_live_patch(struct mlx5_core_dev *dev)
>@@ -66,19 +76,36 @@ static int mlx5_fw_set_reset_sync_ack(struct mlx5_core_dev *dev)
> 	return mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL3, 0, 1, false);
> }
> 
>+static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev)
>+{
>+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
>+
>+	/* if this is the driver that initiated the fw reset, devlink completed the reload */
>+	if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) {
>+		complete(&fw_reset->done);
>+	} else {
>+		mlx5_load_one(dev, false);
>+		devlink_reload_implicit_actions_performed(priv_to_devlink(dev),
>+							  DEVLINK_RELOAD_ACTION_LIMIT_LEVEL_NONE,
>+							  BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) |
>+							  BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE));
>+	}
>+}
>+
> static void mlx5_sync_reset_reload_work(struct work_struct *work)
> {
> 	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
> 						      reset_reload_work);
> 	struct mlx5_core_dev *dev = fw_reset->dev;
>+	int err;
> 
> 	mlx5_enter_error_state(dev, true);
> 	mlx5_unload_one(dev, false);
>-	if (mlx5_health_wait_pci_up(dev)) {
>+	err = mlx5_health_wait_pci_up(dev);
>+	if (err)
> 		mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n");
>-		return;
>-	}
>-	mlx5_load_one(dev, false);
>+	fw_reset->ret = err;
>+	mlx5_fw_reset_complete_reload(dev);
> }
> 
> static void mlx5_stop_sync_reset_poll(struct mlx5_core_dev *dev)
>@@ -264,7 +291,8 @@ static void mlx5_sync_reset_now_event(struct work_struct *work)
> done:
> 	if (err)
> 		mlx5_start_health_poll(dev);
>-	mlx5_load_one(dev, false);
>+	fw_reset->ret = err;
>+	mlx5_fw_reset_complete_reload(dev);
> }
> 
> static void mlx5_sync_reset_abort_event(struct work_struct *work)
>@@ -313,6 +341,25 @@ static int fw_reset_event_notifier(struct notifier_block *nb, unsigned long acti
> 	return NOTIFY_OK;
> }
> 
>+#define MLX5_FW_RESET_TIMEOUT_MSEC 5000
>+int mlx5_fw_wait_fw_reset_done(struct mlx5_core_dev *dev)
>+{
>+	unsigned long timeout = msecs_to_jiffies(MLX5_FW_RESET_TIMEOUT_MSEC);
>+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
>+	int err;
>+
>+	if (!wait_for_completion_timeout(&fw_reset->done, timeout)) {
>+		mlx5_core_warn(dev, "FW sync reset timeout after %d seconds\n",
>+			       MLX5_FW_RESET_TIMEOUT_MSEC / 1000);
>+		err = -ETIMEDOUT;
>+		goto out;
>+	}
>+	err = fw_reset->ret;
>+out:
>+	clear_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags);
>+	return err;
>+}
>+
> int mlx5_fw_reset_events_init(struct mlx5_core_dev *dev)
> {
> 	struct mlx5_fw_reset *fw_reset = kzalloc(sizeof(*fw_reset), GFP_KERNEL);
>@@ -336,6 +383,7 @@ int mlx5_fw_reset_events_init(struct mlx5_core_dev *dev)
> 	MLX5_NB_INIT(&fw_reset->nb, fw_reset_event_notifier, GENERAL_EVENT);
> 	mlx5_eq_notifier_register(dev, &fw_reset->nb);
> 
>+	init_completion(&fw_reset->done);
> 	return 0;
> }
> 
>diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
>index 278f538ea92a..d7ee951a2258 100644
>--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
>+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
>@@ -10,6 +10,7 @@ int mlx5_reg_mfrl_query(struct mlx5_core_dev *dev, u8 *reset_level, u8 *reset_ty
> int mlx5_fw_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel);
> int mlx5_fw_set_live_patch(struct mlx5_core_dev *dev);
> 
>+int mlx5_fw_wait_fw_reset_done(struct mlx5_core_dev *dev);
> int mlx5_fw_reset_events_init(struct mlx5_core_dev *dev);
> void mlx5_fw_reset_events_cleanup(struct mlx5_core_dev *dev);
> 
>-- 
>2.17.1
>

  reply	other threads:[~2020-09-14 13:56 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-09-14  6:07 [PATCH net-next RFC v4 00/15] Add devlink reload action and Moshe Shemesh
2020-09-14  6:07 ` [PATCH net-next RFC v4 01/15] devlink: Add reload action option to devlink reload command Moshe Shemesh
2020-09-14  7:08   ` Vasundhara Volam
2020-09-14  9:32     ` Jiri Pirko
2020-09-14  9:54       ` Vasundhara Volam
2020-09-14 11:28         ` Jiri Pirko
2020-09-14 21:31           ` Jakub Kicinski
2020-09-14 22:06             ` Michael Chan
2020-09-15  6:18               ` Jiri Pirko
2020-09-14 12:27   ` Jiri Pirko
2020-09-15 12:12     ` Moshe Shemesh
2020-09-15 13:26       ` Jiri Pirko
2020-09-15 20:06         ` Moshe Shemesh
2020-09-14 21:33   ` Jakub Kicinski
2020-09-15 12:56     ` Moshe Shemesh
2020-09-15 13:26       ` Jiri Pirko
2020-09-15 16:00       ` Jakub Kicinski
2020-09-14  6:07 ` [PATCH net-next RFC v4 02/15] devlink: Add reload action limit level Moshe Shemesh
2020-09-14 13:10   ` Jiri Pirko
2020-09-15 12:15     ` Moshe Shemesh
2020-09-14  6:07 ` [PATCH net-next RFC v4 03/15] devlink: Add reload action stats Moshe Shemesh
2020-09-14 13:39   ` Jiri Pirko
2020-09-15 12:30     ` Moshe Shemesh
2020-09-15 13:33       ` Jiri Pirko
2020-09-15 20:20         ` Moshe Shemesh
2020-09-16  6:07           ` Jiri Pirko
2020-09-14  6:07 ` [PATCH net-next RFC v4 04/15] devlink: Add reload actions stats to dev get Moshe Shemesh
2020-09-14 13:45   ` Jiri Pirko
2020-09-15  6:45     ` Ido Schimmel
2020-09-15  7:44       ` Jiri Pirko
2020-09-15 12:31         ` Moshe Shemesh
2020-09-15 13:34           ` Jiri Pirko
2020-09-15 20:33             ` Moshe Shemesh
2020-09-18 16:13               ` Moshe Shemesh
2020-09-21 10:33                 ` Jiri Pirko
2020-09-14  6:07 ` [PATCH net-next RFC v4 05/15] net/mlx5: Add functions to set/query MFRL register Moshe Shemesh
2020-09-14  6:07 ` [PATCH net-next RFC v4 06/15] net/mlx5: Set cap for pci sync for fw update event Moshe Shemesh
2020-09-14  6:07 ` [PATCH net-next RFC v4 07/15] net/mlx5: Handle sync reset request event Moshe Shemesh
2020-09-14  6:07 ` [PATCH net-next RFC v4 08/15] net/mlx5: Handle sync reset now event Moshe Shemesh
2020-09-14  6:07 ` [PATCH net-next RFC v4 09/15] net/mlx5: Handle sync reset abort event Moshe Shemesh
2020-09-14  6:07 ` [PATCH net-next RFC v4 10/15] net/mlx5: Add support for devlink reload action fw activate Moshe Shemesh
2020-09-14 13:52   ` Jiri Pirko [this message]
2020-09-15 12:38     ` Moshe Shemesh
2020-09-14 13:54   ` Jiri Pirko
2020-09-15 12:44     ` Moshe Shemesh
2020-09-15 13:37       ` Jiri Pirko
2020-09-15 20:28         ` Moshe Shemesh
2020-09-16  6:08           ` Jiri Pirko
2020-09-14  6:07 ` [PATCH net-next RFC v4 11/15] devlink: Add enable_remote_dev_reset generic parameter Moshe Shemesh
2020-09-14 14:12   ` Jiri Pirko
2020-09-14  6:07 ` [PATCH net-next RFC v4 12/15] net/mlx5: Add devlink param enable_remote_dev_reset support Moshe Shemesh
2020-09-14  6:08 ` [PATCH net-next RFC v4 13/15] net/mlx5: Add support for fw live patch event Moshe Shemesh
2020-09-14  6:08 ` [PATCH net-next RFC v4 14/15] net/mlx5: Add support for devlink reload action limit level no reset Moshe Shemesh
2020-09-14  6:08 ` [PATCH net-next RFC v4 15/15] devlink: Add Documentation/networking/devlink/devlink-reload.rst Moshe Shemesh
2020-09-14 11:43   ` Jiri Pirko
2020-09-15 16:04   ` Jakub Kicinski
2020-09-15 19:59     ` Moshe Shemesh

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200914135251.GI2236@nanopsycho.orion \
    --to=jiri@resnulli.us \
    --cc=davem@davemloft.net \
    --cc=jiri@mellanox.com \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=moshe@mellanox.com \
    --cc=netdev@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.