kmod-redhat-mlx5_core/SOURCES/0280-netdrv-net-mlx5-Avoid-processing-commands-before-cmd.patch

From e1a165d97b043db33a647577da3cac42d9653202 Mon Sep 17 00:00:00 2001
From: Alaa Hleihel <ahleihel@redhat.com>
Date: Mon, 1 Jun 2020 15:40:33 -0400
Subject: [PATCH 280/312] [netdrv] net/mlx5: Avoid processing commands before
 cmdif is ready

Message-id: <20200601154102.25980-11-ahleihel@redhat.com>
Patchwork-id: 315715
Patchwork-instance: patchwork
O-Subject: [RHEL8.3 BZ 1842258 10/39] net/mlx5: Avoid processing commands before cmdif is ready
Bugzilla: 1842258
RH-Acked-by: Honggang Li <honli@redhat.com>
RH-Acked-by: Kamal Heib <kheib@redhat.com>
RH-Acked-by: Marcelo Leitner <mleitner@redhat.com>
RH-Acked-by: Jarod Wilson <jarod@redhat.com>

Bugzilla: http://bugzilla.redhat.com/1842258
Upstream: v5.7-rc7

commit f7936ddd35d8b849daf0372770c7c9dbe7910fca
Author: Eran Ben Elisha <eranbe@mellanox.com>
Date:   Thu Mar 19 21:43:13 2020 +0200

    net/mlx5: Avoid processing commands before cmdif is ready

    When driver is reloading during recovery flow, it can't get new commands
    till command interface is up again. Otherwise we may get to null pointer
    trying to access non initialized command structures.

    Add cmdif state to avoid processing commands while cmdif is not ready.

    Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
    Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
    Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
    Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

Signed-off-by: Alaa Hleihel <ahleihel@redhat.com>
Signed-off-by: Frantisek Hrbata <fhrbata@redhat.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c  | 10 ++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/main.c |  4 ++++
 include/linux/mlx5/driver.h                    |  9 +++++++++
 3 files changed, 23 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 2280bb7e748d..3745fcd9a99e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -923,6 +923,7 @@ static void cmd_work_handler(struct work_struct *work)
 	/* Skip sending command to fw if internal error */
 	if (pci_channel_offline(dev->pdev) ||
 	    dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR ||
+	    cmd->state != MLX5_CMDIF_STATE_UP ||
 	    !opcode_allowed(&dev->cmd, ent->op)) {
 		u8 status = 0;
 		u32 drv_synd;
@@ -1712,6 +1713,7 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 	opcode = MLX5_GET(mbox_in, in, opcode);
 	if (pci_channel_offline(dev->pdev) ||
 	    dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR ||
+	    dev->cmd.state != MLX5_CMDIF_STATE_UP ||
 	    !opcode_allowed(&dev->cmd, opcode)) {
 		err = mlx5_internal_err_ret_value(dev, opcode, &drv_synd, &status);
 		MLX5_SET(mbox_out, out, status, status);
@@ -1977,6 +1979,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 		goto err_free_page;
 	}
 
+	cmd->state = MLX5_CMDIF_STATE_DOWN;
 	cmd->checksum_disabled = 1;
 	cmd->max_reg_cmds = (1 << cmd->log_sz) - 1;
 	cmd->bitmask = (1UL << cmd->max_reg_cmds) - 1;
@@ -2054,3 +2057,10 @@ void mlx5_cmd_cleanup(struct mlx5_core_dev *dev)
 	dma_pool_destroy(cmd->pool);
 }
 EXPORT_SYMBOL(mlx5_cmd_cleanup);
+
+void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
+			enum mlx5_cmdif_state cmdif_state)
+{
+	dev->cmd.state = cmdif_state;
+}
+EXPORT_SYMBOL(mlx5_cmd_set_state);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 880bc53d0b1b..fdc0c0f7da96 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -993,6 +993,8 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot)
 		goto err_cmd_cleanup;
 	}
 
+	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_UP);
+
 	err = mlx5_core_enable_hca(dev, 0);
 	if (err) {
 		mlx5_core_err(dev, "enable hca failed\n");
@@ -1056,6 +1058,7 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot)
 err_disable_hca:
 	mlx5_core_disable_hca(dev, 0);
 err_cmd_cleanup:
+	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_cleanup(dev);
 
 	return err;
@@ -1073,6 +1076,7 @@ static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot)
 	}
 	mlx5_reclaim_startup_pages(dev);
 	mlx5_core_disable_hca(dev, 0);
+	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_cleanup(dev);
 
 	return 0;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index c2009064805a..013786924596 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -228,6 +228,12 @@ struct mlx5_bfreg_info {
 	u32			num_dyn_bfregs;
 };
 
+enum mlx5_cmdif_state {
+	MLX5_CMDIF_STATE_UNINITIALIZED,
+	MLX5_CMDIF_STATE_UP,
+	MLX5_CMDIF_STATE_DOWN,
+};
+
 struct mlx5_cmd_first {
 	__be32		data[4];
 };
@@ -301,6 +307,7 @@ struct mlx5_cmd {
 	spinlock_t	token_lock;
 	u8		token;
 #ifndef __GENKSYMS__
+	u8 /* enum mlx5_cmdif_state */	state;
 	u16     allowed_opcode;
 #endif
 	unsigned long	bitmask;
@@ -904,6 +911,8 @@ enum {
 
 int mlx5_cmd_init(struct mlx5_core_dev *dev);
 void mlx5_cmd_cleanup(struct mlx5_core_dev *dev);
+void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
+			enum mlx5_cmdif_state cmdif_state);
 void mlx5_cmd_use_events(struct mlx5_core_dev *dev);
 void mlx5_cmd_use_polling(struct mlx5_core_dev *dev);
 void mlx5_cmd_allowed_opcode(struct mlx5_core_dev *dev, u16 opcode);
-- 
2.13.6