From 43c075959de3c45608636d9d80ff9e61d166fb21 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 26 Jan 2022 10:57:07 -0800
Subject: mlx5: remove unused static inlines

mlx5 has some unused static inline helpers in include/
while at it also clean static inlines in the driver itself.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 include/linux/mlx5/driver.h | 10 ----------
 1 file changed, 10 deletions(-)

(limited to 'include/linux/mlx5/driver.h')

diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 78655d8d13a7..1b398c9e17b9 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -863,20 +863,10 @@ struct mlx5_hca_vport_context {
 	bool			grh_required;
 };
 
-static inline void *mlx5_buf_offset(struct mlx5_frag_buf *buf, int offset)
-{
-		return buf->frags->buf + offset;
-}
-
 #define STRUCT_FIELD(header, field) \
 	.struct_offset_bytes = offsetof(struct ib_unpacked_ ## header, field),      \
 	.struct_size_bytes   = sizeof((struct ib_unpacked_ ## header *)0)->field
 
-static inline struct mlx5_core_dev *pci2mlx5_core_dev(struct pci_dev *pdev)
-{
-	return pci_get_drvdata(pdev);
-}
-
 extern struct dentry *mlx5_debugfs_root;
 
 static inline u16 fw_rev_maj(struct mlx5_core_dev *dev)
-- 
cgit v1.2.3


From 605bef0015b163867127202b821dce79804d603d Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Sun, 5 Apr 2020 17:50:25 -0700
Subject: net/mlx5: cmdif, cmd_check refactoring

Do not mangle the command outbox in the internal low level cmd_exec and
cmd_invoke functions.

Instead return a proper unique error code and move the driver error
checking to be at a higher level in mlx5_cmd_exec().

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c  | 173 +++++++++++++------------
 drivers/net/ethernet/mellanox/mlx5/core/main.c |   5 +-
 include/linux/mlx5/driver.h                    |   1 -
 3 files changed, 95 insertions(+), 84 deletions(-)

(limited to 'include/linux/mlx5/driver.h')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 3c6a533ee0c9..7ff01b901f53 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -760,43 +760,61 @@ struct mlx5_ifc_mbox_in_bits {
 	u8         reserved_at_40[0x40];
 };
 
-void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome)
-{
-	*status = MLX5_GET(mbox_out, out, status);
-	*syndrome = MLX5_GET(mbox_out, out, syndrome);
-}
-
-static int mlx5_cmd_check(struct mlx5_core_dev *dev, void *in, void *out)
+static void cmd_status_print(struct mlx5_core_dev *dev, void *in, void *out)
 {
+	u16 opcode, op_mod;
 	u32 syndrome;
 	u8  status;
-	u16 opcode;
-	u16 op_mod;
 	u16 uid;
+	int err;
 
-	mlx5_cmd_mbox_status(out, &status, &syndrome);
-	if (!status)
-		return 0;
+	syndrome = MLX5_GET(mbox_out, out, syndrome);
+	status = MLX5_GET(mbox_out, out, status);
 
 	opcode = MLX5_GET(mbox_in, in, opcode);
 	op_mod = MLX5_GET(mbox_in, in, op_mod);
 	uid    = MLX5_GET(mbox_in, in, uid);
 
+	err = cmd_status_to_err(status);
+
 	if (!uid && opcode != MLX5_CMD_OP_DESTROY_MKEY)
 		mlx5_core_err_rl(dev,
-			"%s(0x%x) op_mod(0x%x) failed, status %s(0x%x), syndrome (0x%x)\n",
+			"%s(0x%x) op_mod(0x%x) failed, status %s(0x%x), syndrome (0x%x), err(%d)\n",
 			mlx5_command_str(opcode), opcode, op_mod,
-			cmd_status_str(status), status, syndrome);
+			cmd_status_str(status), status, syndrome, err);
 	else
 		mlx5_core_dbg(dev,
-		      "%s(0x%x) op_mod(0x%x) failed, status %s(0x%x), syndrome (0x%x)\n",
-		      mlx5_command_str(opcode),
-		      opcode, op_mod,
-		      cmd_status_str(status),
-		      status,
-		      syndrome);
+			"%s(0x%x) op_mod(0x%x) uid(%d) failed, status %s(0x%x), syndrome (0x%x), err(%d)\n",
+			mlx5_command_str(opcode), opcode, op_mod, uid,
+			cmd_status_str(status), status, syndrome, err);
+}
+
+static int mlx5_cmd_check(struct mlx5_core_dev *dev, int err, void *in, void *out)
+{
+	/* aborted due to PCI error or via reset flow mlx5_cmd_trigger_completions() */
+	if (err == -ENXIO) {
+		u16 opcode = MLX5_GET(mbox_in, in, opcode);
+		u32 syndrome;
+		u8 status;
+
+		/* PCI Error, emulate command return status, for smooth reset */
+		err = mlx5_internal_err_ret_value(dev, opcode, &syndrome, &status);
+		MLX5_SET(mbox_out, out, status, status);
+		MLX5_SET(mbox_out, out, syndrome, syndrome);
+		if (!err)
+			return 0;
+	}
+
+	/* driver or FW delivery error */
+	if (err)
+		return err;
 
-	return cmd_status_to_err(status);
+	/* check outbox status */
+	err = cmd_status_to_err(MLX5_GET(mbox_out, out, status));
+	if (err)
+		cmd_status_print(dev, in, out);
+
+	return err;
 }
 
 static void dump_command(struct mlx5_core_dev *dev,
@@ -980,13 +998,7 @@ static void cmd_work_handler(struct work_struct *work)
 
 	/* Skip sending command to fw if internal error */
 	if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, ent->op)) {
-		u8 status = 0;
-		u32 drv_synd;
-
-		ent->ret = mlx5_internal_err_ret_value(dev, msg_to_opcode(ent->in), &drv_synd, &status);
-		MLX5_SET(mbox_out, ent->out, status, status);
-		MLX5_SET(mbox_out, ent->out, syndrome, drv_synd);
-
+		ent->ret = -ENXIO;
 		mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true);
 		return;
 	}
@@ -1005,6 +1017,31 @@ static void cmd_work_handler(struct work_struct *work)
 	}
 }
 
+static int deliv_status_to_err(u8 status)
+{
+	switch (status) {
+	case MLX5_CMD_DELIVERY_STAT_OK:
+	case MLX5_DRIVER_STATUS_ABORTED:
+		return 0;
+	case MLX5_CMD_DELIVERY_STAT_SIGNAT_ERR:
+	case MLX5_CMD_DELIVERY_STAT_TOK_ERR:
+		return -EBADR;
+	case MLX5_CMD_DELIVERY_STAT_BAD_BLK_NUM_ERR:
+	case MLX5_CMD_DELIVERY_STAT_OUT_PTR_ALIGN_ERR:
+	case MLX5_CMD_DELIVERY_STAT_IN_PTR_ALIGN_ERR:
+		return -EFAULT; /* Bad address */
+	case MLX5_CMD_DELIVERY_STAT_IN_LENGTH_ERR:
+	case MLX5_CMD_DELIVERY_STAT_OUT_LENGTH_ERR:
+	case MLX5_CMD_DELIVERY_STAT_CMD_DESCR_ERR:
+	case MLX5_CMD_DELIVERY_STAT_RES_FLD_NOT_CLR_ERR:
+		return -ENOMSG;
+	case MLX5_CMD_DELIVERY_STAT_FW_ERR:
+		return -EIO;
+	default:
+		return -EINVAL;
+	}
+}
+
 static const char *deliv_status_to_str(u8 status)
 {
 	switch (status) {
@@ -1622,15 +1659,15 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force
 			ent->ts2 = ktime_get_ns();
 			memcpy(ent->out->first.data, ent->lay->out, sizeof(ent->lay->out));
 			dump_command(dev, ent, 0);
-			if (!ent->ret) {
+
+			if (vec & MLX5_TRIGGERED_CMD_COMP)
+				ent->ret = -ENXIO;
+
+			if (!ent->ret) { /* Command completed by FW */
 				if (!cmd->checksum_disabled)
 					ent->ret = verify_signature(ent);
-				else
-					ent->ret = 0;
-				if (vec & MLX5_TRIGGERED_CMD_COMP)
-					ent->status = MLX5_DRIVER_STATUS_ABORTED;
-				else
-					ent->status = ent->lay->status_own >> 1;
+
+				ent->status = ent->lay->status_own >> 1;
 
 				mlx5_core_dbg(dev, "command completed. ret 0x%x, delivery status %s(0x%x)\n",
 					      ent->ret, deliv_status_to_str(ent->status), ent->status);
@@ -1649,14 +1686,13 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force
 				callback = ent->callback;
 				context = ent->context;
 				err = ent->ret;
-				if (!err) {
+				if (!err && !ent->status) {
 					err = mlx5_copy_from_msg(ent->uout,
 								 ent->out,
 								 ent->uout_size);
 
-					err = err ? err : mlx5_cmd_check(dev,
-									ent->in->first.data,
-									ent->uout);
+					err = mlx5_cmd_check(dev, err, ent->in->first.data,
+							     ent->uout);
 				}
 
 				mlx5_free_cmd_msg(dev, ent->out);
@@ -1729,31 +1765,6 @@ void mlx5_cmd_flush(struct mlx5_core_dev *dev)
 		up(&cmd->sem);
 }
 
-static int deliv_status_to_err(u8 status)
-{
-	switch (status) {
-	case MLX5_CMD_DELIVERY_STAT_OK:
-	case MLX5_DRIVER_STATUS_ABORTED:
-		return 0;
-	case MLX5_CMD_DELIVERY_STAT_SIGNAT_ERR:
-	case MLX5_CMD_DELIVERY_STAT_TOK_ERR:
-		return -EBADR;
-	case MLX5_CMD_DELIVERY_STAT_BAD_BLK_NUM_ERR:
-	case MLX5_CMD_DELIVERY_STAT_OUT_PTR_ALIGN_ERR:
-	case MLX5_CMD_DELIVERY_STAT_IN_PTR_ALIGN_ERR:
-		return -EFAULT; /* Bad address */
-	case MLX5_CMD_DELIVERY_STAT_IN_LENGTH_ERR:
-	case MLX5_CMD_DELIVERY_STAT_OUT_LENGTH_ERR:
-	case MLX5_CMD_DELIVERY_STAT_CMD_DESCR_ERR:
-	case MLX5_CMD_DELIVERY_STAT_RES_FLD_NOT_CLR_ERR:
-		return -ENOMSG;
-	case MLX5_CMD_DELIVERY_STAT_FW_ERR:
-		return -EIO;
-	default:
-		return -EINVAL;
-	}
-}
-
 static struct mlx5_cmd_msg *alloc_msg(struct mlx5_core_dev *dev, int in_size,
 				      gfp_t gfp)
 {
@@ -1812,15 +1823,8 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 	u8 token;
 	int err;
 
-	if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, opcode)) {
-		u32 drv_synd;
-		u8 status;
-
-		err = mlx5_internal_err_ret_value(dev, opcode, &drv_synd, &status);
-		MLX5_SET(mbox_out, out, status, status);
-		MLX5_SET(mbox_out, out, syndrome, drv_synd);
-		return err;
-	}
+	if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, opcode))
+		return -ENXIO;
 
 	pages_queue = is_manage_pages(in);
 	gfp = callback ? GFP_ATOMIC : GFP_KERNEL;
@@ -1865,13 +1869,24 @@ out_in:
 	return err;
 }
 
+/**
+ * mlx5_cmd_exec - Executes a fw command, wait for completion
+ *
+ * @dev: mlx5 core device
+ * @in: inbox mlx5_ifc command buffer
+ * @in_size: inbox buffer size
+ * @out: outbox mlx5_ifc buffer
+ * @out_size: outbox size
+ *
+ * @return: 0 if no error, FW command execution was successful,
+ *          and outbox status is ok.
+ */
 int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 		  int out_size)
 {
-	int err;
+	int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, false);
 
-	err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, false);
-	return err ? : mlx5_cmd_check(dev, in, out);
+	return mlx5_cmd_check(dev, err, in, out);
 }
 EXPORT_SYMBOL(mlx5_cmd_exec);
 
@@ -1932,11 +1947,9 @@ EXPORT_SYMBOL(mlx5_cmd_exec_cb);
 int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size,
 			  void *out, int out_size)
 {
-	int err;
-
-	err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, true);
+	int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, true);
 
-	return err ? : mlx5_cmd_check(dev, in, out);
+	return mlx5_cmd_check(dev, err, in, out);
 }
 EXPORT_SYMBOL(mlx5_cmd_exec_polling);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 2c774f367199..cea1a8ac196e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -736,10 +736,9 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev)
 	MLX5_SET(query_issi_in, query_in, opcode, MLX5_CMD_OP_QUERY_ISSI);
 	err = mlx5_cmd_exec_inout(dev, query_issi, query_in, query_out);
 	if (err) {
-		u32 syndrome;
-		u8 status;
+		u32 syndrome = MLX5_GET(query_issi_out, query_out, syndrome);
+		u8 status = MLX5_GET(query_issi_out, query_out, status);
 
-		mlx5_cmd_mbox_status(query_out, &status, &syndrome);
 		if (!status || syndrome == MLX5_DRIVER_SYND) {
 			mlx5_core_err(dev, "Failed to query ISSI err(%d) status(%d) synd(%d)\n",
 				      err, status, syndrome);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 1b398c9e17b9..8a8408708e6c 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -981,7 +981,6 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 
 int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size,
 			  void *out, int out_size);
-void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome);
 bool mlx5_cmd_is_down(struct mlx5_core_dev *dev);
 
 int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type);
-- 
cgit v1.2.3


From f23519e542e51c19ab3081deb089bb3f8fec7bb9 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Sat, 17 Aug 2019 03:05:10 -0700
Subject: net/mlx5: cmdif, Add new api for command execution

Add mlx5_cmd_do. Unlike mlx5_cmd_exec, this function will not modify
or translate outbox.status.

The function will return:

return = 0: Command was executed, outbox.status == MLX5_CMD_STAT_OK.

return = -EREMOTEIO: Executed, outbox.status != MLX5_CMD_STAT_OK.

return < 0: Command execution couldn't be performed by FW or driver.

And document other mlx5_cmd_exec functions.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 79 ++++++++++++++++++++++-----
 include/linux/mlx5/driver.h                   |  2 +
 2 files changed, 68 insertions(+), 13 deletions(-)

(limited to 'include/linux/mlx5/driver.h')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 7ff01b901f53..a2f87a686a18 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -789,7 +789,7 @@ static void cmd_status_print(struct mlx5_core_dev *dev, void *in, void *out)
 			cmd_status_str(status), status, syndrome, err);
 }
 
-static int mlx5_cmd_check(struct mlx5_core_dev *dev, int err, void *in, void *out)
+int mlx5_cmd_check(struct mlx5_core_dev *dev, int err, void *in, void *out)
 {
 	/* aborted due to PCI error or via reset flow mlx5_cmd_trigger_completions() */
 	if (err == -ENXIO) {
@@ -806,7 +806,7 @@ static int mlx5_cmd_check(struct mlx5_core_dev *dev, int err, void *in, void *ou
 	}
 
 	/* driver or FW delivery error */
-	if (err)
+	if (err != -EREMOTEIO && err)
 		return err;
 
 	/* check outbox status */
@@ -816,6 +816,7 @@ static int mlx5_cmd_check(struct mlx5_core_dev *dev, int err, void *in, void *ou
 
 	return err;
 }
+EXPORT_SYMBOL(mlx5_cmd_check);
 
 static void dump_command(struct mlx5_core_dev *dev,
 			 struct mlx5_cmd_work_ent *ent, int input)
@@ -1869,6 +1870,38 @@ out_in:
 	return err;
 }
 
+/**
+ * mlx5_cmd_do - Executes a fw command, wait for completion.
+ * Unlike mlx5_cmd_exec, this function will not translate or intercept
+ * outbox.status and will return -EREMOTEIO when
+ * outbox.status != MLX5_CMD_STAT_OK
+ *
+ * @dev: mlx5 core device
+ * @in: inbox mlx5_ifc command buffer
+ * @in_size: inbox buffer size
+ * @out: outbox mlx5_ifc buffer
+ * @out_size: outbox size
+ *
+ * @return:
+ * -EREMOTEIO : Command executed by FW, outbox.status != MLX5_CMD_STAT_OK.
+ *              Caller must check FW outbox status.
+ *   0 : Command execution successful, outbox.status == MLX5_CMD_STAT_OK.
+ * < 0 : Command execution couldn't be performed by firmware or driver
+ */
+int mlx5_cmd_do(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size)
+{
+	int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, false);
+
+	if (err) /* -EREMOTEIO is preserved */
+		return err == -EREMOTEIO ? -EIO : err;
+
+	if (MLX5_GET(mbox_out, out, status) != MLX5_CMD_STAT_OK)
+		return -EREMOTEIO;
+
+	return 0;
+}
+EXPORT_SYMBOL(mlx5_cmd_do);
+
 /**
  * mlx5_cmd_exec - Executes a fw command, wait for completion
  *
@@ -1878,18 +1911,47 @@ out_in:
  * @out: outbox mlx5_ifc buffer
  * @out_size: outbox size
  *
- * @return: 0 if no error, FW command execution was successful,
+ * @return: 0 if no error, FW command execution was successful
  *          and outbox status is ok.
  */
 int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 		  int out_size)
 {
-	int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, false);
+	int err = mlx5_cmd_do(dev, in, in_size, out, out_size);
 
 	return mlx5_cmd_check(dev, err, in, out);
 }
 EXPORT_SYMBOL(mlx5_cmd_exec);
 
+/**
+ * mlx5_cmd_exec_polling - Executes a fw command, poll for completion
+ *	Needed for driver force teardown, when command completion EQ
+ *	will not be available to complete the command
+ *
+ * @dev: mlx5 core device
+ * @in: inbox mlx5_ifc command buffer
+ * @in_size: inbox buffer size
+ * @out: outbox mlx5_ifc buffer
+ * @out_size: outbox size
+ *
+ * @return: 0 if no error, FW command execution was successful
+ *          and outbox status is ok.
+ */
+int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size,
+			  void *out, int out_size)
+{
+	int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, true);
+
+	if (err) /* -EREMOTEIO is preserved */
+		return err == -EREMOTEIO ? -EIO : err;
+
+	if (MLX5_GET(mbox_out, out, status) != MLX5_CMD_STAT_OK)
+		err = -EREMOTEIO;
+
+	return mlx5_cmd_check(dev, err, in, out);
+}
+EXPORT_SYMBOL(mlx5_cmd_exec_polling);
+
 void mlx5_cmd_init_async_ctx(struct mlx5_core_dev *dev,
 			     struct mlx5_async_ctx *ctx)
 {
@@ -1944,15 +2006,6 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
 }
 EXPORT_SYMBOL(mlx5_cmd_exec_cb);
 
-int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size,
-			  void *out, int out_size)
-{
-	int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, true);
-
-	return mlx5_cmd_check(dev, err, in, out);
-}
-EXPORT_SYMBOL(mlx5_cmd_exec_polling);
-
 static void destroy_msg_cache(struct mlx5_core_dev *dev)
 {
 	struct cmd_msg_cache *ch;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 8a8408708e6c..1b9bec8fa870 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -964,6 +964,8 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
 		     void *out, int out_size, mlx5_async_cbk_t callback,
 		     struct mlx5_async_work *work);
 
+int mlx5_cmd_do(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size);
+int mlx5_cmd_check(struct mlx5_core_dev *dev, int err, void *in, void *out);
 int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 		  int out_size);
 
-- 
cgit v1.2.3


From 0a41527608e7f3da61e76564f5a8749a1fddc7f1 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 31 Mar 2020 22:03:00 -0700
Subject: net/mlx5: cmdif, Refactor error handling and reporting of async
 commands

Same as the new mlx5_cmd_do API, report all information to callers and
let them handle the error values and outbox parsing.

The user callback status "work->user_callback(status)" is now similar to
the error rc code returned from the blocking mlx5_cmd_do() version,
and now is defined as follows:

 -EREMOTEIO : Command executed by FW, outbox.status != MLX5_CMD_STAT_OK.
              Caller must check FW outbox status.
 0 : Command execution successful,  outbox.status == MLX5_CMD_STAT_OK.
 < 0 : Command couldn't execute, FW or driver induced error.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/infiniband/hw/mlx5/mr.c               | 15 ++++++-
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 61 ++++++++++++++++-----------
 include/linux/mlx5/driver.h                   |  3 +-
 3 files changed, 52 insertions(+), 27 deletions(-)

(limited to 'include/linux/mlx5/driver.h')

diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 157d862fb864..06e4b8cea6bd 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -140,6 +140,19 @@ static int destroy_mkey(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
 	return mlx5_core_destroy_mkey(dev->mdev, mr->mmkey.key);
 }
 
+static void create_mkey_warn(struct mlx5_ib_dev *dev, int status, void *out)
+{
+	if (status == -ENXIO) /* core driver is not available */
+		return;
+
+	mlx5_ib_warn(dev, "async reg mr failed. status %d\n", status);
+	if (status != -EREMOTEIO) /* driver specific failure */
+		return;
+
+	/* Failed in FW, print cmd out failure details */
+	mlx5_cmd_out_err(dev->mdev, MLX5_CMD_OP_CREATE_MKEY, 0, out);
+}
+
 static void create_mkey_callback(int status, struct mlx5_async_work *context)
 {
 	struct mlx5_ib_mr *mr =
@@ -149,7 +162,7 @@ static void create_mkey_callback(int status, struct mlx5_async_work *context)
 	unsigned long flags;
 
 	if (status) {
-		mlx5_ib_warn(dev, "async reg mr failed. status %d\n", status);
+		create_mkey_warn(dev, status, mr->out);
 		kfree(mr);
 		spin_lock_irqsave(&ent->lock, flags);
 		ent->pending--;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index a2f87a686a18..823d5808d5a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -760,6 +760,18 @@ struct mlx5_ifc_mbox_in_bits {
 	u8         reserved_at_40[0x40];
 };
 
+void mlx5_cmd_out_err(struct mlx5_core_dev *dev, u16 opcode, u16 op_mod, void *out)
+{
+	u32 syndrome = MLX5_GET(mbox_out, out, syndrome);
+	u8 status = MLX5_GET(mbox_out, out, status);
+
+	mlx5_core_err_rl(dev,
+			 "%s(0x%x) op_mod(0x%x) failed, status %s(0x%x), syndrome (0x%x), err(%d)\n",
+			 mlx5_command_str(opcode), opcode, op_mod,
+			 cmd_status_str(status), status, syndrome, cmd_status_to_err(status));
+}
+EXPORT_SYMBOL(mlx5_cmd_out_err);
+
 static void cmd_status_print(struct mlx5_core_dev *dev, void *in, void *out)
 {
 	u16 opcode, op_mod;
@@ -778,10 +790,7 @@ static void cmd_status_print(struct mlx5_core_dev *dev, void *in, void *out)
 	err = cmd_status_to_err(status);
 
 	if (!uid && opcode != MLX5_CMD_OP_DESTROY_MKEY)
-		mlx5_core_err_rl(dev,
-			"%s(0x%x) op_mod(0x%x) failed, status %s(0x%x), syndrome (0x%x), err(%d)\n",
-			mlx5_command_str(opcode), opcode, op_mod,
-			cmd_status_str(status), status, syndrome, err);
+		mlx5_cmd_out_err(dev, opcode, op_mod, out);
 	else
 		mlx5_core_dbg(dev,
 			"%s(0x%x) op_mod(0x%x) uid(%d) failed, status %s(0x%x), syndrome (0x%x), err(%d)\n",
@@ -1686,20 +1695,18 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force
 
 				callback = ent->callback;
 				context = ent->context;
-				err = ent->ret;
-				if (!err && !ent->status) {
+				err = ent->ret ? : ent->status;
+				if (err > 0) /* Failed in FW, command didn't execute */
+					err = deliv_status_to_err(err);
+
+				if (!err)
 					err = mlx5_copy_from_msg(ent->uout,
 								 ent->out,
 								 ent->uout_size);
 
-					err = mlx5_cmd_check(dev, err, ent->in->first.data,
-							     ent->uout);
-				}
-
 				mlx5_free_cmd_msg(dev, ent->out);
 				free_msg(dev, ent->in);
 
-				err = err ? err : ent->status;
 				/* final consumer is done, release ent */
 				cmd_ent_put(ent);
 				callback(err, context);
@@ -1870,6 +1877,18 @@ out_in:
 	return err;
 }
 
+/* preserve -EREMOTEIO for outbox.status != OK, otherwise return err as is */
+static int cmd_status_err(int err, void *out)
+{
+	if (err) /* -EREMOTEIO is preserved */
+		return err == -EREMOTEIO ? -EIO : err;
+
+	if (MLX5_GET(mbox_out, out, status) != MLX5_CMD_STAT_OK)
+		return -EREMOTEIO;
+
+	return 0;
+}
+
 /**
  * mlx5_cmd_do - Executes a fw command, wait for completion.
  * Unlike mlx5_cmd_exec, this function will not translate or intercept
@@ -1892,13 +1911,7 @@ int mlx5_cmd_do(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int
 {
 	int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, false);
 
-	if (err) /* -EREMOTEIO is preserved */
-		return err == -EREMOTEIO ? -EIO : err;
-
-	if (MLX5_GET(mbox_out, out, status) != MLX5_CMD_STAT_OK)
-		return -EREMOTEIO;
-
-	return 0;
+	return cmd_status_err(err, out);
 }
 EXPORT_SYMBOL(mlx5_cmd_do);
 
@@ -1942,12 +1955,7 @@ int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size,
 {
 	int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, true);
 
-	if (err) /* -EREMOTEIO is preserved */
-		return err == -EREMOTEIO ? -EIO : err;
-
-	if (MLX5_GET(mbox_out, out, status) != MLX5_CMD_STAT_OK)
-		err = -EREMOTEIO;
-
+	err = cmd_status_err(err, out);
 	return mlx5_cmd_check(dev, err, in, out);
 }
 EXPORT_SYMBOL(mlx5_cmd_exec_polling);
@@ -1980,8 +1988,10 @@ EXPORT_SYMBOL(mlx5_cmd_cleanup_async_ctx);
 static void mlx5_cmd_exec_cb_handler(int status, void *_work)
 {
 	struct mlx5_async_work *work = _work;
-	struct mlx5_async_ctx *ctx = work->ctx;
+	struct mlx5_async_ctx *ctx;
 
+	ctx = work->ctx;
+	status = cmd_status_err(status, work->out);
 	work->user_callback(status, work);
 	if (atomic_dec_and_test(&ctx->num_inflight))
 		wake_up(&ctx->wait);
@@ -1995,6 +2005,7 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
 
 	work->ctx = ctx;
 	work->user_callback = callback;
+	work->out = out;
 	if (WARN_ON(!atomic_inc_not_zero(&ctx->num_inflight)))
 		return -EIO;
 	ret = cmd_exec(ctx->dev, in, in_size, out, out_size,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 1b9bec8fa870..432151d7d0bf 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -955,6 +955,7 @@ typedef void (*mlx5_async_cbk_t)(int status, struct mlx5_async_work *context);
 struct mlx5_async_work {
 	struct mlx5_async_ctx *ctx;
 	mlx5_async_cbk_t user_callback;
+	void *out; /* pointer to the cmd output buffer */
 };
 
 void mlx5_cmd_init_async_ctx(struct mlx5_core_dev *dev,
@@ -963,7 +964,7 @@ void mlx5_cmd_cleanup_async_ctx(struct mlx5_async_ctx *ctx);
 int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
 		     void *out, int out_size, mlx5_async_cbk_t callback,
 		     struct mlx5_async_work *work);
-
+void mlx5_cmd_out_err(struct mlx5_core_dev *dev, u16 opcode, u16 op_mod, void *out);
 int mlx5_cmd_do(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size);
 int mlx5_cmd_check(struct mlx5_core_dev *dev, int err, void *in, void *out);
 int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
-- 
cgit v1.2.3


From 45fee8edb4b333af79efad7a99de51718ebda94b Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Mon, 6 Sep 2021 11:02:44 +0300
Subject: net/mlx5: Add clarification on sync reset failure

In case devlink reload action fw_activate failed in sync reset stage,
use the new MFRL field reset_state to find why it failed and share this
clarification with the user.

Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c  | 10 ++--
 drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c | 57 +++++++++++++++++++---
 drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h |  3 +-
 drivers/net/ethernet/mellanox/mlx5/core/port.c     | 20 ++++++--
 include/linux/mlx5/driver.h                        |  3 ++
 5 files changed, 74 insertions(+), 19 deletions(-)

(limited to 'include/linux/mlx5/driver.h')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index d1093bb2d436..057dde6f4417 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -100,15 +100,11 @@ static int mlx5_devlink_reload_fw_activate(struct devlink *devlink, struct netli
 	}
 
 	net_port_alive = !!(reset_type & MLX5_MFRL_REG_RESET_TYPE_NET_PORT_ALIVE);
-	err = mlx5_fw_reset_set_reset_sync(dev, net_port_alive);
+	err = mlx5_fw_reset_set_reset_sync(dev, net_port_alive, extack);
 	if (err)
-		goto out;
+		return err;
 
-	err = mlx5_fw_reset_wait_reset_done(dev);
-out:
-	if (err)
-		NL_SET_ERR_MSG_MOD(extack, "FW activate command failed");
-	return err;
+	return mlx5_fw_reset_wait_reset_done(dev);
 }
 
 static int mlx5_devlink_trigger_fw_live_patch(struct devlink *devlink,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index 0b0234f9d694..d438d7a61500 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -57,7 +57,8 @@ static int mlx5_reg_mfrl_set(struct mlx5_core_dev *dev, u8 reset_level,
 	return mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), MLX5_REG_MFRL, 0, 1);
 }
 
-static int mlx5_reg_mfrl_query(struct mlx5_core_dev *dev, u8 *reset_level, u8 *reset_type)
+static int mlx5_reg_mfrl_query(struct mlx5_core_dev *dev, u8 *reset_level,
+			       u8 *reset_type, u8 *reset_state)
 {
 	u32 out[MLX5_ST_SZ_DW(mfrl_reg)] = {};
 	u32 in[MLX5_ST_SZ_DW(mfrl_reg)] = {};
@@ -71,25 +72,67 @@ static int mlx5_reg_mfrl_query(struct mlx5_core_dev *dev, u8 *reset_level, u8 *r
 		*reset_level = MLX5_GET(mfrl_reg, out, reset_level);
 	if (reset_type)
 		*reset_type = MLX5_GET(mfrl_reg, out, reset_type);
+	if (reset_state)
+		*reset_state = MLX5_GET(mfrl_reg, out, reset_state);
 
 	return 0;
 }
 
 int mlx5_fw_reset_query(struct mlx5_core_dev *dev, u8 *reset_level, u8 *reset_type)
 {
-	return mlx5_reg_mfrl_query(dev, reset_level, reset_type);
+	return mlx5_reg_mfrl_query(dev, reset_level, reset_type, NULL);
 }
 
-int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel)
+static int mlx5_fw_reset_get_reset_state_err(struct mlx5_core_dev *dev,
+					     struct netlink_ext_ack *extack)
+{
+	u8 reset_state;
+
+	if (mlx5_reg_mfrl_query(dev, NULL, NULL, &reset_state))
+		goto out;
+
+	switch (reset_state) {
+	case MLX5_MFRL_REG_RESET_STATE_IN_NEGOTIATION:
+	case MLX5_MFRL_REG_RESET_STATE_RESET_IN_PROGRESS:
+		NL_SET_ERR_MSG_MOD(extack, "Sync reset was already triggered");
+		return -EBUSY;
+	case MLX5_MFRL_REG_RESET_STATE_TIMEOUT:
+		NL_SET_ERR_MSG_MOD(extack, "Sync reset got timeout");
+		return -ETIMEDOUT;
+	case MLX5_MFRL_REG_RESET_STATE_NACK:
+		NL_SET_ERR_MSG_MOD(extack, "One of the hosts disabled reset");
+		return -EPERM;
+	}
+
+out:
+	NL_SET_ERR_MSG_MOD(extack, "Sync reset failed");
+	return -EIO;
+}
+
+int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel,
+				 struct netlink_ext_ack *extack)
 {
 	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+	u32 out[MLX5_ST_SZ_DW(mfrl_reg)] = {};
+	u32 in[MLX5_ST_SZ_DW(mfrl_reg)] = {};
 	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;
+
+	MLX5_SET(mfrl_reg, in, reset_level, MLX5_MFRL_REG_RESET_LEVEL3);
+	MLX5_SET(mfrl_reg, in, rst_type_sel, reset_type_sel);
+	MLX5_SET(mfrl_reg, in, pci_sync_for_fw_update_start, 1);
+	err = mlx5_access_reg(dev, in, sizeof(in), out, sizeof(out),
+			      MLX5_REG_MFRL, 0, 1, false);
+	if (!err)
+		return 0;
+
+	clear_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags);
+	if (err == -EREMOTEIO && MLX5_CAP_MCAM_FEATURE(dev, reset_state))
+		return mlx5_fw_reset_get_reset_state_err(dev, extack);
+
+	NL_SET_ERR_MSG_MOD(extack, "Sync reset command failed");
+	return mlx5_cmd_check(dev, err, in, out);
 }
 
 int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
index 7761ee5fc7d0..694fc7cb2684 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
@@ -9,7 +9,8 @@
 void mlx5_fw_reset_enable_remote_dev_reset_set(struct mlx5_core_dev *dev, bool enable);
 bool mlx5_fw_reset_enable_remote_dev_reset_get(struct mlx5_core_dev *dev);
 int mlx5_fw_reset_query(struct mlx5_core_dev *dev, u8 *reset_level, u8 *reset_type);
-int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel);
+int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel,
+				 struct netlink_ext_ack *extack);
 int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev);
 
 int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 1ef2b6a848c1..d15b417d3e07 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -33,9 +33,10 @@
 #include <linux/mlx5/port.h>
 #include "mlx5_core.h"
 
-int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in,
-			 int size_in, void *data_out, int size_out,
-			 u16 reg_id, int arg, int write)
+/* calling with verbose false will not print error to log */
+int mlx5_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in,
+		    void *data_out, int size_out, u16 reg_id, int arg,
+		    int write, bool verbose)
 {
 	int outlen = MLX5_ST_SZ_BYTES(access_register_out) + size_out;
 	int inlen = MLX5_ST_SZ_BYTES(access_register_in) + size_in;
@@ -57,7 +58,9 @@ int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in,
 	MLX5_SET(access_register_in, in, argument, arg);
 	MLX5_SET(access_register_in, in, register_id, reg_id);
 
-	err = mlx5_cmd_exec(dev, in, inlen, out, outlen);
+	err = mlx5_cmd_do(dev, in, inlen, out, outlen);
+	if (verbose)
+		err = mlx5_cmd_check(dev, err, in, out);
 	if (err)
 		goto out;
 
@@ -69,6 +72,15 @@ out:
 	kvfree(in);
 	return err;
 }
+EXPORT_SYMBOL_GPL(mlx5_access_reg);
+
+int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in,
+			 int size_in, void *data_out, int size_out,
+			 u16 reg_id, int arg, int write)
+{
+	return mlx5_access_reg(dev, data_in, size_in, data_out, size_out,
+			       reg_id, arg, write, true);
+}
 EXPORT_SYMBOL_GPL(mlx5_core_access_reg);
 
 int mlx5_query_pcam_reg(struct mlx5_core_dev *dev, u32 *pcam, u8 feature_group,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 432151d7d0bf..d3b1a6a1f8d2 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1031,6 +1031,9 @@ int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn)
 
 void mlx5_qp_debugfs_init(struct mlx5_core_dev *dev);
 void mlx5_qp_debugfs_cleanup(struct mlx5_core_dev *dev);
+int mlx5_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in,
+		    void *data_out, int size_out, u16 reg_id, int arg,
+		    int write, bool verbose);
 int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in,
 			 int size_in, void *data_out, int size_out,
 			 u16 reg_num, int arg, int write);
-- 
cgit v1.2.3


From 1695b97b291e79295bf5c26cba5ecc4b443d8ac7 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Thu, 24 Feb 2022 16:20:14 +0200
Subject: net/mlx5: Expose APIs to get/put the mlx5 core device

Expose an API to get the mlx5 core device from a given VF PCI device if
mlx5_core is its driver.

Upon the get API we stay with the intf_state_mutex locked to make sure
that the device can't be gone/unloaded till the caller will complete
its job over the device, this expects to be for a short period of time
for any flow that the lock is taken.

Upon the put API we unlock the intf_state_mutex.

The use case for those APIs is the migration flow of a VF over VFIO PCI.
In that case the VF doesn't ride on mlx5_core, because the device is
driving *two* different PCI devices, the PF owned by mlx5_core and the
VF owned by the vfio driver.

The mlx5_core of the PF is accessed only during the narrow window of the
VF's ioctl that requires its services.

This allows the PF driver to be more independent of the VF driver, so
long as it doesn't reset the FW.

Link: https://lore.kernel.org/all/20220224142024.147653-6-yishaih@nvidia.com
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 44 ++++++++++++++++++++++++++
 include/linux/mlx5/driver.h                    |  3 ++
 2 files changed, 47 insertions(+)

(limited to 'include/linux/mlx5/driver.h')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 5b8958186157..e9aeba4267ff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1881,6 +1881,50 @@ static struct pci_driver mlx5_core_driver = {
 	.sriov_set_msix_vec_count = mlx5_core_sriov_set_msix_vec_count,
 };
 
+/**
+ * mlx5_vf_get_core_dev - Get the mlx5 core device from a given VF PCI device if
+ *                     mlx5_core is its driver.
+ * @pdev: The associated PCI device.
+ *
+ * Upon return the interface state lock stay held to let caller uses it safely.
+ * Caller must ensure to use the returned mlx5 device for a narrow window
+ * and put it back with mlx5_vf_put_core_dev() immediately once usage was over.
+ *
+ * Return: Pointer to the associated mlx5_core_dev or NULL.
+ */
+struct mlx5_core_dev *mlx5_vf_get_core_dev(struct pci_dev *pdev)
+			__acquires(&mdev->intf_state_mutex)
+{
+	struct mlx5_core_dev *mdev;
+
+	mdev = pci_iov_get_pf_drvdata(pdev, &mlx5_core_driver);
+	if (IS_ERR(mdev))
+		return NULL;
+
+	mutex_lock(&mdev->intf_state_mutex);
+	if (!test_bit(MLX5_INTERFACE_STATE_UP, &mdev->intf_state)) {
+		mutex_unlock(&mdev->intf_state_mutex);
+		return NULL;
+	}
+
+	return mdev;
+}
+EXPORT_SYMBOL(mlx5_vf_get_core_dev);
+
+/**
+ * mlx5_vf_put_core_dev - Put the mlx5 core device back.
+ * @mdev: The mlx5 core device.
+ *
+ * Upon return the interface state lock is unlocked and caller should not
+ * access the mdev any more.
+ */
+void mlx5_vf_put_core_dev(struct mlx5_core_dev *mdev)
+			__releases(&mdev->intf_state_mutex)
+{
+	mutex_unlock(&mdev->intf_state_mutex);
+}
+EXPORT_SYMBOL(mlx5_vf_put_core_dev);
+
 static void mlx5_core_verify_params(void)
 {
 	if (prof_sel >= ARRAY_SIZE(profile)) {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 78655d8d13a7..319322a8ff94 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1143,6 +1143,9 @@ int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type,
 int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type,
 			   u64 length, u16 uid, phys_addr_t addr, u32 obj_id);
 
+struct mlx5_core_dev *mlx5_vf_get_core_dev(struct pci_dev *pdev);
+void mlx5_vf_put_core_dev(struct mlx5_core_dev *mdev);
+
 #ifdef CONFIG_MLX5_CORE_IPOIB
 struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,
 					  struct ib_device *ibdev,
-- 
cgit v1.2.3


From 34f46ae0d4b38e83cfb26fb6f06b5b5efea47fdc Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Thu, 27 Jan 2022 15:22:21 +0200
Subject: net/mlx5: Add command failures data to debugfs

Add new counters to command interface debugfs to count command failures.
The following counters added:
total_failed - number of times command failed (any kind of failure).
failed_mbox_status - number of times command failed on bad status
returned by FW.

In addition, add data about last command failure to command interface
debugfs:
last_failed_errno - last command failed returned errno.
last_failed_mbox_status - last bad status returned by FW.

Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c     | 44 ++++++++++++++++++-----
 drivers/net/ethernet/mellanox/mlx5/core/debugfs.c |  7 ++++
 include/linux/mlx5/driver.h                       |  9 +++++
 3 files changed, 51 insertions(+), 9 deletions(-)

(limited to 'include/linux/mlx5/driver.h')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 823d5808d5a0..8933c00067e8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1877,16 +1877,38 @@ out_in:
 	return err;
 }
 
+static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, int err)
+{
+	struct mlx5_cmd_stats *stats;
+
+	if (!err)
+		return;
+
+	stats = &dev->cmd.stats[opcode];
+	spin_lock_irq(&stats->lock);
+	stats->failed++;
+	if (err < 0)
+		stats->last_failed_errno = -err;
+	if (err == -EREMOTEIO) {
+		stats->failed_mbox_status++;
+		stats->last_failed_mbox_status = status;
+	}
+	spin_unlock_irq(&stats->lock);
+}
+
 /* preserve -EREMOTEIO for outbox.status != OK, otherwise return err as is */
-static int cmd_status_err(int err, void *out)
+static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, void *out)
 {
-	if (err) /* -EREMOTEIO is preserved */
-		return err == -EREMOTEIO ? -EIO : err;
+	u8 status = MLX5_GET(mbox_out, out, status);
 
-	if (MLX5_GET(mbox_out, out, status) != MLX5_CMD_STAT_OK)
-		return -EREMOTEIO;
+	if (err == -EREMOTEIO) /* -EREMOTEIO is preserved */
+		err = -EIO;
 
-	return 0;
+	if (!err && status != MLX5_CMD_STAT_OK)
+		err = -EREMOTEIO;
+
+	cmd_status_log(dev, opcode, status, err);
+	return err;
 }
 
 /**
@@ -1910,8 +1932,10 @@ static int cmd_status_err(int err, void *out)
 int mlx5_cmd_do(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size)
 {
 	int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, false);
+	u16 opcode = MLX5_GET(mbox_in, in, opcode);
 
-	return cmd_status_err(err, out);
+	err = cmd_status_err(dev, err, opcode, out);
+	return err;
 }
 EXPORT_SYMBOL(mlx5_cmd_do);
 
@@ -1954,8 +1978,9 @@ int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size,
 			  void *out, int out_size)
 {
 	int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, true);
+	u16 opcode = MLX5_GET(mbox_in, in, opcode);
 
-	err = cmd_status_err(err, out);
+	err = cmd_status_err(dev, err, opcode, out);
 	return mlx5_cmd_check(dev, err, in, out);
 }
 EXPORT_SYMBOL(mlx5_cmd_exec_polling);
@@ -1991,7 +2016,7 @@ static void mlx5_cmd_exec_cb_handler(int status, void *_work)
 	struct mlx5_async_ctx *ctx;
 
 	ctx = work->ctx;
-	status = cmd_status_err(status, work->out);
+	status = cmd_status_err(ctx->dev, status, work->opcode, work->out);
 	work->user_callback(status, work);
 	if (atomic_dec_and_test(&ctx->num_inflight))
 		wake_up(&ctx->wait);
@@ -2005,6 +2030,7 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
 
 	work->ctx = ctx;
 	work->user_callback = callback;
+	work->opcode = MLX5_GET(mbox_in, in, opcode);
 	work->out = out;
 	if (WARN_ON(!atomic_inc_not_zero(&ctx->num_inflight)))
 		return -EIO;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index 10d195042ab5..18b04e977bb8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -180,6 +180,13 @@ void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev)
 			debugfs_create_file("average", 0400, stats->root, stats,
 					    &stats_fops);
 			debugfs_create_u64("n", 0400, stats->root, &stats->n);
+			debugfs_create_u64("failed", 0400, stats->root, &stats->failed);
+			debugfs_create_u64("failed_mbox_status", 0400, stats->root,
+					   &stats->failed_mbox_status);
+			debugfs_create_u32("last_failed_errno", 0400, stats->root,
+					   &stats->last_failed_errno);
+			debugfs_create_u8("last_failed_mbox_status", 0400, stats->root,
+					  &stats->last_failed_mbox_status);
 		}
 	}
 }
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index d3b1a6a1f8d2..f18c1e15a12c 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -264,6 +264,14 @@ enum {
 struct mlx5_cmd_stats {
 	u64		sum;
 	u64		n;
+	/* number of times command failed */
+	u64		failed;
+	/* number of times command failed on bad status returned by FW */
+	u64		failed_mbox_status;
+	/* last command failed returned errno */
+	u32		last_failed_errno;
+	/* last bad status returned by FW */
+	u8		last_failed_mbox_status;
 	struct dentry  *root;
 	/* protect command average calculations */
 	spinlock_t	lock;
@@ -955,6 +963,7 @@ typedef void (*mlx5_async_cbk_t)(int status, struct mlx5_async_work *context);
 struct mlx5_async_work {
 	struct mlx5_async_ctx *ctx;
 	mlx5_async_cbk_t user_callback;
+	u16 opcode; /* cmd opcode */
 	void *out; /* pointer to the cmd output buffer */
 };
 
-- 
cgit v1.2.3


From 66771a1c729e816dc84e29ba555013b6e722fb22 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Fri, 18 Feb 2022 09:36:20 +0200
Subject: net/mlx5: Move debugfs entries to separate struct

Move the debugfs entry pointers under priv to their own struct.
Add get function for device debugfs root.

Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/infiniband/hw/mlx5/cong.c                  |  3 +--
 drivers/infiniband/hw/mlx5/main.c                  |  2 +-
 drivers/infiniband/hw/mlx5/mr.c                    |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c      |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/debugfs.c  | 30 +++++++++++++---------
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |  8 +++---
 .../ethernet/mellanox/mlx5/core/steering/dr_dbg.c  |  2 +-
 include/linux/mlx5/driver.h                        | 17 +++++++-----
 8 files changed, 37 insertions(+), 29 deletions(-)

(limited to 'include/linux/mlx5/driver.h')

diff --git a/drivers/infiniband/hw/mlx5/cong.c b/drivers/infiniband/hw/mlx5/cong.c
index 0b61df52332a..290ea8ac3838 100644
--- a/drivers/infiniband/hw/mlx5/cong.c
+++ b/drivers/infiniband/hw/mlx5/cong.c
@@ -433,8 +433,7 @@ void mlx5_ib_init_cong_debugfs(struct mlx5_ib_dev *dev, u32 port_num)
 
 	dev->port[port_num].dbg_cc_params = dbg_cc_params;
 
-	dbg_cc_params->root = debugfs_create_dir("cc_params",
-						 mdev->priv.dbg_root);
+	dbg_cc_params->root = debugfs_create_dir("cc_params", mlx5_debugfs_get_dev_root(mdev));
 
 	for (i = 0; i < MLX5_IB_DBG_CC_MAX; i++) {
 		dbg_cc_params->params[i].offset = i;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 85f526c861e9..32a0ea820573 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -4178,7 +4178,7 @@ static int mlx5_ib_stage_delay_drop_init(struct mlx5_ib_dev *dev)
 	if (!mlx5_debugfs_root)
 		return 0;
 
-	root = debugfs_create_dir("delay_drop", dev->mdev->priv.dbg_root);
+	root = debugfs_create_dir("delay_drop", mlx5_debugfs_get_dev_root(dev->mdev));
 	dev->delay_drop.dir_debugfs = root;
 
 	debugfs_create_atomic_t("num_timeout_events", 0400, root,
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 06e4b8cea6bd..32cb7068f0ca 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -696,7 +696,7 @@ static void mlx5_mr_cache_debugfs_init(struct mlx5_ib_dev *dev)
 	if (!mlx5_debugfs_root || dev->is_rep)
 		return;
 
-	cache->root = debugfs_create_dir("mr_cache", dev->mdev->priv.dbg_root);
+	cache->root = debugfs_create_dir("mr_cache", mlx5_debugfs_get_dev_root(dev->mdev));
 
 	for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) {
 		ent = &cache->ent[i];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 8933c00067e8..3b61224e9a3a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1543,7 +1543,7 @@ static void create_debugfs_files(struct mlx5_core_dev *dev)
 {
 	struct mlx5_cmd_debug *dbg = &dev->cmd.dbg;
 
-	dbg->dbg_root = debugfs_create_dir("cmd", dev->priv.dbg_root);
+	dbg->dbg_root = debugfs_create_dir("cmd", mlx5_debugfs_get_dev_root(dev));
 
 	debugfs_create_file("in", 0400, dbg->dbg_root, dev, &dfops);
 	debugfs_create_file("out", 0200, dbg->dbg_root, dev, &dfops);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index 18b04e977bb8..883e44457367 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -99,26 +99,32 @@ void mlx5_unregister_debugfs(void)
 	debugfs_remove(mlx5_debugfs_root);
 }
 
+struct dentry *mlx5_debugfs_get_dev_root(struct mlx5_core_dev *dev)
+{
+	return dev->priv.dbg.dbg_root;
+}
+EXPORT_SYMBOL(mlx5_debugfs_get_dev_root);
+
 void mlx5_qp_debugfs_init(struct mlx5_core_dev *dev)
 {
-	dev->priv.qp_debugfs = debugfs_create_dir("QPs",  dev->priv.dbg_root);
+	dev->priv.dbg.qp_debugfs = debugfs_create_dir("QPs", dev->priv.dbg.dbg_root);
 }
 EXPORT_SYMBOL(mlx5_qp_debugfs_init);
 
 void mlx5_qp_debugfs_cleanup(struct mlx5_core_dev *dev)
 {
-	debugfs_remove_recursive(dev->priv.qp_debugfs);
+	debugfs_remove_recursive(dev->priv.dbg.qp_debugfs);
 }
 EXPORT_SYMBOL(mlx5_qp_debugfs_cleanup);
 
 void mlx5_eq_debugfs_init(struct mlx5_core_dev *dev)
 {
-	dev->priv.eq_debugfs = debugfs_create_dir("EQs",  dev->priv.dbg_root);
+	dev->priv.dbg.eq_debugfs = debugfs_create_dir("EQs", dev->priv.dbg.dbg_root);
 }
 
 void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev)
 {
-	debugfs_remove_recursive(dev->priv.eq_debugfs);
+	debugfs_remove_recursive(dev->priv.dbg.eq_debugfs);
 }
 
 static ssize_t average_read(struct file *filp, char __user *buf, size_t count,
@@ -168,8 +174,8 @@ void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev)
 	const char *namep;
 	int i;
 
-	cmd = &dev->priv.cmdif_debugfs;
-	*cmd = debugfs_create_dir("commands", dev->priv.dbg_root);
+	cmd = &dev->priv.dbg.cmdif_debugfs;
+	*cmd = debugfs_create_dir("commands", dev->priv.dbg.dbg_root);
 
 	for (i = 0; i < MLX5_CMD_OP_MAX; i++) {
 		stats = &dev->cmd.stats[i];
@@ -193,17 +199,17 @@ void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev)
 
 void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev)
 {
-	debugfs_remove_recursive(dev->priv.cmdif_debugfs);
+	debugfs_remove_recursive(dev->priv.dbg.cmdif_debugfs);
 }
 
 void mlx5_cq_debugfs_init(struct mlx5_core_dev *dev)
 {
-	dev->priv.cq_debugfs = debugfs_create_dir("CQs",  dev->priv.dbg_root);
+	dev->priv.dbg.cq_debugfs = debugfs_create_dir("CQs", dev->priv.dbg.dbg_root);
 }
 
 void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev)
 {
-	debugfs_remove_recursive(dev->priv.cq_debugfs);
+	debugfs_remove_recursive(dev->priv.dbg.cq_debugfs);
 }
 
 static u64 qp_read_field(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp,
@@ -448,7 +454,7 @@ int mlx5_debug_qp_add(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp)
 	if (!mlx5_debugfs_root)
 		return 0;
 
-	err = add_res_tree(dev, MLX5_DBG_RSC_QP, dev->priv.qp_debugfs,
+	err = add_res_tree(dev, MLX5_DBG_RSC_QP, dev->priv.dbg.qp_debugfs,
 			   &qp->dbg, qp->qpn, qp_fields,
 			   ARRAY_SIZE(qp_fields), qp);
 	if (err)
@@ -475,7 +481,7 @@ int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 	if (!mlx5_debugfs_root)
 		return 0;
 
-	err = add_res_tree(dev, MLX5_DBG_RSC_EQ, dev->priv.eq_debugfs,
+	err = add_res_tree(dev, MLX5_DBG_RSC_EQ, dev->priv.dbg.eq_debugfs,
 			   &eq->dbg, eq->eqn, eq_fields,
 			   ARRAY_SIZE(eq_fields), eq);
 	if (err)
@@ -500,7 +506,7 @@ int mlx5_debug_cq_add(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq)
 	if (!mlx5_debugfs_root)
 		return 0;
 
-	err = add_res_tree(dev, MLX5_DBG_RSC_CQ, dev->priv.cq_debugfs,
+	err = add_res_tree(dev, MLX5_DBG_RSC_CQ, dev->priv.dbg.cq_debugfs,
 			   &cq->dbg, cq->cqn, cq_fields,
 			   ARRAY_SIZE(cq_fields), cq);
 	if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 98be7050aa8d..d8d36477b97f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1487,8 +1487,8 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 	INIT_LIST_HEAD(&priv->pgdir_list);
 
 	priv->numa_node = dev_to_node(mlx5_core_dma_dev(dev));
-	priv->dbg_root = debugfs_create_dir(dev_name(dev->device),
-					    mlx5_debugfs_root);
+	priv->dbg.dbg_root = debugfs_create_dir(dev_name(dev->device),
+						mlx5_debugfs_root);
 	INIT_LIST_HEAD(&priv->traps);
 
 	err = mlx5_tout_init(dev);
@@ -1524,7 +1524,7 @@ err_pagealloc_init:
 err_health_init:
 	mlx5_tout_cleanup(dev);
 err_timeout_init:
-	debugfs_remove(dev->priv.dbg_root);
+	debugfs_remove(dev->priv.dbg.dbg_root);
 	mutex_destroy(&priv->pgdir_mutex);
 	mutex_destroy(&priv->alloc_mutex);
 	mutex_destroy(&priv->bfregs.wc_head.lock);
@@ -1542,7 +1542,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
 	mlx5_pagealloc_cleanup(dev);
 	mlx5_health_cleanup(dev);
 	mlx5_tout_cleanup(dev);
-	debugfs_remove_recursive(dev->priv.dbg_root);
+	debugfs_remove_recursive(dev->priv.dbg.dbg_root);
 	mutex_destroy(&priv->pgdir_mutex);
 	mutex_destroy(&priv->alloc_mutex);
 	mutex_destroy(&priv->bfregs.wc_head.lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c
index 2784cd59fefe..2e8b109fb34e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c
@@ -630,7 +630,7 @@ void mlx5dr_dbg_init_dump(struct mlx5dr_domain *dmn)
 	}
 
 	dmn->dump_info.steering_debugfs =
-		debugfs_create_dir("steering", dev->priv.dbg_root);
+		debugfs_create_dir("steering", mlx5_debugfs_get_dev_root(dev));
 	dmn->dump_info.fdb_debugfs =
 		debugfs_create_dir("fdb", dmn->dump_info.steering_debugfs);
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index f18c1e15a12c..aa539d245a12 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -551,6 +551,14 @@ struct mlx5_adev {
 	int idx;
 };
 
+struct mlx5_debugfs_entries {
+	struct dentry *dbg_root;
+	struct dentry *qp_debugfs;
+	struct dentry *eq_debugfs;
+	struct dentry *cq_debugfs;
+	struct dentry *cmdif_debugfs;
+};
+
 struct mlx5_ft_pool;
 struct mlx5_priv {
 	/* IRQ table valid only for real pci devices PF or VF */
@@ -570,12 +578,7 @@ struct mlx5_priv {
 	struct mlx5_core_health health;
 	struct list_head	traps;
 
-	/* start: qp staff */
-	struct dentry	       *qp_debugfs;
-	struct dentry	       *eq_debugfs;
-	struct dentry	       *cq_debugfs;
-	struct dentry	       *cmdif_debugfs;
-	/* end: qp staff */
+	struct mlx5_debugfs_entries dbg;
 
 	/* start: alloc staff */
 	/* protect buffer allocation according to numa node */
@@ -585,7 +588,6 @@ struct mlx5_priv {
 	struct mutex            pgdir_mutex;
 	struct list_head        pgdir_list;
 	/* end: alloc staff */
-	struct dentry	       *dbg_root;
 
 	struct list_head        ctx_list;
 	spinlock_t              ctx_lock;
@@ -1038,6 +1040,7 @@ int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn);
 int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn);
 int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn);
 
+struct dentry *mlx5_debugfs_get_dev_root(struct mlx5_core_dev *dev);
 void mlx5_qp_debugfs_init(struct mlx5_core_dev *dev);
 void mlx5_qp_debugfs_cleanup(struct mlx5_core_dev *dev);
 int mlx5_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in,
-- 
cgit v1.2.3


From 4e05cbf05c66ca6931ee4f2a5aff0d84f1e65f40 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Thu, 27 Jan 2022 07:03:33 +0200
Subject: net/mlx5: Add pages debugfs

Add pages debugfs to expose the following counters for debuggability:
fw_pages_total - How many pages were given to FW and not returned yet.
vfs_pages - For SRIOV, how many pages were given to FW for virtual
functions usage.
host_pf_pages - For ECPF, how many pages were given to FW for external
hosts physical functions usage.

Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/debugfs.c   | 17 +++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c |  2 ++
 include/linux/mlx5/driver.h                         |  9 ++++++---
 3 files changed, 25 insertions(+), 3 deletions(-)

(limited to 'include/linux/mlx5/driver.h')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index 883e44457367..8673ba2df910 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -212,6 +212,23 @@ void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev)
 	debugfs_remove_recursive(dev->priv.dbg.cq_debugfs);
 }
 
+void mlx5_pages_debugfs_init(struct mlx5_core_dev *dev)
+{
+	struct dentry *pages;
+
+	dev->priv.dbg.pages_debugfs = debugfs_create_dir("pages", dev->priv.dbg.dbg_root);
+	pages = dev->priv.dbg.pages_debugfs;
+
+	debugfs_create_u32("fw_pages_total", 0400, pages, &dev->priv.fw_pages);
+	debugfs_create_u32("fw_pages_vfs", 0400, pages, &dev->priv.vfs_pages);
+	debugfs_create_u32("fw_pages_host_pf", 0400, pages, &dev->priv.host_pf_pages);
+}
+
+void mlx5_pages_debugfs_cleanup(struct mlx5_core_dev *dev)
+{
+	debugfs_remove_recursive(dev->priv.dbg.pages_debugfs);
+}
+
 static u64 qp_read_field(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp,
 			 int index, int *is_str)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index d29a305858ad..8855fe71d480 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -714,12 +714,14 @@ int mlx5_pagealloc_init(struct mlx5_core_dev *dev)
 		return -ENOMEM;
 
 	xa_init(&dev->priv.page_root_xa);
+	mlx5_pages_debugfs_init(dev);
 
 	return 0;
 }
 
 void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev)
 {
+	mlx5_pages_debugfs_cleanup(dev);
 	xa_destroy(&dev->priv.page_root_xa);
 	destroy_workqueue(dev->priv.pg_wq);
 }
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index aa539d245a12..c5f93b5910ed 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -557,6 +557,7 @@ struct mlx5_debugfs_entries {
 	struct dentry *eq_debugfs;
 	struct dentry *cq_debugfs;
 	struct dentry *cmdif_debugfs;
+	struct dentry *pages_debugfs;
 };
 
 struct mlx5_ft_pool;
@@ -569,11 +570,11 @@ struct mlx5_priv {
 	struct mlx5_nb          pg_nb;
 	struct workqueue_struct *pg_wq;
 	struct xarray           page_root_xa;
-	int			fw_pages;
+	u32			fw_pages;
 	atomic_t		reg_pages;
 	struct list_head	free_list;
-	int			vfs_pages;
-	int			host_pf_pages;
+	u32			vfs_pages;
+	u32			host_pf_pages;
 
 	struct mlx5_core_health health;
 	struct list_head	traps;
@@ -1026,6 +1027,8 @@ int mlx5_pagealloc_init(struct mlx5_core_dev *dev);
 void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev);
 void mlx5_pagealloc_start(struct mlx5_core_dev *dev);
 void mlx5_pagealloc_stop(struct mlx5_core_dev *dev);
+void mlx5_pages_debugfs_init(struct mlx5_core_dev *dev);
+void mlx5_pages_debugfs_cleanup(struct mlx5_core_dev *dev);
 void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id,
 				 s32 npages, bool ec_function);
 int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot);
-- 
cgit v1.2.3


From 32071187e9fb18da62f5be569bd2ea0d7a981ee8 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Thu, 27 Jan 2022 07:51:14 +0200
Subject: net/mlx5: Add debugfs counters for page commands failures

Add the following new debugfs counters for debug and verbosity:
fw_pages_alloc_failed - number of pages FW requested but driver failed
to allocate.
give_pages_dropped - number of pages given to FW, but command give pages
failed by FW.
reclaim_pages_discard - number of pages which were about to reclaim back
and FW failed the command.

Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/debugfs.c   |  4 ++++
 drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c | 14 +++++++++++---
 include/linux/mlx5/driver.h                         |  3 +++
 3 files changed, 18 insertions(+), 3 deletions(-)

(limited to 'include/linux/mlx5/driver.h')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index 8673ba2df910..d69bac93a83b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -222,6 +222,10 @@ void mlx5_pages_debugfs_init(struct mlx5_core_dev *dev)
 	debugfs_create_u32("fw_pages_total", 0400, pages, &dev->priv.fw_pages);
 	debugfs_create_u32("fw_pages_vfs", 0400, pages, &dev->priv.vfs_pages);
 	debugfs_create_u32("fw_pages_host_pf", 0400, pages, &dev->priv.host_pf_pages);
+	debugfs_create_u32("fw_pages_alloc_failed", 0400, pages, &dev->priv.fw_pages_alloc_failed);
+	debugfs_create_u32("fw_pages_give_dropped", 0400, pages, &dev->priv.give_pages_dropped);
+	debugfs_create_u32("fw_pages_reclaim_discard", 0400, pages,
+			   &dev->priv.reclaim_pages_discard);
 }
 
 void mlx5_pages_debugfs_cleanup(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index 8855fe71d480..e0543b860144 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -352,8 +352,10 @@ retry:
 		if (err) {
 			if (err == -ENOMEM)
 				err = alloc_system_page(dev, function);
-			if (err)
+			if (err) {
+				dev->priv.fw_pages_alloc_failed += (npages - i);
 				goto out_4k;
+			}
 
 			goto retry;
 		}
@@ -372,14 +374,14 @@ retry:
 		/* if triggered by FW and failed by FW ignore */
 		if (event) {
 			err = 0;
-			goto out_4k;
+			goto out_dropped;
 		}
 	}
 	if (err) {
 		err = mlx5_cmd_check(dev, err, in, out);
 		mlx5_core_warn(dev, "func_id 0x%x, npages %d, err %d\n",
 			       func_id, npages, err);
-		goto out_4k;
+		goto out_dropped;
 	}
 
 	dev->priv.fw_pages += npages;
@@ -394,6 +396,8 @@ retry:
 	kvfree(in);
 	return 0;
 
+out_dropped:
+	dev->priv.give_pages_dropped += npages;
 out_4k:
 	for (i--; i >= 0; i--)
 		free_4k(dev, MLX5_GET64(manage_pages_in, in, pas[i]), function);
@@ -516,6 +520,10 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
 	mlx5_core_dbg(dev, "func 0x%x, npages %d, outlen %d\n",
 		      func_id, npages, outlen);
 	err = reclaim_pages_cmd(dev, in, sizeof(in), out, outlen);
+	if (err) {
+		npages = MLX5_GET(manage_pages_in, in, input_num_entries);
+		dev->priv.reclaim_pages_discard += npages;
+	}
 	/* if triggered by FW event and failed by FW then ignore */
 	if (event && err == -EREMOTEIO)
 		err = 0;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index c5f93b5910ed..00a914b0716e 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -575,6 +575,9 @@ struct mlx5_priv {
 	struct list_head	free_list;
 	u32			vfs_pages;
 	u32			host_pf_pages;
+	u32			fw_pages_alloc_failed;
+	u32			give_pages_dropped;
+	u32			reclaim_pages_discard;
 
 	struct mlx5_core_health health;
 	struct list_head	traps;
-- 
cgit v1.2.3


From 4206fe40b2c01fb5988980cff6ea958b16578026 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Tue, 27 Apr 2021 16:30:32 +0300
Subject: net/mlx5: Remove unused exported contiguous coherent buffer
 allocation API

All WQ types moved to using the fragmented allocation API
for coherent memory. Contiguous API is not used anymore.
Remove it, reduce the number of exported functions.

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/alloc.c | 47 -------------------------
 include/linux/mlx5/driver.h                     |  3 --
 2 files changed, 50 deletions(-)

(limited to 'include/linux/mlx5/driver.h')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
index d5408f6ce5a7..1762c5c36042 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
@@ -71,53 +71,6 @@ static void *mlx5_dma_zalloc_coherent_node(struct mlx5_core_dev *dev,
 	return cpu_handle;
 }
 
-static int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size,
-			       struct mlx5_frag_buf *buf, int node)
-{
-	dma_addr_t t;
-
-	buf->size = size;
-	buf->npages       = 1;
-	buf->page_shift   = (u8)get_order(size) + PAGE_SHIFT;
-
-	buf->frags = kzalloc(sizeof(*buf->frags), GFP_KERNEL);
-	if (!buf->frags)
-		return -ENOMEM;
-
-	buf->frags->buf   = mlx5_dma_zalloc_coherent_node(dev, size,
-							  &t, node);
-	if (!buf->frags->buf)
-		goto err_out;
-
-	buf->frags->map = t;
-
-	while (t & ((1 << buf->page_shift) - 1)) {
-		--buf->page_shift;
-		buf->npages *= 2;
-	}
-
-	return 0;
-err_out:
-	kfree(buf->frags);
-	return -ENOMEM;
-}
-
-int mlx5_buf_alloc(struct mlx5_core_dev *dev,
-		   int size, struct mlx5_frag_buf *buf)
-{
-	return mlx5_buf_alloc_node(dev, size, buf, dev->priv.numa_node);
-}
-EXPORT_SYMBOL(mlx5_buf_alloc);
-
-void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf)
-{
-	dma_free_coherent(mlx5_core_dma_dev(dev), buf->size, buf->frags->buf,
-			  buf->frags->map);
-
-	kfree(buf->frags);
-}
-EXPORT_SYMBOL_GPL(mlx5_buf_free);
-
 int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size,
 			     struct mlx5_frag_buf *buf, int node)
 {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 00a914b0716e..a386aec1eb65 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1009,9 +1009,6 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev);
 void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health);
 void mlx5_drain_health_wq(struct mlx5_core_dev *dev);
 void mlx5_trigger_health_work(struct mlx5_core_dev *dev);
-int mlx5_buf_alloc(struct mlx5_core_dev *dev,
-		   int size, struct mlx5_frag_buf *buf);
-void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf);
 int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size,
 			     struct mlx5_frag_buf *buf, int node);
 void mlx5_frag_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf);
-- 
cgit v1.2.3


From 770c9a3a01af178a90368a78c75eb91707c7233c Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Thu, 20 May 2021 15:34:57 +0300
Subject: net/mlx5: Remove unused fill page array API function

mlx5_fill_page_array API function is not used.
Remove it, reduce the number of exported functions.

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/alloc.c | 13 -------------
 include/linux/mlx5/driver.h                     |  1 -
 2 files changed, 14 deletions(-)

(limited to 'include/linux/mlx5/driver.h')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
index 1762c5c36042..e52b0bac09da 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
@@ -239,19 +239,6 @@ void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db)
 }
 EXPORT_SYMBOL_GPL(mlx5_db_free);
 
-void mlx5_fill_page_array(struct mlx5_frag_buf *buf, __be64 *pas)
-{
-	u64 addr;
-	int i;
-
-	for (i = 0; i < buf->npages; i++) {
-		addr = buf->frags->map + (i << buf->page_shift);
-
-		pas[i] = cpu_to_be64(addr);
-	}
-}
-EXPORT_SYMBOL_GPL(mlx5_fill_page_array);
-
 void mlx5_fill_page_frag_array_perm(struct mlx5_frag_buf *buf, __be64 *pas, u8 perm)
 {
 	int i;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index a386aec1eb65..96cd740d94a3 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1036,7 +1036,6 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev);
 void mlx5_register_debugfs(void);
 void mlx5_unregister_debugfs(void);
 
-void mlx5_fill_page_array(struct mlx5_frag_buf *buf, __be64 *pas);
 void mlx5_fill_page_frag_array_perm(struct mlx5_frag_buf *buf, __be64 *pas, u8 perm);
 void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas);
 int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn);
-- 
cgit v1.2.3


From 54deb0e77561973f4ca4515e18ab972c281eea1d Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Wed, 6 Apr 2022 11:25:48 +0300
Subject: net/mlx5: Remove not-needed IPsec config

In current code, the CONFIG_MLX5_IPSEC and CONFIG_MLX5_EN_IPSEC are
the same. So remove useless indirection.

Link: https://lore.kernel.org/r/fd14492cbc01a0d51a5bfedde02bcd2154123fde.1649232994.git.leonro@nvidia.com
Reviewed-by: Raed Salem <raeds@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Kconfig        | 16 +---------------
 drivers/net/ethernet/mellanox/mlx5/core/Makefile       |  4 ++--
 .../ethernet/mellanox/mlx5/core/accel/ipsec_offload.h  | 18 ++----------------
 include/linux/mlx5/accel.h                             |  4 ++--
 include/linux/mlx5/driver.h                            |  2 +-
 5 files changed, 8 insertions(+), 36 deletions(-)

(limited to 'include/linux/mlx5/driver.h')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index e34e64a9ff4a..176883cf2827 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -142,28 +142,14 @@ config MLX5_CORE_IPOIB
 	help
 	  MLX5 IPoIB offloads & acceleration support.
 
-config MLX5_IPSEC
+config MLX5_EN_IPSEC
 	bool "Mellanox Technologies IPsec Connect-X support"
 	depends on MLX5_CORE_EN
 	depends on XFRM_OFFLOAD
 	depends on INET_ESP_OFFLOAD || INET6_ESP_OFFLOAD
 	select MLX5_ACCEL
-	help
-	Build IPsec support for the Connect-X family of network cards by Mellanox
-	Technologies.
-	Note: If you select this option, the mlx5_core driver will include
-	IPsec support for the Connect-X family.
-
-config MLX5_EN_IPSEC
-	bool "IPSec XFRM cryptography-offload acceleration"
-	depends on MLX5_CORE_EN
-	depends on XFRM_OFFLOAD
-	depends on INET_ESP_OFFLOAD || INET6_ESP_OFFLOAD
-	depends on MLX5_IPSEC
 	help
 	  Build support for IPsec cryptography-offload acceleration in the NIC.
-	  Note: Support for hardware with this capability needs to be selected
-	  for this option to become available.
 
 config MLX5_EN_TLS
 	bool "Mellanox Technologies TLS Connect-X support"
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index ad852703a3cb..9e715a1056f8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -88,13 +88,13 @@ mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o ipoib/ipoib
 #
 # Accelerations & FPGA
 #
-mlx5_core-$(CONFIG_MLX5_IPSEC) += accel/ipsec_offload.o
 mlx5_core-$(CONFIG_MLX5_ACCEL) += lib/crypto.o
 
 mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o
 
 mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \
-				     en_accel/ipsec_stats.o en_accel/ipsec_fs.o
+				     en_accel/ipsec_stats.o en_accel/ipsec_fs.o \
+				     accel/ipsec_offload.o
 
 mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/ktls_stats.o \
 				   en_accel/fs_tcp.o en_accel/ktls.o en_accel/ktls_txrx.o \
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec_offload.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec_offload.h
index 3d13e2c136b1..36e700b596d8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec_offload.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec_offload.h
@@ -7,7 +7,7 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/accel.h>
 
-#ifdef CONFIG_MLX5_IPSEC
+#ifdef CONFIG_MLX5_EN_IPSEC
 
 unsigned int mlx5_accel_ipsec_counters_count(struct mlx5_core_dev *mdev);
 int mlx5_accel_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters,
@@ -42,22 +42,8 @@ struct mlx5_accel_ipsec_ops {
 };
 
 #else
-
-static inline void *
-mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
-				 struct mlx5_accel_esp_xfrm *xfrm,
-				 u32 *sa_handle)
-{
-	return NULL;
-}
-
-static inline void mlx5_accel_esp_free_hw_context(struct mlx5_core_dev *mdev,
-						  void *context)
-{
-}
-
 static inline void mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev) {}
 
 static inline void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev) {}
-#endif /* CONFIG_MLX5_IPSEC */
+#endif /* CONFIG_MLX5_EN_IPSEC */
 #endif /* __MLX5_IPSEC_OFFLOAD_H__ */
diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h
index 9145e2d37c0e..73e4d50a9f02 100644
--- a/include/linux/mlx5/accel.h
+++ b/include/linux/mlx5/accel.h
@@ -122,7 +122,7 @@ enum mlx5_accel_ipsec_cap {
 	MLX5_ACCEL_IPSEC_CAP_TX_IV_IS_ESN	= 1 << 7,
 };
 
-#ifdef CONFIG_MLX5_ACCEL
+#ifdef CONFIG_MLX5_EN_IPSEC
 
 u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev);
 
@@ -152,5 +152,5 @@ static inline int
 mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
 			   const struct mlx5_accel_esp_xfrm_attrs *attrs) { return -EOPNOTSUPP; }
 
-#endif /* CONFIG_MLX5_ACCEL */
+#endif /* CONFIG_MLX5_EN_IPSEC */
 #endif /* __MLX5_ACCEL_H__ */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 9424503eb8d3..5af53c035949 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -778,7 +778,7 @@ struct mlx5_core_dev {
 #ifdef CONFIG_MLX5_FPGA
 	struct mlx5_fpga_device *fpga;
 #endif
-#ifdef CONFIG_MLX5_ACCEL
+#ifdef CONFIG_MLX5_EN_IPSEC
 	const struct mlx5_accel_ipsec_ops *ipsec_ops;
 #endif
 	struct mlx5_clock        clock;
-- 
cgit v1.2.3


From f2b41b32cde8453a0a26875261f0e26809c2805a Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Wed, 6 Apr 2022 11:25:51 +0300
Subject: net/mlx5: Remove ipsec_ops function table

There is only one IPsec implementation and ipsec_ops is not needed
at all in this situation. Together with removal of ipsec_ops, we can
drop the entry checks as these functions are called for IPsec devices
only.

Link: https://lore.kernel.org/r/bc8dd1c8a77b65dbf5e2cf92c813ffaca2505c5f.1649232994.git.leonro@nvidia.com
Reviewed-by: Raed Salem <raeds@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../mellanox/mlx5/core/en_accel/ipsec_fs.h         |   5 -
 .../mellanox/mlx5/core/en_accel/ipsec_offload.c    | 118 ++-------------------
 .../mellanox/mlx5/core/en_accel/ipsec_offload.h    |  35 ------
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |   4 -
 include/linux/mlx5/driver.h                        |   3 -
 5 files changed, 8 insertions(+), 157 deletions(-)

(limited to 'include/linux/mlx5/driver.h')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.h
index b3e23aa5beeb..b70953979709 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.h
@@ -9,7 +9,6 @@
 #include "ipsec_offload.h"
 #include "en/fs.h"
 
-#ifdef CONFIG_MLX5_EN_IPSEC
 void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_priv *priv);
 int mlx5e_accel_ipsec_fs_init(struct mlx5e_priv *priv);
 int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_priv *priv,
@@ -19,8 +18,4 @@ int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_priv *priv,
 void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_priv *priv,
 				   struct mlx5_accel_esp_xfrm_attrs *attrs,
 				   struct mlx5e_ipsec_rule *ipsec_rule);
-#else
-static inline void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_priv *priv) {}
-static inline int mlx5e_accel_ipsec_fs_init(struct mlx5e_priv *priv) { return 0; }
-#endif
 #endif /* __MLX5_IPSEC_STEERING_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index 7ae2d308139e..f0f44bd95cc9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -106,8 +106,7 @@ mlx5_ipsec_offload_esp_validate_xfrm_attrs(struct mlx5_core_dev *mdev,
 
 static struct mlx5_accel_esp_xfrm *
 mlx5_ipsec_offload_esp_create_xfrm(struct mlx5_core_dev *mdev,
-				   const struct mlx5_accel_esp_xfrm_attrs *attrs,
-				   u32 flags)
+				   const struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
 	struct mlx5_ipsec_esp_xfrm *mxfrm;
 	int err = 0;
@@ -286,11 +285,6 @@ static void mlx5_ipsec_offload_delete_sa_ctx(void *context)
 	mutex_unlock(&mxfrm->lock);
 }
 
-static int mlx5_ipsec_offload_init(struct mlx5_core_dev *mdev)
-{
-	return 0;
-}
-
 static int mlx5_modify_ipsec_obj(struct mlx5_core_dev *mdev,
 				 struct mlx5_ipsec_obj_attrs *attrs,
 				 u32 ipsec_id)
@@ -378,86 +372,12 @@ change_sw_xfrm_attrs:
 	return err;
 }
 
-static const struct mlx5_accel_ipsec_ops ipsec_offload_ops = {
-	.create_hw_context = mlx5_ipsec_offload_create_sa_ctx,
-	.free_hw_context = mlx5_ipsec_offload_delete_sa_ctx,
-	.init = mlx5_ipsec_offload_init,
-	.esp_create_xfrm = mlx5_ipsec_offload_esp_create_xfrm,
-	.esp_destroy_xfrm = mlx5_ipsec_offload_esp_destroy_xfrm,
-	.esp_modify_xfrm = mlx5_ipsec_offload_esp_modify_xfrm,
-};
-
-static const struct mlx5_accel_ipsec_ops *
-mlx5_ipsec_offload_ops(struct mlx5_core_dev *mdev)
-{
-	if (!mlx5_ipsec_device_caps(mdev))
-		return NULL;
-
-	return &ipsec_offload_ops;
-}
-
-void mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev)
-{
-	const struct mlx5_accel_ipsec_ops *ipsec_ops;
-	int err = 0;
-
-	ipsec_ops = mlx5_ipsec_offload_ops(mdev);
-	if (!ipsec_ops || !ipsec_ops->init) {
-		mlx5_core_dbg(mdev, "IPsec ops is not supported\n");
-		return;
-	}
-
-	err = ipsec_ops->init(mdev);
-	if (err) {
-		mlx5_core_warn_once(
-			mdev, "Failed to start IPsec device, err = %d\n", err);
-		return;
-	}
-
-	mdev->ipsec_ops = ipsec_ops;
-}
-
-void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev)
-{
-	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
-
-	if (!ipsec_ops || !ipsec_ops->cleanup)
-		return;
-
-	ipsec_ops->cleanup(mdev);
-}
-
-unsigned int mlx5_accel_ipsec_counters_count(struct mlx5_core_dev *mdev)
-{
-	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
-
-	if (!ipsec_ops || !ipsec_ops->counters_count)
-		return -EOPNOTSUPP;
-
-	return ipsec_ops->counters_count(mdev);
-}
-
-int mlx5_accel_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters,
-				   unsigned int count)
-{
-	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
-
-	if (!ipsec_ops || !ipsec_ops->counters_read)
-		return -EOPNOTSUPP;
-
-	return ipsec_ops->counters_read(mdev, counters, count);
-}
-
 void *mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
 				       struct mlx5_accel_esp_xfrm *xfrm,
 				       u32 *sa_handle)
 {
-	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
 	__be32 saddr[4] = {}, daddr[4] = {};
 
-	if (!ipsec_ops || !ipsec_ops->create_hw_context)
-		return  ERR_PTR(-EOPNOTSUPP);
-
 	if (!xfrm->attrs.is_ipv6) {
 		saddr[3] = xfrm->attrs.saddr.a4;
 		daddr[3] = xfrm->attrs.daddr.a4;
@@ -466,59 +386,37 @@ void *mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
 		memcpy(daddr, xfrm->attrs.daddr.a6, sizeof(daddr));
 	}
 
-	return ipsec_ops->create_hw_context(mdev, xfrm, saddr, daddr,
-					    xfrm->attrs.spi,
-					    xfrm->attrs.is_ipv6, sa_handle);
+	return mlx5_ipsec_offload_create_sa_ctx(mdev, xfrm, saddr, daddr,
+						xfrm->attrs.spi,
+						xfrm->attrs.is_ipv6, sa_handle);
 }
 
 void mlx5_accel_esp_free_hw_context(struct mlx5_core_dev *mdev, void *context)
 {
-	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
-
-	if (!ipsec_ops || !ipsec_ops->free_hw_context)
-		return;
-
-	ipsec_ops->free_hw_context(context);
+	mlx5_ipsec_offload_delete_sa_ctx(context);
 }
 
 struct mlx5_accel_esp_xfrm *
 mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev,
 			   const struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
-	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
 	struct mlx5_accel_esp_xfrm *xfrm;
 
-	if (!ipsec_ops || !ipsec_ops->esp_create_xfrm)
-		return ERR_PTR(-EOPNOTSUPP);
-
-	xfrm = ipsec_ops->esp_create_xfrm(mdev, attrs, 0);
+	xfrm = mlx5_ipsec_offload_esp_create_xfrm(mdev, attrs);
 	if (IS_ERR(xfrm))
 		return xfrm;
 
 	xfrm->mdev = mdev;
 	return xfrm;
 }
-EXPORT_SYMBOL_GPL(mlx5_accel_esp_create_xfrm);
 
 void mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm)
 {
-	const struct mlx5_accel_ipsec_ops *ipsec_ops = xfrm->mdev->ipsec_ops;
-
-	if (!ipsec_ops || !ipsec_ops->esp_destroy_xfrm)
-		return;
-
-	ipsec_ops->esp_destroy_xfrm(xfrm);
+	mlx5_ipsec_offload_esp_destroy_xfrm(xfrm);
 }
-EXPORT_SYMBOL_GPL(mlx5_accel_esp_destroy_xfrm);
 
 int mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
 			       const struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
-	const struct mlx5_accel_ipsec_ops *ipsec_ops = xfrm->mdev->ipsec_ops;
-
-	if (!ipsec_ops || !ipsec_ops->esp_modify_xfrm)
-		return -EOPNOTSUPP;
-
-	return ipsec_ops->esp_modify_xfrm(xfrm, attrs);
+	return mlx5_ipsec_offload_esp_modify_xfrm(xfrm, attrs);
 }
-EXPORT_SYMBOL_GPL(mlx5_accel_esp_modify_xfrm);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.h
index 36e700b596d8..7dac104e6ef1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.h
@@ -7,43 +7,8 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/accel.h>
 
-#ifdef CONFIG_MLX5_EN_IPSEC
-
-unsigned int mlx5_accel_ipsec_counters_count(struct mlx5_core_dev *mdev);
-int mlx5_accel_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters,
-				   unsigned int count);
-
 void *mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
 				       struct mlx5_accel_esp_xfrm *xfrm,
 				       u32 *sa_handle);
 void mlx5_accel_esp_free_hw_context(struct mlx5_core_dev *mdev, void *context);
-
-void mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev);
-void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev);
-
-struct mlx5_accel_ipsec_ops {
-	unsigned int (*counters_count)(struct mlx5_core_dev *mdev);
-	int (*counters_read)(struct mlx5_core_dev *mdev, u64 *counters,
-			     unsigned int count);
-	void *(*create_hw_context)(struct mlx5_core_dev *mdev,
-				   struct mlx5_accel_esp_xfrm *xfrm,
-				   const __be32 saddr[4], const __be32 daddr[4],
-				   const __be32 spi, bool is_ipv6,
-				   u32 *sa_handle);
-	void (*free_hw_context)(void *context);
-	int (*init)(struct mlx5_core_dev *mdev);
-	void (*cleanup)(struct mlx5_core_dev *mdev);
-	struct mlx5_accel_esp_xfrm *(*esp_create_xfrm)(
-		struct mlx5_core_dev *mdev,
-		const struct mlx5_accel_esp_xfrm_attrs *attrs, u32 flags);
-	int (*esp_modify_xfrm)(struct mlx5_accel_esp_xfrm *xfrm,
-			       const struct mlx5_accel_esp_xfrm_attrs *attrs);
-	void (*esp_destroy_xfrm)(struct mlx5_accel_esp_xfrm *xfrm);
-};
-
-#else
-static inline void mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev) {}
-
-static inline void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev) {}
-#endif /* CONFIG_MLX5_EN_IPSEC */
 #endif /* __MLX5_IPSEC_OFFLOAD_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 032de078723c..d504c8cb8f96 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1181,8 +1181,6 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 		goto err_fpga_start;
 	}
 
-	mlx5_accel_ipsec_init(dev);
-
 	err = mlx5_init_fs(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to init flow steering\n");
@@ -1230,7 +1228,6 @@ err_vhca:
 err_set_hca:
 	mlx5_cleanup_fs(dev);
 err_fs:
-	mlx5_accel_ipsec_cleanup(dev);
 	mlx5_fpga_device_stop(dev);
 err_fpga_start:
 	mlx5_rsc_dump_cleanup(dev);
@@ -1256,7 +1253,6 @@ static void mlx5_unload(struct mlx5_core_dev *dev)
 	mlx5_sf_hw_table_destroy(dev);
 	mlx5_vhca_event_stop(dev);
 	mlx5_cleanup_fs(dev);
-	mlx5_accel_ipsec_cleanup(dev);
 	mlx5_fpga_device_stop(dev);
 	mlx5_rsc_dump_cleanup(dev);
 	mlx5_hv_vhca_cleanup(dev->hv_vhca);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 5af53c035949..ff47d49d8be4 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -777,9 +777,6 @@ struct mlx5_core_dev {
 	} roce;
 #ifdef CONFIG_MLX5_FPGA
 	struct mlx5_fpga_device *fpga;
-#endif
-#ifdef CONFIG_MLX5_EN_IPSEC
-	const struct mlx5_accel_ipsec_ops *ipsec_ops;
 #endif
 	struct mlx5_clock        clock;
 	struct mlx5_ib_clock_info  *clock_info;
-- 
cgit v1.2.3


From 8324a02c342a36336114a497130826612ed5520d Mon Sep 17 00:00:00 2001
From: Gavin Li <gavinl@nvidia.com>
Date: Sun, 27 Mar 2022 17:45:32 +0300
Subject: net/mlx5: Add exit route when waiting for FW

Currently, removing a device needs to get the driver interface lock before
doing any cleanup. If the driver is waiting in a loop for FW init, there
is no way to cancel the wait, instead the device cleanup waits for the
loop to conclude and release the lock.

To allow immediate response to remove device commands, check the TEARDOWN
flag while waiting for FW init, and exit the loop if it has been set.

Signed-off-by: Gavin Li <gavinl@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 5 ++++-
 include/linux/mlx5/driver.h                    | 1 +
 2 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include/linux/mlx5/driver.h')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 35e48ef04845..f28a3526aafa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -189,7 +189,8 @@ static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili,
 		fw_initializing = ioread32be(&dev->iseg->initializing);
 		if (!(fw_initializing >> 31))
 			break;
-		if (time_after(jiffies, end)) {
+		if (time_after(jiffies, end) ||
+		    test_and_clear_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state)) {
 			err = -EBUSY;
 			break;
 		}
@@ -1602,6 +1603,7 @@ static void remove_one(struct pci_dev *pdev)
 	struct mlx5_core_dev *dev  = pci_get_drvdata(pdev);
 	struct devlink *devlink = priv_to_devlink(dev);
 
+	set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state);
 	devlink_unregister(devlink);
 	mlx5_sriov_disable(pdev);
 	mlx5_crdump_disable(dev);
@@ -1785,6 +1787,7 @@ static void shutdown(struct pci_dev *pdev)
 	int err;
 
 	mlx5_core_info(dev, "Shutdown was called\n");
+	set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state);
 	err = mlx5_try_fast_unload(dev);
 	if (err)
 		mlx5_unload_one(dev);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index ff47d49d8be4..f327d0544038 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -632,6 +632,7 @@ enum mlx5_device_state {
 
 enum mlx5_interface_state {
 	MLX5_INTERFACE_STATE_UP = BIT(0),
+	MLX5_BREAK_FW_WAIT = BIT(1),
 };
 
 enum mlx5_pci_status {
-- 
cgit v1.2.3


From 34a30d7635a8e37275a7b63bec09035ed762969b Mon Sep 17 00:00:00 2001
From: Mark Bloch <mbloch@nvidia.com>
Date: Tue, 1 Mar 2022 15:42:01 +0000
Subject: net/mlx5: Lag, expose number of lag ports

Downstream patches will add support for hardware lag with
more than 2 ports. Add a way for users to query the number of lag ports.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/infiniband/hw/mlx5/gsi.c                  | 2 +-
 drivers/infiniband/hw/mlx5/main.c                 | 1 +
 drivers/infiniband/hw/mlx5/mlx5_ib.h              | 1 +
 drivers/infiniband/hw/mlx5/qp.c                   | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c | 6 ++++++
 include/linux/mlx5/driver.h                       | 1 +
 6 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'include/linux/mlx5/driver.h')

diff --git a/drivers/infiniband/hw/mlx5/gsi.c b/drivers/infiniband/hw/mlx5/gsi.c
index 3ad8f637c589..b804f2dd5628 100644
--- a/drivers/infiniband/hw/mlx5/gsi.c
+++ b/drivers/infiniband/hw/mlx5/gsi.c
@@ -100,7 +100,7 @@ int mlx5_ib_create_gsi(struct ib_pd *pd, struct mlx5_ib_qp *mqp,
 				 port_type) == MLX5_CAP_PORT_TYPE_IB)
 			num_qps = pd->device->attrs.max_pkeys;
 		else if (dev->lag_active)
-			num_qps = MLX5_MAX_PORTS;
+			num_qps = dev->lag_ports;
 	}
 
 	gsi = &mqp->gsi;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 61aa196d6484..61a3b767262f 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2991,6 +2991,7 @@ static int mlx5_eth_lag_init(struct mlx5_ib_dev *dev)
 	}
 
 	dev->flow_db->lag_demux_ft = ft;
+	dev->lag_ports = mlx5_lag_get_num_ports(mdev);
 	dev->lag_active = true;
 	return 0;
 
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 4f04bb55c4c6..8b3c83c0b70a 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1131,6 +1131,7 @@ struct mlx5_ib_dev {
 	struct xarray sig_mrs;
 	struct mlx5_port_caps port_caps[MLX5_MAX_PORTS];
 	u16 pkey_table_len;
+	u8 lag_ports;
 };
 
 static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq)
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 3f467557d34e..fb8669c02546 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -3907,7 +3907,7 @@ static unsigned int get_tx_affinity_rr(struct mlx5_ib_dev *dev,
 		tx_port_affinity = &dev->port[port_num].roce.tx_port_affinity;
 
 	return (unsigned int)atomic_add_return(1, tx_port_affinity) %
-		MLX5_MAX_PORTS + 1;
+		(dev->lag_active ? dev->lag_ports : MLX5_CAP_GEN(dev->mdev, num_lag_ports)) + 1;
 }
 
 static bool qp_supports_affinity(struct mlx5_ib_qp *qp)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 6cad3b72c133..fe34cce77d07 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -1185,6 +1185,12 @@ unlock:
 }
 EXPORT_SYMBOL(mlx5_lag_get_slave_port);
 
+u8 mlx5_lag_get_num_ports(struct mlx5_core_dev *dev)
+{
+	return MLX5_MAX_PORTS;
+}
+EXPORT_SYMBOL(mlx5_lag_get_num_ports);
+
 struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_dev *peer_dev = NULL;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index f327d0544038..62ea1120de9c 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1142,6 +1142,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 				 int num_counters,
 				 size_t *offsets);
 struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev);
+u8 mlx5_lag_get_num_ports(struct mlx5_core_dev *dev);
 struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev);
 void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up);
 int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type,
-- 
cgit v1.2.3


From 4cd14d44b11dabf195d1e66dadbb954336224658 Mon Sep 17 00:00:00 2001
From: Mark Bloch <mbloch@nvidia.com>
Date: Tue, 1 Mar 2022 17:34:58 +0000
Subject: net/mlx5: Support devices with more than 2 ports

Increase the define MLX5_MAX_PORTS to 4 as the driver is ready
to support NICs with 4 ports.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/dev.c     | 3 ++-
 drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c | 3 ++-
 include/linux/mlx5/driver.h                       | 2 +-
 3 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'include/linux/mlx5/driver.h')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index 3e750b827a19..11f7c03ae81b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -586,7 +586,8 @@ static int next_phys_dev_lag(struct device *dev, const void *data)
 
 	if (!MLX5_CAP_GEN(mdev, vport_group_manager) ||
 	    !MLX5_CAP_GEN(mdev, lag_master) ||
-	    MLX5_CAP_GEN(mdev, num_lag_ports) != MLX5_MAX_PORTS)
+	    (MLX5_CAP_GEN(mdev, num_lag_ports) > MLX5_MAX_PORTS ||
+	     MLX5_CAP_GEN(mdev, num_lag_ports) <= 1))
 		return 0;
 
 	return _next_phys_dev(mdev, data);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index f2659b0f8cc5..716e073c80d4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -1050,7 +1050,8 @@ void mlx5_lag_add_mdev(struct mlx5_core_dev *dev)
 
 	if (!MLX5_CAP_GEN(dev, vport_group_manager) ||
 	    !MLX5_CAP_GEN(dev, lag_master) ||
-	    MLX5_CAP_GEN(dev, num_lag_ports) != MLX5_MAX_PORTS)
+	    (MLX5_CAP_GEN(dev, num_lag_ports) > MLX5_MAX_PORTS ||
+	     MLX5_CAP_GEN(dev, num_lag_ports) <= 1))
 		return;
 
 recheck:
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 62ea1120de9c..fdb9d07a05a4 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -84,7 +84,7 @@ enum mlx5_sqp_t {
 };
 
 enum {
-	MLX5_MAX_PORTS	= 2,
+	MLX5_MAX_PORTS	= 4,
 };
 
 enum {
-- 
cgit v1.2.3


From 7f46a0b7327ae261f9981888708dbca22c283900 Mon Sep 17 00:00:00 2001
From: Mark Bloch <mbloch@nvidia.com>
Date: Tue, 15 Mar 2022 16:56:50 +0000
Subject: net/mlx5: Lag, add debugfs to query hardware lag state

Lag state has become very complicated with many modes, flags, types and
port selections methods and future work will add additional features.

Add a debugfs to query the current lag state. A new directory named "lag"
will be created under the mlx5 debugfs directory. As the driver has
debugfs per pci function the location will be: <debugfs>/mlx5/<BDF>/lag

For example:
/sys/kernel/debug/mlx5/0000:08:00.0/lag

The following files are exposed:

- state: Returns "active" or "disabled". If "active" it means hardware
         lag is active.

- members: Returns the BDFs of all the members of lag object.

- type: Returns the type of the lag currently configured. Valid only
	if hardware lag is active.
	* "roce" - Members are bare metal PFs.
	* "switchdev" - Members are in switchdev mode.
	* "multipath" - ECMP offloads.

- port_sel_mode: Returns the egress port selection method, valid
		 only if hardware lag is active.
		 * "queue_affinity" - Egress port is selected by
		   the QP/SQ affinity.
		 * "hash" - Egress port is selected by hash done on
		   each packet. Controlled by: xmit_hash_policy of the
		   bond device.
- flags: Returns flags that are specific per lag @type. Valid only if
	 hardware lag is active.
	 * "shared_fdb" - "on" or "off", if "on" single FDB is used.

- mapping: Returns the mapping which is used to select egress port.
	   Valid only if hardware lag is active.
	   If @port_sel_mode is "hash" returns the active egress ports.
	   The hash result will select only active ports.
	   if @port_sel_mode is "queue_affinity" returns the mapping
	   between the configured port affinity of the QP/SQ and actual
	   egress port. For example:
	   * 1:1 - Mapping means if the configured affinity is port 1
	           traffic will egress via port 1.
	   * 1:2 - Mapping means if the configured affinity is port 1
		   traffic will egress via port 2. This can happen
		   if port 1 is down or in active/backup mode and port 1
		   is backup.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   2 +-
 .../net/ethernet/mellanox/mlx5/core/lag/debugfs.c  | 173 +++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c  |  11 +-
 drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h  |   9 ++
 include/linux/mlx5/driver.h                        |   1 +
 5 files changed, 192 insertions(+), 4 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c

(limited to 'include/linux/mlx5/driver.h')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 81620c25c77e..7895ed7cc285 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -14,7 +14,7 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o
 mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		health.o mcg.o cq.o alloc.o port.o mr.o pd.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/lag.o dev.o events.o wq.o lib/gid.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 \
 		fw_reset.o qos.o lib/tout.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c
new file mode 100644
index 000000000000..443daf6e3d4b
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c
@@ -0,0 +1,173 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include "lag.h"
+
+static char *get_str_mode_type(struct mlx5_lag *ldev)
+{
+	if (ldev->flags & MLX5_LAG_FLAG_ROCE)
+		return "roce";
+	if (ldev->flags & MLX5_LAG_FLAG_SRIOV)
+		return "switchdev";
+	if (ldev->flags & MLX5_LAG_FLAG_MULTIPATH)
+		return "multipath";
+
+	return NULL;
+}
+
+static int type_show(struct seq_file *file, void *priv)
+{
+	struct mlx5_core_dev *dev = file->private;
+	struct mlx5_lag *ldev;
+	char *mode = NULL;
+
+	ldev = dev->priv.lag;
+	mutex_lock(&ldev->lock);
+	if (__mlx5_lag_is_active(ldev))
+		mode = get_str_mode_type(ldev);
+	mutex_unlock(&ldev->lock);
+	if (!mode)
+		return -EINVAL;
+	seq_printf(file, "%s\n", mode);
+
+	return 0;
+}
+
+static int port_sel_mode_show(struct seq_file *file, void *priv)
+{
+	struct mlx5_core_dev *dev = file->private;
+	struct mlx5_lag *ldev;
+	int ret = 0;
+	char *mode;
+
+	ldev = dev->priv.lag;
+	mutex_lock(&ldev->lock);
+	if (__mlx5_lag_is_active(ldev))
+		mode = get_str_port_sel_mode(ldev->flags);
+	else
+		ret = -EINVAL;
+	mutex_unlock(&ldev->lock);
+	if (ret || !mode)
+		return ret;
+
+	seq_printf(file, "%s\n", mode);
+	return 0;
+}
+
+static int state_show(struct seq_file *file, void *priv)
+{
+	struct mlx5_core_dev *dev = file->private;
+	struct mlx5_lag *ldev;
+	bool active;
+
+	ldev = dev->priv.lag;
+	mutex_lock(&ldev->lock);
+	active = __mlx5_lag_is_active(ldev);
+	mutex_unlock(&ldev->lock);
+	seq_printf(file, "%s\n", active ? "active" : "disabled");
+	return 0;
+}
+
+static int flags_show(struct seq_file *file, void *priv)
+{
+	struct mlx5_core_dev *dev = file->private;
+	struct mlx5_lag *ldev;
+	bool shared_fdb;
+	bool lag_active;
+
+	ldev = dev->priv.lag;
+	mutex_lock(&ldev->lock);
+	lag_active = __mlx5_lag_is_active(ldev);
+	if (lag_active)
+		shared_fdb = ldev->shared_fdb;
+
+	mutex_unlock(&ldev->lock);
+	if (!lag_active)
+		return -EINVAL;
+
+	seq_printf(file, "%s:%s\n", "shared_fdb", shared_fdb ? "on" : "off");
+	return 0;
+}
+
+static int mapping_show(struct seq_file *file, void *priv)
+{
+	struct mlx5_core_dev *dev = file->private;
+	u8 ports[MLX5_MAX_PORTS] = {};
+	struct mlx5_lag *ldev;
+	bool hash = false;
+	bool lag_active;
+	int num_ports;
+	int i;
+
+	ldev = dev->priv.lag;
+	mutex_lock(&ldev->lock);
+	lag_active = __mlx5_lag_is_active(ldev);
+	if (lag_active) {
+		if (ldev->flags & MLX5_LAG_FLAG_HASH_BASED) {
+			mlx5_infer_tx_enabled(&ldev->tracker, ldev->ports, ports,
+					      &num_ports);
+			hash = true;
+		} else {
+			for (i = 0; i < ldev->ports; i++)
+				ports[i] = ldev->v2p_map[i];
+			num_ports = ldev->ports;
+		}
+	}
+	mutex_unlock(&ldev->lock);
+	if (!lag_active)
+		return -EINVAL;
+
+	for (i = 0; i < num_ports; i++) {
+		if (hash)
+			seq_printf(file, "%d\n", ports[i] + 1);
+		else
+			seq_printf(file, "%d:%d\n", i + 1, ports[i]);
+	}
+
+	return 0;
+}
+
+static int members_show(struct seq_file *file, void *priv)
+{
+	struct mlx5_core_dev *dev = file->private;
+	struct mlx5_lag *ldev;
+	int i;
+
+	ldev = dev->priv.lag;
+	mutex_lock(&ldev->lock);
+	for (i = 0; i < ldev->ports; i++) {
+		if (!ldev->pf[i].dev)
+			continue;
+		seq_printf(file, "%s\n", dev_name(ldev->pf[i].dev->device));
+	}
+	mutex_unlock(&ldev->lock);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(type);
+DEFINE_SHOW_ATTRIBUTE(port_sel_mode);
+DEFINE_SHOW_ATTRIBUTE(state);
+DEFINE_SHOW_ATTRIBUTE(flags);
+DEFINE_SHOW_ATTRIBUTE(mapping);
+DEFINE_SHOW_ATTRIBUTE(members);
+
+void mlx5_ldev_add_debugfs(struct mlx5_core_dev *dev)
+{
+	struct dentry *dbg;
+
+	dbg = debugfs_create_dir("lag", mlx5_debugfs_get_dev_root(dev));
+	dev->priv.dbg.lag_debugfs = dbg;
+
+	debugfs_create_file("type", 0444, dbg, dev, &type_fops);
+	debugfs_create_file("port_sel_mode", 0444, dbg, dev, &port_sel_mode_fops);
+	debugfs_create_file("state", 0444, dbg, dev, &state_fops);
+	debugfs_create_file("flags", 0444, dbg, dev, &flags_fops);
+	debugfs_create_file("mapping", 0444, dbg, dev, &mapping_fops);
+	debugfs_create_file("members", 0444, dbg, dev, &members_fops);
+}
+
+void mlx5_ldev_remove_debugfs(struct dentry *dbg)
+{
+	debugfs_remove_recursive(dbg);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 8a74c409b501..b6dd9043061f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -120,8 +120,8 @@ static void mlx5_infer_tx_disabled(struct lag_tracker *tracker, u8 num_ports,
 	}
 }
 
-static void mlx5_infer_tx_enabled(struct lag_tracker *tracker, u8 num_ports,
-				  u8 *ports, int *num_enabled)
+void mlx5_infer_tx_enabled(struct lag_tracker *tracker, u8 num_ports,
+			   u8 *ports, int *num_enabled)
 {
 	int i;
 
@@ -454,7 +454,7 @@ static int mlx5_lag_set_port_sel_mode(struct mlx5_lag *ldev,
 	return mlx5_lag_set_port_sel_mode_offloads(ldev, tracker, flags);
 }
 
-static char *get_str_port_sel_mode(u8 flags)
+char *get_str_port_sel_mode(u8 flags)
 {
 	if (flags &  MLX5_LAG_FLAG_HASH_BASED)
 		return "hash";
@@ -1106,6 +1106,10 @@ void mlx5_lag_remove_mdev(struct mlx5_core_dev *dev)
 	if (!ldev)
 		return;
 
+	/* mdev is being removed, might as well remove debugfs
+	 * as early as possible.
+	 */
+	mlx5_ldev_remove_debugfs(dev->priv.dbg.lag_debugfs);
 recheck:
 	mutex_lock(&ldev->lock);
 	if (ldev->mode_changes_in_progress) {
@@ -1137,6 +1141,7 @@ recheck:
 		msleep(100);
 		goto recheck;
 	}
+	mlx5_ldev_add_debugfs(dev);
 }
 
 void mlx5_lag_remove_netdev(struct mlx5_core_dev *dev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
index 0c90d0ed03be..46683b84ff84 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
@@ -4,6 +4,8 @@
 #ifndef __MLX5_LAG_H__
 #define __MLX5_LAG_H__
 
+#include <linux/debugfs.h>
+
 #define MLX5_LAG_MAX_HASH_BUCKETS 16
 #include "mlx5_core.h"
 #include "mp.h"
@@ -90,4 +92,11 @@ int mlx5_activate_lag(struct mlx5_lag *ldev,
 int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
 				struct net_device *ndev);
 
+char *get_str_port_sel_mode(u8 flags);
+void mlx5_infer_tx_enabled(struct lag_tracker *tracker, u8 num_ports,
+			   u8 *ports, int *num_enabled);
+
+void mlx5_ldev_add_debugfs(struct mlx5_core_dev *dev);
+void mlx5_ldev_remove_debugfs(struct dentry *dbg);
+
 #endif /* __MLX5_LAG_H__ */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index fdb9d07a05a4..d6bac3976913 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -558,6 +558,7 @@ struct mlx5_debugfs_entries {
 	struct dentry *cq_debugfs;
 	struct dentry *cmdif_debugfs;
 	struct dentry *pages_debugfs;
+	struct dentry *lag_debugfs;
 };
 
 struct mlx5_ft_pool;
-- 
cgit v1.2.3


From 846e437387e74c44ddc9f3eeec472fd37ca3cdb9 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Tue, 10 May 2022 12:02:03 +0300
Subject: net/mlx5: Expose mlx5_sriov_blocking_notifier_register / unregister
 APIs

Expose mlx5_sriov_blocking_notifier_register / unregister APIs to let a
VF register to be notified for its enablement / disablement by the PF.

Upon VF probe it will call mlx5_sriov_blocking_notifier_register() with
its notifier block and upon VF remove it will call
mlx5_sriov_blocking_notifier_unregister() to drop its registration.

This can give a VF the ability to clean some resources upon disable
before that the command interface goes down and on the other hand sets
some stuff before that it's enabled.

This may be used by a VF which is migration capable in few cases.(e.g.
PF load/unload upon an health recovery).

Link: https://lore.kernel.org/r/20220510090206.90374-2-yishaih@nvidia.com
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/sriov.c | 65 ++++++++++++++++++++++++-
 include/linux/mlx5/driver.h                     | 12 +++++
 2 files changed, 76 insertions(+), 1 deletion(-)

(limited to 'include/linux/mlx5/driver.h')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index 887ee0f729d1..2935614f6fa9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -87,6 +87,11 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs)
 enable_vfs_hca:
 	num_msix_count = mlx5_get_default_msix_vec_count(dev, num_vfs);
 	for (vf = 0; vf < num_vfs; vf++) {
+		/* Notify the VF before its enablement to let it set
+		 * some stuff.
+		 */
+		blocking_notifier_call_chain(&sriov->vfs_ctx[vf].notifier,
+					     MLX5_PF_NOTIFY_ENABLE_VF, dev);
 		err = mlx5_core_enable_hca(dev, vf + 1);
 		if (err) {
 			mlx5_core_warn(dev, "failed to enable VF %d (%d)\n", vf, err);
@@ -127,6 +132,11 @@ mlx5_device_disable_sriov(struct mlx5_core_dev *dev, int num_vfs, bool clear_vf)
 	for (vf = num_vfs - 1; vf >= 0; vf--) {
 		if (!sriov->vfs_ctx[vf].enabled)
 			continue;
+		/* Notify the VF before its disablement to let it clean
+		 * some resources.
+		 */
+		blocking_notifier_call_chain(&sriov->vfs_ctx[vf].notifier,
+					     MLX5_PF_NOTIFY_DISABLE_VF, dev);
 		err = mlx5_core_disable_hca(dev, vf + 1);
 		if (err) {
 			mlx5_core_warn(dev, "failed to disable VF %d\n", vf);
@@ -257,7 +267,7 @@ int mlx5_sriov_init(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_sriov *sriov = &dev->priv.sriov;
 	struct pci_dev *pdev = dev->pdev;
-	int total_vfs;
+	int total_vfs, i;
 
 	if (!mlx5_core_is_pf(dev))
 		return 0;
@@ -269,6 +279,9 @@ int mlx5_sriov_init(struct mlx5_core_dev *dev)
 	if (!sriov->vfs_ctx)
 		return -ENOMEM;
 
+	for (i = 0; i < total_vfs; i++)
+		BLOCKING_INIT_NOTIFIER_HEAD(&sriov->vfs_ctx[i].notifier);
+
 	return 0;
 }
 
@@ -281,3 +294,53 @@ void mlx5_sriov_cleanup(struct mlx5_core_dev *dev)
 
 	kfree(sriov->vfs_ctx);
 }
+
+/**
+ * mlx5_sriov_blocking_notifier_unregister - Unregister a VF from
+ * a notification block chain.
+ *
+ * @mdev: The mlx5 core device.
+ * @vf_id: The VF id.
+ * @nb: The notifier block to be unregistered.
+ */
+void mlx5_sriov_blocking_notifier_unregister(struct mlx5_core_dev *mdev,
+					     int vf_id,
+					     struct notifier_block *nb)
+{
+	struct mlx5_vf_context *vfs_ctx;
+	struct mlx5_core_sriov *sriov;
+
+	sriov = &mdev->priv.sriov;
+	if (WARN_ON(vf_id < 0 || vf_id >= sriov->num_vfs))
+		return;
+
+	vfs_ctx = &sriov->vfs_ctx[vf_id];
+	blocking_notifier_chain_unregister(&vfs_ctx->notifier, nb);
+}
+EXPORT_SYMBOL(mlx5_sriov_blocking_notifier_unregister);
+
+/**
+ * mlx5_sriov_blocking_notifier_register - Register a VF notification
+ * block chain.
+ *
+ * @mdev: The mlx5 core device.
+ * @vf_id: The VF id.
+ * @nb: The notifier block to be called upon the VF events.
+ *
+ * Returns 0 on success or an error code.
+ */
+int mlx5_sriov_blocking_notifier_register(struct mlx5_core_dev *mdev,
+					  int vf_id,
+					  struct notifier_block *nb)
+{
+	struct mlx5_vf_context *vfs_ctx;
+	struct mlx5_core_sriov *sriov;
+
+	sriov = &mdev->priv.sriov;
+	if (vf_id < 0 || vf_id >= sriov->num_vfs)
+		return -EINVAL;
+
+	vfs_ctx = &sriov->vfs_ctx[vf_id];
+	return blocking_notifier_chain_register(&vfs_ctx->notifier, nb);
+}
+EXPORT_SYMBOL(mlx5_sriov_blocking_notifier_register);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index ff47d49d8be4..6fac5427d899 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -445,6 +445,11 @@ struct mlx5_qp_table {
 	struct radix_tree_root	tree;
 };
 
+enum {
+	MLX5_PF_NOTIFY_DISABLE_VF,
+	MLX5_PF_NOTIFY_ENABLE_VF,
+};
+
 struct mlx5_vf_context {
 	int	enabled;
 	u64	port_guid;
@@ -455,6 +460,7 @@ struct mlx5_vf_context {
 	u8	port_guid_valid:1;
 	u8	node_guid_valid:1;
 	enum port_state_policy	policy;
+	struct blocking_notifier_head notifier;
 };
 
 struct mlx5_core_sriov {
@@ -1152,6 +1158,12 @@ int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type
 struct mlx5_core_dev *mlx5_vf_get_core_dev(struct pci_dev *pdev);
 void mlx5_vf_put_core_dev(struct mlx5_core_dev *mdev);
 
+int mlx5_sriov_blocking_notifier_register(struct mlx5_core_dev *mdev,
+					  int vf_id,
+					  struct notifier_block *nb);
+void mlx5_sriov_blocking_notifier_unregister(struct mlx5_core_dev *mdev,
+					     int vf_id,
+					     struct notifier_block *nb);
 #ifdef CONFIG_MLX5_CORE_IPOIB
 struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,
 					  struct ib_device *ibdev,
-- 
cgit v1.2.3


From 1d2c717bc7f7fd3c9cf38d4a0d5d7ede06adf05b Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Fri, 13 May 2022 06:19:31 +0300
Subject: net/mlx5: Add last command failure syndrome to debugfs

Add syndrome of last command failure per command type to debugfs to ease
debugging of such failure.
last_failed_syndrome - last command failed syndrome returned by FW.

Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c     | 7 +++++--
 drivers/net/ethernet/mellanox/mlx5/core/debugfs.c | 2 ++
 include/linux/mlx5/driver.h                       | 2 ++
 3 files changed, 9 insertions(+), 2 deletions(-)

(limited to 'include/linux/mlx5/driver.h')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 26ba94cb432e..0377392848d9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1887,7 +1887,8 @@ out_in:
 	return err;
 }
 
-static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, int err)
+static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status,
+			   u32 syndrome, int err)
 {
 	struct mlx5_cmd_stats *stats;
 
@@ -1902,6 +1903,7 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, int
 	if (err == -EREMOTEIO) {
 		stats->failed_mbox_status++;
 		stats->last_failed_mbox_status = status;
+		stats->last_failed_syndrome = syndrome;
 	}
 	spin_unlock_irq(&stats->lock);
 }
@@ -1909,6 +1911,7 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, int
 /* preserve -EREMOTEIO for outbox.status != OK, otherwise return err as is */
 static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, void *out)
 {
+	u32 syndrome = MLX5_GET(mbox_out, out, syndrome);
 	u8 status = MLX5_GET(mbox_out, out, status);
 
 	if (err == -EREMOTEIO) /* -EREMOTEIO is preserved */
@@ -1917,7 +1920,7 @@ static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, void *
 	if (!err && status != MLX5_CMD_STAT_OK)
 		err = -EREMOTEIO;
 
-	cmd_status_log(dev, opcode, status, err);
+	cmd_status_log(dev, opcode, status, syndrome, err);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index 3d3e55a5cb11..9caa1b52321b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -192,6 +192,8 @@ void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev)
 					   &stats->last_failed_errno);
 			debugfs_create_u8("last_failed_mbox_status", 0400, stats->root,
 					  &stats->last_failed_mbox_status);
+			debugfs_create_x32("last_failed_syndrome", 0400, stats->root,
+					   &stats->last_failed_syndrome);
 		}
 	}
 }
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index d6bac3976913..74c8cfb771a2 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -272,6 +272,8 @@ struct mlx5_cmd_stats {
 	u32		last_failed_errno;
 	/* last bad status returned by FW */
 	u8		last_failed_mbox_status;
+	/* last command failed syndrome returned by FW */
+	u32		last_failed_syndrome;
 	struct dentry  *root;
 	/* protect command average calculations */
 	spinlock_t	lock;
-- 
cgit v1.2.3


From 9b45bde82c229fda94618896ff530dcba9d66fe0 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Tue, 25 Jan 2022 14:47:36 +0200
Subject: net/mlx5: Inline db alloc API function

Take the wrapper version which picks default node into a header file.
This reduces the number of exported functions.

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/alloc.c | 6 ------
 include/linux/mlx5/driver.h                     | 7 ++++++-
 2 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'include/linux/mlx5/driver.h')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
index e52b0bac09da..6aca004e88cd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
@@ -213,12 +213,6 @@ out:
 }
 EXPORT_SYMBOL_GPL(mlx5_db_alloc_node);
 
-int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db)
-{
-	return mlx5_db_alloc_node(dev, db, dev->priv.numa_node);
-}
-EXPORT_SYMBOL_GPL(mlx5_db_alloc);
-
 void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db)
 {
 	u32 db_per_page = PAGE_SIZE / cache_line_size();
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 74c8cfb771a2..b064bc278f52 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1053,9 +1053,14 @@ int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in,
 			 int size_in, void *data_out, int size_out,
 			 u16 reg_num, int arg, int write);
 
-int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db);
 int mlx5_db_alloc_node(struct mlx5_core_dev *dev, struct mlx5_db *db,
 		       int node);
+
+static inline int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db)
+{
+	return mlx5_db_alloc_node(dev, db, dev->priv.numa_node);
+}
+
 void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db);
 
 const char *mlx5_command_str(int command);
-- 
cgit v1.2.3