From: Saeed Mahameed <saeedm@mellanox.com>
To: "David S. Miller" <davem@davemloft.net>
Cc: "netdev@vger.kernel.org" <netdev@vger.kernel.org>,
Jiri Pirko <jiri@mellanox.com>, Alex Vesker <valex@mellanox.com>,
Moshe Shemesh <moshe@mellanox.com>,
Feras Daoud <ferasda@mellanox.com>,
Saeed Mahameed <saeedm@mellanox.com>
Subject: [net-next v2 05/15] net/mlx5: Add Crdump support
Date: Thu, 13 Jun 2019 20:39:23 +0000 [thread overview]
Message-ID: <20190613203825.31049-6-saeedm@mellanox.com> (raw)
In-Reply-To: <20190613203825.31049-1-saeedm@mellanox.com>
From: Alex Vesker <valex@mellanox.com>
Crdump allows the driver to retrieve a dump of the FW PCI crspace.
This is useful in case of catastrophic issues which may require FW
reset. The crspace dump can be used for later debug.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/Makefile | 2 +-
.../ethernet/mellanox/mlx5/core/diag/crdump.c | 106 ++++++++++++++++++
.../ethernet/mellanox/mlx5/core/lib/mlx5.h | 3 +
.../net/ethernet/mellanox/mlx5/core/main.c | 5 +
include/linux/mlx5/driver.h | 1 +
5 files changed, 116 insertions(+), 1 deletion(-)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/diag/crdump.c
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 8e07354faea1..5fe2bf916c06 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -16,7 +16,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \
lib/devcom.o lib/pci_vsc.o diag/fs_tracepoint.o \
- diag/fw_tracer.o devlink.o
+ diag/fw_tracer.o diag/crdump.o devlink.o
#
# Netdev basic
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/crdump.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/crdump.c
new file mode 100644
index 000000000000..dfb34172c69b
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/crdump.c
@@ -0,0 +1,106 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies */
+
+#include <linux/mlx5/driver.h>
+#include "mlx5_core.h"
+#include "lib/pci_vsc.h"
+#include "lib/mlx5.h"
+
+#define BAD_ACCESS 0xBADACCE5
+#define MLX5_PROTECTED_CR_SCAN_CRSPACE 0x7
+
+static bool mlx5_crdump_enabled(struct mlx5_core_dev *dev)
+{
+ return !!dev->priv.health.crdump_size;
+}
+
+static int mlx5_crdump_fill(struct mlx5_core_dev *dev, u32 *cr_data)
+{
+ u32 crdump_size = dev->priv.health.crdump_size;
+ int i, ret;
+
+ for (i = 0; i < (crdump_size / 4); i++)
+ cr_data[i] = BAD_ACCESS;
+
+ ret = mlx5_vsc_gw_read_block_fast(dev, cr_data, crdump_size);
+ if (ret <= 0) {
+ if (ret == 0)
+ return -EIO;
+ return ret;
+ }
+
+ if (crdump_size != ret) {
+ mlx5_core_warn(dev, "failed to read full dump, read %d out of %u\n",
+ ret, crdump_size);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+int mlx5_crdump_collect(struct mlx5_core_dev *dev, u32 *cr_data)
+{
+ int ret;
+
+ if (!mlx5_crdump_enabled(dev))
+ return -ENODEV;
+
+ ret = mlx5_vsc_gw_lock(dev);
+ if (ret) {
+ mlx5_core_warn(dev, "crdump: failed to lock vsc gw err %d\n",
+ ret);
+ return ret;
+ }
+
+ ret = mlx5_vsc_gw_set_space(dev, MLX5_VSC_SPACE_SCAN_CRSPACE, NULL);
+ if (ret)
+ goto unlock;
+
+ ret = mlx5_crdump_fill(dev, cr_data);
+
+unlock:
+ mlx5_vsc_gw_unlock(dev);
+ return ret;
+}
+
+int mlx5_crdump_enable(struct mlx5_core_dev *dev)
+{
+ struct mlx5_priv *priv = &dev->priv;
+ u32 space_size;
+ int ret;
+
+ if (!mlx5_core_is_pf(dev) || !mlx5_vsc_accessible(dev) ||
+ mlx5_crdump_enabled(dev))
+ return 0;
+
+ ret = mlx5_vsc_gw_lock(dev);
+ if (ret)
+ return ret;
+
+ /* Check if space is supported and get space size */
+ ret = mlx5_vsc_gw_set_space(dev, MLX5_VSC_SPACE_SCAN_CRSPACE,
+ &space_size);
+ if (ret) {
+ /* Unlock and mask error since space is not supported */
+ mlx5_vsc_gw_unlock(dev);
+ return 0;
+ }
+
+ if (!space_size) {
+ mlx5_core_warn(dev, "Invalid Crspace size, zero\n");
+ mlx5_vsc_gw_unlock(dev);
+ return -EINVAL;
+ }
+
+ ret = mlx5_vsc_gw_unlock(dev);
+ if (ret)
+ return ret;
+
+ priv->health.crdump_size = space_size;
+ return 0;
+}
+
+void mlx5_crdump_disable(struct mlx5_core_dev *dev)
+{
+ dev->priv.health.crdump_size = 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
index 397a2847867a..d918e44491f4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
@@ -41,6 +41,9 @@ int mlx5_core_reserve_gids(struct mlx5_core_dev *dev, unsigned int count);
void mlx5_core_unreserve_gids(struct mlx5_core_dev *dev, unsigned int count);
int mlx5_core_reserved_gid_alloc(struct mlx5_core_dev *dev, int *gid_index);
void mlx5_core_reserved_gid_free(struct mlx5_core_dev *dev, int gid_index);
+int mlx5_crdump_enable(struct mlx5_core_dev *dev);
+void mlx5_crdump_disable(struct mlx5_core_dev *dev);
+int mlx5_crdump_collect(struct mlx5_core_dev *dev, u32 *cr_data);
/* TODO move to lib/events.h */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 3adc09a1a312..c70e97071b87 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1313,6 +1313,10 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
if (err)
goto clean_load;
+ err = mlx5_crdump_enable(dev);
+ if (err)
+ dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err);
+
pci_save_state(pdev);
return 0;
@@ -1334,6 +1338,7 @@ static void remove_one(struct pci_dev *pdev)
struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
struct devlink *devlink = priv_to_devlink(dev);
+ mlx5_crdump_disable(dev);
mlx5_devlink_unregister(devlink);
mlx5_unregister_device(dev);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index f732445bcbdb..4ae533b3da07 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -435,6 +435,7 @@ struct mlx5_core_health {
u32 prev;
int miss_counter;
bool sick;
+ u32 crdump_size;
/* wq spinlock to synchronize draining */
spinlock_t wq_lock;
struct workqueue_struct *wq;
--
2.21.0
next prev parent reply other threads:[~2019-06-13 20:39 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-13 20:39 [pull request][net-next v2 00/15] Mellanox, mlx5 Firmware devlink health and sw reset Saeed Mahameed
2019-06-13 20:39 ` [net-next v2 01/15] devlink: Hang reporter's dump method on a dumpit cb Saeed Mahameed
2019-06-13 20:39 ` [net-next v2 02/15] Documentation: net: mlx5: Add mlx5 initial documentation Saeed Mahameed
2019-06-13 20:39 ` [net-next v2 03/15] net/mlx5: Move all devlink related functions calls to devlink.c Saeed Mahameed
2019-06-13 20:39 ` [net-next v2 04/15] net/mlx5: Add Vendor Specific Capability access gateway Saeed Mahameed
2019-06-13 20:39 ` Saeed Mahameed [this message]
2019-06-13 20:39 ` [net-next v2 06/15] net/mlx5: Handle SW reset of FW in error flow Saeed Mahameed
2019-06-13 20:39 ` [net-next v2 07/15] net/mlx5: Control CR-space access by different PFs Saeed Mahameed
2019-06-13 20:39 ` [net-next v2 08/15] net/mlx5: Issue SW reset on FW assert Saeed Mahameed
2019-06-13 20:39 ` [net-next v2 09/15] net/mlx5: Create FW devlink_health_reporter Saeed Mahameed
2019-06-13 20:39 ` [net-next v2 10/15] net/mlx5: Add support for FW reporter dump Saeed Mahameed
2019-06-13 20:39 ` [net-next v2 11/15] net/mlx5: Report devlink health on FW issues Saeed Mahameed
2019-06-13 20:39 ` [net-next v2 12/15] net/mlx5: Add fw fatal devlink_health_reporter Saeed Mahameed
2019-06-13 20:39 ` [net-next v2 13/15] net/mlx5: Add support for FW fatal reporter dump Saeed Mahameed
2019-06-13 20:39 ` [net-next v2 14/15] net/mlx5: Report devlink health on FW fatal issues Saeed Mahameed
2019-06-13 20:39 ` [net-next v2 15/15] Documentation: net: mlx5: Devlink health documentation Saeed Mahameed
2019-06-15 2:46 ` [pull request][net-next v2 00/15] Mellanox, mlx5 Firmware devlink health and sw reset David Miller
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190613203825.31049-6-saeedm@mellanox.com \
--to=saeedm@mellanox.com \
--cc=davem@davemloft.net \
--cc=ferasda@mellanox.com \
--cc=jiri@mellanox.com \
--cc=moshe@mellanox.com \
--cc=netdev@vger.kernel.org \
--cc=valex@mellanox.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).