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>,
Feras Daoud <ferasda@mellanox.com>,
Saeed Mahameed <saeedm@mellanox.com>,
Alex Vesker <valex@mellanox.com>
Subject: [net-next 06/15] net/mlx5: Control CR-space access by different PFs
Date: Sun, 5 May 2019 00:33:06 +0000 [thread overview]
Message-ID: <20190505003207.1353-7-saeedm@mellanox.com> (raw)
In-Reply-To: <20190505003207.1353-1-saeedm@mellanox.com>
From: Feras Daoud <ferasda@mellanox.com>
Since the FW can be shared between different PFs/VFs it is common
that more than one health poll will detected a failure, this can
lead to multiple resets which are unneeded.
The solution is to use a FW locking mechanism using semaphore space
to provide a way to allow only one device to collect the cr-dump and
to issue a sw-reset.
Signed-off-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../ethernet/mellanox/mlx5/core/lib/pci_vsc.c | 40 ++++++++++++++++---
.../ethernet/mellanox/mlx5/core/lib/pci_vsc.h | 8 ++++
.../ethernet/mellanox/mlx5/core/mlx5_core.h | 4 ++
3 files changed, 47 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c
index f42890bdd6b1..b6b8fb13f621 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c
@@ -24,11 +24,6 @@
pci_write_config_dword((dev)->pdev, (dev)->vsc_addr + (offset), (val))
#define VSC_MAX_RETRIES 2048
-enum mlx5_vsc_state {
- MLX5_VSC_UNLOCK,
- MLX5_VSC_LOCK,
-};
-
enum {
VSC_CTRL_OFFSET = 0x4,
VSC_COUNTER_OFFSET = 0x8,
@@ -281,3 +276,38 @@ int mlx5_vsc_gw_read_block_fast(struct mlx5_core_dev *dev, u32 *data,
}
return length;
}
+
+int mlx5_vsc_sem_set_space(struct mlx5_core_dev *dev, u16 space,
+ enum mlx5_vsc_state state)
+{
+ u32 data, id = 0;
+ int ret;
+
+ ret = mlx5_vsc_gw_set_space(dev, MLX5_SEMAPHORE_SPACE_DOMAIN, NULL);
+ if (ret) {
+ mlx5_core_warn(dev, "Failed to set gw space %d\n", ret);
+ return ret;
+ }
+
+ if (state == MLX5_VSC_LOCK) {
+ /* Get a unique ID based on the counter */
+ ret = vsc_read(dev, VSC_COUNTER_OFFSET, &id);
+ if (ret)
+ return ret;
+ }
+
+ /* Try to modify lock */
+ ret = mlx5_vsc_gw_write(dev, space, id);
+ if (ret)
+ return ret;
+
+ /* Verify lock was modified */
+ ret = mlx5_vsc_gw_read(dev, space, &data);
+ if (ret)
+ return -EINVAL;
+
+ if (data != id)
+ return -EBUSY;
+
+ return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.h
index c6ebf59006c5..4264b65f7437 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.h
@@ -4,6 +4,11 @@
#ifndef __MLX5_PCI_VSC_H__
#define __MLX5_PCI_VSC_H__
+enum mlx5_vsc_state {
+ MLX5_VSC_UNLOCK,
+ MLX5_VSC_LOCK,
+};
+
enum {
MLX5_VSC_SPACE_SCAN_CRSPACE = 0x7,
};
@@ -22,4 +27,7 @@ static inline bool mlx5_vsc_accessible(struct mlx5_core_dev *dev)
return !!dev->vsc_addr;
}
+int mlx5_vsc_sem_set_space(struct mlx5_core_dev *dev, u16 space,
+ enum mlx5_vsc_state state);
+
#endif /* __MLX5_PCI_VSC_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index d31b77ad533d..439cf23945a4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -111,6 +111,10 @@ enum {
MLX5_DRIVER_SYND = 0xbadd00de,
};
+enum mlx5_semaphore_space_address {
+ MLX5_SEMAPHORE_SPACE_DOMAIN = 0xA,
+};
+
int mlx5_query_hca_caps(struct mlx5_core_dev *dev);
int mlx5_query_board_id(struct mlx5_core_dev *dev);
int mlx5_cmd_init_hca(struct mlx5_core_dev *dev, uint32_t *sw_owner_id);
--
2.20.1
next prev parent reply other threads:[~2019-05-05 0:33 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-05 0:32 [pull request][net-next 00/15] Mellanox, mlx5 Firmware devlink health and sw reset Saeed Mahameed
2019-05-05 0:32 ` [net-next 01/15] net/mlx5: Move all devlink related functions calls to devlink.c Saeed Mahameed
2019-05-05 0:32 ` [net-next 02/15] net/mlx5: Add Vendor Specific Capability access gateway Saeed Mahameed
2019-05-05 0:33 ` [net-next 03/15] net/mlx5: Add Crdump FW snapshot support Saeed Mahameed
2019-05-05 15:36 ` Jiri Pirko
2019-05-05 0:33 ` [net-next 04/15] net/mlx5: Add support for devlink region_snapshot parameter Saeed Mahameed
2019-05-05 0:33 ` [net-next 05/15] net/mlx5: Handle SW reset of FW in error flow Saeed Mahameed
2019-05-05 0:33 ` Saeed Mahameed [this message]
2019-05-05 0:33 ` [net-next 07/15] net/mlx5: Issue SW reset on FW assert Saeed Mahameed
2019-05-05 15:38 ` Jiri Pirko
2019-05-06 10:44 ` Moshe Shemesh
2019-05-05 0:33 ` [net-next 08/15] net/mlx5: Refactor print health info Saeed Mahameed
2019-05-05 15:42 ` Jiri Pirko
2019-05-05 0:33 ` [net-next 09/15] net/mlx5: Create FW devlink health reporter Saeed Mahameed
2019-05-05 15:42 ` Jiri Pirko
2019-05-06 10:45 ` Moshe Shemesh
2019-05-06 11:38 ` Jiri Pirko
2019-05-06 19:52 ` Saeed Mahameed
2019-05-06 21:46 ` Alexei Starovoitov
2019-05-07 5:59 ` Jiri Pirko
2019-05-07 6:01 ` Jiri Pirko
2019-05-07 0:11 ` Jakub Kicinski
2019-05-05 0:33 ` [net-next 10/15] net/mlx5: Add core dump register access functions Saeed Mahameed
2019-05-05 0:33 ` [net-next 11/15] net/mlx5: Add support for FW reporter dump Saeed Mahameed
2019-05-05 15:49 ` Jiri Pirko
2019-05-06 10:51 ` Moshe Shemesh
2019-05-06 11:37 ` Jiri Pirko
2019-05-05 0:33 ` [net-next 12/15] net/mlx5: Report devlink health on FW issues Saeed Mahameed
2019-05-05 0:33 ` [net-next 13/15] net/mlx5: Add fw fatal devlink health reporter Saeed Mahameed
2019-05-05 0:33 ` [net-next 14/15] net/mlx5: Add support for FW fatal reporter dump Saeed Mahameed
2019-05-05 15:52 ` Jiri Pirko
2019-05-06 10:54 ` Moshe Shemesh
2019-05-06 11:42 ` Jiri Pirko
2019-05-05 0:33 ` [net-next 15/15] net/mlx5: Report devlink health on FW fatal issues Saeed Mahameed
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=20190505003207.1353-7-saeedm@mellanox.com \
--to=saeedm@mellanox.com \
--cc=davem@davemloft.net \
--cc=ferasda@mellanox.com \
--cc=jiri@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).