* [PATCH net-next v3 01/11] devlink: Add support for creating and destroying regions
From: Alex Vesker @ 2018-07-12 12:13 UTC (permalink / raw)
To: netdev, jiri
Cc: dsahern, andrew, rahul.lakkireddy, jakub.kicinski, Alex Vesker
In-Reply-To: <1531397598-11207-1-git-send-email-valex@mellanox.com>
This allows a device to register its supported address regions.
Each address region can be accessed directly for example reading
the snapshots taken of this address space.
Drivers are not limited in the name selection for different regions.
An example of a region-name can be: pci cr-space, register-space.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
include/net/devlink.h | 22 ++++++++++++++
net/core/devlink.c | 84 +++++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 106 insertions(+)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index f67c29c..e539765 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -28,6 +28,7 @@ struct devlink {
struct list_head dpipe_table_list;
struct list_head resource_list;
struct list_head param_list;
+ struct list_head region_list;
struct devlink_dpipe_headers *dpipe_headers;
const struct devlink_ops *ops;
struct device *dev;
@@ -397,6 +398,8 @@ enum devlink_param_generic_id {
.validate = _validate, \
}
+struct devlink_region;
+
struct devlink_ops {
int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack);
int (*port_type_set)(struct devlink_port *devlink_port,
@@ -543,6 +546,11 @@ int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id,
int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id,
union devlink_param_value init_val);
void devlink_param_value_changed(struct devlink *devlink, u32 param_id);
+struct devlink_region *devlink_region_create(struct devlink *devlink,
+ const char *region_name,
+ u32 region_max_snapshots,
+ u64 region_size);
+void devlink_region_destroy(struct devlink_region *region);
#else
@@ -770,6 +778,20 @@ static inline bool devlink_dpipe_table_counter_enabled(struct devlink *devlink,
{
}
+static inline struct devlink_region *
+devlink_region_create(struct devlink *devlink,
+ const char *region_name,
+ u32 region_max_snapshots,
+ u64 region_size)
+{
+ return NULL;
+}
+
+static inline void
+devlink_region_destroy(struct devlink_region *region)
+{
+}
+
#endif
#endif /* _NET_DEVLINK_H_ */
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 470f3db..cac8561 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -326,6 +326,28 @@ static int devlink_sb_pool_index_get_from_info(struct devlink_sb *devlink_sb,
pool_type, p_tc_index);
}
+struct devlink_region {
+ struct devlink *devlink;
+ struct list_head list;
+ const char *name;
+ struct list_head snapshot_list;
+ u32 max_snapshots;
+ u32 cur_snapshots;
+ u64 size;
+};
+
+static struct devlink_region *
+devlink_region_get_by_name(struct devlink *devlink, const char *region_name)
+{
+ struct devlink_region *region;
+
+ list_for_each_entry(region, &devlink->region_list, list)
+ if (!strcmp(region->name, region_name))
+ return region;
+
+ return NULL;
+}
+
#define DEVLINK_NL_FLAG_NEED_DEVLINK BIT(0)
#define DEVLINK_NL_FLAG_NEED_PORT BIT(1)
#define DEVLINK_NL_FLAG_NEED_SB BIT(2)
@@ -3358,6 +3380,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list);
INIT_LIST_HEAD(&devlink->resource_list);
INIT_LIST_HEAD(&devlink->param_list);
+ INIT_LIST_HEAD(&devlink->region_list);
mutex_init(&devlink->lock);
return devlink;
}
@@ -4109,6 +4132,67 @@ void devlink_param_value_changed(struct devlink *devlink, u32 param_id)
}
EXPORT_SYMBOL_GPL(devlink_param_value_changed);
+/**
+ * devlink_region_create - create a new address region
+ *
+ * @devlink: devlink
+ * @region_name: region name
+ * @region_max_snapshots: Maximum supported number of snapshots for region
+ * @region_size: size of region
+ */
+struct devlink_region *devlink_region_create(struct devlink *devlink,
+ const char *region_name,
+ u32 region_max_snapshots,
+ u64 region_size)
+{
+ struct devlink_region *region;
+ int err = 0;
+
+ mutex_lock(&devlink->lock);
+
+ if (devlink_region_get_by_name(devlink, region_name)) {
+ err = -EEXIST;
+ goto unlock;
+ }
+
+ region = kzalloc(sizeof(*region), GFP_KERNEL);
+ if (!region) {
+ err = -ENOMEM;
+ goto unlock;
+ }
+
+ region->devlink = devlink;
+ region->max_snapshots = region_max_snapshots;
+ region->name = region_name;
+ region->size = region_size;
+ INIT_LIST_HEAD(®ion->snapshot_list);
+ list_add_tail(®ion->list, &devlink->region_list);
+
+ mutex_unlock(&devlink->lock);
+ return region;
+
+unlock:
+ mutex_unlock(&devlink->lock);
+ return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(devlink_region_create);
+
+/**
+ * devlink_region_destroy - destroy address region
+ *
+ * @region: devlink region to destroy
+ */
+void devlink_region_destroy(struct devlink_region *region)
+{
+ struct devlink *devlink = region->devlink;
+
+ mutex_lock(&devlink->lock);
+ list_del(®ion->list);
+ mutex_unlock(&devlink->lock);
+ kfree(region);
+}
+EXPORT_SYMBOL_GPL(devlink_region_destroy);
+
static int __init devlink_module_init(void)
{
return genl_register_family(&devlink_nl_family);
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next v3 04/11] devlink: Add support for region get command
From: Alex Vesker @ 2018-07-12 12:13 UTC (permalink / raw)
To: netdev, jiri
Cc: dsahern, andrew, rahul.lakkireddy, jakub.kicinski, Alex Vesker
In-Reply-To: <1531397598-11207-1-git-send-email-valex@mellanox.com>
Add support for DEVLINK_CMD_REGION_GET command which is used for
querying for the supported DEV/REGION values of devlink devices.
The support is both for doit and dumpit.
Reply includes:
BUS_NAME, DEVICE_NAME, REGION_NAME, REGION_SIZE
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
include/uapi/linux/devlink.h | 6 +++
net/core/devlink.c | 114 +++++++++++++++++++++++++++++++++++++++++++
2 files changed, 120 insertions(+)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 68641fb..28bfa8a 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -83,6 +83,9 @@ enum devlink_command {
DEVLINK_CMD_PARAM_NEW,
DEVLINK_CMD_PARAM_DEL,
+ DEVLINK_CMD_REGION_GET,
+ DEVLINK_CMD_REGION_SET,
+
/* add new commands above here */
__DEVLINK_CMD_MAX,
DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
@@ -262,6 +265,9 @@ enum devlink_attr {
DEVLINK_ATTR_PARAM_VALUE_DATA, /* dynamic */
DEVLINK_ATTR_PARAM_VALUE_CMODE, /* u8 */
+ DEVLINK_ATTR_REGION_NAME, /* string */
+ DEVLINK_ATTR_REGION_SIZE, /* u64 */
+
/* add new attributes above here, update the policy in devlink.c */
__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 7d09fe6..221ddb6 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3149,6 +3149,111 @@ static void devlink_param_unregister_one(struct devlink *devlink,
kfree(param_item);
}
+static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink,
+ enum devlink_command cmd, u32 portid,
+ u32 seq, int flags,
+ struct devlink_region *region)
+{
+ void *hdr;
+ int err;
+
+ hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+ if (!hdr)
+ return -EMSGSIZE;
+
+ err = devlink_nl_put_handle(msg, devlink);
+ if (err)
+ goto nla_put_failure;
+
+ err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->name);
+ if (err)
+ goto nla_put_failure;
+
+ err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_SIZE,
+ region->size,
+ DEVLINK_ATTR_PAD);
+ if (err)
+ goto nla_put_failure;
+
+ genlmsg_end(msg, hdr);
+ return 0;
+
+nla_put_failure:
+ genlmsg_cancel(msg, hdr);
+ return err;
+}
+
+static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ struct devlink_region *region;
+ const char *region_name;
+ struct sk_buff *msg;
+ int err;
+
+ if (!info->attrs[DEVLINK_ATTR_REGION_NAME])
+ return -EINVAL;
+
+ region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]);
+ region = devlink_region_get_by_name(devlink, region_name);
+ if (!region)
+ return -EINVAL;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ err = devlink_nl_region_fill(msg, devlink, DEVLINK_CMD_REGION_GET,
+ info->snd_portid, info->snd_seq, 0,
+ region);
+ if (err) {
+ nlmsg_free(msg);
+ return err;
+ }
+
+ return genlmsg_reply(msg, info);
+}
+
+static int devlink_nl_cmd_region_get_dumpit(struct sk_buff *msg,
+ struct netlink_callback *cb)
+{
+ struct devlink_region *region;
+ struct devlink *devlink;
+ int start = cb->args[0];
+ int idx = 0;
+ int err;
+
+ mutex_lock(&devlink_mutex);
+ list_for_each_entry(devlink, &devlink_list, list) {
+ if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
+ continue;
+
+ mutex_lock(&devlink->lock);
+ list_for_each_entry(region, &devlink->region_list, list) {
+ if (idx < start) {
+ idx++;
+ continue;
+ }
+ err = devlink_nl_region_fill(msg, devlink,
+ DEVLINK_CMD_REGION_GET,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NLM_F_MULTI, region);
+ if (err) {
+ mutex_unlock(&devlink->lock);
+ goto out;
+ }
+ idx++;
+ }
+ mutex_unlock(&devlink->lock);
+ }
+out:
+ mutex_unlock(&devlink_mutex);
+ cb->args[0] = idx;
+ return msg->len;
+}
+
static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING },
[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING },
@@ -3172,6 +3277,7 @@ static void devlink_param_unregister_one(struct devlink *devlink,
[DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING },
[DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8 },
[DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING },
};
static const struct genl_ops devlink_nl_ops[] = {
@@ -3370,6 +3476,14 @@ static void devlink_param_unregister_one(struct devlink *devlink,
.flags = GENL_ADMIN_PERM,
.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
},
+ {
+ .cmd = DEVLINK_CMD_REGION_GET,
+ .doit = devlink_nl_cmd_region_get_doit,
+ .dumpit = devlink_nl_cmd_region_get_dumpit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
};
static struct genl_family devlink_nl_family __ro_after_init = {
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next v3 05/11] devlink: Extend the support querying for region snapshot IDs
From: Alex Vesker @ 2018-07-12 12:13 UTC (permalink / raw)
To: netdev, jiri
Cc: dsahern, andrew, rahul.lakkireddy, jakub.kicinski, Alex Vesker
In-Reply-To: <1531397598-11207-1-git-send-email-valex@mellanox.com>
Extend the support for DEVLINK_CMD_REGION_GET command to also
return the IDs of the snapshot currently present on the region.
Each reply will include a nested snapshots attribute that
can contain multiple snapshot attributes each with an ID.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
include/uapi/linux/devlink.h | 3 +++
net/core/devlink.c | 53 ++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 56 insertions(+)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 28bfa8a..abde4e3 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -267,6 +267,9 @@ enum devlink_attr {
DEVLINK_ATTR_REGION_NAME, /* string */
DEVLINK_ATTR_REGION_SIZE, /* u64 */
+ DEVLINK_ATTR_REGION_SNAPSHOTS, /* nested */
+ DEVLINK_ATTR_REGION_SNAPSHOT, /* nested */
+ DEVLINK_ATTR_REGION_SNAPSHOT_ID, /* u32 */
/* add new attributes above here, update the policy in devlink.c */
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 221ddb6..cb75e26 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3149,6 +3149,55 @@ static void devlink_param_unregister_one(struct devlink *devlink,
kfree(param_item);
}
+static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg,
+ struct devlink *devlink,
+ struct devlink_snapshot *snapshot)
+{
+ struct nlattr *snap_attr;
+ int err;
+
+ snap_attr = nla_nest_start(msg, DEVLINK_ATTR_REGION_SNAPSHOT);
+ if (!snap_attr)
+ return -EINVAL;
+
+ err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID, snapshot->id);
+ if (err)
+ goto nla_put_failure;
+
+ nla_nest_end(msg, snap_attr);
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(msg, snap_attr);
+ return err;
+}
+
+static int devlink_nl_region_snapshots_id_put(struct sk_buff *msg,
+ struct devlink *devlink,
+ struct devlink_region *region)
+{
+ struct devlink_snapshot *snapshot;
+ struct nlattr *snapshots_attr;
+ int err;
+
+ snapshots_attr = nla_nest_start(msg, DEVLINK_ATTR_REGION_SNAPSHOTS);
+ if (!snapshots_attr)
+ return -EINVAL;
+
+ list_for_each_entry(snapshot, ®ion->snapshot_list, list) {
+ err = devlink_nl_region_snapshot_id_put(msg, devlink, snapshot);
+ if (err)
+ goto nla_put_failure;
+ }
+
+ nla_nest_end(msg, snapshots_attr);
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(msg, snapshots_attr);
+ return err;
+}
+
static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink,
enum devlink_command cmd, u32 portid,
u32 seq, int flags,
@@ -3175,6 +3224,10 @@ static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink,
if (err)
goto nla_put_failure;
+ err = devlink_nl_region_snapshots_id_put(msg, devlink, region);
+ if (err)
+ goto nla_put_failure;
+
genlmsg_end(msg, hdr);
return 0;
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next v3 08/11] net/mlx4_core: Add health buffer address capability
From: Alex Vesker @ 2018-07-12 12:13 UTC (permalink / raw)
To: netdev, jiri
Cc: dsahern, andrew, rahul.lakkireddy, jakub.kicinski, Alex Vesker,
Tariq Toukan
In-Reply-To: <1531397598-11207-1-git-send-email-valex@mellanox.com>
Health buffer address is a 32 bit PCI address offset provided by
the FW. This offset is used for reading FW health debug data
located on the shared CR space. Cr space is accessible in both
driver and FW and allows for different queries and configurations.
Health buffer size is always 64B of readable data followed by a
lock which is used to block volatile CR space access.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/fw.c | 5 ++++-
drivers/net/ethernet/mellanox/mlx4/fw.h | 1 +
drivers/net/ethernet/mellanox/mlx4/main.c | 1 +
include/linux/mlx4/device.h | 1 +
4 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 46dcbfb..babcfd9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -825,7 +825,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
#define QUERY_DEV_CAP_QP_RATE_LIMIT_NUM_OFFSET 0xcc
#define QUERY_DEV_CAP_QP_RATE_LIMIT_MAX_OFFSET 0xd0
#define QUERY_DEV_CAP_QP_RATE_LIMIT_MIN_OFFSET 0xd2
-
+#define QUERY_DEV_CAP_HEALTH_BUFFER_ADDRESS_OFFSET 0xe4
dev_cap->flags2 = 0;
mailbox = mlx4_alloc_cmd_mailbox(dev);
@@ -1082,6 +1082,9 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
dev_cap->rl_caps.min_unit = size >> 14;
}
+ MLX4_GET(dev_cap->health_buffer_addrs, outbox,
+ QUERY_DEV_CAP_HEALTH_BUFFER_ADDRESS_OFFSET);
+
MLX4_GET(field32, outbox, QUERY_DEV_CAP_EXT_2_FLAGS_OFFSET);
if (field32 & (1 << 16))
dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_UPDATE_QP;
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index cd6399c..650ae08 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -128,6 +128,7 @@ struct mlx4_dev_cap {
u32 dmfs_high_rate_qpn_base;
u32 dmfs_high_rate_qpn_range;
struct mlx4_rate_limit_caps rl_caps;
+ u32 health_buffer_addrs;
struct mlx4_port_cap port_cap[MLX4_MAX_PORTS + 1];
bool wol_port[MLX4_MAX_PORTS + 1];
};
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index c42eddf..806d441 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -523,6 +523,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
dev->caps.max_rss_tbl_sz = dev_cap->max_rss_tbl_sz;
dev->caps.wol_port[1] = dev_cap->wol_port[1];
dev->caps.wol_port[2] = dev_cap->wol_port[2];
+ dev->caps.health_buffer_addrs = dev_cap->health_buffer_addrs;
/* Save uar page shift */
if (!mlx4_is_slave(dev)) {
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 122e7e9..e3bfe76 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -630,6 +630,7 @@ struct mlx4_caps {
u32 vf_caps;
bool wol_port[MLX4_MAX_PORTS + 1];
struct mlx4_rate_limit_caps rl_caps;
+ u32 health_buffer_addrs;
};
struct mlx4_buf_list {
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next v3 06/11] devlink: Add support for region snapshot delete command
From: Alex Vesker @ 2018-07-12 12:13 UTC (permalink / raw)
To: netdev, jiri
Cc: dsahern, andrew, rahul.lakkireddy, jakub.kicinski, Alex Vesker
In-Reply-To: <1531397598-11207-1-git-send-email-valex@mellanox.com>
Add support for DEVLINK_CMD_REGION_DEL used
for deleting a snapshot from a region. The snapshot ID is required.
Also added notification support for NEW and DEL of snapshots.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
include/uapi/linux/devlink.h | 2 +
net/core/devlink.c | 93 ++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 95 insertions(+)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index abde4e3..d212e02 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -85,6 +85,8 @@ enum devlink_command {
DEVLINK_CMD_REGION_GET,
DEVLINK_CMD_REGION_SET,
+ DEVLINK_CMD_REGION_NEW,
+ DEVLINK_CMD_REGION_DEL,
/* add new commands above here */
__DEVLINK_CMD_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index cb75e26..fc08363 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3236,6 +3236,58 @@ static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink,
return err;
}
+static void devlink_nl_region_notify(struct devlink_region *region,
+ struct devlink_snapshot *snapshot,
+ enum devlink_command cmd)
+{
+ struct devlink *devlink = region->devlink;
+ struct sk_buff *msg;
+ void *hdr;
+ int err;
+
+ WARN_ON(cmd != DEVLINK_CMD_REGION_NEW && cmd != DEVLINK_CMD_REGION_DEL);
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return;
+
+ hdr = genlmsg_put(msg, 0, 0, &devlink_nl_family, 0, cmd);
+ if (!hdr)
+ goto out_free_msg;
+
+ err = devlink_nl_put_handle(msg, devlink);
+ if (err)
+ goto out_cancel_msg;
+
+ err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME,
+ region->name);
+ if (err)
+ goto out_cancel_msg;
+
+ if (snapshot) {
+ err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID,
+ snapshot->id);
+ if (err)
+ goto out_cancel_msg;
+ } else {
+ err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_SIZE,
+ region->size, DEVLINK_ATTR_PAD);
+ if (err)
+ goto out_cancel_msg;
+ }
+ genlmsg_end(msg, hdr);
+
+ genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+ msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+
+ return;
+
+out_cancel_msg:
+ genlmsg_cancel(msg, hdr);
+out_free_msg:
+ nlmsg_free(msg);
+}
+
static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb,
struct genl_info *info)
{
@@ -3307,6 +3359,35 @@ static int devlink_nl_cmd_region_get_dumpit(struct sk_buff *msg,
return msg->len;
}
+static int devlink_nl_cmd_region_del(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ struct devlink_snapshot *snapshot;
+ struct devlink_region *region;
+ const char *region_name;
+ u32 snapshot_id;
+
+ if (!info->attrs[DEVLINK_ATTR_REGION_NAME] ||
+ !info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID])
+ return -EINVAL;
+
+ region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]);
+ snapshot_id = nla_get_u32(info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]);
+
+ region = devlink_region_get_by_name(devlink, region_name);
+ if (!region)
+ return -EINVAL;
+
+ snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id);
+ if (!snapshot)
+ return -EINVAL;
+
+ devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_DEL);
+ devlink_region_snapshot_del(snapshot);
+ return 0;
+}
+
static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING },
[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING },
@@ -3331,6 +3412,7 @@ static int devlink_nl_cmd_region_get_dumpit(struct sk_buff *msg,
[DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8 },
[DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 },
[DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING },
+ [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 },
};
static const struct genl_ops devlink_nl_ops[] = {
@@ -3537,6 +3619,13 @@ static int devlink_nl_cmd_region_get_dumpit(struct sk_buff *msg,
.flags = GENL_ADMIN_PERM,
.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
},
+ {
+ .cmd = DEVLINK_CMD_REGION_DEL,
+ .doit = devlink_nl_cmd_region_del,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
};
static struct genl_family devlink_nl_family __ro_after_init = {
@@ -4363,6 +4452,7 @@ struct devlink_region *devlink_region_create(struct devlink *devlink,
region->size = region_size;
INIT_LIST_HEAD(®ion->snapshot_list);
list_add_tail(®ion->list, &devlink->region_list);
+ devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW);
mutex_unlock(&devlink->lock);
return region;
@@ -4390,6 +4480,8 @@ void devlink_region_destroy(struct devlink_region *region)
devlink_region_snapshot_del(snapshot);
list_del(®ion->list);
+
+ devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL);
mutex_unlock(&devlink->lock);
kfree(region);
}
@@ -4467,6 +4559,7 @@ int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len,
region->cur_snapshots++;
+ devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_NEW);
mutex_unlock(&devlink->lock);
return 0;
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next v3 07/11] devlink: Add support for region snapshot read command
From: Alex Vesker @ 2018-07-12 12:13 UTC (permalink / raw)
To: netdev, jiri
Cc: dsahern, andrew, rahul.lakkireddy, jakub.kicinski, Alex Vesker
In-Reply-To: <1531397598-11207-1-git-send-email-valex@mellanox.com>
Add support for DEVLINK_CMD_REGION_READ_GET used for both reading
and dumping region data. Read allows reading from a region specific
address for given length. Dump allows reading the full region.
If only snapshot ID is provided a snapshot dump will be done.
If snapshot ID, Address and Length are provided a snapshot read
will done.
This is used for both snapshot access and will be used in the same
way to access current data on the region.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
include/uapi/linux/devlink.h | 7 ++
net/core/devlink.c | 182 +++++++++++++++++++++++++++++++++++++++++++
2 files changed, 189 insertions(+)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index d212e02..79407bb 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -87,6 +87,7 @@ enum devlink_command {
DEVLINK_CMD_REGION_SET,
DEVLINK_CMD_REGION_NEW,
DEVLINK_CMD_REGION_DEL,
+ DEVLINK_CMD_REGION_READ,
/* add new commands above here */
__DEVLINK_CMD_MAX,
@@ -273,6 +274,12 @@ enum devlink_attr {
DEVLINK_ATTR_REGION_SNAPSHOT, /* nested */
DEVLINK_ATTR_REGION_SNAPSHOT_ID, /* u32 */
+ DEVLINK_ATTR_REGION_CHUNKS, /* nested */
+ DEVLINK_ATTR_REGION_CHUNK, /* nested */
+ DEVLINK_ATTR_REGION_CHUNK_DATA, /* binary */
+ DEVLINK_ATTR_REGION_CHUNK_ADDR, /* u64 */
+ DEVLINK_ATTR_REGION_CHUNK_LEN, /* u64 */
+
/* add new attributes above here, update the policy in devlink.c */
__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index fc08363..e5118db 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3388,6 +3388,181 @@ static int devlink_nl_cmd_region_del(struct sk_buff *skb,
return 0;
}
+static int devlink_nl_cmd_region_read_chunk_fill(struct sk_buff *msg,
+ struct devlink *devlink,
+ u8 *chunk, u32 chunk_size,
+ u64 addr)
+{
+ struct nlattr *chunk_attr;
+ int err;
+
+ chunk_attr = nla_nest_start(msg, DEVLINK_ATTR_REGION_CHUNK);
+ if (!chunk_attr)
+ return -EINVAL;
+
+ err = nla_put(msg, DEVLINK_ATTR_REGION_CHUNK_DATA, chunk_size, chunk);
+ if (err)
+ goto nla_put_failure;
+
+ err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_CHUNK_ADDR, addr,
+ DEVLINK_ATTR_PAD);
+ if (err)
+ goto nla_put_failure;
+
+ nla_nest_end(msg, chunk_attr);
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(msg, chunk_attr);
+ return err;
+}
+
+#define DEVLINK_REGION_READ_CHUNK_SIZE 256
+
+static int devlink_nl_region_read_snapshot_fill(struct sk_buff *skb,
+ struct devlink *devlink,
+ struct devlink_region *region,
+ struct nlattr **attrs,
+ u64 start_offset,
+ u64 end_offset,
+ bool dump,
+ u64 *new_offset)
+{
+ struct devlink_snapshot *snapshot;
+ u64 curr_offset = start_offset;
+ u32 snapshot_id;
+ int err = 0;
+
+ *new_offset = start_offset;
+
+ snapshot_id = nla_get_u32(attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]);
+ snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id);
+ if (!snapshot)
+ return -EINVAL;
+
+ if (end_offset > snapshot->data_len || dump)
+ end_offset = snapshot->data_len;
+
+ while (curr_offset < end_offset) {
+ u32 data_size;
+ u8 *data;
+
+ if (end_offset - curr_offset < DEVLINK_REGION_READ_CHUNK_SIZE)
+ data_size = end_offset - curr_offset;
+ else
+ data_size = DEVLINK_REGION_READ_CHUNK_SIZE;
+
+ data = &snapshot->data[curr_offset];
+ err = devlink_nl_cmd_region_read_chunk_fill(skb, devlink,
+ data, data_size,
+ curr_offset);
+ if (err)
+ break;
+
+ curr_offset += data_size;
+ }
+ *new_offset = curr_offset;
+
+ return err;
+}
+
+static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ u64 ret_offset, start_offset, end_offset = 0;
+ struct nlattr *attrs[DEVLINK_ATTR_MAX + 1];
+ const struct genl_ops *ops = cb->data;
+ struct devlink_region *region;
+ struct nlattr *chunks_attr;
+ const char *region_name;
+ struct devlink *devlink;
+ bool dump = true;
+ void *hdr;
+ int err;
+
+ start_offset = *((u64 *)&cb->args[0]);
+
+ err = nlmsg_parse(cb->nlh, GENL_HDRLEN + devlink_nl_family.hdrsize,
+ attrs, DEVLINK_ATTR_MAX, ops->policy, NULL);
+ if (err)
+ goto out;
+
+ devlink = devlink_get_from_attrs(sock_net(cb->skb->sk), attrs);
+ if (IS_ERR(devlink))
+ goto out;
+
+ mutex_lock(&devlink_mutex);
+ mutex_lock(&devlink->lock);
+
+ if (!attrs[DEVLINK_ATTR_REGION_NAME] ||
+ !attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID])
+ goto out_unlock;
+
+ region_name = nla_data(attrs[DEVLINK_ATTR_REGION_NAME]);
+ region = devlink_region_get_by_name(devlink, region_name);
+ if (!region)
+ goto out_unlock;
+
+ hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+ &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI,
+ DEVLINK_CMD_REGION_READ);
+ if (!hdr)
+ goto out_unlock;
+
+ err = devlink_nl_put_handle(skb, devlink);
+ if (err)
+ goto nla_put_failure;
+
+ err = nla_put_string(skb, DEVLINK_ATTR_REGION_NAME, region_name);
+ if (err)
+ goto nla_put_failure;
+
+ chunks_attr = nla_nest_start(skb, DEVLINK_ATTR_REGION_CHUNKS);
+ if (!chunks_attr)
+ goto nla_put_failure;
+
+ if (attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR] &&
+ attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]) {
+ if (!start_offset)
+ start_offset =
+ nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]);
+
+ end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]);
+ end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]);
+ dump = false;
+ }
+
+ err = devlink_nl_region_read_snapshot_fill(skb, devlink,
+ region, attrs,
+ start_offset,
+ end_offset, dump,
+ &ret_offset);
+
+ if (err && err != -EMSGSIZE)
+ goto nla_put_failure;
+
+ /* Check if there was any progress done to prevent infinite loop */
+ if (ret_offset == start_offset)
+ goto nla_put_failure;
+
+ *((u64 *)&cb->args[0]) = ret_offset;
+
+ nla_nest_end(skb, chunks_attr);
+ genlmsg_end(skb, hdr);
+ mutex_unlock(&devlink->lock);
+ mutex_unlock(&devlink_mutex);
+
+ return skb->len;
+
+nla_put_failure:
+ genlmsg_cancel(skb, hdr);
+out_unlock:
+ mutex_unlock(&devlink->lock);
+ mutex_unlock(&devlink_mutex);
+out:
+ return 0;
+}
+
static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING },
[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING },
@@ -3626,6 +3801,13 @@ static int devlink_nl_cmd_region_del(struct sk_buff *skb,
.flags = GENL_ADMIN_PERM,
.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
},
+ {
+ .cmd = DEVLINK_CMD_REGION_READ,
+ .dumpit = devlink_nl_cmd_region_read_dumpit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
};
static struct genl_family devlink_nl_family __ro_after_init = {
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next v3 09/11] net/mlx4_core: Add Crdump FW snapshot support
From: Alex Vesker @ 2018-07-12 12:13 UTC (permalink / raw)
To: netdev, jiri
Cc: dsahern, andrew, rahul.lakkireddy, jakub.kicinski, Alex Vesker,
Tariq Toukan
In-Reply-To: <1531397598-11207-1-git-send-email-valex@mellanox.com>
Crdump allows the driver to create a snapshot of the FW PCI
crspace and health buffer during a critical FW issue.
In case of a FW command timeout, FW getting stuck or a non zero
value on the catastrophic buffer, a snapshot will be taken.
The snapshot is exposed using devlink, cr-space, fw-health
address regions are registered on init and snapshots are attached
once a new snapshot is collected by the driver.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/Makefile | 2 +-
drivers/net/ethernet/mellanox/mlx4/catas.c | 6 +-
drivers/net/ethernet/mellanox/mlx4/crdump.c | 231 ++++++++++++++++++++++++++++
drivers/net/ethernet/mellanox/mlx4/main.c | 10 +-
drivers/net/ethernet/mellanox/mlx4/mlx4.h | 4 +
include/linux/mlx4/device.h | 6 +
6 files changed, 255 insertions(+), 4 deletions(-)
create mode 100644 drivers/net/ethernet/mellanox/mlx4/crdump.c
diff --git a/drivers/net/ethernet/mellanox/mlx4/Makefile b/drivers/net/ethernet/mellanox/mlx4/Makefile
index 16b10d0..3f40077 100644
--- a/drivers/net/ethernet/mellanox/mlx4/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx4/Makefile
@@ -3,7 +3,7 @@ obj-$(CONFIG_MLX4_CORE) += mlx4_core.o
mlx4_core-y := alloc.o catas.o cmd.o cq.o eq.o fw.o fw_qos.o icm.o intf.o \
main.o mcg.o mr.o pd.o port.o profile.o qp.o reset.o sense.o \
- srq.o resource_tracker.o
+ srq.o resource_tracker.o crdump.o
obj-$(CONFIG_MLX4_EN) += mlx4_en.o
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index 8afe4b5..c81d15b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -178,10 +178,12 @@ void mlx4_enter_error_state(struct mlx4_dev_persistent *persist)
dev = persist->dev;
mlx4_err(dev, "device is going to be reset\n");
- if (mlx4_is_slave(dev))
+ if (mlx4_is_slave(dev)) {
err = mlx4_reset_slave(dev);
- else
+ } else {
+ mlx4_crdump_collect(dev);
err = mlx4_reset_master(dev);
+ }
if (!err) {
mlx4_err(dev, "device was reset successfully\n");
diff --git a/drivers/net/ethernet/mellanox/mlx4/crdump.c b/drivers/net/ethernet/mellanox/mlx4/crdump.c
new file mode 100644
index 0000000..4d5524d
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx4/crdump.c
@@ -0,0 +1,231 @@
+/*
+ * Copyright (c) 2018, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "mlx4.h"
+
+#define BAD_ACCESS 0xBADACCE5
+#define HEALTH_BUFFER_SIZE 0x40
+#define CR_ENABLE_BIT swab32(BIT(6))
+#define CR_ENABLE_BIT_OFFSET 0xF3F04
+#define MAX_NUM_OF_DUMPS_TO_STORE (8)
+
+static const char *region_cr_space_str = "cr-space";
+static const char *region_fw_health_str = "fw-health";
+
+/* Set to true in case cr enable bit was set to true before crdump */
+static bool crdump_enbale_bit_set;
+
+static void crdump_enable_crspace_access(struct mlx4_dev *dev,
+ u8 __iomem *cr_space)
+{
+ /* Get current enable bit value */
+ crdump_enbale_bit_set =
+ readl(cr_space + CR_ENABLE_BIT_OFFSET) & CR_ENABLE_BIT;
+
+ /* Enable FW CR filter (set bit6 to 0) */
+ if (crdump_enbale_bit_set)
+ writel(readl(cr_space + CR_ENABLE_BIT_OFFSET) & ~CR_ENABLE_BIT,
+ cr_space + CR_ENABLE_BIT_OFFSET);
+
+ /* Enable block volatile crspace accesses */
+ writel(swab32(1), cr_space + dev->caps.health_buffer_addrs +
+ HEALTH_BUFFER_SIZE);
+}
+
+static void crdump_disable_crspace_access(struct mlx4_dev *dev,
+ u8 __iomem *cr_space)
+{
+ /* Disable block volatile crspace accesses */
+ writel(0, cr_space + dev->caps.health_buffer_addrs +
+ HEALTH_BUFFER_SIZE);
+
+ /* Restore FW CR filter value (set bit6 to original value) */
+ if (crdump_enbale_bit_set)
+ writel(readl(cr_space + CR_ENABLE_BIT_OFFSET) | CR_ENABLE_BIT,
+ cr_space + CR_ENABLE_BIT_OFFSET);
+}
+
+static void mlx4_crdump_collect_crspace(struct mlx4_dev *dev,
+ u8 __iomem *cr_space,
+ u32 id)
+{
+ struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+ struct pci_dev *pdev = dev->persist->pdev;
+ unsigned long cr_res_size;
+ u8 *crspace_data;
+ int offset;
+ int err;
+
+ if (!crdump->region_crspace) {
+ mlx4_err(dev, "crdump: cr-space region is NULL\n");
+ return;
+ }
+
+ /* Try to collect CR space */
+ cr_res_size = pci_resource_len(pdev, 0);
+ crspace_data = kvmalloc(cr_res_size, GFP_KERNEL);
+ if (crspace_data) {
+ for (offset = 0; offset < cr_res_size; offset += 4)
+ *(u32 *)(crspace_data + offset) =
+ readl(cr_space + offset);
+
+ err = devlink_region_snapshot_create(crdump->region_crspace,
+ cr_res_size, crspace_data,
+ id, &kvfree);
+ if (err) {
+ kvfree(crspace_data);
+ mlx4_warn(dev, "crdump: devlink create %s snapshot id %d err %d\n",
+ region_cr_space_str, id, err);
+ } else {
+ mlx4_info(dev, "crdump: added snapshot %d to devlink region %s\n",
+ id, region_cr_space_str);
+ }
+ } else {
+ mlx4_err(dev, "crdump: Failed to allocate crspace buffer\n");
+ }
+}
+
+static void mlx4_crdump_collect_fw_health(struct mlx4_dev *dev,
+ u8 __iomem *cr_space,
+ u32 id)
+{
+ struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+ u8 *health_data;
+ int offset;
+ int err;
+
+ if (!crdump->region_fw_health) {
+ mlx4_err(dev, "crdump: fw-health region is NULL\n");
+ return;
+ }
+
+ /* Try to collect health buffer */
+ health_data = kvmalloc(HEALTH_BUFFER_SIZE, GFP_KERNEL);
+ if (health_data) {
+ u8 __iomem *health_buf_start =
+ cr_space + dev->caps.health_buffer_addrs;
+
+ for (offset = 0; offset < HEALTH_BUFFER_SIZE; offset += 4)
+ *(u32 *)(health_data + offset) =
+ readl(health_buf_start + offset);
+
+ err = devlink_region_snapshot_create(crdump->region_fw_health,
+ HEALTH_BUFFER_SIZE,
+ health_data,
+ id, &kvfree);
+ if (err) {
+ kvfree(health_data);
+ mlx4_warn(dev, "crdump: devlink create %s snapshot id %d err %d\n",
+ region_fw_health_str, id, err);
+ } else {
+ mlx4_info(dev, "crdump: added snapshot %d to devlink region %s\n",
+ id, region_fw_health_str);
+ }
+ } else {
+ mlx4_err(dev, "crdump: Failed to allocate health buffer\n");
+ }
+}
+
+int mlx4_crdump_collect(struct mlx4_dev *dev)
+{
+ struct devlink *devlink = priv_to_devlink(mlx4_priv(dev));
+ struct pci_dev *pdev = dev->persist->pdev;
+ unsigned long cr_res_size;
+ u8 __iomem *cr_space;
+ u32 id;
+
+ if (!dev->caps.health_buffer_addrs) {
+ mlx4_info(dev, "crdump: FW doesn't support health buffer access, skipping\n");
+ return 0;
+ }
+
+ cr_res_size = pci_resource_len(pdev, 0);
+
+ cr_space = ioremap(pci_resource_start(pdev, 0), cr_res_size);
+ if (!cr_space) {
+ mlx4_err(dev, "crdump: Failed to map pci cr region\n");
+ return -ENODEV;
+ }
+
+ crdump_enable_crspace_access(dev, cr_space);
+
+ /* Get the available snapshot ID for the dumps */
+ id = devlink_region_shapshot_id_get(devlink);
+
+ /* Try to capture dumps */
+ mlx4_crdump_collect_crspace(dev, cr_space, id);
+ mlx4_crdump_collect_fw_health(dev, cr_space, id);
+
+ crdump_disable_crspace_access(dev, cr_space);
+
+ iounmap(cr_space);
+ return 0;
+}
+
+int mlx4_crdump_init(struct mlx4_dev *dev)
+{
+ struct devlink *devlink = priv_to_devlink(mlx4_priv(dev));
+ struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+ struct pci_dev *pdev = dev->persist->pdev;
+
+ /* Create cr-space region */
+ crdump->region_crspace =
+ devlink_region_create(devlink,
+ region_cr_space_str,
+ MAX_NUM_OF_DUMPS_TO_STORE,
+ pci_resource_len(pdev, 0));
+ if (IS_ERR(crdump->region_crspace))
+ mlx4_warn(dev, "crdump: create devlink region %s err %ld\n",
+ region_cr_space_str,
+ PTR_ERR(crdump->region_crspace));
+
+ /* Create fw-health region */
+ crdump->region_fw_health =
+ devlink_region_create(devlink,
+ region_fw_health_str,
+ MAX_NUM_OF_DUMPS_TO_STORE,
+ HEALTH_BUFFER_SIZE);
+ if (IS_ERR(crdump->region_fw_health))
+ mlx4_warn(dev, "crdump: create devlink region %s err %ld\n",
+ region_fw_health_str,
+ PTR_ERR(crdump->region_fw_health));
+
+ return 0;
+}
+
+void mlx4_crdump_end(struct mlx4_dev *dev)
+{
+ struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+
+ devlink_region_destroy(crdump->region_fw_health);
+ devlink_region_destroy(crdump->region_crspace);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 806d441..46b0214 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -3807,10 +3807,14 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data,
}
}
- err = mlx4_catas_init(&priv->dev);
+ err = mlx4_crdump_init(&priv->dev);
if (err)
goto err_release_regions;
+ err = mlx4_catas_init(&priv->dev);
+ if (err)
+ goto err_crdump;
+
err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv, 0);
if (err)
goto err_catas;
@@ -3820,6 +3824,9 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data,
err_catas:
mlx4_catas_end(&priv->dev);
+err_crdump:
+ mlx4_crdump_end(&priv->dev);
+
err_release_regions:
pci_release_regions(pdev);
@@ -4081,6 +4088,7 @@ static void mlx4_remove_one(struct pci_dev *pdev)
else
mlx4_info(dev, "%s: interface is down\n", __func__);
mlx4_catas_end(dev);
+ mlx4_crdump_end(dev);
if (dev->flags & MLX4_FLAG_SRIOV && !active_vfs) {
mlx4_warn(dev, "Disabling SR-IOV\n");
pci_disable_sriov(pdev);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 2ebaa3b..6e01609 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -1042,6 +1042,8 @@ int mlx4_calc_vf_counters(struct mlx4_dev *dev, int slave, int port,
void mlx4_stop_catas_poll(struct mlx4_dev *dev);
int mlx4_catas_init(struct mlx4_dev *dev);
void mlx4_catas_end(struct mlx4_dev *dev);
+int mlx4_crdump_init(struct mlx4_dev *dev);
+void mlx4_crdump_end(struct mlx4_dev *dev);
int mlx4_restart_one(struct pci_dev *pdev, bool reload,
struct devlink *devlink);
int mlx4_register_device(struct mlx4_dev *dev);
@@ -1228,6 +1230,8 @@ int mlx4_comm_cmd(struct mlx4_dev *dev, u8 cmd, u16 param,
void mlx4_enter_error_state(struct mlx4_dev_persistent *persist);
int mlx4_comm_internal_err(u32 slave_read);
+int mlx4_crdump_collect(struct mlx4_dev *dev);
+
int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port,
enum mlx4_port_type *type);
void mlx4_do_sense_ports(struct mlx4_dev *dev,
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index e3bfe76..300b944 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -852,6 +852,11 @@ struct mlx4_vf_dev {
u8 n_ports;
};
+struct mlx4_fw_crdump {
+ struct devlink_region *region_crspace;
+ struct devlink_region *region_fw_health;
+};
+
enum mlx4_pci_status {
MLX4_PCI_STATUS_DISABLED,
MLX4_PCI_STATUS_ENABLED,
@@ -872,6 +877,7 @@ struct mlx4_dev_persistent {
u8 interface_state;
struct mutex pci_status_mutex; /* sync pci state */
enum mlx4_pci_status pci_status;
+ struct mlx4_fw_crdump crdump;
};
struct mlx4_dev {
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next v3 10/11] devlink: Add generic parameters region_snapshot
From: Alex Vesker @ 2018-07-12 12:13 UTC (permalink / raw)
To: netdev, jiri
Cc: dsahern, andrew, rahul.lakkireddy, jakub.kicinski, Alex Vesker
In-Reply-To: <1531397598-11207-1-git-send-email-valex@mellanox.com>
region_snapshot - When set enables capturing region snapshots
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
---
include/net/devlink.h | 4 ++++
net/core/devlink.c | 5 +++++
2 files changed, 9 insertions(+)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 905f0bb..b9b89d6 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -361,6 +361,7 @@ enum devlink_param_generic_id {
DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET,
DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV,
+ DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT,
/* add new param generic ids above here*/
__DEVLINK_PARAM_GENERIC_ID_MAX,
@@ -376,6 +377,9 @@ enum devlink_param_generic_id {
#define DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_NAME "enable_sriov"
#define DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_TYPE DEVLINK_PARAM_TYPE_BOOL
+#define DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_NAME "region_snapshot_enable"
+#define DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_TYPE DEVLINK_PARAM_TYPE_BOOL
+
#define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \
{ \
.id = DEVLINK_PARAM_GENERIC_ID_##_id, \
diff --git a/net/core/devlink.c b/net/core/devlink.c
index e5118db..65fc366 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -2671,6 +2671,11 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
.name = DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_NAME,
.type = DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_TYPE,
},
+ {
+ .id = DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT,
+ .name = DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_NAME,
+ .type = DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_TYPE,
+ },
};
static int devlink_param_generic_verify(const struct devlink_param *param)
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next v3 11/11] net/mlx4_core: Use devlink region_snapshot parameter
From: Alex Vesker @ 2018-07-12 12:13 UTC (permalink / raw)
To: netdev, jiri
Cc: dsahern, andrew, rahul.lakkireddy, jakub.kicinski, Alex Vesker
In-Reply-To: <1531397598-11207-1-git-send-email-valex@mellanox.com>
This parameter enables capturing region snapshot of the crspace
during critical errors. The default value of this parameter is
disabled, it can be enabled using devlink param commands.
It is possible to configure during runtime and also driver init.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/crdump.c | 8 ++++++
drivers/net/ethernet/mellanox/mlx4/main.c | 41 +++++++++++++++++++++++++++++
include/linux/mlx4/device.h | 1 +
3 files changed, 50 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx4/crdump.c b/drivers/net/ethernet/mellanox/mlx4/crdump.c
index 4d5524d..88316c7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/crdump.c
+++ b/drivers/net/ethernet/mellanox/mlx4/crdump.c
@@ -158,6 +158,7 @@ static void mlx4_crdump_collect_fw_health(struct mlx4_dev *dev,
int mlx4_crdump_collect(struct mlx4_dev *dev)
{
struct devlink *devlink = priv_to_devlink(mlx4_priv(dev));
+ struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
struct pci_dev *pdev = dev->persist->pdev;
unsigned long cr_res_size;
u8 __iomem *cr_space;
@@ -168,6 +169,11 @@ int mlx4_crdump_collect(struct mlx4_dev *dev)
return 0;
}
+ if (!crdump->snapshot_enable) {
+ mlx4_info(dev, "crdump: devlink snapshot disabled, skipping\n");
+ return 0;
+ }
+
cr_res_size = pci_resource_len(pdev, 0);
cr_space = ioremap(pci_resource_start(pdev, 0), cr_res_size);
@@ -197,6 +203,8 @@ int mlx4_crdump_init(struct mlx4_dev *dev)
struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
struct pci_dev *pdev = dev->persist->pdev;
+ crdump->snapshot_enable = false;
+
/* Create cr-space region */
crdump->region_crspace =
devlink_region_create(devlink,
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 46b0214..2d979a6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -191,6 +191,26 @@ static int mlx4_devlink_ierr_reset_set(struct devlink *devlink, u32 id,
return 0;
}
+static int mlx4_devlink_crdump_snapshot_get(struct devlink *devlink, u32 id,
+ struct devlink_param_gset_ctx *ctx)
+{
+ struct mlx4_priv *priv = devlink_priv(devlink);
+ struct mlx4_dev *dev = &priv->dev;
+
+ ctx->val.vbool = dev->persist->crdump.snapshot_enable;
+ return 0;
+}
+
+static int mlx4_devlink_crdump_snapshot_set(struct devlink *devlink, u32 id,
+ struct devlink_param_gset_ctx *ctx)
+{
+ struct mlx4_priv *priv = devlink_priv(devlink);
+ struct mlx4_dev *dev = &priv->dev;
+
+ dev->persist->crdump.snapshot_enable = ctx->val.vbool;
+ return 0;
+}
+
static int
mlx4_devlink_max_macs_validate(struct devlink *devlink, u32 id,
union devlink_param_value val,
@@ -224,6 +244,11 @@ enum mlx4_devlink_param_id {
DEVLINK_PARAM_GENERIC(MAX_MACS,
BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
NULL, NULL, mlx4_devlink_max_macs_validate),
+ DEVLINK_PARAM_GENERIC(REGION_SNAPSHOT,
+ BIT(DEVLINK_PARAM_CMODE_RUNTIME) |
+ BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+ mlx4_devlink_crdump_snapshot_get,
+ mlx4_devlink_crdump_snapshot_set, NULL),
DEVLINK_PARAM_DRIVER(MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE,
"enable_64b_cqe_eqe", DEVLINK_PARAM_TYPE_BOOL,
BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
@@ -270,6 +295,11 @@ static void mlx4_devlink_set_params_init_values(struct devlink *devlink)
mlx4_devlink_set_init_value(devlink,
MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR,
value);
+
+ value.vbool = false;
+ mlx4_devlink_set_init_value(devlink,
+ DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT,
+ value);
}
static inline void mlx4_set_num_reserved_uars(struct mlx4_dev *dev,
@@ -3862,6 +3892,9 @@ static int mlx4_devlink_port_type_set(struct devlink_port *devlink_port,
static void mlx4_devlink_param_load_driverinit_values(struct devlink *devlink)
{
+ struct mlx4_priv *priv = devlink_priv(devlink);
+ struct mlx4_dev *dev = &priv->dev;
+ struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
union devlink_param_value saved_value;
int err;
@@ -3889,6 +3922,14 @@ static void mlx4_devlink_param_load_driverinit_values(struct devlink *devlink)
&saved_value);
if (!err)
enable_4k_uar = saved_value.vbool;
+ err = devlink_param_driverinit_value_get(devlink,
+ DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT,
+ &saved_value);
+ if (!err && crdump->snapshot_enable != saved_value.vbool) {
+ crdump->snapshot_enable = saved_value.vbool;
+ devlink_param_value_changed(devlink,
+ DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT);
+ }
}
static int mlx4_devlink_reload(struct devlink *devlink,
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 300b944..dca6ab4 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -853,6 +853,7 @@ struct mlx4_vf_dev {
};
struct mlx4_fw_crdump {
+ bool snapshot_enable;
struct devlink_region *region_crspace;
struct devlink_region *region_fw_health;
};
--
1.8.3.1
^ permalink raw reply related
* [PATCH net] qlogic: check kstrtoul() for errors
From: Dan Carpenter @ 2018-07-12 12:23 UTC (permalink / raw)
To: Harish Patil, Himanshu Madhani
Cc: Manish Chopra, Dept-GELinuxNICDev, David S. Miller, netdev,
kernel-janitors
We accidentally left out the error handling for kstrtoul().
Fixes: a520030e326a ("qlcnic: Implement flash sysfs callback for 83xx adapter")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
index 891f03a7a33d..8d7b9bb910f2 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
@@ -1128,6 +1128,8 @@ static ssize_t qlcnic_83xx_sysfs_flash_write_handler(struct file *filp,
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
ret = kstrtoul(buf, 16, &data);
+ if (ret)
+ return ret;
switch (data) {
case QLC_83XX_FLASH_SECTOR_ERASE_CMD:
^ permalink raw reply related
* Re: [net-next, 1/3] tcp: convert icsk_user_timeout from jiffies to msecs
From: Eric Dumazet @ 2018-07-12 12:35 UTC (permalink / raw)
To: David Laight
Cc: jmaxwell37, David Miller, Neal Cardwell, Alexey Kuznetsov,
Hideaki YOSHIFUJI, netdev, LKML, jmaxwell
In-Reply-To: <f65200d8942d4eca92f854e63d2d5286@AcuMS.aculab.com>
On Thu, Jul 12, 2018 at 1:57 AM David Laight <David.Laight@aculab.com> wrote:
>
> From: Jon Maxwell Sent: 12 July 2018 01:36
> ...
> > - (s32)(tcp_time_stamp(tp) - start_ts) >
> > - jiffies_to_msecs(icsk->icsk_user_timeout))
> > + (s32)(tcp_time_stamp(tp) - start_ts) > icsk->icsk_user_timeout)
>
> That has never been tested properly.
> icsk_user_timeout is u32 so the comparison is unsigned and the (s32) cast
> has no effect.
>
The existing code had this ' bug' already.
Please do not blame this patch, and send a patch if you believe there
is an issue ?
In my opinion, the (s32) here is a reminder for the reader of the
width of the expression,
more than anything, since there is no chance the result can be negative.
^ permalink raw reply
* [PATCH net 0/2] fix DCTCP delayed ACK
From: Yuchung Cheng @ 2018-07-12 13:04 UTC (permalink / raw)
To: davem; +Cc: netdev, brakmo, ncardwell, ysseung, edumazet, Yuchung Cheng
This patch series addresses the issue that sometimes DCTCP
fail to acknowledge the latest sequence and result in sender timeout
if inflight is small.
Yuchung Cheng (2):
tcp: fix dctcp delayed ACK schedule
tcp: remove DELAYED ACK events in DCTCP
include/net/tcp.h | 2 --
net/ipv4/tcp_dctcp.c | 31 ++++---------------------------
net/ipv4/tcp_output.c | 4 ----
3 files changed, 4 insertions(+), 33 deletions(-)
--
2.18.0.203.gfac676dfb9-goog
^ permalink raw reply
* [PATCH net 1/2] tcp: fix dctcp delayed ACK schedule
From: Yuchung Cheng @ 2018-07-12 13:04 UTC (permalink / raw)
To: davem; +Cc: netdev, brakmo, ncardwell, ysseung, edumazet, Yuchung Cheng
In-Reply-To: <20180712130453.95007-1-ycheng@google.com>
Previously, when a data segment was sent an ACK was piggybacked
on the data segment without generating a CA_EVENT_NON_DELAYED_ACK
event to notify congestion control modules. So the DCTCP
ca->delayed_ack_reserved flag could incorrectly stay set when
in fact there were no delayed ACKs being reserved. This could result
in sending a special ECN notification ACK that carries an older
ACK sequence, when in fact there was no need for such an ACK.
DCTCP keeps track of the delayed ACK status with its own separate
state ca->delayed_ack_reserved. Previously it may accidentally cancel
the delayed ACK without updating this field upon sending a special
ACK that carries a older ACK sequence. This inconsistency would
lead to DCTCP receiver never acknowledging the latest data until the
sender times out and retry in some cases.
Packetdrill script (provided by Larry Brakmo)
0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
0.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
0.000 setsockopt(3, SOL_TCP, TCP_CONGESTION, "dctcp", 5) = 0
0.000 bind(3, ..., ...) = 0
0.000 listen(3, 1) = 0
0.100 < [ect0] SEW 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
0.100 > SE. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
0.110 < [ect0] . 1:1(0) ack 1 win 257
0.200 accept(3, ..., ...) = 4
0.200 < [ect0] . 1:1001(1000) ack 1 win 257
0.200 > [ect01] . 1:1(0) ack 1001
0.200 write(4, ..., 1) = 1
0.200 > [ect01] P. 1:2(1) ack 1001
0.200 < [ect0] . 1001:2001(1000) ack 2 win 257
0.200 write(4, ..., 1) = 1
0.200 > [ect01] P. 2:3(1) ack 2001
0.200 < [ect0] . 2001:3001(1000) ack 3 win 257
0.200 < [ect0] . 3001:4001(1000) ack 3 win 257
0.200 > [ect01] . 3:3(0) ack 4001
0.210 < [ce] P. 4001:4501(500) ack 3 win 257
+0.001 read(4, ..., 4500) = 4500
+0 write(4, ..., 1) = 1
+0 > [ect01] PE. 3:4(1) ack 4501
+0.010 < [ect0] W. 4501:5501(1000) ack 4 win 257
// Previously the ACK sequence below would be 4501, causing a long RTO
+0.040~+0.045 > [ect01] . 4:4(0) ack 5501 // delayed ack
+0.311 < [ect0] . 5501:6501(1000) ack 4 win 257 // More data
+0 > [ect01] . 4:4(0) ack 6501 // now acks everything
+0.500 < F. 9501:9501(0) ack 4 win 257
Reported-by: Larry Brakmo <brakmo@fb.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
---
net/ipv4/tcp_dctcp.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 5f5e5936760e..89f88b0d8167 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -134,7 +134,8 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
/* State has changed from CE=0 to CE=1 and delayed
* ACK has not sent yet.
*/
- if (!ca->ce_state && ca->delayed_ack_reserved) {
+ if (!ca->ce_state &&
+ inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
u32 tmp_rcv_nxt;
/* Save current rcv_nxt. */
@@ -164,7 +165,8 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
/* State has changed from CE=1 to CE=0 and delayed
* ACK has not sent yet.
*/
- if (ca->ce_state && ca->delayed_ack_reserved) {
+ if (ca->ce_state &&
+ inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
u32 tmp_rcv_nxt;
/* Save current rcv_nxt. */
--
2.18.0.203.gfac676dfb9-goog
^ permalink raw reply related
* [PATCH net 2/2] tcp: remove DELAYED ACK events in DCTCP
From: Yuchung Cheng @ 2018-07-12 13:04 UTC (permalink / raw)
To: davem; +Cc: netdev, brakmo, ncardwell, ysseung, edumazet, Yuchung Cheng
In-Reply-To: <20180712130453.95007-1-ycheng@google.com>
After fixing the way DCTCP tracking delayed ACKs, the delayed-ACK
related callbacks are no longer needed
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
---
include/net/tcp.h | 2 --
net/ipv4/tcp_dctcp.c | 25 -------------------------
net/ipv4/tcp_output.c | 4 ----
3 files changed, 31 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index af3ec72d5d41..3482d13d655b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -912,8 +912,6 @@ enum tcp_ca_event {
CA_EVENT_LOSS, /* loss timeout */
CA_EVENT_ECN_NO_CE, /* ECT set, but not CE marked */
CA_EVENT_ECN_IS_CE, /* received CE marked IP packet */
- CA_EVENT_DELAYED_ACK, /* Delayed ack is sent */
- CA_EVENT_NON_DELAYED_ACK,
};
/* Information about inbound ACK, passed to cong_ops->in_ack_event() */
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 89f88b0d8167..5869f89ca656 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -55,7 +55,6 @@ struct dctcp {
u32 dctcp_alpha;
u32 next_seq;
u32 ce_state;
- u32 delayed_ack_reserved;
u32 loss_cwnd;
};
@@ -96,7 +95,6 @@ static void dctcp_init(struct sock *sk)
ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
- ca->delayed_ack_reserved = 0;
ca->loss_cwnd = 0;
ca->ce_state = 0;
@@ -250,25 +248,6 @@ static void dctcp_state(struct sock *sk, u8 new_state)
}
}
-static void dctcp_update_ack_reserved(struct sock *sk, enum tcp_ca_event ev)
-{
- struct dctcp *ca = inet_csk_ca(sk);
-
- switch (ev) {
- case CA_EVENT_DELAYED_ACK:
- if (!ca->delayed_ack_reserved)
- ca->delayed_ack_reserved = 1;
- break;
- case CA_EVENT_NON_DELAYED_ACK:
- if (ca->delayed_ack_reserved)
- ca->delayed_ack_reserved = 0;
- break;
- default:
- /* Don't care for the rest. */
- break;
- }
-}
-
static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
{
switch (ev) {
@@ -278,10 +257,6 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
case CA_EVENT_ECN_NO_CE:
dctcp_ce_state_1_to_0(sk);
break;
- case CA_EVENT_DELAYED_ACK:
- case CA_EVENT_NON_DELAYED_ACK:
- dctcp_update_ack_reserved(sk, ev);
- break;
default:
/* Don't care for the rest. */
break;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8e08b409c71e..00e5a300ddb9 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3523,8 +3523,6 @@ void tcp_send_delayed_ack(struct sock *sk)
int ato = icsk->icsk_ack.ato;
unsigned long timeout;
- tcp_ca_event(sk, CA_EVENT_DELAYED_ACK);
-
if (ato > TCP_DELACK_MIN) {
const struct tcp_sock *tp = tcp_sk(sk);
int max_ato = HZ / 2;
@@ -3581,8 +3579,6 @@ void tcp_send_ack(struct sock *sk)
if (sk->sk_state == TCP_CLOSE)
return;
- tcp_ca_event(sk, CA_EVENT_NON_DELAYED_ACK);
-
/* We are not putting this on the write queue, so
* tcp_transmit_skb() will set the ownership to this
* sock.
--
2.18.0.203.gfac676dfb9-goog
^ permalink raw reply related
* Re: [PATCH net 1/2] tcp: fix dctcp delayed ACK schedule
From: Lawrence Brakmo @ 2018-07-12 13:09 UTC (permalink / raw)
To: Yuchung Cheng, davem@davemloft.net
Cc: netdev@vger.kernel.org, ncardwell@google.com, ysseung@google.com,
edumazet@google.com
In-Reply-To: <20180712130453.95007-2-ycheng@google.com>
On 7/12/18, 9:05 AM, "netdev-owner@vger.kernel.org on behalf of Yuchung Cheng" <netdev-owner@vger.kernel.org on behalf of ycheng@google.com> wrote:
Previously, when a data segment was sent an ACK was piggybacked
on the data segment without generating a CA_EVENT_NON_DELAYED_ACK
event to notify congestion control modules. So the DCTCP
ca->delayed_ack_reserved flag could incorrectly stay set when
in fact there were no delayed ACKs being reserved. This could result
in sending a special ECN notification ACK that carries an older
ACK sequence, when in fact there was no need for such an ACK.
DCTCP keeps track of the delayed ACK status with its own separate
state ca->delayed_ack_reserved. Previously it may accidentally cancel
the delayed ACK without updating this field upon sending a special
ACK that carries a older ACK sequence. This inconsistency would
lead to DCTCP receiver never acknowledging the latest data until the
sender times out and retry in some cases.
Packetdrill script (provided by Larry Brakmo)
0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
0.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
0.000 setsockopt(3, SOL_TCP, TCP_CONGESTION, "dctcp", 5) = 0
0.000 bind(3, ..., ...) = 0
0.000 listen(3, 1) = 0
0.100 < [ect0] SEW 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
0.100 > SE. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
0.110 < [ect0] . 1:1(0) ack 1 win 257
0.200 accept(3, ..., ...) = 4
0.200 < [ect0] . 1:1001(1000) ack 1 win 257
0.200 > [ect01] . 1:1(0) ack 1001
0.200 write(4, ..., 1) = 1
0.200 > [ect01] P. 1:2(1) ack 1001
0.200 < [ect0] . 1001:2001(1000) ack 2 win 257
0.200 write(4, ..., 1) = 1
0.200 > [ect01] P. 2:3(1) ack 2001
0.200 < [ect0] . 2001:3001(1000) ack 3 win 257
0.200 < [ect0] . 3001:4001(1000) ack 3 win 257
0.200 > [ect01] . 3:3(0) ack 4001
0.210 < [ce] P. 4001:4501(500) ack 3 win 257
+0.001 read(4, ..., 4500) = 4500
+0 write(4, ..., 1) = 1
+0 > [ect01] PE. 3:4(1) ack 4501
+0.010 < [ect0] W. 4501:5501(1000) ack 4 win 257
// Previously the ACK sequence below would be 4501, causing a long RTO
+0.040~+0.045 > [ect01] . 4:4(0) ack 5501 // delayed ack
+0.311 < [ect0] . 5501:6501(1000) ack 4 win 257 // More data
+0 > [ect01] . 4:4(0) ack 6501 // now acks everything
+0.500 < F. 9501:9501(0) ack 4 win 257
Reported-by: Larry Brakmo <brakmo@fb.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
---
net/ipv4/tcp_dctcp.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 5f5e5936760e..89f88b0d8167 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -134,7 +134,8 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
/* State has changed from CE=0 to CE=1 and delayed
* ACK has not sent yet.
*/
- if (!ca->ce_state && ca->delayed_ack_reserved) {
+ if (!ca->ce_state &&
+ inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
u32 tmp_rcv_nxt;
/* Save current rcv_nxt. */
@@ -164,7 +165,8 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
/* State has changed from CE=1 to CE=0 and delayed
* ACK has not sent yet.
*/
- if (ca->ce_state && ca->delayed_ack_reserved) {
+ if (ca->ce_state &&
+ inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
u32 tmp_rcv_nxt;
/* Save current rcv_nxt. */
--
2.18.0.203.gfac676dfb9-goog
LGTM. Thanks for the patch.
Acked-by: Lawrence Brakmo <brakmo@fb.com>
^ permalink raw reply
* Re: [PATCH net 2/2] tcp: remove DELAYED ACK events in DCTCP
From: Lawrence Brakmo @ 2018-07-12 13:09 UTC (permalink / raw)
To: Yuchung Cheng, davem@davemloft.net
Cc: netdev@vger.kernel.org, ncardwell@google.com, ysseung@google.com,
edumazet@google.com
In-Reply-To: <20180712130453.95007-3-ycheng@google.com>
LGTM. Thanks for the patch.
Acked-by: Lawrence Brakmo <brakmo@fb.com>
On 7/12/18, 9:05 AM, "Yuchung Cheng" <ycheng@google.com> wrote:
After fixing the way DCTCP tracking delayed ACKs, the delayed-ACK
related callbacks are no longer needed
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
---
include/net/tcp.h | 2 --
net/ipv4/tcp_dctcp.c | 25 -------------------------
net/ipv4/tcp_output.c | 4 ----
3 files changed, 31 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index af3ec72d5d41..3482d13d655b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -912,8 +912,6 @@ enum tcp_ca_event {
CA_EVENT_LOSS, /* loss timeout */
CA_EVENT_ECN_NO_CE, /* ECT set, but not CE marked */
CA_EVENT_ECN_IS_CE, /* received CE marked IP packet */
- CA_EVENT_DELAYED_ACK, /* Delayed ack is sent */
- CA_EVENT_NON_DELAYED_ACK,
};
/* Information about inbound ACK, passed to cong_ops->in_ack_event() */
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 89f88b0d8167..5869f89ca656 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -55,7 +55,6 @@ struct dctcp {
u32 dctcp_alpha;
u32 next_seq;
u32 ce_state;
- u32 delayed_ack_reserved;
u32 loss_cwnd;
};
@@ -96,7 +95,6 @@ static void dctcp_init(struct sock *sk)
ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
- ca->delayed_ack_reserved = 0;
ca->loss_cwnd = 0;
ca->ce_state = 0;
@@ -250,25 +248,6 @@ static void dctcp_state(struct sock *sk, u8 new_state)
}
}
-static void dctcp_update_ack_reserved(struct sock *sk, enum tcp_ca_event ev)
-{
- struct dctcp *ca = inet_csk_ca(sk);
-
- switch (ev) {
- case CA_EVENT_DELAYED_ACK:
- if (!ca->delayed_ack_reserved)
- ca->delayed_ack_reserved = 1;
- break;
- case CA_EVENT_NON_DELAYED_ACK:
- if (ca->delayed_ack_reserved)
- ca->delayed_ack_reserved = 0;
- break;
- default:
- /* Don't care for the rest. */
- break;
- }
-}
-
static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
{
switch (ev) {
@@ -278,10 +257,6 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
case CA_EVENT_ECN_NO_CE:
dctcp_ce_state_1_to_0(sk);
break;
- case CA_EVENT_DELAYED_ACK:
- case CA_EVENT_NON_DELAYED_ACK:
- dctcp_update_ack_reserved(sk, ev);
- break;
default:
/* Don't care for the rest. */
break;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8e08b409c71e..00e5a300ddb9 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3523,8 +3523,6 @@ void tcp_send_delayed_ack(struct sock *sk)
int ato = icsk->icsk_ack.ato;
unsigned long timeout;
- tcp_ca_event(sk, CA_EVENT_DELAYED_ACK);
-
if (ato > TCP_DELACK_MIN) {
const struct tcp_sock *tp = tcp_sk(sk);
int max_ato = HZ / 2;
@@ -3581,8 +3579,6 @@ void tcp_send_ack(struct sock *sk)
if (sk->sk_state == TCP_CLOSE)
return;
- tcp_ca_event(sk, CA_EVENT_NON_DELAYED_ACK);
-
/* We are not putting this on the write queue, so
* tcp_transmit_skb() will set the ownership to this
* sock.
--
2.18.0.203.gfac676dfb9-goog
^ permalink raw reply
* Re: KMSAN: uninit-value in p9_client_rpc
From: Alexander Potapenko @ 2018-07-12 13:36 UTC (permalink / raw)
To: syzbot+4de40388f584432bf004
Cc: David Miller, ericvh, LKML, lucho, Networking, rminnich,
syzkaller-bugs, v9fs-developer
In-Reply-To: <00000000000077da4b0570c9eccc@google.com>
On Thu, Jul 12, 2018 at 11:24 AM syzbot
<syzbot+4de40388f584432bf004@syzkaller.appspotmail.com> wrote:
>
> syzbot has found a reproducer for the following crash on:
>
> HEAD commit: b64f7ec04e12 kmsan: implement kmsan_memmove_shadow() and k..
> git tree: https://github.com/google/kmsan.git/master
> console output: https://syzkaller.appspot.com/x/log.txt?x=12f6791c400000
> kernel config: https://syzkaller.appspot.com/x/.config?x=93d57043084eee38
> dashboard link: https://syzkaller.appspot.com/bug?extid=4de40388f584432bf004
> compiler: clang version 7.0.0 (trunk 334104)
> syzkaller repro:https://syzkaller.appspot.com/x/repro.syz?x=147c36dc400000
> C reproducer: https://syzkaller.appspot.com/x/repro.c?x=14e87044400000
>
> IMPORTANT: if you fix the bug, please add the following tag to the commit:
> Reported-by: syzbot+4de40388f584432bf004@syzkaller.appspotmail.com
>
> FS-Cache: O-key=[10] '34323934373135343132'
> FS-Cache: N-cookie c=(____ptrval____) [p=(____ptrval____) fl=2 nc=0 na=1]
> FS-Cache: N-cookie d=(____ptrval____) n=(____ptrval____)
> FS-Cache: N-key=[10] '34323934373135343132'
> ==================================================================
> BUG: KMSAN: uninit-value in p9_client_rpc+0x194c/0x1dc0 net/9p/client.c:818
> CPU: 1 PID: 4620 Comm: syz-executor262 Not tainted 4.18.0-rc4+ #24
> Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
> Google 01/01/2011
> Call Trace:
> __dump_stack lib/dump_stack.c:77 [inline]
> dump_stack+0x185/0x1e0 lib/dump_stack.c:113
> kmsan_report+0x195/0x2c0 mm/kmsan/kmsan.c:1092
> __msan_warning_32+0x7d/0xe0 mm/kmsan/kmsan_instr.c:640
> p9_client_rpc+0x194c/0x1dc0 net/9p/client.c:818
> p9_client_attach+0x35b/0xc30 net/9p/client.c:1147
> v9fs_session_init+0x24b9/0x2970 fs/9p/v9fs.c:449
> v9fs_mount+0x107/0x11b0 fs/9p/vfs_super.c:135
> mount_fs+0x29b/0x780 fs/super.c:1277
> vfs_kern_mount+0x222/0x990 fs/namespace.c:1037
> do_new_mount fs/namespace.c:2518 [inline]
> do_mount+0xd30/0x5310 fs/namespace.c:2848
> ksys_mount+0x32e/0x3d0 fs/namespace.c:3064
> __do_sys_mount fs/namespace.c:3078 [inline]
> __se_sys_mount fs/namespace.c:3075 [inline]
> __x64_sys_mount+0x157/0x1c0 fs/namespace.c:3075
> do_syscall_64+0x15b/0x230 arch/x86/entry/common.c:290
> entry_SYSCALL_64_after_hwframe+0x63/0xe7
> RIP: 0033:0x445f79
> Code: e8 cc e6 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7
> 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff
> ff 0f 83 3b 0d fc ff c3 66 2e 0f 1f 84 00 00 00 00
> RSP: 002b:00007ffb83104da8 EFLAGS: 00000202 ORIG_RAX: 00000000000000a5
> RAX: ffffffffffffffda RBX: 00000000006dbc3c RCX: 0000000000445f79
> RDX: 0000000020000180 RSI: 00000000200000c0 RDI: 0000000000000000
> RBP: 00000000006dbc38 R08: 00000000200001c0 R09: 0000000000000000
> R10: 0000000000000000 R11: 0000000000000202 R12: 0030656c69662f2e
> R13: 64663d736e617274 R14: 7974697275636573 R15: 0000000000000001
>
> Local variable description: ----ecode.i@p9_client_rpc
> Variable was created at:
> p9_client_rpc+0x183/0x1dc0 net/9p/client.c:750
> p9_client_attach+0x35b/0xc30 net/9p/client.c:1147
> ==================================================================
FWIW the bug occurs here:
https://elixir.bootlin.com/linux/latest/source/net/9p/client.c#L560
} else {
err = p9pdu_readf(req->rc, c->proto_version, "d", &ecode);
err = -ecode;
p9_debug(P9_DEBUG_9P, "<<< RLERROR (%d)\n", -ecode);
}
When p9pdu_readf() fails with -EFAULT, |ecode| may remain uninitialized.
We need to check the value of |err| before assigning |-ecode| to it.
> --
> You received this message because you are subscribed to the Google Groups "syzkaller-bugs" group.
> To unsubscribe from this group and stop receiving emails from it, send an email to syzkaller-bugs+unsubscribe@googlegroups.com.
> To view this discussion on the web visit https://groups.google.com/d/msgid/syzkaller-bugs/00000000000077da4b0570c9eccc%40google.com.
> For more options, visit https://groups.google.com/d/optout.
--
Alexander Potapenko
Software Engineer
Google Germany GmbH
Erika-Mann-Straße, 33
80636 München
Geschäftsführer: Paul Manicle, Halimah DeLaine Prado
Registergericht und -nummer: Hamburg, HRB 86891
Sitz der Gesellschaft: Hamburg
^ permalink raw reply
* Re: [PATCH net-next 03/18] net: mvpp2: make sure we use single queue mode on PPv2.1
From: Sergei Shtylyov @ 2018-07-12 14:10 UTC (permalink / raw)
To: Maxime Chevallier, davem
Cc: netdev, linux-kernel, Antoine Tenart, thomas.petazzoni,
gregory.clement, miquel.raynal, nadavh, stefanc, ymarkman, mw
In-Reply-To: <20180712115427.27375-4-maxime.chevallier@bootlin.com>
Hello!
On 07/12/2018 02:54 PM, Maxime Chevallier wrote:
> The PPv2 driver defines 2 "queue_modes" :
> - QDIST_SINGLE_MODE, where we each port share one rx queue vector
Doesn't look like "we" is needed here.
> between all CPUs
> - QDIST_MULTI_MODE, where each port has one rx queue vector per CPU.
>
> Multi queue mode isn't available on PPv2.1, make sure we fallback to
> single mode when running on this revision.
>
> Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
[...]
MBR, Sergei
^ permalink raw reply
* Re: [PATCH net-next][RESEND] net/tls: Use aead_request_alloc/free for request alloc/free
From: Dave Watson @ 2018-07-12 14:38 UTC (permalink / raw)
To: Vakul Garg; +Cc: davem, netdev, linux-kernel, borisp, aviadye
In-Reply-To: <20180711090220.14697-1-vakul.garg@nxp.com>
On 07/11/18 02:32 PM, Vakul Garg wrote:
> Instead of kzalloc/free for aead_request allocation and free, use
> functions aead_request_alloc(), aead_request_free(). It ensures that
> any sensitive crypto material held in crypto transforms is securely
> erased from memory.
>
> Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Acked-by: Dave Watson <davejwatson@fb.com>
^ permalink raw reply
* Re: [PATCH net-next] net/tls: Removed redundant variable from 'struct tls_sw_context_rx'
From: Dave Watson @ 2018-07-12 14:31 UTC (permalink / raw)
To: Vakul Garg
Cc: Boris Pismenny, davem@davemloft.net, netdev@vger.kernel.org,
aviadye@mellanox.com
In-Reply-To: <DB7PR04MB425292189C05496BD550D3F28B590@DB7PR04MB4252.eurprd04.prod.outlook.com>
On 07/12/18 11:14 AM, Vakul Garg wrote:
> Hi Boris
>
> Thanks for explaining.
> Few questions/observations.
>
> 1. Isn't ' ctx->decrypted = true' a redundant statement in tls_do_decryption()?
> The same has been repeated in tls_recvmsg() after calling decrypt_skb()?
>
> 2. Similarly, ctx->saved_data_ready(sk) seems not required in tls_do_decryption().
> This is because tls_do_decryption() is already triggered from tls_recvmsg() i.e. from user space app context.
>
> 3. In tls_queue(), I think strp->sk->sk_state_change() needs to be replaced with ctx->saved_data_ready().
Yes, I think these 3 can all be changed. #2 would be required if
do_decryption ever is called not in user context, but that's not the
case currently.
^ permalink raw reply
* [PATCH nf-next 1/2] ipv6: remove dependency of nf_defrag_ipv6 on ipv6 module
From: Florian Westphal @ 2018-07-12 14:35 UTC (permalink / raw)
To: netfilter-devel; +Cc: netdev, arnd, Florian Westphal
IPV6=m
DEFRAG_IPV6=m
CONNTRACK=y yields:
net/netfilter/nf_conntrack_proto.o: In function `nf_ct_netns_do_get':
net/netfilter/nf_conntrack_proto.c:802: undefined reference to `nf_defrag_ipv6_enable'
net/netfilter/nf_conntrack_proto.o:(.rodata+0x640): undefined reference to `nf_conntrack_l4proto_icmpv6'
Setting DEFRAG_IPV6=y causes undefined references to ip6_rhash_params
ip6_frag_init and ip6_expire_frag_queue so it would be needed to force
IPV6=y too.
This patch gets rid of the 'followup linker error' by removing
the dependency of ipv6.ko symbols from netfilter ipv6 defrag.
Shared code is placed into a header, then used from both.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
include/net/ipv6.h | 28 --------
include/net/ipv6_frag.h | 102 ++++++++++++++++++++++++++++++
net/ipv6/netfilter/nf_conntrack_reasm.c | 17 +++--
net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 3 +-
net/ipv6/reassembly.c | 92 ++-------------------------
net/openvswitch/conntrack.c | 1 +
6 files changed, 123 insertions(+), 120 deletions(-)
create mode 100644 include/net/ipv6_frag.h
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 16475c269749..0012c0a6c86e 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -561,34 +561,6 @@ static inline bool ipv6_prefix_equal(const struct in6_addr *addr1,
}
#endif
-struct inet_frag_queue;
-
-enum ip6_defrag_users {
- IP6_DEFRAG_LOCAL_DELIVER,
- IP6_DEFRAG_CONNTRACK_IN,
- __IP6_DEFRAG_CONNTRACK_IN = IP6_DEFRAG_CONNTRACK_IN + USHRT_MAX,
- IP6_DEFRAG_CONNTRACK_OUT,
- __IP6_DEFRAG_CONNTRACK_OUT = IP6_DEFRAG_CONNTRACK_OUT + USHRT_MAX,
- IP6_DEFRAG_CONNTRACK_BRIDGE_IN,
- __IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX,
-};
-
-void ip6_frag_init(struct inet_frag_queue *q, const void *a);
-extern const struct rhashtable_params ip6_rhash_params;
-
-/*
- * Equivalent of ipv4 struct ip
- */
-struct frag_queue {
- struct inet_frag_queue q;
-
- int iif;
- __u16 nhoffset;
- u8 ecn;
-};
-
-void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq);
-
static inline bool ipv6_addr_any(const struct in6_addr *a)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h
new file mode 100644
index 000000000000..ff3be4ca9471
--- /dev/null
+++ b/include/net/ipv6_frag.h
@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _IPV6_FRAG_H
+#define _IPV6_FRAG_H
+#include <linux/kernel.h>
+#include <net/addrconf.h>
+#include <net/ipv6.h>
+#include <net/inet_frag.h>
+
+enum ip6_defrag_users {
+ IP6_DEFRAG_LOCAL_DELIVER,
+ IP6_DEFRAG_CONNTRACK_IN,
+ __IP6_DEFRAG_CONNTRACK_IN = IP6_DEFRAG_CONNTRACK_IN + USHRT_MAX,
+ IP6_DEFRAG_CONNTRACK_OUT,
+ __IP6_DEFRAG_CONNTRACK_OUT = IP6_DEFRAG_CONNTRACK_OUT + USHRT_MAX,
+ IP6_DEFRAG_CONNTRACK_BRIDGE_IN,
+ __IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX,
+};
+
+/*
+ * Equivalent of ipv4 struct ip
+ */
+struct frag_queue {
+ struct inet_frag_queue q;
+
+ int iif;
+ __u16 nhoffset;
+ u8 ecn;
+};
+
+static inline void ip6frag_init(struct inet_frag_queue *q, const void *a)
+{
+ struct frag_queue *fq = container_of(q, struct frag_queue, q);
+ const struct frag_v6_compare_key *key = a;
+
+ q->key.v6 = *key;
+ fq->ecn = 0;
+}
+
+static inline u32 ip6frag_key_hashfn(const void *data, u32 len, u32 seed)
+{
+ return jhash2(data,
+ sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static inline u32 ip6frag_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+ const struct inet_frag_queue *fq = data;
+
+ return jhash2((const u32 *)&fq->key.v6,
+ sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static inline int
+ip6frag_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+ const struct frag_v6_compare_key *key = arg->key;
+ const struct inet_frag_queue *fq = ptr;
+
+ return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+static inline void
+ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq)
+{
+ struct net_device *dev = NULL;
+ struct sk_buff *head;
+
+ rcu_read_lock();
+ spin_lock(&fq->q.lock);
+
+ if (fq->q.flags & INET_FRAG_COMPLETE)
+ goto out;
+
+ inet_frag_kill(&fq->q);
+
+ dev = dev_get_by_index_rcu(net, fq->iif);
+ if (!dev)
+ goto out;
+
+ __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
+ __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
+
+ /* Don't send error if the first segment did not arrive. */
+ head = fq->q.fragments;
+ if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !head)
+ goto out;
+
+ head->dev = dev;
+ skb_get(head);
+ spin_unlock(&fq->q.lock);
+
+ icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
+ kfree_skb(head);
+ goto out_rcu_unlock;
+
+out:
+ spin_unlock(&fq->q.lock);
+out_rcu_unlock:
+ rcu_read_unlock();
+ inet_frag_put(&fq->q);
+}
+#endif
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 5e0332014c17..a44156b54ec9 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -33,9 +33,8 @@
#include <net/sock.h>
#include <net/snmp.h>
-#include <net/inet_frag.h>
+#include <net/ipv6_frag.h>
-#include <net/ipv6.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/rawv6.h>
@@ -151,7 +150,7 @@ static void nf_ct_frag6_expire(struct timer_list *t)
fq = container_of(frag, struct frag_queue, q);
net = container_of(fq->q.net, struct net, nf_frag.frags);
- ip6_expire_frag_queue(net, fq);
+ ip6frag_expire_frag_queue(net, fq);
}
/* Creation primitives. */
@@ -622,16 +621,24 @@ static struct pernet_operations nf_ct_net_ops = {
.exit = nf_ct_net_exit,
};
+static const struct rhashtable_params nfct_rhash_params = {
+ .head_offset = offsetof(struct inet_frag_queue, node),
+ .hashfn = ip6frag_key_hashfn,
+ .obj_hashfn = ip6frag_obj_hashfn,
+ .obj_cmpfn = ip6frag_obj_cmpfn,
+ .automatic_shrinking = true,
+};
+
int nf_ct_frag6_init(void)
{
int ret = 0;
- nf_frags.constructor = ip6_frag_init;
+ nf_frags.constructor = ip6frag_init;
nf_frags.destructor = NULL;
nf_frags.qsize = sizeof(struct frag_queue);
nf_frags.frag_expire = nf_ct_frag6_expire;
nf_frags.frags_cache_name = nf_frags_cache_name;
- nf_frags.rhash_params = ip6_rhash_params;
+ nf_frags.rhash_params = nfct_rhash_params;
ret = inet_frags_init(&nf_frags);
if (ret)
goto out;
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index e631be25337e..72dd3e202375 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -14,8 +14,7 @@
#include <linux/skbuff.h>
#include <linux/icmp.h>
#include <linux/sysctl.h>
-#include <net/ipv6.h>
-#include <net/inet_frag.h>
+#include <net/ipv6_frag.h>
#include <linux/netfilter_ipv6.h>
#include <linux/netfilter_bridge.h>
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index b939b94e7e91..6edd2ac8ae4b 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -57,7 +57,7 @@
#include <net/rawv6.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
-#include <net/inet_frag.h>
+#include <net/ipv6_frag.h>
#include <net/inet_ecn.h>
static const char ip6_frag_cache_name[] = "ip6-frags";
@@ -72,61 +72,6 @@ static struct inet_frags ip6_frags;
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
struct net_device *dev);
-void ip6_frag_init(struct inet_frag_queue *q, const void *a)
-{
- struct frag_queue *fq = container_of(q, struct frag_queue, q);
- const struct frag_v6_compare_key *key = a;
-
- q->key.v6 = *key;
- fq->ecn = 0;
-}
-EXPORT_SYMBOL(ip6_frag_init);
-
-void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)
-{
- struct net_device *dev = NULL;
- struct sk_buff *head;
-
- rcu_read_lock();
- spin_lock(&fq->q.lock);
-
- if (fq->q.flags & INET_FRAG_COMPLETE)
- goto out;
-
- inet_frag_kill(&fq->q);
-
- dev = dev_get_by_index_rcu(net, fq->iif);
- if (!dev)
- goto out;
-
- __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
- __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
-
- /* Don't send error if the first segment did not arrive. */
- head = fq->q.fragments;
- if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !head)
- goto out;
-
- /* But use as source device on which LAST ARRIVED
- * segment was received. And do not use fq->dev
- * pointer directly, device might already disappeared.
- */
- head->dev = dev;
- skb_get(head);
- spin_unlock(&fq->q.lock);
-
- icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
- kfree_skb(head);
- goto out_rcu_unlock;
-
-out:
- spin_unlock(&fq->q.lock);
-out_rcu_unlock:
- rcu_read_unlock();
- inet_frag_put(&fq->q);
-}
-EXPORT_SYMBOL(ip6_expire_frag_queue);
-
static void ip6_frag_expire(struct timer_list *t)
{
struct inet_frag_queue *frag = from_timer(frag, t, timer);
@@ -136,7 +81,7 @@ static void ip6_frag_expire(struct timer_list *t)
fq = container_of(frag, struct frag_queue, q);
net = container_of(fq->q.net, struct net, ipv6.frags);
- ip6_expire_frag_queue(net, fq);
+ ip6frag_expire_frag_queue(net, fq);
}
static struct frag_queue *
@@ -696,42 +641,19 @@ static struct pernet_operations ip6_frags_ops = {
.exit = ipv6_frags_exit_net,
};
-static u32 ip6_key_hashfn(const void *data, u32 len, u32 seed)
-{
- return jhash2(data,
- sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
-}
-
-static u32 ip6_obj_hashfn(const void *data, u32 len, u32 seed)
-{
- const struct inet_frag_queue *fq = data;
-
- return jhash2((const u32 *)&fq->key.v6,
- sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
-}
-
-static int ip6_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
-{
- const struct frag_v6_compare_key *key = arg->key;
- const struct inet_frag_queue *fq = ptr;
-
- return !!memcmp(&fq->key, key, sizeof(*key));
-}
-
-const struct rhashtable_params ip6_rhash_params = {
+static const struct rhashtable_params ip6_rhash_params = {
.head_offset = offsetof(struct inet_frag_queue, node),
- .hashfn = ip6_key_hashfn,
- .obj_hashfn = ip6_obj_hashfn,
- .obj_cmpfn = ip6_obj_cmpfn,
+ .hashfn = ip6frag_key_hashfn,
+ .obj_hashfn = ip6frag_obj_hashfn,
+ .obj_cmpfn = ip6frag_obj_cmpfn,
.automatic_shrinking = true,
};
-EXPORT_SYMBOL(ip6_rhash_params);
int __init ipv6_frag_init(void)
{
int ret;
- ip6_frags.constructor = ip6_frag_init;
+ ip6_frags.constructor = ip6frag_init;
ip6_frags.destructor = NULL;
ip6_frags.qsize = sizeof(struct frag_queue);
ip6_frags.frag_expire = ip6_frag_expire;
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index e05bd3e53f0f..3ede65344e4d 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -26,6 +26,7 @@
#include <net/netfilter/nf_conntrack_seqadj.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
+#include <net/ipv6_frag.h>
#ifdef CONFIG_NF_NAT_NEEDED
#include <linux/netfilter/nf_nat.h>
--
2.16.4
^ permalink raw reply related
* [PATCH nf-next 2/2] netfilter: fix IPV6=m CONNTRACK=y link failure
From: Florian Westphal @ 2018-07-12 14:35 UTC (permalink / raw)
To: netfilter-devel; +Cc: netdev, arnd, Florian Westphal
In-Reply-To: <20180712143547.2194-1-fw@strlen.de>
IPV6=m
DEFRAG_IPV6=m
CONNTRACK=y yields:
net/netfilter/nf_conntrack_proto.o: In function `nf_ct_netns_do_get':
net/netfilter/nf_conntrack_proto.c:802: undefined reference to `nf_defrag_ipv6_enable'
net/netfilter/nf_conntrack_proto.o:(.rodata+0x640): undefined reference to `nf_conntrack_l4proto_icmpv6'
After previous patch, DEFRAG_IPV6 and IPV6 are no longer retain any
dependencies, so we can tell Kconfig DEFRAG_IPV6 needs to be built-in as
well, this resolves missing nf_defrag_ipv6_enable.
Second error can be fixed via makefile, just make sure conntrack_proto_ipv6
is part of conntrack module.
based on earlier patch from Arnd Bergmann.
Fixes: 66c524acfb5186 ("netfilter: conntrack: remove l3proto abstraction")
Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
net/ipv6/netfilter/Kconfig | 7 ++-----
net/netfilter/Kconfig | 2 +-
net/netfilter/Makefile | 2 +-
3 files changed, 4 insertions(+), 7 deletions(-)
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 07516d5c2f80..339d0762b027 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -5,10 +5,6 @@
menu "IPv6: Netfilter Configuration"
depends on INET && IPV6 && NETFILTER
-config NF_DEFRAG_IPV6
- tristate
- default n
-
config NF_SOCKET_IPV6
tristate "IPv6 socket lookup support"
help
@@ -349,6 +345,7 @@ config IP6_NF_TARGET_NPT
endif # IP6_NF_NAT
endif # IP6_NF_IPTABLES
-
endmenu
+config NF_DEFRAG_IPV6
+ tristate
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 6c65d756e603..e0ab50c58dc4 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -50,7 +50,7 @@ config NF_CONNTRACK
tristate "Netfilter connection tracking support"
default m if NETFILTER_ADVANCED=n
select NF_DEFRAG_IPV4
- select NF_DEFRAG_IPV6 if IPV6
+ select NF_DEFRAG_IPV6 if IPV6 != n
help
Connection tracking keeps a record of what packets have passed
through your machine, in order to figure out how they are related
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 0b3851e825fa..53bd1ed1228a 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -6,7 +6,7 @@ nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_exp
nf_conntrack_proto_icmp.o \
nf_conntrack_extend.o nf_conntrack_acct.o nf_conntrack_seqadj.o
-nf_conntrack-$(CONFIG_IPV6) += nf_conntrack_proto_icmpv6.o
+nf_conntrack-$(subst m,y,$(CONFIG_IPV6)) += nf_conntrack_proto_icmpv6.o
nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMEOUT) += nf_conntrack_timeout.o
nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o
nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o
--
2.16.4
^ permalink raw reply related
* Re: [BUG] bonded interfaces drop bpdu (stp) frames
From: Jay Vosburgh @ 2018-07-12 14:51 UTC (permalink / raw)
To: =?UTF-8?B?TWFoZXNoIEJhbmRld2FyICjgpK7gpLngpYfgpLYg4KSs4KSC4KSh4KWH4KS14KS+4KSwKQ==?=
Cc: Michal Soltys, linux-netdev
In-Reply-To: <CAF2d9jjK5DdoTgG2YYsZ+M5TBx-C1AcbT4VVmKrEMeJ7+PacnQ@mail.gmail.com>
Mahesh Bandewar (महेश बंडेवार) wrote:
>On Wed, Jul 11, 2018 at 3:23 PM, Michal Soltys <soltys@ziu.info> wrote:
>>
>> Hi,
>>
>> As weird as that sounds, this is what I observed today after bumping
>> kernel version. I have a setup where 2 bonds are attached to linux
>> bridge and physically are connected to two switches doing MSTP (and
>> linux bridge is just passing them).
>>
>> Initially I suspected some changes related to bridge code - but quick
>> peek at the code showed nothing suspicious - and the part of it that
>> explicitly passes stp frames if stp is not enabled has seen little
>> changes (e.g. per-port group_fwd_mask added recently). Furthermore - if
>> regular non-bonded interfaces are attached everything works fine.
>>
>> Just to be sure I detached the bond (802.3ad mode) and checked it with
>> simple tcpdump (ether proto \\stp) - and indeed no hello packets were
>> there (with them being present just fine on active enslaved interface,
>> or on the bond device in earlier kernels).
>>
>> If time permits I'll bisect tommorow to pinpoint the commit, but from
>> quick todays test - 4.9.x is working fine, while 4.16.16 (tested on
>> debian) and 4.17.3 (tested on archlinux) are failing.
>>
>> Unless this is already a known issue (or you have any suggestions what
>> could be responsible).
>>
>I believe these are link-local-multicast messages and sometime back a
>change went into to not pass those frames to the bonding master. This
>could be the side effect of that.
Mahesh, I suspect you're thinking of:
commit b89f04c61efe3b7756434d693b9203cc0cce002e
Author: Chonggang Li <chonggangli@google.com>
Date: Sun Apr 16 12:02:18 2017 -0700
bonding: deliver link-local packets with skb->dev set to link that packets arrived on
Michal, are you able to revert this patch and test?
-J
---
-Jay Vosburgh, jay.vosburgh@canonical.com
^ permalink raw reply
* Re: [PATCH bpf-next 0/6] TCP-BPF callback for listening sockets
From: Lawrence Brakmo @ 2018-07-12 14:59 UTC (permalink / raw)
To: Andrey Ignatov, netdev@vger.kernel.org
Cc: ast@kernel.org, daniel@iogearbox.net, Kernel Team
In-Reply-To: <cover.1531355394.git.rdna@fb.com>
LGTM. Thank you for adding the listen callback and cleaning up the test.
Acked-by: Lawrence Brakmo <brakmo@fb.com>
On 7/11/18, 8:34 PM, "Andrey Ignatov" <rdna@fb.com> wrote:
This patchset adds TCP-BPF callback for listening sockets.
Patch 0001 provides more details and is the main patch in the set.
Patch 0006 adds selftest for the new callback.
Other patches are bug fixes and improvements in TCP-BPF selftest to make it
easier to extend in 0006.
Andrey Ignatov (6):
bpf: Add BPF_SOCK_OPS_TCP_LISTEN_CB
bpf: Sync bpf.h to tools/
selftests/bpf: Fix const'ness in cgroup_helpers
selftests/bpf: Switch test_tcpbpf_user to cgroup_helpers
selftests/bpf: Better verification in test_tcpbpf
selftests/bpf: Test case for BPF_SOCK_OPS_TCP_LISTEN_CB
include/uapi/linux/bpf.h | 3 +
net/ipv4/af_inet.c | 1 +
tools/include/uapi/linux/bpf.h | 3 +
tools/testing/selftests/bpf/Makefile | 1 +
tools/testing/selftests/bpf/cgroup_helpers.c | 6 +-
tools/testing/selftests/bpf/cgroup_helpers.h | 6 +-
tools/testing/selftests/bpf/test_tcpbpf.h | 1 +
.../testing/selftests/bpf/test_tcpbpf_kern.c | 17 ++-
.../testing/selftests/bpf/test_tcpbpf_user.c | 119 +++++++++---------
9 files changed, 88 insertions(+), 69 deletions(-)
--
2.17.1
^ permalink raw reply
* [PATCH net] tls: Stricter error checking in zerocopy sendmsg path
From: Dave Watson @ 2018-07-12 15:03 UTC (permalink / raw)
To: Boris Pismenny, davem@davemloft.net, netdev@vger.kernel.org,
aviadye@mellanox.com, Daniel Borkmann, doronrk, Vakul Garg
In the zerocopy sendmsg() path, there are error checks to revert
the zerocopy if we get any error code. syzkaller has discovered
that tls_push_record can return -ECONNRESET, which is fatal, and
happens after the point at which it is safe to revert the iter,
as we've already passed the memory to do_tcp_sendpages.
Previously this code could return -ENOMEM and we would want to
revert the iter, but AFAIK this no longer returns ENOMEM after
a447da7d004 ("tls: fix waitall behavior in tls_sw_recvmsg"),
so we fail for all error codes.
Reported-by: syzbot+c226690f7b3126c5ee04@syzkaller.appspotmail.com
Reported-by: syzbot+709f2810a6a05f11d4d3@syzkaller.appspotmail.com
Signed-off-by: Dave Watson <davejwatson@fb.com>
Fixes: 3c4d7559159b ("tls: kernel TLS support")
---
net/tls/tls_sw.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 7818011fd250..4618f1c31137 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -440,7 +440,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
ret = tls_push_record(sk, msg->msg_flags, record_type);
if (!ret)
continue;
- if (ret == -EAGAIN)
+ if (ret < 0)
goto send_end;
copied -= try_to_copy;
--
2.17.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox