summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/Makefile2
-rw-r--r--net/core/dev.c77
-rw-r--r--net/core/devlink.c1711
-rw-r--r--net/core/dst.c6
-rw-r--r--net/core/ethtool.c257
-rw-r--r--net/core/filter.c38
-rw-r--r--net/core/flow_dissector.c92
-rw-r--r--net/core/flow_offload.c153
-rw-r--r--net/core/net-sysfs.c12
-rw-r--r--net/core/net_namespace.c38
-rw-r--r--net/core/rtnetlink.c128
-rw-r--r--net/core/scm.c27
-rw-r--r--net/core/skmsg.c25
-rw-r--r--net/core/sock.c199
-rw-r--r--net/core/sysctl_net_core.c18
15 files changed, 2540 insertions, 243 deletions
diff --git a/net/core/Makefile b/net/core/Makefile
index fccd31e0e7f7..f97d6254e564 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -11,7 +11,7 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \
neighbour.o rtnetlink.o utils.o link_watch.o filter.o \
sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \
- fib_notifier.o xdp.o
+ fib_notifier.o xdp.o flow_offload.o
obj-y += net-sysfs.o
obj-$(CONFIG_PAGE_POOL) += page_pool.o
diff --git a/net/core/dev.c b/net/core/dev.c
index 8e276e0192a1..ecbe419e05ab 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7878,6 +7878,63 @@ int dev_get_phys_port_name(struct net_device *dev,
EXPORT_SYMBOL(dev_get_phys_port_name);
/**
+ * dev_get_port_parent_id - Get the device's port parent identifier
+ * @dev: network device
+ * @ppid: pointer to a storage for the port's parent identifier
+ * @recurse: allow/disallow recursion to lower devices
+ *
+ * Get the devices's port parent identifier
+ */
+int dev_get_port_parent_id(struct net_device *dev,
+ struct netdev_phys_item_id *ppid,
+ bool recurse)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+ struct netdev_phys_item_id first = { };
+ struct net_device *lower_dev;
+ struct list_head *iter;
+ int err = -EOPNOTSUPP;
+
+ if (ops->ndo_get_port_parent_id)
+ return ops->ndo_get_port_parent_id(dev, ppid);
+
+ if (!recurse)
+ return err;
+
+ netdev_for_each_lower_dev(dev, lower_dev, iter) {
+ err = dev_get_port_parent_id(lower_dev, ppid, recurse);
+ if (err)
+ break;
+ if (!first.id_len)
+ first = *ppid;
+ else if (memcmp(&first, ppid, sizeof(*ppid)))
+ return -ENODATA;
+ }
+
+ return err;
+}
+EXPORT_SYMBOL(dev_get_port_parent_id);
+
+/**
+ * netdev_port_same_parent_id - Indicate if two network devices have
+ * the same port parent identifier
+ * @a: first network device
+ * @b: second network device
+ */
+bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b)
+{
+ struct netdev_phys_item_id a_id = { };
+ struct netdev_phys_item_id b_id = { };
+
+ if (dev_get_port_parent_id(a, &a_id, true) ||
+ dev_get_port_parent_id(b, &b_id, true))
+ return false;
+
+ return netdev_phys_item_id_same(&a_id, &b_id);
+}
+EXPORT_SYMBOL(netdev_port_same_parent_id);
+
+/**
* dev_change_proto_down - update protocol port state information
* @dev: device
* @proto_down: new value
@@ -7976,35 +8033,41 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
enum bpf_netdev_command query;
struct bpf_prog *prog = NULL;
bpf_op_t bpf_op, bpf_chk;
+ bool offload;
int err;
ASSERT_RTNL();
- query = flags & XDP_FLAGS_HW_MODE ? XDP_QUERY_PROG_HW : XDP_QUERY_PROG;
+ offload = flags & XDP_FLAGS_HW_MODE;
+ query = offload ? XDP_QUERY_PROG_HW : XDP_QUERY_PROG;
bpf_op = bpf_chk = ops->ndo_bpf;
- if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE)))
+ if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE))) {
+ NL_SET_ERR_MSG(extack, "underlying driver does not support XDP in native mode");
return -EOPNOTSUPP;
+ }
if (!bpf_op || (flags & XDP_FLAGS_SKB_MODE))
bpf_op = generic_xdp_install;
if (bpf_op == bpf_chk)
bpf_chk = generic_xdp_install;
if (fd >= 0) {
- if (__dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG) ||
- __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG_HW))
+ if (!offload && __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG)) {
+ NL_SET_ERR_MSG(extack, "native and generic XDP can't be active at the same time");
return -EEXIST;
+ }
if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) &&
- __dev_xdp_query(dev, bpf_op, query))
+ __dev_xdp_query(dev, bpf_op, query)) {
+ NL_SET_ERR_MSG(extack, "XDP program already attached");
return -EBUSY;
+ }
prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP,
bpf_op == ops->ndo_bpf);
if (IS_ERR(prog))
return PTR_ERR(prog);
- if (!(flags & XDP_FLAGS_HW_MODE) &&
- bpf_prog_is_dev_bound(prog->aux)) {
+ if (!offload && bpf_prog_is_dev_bound(prog->aux)) {
NL_SET_ERR_MSG(extack, "using device-bound program without HW_MODE flag is not supported");
bpf_prog_put(prog);
return -EINVAL;
diff --git a/net/core/devlink.c b/net/core/devlink.c
index abb0da9d7b4b..7fbdba547d4f 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -81,6 +81,7 @@ struct devlink_dpipe_header devlink_dpipe_header_ipv6 = {
EXPORT_SYMBOL(devlink_dpipe_header_ipv6);
EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg);
+EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr);
static LIST_HEAD(devlink_list);
@@ -932,6 +933,9 @@ static int devlink_nl_sb_pool_fill(struct sk_buff *msg, struct devlink *devlink,
if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE,
pool_info.threshold_type))
goto nla_put_failure;
+ if (nla_put_u32(msg, DEVLINK_ATTR_SB_POOL_CELL_SIZE,
+ pool_info.cell_size))
+ goto nla_put_failure;
genlmsg_end(msg, hdr);
return 0;
@@ -2697,6 +2701,11 @@ static const struct devlink_param devlink_param_generic[] = {
.name = DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_NAME,
.type = DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_TYPE,
},
+ {
+ .id = DEVLINK_PARAM_GENERIC_ID_WOL,
+ .name = DEVLINK_PARAM_GENERIC_WOL_NAME,
+ .type = DEVLINK_PARAM_GENERIC_WOL_TYPE,
+ },
};
static int devlink_param_generic_verify(const struct devlink_param *param)
@@ -2843,6 +2852,7 @@ nla_put_failure:
}
static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink,
+ unsigned int port_index,
struct devlink_param_item *param_item,
enum devlink_command cmd,
u32 portid, u32 seq, int flags)
@@ -2880,6 +2890,13 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink,
if (devlink_nl_put_handle(msg, devlink))
goto genlmsg_cancel;
+
+ if (cmd == DEVLINK_CMD_PORT_PARAM_GET ||
+ cmd == DEVLINK_CMD_PORT_PARAM_NEW ||
+ cmd == DEVLINK_CMD_PORT_PARAM_DEL)
+ if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, port_index))
+ goto genlmsg_cancel;
+
param_attr = nla_nest_start(msg, DEVLINK_ATTR_PARAM);
if (!param_attr)
goto genlmsg_cancel;
@@ -2922,18 +2939,22 @@ genlmsg_cancel:
}
static void devlink_param_notify(struct devlink *devlink,
+ unsigned int port_index,
struct devlink_param_item *param_item,
enum devlink_command cmd)
{
struct sk_buff *msg;
int err;
- WARN_ON(cmd != DEVLINK_CMD_PARAM_NEW && cmd != DEVLINK_CMD_PARAM_DEL);
+ WARN_ON(cmd != DEVLINK_CMD_PARAM_NEW && cmd != DEVLINK_CMD_PARAM_DEL &&
+ cmd != DEVLINK_CMD_PORT_PARAM_NEW &&
+ cmd != DEVLINK_CMD_PORT_PARAM_DEL);
msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
if (!msg)
return;
- err = devlink_nl_param_fill(msg, devlink, param_item, cmd, 0, 0, 0);
+ err = devlink_nl_param_fill(msg, devlink, port_index, param_item, cmd,
+ 0, 0, 0);
if (err) {
nlmsg_free(msg);
return;
@@ -2962,7 +2983,7 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg,
idx++;
continue;
}
- err = devlink_nl_param_fill(msg, devlink, param_item,
+ err = devlink_nl_param_fill(msg, devlink, 0, param_item,
DEVLINK_CMD_PARAM_GET,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
@@ -3051,7 +3072,7 @@ devlink_param_value_get_from_info(const struct devlink_param *param,
}
static struct devlink_param_item *
-devlink_param_get_from_info(struct devlink *devlink,
+devlink_param_get_from_info(struct list_head *param_list,
struct genl_info *info)
{
char *param_name;
@@ -3060,7 +3081,7 @@ devlink_param_get_from_info(struct devlink *devlink,
return NULL;
param_name = nla_data(info->attrs[DEVLINK_ATTR_PARAM_NAME]);
- return devlink_param_find_by_name(&devlink->param_list, param_name);
+ return devlink_param_find_by_name(param_list, param_name);
}
static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb,
@@ -3071,7 +3092,7 @@ static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb,
struct sk_buff *msg;
int err;
- param_item = devlink_param_get_from_info(devlink, info);
+ param_item = devlink_param_get_from_info(&devlink->param_list, info);
if (!param_item)
return -EINVAL;
@@ -3079,7 +3100,7 @@ static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb,
if (!msg)
return -ENOMEM;
- err = devlink_nl_param_fill(msg, devlink, param_item,
+ err = devlink_nl_param_fill(msg, devlink, 0, param_item,
DEVLINK_CMD_PARAM_GET,
info->snd_portid, info->snd_seq, 0);
if (err) {
@@ -3090,10 +3111,12 @@ static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb,
return genlmsg_reply(msg, info);
}
-static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb,
- struct genl_info *info)
+static int __devlink_nl_cmd_param_set_doit(struct devlink *devlink,
+ unsigned int port_index,
+ struct list_head *param_list,
+ struct genl_info *info,
+ enum devlink_command cmd)
{
- struct devlink *devlink = info->user_ptr[0];
enum devlink_param_type param_type;
struct devlink_param_gset_ctx ctx;
enum devlink_param_cmode cmode;
@@ -3102,7 +3125,7 @@ static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb,
union devlink_param_value value;
int err = 0;
- param_item = devlink_param_get_from_info(devlink, info);
+ param_item = devlink_param_get_from_info(param_list, info);
if (!param_item)
return -EINVAL;
param = param_item->param;
@@ -3142,17 +3165,28 @@ static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb,
return err;
}
- devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW);
+ devlink_param_notify(devlink, port_index, param_item, cmd);
return 0;
}
+static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+
+ return __devlink_nl_cmd_param_set_doit(devlink, 0, &devlink->param_list,
+ info, DEVLINK_CMD_PARAM_NEW);
+}
+
static int devlink_param_register_one(struct devlink *devlink,
- const struct devlink_param *param)
+ unsigned int port_index,
+ struct list_head *param_list,
+ const struct devlink_param *param,
+ enum devlink_command cmd)
{
struct devlink_param_item *param_item;
- if (devlink_param_find_by_name(&devlink->param_list,
- param->name))
+ if (devlink_param_find_by_name(param_list, param->name))
return -EEXIST;
if (param->supported_cmodes == BIT(DEVLINK_PARAM_CMODE_DRIVERINIT))
@@ -3165,24 +3199,111 @@ static int devlink_param_register_one(struct devlink *devlink,
return -ENOMEM;
param_item->param = param;
- list_add_tail(&param_item->list, &devlink->param_list);
- devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW);
+ list_add_tail(&param_item->list, param_list);
+ devlink_param_notify(devlink, port_index, param_item, cmd);
return 0;
}
static void devlink_param_unregister_one(struct devlink *devlink,
- const struct devlink_param *param)
+ unsigned int port_index,
+ struct list_head *param_list,
+ const struct devlink_param *param,
+ enum devlink_command cmd)
{
struct devlink_param_item *param_item;
- param_item = devlink_param_find_by_name(&devlink->param_list,
- param->name);
+ param_item = devlink_param_find_by_name(param_list, param->name);
WARN_ON(!param_item);
- devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_DEL);
+ devlink_param_notify(devlink, port_index, param_item, cmd);
list_del(&param_item->list);
kfree(param_item);
}
+static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg,
+ struct netlink_callback *cb)
+{
+ struct devlink_param_item *param_item;
+ struct devlink_port *devlink_port;
+ 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(devlink_port, &devlink->port_list, list) {
+ list_for_each_entry(param_item,
+ &devlink_port->param_list, list) {
+ if (idx < start) {
+ idx++;
+ continue;
+ }
+ err = devlink_nl_param_fill(msg,
+ devlink_port->devlink,
+ devlink_port->index, param_item,
+ DEVLINK_CMD_PORT_PARAM_GET,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NLM_F_MULTI);
+ 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 int devlink_nl_cmd_port_param_get_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink_port *devlink_port = info->user_ptr[0];
+ struct devlink_param_item *param_item;
+ struct sk_buff *msg;
+ int err;
+
+ param_item = devlink_param_get_from_info(&devlink_port->param_list,
+ info);
+ if (!param_item)
+ return -EINVAL;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ err = devlink_nl_param_fill(msg, devlink_port->devlink,
+ devlink_port->index, param_item,
+ DEVLINK_CMD_PORT_PARAM_GET,
+ info->snd_portid, info->snd_seq, 0);
+ if (err) {
+ nlmsg_free(msg);
+ return err;
+ }
+
+ return genlmsg_reply(msg, info);
+}
+
+static int devlink_nl_cmd_port_param_set_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink_port *devlink_port = info->user_ptr[0];
+
+ return __devlink_nl_cmd_param_set_doit(devlink_port->devlink,
+ devlink_port->index,
+ &devlink_port->param_list, info,
+ DEVLINK_CMD_PORT_PARAM_NEW);
+}
+
static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg,
struct devlink *devlink,
struct devlink_snapshot *snapshot)
@@ -3597,6 +3718,1126 @@ out:
return 0;
}
+struct devlink_info_req {
+ struct sk_buff *msg;
+};
+
+int devlink_info_driver_name_put(struct devlink_info_req *req, const char *name)
+{
+ return nla_put_string(req->msg, DEVLINK_ATTR_INFO_DRIVER_NAME, name);
+}
+EXPORT_SYMBOL_GPL(devlink_info_driver_name_put);
+
+int devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn)
+{
+ return nla_put_string(req->msg, DEVLINK_ATTR_INFO_SERIAL_NUMBER, sn);
+}
+EXPORT_SYMBOL_GPL(devlink_info_serial_number_put);
+
+static int devlink_info_version_put(struct devlink_info_req *req, int attr,
+ const char *version_name,
+ const char *version_value)
+{
+ struct nlattr *nest;
+ int err;
+
+ nest = nla_nest_start(req->msg, attr);
+ if (!nest)
+ return -EMSGSIZE;
+
+ err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_NAME,
+ version_name);
+ if (err)
+ goto nla_put_failure;
+
+ err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_VALUE,
+ version_value);
+ if (err)
+ goto nla_put_failure;
+
+ nla_nest_end(req->msg, nest);
+
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(req->msg, nest);
+ return err;
+}
+
+int devlink_info_version_fixed_put(struct devlink_info_req *req,
+ const char *version_name,
+ const char *version_value)
+{
+ return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_FIXED,
+ version_name, version_value);
+}
+EXPORT_SYMBOL_GPL(devlink_info_version_fixed_put);
+
+int devlink_info_version_stored_put(struct devlink_info_req *req,
+ const char *version_name,
+ const char *version_value)
+{
+ return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED,
+ version_name, version_value);
+}
+EXPORT_SYMBOL_GPL(devlink_info_version_stored_put);
+
+int devlink_info_version_running_put(struct devlink_info_req *req,
+ const char *version_name,
+ const char *version_value)
+{
+ return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING,
+ version_name, version_value);
+}
+EXPORT_SYMBOL_GPL(devlink_info_version_running_put);
+
+static int
+devlink_nl_info_fill(struct sk_buff *msg, struct devlink *devlink,
+ enum devlink_command cmd, u32 portid,
+ u32 seq, int flags, struct netlink_ext_ack *extack)
+{
+ struct devlink_info_req req;
+ void *hdr;
+ int err;
+
+ hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+ if (!hdr)
+ return -EMSGSIZE;
+
+ err = -EMSGSIZE;
+ if (devlink_nl_put_handle(msg, devlink))
+ goto err_cancel_msg;
+
+ req.msg = msg;
+ err = devlink->ops->info_get(devlink, &req, extack);
+ if (err)
+ goto err_cancel_msg;
+
+ genlmsg_end(msg, hdr);
+ return 0;
+
+err_cancel_msg:
+ genlmsg_cancel(msg, hdr);
+ return err;
+}
+
+static int devlink_nl_cmd_info_get_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ struct sk_buff *msg;
+ int err;
+
+ if (!devlink->ops || !devlink->ops->info_get)
+ return -EOPNOTSUPP;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET,
+ info->snd_portid, info->snd_seq, 0,
+ info->extack);
+ if (err) {
+ nlmsg_free(msg);
+ return err;
+ }
+
+ return genlmsg_reply(msg, info);
+}
+
+static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg,
+ struct netlink_callback *cb)
+{
+ 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;
+ if (idx < start) {
+ idx++;
+ continue;
+ }
+
+ mutex_lock(&devlink->lock);
+ err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ cb->extack);
+ mutex_unlock(&devlink->lock);
+ if (err)
+ break;
+ idx++;
+ }
+ mutex_unlock(&devlink_mutex);
+
+ cb->args[0] = idx;
+ return msg->len;
+}
+
+struct devlink_fmsg_item {
+ struct list_head list;
+ int attrtype;
+ u8 nla_type;
+ u16 len;
+ int value[0];
+};
+
+struct devlink_fmsg {
+ struct list_head item_list;
+};
+
+static struct devlink_fmsg *devlink_fmsg_alloc(void)
+{
+ struct devlink_fmsg *fmsg;
+
+ fmsg = kzalloc(sizeof(*fmsg), GFP_KERNEL);
+ if (!fmsg)
+ return NULL;
+
+ INIT_LIST_HEAD(&fmsg->item_list);
+
+ return fmsg;
+}
+
+static void devlink_fmsg_free(struct devlink_fmsg *fmsg)
+{
+ struct devlink_fmsg_item *item, *tmp;
+
+ list_for_each_entry_safe(item, tmp, &fmsg->item_list, list) {
+ list_del(&item->list);
+ kfree(item);
+ }
+ kfree(fmsg);
+}
+
+static int devlink_fmsg_nest_common(struct devlink_fmsg *fmsg,
+ int attrtype)
+{
+ struct devlink_fmsg_item *item;
+
+ item = kzalloc(sizeof(*item), GFP_KERNEL);
+ if (!item)
+ return -ENOMEM;
+
+ item->attrtype = attrtype;
+ list_add_tail(&item->list, &fmsg->item_list);
+
+ return 0;
+}
+
+int devlink_fmsg_obj_nest_start(struct devlink_fmsg *fmsg)
+{
+ return devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_OBJ_NEST_START);
+}
+EXPORT_SYMBOL_GPL(devlink_fmsg_obj_nest_start);
+
+static int devlink_fmsg_nest_end(struct devlink_fmsg *fmsg)
+{
+ return devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_NEST_END);
+}
+
+int devlink_fmsg_obj_nest_end(struct devlink_fmsg *fmsg)
+{
+ return devlink_fmsg_nest_end(fmsg);
+}
+EXPORT_SYMBOL_GPL(devlink_fmsg_obj_nest_end);
+
+#define DEVLINK_FMSG_MAX_SIZE (GENLMSG_DEFAULT_SIZE - GENL_HDRLEN - NLA_HDRLEN)
+
+static int devlink_fmsg_put_name(struct devlink_fmsg *fmsg, const char *name)
+{
+ struct devlink_fmsg_item *item;
+
+ if (strlen(name) + 1 > DEVLINK_FMSG_MAX_SIZE)
+ return -EMSGSIZE;
+
+ item = kzalloc(sizeof(*item) + strlen(name) + 1, GFP_KERNEL);
+ if (!item)
+ return -ENOMEM;
+
+ item->nla_type = NLA_NUL_STRING;
+ item->len = strlen(name) + 1;
+ item->attrtype = DEVLINK_ATTR_FMSG_OBJ_NAME;
+ memcpy(&item->value, name, item->len);
+ list_add_tail(&item->list, &fmsg->item_list);
+
+ return 0;
+}
+
+int devlink_fmsg_pair_nest_start(struct devlink_fmsg *fmsg, const char *name)
+{
+ int err;
+
+ err = devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_PAIR_NEST_START);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_put_name(fmsg, name);
+ if (err)
+ return err;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_fmsg_pair_nest_start);
+
+int devlink_fmsg_pair_nest_end(struct devlink_fmsg *fmsg)
+{
+ return devlink_fmsg_nest_end(fmsg);
+}
+EXPORT_SYMBOL_GPL(devlink_fmsg_pair_nest_end);
+
+int devlink_fmsg_arr_pair_nest_start(struct devlink_fmsg *fmsg,
+ const char *name)
+{
+ int err;
+
+ err = devlink_fmsg_pair_nest_start(fmsg, name);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_ARR_NEST_START);
+ if (err)
+ return err;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_fmsg_arr_pair_nest_start);
+
+int devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg)
+{
+ int err;
+
+ err = devlink_fmsg_nest_end(fmsg);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_nest_end(fmsg);
+ if (err)
+ return err;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_fmsg_arr_pair_nest_end);
+
+static int devlink_fmsg_put_value(struct devlink_fmsg *fmsg,
+ const void *value, u16 value_len,
+ u8 value_nla_type)
+{
+ struct devlink_fmsg_item *item;
+
+ if (value_len > DEVLINK_FMSG_MAX_SIZE)
+ return -EMSGSIZE;
+
+ item = kzalloc(sizeof(*item) + value_len, GFP_KERNEL);
+ if (!item)
+ return -ENOMEM;
+
+ item->nla_type = value_nla_type;
+ item->len = value_len;
+ item->attrtype = DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA;
+ memcpy(&item->value, value, item->len);
+ list_add_tail(&item->list, &fmsg->item_list);
+
+ return 0;
+}
+
+int devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value)
+{
+ return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_FLAG);
+}
+EXPORT_SYMBOL_GPL(devlink_fmsg_bool_put);
+
+int devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value)
+{
+ return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U8);
+}
+EXPORT_SYMBOL_GPL(devlink_fmsg_u8_put);
+
+int devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value)
+{
+ return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U32);
+}
+EXPORT_SYMBOL_GPL(devlink_fmsg_u32_put);
+
+int devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value)
+{
+ return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U64);
+}
+EXPORT_SYMBOL_GPL(devlink_fmsg_u64_put);
+
+int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value)
+{
+ return devlink_fmsg_put_value(fmsg, value, strlen(value) + 1,
+ NLA_NUL_STRING);
+}
+EXPORT_SYMBOL_GPL(devlink_fmsg_string_put);
+
+int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value,
+ u16 value_len)
+{
+ return devlink_fmsg_put_value(fmsg, value, value_len, NLA_BINARY);
+}
+EXPORT_SYMBOL_GPL(devlink_fmsg_binary_put);
+
+int devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name,
+ bool value)
+{
+ int err;
+
+ err = devlink_fmsg_pair_nest_start(fmsg, name);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_bool_put(fmsg, value);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_pair_nest_end(fmsg);
+ if (err)
+ return err;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_fmsg_bool_pair_put);
+
+int devlink_fmsg_u8_pair_put(struct devlink_fmsg *fmsg, const char *name,
+ u8 value)
+{
+ int err;
+
+ err = devlink_fmsg_pair_nest_start(fmsg, name);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_u8_put(fmsg, value);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_pair_nest_end(fmsg);
+ if (err)
+ return err;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_fmsg_u8_pair_put);
+
+int devlink_fmsg_u32_pair_put(struct devlink_fmsg *fmsg, const char *name,
+ u32 value)
+{
+ int err;
+
+ err = devlink_fmsg_pair_nest_start(fmsg, name);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_u32_put(fmsg, value);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_pair_nest_end(fmsg);
+ if (err)
+ return err;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_fmsg_u32_pair_put);
+
+int devlink_fmsg_u64_pair_put(struct devlink_fmsg *fmsg, const char *name,
+ u64 value)
+{
+ int err;
+
+ err = devlink_fmsg_pair_nest_start(fmsg, name);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_u64_put(fmsg, value);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_pair_nest_end(fmsg);
+ if (err)
+ return err;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_fmsg_u64_pair_put);
+
+int devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name,
+ const char *value)
+{
+ int err;
+
+ err = devlink_fmsg_pair_nest_start(fmsg, name);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_string_put(fmsg, value);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_pair_nest_end(fmsg);
+ if (err)
+ return err;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_fmsg_string_pair_put);
+
+int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name,
+ const void *value, u16 value_len)
+{
+ int err;
+
+ err = devlink_fmsg_pair_nest_start(fmsg, name);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_binary_put(fmsg, value, value_len);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_pair_nest_end(fmsg);
+ if (err)
+ return err;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_put);
+
+static int
+devlink_fmsg_item_fill_type(struct devlink_fmsg_item *msg, struct sk_buff *skb)
+{
+ switch (msg->nla_type) {
+ case NLA_FLAG:
+ case NLA_U8:
+ case NLA_U32:
+ case NLA_U64:
+ case NLA_NUL_STRING:
+ case NLA_BINARY:
+ return nla_put_u8(skb, DEVLINK_ATTR_FMSG_OBJ_VALUE_TYPE,
+ msg->nla_type);
+ default:
+ return -EINVAL;
+ }
+}
+
+static int
+devlink_fmsg_item_fill_data(struct devlink_fmsg_item *msg, struct sk_buff *skb)
+{
+ int attrtype = DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA;
+ u8 tmp;
+
+ switch (msg->nla_type) {
+ case NLA_FLAG:
+ /* Always provide flag data, regardless of its value */
+ tmp = *(bool *) msg->value;
+
+ return nla_put_u8(skb, attrtype, tmp);
+ case NLA_U8:
+ return nla_put_u8(skb, attrtype, *(u8 *) msg->value);
+ case NLA_U32:
+ return nla_put_u32(skb, attrtype, *(u32 *) msg->value);
+ case NLA_U64:
+ return nla_put_u64_64bit(skb, attrtype, *(u64 *) msg->value,
+ DEVLINK_ATTR_PAD);
+ case NLA_NUL_STRING:
+ return nla_put_string(skb, attrtype, (char *) &msg->value);
+ case NLA_BINARY:
+ return nla_put(skb, attrtype, msg->len, (void *) &msg->value);
+ default:
+ return -EINVAL;
+ }
+}
+
+static int
+devlink_fmsg_prepare_skb(struct devlink_fmsg *fmsg, struct sk_buff *skb,
+ int *start)
+{
+ struct devlink_fmsg_item *item;
+ struct nlattr *fmsg_nlattr;
+ int i = 0;
+ int err;
+
+ fmsg_nlattr = nla_nest_start(skb, DEVLINK_ATTR_FMSG);
+ if (!fmsg_nlattr)
+ return -EMSGSIZE;
+
+ list_for_each_entry(item, &fmsg->item_list, list) {
+ if (i < *start) {
+ i++;
+ continue;
+ }
+
+ switch (item->attrtype) {
+ case DEVLINK_ATTR_FMSG_OBJ_NEST_START:
+ case DEVLINK_ATTR_FMSG_PAIR_NEST_START:
+ case DEVLINK_ATTR_FMSG_ARR_NEST_START:
+ case DEVLINK_ATTR_FMSG_NEST_END:
+ err = nla_put_flag(skb, item->attrtype);
+ break;
+ case DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA:
+ err = devlink_fmsg_item_fill_type(item, skb);
+ if (err)
+ break;
+ err = devlink_fmsg_item_fill_data(item, skb);
+ break;
+ case DEVLINK_ATTR_FMSG_OBJ_NAME:
+ err = nla_put_string(skb, item->attrtype,
+ (char *) &item->value);
+ break;
+ default:
+ err = -EINVAL;
+ break;
+ }
+ if (!err)
+ *start = ++i;
+ else
+ break;
+ }
+
+ nla_nest_end(skb, fmsg_nlattr);
+ return err;
+}
+
+static int devlink_fmsg_snd(struct devlink_fmsg *fmsg,
+ struct genl_info *info,
+ enum devlink_command cmd, int flags)
+{
+ struct nlmsghdr *nlh;
+ struct sk_buff *skb;
+ bool last = false;
+ int index = 0;
+ void *hdr;
+ int err;
+
+ while (!last) {
+ int tmp_index = index;
+
+ skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!skb)
+ return -ENOMEM;
+
+ hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
+ &devlink_nl_family, flags | NLM_F_MULTI, cmd);
+ if (!hdr) {
+ err = -EMSGSIZE;
+ goto nla_put_failure;
+ }
+
+ err = devlink_fmsg_prepare_skb(fmsg, skb, &index);
+ if (!err)
+ last = true;
+ else if (err != -EMSGSIZE || tmp_index == index)
+ goto nla_put_failure;
+
+ genlmsg_end(skb, hdr);
+ err = genlmsg_reply(skb, info);
+ if (err)
+ return err;
+ }
+
+ skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!skb)
+ return -ENOMEM;
+ nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq,
+ NLMSG_DONE, 0, flags | NLM_F_MULTI);
+ if (!nlh) {
+ err = -EMSGSIZE;
+ goto nla_put_failure;
+ }
+ err = genlmsg_reply(skb, info);
+ if (err)
+ return err;
+
+ return 0;
+
+nla_put_failure:
+ nlmsg_free(skb);
+ return err;
+}
+
+struct devlink_health_reporter {
+ struct list_head list;
+ void *priv;
+ const struct devlink_health_reporter_ops *ops;
+ struct devlink *devlink;
+ struct devlink_fmsg *dump_fmsg;
+ struct mutex dump_lock; /* lock parallel read/write from dump buffers */
+ u64 graceful_period;
+ bool auto_recover;
+ u8 health_state;
+ u64 dump_ts;
+ u64 error_count;
+ u64 recovery_count;
+ u64 last_recovery_ts;
+};
+
+enum devlink_health_reporter_state {
+ DEVLINK_HEALTH_REPORTER_STATE_HEALTHY,
+ DEVLINK_HEALTH_REPORTER_STATE_ERROR,
+};
+
+void *
+devlink_health_reporter_priv(struct devlink_health_reporter *reporter)
+{
+ return reporter->priv;
+}
+EXPORT_SYMBOL_GPL(devlink_health_reporter_priv);
+
+static struct devlink_health_reporter *
+devlink_health_reporter_find_by_name(struct devlink *devlink,
+ const char *reporter_name)
+{
+ struct devlink_health_reporter *reporter;
+
+ list_for_each_entry(reporter, &devlink->reporter_list, list)
+ if (!strcmp(reporter->ops->name, reporter_name))
+ return reporter;
+ return NULL;
+}
+
+/**
+ * devlink_health_reporter_create - create devlink health reporter
+ *
+ * @devlink: devlink
+ * @ops: ops
+ * @graceful_period: to avoid recovery loops, in msecs
+ * @auto_recover: auto recover when error occurs
+ * @priv: priv
+ */
+struct devlink_health_reporter *
+devlink_health_reporter_create(struct devlink *devlink,
+ const struct devlink_health_reporter_ops *ops,
+ u64 graceful_period, bool auto_recover,
+ void *priv)
+{
+ struct devlink_health_reporter *reporter;
+
+ mutex_lock(&devlink->lock);
+ if (devlink_health_reporter_find_by_name(devlink, ops->name)) {
+ reporter = ERR_PTR(-EEXIST);
+ goto unlock;
+ }
+
+ if (WARN_ON(auto_recover && !ops->recover) ||
+ WARN_ON(graceful_period && !ops->recover)) {
+ reporter = ERR_PTR(-EINVAL);
+ goto unlock;
+ }
+
+ reporter = kzalloc(sizeof(*reporter), GFP_KERNEL);
+ if (!reporter) {
+ reporter = ERR_PTR(-ENOMEM);
+ goto unlock;
+ }
+
+ reporter->priv = priv;
+ reporter->ops = ops;
+ reporter->devlink = devlink;
+ reporter->graceful_period = graceful_period;
+ reporter->auto_recover = auto_recover;
+ mutex_init(&reporter->dump_lock);
+ list_add_tail(&reporter->list, &devlink->reporter_list);
+unlock:
+ mutex_unlock(&devlink->lock);
+ return reporter;
+}
+EXPORT_SYMBOL_GPL(devlink_health_reporter_create);
+
+/**
+ * devlink_health_reporter_destroy - destroy devlink health reporter
+ *
+ * @reporter: devlink health reporter to destroy
+ */
+void
+devlink_health_reporter_destroy(struct devlink_health_reporter *reporter)
+{
+ mutex_lock(&reporter->devlink->lock);
+ list_del(&reporter->list);
+ mutex_unlock(&reporter->devlink->lock);
+ if (reporter->dump_fmsg)
+ devlink_fmsg_free(reporter->dump_fmsg);
+ kfree(reporter);
+}
+EXPORT_SYMBOL_GPL(devlink_health_reporter_destroy);
+
+static int
+devlink_health_reporter_recover(struct devlink_health_reporter *reporter,
+ void *priv_ctx)
+{
+ int err;
+
+ if (!reporter->ops->recover)
+ return -EOPNOTSUPP;
+
+ err = reporter->ops->recover(reporter, priv_ctx);
+ if (err)
+ return err;
+
+ reporter->recovery_count++;
+ reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_HEALTHY;
+ reporter->last_recovery_ts = jiffies;
+
+ return 0;
+}
+
+static void
+devlink_health_dump_clear(struct devlink_health_reporter *reporter)
+{
+ if (!reporter->dump_fmsg)
+ return;
+ devlink_fmsg_free(reporter->dump_fmsg);
+ reporter->dump_fmsg = NULL;
+}
+
+static int devlink_health_do_dump(struct devlink_health_reporter *reporter,
+ void *priv_ctx)
+{
+ int err;
+
+ if (!reporter->ops->dump)
+ return 0;
+
+ if (reporter->dump_fmsg)
+ return 0;
+
+ reporter->dump_fmsg = devlink_fmsg_alloc();
+ if (!reporter->dump_fmsg) {
+ err = -ENOMEM;
+ return err;
+ }
+
+ err = devlink_fmsg_obj_nest_start(reporter->dump_fmsg);
+ if (err)
+ goto dump_err;
+
+ err = reporter->ops->dump(reporter, reporter->dump_fmsg,
+ priv_ctx);
+ if (err)
+ goto dump_err;
+
+ err = devlink_fmsg_obj_nest_end(reporter->dump_fmsg);
+ if (err)
+ goto dump_err;
+
+ reporter->dump_ts = jiffies;
+
+ return 0;
+
+dump_err:
+ devlink_health_dump_clear(reporter);
+ return err;
+}
+
+int devlink_health_report(struct devlink_health_reporter *reporter,
+ const char *msg, void *priv_ctx)
+{
+ struct devlink *devlink = reporter->devlink;
+
+ /* write a log message of the current error */
+ WARN_ON(!msg);
+ trace_devlink_health_report(devlink, reporter->ops->name, msg);
+ reporter->error_count++;
+
+ /* abort if the previous error wasn't recovered */
+ if (reporter->auto_recover &&
+ (reporter->health_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY ||
+ jiffies - reporter->last_recovery_ts <
+ msecs_to_jiffies(reporter->graceful_period))) {
+ trace_devlink_health_recover_aborted(devlink,
+ reporter->ops->name,
+ reporter->health_state,
+ jiffies -
+ reporter->last_recovery_ts);
+ return -ECANCELED;
+ }
+
+ reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR;
+
+ mutex_lock(&reporter->dump_lock);
+ /* store current dump of current error, for later analysis */
+ devlink_health_do_dump(reporter, priv_ctx);
+ mutex_unlock(&reporter->dump_lock);
+
+ if (reporter->auto_recover)
+ return devlink_health_reporter_recover(reporter, priv_ctx);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_health_report);
+
+static struct devlink_health_reporter *
+devlink_health_reporter_get_from_info(struct devlink *devlink,
+ struct genl_info *info)
+{
+ char *reporter_name;
+
+ if (!info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME])
+ return NULL;
+
+ reporter_name =
+ nla_data(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]);
+ return devlink_health_reporter_find_by_name(devlink, reporter_name);
+}
+
+static int
+devlink_nl_health_reporter_fill(struct sk_buff *msg,
+ struct devlink *devlink,
+ struct devlink_health_reporter *reporter,
+ enum devlink_command cmd, u32 portid,
+ u32 seq, int flags)
+{
+ struct nlattr *reporter_attr;
+ void *hdr;
+
+ hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+ if (!hdr)
+ return -EMSGSIZE;
+
+ if (devlink_nl_put_handle(msg, devlink))
+ goto genlmsg_cancel;
+
+ reporter_attr = nla_nest_start(msg, DEVLINK_ATTR_HEALTH_REPORTER);
+ if (!reporter_attr)
+ goto genlmsg_cancel;
+ if (nla_put_string(msg, DEVLINK_ATTR_HEALTH_REPORTER_NAME,
+ reporter->ops->name))
+ goto reporter_nest_cancel;
+ if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_STATE,
+ reporter->health_state))
+ goto reporter_nest_cancel;
+ if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_ERR,
+ reporter->error_count, DEVLINK_ATTR_PAD))
+ goto reporter_nest_cancel;
+ if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_RECOVER,
+ reporter->recovery_count, DEVLINK_ATTR_PAD))
+ goto reporter_nest_cancel;
+ if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD,
+ reporter->graceful_period,
+ DEVLINK_ATTR_PAD))
+ goto reporter_nest_cancel;
+ if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER,
+ reporter->auto_recover))
+ goto reporter_nest_cancel;
+ if (reporter->dump_fmsg &&
+ nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS,
+ jiffies_to_msecs(reporter->dump_ts),
+ DEVLINK_ATTR_PAD))
+ goto reporter_nest_cancel;
+
+ nla_nest_end(msg, reporter_attr);
+ genlmsg_end(msg, hdr);
+ return 0;
+
+reporter_nest_cancel:
+ nla_nest_end(msg, reporter_attr);
+genlmsg_cancel:
+ genlmsg_cancel(msg, hdr);
+ return -EMSGSIZE;
+}
+
+static int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ struct devlink_health_reporter *reporter;
+ struct sk_buff *msg;
+ int err;
+
+ reporter = devlink_health_reporter_get_from_info(devlink, info);
+ if (!reporter)
+ return -EINVAL;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ err = devlink_nl_health_reporter_fill(msg, devlink, reporter,
+ DEVLINK_CMD_HEALTH_REPORTER_GET,
+ info->snd_portid, info->snd_seq,
+ 0);
+ if (err) {
+ nlmsg_free(msg);
+ return err;
+ }
+
+ return genlmsg_reply(msg, info);
+}
+
+static int
+devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg,
+ struct netlink_callback *cb)
+{
+ struct devlink_health_reporter *reporter;
+ 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(reporter, &devlink->reporter_list,
+ list) {
+ if (idx < start) {
+ idx++;
+ continue;
+ }
+ err = devlink_nl_health_reporter_fill(msg, devlink,
+ reporter,
+ DEVLINK_CMD_HEALTH_REPORTER_GET,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NLM_F_MULTI);
+ 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 int
+devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ struct devlink_health_reporter *reporter;
+
+ reporter = devlink_health_reporter_get_from_info(devlink, info);
+ if (!reporter)
+ return -EINVAL;
+
+ if (!reporter->ops->recover &&
+ (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] ||
+ info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]))
+ return -EOPNOTSUPP;
+
+ if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD])
+ reporter->graceful_period =
+ nla_get_u64(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]);
+
+ if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER])
+ reporter->auto_recover =
+ nla_get_u8(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]);
+
+ return 0;
+}
+
+static int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ struct devlink_health_reporter *reporter;
+
+ reporter = devlink_health_reporter_get_from_info(devlink, info);
+ if (!reporter)
+ return -EINVAL;
+
+ return devlink_health_reporter_recover(reporter, NULL);
+}
+
+static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ struct devlink_health_reporter *reporter;
+ struct devlink_fmsg *fmsg;
+ int err;
+
+ reporter = devlink_health_reporter_get_from_info(devlink, info);
+ if (!reporter)
+ return -EINVAL;
+
+ if (!reporter->ops->diagnose)
+ return -EOPNOTSUPP;
+
+ fmsg = devlink_fmsg_alloc();
+ if (!fmsg)
+ return -ENOMEM;
+
+ err = devlink_fmsg_obj_nest_start(fmsg);
+ if (err)
+ goto out;
+
+ err = reporter->ops->diagnose(reporter, fmsg);
+ if (err)
+ goto out;
+
+ err = devlink_fmsg_obj_nest_end(fmsg);
+ if (err)
+ goto out;
+
+ err = devlink_fmsg_snd(fmsg, info,
+ DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, 0);
+
+out:
+ devlink_fmsg_free(fmsg);
+ return err;
+}
+
+static int devlink_nl_cmd_health_reporter_dump_get_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ struct devlink_health_reporter *reporter;
+ int err;
+
+ reporter = devlink_health_reporter_get_from_info(devlink, info);
+ if (!reporter)
+ return -EINVAL;
+
+ if (!reporter->ops->dump)
+ return -EOPNOTSUPP;
+
+ mutex_lock(&reporter->dump_lock);
+ err = devlink_health_do_dump(reporter, NULL);
+ if (err)
+ goto out;
+
+ err = devlink_fmsg_snd(reporter->dump_fmsg, info,
+ DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, 0);
+
+out:
+ mutex_unlock(&reporter->dump_lock);
+ return err;
+}
+
+static int
+devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ struct devlink_health_reporter *reporter;
+
+ reporter = devlink_health_reporter_get_from_info(devlink, info);
+ if (!reporter)
+ return -EINVAL;
+
+ if (!reporter->ops->dump)
+ return -EOPNOTSUPP;
+
+ mutex_lock(&reporter->dump_lock);
+ devlink_health_dump_clear(reporter);
+ mutex_unlock(&reporter->dump_lock);
+ 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 },
@@ -3622,6 +4863,9 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
[DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 },
[DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING },
[DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING },
+ [DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64 },
+ [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 },
};
static const struct genl_ops devlink_nl_ops[] = {
@@ -3821,6 +5065,21 @@ static const struct genl_ops devlink_nl_ops[] = {
.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
},
{
+ .cmd = DEVLINK_CMD_PORT_PARAM_GET,
+ .doit = devlink_nl_cmd_port_param_get_doit,
+ .dumpit = devlink_nl_cmd_port_param_get_dumpit,
+ .policy = devlink_nl_policy,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+ /* can be retrieved by unprivileged users */
+ },
+ {
+ .cmd = DEVLINK_CMD_PORT_PARAM_SET,
+ .doit = devlink_nl_cmd_port_param_set_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+ },
+ {
.cmd = DEVLINK_CMD_REGION_GET,
.doit = devlink_nl_cmd_region_get_doit,
.dumpit = devlink_nl_cmd_region_get_dumpit,
@@ -3842,6 +5101,59 @@ static const struct genl_ops devlink_nl_ops[] = {
.flags = GENL_ADMIN_PERM,
.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
},
+ {
+ .cmd = DEVLINK_CMD_INFO_GET,
+ .doit = devlink_nl_cmd_info_get_doit,
+ .dumpit = devlink_nl_cmd_info_get_dumpit,
+ .policy = devlink_nl_policy,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ /* can be retrieved by unprivileged users */
+ },
+ {
+ .cmd = DEVLINK_CMD_HEALTH_REPORTER_GET,
+ .doit = devlink_nl_cmd_health_reporter_get_doit,
+ .dumpit = devlink_nl_cmd_health_reporter_get_dumpit,
+ .policy = devlink_nl_policy,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ /* can be retrieved by unprivileged users */
+ },
+ {
+ .cmd = DEVLINK_CMD_HEALTH_REPORTER_SET,
+ .doit = devlink_nl_cmd_health_reporter_set_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
+ {
+ .cmd = DEVLINK_CMD_HEALTH_REPORTER_RECOVER,
+ .doit = devlink_nl_cmd_health_reporter_recover_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
+ {
+ .cmd = DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE,
+ .doit = devlink_nl_cmd_health_reporter_diagnose_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
+ {
+ .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET,
+ .doit = devlink_nl_cmd_health_reporter_dump_get_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+ DEVLINK_NL_FLAG_NO_LOCK,
+ },
+ {
+ .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR,
+ .doit = devlink_nl_cmd_health_reporter_dump_clear_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+ DEVLINK_NL_FLAG_NO_LOCK,
+ },
};
static struct genl_family devlink_nl_family __ro_after_init = {
@@ -3882,6 +5194,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
INIT_LIST_HEAD(&devlink->resource_list);
INIT_LIST_HEAD(&devlink->param_list);
INIT_LIST_HEAD(&devlink->region_list);
+ INIT_LIST_HEAD(&devlink->reporter_list);
mutex_init(&devlink->lock);
return devlink;
}
@@ -3954,6 +5267,7 @@ int devlink_port_register(struct devlink *devlink,
devlink_port->index = port_index;
devlink_port->registered = true;
list_add_tail(&devlink_port->list, &devlink->port_list);
+ INIT_LIST_HEAD(&devlink_port->param_list);
mutex_unlock(&devlink->lock);
devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
return 0;
@@ -4471,18 +5785,23 @@ out:
}
EXPORT_SYMBOL_GPL(devlink_resource_occ_get_unregister);
-/**
- * devlink_params_register - register configuration parameters
- *
- * @devlink: devlink
- * @params: configuration parameters array
- * @params_count: number of parameters provided
- *
- * Register the configuration parameters supported by the driver.
- */
-int devlink_params_register(struct devlink *devlink,
- const struct devlink_param *params,
- size_t params_count)
+static int devlink_param_verify(const struct devlink_param *param)
+{
+ if (!param || !param->name || !param->supported_cmodes)
+ return -EINVAL;
+ if (param->generic)
+ return devlink_param_generic_verify(param);
+ else
+ return devlink_param_driver_verify(param);
+}
+
+static int __devlink_params_register(struct devlink *devlink,
+ unsigned int port_index,
+ struct list_head *param_list,
+ const struct devlink_param *params,
+ size_t params_count,
+ enum devlink_command reg_cmd,
+ enum devlink_command unreg_cmd)
{
const struct devlink_param *param = params;
int i;
@@ -4490,20 +5809,12 @@ int devlink_params_register(struct devlink *devlink,
mutex_lock(&devlink->lock);
for (i = 0; i < params_count; i++, param++) {
- if (!param || !param->name || !param->supported_cmodes) {
- err = -EINVAL;
+ err = devlink_param_verify(param);
+ if (err)
goto rollback;
- }
- if (param->generic) {
- err = devlink_param_generic_verify(param);
- if (err)
- goto rollback;
- } else {
- err = devlink_param_driver_verify(param);
- if (err)
- goto rollback;
- }
- err = devlink_param_register_one(devlink, param);
+
+ err = devlink_param_register_one(devlink, port_index,
+ param_list, param, reg_cmd);
if (err)
goto rollback;
}
@@ -4515,11 +5826,48 @@ rollback:
if (!i)
goto unlock;
for (param--; i > 0; i--, param--)
- devlink_param_unregister_one(devlink, param);
+ devlink_param_unregister_one(devlink, port_index, param_list,
+ param, unreg_cmd);
unlock:
mutex_unlock(&devlink->lock);
return err;
}
+
+static void __devlink_params_unregister(struct devlink *devlink,
+ unsigned int port_index,
+ struct list_head *param_list,
+ const struct devlink_param *params,
+ size_t params_count,
+ enum devlink_command cmd)
+{
+ const struct devlink_param *param = params;
+ int i;
+
+ mutex_lock(&devlink->lock);
+ for (i = 0; i < params_count; i++, param++)
+ devlink_param_unregister_one(devlink, 0, param_list, param,
+ cmd);
+ mutex_unlock(&devlink->lock);
+}
+
+/**
+ * devlink_params_register - register configuration parameters
+ *
+ * @devlink: devlink
+ * @params: configuration parameters array
+ * @params_count: number of parameters provided
+ *
+ * Register the configuration parameters supported by the driver.
+ */
+int devlink_params_register(struct devlink *devlink,
+ const struct devlink_param *params,
+ size_t params_count)
+{
+ return __devlink_params_register(devlink, 0, &devlink->param_list,
+ params, params_count,
+ DEVLINK_CMD_PARAM_NEW,
+ DEVLINK_CMD_PARAM_DEL);
+}
EXPORT_SYMBOL_GPL(devlink_params_register);
/**
@@ -4532,36 +5880,61 @@ void devlink_params_unregister(struct devlink *devlink,
const struct devlink_param *params,
size_t params_count)
{
- const struct devlink_param *param = params;
- int i;
-
- mutex_lock(&devlink->lock);
- for (i = 0; i < params_count; i++, param++)
- devlink_param_unregister_one(devlink, param);
- mutex_unlock(&devlink->lock);
+ return __devlink_params_unregister(devlink, 0, &devlink->param_list,
+ params, params_count,
+ DEVLINK_CMD_PARAM_DEL);
}
EXPORT_SYMBOL_GPL(devlink_params_unregister);
/**
- * devlink_param_driverinit_value_get - get configuration parameter
- * value for driver initializing
+ * devlink_port_params_register - register port configuration parameters
*
- * @devlink: devlink
- * @param_id: parameter ID
- * @init_val: value of parameter in driverinit configuration mode
+ * @devlink_port: devlink port
+ * @params: configuration parameters array
+ * @params_count: number of parameters provided
*
- * This function should be used by the driver to get driverinit
- * configuration for initialization after reload command.
+ * Register the configuration parameters supported by the port.
*/
-int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id,
- union devlink_param_value *init_val)
+int devlink_port_params_register(struct devlink_port *devlink_port,
+ const struct devlink_param *params,
+ size_t params_count)
{
- struct devlink_param_item *param_item;
+ return __devlink_params_register(devlink_port->devlink,
+ devlink_port->index,
+ &devlink_port->param_list, params,
+ params_count,
+ DEVLINK_CMD_PORT_PARAM_NEW,
+ DEVLINK_CMD_PORT_PARAM_DEL);
+}
+EXPORT_SYMBOL_GPL(devlink_port_params_register);
- if (!devlink->ops || !devlink->ops->reload)
- return -EOPNOTSUPP;
+/**
+ * devlink_port_params_unregister - unregister port configuration
+ * parameters
+ *
+ * @devlink_port: devlink port
+ * @params: configuration parameters array
+ * @params_count: number of parameters provided
+ */
+void devlink_port_params_unregister(struct devlink_port *devlink_port,
+ const struct devlink_param *params,
+ size_t params_count)
+{
+ return __devlink_params_unregister(devlink_port->devlink,
+ devlink_port->index,
+ &devlink_port->param_list,
+ params, params_count,
+ DEVLINK_CMD_PORT_PARAM_DEL);
+}
+EXPORT_SYMBOL_GPL(devlink_port_params_unregister);
- param_item = devlink_param_find_by_id(&devlink->param_list, param_id);
+static int
+__devlink_param_driverinit_value_get(struct list_head *param_list, u32 param_id,
+ union devlink_param_value *init_val)
+{
+ struct devlink_param_item *param_item;
+
+ param_item = devlink_param_find_by_id(param_list, param_id);
if (!param_item)
return -EINVAL;
@@ -4577,6 +5950,54 @@ int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id,
return 0;
}
+
+static int
+__devlink_param_driverinit_value_set(struct devlink *devlink,
+ unsigned int port_index,
+ struct list_head *param_list, u32 param_id,
+ union devlink_param_value init_val,
+ enum devlink_command cmd)
+{
+ struct devlink_param_item *param_item;
+
+ param_item = devlink_param_find_by_id(param_list, param_id);
+ if (!param_item)
+ return -EINVAL;
+
+ if (!devlink_param_cmode_is_supported(param_item->param,
+ DEVLINK_PARAM_CMODE_DRIVERINIT))
+ return -EOPNOTSUPP;
+
+ if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING)
+ strcpy(param_item->driverinit_value.vstr, init_val.vstr);
+ else
+ param_item->driverinit_value = init_val;
+ param_item->driverinit_value_valid = true;
+
+ devlink_param_notify(devlink, port_index, param_item, cmd);
+ return 0;
+}
+
+/**
+ * devlink_param_driverinit_value_get - get configuration parameter
+ * value for driver initializing
+ *
+ * @devlink: devlink
+ * @param_id: parameter ID
+ * @init_val: value of parameter in driverinit configuration mode
+ *
+ * This function should be used by the driver to get driverinit
+ * configuration for initialization after reload command.
+ */
+int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id,
+ union devlink_param_value *init_val)
+{
+ if (!devlink->ops || !devlink->ops->reload)
+ return -EOPNOTSUPP;
+
+ return __devlink_param_driverinit_value_get(&devlink->param_list,
+ param_id, init_val);
+}
EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_get);
/**
@@ -4594,26 +6015,61 @@ EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_get);
int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id,
union devlink_param_value init_val)
{
- struct devlink_param_item *param_item;
+ return __devlink_param_driverinit_value_set(devlink, 0,
+ &devlink->param_list,
+ param_id, init_val,
+ DEVLINK_CMD_PARAM_NEW);
+}
+EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set);
- param_item = devlink_param_find_by_id(&devlink->param_list, param_id);
- if (!param_item)
- return -EINVAL;
+/**
+ * devlink_port_param_driverinit_value_get - get configuration parameter
+ * value for driver initializing
+ *
+ * @devlink_port: devlink_port
+ * @param_id: parameter ID
+ * @init_val: value of parameter in driverinit configuration mode
+ *
+ * This function should be used by the driver to get driverinit
+ * configuration for initialization after reload command.
+ */
+int devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port,
+ u32 param_id,
+ union devlink_param_value *init_val)
+{
+ struct devlink *devlink = devlink_port->devlink;
- if (!devlink_param_cmode_is_supported(param_item->param,
- DEVLINK_PARAM_CMODE_DRIVERINIT))
+ if (!devlink->ops || !devlink->ops->reload)
return -EOPNOTSUPP;
- if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING)
- strcpy(param_item->driverinit_value.vstr, init_val.vstr);
- else
- param_item->driverinit_value = init_val;
- param_item->driverinit_value_valid = true;
+ return __devlink_param_driverinit_value_get(&devlink_port->param_list,
+ param_id, init_val);
+}
+EXPORT_SYMBOL_GPL(devlink_port_param_driverinit_value_get);
- devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW);
- return 0;
+/**
+ * devlink_port_param_driverinit_value_set - set value of configuration
+ * parameter for driverinit
+ * configuration mode
+ *
+ * @devlink_port: devlink_port
+ * @param_id: parameter ID
+ * @init_val: value of parameter to set for driverinit configuration mode
+ *
+ * This function should be used by the driver to set driverinit
+ * configuration mode default value.
+ */
+int devlink_port_param_driverinit_value_set(struct devlink_port *devlink_port,
+ u32 param_id,
+ union devlink_param_value init_val)
+{
+ return __devlink_param_driverinit_value_set(devlink_port->devlink,
+ devlink_port->index,
+ &devlink_port->param_list,
+ param_id, init_val,
+ DEVLINK_CMD_PORT_PARAM_NEW);
}
-EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set);
+EXPORT_SYMBOL_GPL(devlink_port_param_driverinit_value_set);
/**
* devlink_param_value_changed - notify devlink on a parameter's value
@@ -4626,7 +6082,6 @@ EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set);
* This function should be used by the driver to notify devlink on value
* change, excluding driverinit configuration mode.
* For driverinit configuration mode driver should use the function
- * devlink_param_driverinit_value_set() instead.
*/
void devlink_param_value_changed(struct devlink *devlink, u32 param_id)
{
@@ -4635,11 +6090,38 @@ void devlink_param_value_changed(struct devlink *devlink, u32 param_id)
param_item = devlink_param_find_by_id(&devlink->param_list, param_id);
WARN_ON(!param_item);
- devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW);
+ devlink_param_notify(devlink, 0, param_item, DEVLINK_CMD_PARAM_NEW);
}
EXPORT_SYMBOL_GPL(devlink_param_value_changed);
/**
+ * devlink_port_param_value_changed - notify devlink on a parameter's value
+ * change. Should be called by the driver
+ * right after the change.
+ *
+ * @devlink_port: devlink_port
+ * @param_id: parameter ID
+ *
+ * This function should be used by the driver to notify devlink on value
+ * change, excluding driverinit configuration mode.
+ * For driverinit configuration mode driver should use the function
+ * devlink_port_param_driverinit_value_set() instead.
+ */
+void devlink_port_param_value_changed(struct devlink_port *devlink_port,
+ u32 param_id)
+{
+ struct devlink_param_item *param_item;
+
+ param_item = devlink_param_find_by_id(&devlink_port->param_list,
+ param_id);
+ WARN_ON(!param_item);
+
+ devlink_param_notify(devlink_port->devlink, devlink_port->index,
+ param_item, DEVLINK_CMD_PORT_PARAM_NEW);
+}
+EXPORT_SYMBOL_GPL(devlink_port_param_value_changed);
+
+/**
* devlink_param_value_str_fill - Safely fill-up the string preventing
* from overflow of the preallocated buffer
*
@@ -4808,6 +6290,69 @@ unlock:
}
EXPORT_SYMBOL_GPL(devlink_region_snapshot_create);
+static void __devlink_compat_running_version(struct devlink *devlink,
+ char *buf, size_t len)
+{
+ const struct nlattr *nlattr;
+ struct devlink_info_req req;
+ struct sk_buff *msg;
+ int rem, err;
+
+ if (!devlink->ops->info_get)
+ return;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return;
+
+ req.msg = msg;
+ err = devlink->ops->info_get(devlink, &req, NULL);
+ if (err)
+ goto free_msg;
+
+ nla_for_each_attr(nlattr, (void *)msg->data, msg->len, rem) {
+ const struct nlattr *kv;
+ int rem_kv;
+
+ if (nla_type(nlattr) != DEVLINK_ATTR_INFO_VERSION_RUNNING)
+ continue;
+
+ nla_for_each_nested(kv, nlattr, rem_kv) {
+ if (nla_type(kv) != DEVLINK_ATTR_INFO_VERSION_VALUE)
+ continue;
+
+ strlcat(buf, nla_data(kv), len);
+ strlcat(buf, " ", len);
+ }
+ }
+free_msg:
+ nlmsg_free(msg);
+}
+
+void devlink_compat_running_version(struct net_device *dev,
+ char *buf, size_t len)
+{
+ struct devlink_port *devlink_port;
+ struct devlink *devlink;
+
+ mutex_lock(&devlink_mutex);
+ list_for_each_entry(devlink, &devlink_list, list) {
+ mutex_lock(&devlink->lock);
+ list_for_each_entry(devlink_port, &devlink->port_list, list) {
+ if (devlink_port->type == DEVLINK_PORT_TYPE_ETH ||
+ devlink_port->type_dev == dev) {
+ __devlink_compat_running_version(devlink,
+ buf, len);
+ mutex_unlock(&devlink->lock);
+ goto out;
+ }
+ }
+ mutex_unlock(&devlink->lock);
+ }
+out:
+ mutex_unlock(&devlink_mutex);
+}
+
static int __init devlink_module_init(void)
{
return genl_register_family(&devlink_nl_family);
diff --git a/net/core/dst.c b/net/core/dst.c
index 81ccf20e2826..a263309df115 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -98,8 +98,12 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
struct dst_entry *dst;
if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) {
- if (ops->gc(ops))
+ if (ops->gc(ops)) {
+ printk_ratelimited(KERN_NOTICE "Route cache is full: "
+ "consider increasing sysctl "
+ "net.ipv[4|6].route.max_size.\n");
return NULL;
+ }
}
dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 158264f7cfaf..0fbf39239b29 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -27,7 +27,9 @@
#include <linux/rtnetlink.h>
#include <linux/sched/signal.h>
#include <linux/net.h>
+#include <net/devlink.h>
#include <net/xdp_sock.h>
+#include <net/flow_offload.h>
/*
* Some useful ethtool_ops methods that're device independent.
@@ -803,6 +805,12 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev,
if (ops->get_eeprom_len)
info.eedump_len = ops->get_eeprom_len(dev);
+ rtnl_unlock();
+ if (!info.fw_version[0])
+ devlink_compat_running_version(dev, info.fw_version,
+ sizeof(info.fw_version));
+ rtnl_lock();
+
if (copy_to_user(useraddr, &info, sizeof(info)))
return -EFAULT;
return 0;
@@ -1348,12 +1356,9 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
if (regs.len > reglen)
regs.len = reglen;
- regbuf = NULL;
- if (reglen) {
- regbuf = vzalloc(reglen);
- if (!regbuf)
- return -ENOMEM;
- }
+ regbuf = vzalloc(reglen);
+ if (!regbuf)
+ return -ENOMEM;
ops->get_regs(dev, &regs, regbuf);
@@ -2816,3 +2821,243 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
return rc;
}
+
+struct ethtool_rx_flow_key {
+ struct flow_dissector_key_basic basic;
+ union {
+ struct flow_dissector_key_ipv4_addrs ipv4;
+ struct flow_dissector_key_ipv6_addrs ipv6;
+ };
+ struct flow_dissector_key_ports tp;
+ struct flow_dissector_key_ip ip;
+ struct flow_dissector_key_vlan vlan;
+ struct flow_dissector_key_eth_addrs eth_addrs;
+} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
+
+struct ethtool_rx_flow_match {
+ struct flow_dissector dissector;
+ struct ethtool_rx_flow_key key;
+ struct ethtool_rx_flow_key mask;
+};
+
+struct ethtool_rx_flow_rule *
+ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input)
+{
+ const struct ethtool_rx_flow_spec *fs = input->fs;
+ static struct in6_addr zero_addr = {};
+ struct ethtool_rx_flow_match *match;
+ struct ethtool_rx_flow_rule *flow;
+ struct flow_action_entry *act;
+
+ flow = kzalloc(sizeof(struct ethtool_rx_flow_rule) +
+ sizeof(struct ethtool_rx_flow_match), GFP_KERNEL);
+ if (!flow)
+ return ERR_PTR(-ENOMEM);
+
+ /* ethtool_rx supports only one single action per rule. */
+ flow->rule = flow_rule_alloc(1);
+ if (!flow->rule) {
+ kfree(flow);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ match = (struct ethtool_rx_flow_match *)flow->priv;
+ flow->rule->match.dissector = &match->dissector;
+ flow->rule->match.mask = &match->mask;
+ flow->rule->match.key = &match->key;
+
+ match->mask.basic.n_proto = htons(0xffff);
+
+ switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS)) {
+ case TCP_V4_FLOW:
+ case UDP_V4_FLOW: {
+ const struct ethtool_tcpip4_spec *v4_spec, *v4_m_spec;
+
+ match->key.basic.n_proto = htons(ETH_P_IP);
+
+ v4_spec = &fs->h_u.tcp_ip4_spec;
+ v4_m_spec = &fs->m_u.tcp_ip4_spec;
+
+ if (v4_m_spec->ip4src) {
+ match->key.ipv4.src = v4_spec->ip4src;
+ match->mask.ipv4.src = v4_m_spec->ip4src;
+ }
+ if (v4_m_spec->ip4dst) {
+ match->key.ipv4.dst = v4_spec->ip4dst;
+ match->mask.ipv4.dst = v4_m_spec->ip4dst;
+ }
+ if (v4_m_spec->ip4src ||
+ v4_m_spec->ip4dst) {
+ match->dissector.used_keys |=
+ BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS);
+ match->dissector.offset[FLOW_DISSECTOR_KEY_IPV4_ADDRS] =
+ offsetof(struct ethtool_rx_flow_key, ipv4);
+ }
+ if (v4_m_spec->psrc) {
+ match->key.tp.src = v4_spec->psrc;
+ match->mask.tp.src = v4_m_spec->psrc;
+ }
+ if (v4_m_spec->pdst) {
+ match->key.tp.dst = v4_spec->pdst;
+ match->mask.tp.dst = v4_m_spec->pdst;
+ }
+ if (v4_m_spec->psrc ||
+ v4_m_spec->pdst) {
+ match->dissector.used_keys |=
+ BIT(FLOW_DISSECTOR_KEY_PORTS);
+ match->dissector.offset[FLOW_DISSECTOR_KEY_PORTS] =
+ offsetof(struct ethtool_rx_flow_key, tp);
+ }
+ if (v4_m_spec->tos) {
+ match->key.ip.tos = v4_spec->tos;
+ match->mask.ip.tos = v4_m_spec->tos;
+ match->dissector.used_keys |=
+ BIT(FLOW_DISSECTOR_KEY_IP);
+ match->dissector.offset[FLOW_DISSECTOR_KEY_IP] =
+ offsetof(struct ethtool_rx_flow_key, ip);
+ }
+ }
+ break;
+ case TCP_V6_FLOW:
+ case UDP_V6_FLOW: {
+ const struct ethtool_tcpip6_spec *v6_spec, *v6_m_spec;
+
+ match->key.basic.n_proto = htons(ETH_P_IPV6);
+
+ v6_spec = &fs->h_u.tcp_ip6_spec;
+ v6_m_spec = &fs->m_u.tcp_ip6_spec;
+ if (memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr))) {
+ memcpy(&match->key.ipv6.src, v6_spec->ip6src,
+ sizeof(match->key.ipv6.src));
+ memcpy(&match->mask.ipv6.src, v6_m_spec->ip6src,
+ sizeof(match->mask.ipv6.src));
+ }
+ if (memcmp(v6_m_spec->ip6dst, &zero_addr, sizeof(zero_addr))) {
+ memcpy(&match->key.ipv6.dst, v6_spec->ip6dst,
+ sizeof(match->key.ipv6.dst));
+ memcpy(&match->mask.ipv6.dst, v6_m_spec->ip6dst,
+ sizeof(match->mask.ipv6.dst));
+ }
+ if (memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr)) ||
+ memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr))) {
+ match->dissector.used_keys |=
+ BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS);
+ match->dissector.offset[FLOW_DISSECTOR_KEY_IPV6_ADDRS] =
+ offsetof(struct ethtool_rx_flow_key, ipv6);
+ }
+ if (v6_m_spec->psrc) {
+ match->key.tp.src = v6_spec->psrc;
+ match->mask.tp.src = v6_m_spec->psrc;
+ }
+ if (v6_m_spec->pdst) {
+ match->key.tp.dst = v6_spec->pdst;
+ match->mask.tp.dst = v6_m_spec->pdst;
+ }
+ if (v6_m_spec->psrc ||
+ v6_m_spec->pdst) {
+ match->dissector.used_keys |=
+ BIT(FLOW_DISSECTOR_KEY_PORTS);
+ match->dissector.offset[FLOW_DISSECTOR_KEY_PORTS] =
+ offsetof(struct ethtool_rx_flow_key, tp);
+ }
+ if (v6_m_spec->tclass) {
+ match->key.ip.tos = v6_spec->tclass;
+ match->mask.ip.tos = v6_m_spec->tclass;
+ match->dissector.used_keys |=
+ BIT(FLOW_DISSECTOR_KEY_IP);
+ match->dissector.offset[FLOW_DISSECTOR_KEY_IP] =
+ offsetof(struct ethtool_rx_flow_key, ip);
+ }
+ }
+ break;
+ default:
+ ethtool_rx_flow_rule_destroy(flow);
+ return ERR_PTR(-EINVAL);
+ }
+
+ switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS)) {
+ case TCP_V4_FLOW:
+ case TCP_V6_FLOW:
+ match->key.basic.ip_proto = IPPROTO_TCP;
+ break;
+ case UDP_V4_FLOW:
+ case UDP_V6_FLOW:
+ match->key.basic.ip_proto = IPPROTO_UDP;
+ break;
+ }
+ match->mask.basic.ip_proto = 0xff;
+
+ match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_BASIC);
+ match->dissector.offset[FLOW_DISSECTOR_KEY_BASIC] =
+ offsetof(struct ethtool_rx_flow_key, basic);
+
+ if (fs->flow_type & FLOW_EXT) {
+ const struct ethtool_flow_ext *ext_h_spec = &fs->h_ext;
+ const struct ethtool_flow_ext *ext_m_spec = &fs->m_ext;
+
+ if (ext_m_spec->vlan_etype &&
+ ext_m_spec->vlan_tci) {
+ match->key.vlan.vlan_tpid = ext_h_spec->vlan_etype;
+ match->mask.vlan.vlan_tpid = ext_m_spec->vlan_etype;
+
+ match->key.vlan.vlan_id =
+ ntohs(ext_h_spec->vlan_tci) & 0x0fff;
+ match->mask.vlan.vlan_id =
+ ntohs(ext_m_spec->vlan_tci) & 0x0fff;
+
+ match->key.vlan.vlan_priority =
+ (ntohs(ext_h_spec->vlan_tci) & 0xe000) >> 13;
+ match->mask.vlan.vlan_priority =
+ (ntohs(ext_m_spec->vlan_tci) & 0xe000) >> 13;
+
+ match->dissector.used_keys |=
+ BIT(FLOW_DISSECTOR_KEY_VLAN);
+ match->dissector.offset[FLOW_DISSECTOR_KEY_VLAN] =
+ offsetof(struct ethtool_rx_flow_key, vlan);
+ }
+ }
+ if (fs->flow_type & FLOW_MAC_EXT) {
+ const struct ethtool_flow_ext *ext_h_spec = &fs->h_ext;
+ const struct ethtool_flow_ext *ext_m_spec = &fs->m_ext;
+
+ if (ext_m_spec->h_dest) {
+ memcpy(match->key.eth_addrs.dst, ext_h_spec->h_dest,
+ ETH_ALEN);
+ memcpy(match->mask.eth_addrs.dst, ext_m_spec->h_dest,
+ ETH_ALEN);
+
+ match->dissector.used_keys |=
+ BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS);
+ match->dissector.offset[FLOW_DISSECTOR_KEY_ETH_ADDRS] =
+ offsetof(struct ethtool_rx_flow_key, eth_addrs);
+ }
+ }
+
+ act = &flow->rule->action.entries[0];
+ switch (fs->ring_cookie) {
+ case RX_CLS_FLOW_DISC:
+ act->id = FLOW_ACTION_DROP;
+ break;
+ case RX_CLS_FLOW_WAKE:
+ act->id = FLOW_ACTION_WAKE;
+ break;
+ default:
+ act->id = FLOW_ACTION_QUEUE;
+ if (fs->flow_type & FLOW_RSS)
+ act->queue.ctx = input->rss_ctx;
+
+ act->queue.vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie);
+ act->queue.index = ethtool_get_flow_spec_ring(fs->ring_cookie);
+ break;
+ }
+
+ return flow;
+}
+EXPORT_SYMBOL(ethtool_rx_flow_rule_create);
+
+void ethtool_rx_flow_rule_destroy(struct ethtool_rx_flow_rule *flow)
+{
+ kfree(flow->rule);
+ kfree(flow);
+}
+EXPORT_SYMBOL(ethtool_rx_flow_rule_destroy);
diff --git a/net/core/filter.c b/net/core/filter.c
index 7a54dc11ac2d..b5a002d7b263 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5316,10 +5316,20 @@ bpf_base_func_proto(enum bpf_func_id func_id)
return &bpf_tail_call_proto;
case BPF_FUNC_ktime_get_ns:
return &bpf_ktime_get_ns_proto;
+ default:
+ break;
+ }
+
+ if (!capable(CAP_SYS_ADMIN))
+ return NULL;
+
+ switch (func_id) {
+ case BPF_FUNC_spin_lock:
+ return &bpf_spin_lock_proto;
+ case BPF_FUNC_spin_unlock:
+ return &bpf_spin_unlock_proto;
case BPF_FUNC_trace_printk:
- if (capable(CAP_SYS_ADMIN))
- return bpf_get_trace_printk_proto();
- /* else, fall through */
+ return bpf_get_trace_printk_proto();
default:
return NULL;
}
@@ -6710,6 +6720,27 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
target_size));
break;
+ case offsetof(struct __sk_buff, gso_segs):
+ /* si->dst_reg = skb_shinfo(SKB); */
+#ifdef NET_SKBUFF_DATA_USES_OFFSET
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head),
+ si->dst_reg, si->src_reg,
+ offsetof(struct sk_buff, head));
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end),
+ BPF_REG_AX, si->src_reg,
+ offsetof(struct sk_buff, end));
+ *insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX);
+#else
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end),
+ si->dst_reg, si->src_reg,
+ offsetof(struct sk_buff, end));
+#endif
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_segs),
+ si->dst_reg, si->dst_reg,
+ bpf_target_off(struct skb_shared_info,
+ gso_segs, 2,
+ target_size));
+ break;
case offsetof(struct __sk_buff, wire_len):
BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, pkt_len) != 4);
@@ -7700,6 +7731,7 @@ const struct bpf_verifier_ops flow_dissector_verifier_ops = {
};
const struct bpf_prog_ops flow_dissector_prog_ops = {
+ .test_run = bpf_prog_test_run_flow_dissector,
};
int sk_detach_filter(struct sock *sk)
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 9f2840510e63..bb1a54747d64 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -683,6 +683,46 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys,
}
}
+bool __skb_flow_bpf_dissect(struct bpf_prog *prog,
+ const struct sk_buff *skb,
+ struct flow_dissector *flow_dissector,
+ struct bpf_flow_keys *flow_keys)
+{
+ struct bpf_skb_data_end cb_saved;
+ struct bpf_skb_data_end *cb;
+ u32 result;
+
+ /* Note that even though the const qualifier is discarded
+ * throughout the execution of the BPF program, all changes(the
+ * control block) are reverted after the BPF program returns.
+ * Therefore, __skb_flow_dissect does not alter the skb.
+ */
+
+ cb = (struct bpf_skb_data_end *)skb->cb;
+
+ /* Save Control Block */
+ memcpy(&cb_saved, cb, sizeof(cb_saved));
+ memset(cb, 0, sizeof(*cb));
+
+ /* Pass parameters to the BPF program */
+ memset(flow_keys, 0, sizeof(*flow_keys));
+ cb->qdisc_cb.flow_keys = flow_keys;
+ flow_keys->nhoff = skb_network_offset(skb);
+ flow_keys->thoff = flow_keys->nhoff;
+
+ bpf_compute_data_pointers((struct sk_buff *)skb);
+ result = BPF_PROG_RUN(prog, skb);
+
+ /* Restore state */
+ memcpy(cb, &cb_saved, sizeof(cb_saved));
+
+ flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, 0, skb->len);
+ flow_keys->thoff = clamp_t(u16, flow_keys->thoff,
+ flow_keys->nhoff, skb->len);
+
+ return result == BPF_OK;
+}
+
/**
* __skb_flow_dissect - extract the flow_keys struct and return it
* @skb: sk_buff to extract the flow from, can be NULL if the rest are specified
@@ -714,7 +754,6 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
struct flow_dissector_key_vlan *key_vlan;
enum flow_dissect_ret fdret;
enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX;
- struct bpf_prog *attached = NULL;
int num_hdrs = 0;
u8 ip_proto = 0;
bool ret;
@@ -754,53 +793,30 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
FLOW_DISSECTOR_KEY_BASIC,
target_container);
- rcu_read_lock();
if (skb) {
+ struct bpf_flow_keys flow_keys;
+ struct bpf_prog *attached = NULL;
+
+ rcu_read_lock();
+
if (skb->dev)
attached = rcu_dereference(dev_net(skb->dev)->flow_dissector_prog);
else if (skb->sk)
attached = rcu_dereference(sock_net(skb->sk)->flow_dissector_prog);
else
WARN_ON_ONCE(1);
- }
- if (attached) {
- /* Note that even though the const qualifier is discarded
- * throughout the execution of the BPF program, all changes(the
- * control block) are reverted after the BPF program returns.
- * Therefore, __skb_flow_dissect does not alter the skb.
- */
- struct bpf_flow_keys flow_keys = {};
- struct bpf_skb_data_end cb_saved;
- struct bpf_skb_data_end *cb;
- u32 result;
-
- cb = (struct bpf_skb_data_end *)skb->cb;
-
- /* Save Control Block */
- memcpy(&cb_saved, cb, sizeof(cb_saved));
- memset(cb, 0, sizeof(cb_saved));
- /* Pass parameters to the BPF program */
- cb->qdisc_cb.flow_keys = &flow_keys;
- flow_keys.nhoff = nhoff;
- flow_keys.thoff = nhoff;
-
- bpf_compute_data_pointers((struct sk_buff *)skb);
- result = BPF_PROG_RUN(attached, skb);
-
- /* Restore state */
- memcpy(cb, &cb_saved, sizeof(cb_saved));
-
- flow_keys.nhoff = clamp_t(u16, flow_keys.nhoff, 0, skb->len);
- flow_keys.thoff = clamp_t(u16, flow_keys.thoff,
- flow_keys.nhoff, skb->len);
-
- __skb_flow_bpf_to_target(&flow_keys, flow_dissector,
- target_container);
+ if (attached) {
+ ret = __skb_flow_bpf_dissect(attached, skb,
+ flow_dissector,
+ &flow_keys);
+ __skb_flow_bpf_to_target(&flow_keys, flow_dissector,
+ target_container);
+ rcu_read_unlock();
+ return ret;
+ }
rcu_read_unlock();
- return result == BPF_OK;
}
- rcu_read_unlock();
if (dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c
new file mode 100644
index 000000000000..c3a00eac4804
--- /dev/null
+++ b/net/core/flow_offload.c
@@ -0,0 +1,153 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <net/flow_offload.h>
+
+struct flow_rule *flow_rule_alloc(unsigned int num_actions)
+{
+ struct flow_rule *rule;
+
+ rule = kzalloc(sizeof(struct flow_rule) +
+ sizeof(struct flow_action_entry) * num_actions,
+ GFP_KERNEL);
+ if (!rule)
+ return NULL;
+
+ rule->action.num_entries = num_actions;
+
+ return rule;
+}
+EXPORT_SYMBOL(flow_rule_alloc);
+
+#define FLOW_DISSECTOR_MATCH(__rule, __type, __out) \
+ const struct flow_match *__m = &(__rule)->match; \
+ struct flow_dissector *__d = (__m)->dissector; \
+ \
+ (__out)->key = skb_flow_dissector_target(__d, __type, (__m)->key); \
+ (__out)->mask = skb_flow_dissector_target(__d, __type, (__m)->mask); \
+
+void flow_rule_match_basic(const struct flow_rule *rule,
+ struct flow_match_basic *out)
+{
+ FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_BASIC, out);
+}
+EXPORT_SYMBOL(flow_rule_match_basic);
+
+void flow_rule_match_control(const struct flow_rule *rule,
+ struct flow_match_control *out)
+{
+ FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_CONTROL, out);
+}
+EXPORT_SYMBOL(flow_rule_match_control);
+
+void flow_rule_match_eth_addrs(const struct flow_rule *rule,
+ struct flow_match_eth_addrs *out)
+{
+ FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS, out);
+}
+EXPORT_SYMBOL(flow_rule_match_eth_addrs);
+
+void flow_rule_match_vlan(const struct flow_rule *rule,
+ struct flow_match_vlan *out)
+{
+ FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_VLAN, out);
+}
+EXPORT_SYMBOL(flow_rule_match_vlan);
+
+void flow_rule_match_ipv4_addrs(const struct flow_rule *rule,
+ struct flow_match_ipv4_addrs *out)
+{
+ FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS, out);
+}
+EXPORT_SYMBOL(flow_rule_match_ipv4_addrs);
+
+void flow_rule_match_ipv6_addrs(const struct flow_rule *rule,
+ struct flow_match_ipv6_addrs *out)
+{
+ FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS, out);
+}
+EXPORT_SYMBOL(flow_rule_match_ipv6_addrs);
+
+void flow_rule_match_ip(const struct flow_rule *rule,
+ struct flow_match_ip *out)
+{
+ FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IP, out);
+}
+EXPORT_SYMBOL(flow_rule_match_ip);
+
+void flow_rule_match_ports(const struct flow_rule *rule,
+ struct flow_match_ports *out)
+{
+ FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_PORTS, out);
+}
+EXPORT_SYMBOL(flow_rule_match_ports);
+
+void flow_rule_match_tcp(const struct flow_rule *rule,
+ struct flow_match_tcp *out)
+{
+ FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_TCP, out);
+}
+EXPORT_SYMBOL(flow_rule_match_tcp);
+
+void flow_rule_match_icmp(const struct flow_rule *rule,
+ struct flow_match_icmp *out)
+{
+ FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ICMP, out);
+}
+EXPORT_SYMBOL(flow_rule_match_icmp);
+
+void flow_rule_match_mpls(const struct flow_rule *rule,
+ struct flow_match_mpls *out)
+{
+ FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_MPLS, out);
+}
+EXPORT_SYMBOL(flow_rule_match_mpls);
+
+void flow_rule_match_enc_control(const struct flow_rule *rule,
+ struct flow_match_control *out)
+{
+ FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_CONTROL, out);
+}
+EXPORT_SYMBOL(flow_rule_match_enc_control);
+
+void flow_rule_match_enc_ipv4_addrs(const struct flow_rule *rule,
+ struct flow_match_ipv4_addrs *out)
+{
+ FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, out);
+}
+EXPORT_SYMBOL(flow_rule_match_enc_ipv4_addrs);
+
+void flow_rule_match_enc_ipv6_addrs(const struct flow_rule *rule,
+ struct flow_match_ipv6_addrs *out)
+{
+ FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, out);
+}
+EXPORT_SYMBOL(flow_rule_match_enc_ipv6_addrs);
+
+void flow_rule_match_enc_ip(const struct flow_rule *rule,
+ struct flow_match_ip *out)
+{
+ FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_IP, out);
+}
+EXPORT_SYMBOL(flow_rule_match_enc_ip);
+
+void flow_rule_match_enc_ports(const struct flow_rule *rule,
+ struct flow_match_ports *out)
+{
+ FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_PORTS, out);
+}
+EXPORT_SYMBOL(flow_rule_match_enc_ports);
+
+void flow_rule_match_enc_keyid(const struct flow_rule *rule,
+ struct flow_match_enc_keyid *out)
+{
+ FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_KEYID, out);
+}
+EXPORT_SYMBOL(flow_rule_match_enc_keyid);
+
+void flow_rule_match_enc_opts(const struct flow_rule *rule,
+ struct flow_match_enc_opts *out)
+{
+ FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_OPTS, out);
+}
+EXPORT_SYMBOL(flow_rule_match_enc_opts);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index ff9fd2bb4ce4..7c5061123ead 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -12,7 +12,6 @@
#include <linux/capability.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
-#include <net/switchdev.h>
#include <linux/if_arp.h>
#include <linux/slab.h>
#include <linux/sched/signal.h>
@@ -501,16 +500,11 @@ static ssize_t phys_switch_id_show(struct device *dev,
return restart_syscall();
if (dev_isalive(netdev)) {
- struct switchdev_attr attr = {
- .orig_dev = netdev,
- .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
- .flags = SWITCHDEV_F_NO_RECURSE,
- };
+ struct netdev_phys_item_id ppid = { };
- ret = switchdev_port_attr_get(netdev, &attr);
+ ret = dev_get_port_parent_id(netdev, &ppid, false);
if (!ret)
- ret = sprintf(buf, "%*phN\n", attr.u.ppid.id_len,
- attr.u.ppid.id);
+ ret = sprintf(buf, "%*phN\n", ppid.id_len, ppid.id);
}
rtnl_unlock();
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index b02fb19df2cc..17f36317363d 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -778,6 +778,41 @@ nla_put_failure:
return -EMSGSIZE;
}
+static int rtnl_net_valid_getid_req(struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ struct nlattr **tb,
+ struct netlink_ext_ack *extack)
+{
+ int i, err;
+
+ if (!netlink_strict_get_check(skb))
+ return nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
+ rtnl_net_policy, extack);
+
+ err = nlmsg_parse_strict(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
+ rtnl_net_policy, extack);
+ if (err)
+ return err;
+
+ for (i = 0; i <= NETNSA_MAX; i++) {
+ if (!tb[i])
+ continue;
+
+ switch (i) {
+ case NETNSA_PID:
+ case NETNSA_FD:
+ case NETNSA_NSID:
+ case NETNSA_TARGET_NSID:
+ break;
+ default:
+ NL_SET_ERR_MSG(extack, "Unsupported attribute in peer netns getid request");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
@@ -793,8 +828,7 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh,
struct sk_buff *msg;
int err;
- err = nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
- rtnl_net_policy, extack);
+ err = rtnl_net_valid_getid_req(skb, nlh, tb, extack);
if (err < 0)
return err;
if (tb[NETNSA_PID]) {
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 5ea1bed08ede..a51cab95ba64 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -46,7 +46,6 @@
#include <linux/inet.h>
#include <linux/netdevice.h>
-#include <net/switchdev.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/arp.h>
@@ -1146,22 +1145,17 @@ static int rtnl_phys_port_name_fill(struct sk_buff *skb, struct net_device *dev)
static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev)
{
+ struct netdev_phys_item_id ppid = { };
int err;
- struct switchdev_attr attr = {
- .orig_dev = dev,
- .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
- .flags = SWITCHDEV_F_NO_RECURSE,
- };
- err = switchdev_port_attr_get(dev, &attr);
+ err = dev_get_port_parent_id(dev, &ppid, false);
if (err) {
if (err == -EOPNOTSUPP)
return 0;
return err;
}
- if (nla_put(skb, IFLA_PHYS_SWITCH_ID, attr.u.ppid.id_len,
- attr.u.ppid.id))
+ if (nla_put(skb, IFLA_PHYS_SWITCH_ID, ppid.id_len, ppid.id))
return -EMSGSIZE;
return 0;
@@ -3242,6 +3236,53 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
return ret;
}
+static int rtnl_valid_getlink_req(struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ struct nlattr **tb,
+ struct netlink_ext_ack *extack)
+{
+ struct ifinfomsg *ifm;
+ int i, err;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+ NL_SET_ERR_MSG(extack, "Invalid header for get link");
+ return -EINVAL;
+ }
+
+ if (!netlink_strict_get_check(skb))
+ return nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy,
+ extack);
+
+ ifm = nlmsg_data(nlh);
+ if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags ||
+ ifm->ifi_change) {
+ NL_SET_ERR_MSG(extack, "Invalid values in header for get link request");
+ return -EINVAL;
+ }
+
+ err = nlmsg_parse_strict(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy,
+ extack);
+ if (err)
+ return err;
+
+ for (i = 0; i <= IFLA_MAX; i++) {
+ if (!tb[i])
+ continue;
+
+ switch (i) {
+ case IFLA_IFNAME:
+ case IFLA_EXT_MASK:
+ case IFLA_TARGET_NETNSID:
+ break;
+ default:
+ NL_SET_ERR_MSG(extack, "Unsupported attribute in get link request");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
@@ -3256,7 +3297,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
int err;
u32 ext_filter_mask = 0;
- err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy, extack);
+ err = rtnl_valid_getlink_req(skb, nlh, tb, extack);
if (err < 0)
return err;
@@ -3639,7 +3680,7 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
const struct net_device_ops *ops = br_dev->netdev_ops;
err = ops->ndo_fdb_add(ndm, tb, dev, addr, vid,
- nlh->nlmsg_flags);
+ nlh->nlmsg_flags, extack);
if (err)
goto out;
else
@@ -3651,7 +3692,8 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
if (dev->netdev_ops->ndo_fdb_add)
err = dev->netdev_ops->ndo_fdb_add(ndm, tb, dev, addr,
vid,
- nlh->nlmsg_flags);
+ nlh->nlmsg_flags,
+ extack);
else
err = ndo_dflt_fdb_add(ndm, tb, dev, addr, vid,
nlh->nlmsg_flags);
@@ -4901,6 +4943,40 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev,
return size;
}
+static int rtnl_valid_stats_req(const struct nlmsghdr *nlh, bool strict_check,
+ bool is_dump, struct netlink_ext_ack *extack)
+{
+ struct if_stats_msg *ifsm;
+
+ if (nlh->nlmsg_len < sizeof(*ifsm)) {
+ NL_SET_ERR_MSG(extack, "Invalid header for stats dump");
+ return -EINVAL;
+ }
+
+ if (!strict_check)
+ return 0;
+
+ ifsm = nlmsg_data(nlh);
+
+ /* only requests using strict checks can pass data to influence
+ * the dump. The legacy exception is filter_mask.
+ */
+ if (ifsm->pad1 || ifsm->pad2 || (is_dump && ifsm->ifindex)) {
+ NL_SET_ERR_MSG(extack, "Invalid values in header for stats dump request");
+ return -EINVAL;
+ }
+ if (nlmsg_attrlen(nlh, sizeof(*ifsm))) {
+ NL_SET_ERR_MSG(extack, "Invalid attributes after stats header");
+ return -EINVAL;
+ }
+ if (ifsm->filter_mask >= IFLA_STATS_FILTER_BIT(IFLA_STATS_MAX + 1)) {
+ NL_SET_ERR_MSG(extack, "Invalid stats requested through filter mask");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int rtnl_stats_get(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
@@ -4912,8 +4988,10 @@ static int rtnl_stats_get(struct sk_buff *skb, struct nlmsghdr *nlh,
u32 filter_mask;
int err;
- if (nlmsg_len(nlh) < sizeof(*ifsm))
- return -EINVAL;
+ err = rtnl_valid_stats_req(nlh, netlink_strict_get_check(skb),
+ false, extack);
+ if (err)
+ return err;
ifsm = nlmsg_data(nlh);
if (ifsm->ifindex > 0)
@@ -4965,27 +5043,11 @@ static int rtnl_stats_dump(struct sk_buff *skb, struct netlink_callback *cb)
cb->seq = net->dev_base_seq;
- if (nlmsg_len(cb->nlh) < sizeof(*ifsm)) {
- NL_SET_ERR_MSG(extack, "Invalid header for stats dump");
- return -EINVAL;
- }
+ err = rtnl_valid_stats_req(cb->nlh, cb->strict_check, true, extack);
+ if (err)
+ return err;
ifsm = nlmsg_data(cb->nlh);
-
- /* only requests using strict checks can pass data to influence
- * the dump. The legacy exception is filter_mask.
- */
- if (cb->strict_check) {
- if (ifsm->pad1 || ifsm->pad2 || ifsm->ifindex) {
- NL_SET_ERR_MSG(extack, "Invalid values in header for stats dump request");
- return -EINVAL;
- }
- if (nlmsg_attrlen(cb->nlh, sizeof(*ifsm))) {
- NL_SET_ERR_MSG(extack, "Invalid attributes after stats header");
- return -EINVAL;
- }
- }
-
filter_mask = ifsm->filter_mask;
if (!filter_mask) {
NL_SET_ERR_MSG(extack, "Filter mask must be set for stats dump");
diff --git a/net/core/scm.c b/net/core/scm.c
index b1ff8a441748..52ef219cf6df 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -29,6 +29,7 @@
#include <linux/pid.h>
#include <linux/nsproxy.h>
#include <linux/slab.h>
+#include <linux/errqueue.h>
#include <linux/uaccess.h>
@@ -252,6 +253,32 @@ out:
}
EXPORT_SYMBOL(put_cmsg);
+void put_cmsg_scm_timestamping64(struct msghdr *msg, struct scm_timestamping_internal *tss_internal)
+{
+ struct scm_timestamping64 tss;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(tss.ts); i++) {
+ tss.ts[i].tv_sec = tss_internal->ts[i].tv_sec;
+ tss.ts[i].tv_nsec = tss_internal->ts[i].tv_nsec;
+ }
+
+ put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPING_NEW, sizeof(tss), &tss);
+}
+EXPORT_SYMBOL(put_cmsg_scm_timestamping64);
+
+void put_cmsg_scm_timestamping(struct msghdr *msg, struct scm_timestamping_internal *tss_internal)
+{
+ struct scm_timestamping tss;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(tss.ts); i++)
+ tss.ts[i] = timespec64_to_timespec(tss_internal->ts[i]);
+
+ put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPING_OLD, sizeof(tss), &tss);
+}
+EXPORT_SYMBOL(put_cmsg_scm_timestamping);
+
void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
{
struct cmsghdr __user *cm
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 8c826603bf36..ae6f06e45737 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -78,11 +78,9 @@ int sk_msg_clone(struct sock *sk, struct sk_msg *dst, struct sk_msg *src,
{
int i = src->sg.start;
struct scatterlist *sge = sk_msg_elem(src, i);
+ struct scatterlist *sgd = NULL;
u32 sge_len, sge_off;
- if (sk_msg_full(dst))
- return -ENOSPC;
-
while (off) {
if (sge->length > off)
break;
@@ -94,16 +92,27 @@ int sk_msg_clone(struct sock *sk, struct sk_msg *dst, struct sk_msg *src,
}
while (len) {
- if (sk_msg_full(dst))
- return -ENOSPC;
-
sge_len = sge->length - off;
- sge_off = sge->offset + off;
if (sge_len > len)
sge_len = len;
+
+ if (dst->sg.end)
+ sgd = sk_msg_elem(dst, dst->sg.end - 1);
+
+ if (sgd &&
+ (sg_page(sge) == sg_page(sgd)) &&
+ (sg_virt(sge) + off == sg_virt(sgd) + sgd->length)) {
+ sgd->length += sge_len;
+ dst->sg.size += sge_len;
+ } else if (!sk_msg_full(dst)) {
+ sge_off = sge->offset + off;
+ sk_msg_page_add(dst, sg_page(sge), sge_len, sge_off);
+ } else {
+ return -ENOSPC;
+ }
+
off = 0;
len -= sge_len;
- sk_msg_page_add(dst, sg_page(sge), sge_len, sge_off);
sk_mem_charge(sk, sge_len);
sk_msg_iter_var_next(i);
if (i == src->sg.end && len)
diff --git a/net/core/sock.c b/net/core/sock.c
index 6aa2e7e0b4fb..71ded4d8025c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -335,14 +335,68 @@ int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
}
EXPORT_SYMBOL(__sk_backlog_rcv);
-static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen)
+static int sock_get_timeout(long timeo, void *optval, bool old_timeval)
{
- struct timeval tv;
+ struct __kernel_sock_timeval tv;
+ int size;
- if (optlen < sizeof(tv))
- return -EINVAL;
- if (copy_from_user(&tv, optval, sizeof(tv)))
- return -EFAULT;
+ if (timeo == MAX_SCHEDULE_TIMEOUT) {
+ tv.tv_sec = 0;
+ tv.tv_usec = 0;
+ } else {
+ tv.tv_sec = timeo / HZ;
+ tv.tv_usec = ((timeo % HZ) * USEC_PER_SEC) / HZ;
+ }
+
+ if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
+ struct old_timeval32 tv32 = { tv.tv_sec, tv.tv_usec };
+ *(struct old_timeval32 *)optval = tv32;
+ return sizeof(tv32);
+ }
+
+ if (old_timeval) {
+ struct __kernel_old_timeval old_tv;
+ old_tv.tv_sec = tv.tv_sec;
+ old_tv.tv_usec = tv.tv_usec;
+ *(struct __kernel_old_timeval *)optval = old_tv;
+ size = sizeof(old_tv);
+ } else {
+ *(struct __kernel_sock_timeval *)optval = tv;
+ size = sizeof(tv);
+ }
+
+ return size;
+}
+
+static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen, bool old_timeval)
+{
+ struct __kernel_sock_timeval tv;
+
+ if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
+ struct old_timeval32 tv32;
+
+ if (optlen < sizeof(tv32))
+ return -EINVAL;
+
+ if (copy_from_user(&tv32, optval, sizeof(tv32)))
+ return -EFAULT;
+ tv.tv_sec = tv32.tv_sec;
+ tv.tv_usec = tv32.tv_usec;
+ } else if (old_timeval) {
+ struct __kernel_old_timeval old_tv;
+
+ if (optlen < sizeof(old_tv))
+ return -EINVAL;
+ if (copy_from_user(&old_tv, optval, sizeof(old_tv)))
+ return -EFAULT;
+ tv.tv_sec = old_tv.tv_sec;
+ tv.tv_usec = old_tv.tv_usec;
+ } else {
+ if (optlen < sizeof(tv))
+ return -EINVAL;
+ if (copy_from_user(&tv, optval, sizeof(tv)))
+ return -EFAULT;
+ }
if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC)
return -EDOM;
@@ -360,8 +414,8 @@ static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen)
*timeo_p = MAX_SCHEDULE_TIMEOUT;
if (tv.tv_sec == 0 && tv.tv_usec == 0)
return 0;
- if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT/HZ - 1))
- *timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP(tv.tv_usec, USEC_PER_SEC / HZ);
+ if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1))
+ *timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, USEC_PER_SEC / HZ);
return 0;
}
@@ -520,14 +574,11 @@ struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie)
}
EXPORT_SYMBOL(sk_dst_check);
-static int sock_setbindtodevice(struct sock *sk, char __user *optval,
- int optlen)
+static int sock_setbindtodevice_locked(struct sock *sk, int ifindex)
{
int ret = -ENOPROTOOPT;
#ifdef CONFIG_NETDEVICES
struct net *net = sock_net(sk);
- char devname[IFNAMSIZ];
- int index;
/* Sorry... */
ret = -EPERM;
@@ -535,6 +586,32 @@ static int sock_setbindtodevice(struct sock *sk, char __user *optval,
goto out;
ret = -EINVAL;
+ if (ifindex < 0)
+ goto out;
+
+ sk->sk_bound_dev_if = ifindex;
+ if (sk->sk_prot->rehash)
+ sk->sk_prot->rehash(sk);
+ sk_dst_reset(sk);
+
+ ret = 0;
+
+out:
+#endif
+
+ return ret;
+}
+
+static int sock_setbindtodevice(struct sock *sk, char __user *optval,
+ int optlen)
+{
+ int ret = -ENOPROTOOPT;
+#ifdef CONFIG_NETDEVICES
+ struct net *net = sock_net(sk);
+ char devname[IFNAMSIZ];
+ int index;
+
+ ret = -EINVAL;
if (optlen < 0)
goto out;
@@ -566,14 +643,9 @@ static int sock_setbindtodevice(struct sock *sk, char __user *optval,
}
lock_sock(sk);
- sk->sk_bound_dev_if = index;
- if (sk->sk_prot->rehash)
- sk->sk_prot->rehash(sk);
- sk_dst_reset(sk);
+ ret = sock_setbindtodevice_locked(sk, index);
release_sock(sk);
- ret = 0;
-
out:
#endif
@@ -815,10 +887,17 @@ set_rcvbuf:
clear_bit(SOCK_PASSCRED, &sock->flags);
break;
- case SO_TIMESTAMP:
- case SO_TIMESTAMPNS:
+ case SO_TIMESTAMP_OLD:
+ case SO_TIMESTAMP_NEW:
+ case SO_TIMESTAMPNS_OLD:
+ case SO_TIMESTAMPNS_NEW:
if (valbool) {
- if (optname == SO_TIMESTAMP)
+ if (optname == SO_TIMESTAMP_NEW || optname == SO_TIMESTAMPNS_NEW)
+ sock_set_flag(sk, SOCK_TSTAMP_NEW);
+ else
+ sock_reset_flag(sk, SOCK_TSTAMP_NEW);
+
+ if (optname == SO_TIMESTAMP_OLD || optname == SO_TIMESTAMP_NEW)
sock_reset_flag(sk, SOCK_RCVTSTAMPNS);
else
sock_set_flag(sk, SOCK_RCVTSTAMPNS);
@@ -827,10 +906,14 @@ set_rcvbuf:
} else {
sock_reset_flag(sk, SOCK_RCVTSTAMP);
sock_reset_flag(sk, SOCK_RCVTSTAMPNS);
+ sock_reset_flag(sk, SOCK_TSTAMP_NEW);
}
break;
- case SO_TIMESTAMPING:
+ case SO_TIMESTAMPING_NEW:
+ sock_set_flag(sk, SOCK_TSTAMP_NEW);
+ /* fall through */
+ case SO_TIMESTAMPING_OLD:
if (val & ~SOF_TIMESTAMPING_MASK) {
ret = -EINVAL;
break;
@@ -861,9 +944,13 @@ set_rcvbuf:
if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
sock_enable_timestamp(sk,
SOCK_TIMESTAMPING_RX_SOFTWARE);
- else
+ else {
+ if (optname == SO_TIMESTAMPING_NEW)
+ sock_reset_flag(sk, SOCK_TSTAMP_NEW);
+
sock_disable_timestamp(sk,
(1UL << SOCK_TIMESTAMPING_RX_SOFTWARE));
+ }
break;
case SO_RCVLOWAT:
@@ -875,12 +962,14 @@ set_rcvbuf:
sk->sk_rcvlowat = val ? : 1;
break;
- case SO_RCVTIMEO:
- ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen);
+ case SO_RCVTIMEO_OLD:
+ case SO_RCVTIMEO_NEW:
+ ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen, optname == SO_RCVTIMEO_OLD);
break;
- case SO_SNDTIMEO:
- ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen);
+ case SO_SNDTIMEO_OLD:
+ case SO_SNDTIMEO_NEW:
+ ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen, optname == SO_SNDTIMEO_OLD);
break;
case SO_ATTACH_FILTER:
@@ -1055,6 +1144,10 @@ set_rcvbuf:
}
break;
+ case SO_BINDTOIFINDEX:
+ ret = sock_setbindtodevice_locked(sk, val);
+ break;
+
default:
ret = -ENOPROTOOPT;
break;
@@ -1099,7 +1192,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
int val;
u64 val64;
struct linger ling;
- struct timeval tm;
+ struct old_timeval32 tm32;
+ struct __kernel_old_timeval tm;
+ struct __kernel_sock_timeval stm;
struct sock_txtime txtime;
} v;
@@ -1186,39 +1281,36 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
sock_warn_obsolete_bsdism("getsockopt");
break;
- case SO_TIMESTAMP:
+ case SO_TIMESTAMP_OLD:
v.val = sock_flag(sk, SOCK_RCVTSTAMP) &&
+ !sock_flag(sk, SOCK_TSTAMP_NEW) &&
!sock_flag(sk, SOCK_RCVTSTAMPNS);
break;
- case SO_TIMESTAMPNS:
- v.val = sock_flag(sk, SOCK_RCVTSTAMPNS);
+ case SO_TIMESTAMPNS_OLD:
+ v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && !sock_flag(sk, SOCK_TSTAMP_NEW);
break;
- case SO_TIMESTAMPING:
+ case SO_TIMESTAMP_NEW:
+ v.val = sock_flag(sk, SOCK_RCVTSTAMP) && sock_flag(sk, SOCK_TSTAMP_NEW);
+ break;
+
+ case SO_TIMESTAMPNS_NEW:
+ v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && sock_flag(sk, SOCK_TSTAMP_NEW);
+ break;
+
+ case SO_TIMESTAMPING_OLD:
v.val = sk->sk_tsflags;
break;
- case SO_RCVTIMEO:
- lv = sizeof(struct timeval);
- if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) {
- v.tm.tv_sec = 0;
- v.tm.tv_usec = 0;
- } else {
- v.tm.tv_sec = sk->sk_rcvtimeo / HZ;
- v.tm.tv_usec = ((sk->sk_rcvtimeo % HZ) * USEC_PER_SEC) / HZ;
- }
+ case SO_RCVTIMEO_OLD:
+ case SO_RCVTIMEO_NEW:
+ lv = sock_get_timeout(sk->sk_rcvtimeo, &v, SO_RCVTIMEO_OLD == optname);
break;
- case SO_SNDTIMEO:
- lv = sizeof(struct timeval);
- if (sk->sk_sndtimeo == MAX_SCHEDULE_TIMEOUT) {
- v.tm.tv_sec = 0;
- v.tm.tv_usec = 0;
- } else {
- v.tm.tv_sec = sk->sk_sndtimeo / HZ;
- v.tm.tv_usec = ((sk->sk_sndtimeo % HZ) * USEC_PER_SEC) / HZ;
- }
+ case SO_SNDTIMEO_OLD:
+ case SO_SNDTIMEO_NEW:
+ lv = sock_get_timeout(sk->sk_sndtimeo, &v, SO_SNDTIMEO_OLD == optname);
break;
case SO_RCVLOWAT:
@@ -1399,6 +1491,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
SOF_TXTIME_REPORT_ERRORS : 0;
break;
+ case SO_BINDTOIFINDEX:
+ v.val = sk->sk_bound_dev_if;
+ break;
+
default:
/* We implement the SO_SNDLOWAT etc to not be settable
* (1003.1g 7).
@@ -1726,7 +1822,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
newsk->sk_err_soft = 0;
newsk->sk_priority = 0;
newsk->sk_incoming_cpu = raw_smp_processor_id();
- atomic64_set(&newsk->sk_cookie, 0);
if (likely(newsk->sk_net_refcnt))
sock_inuse_add(sock_net(newsk), 1);
@@ -2122,7 +2217,7 @@ int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
return -EINVAL;
sockc->mark = *(u32 *)CMSG_DATA(cmsg);
break;
- case SO_TIMESTAMPING:
+ case SO_TIMESTAMPING_OLD:
if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
return -EINVAL;
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index d67ec17f2cc8..84bf2861f45f 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -36,6 +36,15 @@ static int net_msg_warn; /* Unused, but still a sysctl */
int sysctl_fb_tunnels_only_for_init_net __read_mostly = 0;
EXPORT_SYMBOL(sysctl_fb_tunnels_only_for_init_net);
+/* 0 - Keep current behavior:
+ * IPv4: inherit all current settings from init_net
+ * IPv6: reset all settings to default
+ * 1 - Both inherit all current settings from init_net
+ * 2 - Both reset all settings to default
+ */
+int sysctl_devconf_inherit_init_net __read_mostly;
+EXPORT_SYMBOL(sysctl_devconf_inherit_init_net);
+
#ifdef CONFIG_RPS
static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
@@ -544,6 +553,15 @@ static struct ctl_table net_core_table[] = {
.extra1 = &zero,
.extra2 = &one,
},
+ {
+ .procname = "devconf_inherit_init_net",
+ .data = &sysctl_devconf_inherit_init_net,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &two,
+ },
{ }
};
generated by cgit v1.2.3-70-g09d2 (git 2.48.1) at 2025-09-22 16:41:16 +0000