summaryrefslogtreecommitdiffstats
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/dev.c3
-rw-r--r--net/core/dev_addr_lists.c10
-rw-r--r--net/core/devlink.c345
-rw-r--r--net/core/filter.c10
-rw-r--r--net/core/flow_dissector.c32
-rw-r--r--net/core/flow_offload.c12
-rw-r--r--net/core/skmsg.c23
-rw-r--r--net/core/sock.c3
-rw-r--r--net/core/sock_map.c53
-rw-r--r--net/core/sysctl_net_core.c2
10 files changed, 347 insertions, 146 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index c02bae927812..b61075828358 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5591,7 +5591,7 @@ void netif_receive_skb_list(struct list_head *head)
}
EXPORT_SYMBOL(netif_receive_skb_list);
-DEFINE_PER_CPU(struct work_struct, flush_works);
+static DEFINE_PER_CPU(struct work_struct, flush_works);
/* Network device is going away, flush any packets still pending */
static void flush_backlog(struct work_struct *work)
@@ -7908,6 +7908,7 @@ EXPORT_SYMBOL(netdev_bonding_info_change);
/**
* netdev_get_xmit_slave - Get the xmit slave of master device
+ * @dev: device
* @skb: The packet
* @all_slaves: assume all the slaves are active
*
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 6393ba930097..54cd568e7c2f 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -690,6 +690,15 @@ void dev_uc_unsync(struct net_device *to, struct net_device *from)
if (to->addr_len != from->addr_len)
return;
+ /* netif_addr_lock_bh() uses lockdep subclass 0, this is okay for two
+ * reasons:
+ * 1) This is always called without any addr_list_lock, so as the
+ * outermost one here, it must be 0.
+ * 2) This is called by some callers after unlinking the upper device,
+ * so the dev->lower_level becomes 1 again.
+ * Therefore, the subclass for 'from' is 0, for 'to' is either 1 or
+ * larger.
+ */
netif_addr_lock_bh(from);
netif_addr_lock_nested(to);
__hw_addr_unsync(&to->uc, &from->uc, to->addr_len);
@@ -911,6 +920,7 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from)
if (to->addr_len != from->addr_len)
return;
+ /* See the above comments inside dev_uc_unsync(). */
netif_addr_lock_bh(from);
netif_addr_lock_nested(to);
__hw_addr_unsync(&to->mc, &from->mc, to->addr_len);
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 6ae36808c152..6335e1851088 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -386,19 +386,21 @@ devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id)
return NULL;
}
-#define DEVLINK_NL_FLAG_NEED_DEVLINK BIT(0)
-#define DEVLINK_NL_FLAG_NEED_PORT BIT(1)
-#define DEVLINK_NL_FLAG_NEED_SB BIT(2)
+#define DEVLINK_NL_FLAG_NEED_DEVLINK BIT(0)
+#define DEVLINK_NL_FLAG_NEED_PORT BIT(1)
+#define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT BIT(2)
+#define DEVLINK_NL_FLAG_NEED_SB BIT(3)
/* The per devlink instance lock is taken by default in the pre-doit
* operation, yet several commands do not require this. The global
* devlink lock is taken and protects from disruption by user-calls.
*/
-#define DEVLINK_NL_FLAG_NO_LOCK BIT(3)
+#define DEVLINK_NL_FLAG_NO_LOCK BIT(4)
static int devlink_nl_pre_doit(const struct genl_ops *ops,
struct sk_buff *skb, struct genl_info *info)
{
+ struct devlink_port *devlink_port;
struct devlink *devlink;
int err;
@@ -413,14 +415,17 @@ static int devlink_nl_pre_doit(const struct genl_ops *ops,
if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK) {
info->user_ptr[0] = devlink;
} else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT) {
- struct devlink_port *devlink_port;
-
devlink_port = devlink_port_get_from_info(devlink, info);
if (IS_ERR(devlink_port)) {
err = PTR_ERR(devlink_port);
goto unlock;
}
info->user_ptr[0] = devlink_port;
+ } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT) {
+ info->user_ptr[0] = devlink;
+ devlink_port = devlink_port_get_from_info(devlink, info);
+ if (!IS_ERR(devlink_port))
+ info->user_ptr[1] = devlink_port;
}
if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_SB) {
struct devlink_sb *devlink_sb;
@@ -528,8 +533,14 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg,
{
struct devlink_port_attrs *attrs = &devlink_port->attrs;
- if (!attrs->set)
+ if (!devlink_port->attrs_set)
return 0;
+ if (attrs->lanes) {
+ if (nla_put_u32(msg, DEVLINK_ATTR_PORT_LANES, attrs->lanes))
+ return -EMSGSIZE;
+ }
+ if (nla_put_u8(msg, DEVLINK_ATTR_PORT_SPLITTABLE, attrs->splittable))
+ return -EMSGSIZE;
if (nla_put_u16(msg, DEVLINK_ATTR_PORT_FLAVOUR, attrs->flavour))
return -EMSGSIZE;
switch (devlink_port->attrs.flavour) {
@@ -934,6 +945,7 @@ static int devlink_nl_cmd_port_split_doit(struct sk_buff *skb,
struct genl_info *info)
{
struct devlink *devlink = info->user_ptr[0];
+ struct devlink_port *devlink_port;
u32 port_index;
u32 count;
@@ -941,8 +953,27 @@ static int devlink_nl_cmd_port_split_doit(struct sk_buff *skb,
!info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT])
return -EINVAL;
+ devlink_port = devlink_port_get_from_info(devlink, info);
port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
count = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]);
+
+ if (IS_ERR(devlink_port))
+ return -EINVAL;
+
+ if (!devlink_port->attrs.splittable) {
+ /* Split ports cannot be split. */
+ if (devlink_port->attrs.split)
+ NL_SET_ERR_MSG_MOD(info->extack, "Port cannot be split further");
+ else
+ NL_SET_ERR_MSG_MOD(info->extack, "Port cannot be split");
+ return -EINVAL;
+ }
+
+ if (count < 2 || !is_power_of_2(count) || count > devlink_port->attrs.lanes) {
+ NL_SET_ERR_MSG_MOD(info->extack, "Invalid split count");
+ return -EINVAL;
+ }
+
return devlink_port_split(devlink, port_index, count, info->extack);
}
@@ -5261,6 +5292,7 @@ struct devlink_health_reporter {
void *priv;
const struct devlink_health_reporter_ops *ops;
struct devlink *devlink;
+ struct devlink_port *devlink_port;
struct devlink_fmsg *dump_fmsg;
struct mutex dump_lock; /* lock parallel read/write from dump buffers */
u64 graceful_period;
@@ -5283,18 +5315,98 @@ devlink_health_reporter_priv(struct devlink_health_reporter *reporter)
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)
+__devlink_health_reporter_find_by_name(struct list_head *reporter_list,
+ struct mutex *list_lock,
+ const char *reporter_name)
{
struct devlink_health_reporter *reporter;
- lockdep_assert_held(&devlink->reporters_lock);
- list_for_each_entry(reporter, &devlink->reporter_list, list)
+ lockdep_assert_held(list_lock);
+ list_for_each_entry(reporter, reporter_list, list)
if (!strcmp(reporter->ops->name, reporter_name))
return reporter;
return NULL;
}
+static struct devlink_health_reporter *
+devlink_health_reporter_find_by_name(struct devlink *devlink,
+ const char *reporter_name)
+{
+ return __devlink_health_reporter_find_by_name(&devlink->reporter_list,
+ &devlink->reporters_lock,
+ reporter_name);
+}
+
+static struct devlink_health_reporter *
+devlink_port_health_reporter_find_by_name(struct devlink_port *devlink_port,
+ const char *reporter_name)
+{
+ return __devlink_health_reporter_find_by_name(&devlink_port->reporter_list,
+ &devlink_port->reporters_lock,
+ reporter_name);
+}
+
+static struct devlink_health_reporter *
+__devlink_health_reporter_create(struct devlink *devlink,
+ const struct devlink_health_reporter_ops *ops,
+ u64 graceful_period, void *priv)
+{
+ struct devlink_health_reporter *reporter;
+
+ if (WARN_ON(graceful_period && !ops->recover))
+ return ERR_PTR(-EINVAL);
+
+ reporter = kzalloc(sizeof(*reporter), GFP_KERNEL);
+ if (!reporter)
+ return ERR_PTR(-ENOMEM);
+
+ reporter->priv = priv;
+ reporter->ops = ops;
+ reporter->devlink = devlink;
+ reporter->graceful_period = graceful_period;
+ reporter->auto_recover = !!ops->recover;
+ reporter->auto_dump = !!ops->dump;
+ mutex_init(&reporter->dump_lock);
+ refcount_set(&reporter->refcount, 1);
+ return reporter;
+}
+
+/**
+ * devlink_port_health_reporter_create - create devlink health reporter for
+ * specified port instance
+ *
+ * @port: devlink_port which should contain the new reporter
+ * @ops: ops
+ * @graceful_period: to avoid recovery loops, in msecs
+ * @priv: priv
+ */
+struct devlink_health_reporter *
+devlink_port_health_reporter_create(struct devlink_port *port,
+ const struct devlink_health_reporter_ops *ops,
+ u64 graceful_period, void *priv)
+{
+ struct devlink_health_reporter *reporter;
+
+ mutex_lock(&port->reporters_lock);
+ if (__devlink_health_reporter_find_by_name(&port->reporter_list,
+ &port->reporters_lock, ops->name)) {
+ reporter = ERR_PTR(-EEXIST);
+ goto unlock;
+ }
+
+ reporter = __devlink_health_reporter_create(port->devlink, ops,
+ graceful_period, priv);
+ if (IS_ERR(reporter))
+ goto unlock;
+
+ reporter->devlink_port = port;
+ list_add_tail(&reporter->list, &port->reporter_list);
+unlock:
+ mutex_unlock(&port->reporters_lock);
+ return reporter;
+}
+EXPORT_SYMBOL_GPL(devlink_port_health_reporter_create);
+
/**
* devlink_health_reporter_create - create devlink health reporter
*
@@ -5316,25 +5428,11 @@ devlink_health_reporter_create(struct devlink *devlink,
goto unlock;
}
- if (WARN_ON(graceful_period && !ops->recover)) {
- reporter = ERR_PTR(-EINVAL);
+ reporter = __devlink_health_reporter_create(devlink, ops,
+ graceful_period, priv);
+ if (IS_ERR(reporter))
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 = !!ops->recover;
- reporter->auto_dump = !!ops->dump;
- mutex_init(&reporter->dump_lock);
- refcount_set(&reporter->refcount, 1);
list_add_tail(&reporter->list, &devlink->reporter_list);
unlock:
mutex_unlock(&devlink->reporters_lock);
@@ -5342,6 +5440,29 @@ unlock:
}
EXPORT_SYMBOL_GPL(devlink_health_reporter_create);
+static void
+devlink_health_reporter_free(struct devlink_health_reporter *reporter)
+{
+ mutex_destroy(&reporter->dump_lock);
+ if (reporter->dump_fmsg)
+ devlink_fmsg_free(reporter->dump_fmsg);
+ kfree(reporter);
+}
+
+static void
+devlink_health_reporter_put(struct devlink_health_reporter *reporter)
+{
+ if (refcount_dec_and_test(&reporter->refcount))
+ devlink_health_reporter_free(reporter);
+}
+
+static void
+__devlink_health_reporter_destroy(struct devlink_health_reporter *reporter)
+{
+ list_del(&reporter->list);
+ devlink_health_reporter_put(reporter);
+}
+
/**
* devlink_health_reporter_destroy - destroy devlink health reporter
*
@@ -5350,18 +5471,30 @@ EXPORT_SYMBOL_GPL(devlink_health_reporter_create);
void
devlink_health_reporter_destroy(struct devlink_health_reporter *reporter)
{
- mutex_lock(&reporter->devlink->reporters_lock);
- list_del(&reporter->list);
- mutex_unlock(&reporter->devlink->reporters_lock);
- while (refcount_read(&reporter->refcount) > 1)
- msleep(100);
- mutex_destroy(&reporter->dump_lock);
- if (reporter->dump_fmsg)
- devlink_fmsg_free(reporter->dump_fmsg);
- kfree(reporter);
+ struct mutex *lock = &reporter->devlink->reporters_lock;
+
+ mutex_lock(lock);
+ __devlink_health_reporter_destroy(reporter);
+ mutex_unlock(lock);
}
EXPORT_SYMBOL_GPL(devlink_health_reporter_destroy);
+/**
+ * devlink_port_health_reporter_destroy - destroy devlink port health reporter
+ *
+ * @reporter: devlink health reporter to destroy
+ */
+void
+devlink_port_health_reporter_destroy(struct devlink_health_reporter *reporter)
+{
+ struct mutex *lock = &reporter->devlink_port->reporters_lock;
+
+ mutex_lock(lock);
+ __devlink_health_reporter_destroy(reporter);
+ mutex_unlock(lock);
+}
+EXPORT_SYMBOL_GPL(devlink_port_health_reporter_destroy);
+
static int
devlink_nl_health_reporter_fill(struct sk_buff *msg,
struct devlink *devlink,
@@ -5379,6 +5512,10 @@ devlink_nl_health_reporter_fill(struct sk_buff *msg,
if (devlink_nl_put_handle(msg, devlink))
goto genlmsg_cancel;
+ if (reporter->devlink_port) {
+ if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, reporter->devlink_port->index))
+ goto genlmsg_cancel;
+ }
reporter_attr = nla_nest_start_noflag(msg,
DEVLINK_ATTR_HEALTH_REPORTER);
if (!reporter_attr)
@@ -5586,17 +5723,28 @@ devlink_health_reporter_get_from_attrs(struct devlink *devlink,
struct nlattr **attrs)
{
struct devlink_health_reporter *reporter;
+ struct devlink_port *devlink_port;
char *reporter_name;
if (!attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME])
return NULL;
reporter_name = nla_data(attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]);
- mutex_lock(&devlink->reporters_lock);
- reporter = devlink_health_reporter_find_by_name(devlink, reporter_name);
- if (reporter)
- refcount_inc(&reporter->refcount);
- mutex_unlock(&devlink->reporters_lock);
+ devlink_port = devlink_port_get_from_attrs(devlink, attrs);
+ if (IS_ERR(devlink_port)) {
+ mutex_lock(&devlink->reporters_lock);
+ reporter = devlink_health_reporter_find_by_name(devlink, reporter_name);
+ if (reporter)
+ refcount_inc(&reporter->refcount);
+ mutex_unlock(&devlink->reporters_lock);
+ } else {
+ mutex_lock(&devlink_port->reporters_lock);
+ reporter = devlink_port_health_reporter_find_by_name(devlink_port, reporter_name);
+ if (reporter)
+ refcount_inc(&reporter->refcount);
+ mutex_unlock(&devlink_port->reporters_lock);
+ }
+
return reporter;
}
@@ -5628,12 +5776,6 @@ unlock:
return NULL;
}
-static void
-devlink_health_reporter_put(struct devlink_health_reporter *reporter)
-{
- refcount_dec(&reporter->refcount);
-}
-
void
devlink_health_reporter_state_update(struct devlink_health_reporter *reporter,
enum devlink_health_reporter_state state)
@@ -5690,6 +5832,7 @@ devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg,
struct netlink_callback *cb)
{
struct devlink_health_reporter *reporter;
+ struct devlink_port *port;
struct devlink *devlink;
int start = cb->args[0];
int idx = 0;
@@ -5720,6 +5863,31 @@ devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg,
}
mutex_unlock(&devlink->reporters_lock);
}
+
+ list_for_each_entry(devlink, &devlink_list, list) {
+ if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
+ continue;
+ list_for_each_entry(port, &devlink->port_list, list) {
+ mutex_lock(&port->reporters_lock);
+ list_for_each_entry(reporter, &port->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(&port->reporters_lock);
+ goto out;
+ }
+ idx++;
+ }
+ mutex_unlock(&port->reporters_lock);
+ }
+ }
out:
mutex_unlock(&devlink_mutex);
@@ -7099,7 +7267,7 @@ static const struct genl_ops devlink_nl_ops[] = {
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = devlink_nl_cmd_health_reporter_get_doit,
.dumpit = devlink_nl_cmd_health_reporter_get_dumpit,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT |
DEVLINK_NL_FLAG_NO_LOCK,
/* can be retrieved by unprivileged users */
},
@@ -7108,7 +7276,7 @@ static const struct genl_ops devlink_nl_ops[] = {
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = devlink_nl_cmd_health_reporter_set_doit,
.flags = GENL_ADMIN_PERM,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT |
DEVLINK_NL_FLAG_NO_LOCK,
},
{
@@ -7116,7 +7284,7 @@ static const struct genl_ops devlink_nl_ops[] = {
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = devlink_nl_cmd_health_reporter_recover_doit,
.flags = GENL_ADMIN_PERM,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT |
DEVLINK_NL_FLAG_NO_LOCK,
},
{
@@ -7124,7 +7292,7 @@ static const struct genl_ops devlink_nl_ops[] = {
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = devlink_nl_cmd_health_reporter_diagnose_doit,
.flags = GENL_ADMIN_PERM,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT |
DEVLINK_NL_FLAG_NO_LOCK,
},
{
@@ -7133,7 +7301,7 @@ static const struct genl_ops devlink_nl_ops[] = {
GENL_DONT_VALIDATE_DUMP_STRICT,
.dumpit = devlink_nl_cmd_health_reporter_dump_get_dumpit,
.flags = GENL_ADMIN_PERM,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT |
DEVLINK_NL_FLAG_NO_LOCK,
},
{
@@ -7141,7 +7309,7 @@ static const struct genl_ops devlink_nl_ops[] = {
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = devlink_nl_cmd_health_reporter_dump_clear_doit,
.flags = GENL_ADMIN_PERM,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT |
DEVLINK_NL_FLAG_NO_LOCK,
},
{
@@ -7401,6 +7569,8 @@ int devlink_port_register(struct devlink *devlink,
list_add_tail(&devlink_port->list, &devlink->port_list);
INIT_LIST_HEAD(&devlink_port->param_list);
mutex_unlock(&devlink->lock);
+ INIT_LIST_HEAD(&devlink_port->reporter_list);
+ mutex_init(&devlink_port->reporters_lock);
INIT_DELAYED_WORK(&devlink_port->type_warn_dw, &devlink_port_type_warn);
devlink_port_type_warn_schedule(devlink_port);
devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
@@ -7417,6 +7587,8 @@ void devlink_port_unregister(struct devlink_port *devlink_port)
{
struct devlink *devlink = devlink_port->devlink;
+ WARN_ON(!list_empty(&devlink_port->reporter_list));
+ mutex_destroy(&devlink_port->reporters_lock);
devlink_port_type_warn_cancel(devlink_port);
devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL);
mutex_lock(&devlink->lock);
@@ -7510,24 +7682,20 @@ void devlink_port_type_clear(struct devlink_port *devlink_port)
EXPORT_SYMBOL_GPL(devlink_port_type_clear);
static int __devlink_port_attrs_set(struct devlink_port *devlink_port,
- enum devlink_port_flavour flavour,
- const unsigned char *switch_id,
- unsigned char switch_id_len)
+ enum devlink_port_flavour flavour)
{
struct devlink_port_attrs *attrs = &devlink_port->attrs;
if (WARN_ON(devlink_port->registered))
return -EEXIST;
- attrs->set = true;
+ devlink_port->attrs_set = true;
attrs->flavour = flavour;
- if (switch_id) {
- attrs->switch_port = true;
- if (WARN_ON(switch_id_len > MAX_PHYS_ITEM_ID_LEN))
- switch_id_len = MAX_PHYS_ITEM_ID_LEN;
- memcpy(attrs->switch_id.id, switch_id, switch_id_len);
- attrs->switch_id.id_len = switch_id_len;
+ if (attrs->switch_id.id_len) {
+ devlink_port->switch_port = true;
+ if (WARN_ON(attrs->switch_id.id_len > MAX_PHYS_ITEM_ID_LEN))
+ attrs->switch_id.id_len = MAX_PHYS_ITEM_ID_LEN;
} else {
- attrs->switch_port = false;
+ devlink_port->switch_port = false;
}
return 0;
}
@@ -7536,33 +7704,18 @@ static int __devlink_port_attrs_set(struct devlink_port *devlink_port,
* devlink_port_attrs_set - Set port attributes
*
* @devlink_port: devlink port
- * @flavour: flavour of the port
- * @port_number: number of the port that is facing user, for example
- * the front panel port number
- * @split: indicates if this is split port
- * @split_subport_number: if the port is split, this is the number
- * of subport.
- * @switch_id: if the port is part of switch, this is buffer with ID,
- * otwerwise this is NULL
- * @switch_id_len: length of the switch_id buffer
+ * @attrs: devlink port attrs
*/
void devlink_port_attrs_set(struct devlink_port *devlink_port,
- enum devlink_port_flavour flavour,
- u32 port_number, bool split,
- u32 split_subport_number,
- const unsigned char *switch_id,
- unsigned char switch_id_len)
+ struct devlink_port_attrs *attrs)
{
- struct devlink_port_attrs *attrs = &devlink_port->attrs;
int ret;
- ret = __devlink_port_attrs_set(devlink_port, flavour,
- switch_id, switch_id_len);
+ devlink_port->attrs = *attrs;
+ ret = __devlink_port_attrs_set(devlink_port, attrs->flavour);
if (ret)
return;
- attrs->split = split;
- attrs->phys.port_number = port_number;
- attrs->phys.split_subport_number = split_subport_number;
+ WARN_ON(attrs->splittable && attrs->split);
}
EXPORT_SYMBOL_GPL(devlink_port_attrs_set);
@@ -7571,20 +7724,14 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_set);
*
* @devlink_port: devlink port
* @pf: associated PF for the devlink port instance
- * @switch_id: if the port is part of switch, this is buffer with ID,
- * otherwise this is NULL
- * @switch_id_len: length of the switch_id buffer
*/
-void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port,
- const unsigned char *switch_id,
- unsigned char switch_id_len, u16 pf)
+void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf)
{
struct devlink_port_attrs *attrs = &devlink_port->attrs;
int ret;
ret = __devlink_port_attrs_set(devlink_port,
- DEVLINK_PORT_FLAVOUR_PCI_PF,
- switch_id, switch_id_len);
+ DEVLINK_PORT_FLAVOUR_PCI_PF);
if (ret)
return;
@@ -7598,21 +7745,15 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set);
* @devlink_port: devlink port
* @pf: associated PF for the devlink port instance
* @vf: associated VF of a PF for the devlink port instance
- * @switch_id: if the port is part of switch, this is buffer with ID,
- * otherwise this is NULL
- * @switch_id_len: length of the switch_id buffer
*/
void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port,
- const unsigned char *switch_id,
- unsigned char switch_id_len,
u16 pf, u16 vf)
{
struct devlink_port_attrs *attrs = &devlink_port->attrs;
int ret;
ret = __devlink_port_attrs_set(devlink_port,
- DEVLINK_PORT_FLAVOUR_PCI_VF,
- switch_id, switch_id_len);
+ DEVLINK_PORT_FLAVOUR_PCI_VF);
if (ret)
return;
attrs->pci_vf.pf = pf;
@@ -7626,7 +7767,7 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
struct devlink_port_attrs *attrs = &devlink_port->attrs;
int n = 0;
- if (!attrs->set)
+ if (!devlink_port->attrs_set)
return -EOPNOTSUPP;
switch (attrs->flavour) {
@@ -9461,7 +9602,7 @@ int devlink_compat_switch_id_get(struct net_device *dev,
* any devlink lock as only permanent values are accessed.
*/
devlink_port = netdev_to_devlink_port(dev);
- if (!devlink_port || !devlink_port->attrs.switch_port)
+ if (!devlink_port || !devlink_port->switch_port)
return -EOPNOTSUPP;
memcpy(ppid, &devlink_port->attrs.switch_id, sizeof(*ppid));
diff --git a/net/core/filter.c b/net/core/filter.c
index 4e572441e64a..bdd2382e655d 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5894,12 +5894,16 @@ BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb)
{
unsigned int iphdr_len;
- if (skb->protocol == cpu_to_be16(ETH_P_IP))
+ switch (skb_protocol(skb, true)) {
+ case cpu_to_be16(ETH_P_IP):
iphdr_len = sizeof(struct iphdr);
- else if (skb->protocol == cpu_to_be16(ETH_P_IPV6))
+ break;
+ case cpu_to_be16(ETH_P_IPV6):
iphdr_len = sizeof(struct ipv6hdr);
- else
+ break;
+ default:
return 0;
+ }
if (skb_headlen(skb) < iphdr_len)
return 0;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index d02df0b6d0d9..142a8824f0a8 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -70,10 +70,10 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
EXPORT_SYMBOL(skb_flow_dissector_init);
#ifdef CONFIG_BPF_SYSCALL
-int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog)
+int flow_dissector_bpf_prog_attach_check(struct net *net,
+ struct bpf_prog *prog)
{
enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR;
- struct bpf_prog *attached;
if (net == &init_net) {
/* BPF flow dissector in the root namespace overrides
@@ -86,26 +86,17 @@ int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog)
for_each_net(ns) {
if (ns == &init_net)
continue;
- if (rcu_access_pointer(ns->bpf.progs[type]))
+ if (rcu_access_pointer(ns->bpf.run_array[type]))
return -EEXIST;
}
} else {
/* Make sure root flow dissector is not attached
* when attaching to the non-root namespace.
*/
- if (rcu_access_pointer(init_net.bpf.progs[type]))
+ if (rcu_access_pointer(init_net.bpf.run_array[type]))
return -EEXIST;
}
- attached = rcu_dereference_protected(net->bpf.progs[type],
- lockdep_is_held(&netns_bpf_mutex));
- if (attached == prog)
- /* The same program cannot be attached twice */
- return -EINVAL;
-
- rcu_assign_pointer(net->bpf.progs[type], prog);
- if (attached)
- bpf_prog_put(attached);
return 0;
}
#endif /* CONFIG_BPF_SYSCALL */
@@ -903,7 +894,6 @@ bool __skb_flow_dissect(const struct net *net,
struct flow_dissector_key_addrs *key_addrs;
struct flow_dissector_key_tags *key_tags;
struct flow_dissector_key_vlan *key_vlan;
- struct bpf_prog *attached = NULL;
enum flow_dissect_ret fdret;
enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX;
bool mpls_el = false;
@@ -960,14 +950,14 @@ bool __skb_flow_dissect(const struct net *net,
WARN_ON_ONCE(!net);
if (net) {
enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR;
+ struct bpf_prog_array *run_array;
rcu_read_lock();
- attached = rcu_dereference(init_net.bpf.progs[type]);
-
- if (!attached)
- attached = rcu_dereference(net->bpf.progs[type]);
+ run_array = rcu_dereference(init_net.bpf.run_array[type]);
+ if (!run_array)
+ run_array = rcu_dereference(net->bpf.run_array[type]);
- if (attached) {
+ if (run_array) {
struct bpf_flow_keys flow_keys;
struct bpf_flow_dissector ctx = {
.flow_keys = &flow_keys,
@@ -975,6 +965,7 @@ bool __skb_flow_dissect(const struct net *net,
.data_end = data + hlen,
};
__be16 n_proto = proto;
+ struct bpf_prog *prog;
if (skb) {
ctx.skb = skb;
@@ -985,7 +976,8 @@ bool __skb_flow_dissect(const struct net *net,
n_proto = skb->protocol;
}
- ret = bpf_flow_dissect(attached, &ctx, n_proto, nhoff,
+ prog = READ_ONCE(run_array->items[0].prog);
+ ret = bpf_flow_dissect(prog, &ctx, n_proto, nhoff,
hlen, flags);
__skb_flow_bpf_to_target(&flow_keys, flow_dissector,
target_container);
diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c
index b739cfab796e..b8cf6ff5f961 100644
--- a/net/core/flow_offload.c
+++ b/net/core/flow_offload.c
@@ -429,7 +429,7 @@ EXPORT_SYMBOL(flow_indr_dev_unregister);
static void flow_block_indr_init(struct flow_block_cb *flow_block,
struct flow_block_offload *bo,
- struct net_device *dev, void *data,
+ struct net_device *dev, struct Qdisc *sch, void *data,
void *cb_priv,
void (*cleanup)(struct flow_block_cb *block_cb))
{
@@ -437,6 +437,7 @@ static void flow_block_indr_init(struct flow_block_cb *flow_block,
flow_block->indr.data = data;
flow_block->indr.cb_priv = cb_priv;
flow_block->indr.dev = dev;
+ flow_block->indr.sch = sch;
flow_block->indr.cleanup = cleanup;
}
@@ -444,7 +445,8 @@ struct flow_block_cb *flow_indr_block_cb_alloc(flow_setup_cb_t *cb,
void *cb_ident, void *cb_priv,
void (*release)(void *cb_priv),
struct flow_block_offload *bo,
- struct net_device *dev, void *data,
+ struct net_device *dev,
+ struct Qdisc *sch, void *data,
void *indr_cb_priv,
void (*cleanup)(struct flow_block_cb *block_cb))
{
@@ -454,7 +456,7 @@ struct flow_block_cb *flow_indr_block_cb_alloc(flow_setup_cb_t *cb,
if (IS_ERR(block_cb))
goto out;
- flow_block_indr_init(block_cb, bo, dev, data, indr_cb_priv, cleanup);
+ flow_block_indr_init(block_cb, bo, dev, sch, data, indr_cb_priv, cleanup);
list_add(&block_cb->indr.list, &flow_block_indr_list);
out:
@@ -462,7 +464,7 @@ out:
}
EXPORT_SYMBOL(flow_indr_block_cb_alloc);
-int flow_indr_dev_setup_offload(struct net_device *dev,
+int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch,
enum tc_setup_type type, void *data,
struct flow_block_offload *bo,
void (*cleanup)(struct flow_block_cb *block_cb))
@@ -471,7 +473,7 @@ int flow_indr_dev_setup_offload(struct net_device *dev,
mutex_lock(&flow_indr_block_lock);
list_for_each_entry(this, &flow_block_indr_dev_list, list)
- this->cb(dev, this->cb_priv, type, bo, data, cleanup);
+ this->cb(dev, sch, this->cb_priv, type, bo, data, cleanup);
mutex_unlock(&flow_indr_block_lock);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 351afbf6bfba..6a32a1fd34f8 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -683,7 +683,7 @@ static struct sk_psock *sk_psock_from_strp(struct strparser *strp)
return container_of(parser, struct sk_psock, parser);
}
-static void sk_psock_skb_redirect(struct sk_psock *psock, struct sk_buff *skb)
+static void sk_psock_skb_redirect(struct sk_buff *skb)
{
struct sk_psock *psock_other;
struct sock *sk_other;
@@ -715,12 +715,11 @@ static void sk_psock_skb_redirect(struct sk_psock *psock, struct sk_buff *skb)
}
}
-static void sk_psock_tls_verdict_apply(struct sk_psock *psock,
- struct sk_buff *skb, int verdict)
+static void sk_psock_tls_verdict_apply(struct sk_buff *skb, int verdict)
{
switch (verdict) {
case __SK_REDIRECT:
- sk_psock_skb_redirect(psock, skb);
+ sk_psock_skb_redirect(skb);
break;
case __SK_PASS:
case __SK_DROP:
@@ -741,8 +740,8 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb)
ret = sk_psock_bpf_run(psock, prog, skb);
ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
}
+ sk_psock_tls_verdict_apply(skb, ret);
rcu_read_unlock();
- sk_psock_tls_verdict_apply(psock, skb, ret);
return ret;
}
EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read);
@@ -770,7 +769,7 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,
}
goto out_free;
case __SK_REDIRECT:
- sk_psock_skb_redirect(psock, skb);
+ sk_psock_skb_redirect(skb);
break;
case __SK_DROP:
/* fall-through */
@@ -782,11 +781,18 @@ out_free:
static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
{
- struct sk_psock *psock = sk_psock_from_strp(strp);
+ struct sk_psock *psock;
struct bpf_prog *prog;
int ret = __SK_DROP;
+ struct sock *sk;
rcu_read_lock();
+ sk = strp->sk;
+ psock = sk_psock(sk);
+ if (unlikely(!psock)) {
+ kfree_skb(skb);
+ goto out;
+ }
prog = READ_ONCE(psock->progs.skb_verdict);
if (likely(prog)) {
skb_orphan(skb);
@@ -794,8 +800,9 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
ret = sk_psock_bpf_run(psock, prog, skb);
ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
}
- rcu_read_unlock();
sk_psock_verdict_apply(psock, skb, ret);
+out:
+ rcu_read_unlock();
}
static int sk_psock_strp_read_done(struct strparser *strp, int err)
diff --git a/net/core/sock.c b/net/core/sock.c
index f5b5fdd61c88..11d6f77dd562 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1917,7 +1917,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
/* sk->sk_memcg will be populated at accept() time */
newsk->sk_memcg = NULL;
- cgroup_sk_alloc(&newsk->sk_cgrp_data);
+ cgroup_sk_clone(&newsk->sk_cgrp_data);
rcu_read_lock();
filter = rcu_dereference(sk->sk_filter);
@@ -3566,6 +3566,7 @@ int sock_load_diag_module(int family, int protocol)
#ifdef CONFIG_INET
if (family == AF_INET &&
protocol != IPPROTO_RAW &&
+ protocol < MAX_INET_PROTOS &&
!rcu_access_pointer(inet_protos[protocol]))
return -ENOENT;
#endif
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 4c1123c749bb..119f52a99dc1 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -70,11 +70,49 @@ int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog)
struct fd f;
int ret;
+ if (attr->attach_flags || attr->replace_bpf_fd)
+ return -EINVAL;
+
f = fdget(ufd);
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
- ret = sock_map_prog_update(map, prog, attr->attach_type);
+ ret = sock_map_prog_update(map, prog, NULL, attr->attach_type);
+ fdput(f);
+ return ret;
+}
+
+int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
+{
+ u32 ufd = attr->target_fd;
+ struct bpf_prog *prog;
+ struct bpf_map *map;
+ struct fd f;
+ int ret;
+
+ if (attr->attach_flags || attr->replace_bpf_fd)
+ return -EINVAL;
+
+ f = fdget(ufd);
+ map = __bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ prog = bpf_prog_get(attr->attach_bpf_fd);
+ if (IS_ERR(prog)) {
+ ret = PTR_ERR(prog);
+ goto put_map;
+ }
+
+ if (prog->type != ptype) {
+ ret = -EINVAL;
+ goto put_prog;
+ }
+
+ ret = sock_map_prog_update(map, NULL, prog, attr->attach_type);
+put_prog:
+ bpf_prog_put(prog);
+put_map:
fdput(f);
return ret;
}
@@ -1209,27 +1247,32 @@ static struct sk_psock_progs *sock_map_progs(struct bpf_map *map)
}
int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
- u32 which)
+ struct bpf_prog *old, u32 which)
{
struct sk_psock_progs *progs = sock_map_progs(map);
+ struct bpf_prog **pprog;
if (!progs)
return -EOPNOTSUPP;
switch (which) {
case BPF_SK_MSG_VERDICT:
- psock_set_prog(&progs->msg_parser, prog);
+ pprog = &progs->msg_parser;
break;
case BPF_SK_SKB_STREAM_PARSER:
- psock_set_prog(&progs->skb_parser, prog);
+ pprog = &progs->skb_parser;
break;
case BPF_SK_SKB_STREAM_VERDICT:
- psock_set_prog(&progs->skb_verdict, prog);
+ pprog = &progs->skb_verdict;
break;
default:
return -EOPNOTSUPP;
}
+ if (old)
+ return psock_replace_prog(pprog, prog, old);
+
+ psock_set_prog(pprog, prog);
return 0;
}
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index f93f8ace6c56..6ada114bbcca 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -274,7 +274,7 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write,
ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
if (write && !ret) {
if (jit_enable < 2 ||
- (jit_enable == 2 && bpf_dump_raw_ok())) {
+ (jit_enable == 2 && bpf_dump_raw_ok(current_cred()))) {
*(int *)table->data = jit_enable;
if (jit_enable == 2)
pr_warn("bpf_jit_enable = 2 was set! NEVER use this in production, only for JIT debugging!\n");
generated by cgit v1.2.3 (git 2.25.1) at 2024-08-12 12:54:11 +0000