* [PATCH 08/10] batman-adv: no need to check return value of debugfs_create functions
From: Simon Wunderlich @ 2019-06-28 13:56 UTC (permalink / raw)
To: davem
Cc: netdev, b.a.t.m.a.n, Greg Kroah-Hartman, Marek Lindner,
Simon Wunderlich, Antonio Quartulli, Sven Eckelmann
In-Reply-To: <20190628135604.11581-1-sw@simonwunderlich.de>
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
When calling debugfs functions, there is no need to ever check the
return value. The function can work or not, but the code logic should
never do something different based on this.
Because we don't care if debugfs works or not, this trickles back a bit
so we can clean things up by making some functions return void instead
of an error value that is never going to fail.
Cc: Marek Lindner <mareklindner@neomailbox.ch>
Cc: Simon Wunderlich <sw@simonwunderlich.de>
Cc: Antonio Quartulli <a@unstable.cc>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: b.a.t.m.a.n@lists.open-mesh.org
Cc: netdev@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[sven@narfation.org: drop unused variables]
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
net/batman-adv/debugfs.c | 99 +++++++++--------------------------------
net/batman-adv/debugfs.h | 5 +--
net/batman-adv/hard-interface.c | 6 +--
net/batman-adv/icmp_socket.c | 20 ++-------
net/batman-adv/icmp_socket.h | 2 +-
net/batman-adv/log.c | 17 ++-----
net/batman-adv/network-coding.c | 29 +++---------
net/batman-adv/network-coding.h | 5 +--
8 files changed, 39 insertions(+), 144 deletions(-)
diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c
index d38d70ccdd5a..38c4d8e51155 100644
--- a/net/batman-adv/debugfs.c
+++ b/net/batman-adv/debugfs.c
@@ -10,7 +10,6 @@
#include <asm/current.h>
#include <linux/dcache.h>
#include <linux/debugfs.h>
-#include <linux/err.h>
#include <linux/errno.h>
#include <linux/export.h>
#include <linux/fs.h>
@@ -293,31 +292,13 @@ static struct batadv_debuginfo *batadv_hardif_debuginfos[] = {
void batadv_debugfs_init(void)
{
struct batadv_debuginfo **bat_debug;
- struct dentry *file;
batadv_debugfs = debugfs_create_dir(BATADV_DEBUGFS_SUBDIR, NULL);
- if (batadv_debugfs == ERR_PTR(-ENODEV))
- batadv_debugfs = NULL;
-
- if (!batadv_debugfs)
- goto err;
-
- for (bat_debug = batadv_general_debuginfos; *bat_debug; ++bat_debug) {
- file = debugfs_create_file(((*bat_debug)->attr).name,
- S_IFREG | ((*bat_debug)->attr).mode,
- batadv_debugfs, NULL,
- &(*bat_debug)->fops);
- if (!file) {
- pr_err("Can't add general debugfs file: %s\n",
- ((*bat_debug)->attr).name);
- goto err;
- }
- }
- return;
-err:
- debugfs_remove_recursive(batadv_debugfs);
- batadv_debugfs = NULL;
+ for (bat_debug = batadv_general_debuginfos; *bat_debug; ++bat_debug)
+ debugfs_create_file(((*bat_debug)->attr).name,
+ S_IFREG | ((*bat_debug)->attr).mode,
+ batadv_debugfs, NULL, &(*bat_debug)->fops);
}
/**
@@ -333,42 +314,23 @@ void batadv_debugfs_destroy(void)
* batadv_debugfs_add_hardif() - creates the base directory for a hard interface
* in debugfs.
* @hard_iface: hard interface which should be added.
- *
- * Return: 0 on success or negative error number in case of failure
*/
-int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface)
+void batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface)
{
struct net *net = dev_net(hard_iface->net_dev);
struct batadv_debuginfo **bat_debug;
- struct dentry *file;
-
- if (!batadv_debugfs)
- goto out;
if (net != &init_net)
- return 0;
+ return;
hard_iface->debug_dir = debugfs_create_dir(hard_iface->net_dev->name,
batadv_debugfs);
- if (!hard_iface->debug_dir)
- goto out;
-
- for (bat_debug = batadv_hardif_debuginfos; *bat_debug; ++bat_debug) {
- file = debugfs_create_file(((*bat_debug)->attr).name,
- S_IFREG | ((*bat_debug)->attr).mode,
- hard_iface->debug_dir,
- hard_iface->net_dev,
- &(*bat_debug)->fops);
- if (!file)
- goto rem_attr;
- }
- return 0;
-rem_attr:
- debugfs_remove_recursive(hard_iface->debug_dir);
- hard_iface->debug_dir = NULL;
-out:
- return -ENOMEM;
+ for (bat_debug = batadv_hardif_debuginfos; *bat_debug; ++bat_debug)
+ debugfs_create_file(((*bat_debug)->attr).name,
+ S_IFREG | ((*bat_debug)->attr).mode,
+ hard_iface->debug_dir, hard_iface->net_dev,
+ &(*bat_debug)->fops);
}
/**
@@ -379,15 +341,12 @@ void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface)
{
const char *name = hard_iface->net_dev->name;
struct dentry *dir;
- struct dentry *d;
dir = hard_iface->debug_dir;
if (!dir)
return;
- d = debugfs_rename(dir->d_parent, dir, dir->d_parent, name);
- if (!d)
- pr_err("Can't rename debugfs dir to %s\n", name);
+ debugfs_rename(dir->d_parent, dir, dir->d_parent, name);
}
/**
@@ -419,44 +378,29 @@ int batadv_debugfs_add_meshif(struct net_device *dev)
struct batadv_priv *bat_priv = netdev_priv(dev);
struct batadv_debuginfo **bat_debug;
struct net *net = dev_net(dev);
- struct dentry *file;
-
- if (!batadv_debugfs)
- goto out;
if (net != &init_net)
return 0;
bat_priv->debug_dir = debugfs_create_dir(dev->name, batadv_debugfs);
- if (!bat_priv->debug_dir)
- goto out;
- if (batadv_socket_setup(bat_priv) < 0)
- goto rem_attr;
+ batadv_socket_setup(bat_priv);
if (batadv_debug_log_setup(bat_priv) < 0)
goto rem_attr;
- for (bat_debug = batadv_mesh_debuginfos; *bat_debug; ++bat_debug) {
- file = debugfs_create_file(((*bat_debug)->attr).name,
- S_IFREG | ((*bat_debug)->attr).mode,
- bat_priv->debug_dir,
- dev, &(*bat_debug)->fops);
- if (!file) {
- batadv_err(dev, "Can't add debugfs file: %s/%s\n",
- dev->name, ((*bat_debug)->attr).name);
- goto rem_attr;
- }
- }
+ for (bat_debug = batadv_mesh_debuginfos; *bat_debug; ++bat_debug)
+ debugfs_create_file(((*bat_debug)->attr).name,
+ S_IFREG | ((*bat_debug)->attr).mode,
+ bat_priv->debug_dir, dev,
+ &(*bat_debug)->fops);
- if (batadv_nc_init_debugfs(bat_priv) < 0)
- goto rem_attr;
+ batadv_nc_init_debugfs(bat_priv);
return 0;
rem_attr:
debugfs_remove_recursive(bat_priv->debug_dir);
bat_priv->debug_dir = NULL;
-out:
return -ENOMEM;
}
@@ -469,15 +413,12 @@ void batadv_debugfs_rename_meshif(struct net_device *dev)
struct batadv_priv *bat_priv = netdev_priv(dev);
const char *name = dev->name;
struct dentry *dir;
- struct dentry *d;
dir = bat_priv->debug_dir;
if (!dir)
return;
- d = debugfs_rename(dir->d_parent, dir, dir->d_parent, name);
- if (!d)
- pr_err("Can't rename debugfs dir to %s\n", name);
+ debugfs_rename(dir->d_parent, dir, dir->d_parent, name);
}
/**
diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h
index ed3343195466..1c5afd301ce9 100644
--- a/net/batman-adv/debugfs.h
+++ b/net/batman-adv/debugfs.h
@@ -22,7 +22,7 @@ void batadv_debugfs_destroy(void);
int batadv_debugfs_add_meshif(struct net_device *dev);
void batadv_debugfs_rename_meshif(struct net_device *dev);
void batadv_debugfs_del_meshif(struct net_device *dev);
-int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface);
+void batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface);
void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface);
void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface);
@@ -54,9 +54,8 @@ static inline void batadv_debugfs_del_meshif(struct net_device *dev)
}
static inline
-int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface)
+void batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface)
{
- return 0;
}
static inline
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 899487641bca..b5465e6e380d 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -921,9 +921,7 @@ batadv_hardif_add_interface(struct net_device *net_dev)
hard_iface->soft_iface = NULL;
hard_iface->if_status = BATADV_IF_NOT_IN_USE;
- ret = batadv_debugfs_add_hardif(hard_iface);
- if (ret)
- goto free_sysfs;
+ batadv_debugfs_add_hardif(hard_iface);
INIT_LIST_HEAD(&hard_iface->list);
INIT_HLIST_HEAD(&hard_iface->neigh_list);
@@ -945,8 +943,6 @@ batadv_hardif_add_interface(struct net_device *net_dev)
return hard_iface;
-free_sysfs:
- batadv_sysfs_del_hardif(&hard_iface->hardif_obj);
free_if:
kfree(hard_iface);
release_dev:
diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c
index 0a91c8661357..0a70b66e8770 100644
--- a/net/batman-adv/icmp_socket.c
+++ b/net/batman-adv/icmp_socket.c
@@ -314,25 +314,11 @@ static const struct file_operations batadv_fops = {
/**
* batadv_socket_setup() - Create debugfs "socket" file
* @bat_priv: the bat priv with all the soft interface information
- *
- * Return: 0 on success or negative error number in case of failure
*/
-int batadv_socket_setup(struct batadv_priv *bat_priv)
+void batadv_socket_setup(struct batadv_priv *bat_priv)
{
- struct dentry *d;
-
- if (!bat_priv->debug_dir)
- goto err;
-
- d = debugfs_create_file(BATADV_ICMP_SOCKET, 0600, bat_priv->debug_dir,
- bat_priv, &batadv_fops);
- if (!d)
- goto err;
-
- return 0;
-
-err:
- return -ENOMEM;
+ debugfs_create_file(BATADV_ICMP_SOCKET, 0600, bat_priv->debug_dir,
+ bat_priv, &batadv_fops);
}
/**
diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h
index 1fc0b0de290e..27fafff586df 100644
--- a/net/batman-adv/icmp_socket.h
+++ b/net/batman-adv/icmp_socket.h
@@ -14,7 +14,7 @@
#define BATADV_ICMP_SOCKET "socket"
-int batadv_socket_setup(struct batadv_priv *bat_priv);
+void batadv_socket_setup(struct batadv_priv *bat_priv);
#ifdef CONFIG_BATMAN_ADV_DEBUGFS
diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c
index f79ebd5b46e9..11941cf1adcc 100644
--- a/net/batman-adv/log.c
+++ b/net/batman-adv/log.c
@@ -190,27 +190,16 @@ static const struct file_operations batadv_log_fops = {
*/
int batadv_debug_log_setup(struct batadv_priv *bat_priv)
{
- struct dentry *d;
-
- if (!bat_priv->debug_dir)
- goto err;
-
bat_priv->debug_log = kzalloc(sizeof(*bat_priv->debug_log), GFP_ATOMIC);
if (!bat_priv->debug_log)
- goto err;
+ return -ENOMEM;
spin_lock_init(&bat_priv->debug_log->lock);
init_waitqueue_head(&bat_priv->debug_log->queue_wait);
- d = debugfs_create_file("log", 0400, bat_priv->debug_dir, bat_priv,
- &batadv_log_fops);
- if (!d)
- goto err;
-
+ debugfs_create_file("log", 0400, bat_priv->debug_dir, bat_priv,
+ &batadv_log_fops);
return 0;
-
-err:
- return -ENOMEM;
}
/**
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index c5e7906045f3..580609389f0f 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -1951,34 +1951,19 @@ int batadv_nc_nodes_seq_print_text(struct seq_file *seq, void *offset)
/**
* batadv_nc_init_debugfs() - create nc folder and related files in debugfs
* @bat_priv: the bat priv with all the soft interface information
- *
- * Return: 0 on success or negative error number in case of failure
*/
-int batadv_nc_init_debugfs(struct batadv_priv *bat_priv)
+void batadv_nc_init_debugfs(struct batadv_priv *bat_priv)
{
- struct dentry *nc_dir, *file;
+ struct dentry *nc_dir;
nc_dir = debugfs_create_dir("nc", bat_priv->debug_dir);
- if (!nc_dir)
- goto out;
- file = debugfs_create_u8("min_tq", 0644, nc_dir, &bat_priv->nc.min_tq);
- if (!file)
- goto out;
+ debugfs_create_u8("min_tq", 0644, nc_dir, &bat_priv->nc.min_tq);
- file = debugfs_create_u32("max_fwd_delay", 0644, nc_dir,
- &bat_priv->nc.max_fwd_delay);
- if (!file)
- goto out;
+ debugfs_create_u32("max_fwd_delay", 0644, nc_dir,
+ &bat_priv->nc.max_fwd_delay);
- file = debugfs_create_u32("max_buffer_time", 0644, nc_dir,
- &bat_priv->nc.max_buffer_time);
- if (!file)
- goto out;
-
- return 0;
-
-out:
- return -ENOMEM;
+ debugfs_create_u32("max_buffer_time", 0644, nc_dir,
+ &bat_priv->nc.max_buffer_time);
}
#endif
diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h
index 4801d0891cc8..753fa49723cf 100644
--- a/net/batman-adv/network-coding.h
+++ b/net/batman-adv/network-coding.h
@@ -39,7 +39,7 @@ void batadv_nc_skb_store_for_decoding(struct batadv_priv *bat_priv,
void batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv,
struct sk_buff *skb);
int batadv_nc_nodes_seq_print_text(struct seq_file *seq, void *offset);
-int batadv_nc_init_debugfs(struct batadv_priv *bat_priv);
+void batadv_nc_init_debugfs(struct batadv_priv *bat_priv);
#else /* ifdef CONFIG_BATMAN_ADV_NC */
@@ -110,9 +110,8 @@ static inline int batadv_nc_nodes_seq_print_text(struct seq_file *seq,
return 0;
}
-static inline int batadv_nc_init_debugfs(struct batadv_priv *bat_priv)
+static inline void batadv_nc_init_debugfs(struct batadv_priv *bat_priv)
{
- return 0;
}
#endif /* ifdef CONFIG_BATMAN_ADV_NC */
--
2.11.0
^ permalink raw reply related
* [PATCH 10/10] batman-adv: mcast: apply optimizations for routable packets, too
From: Simon Wunderlich @ 2019-06-28 13:56 UTC (permalink / raw)
To: davem
Cc: netdev, b.a.t.m.a.n, Linus Lüssing, Sven Eckelmann,
Simon Wunderlich
In-Reply-To: <20190628135604.11581-1-sw@simonwunderlich.de>
From: Linus Lüssing <linus.luessing@c0d3.blue>
Now that we not only track the presence of multicast listeners but also
multicast routers we can safely apply group-aware multicast-to-unicast
forwarding to packets with a destination address of scope greater than
link-local as well.
Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
net/batman-adv/multicast.c | 259 +++++++++++++++++++++++++++++++++++++++++----
1 file changed, 241 insertions(+), 18 deletions(-)
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index 80d5f3c892cb..67d7f83009ae 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -980,6 +980,7 @@ static bool batadv_mcast_is_report_ipv4(struct sk_buff *skb)
* @bat_priv: the bat priv with all the soft interface information
* @skb: the IPv4 packet to check
* @is_unsnoopable: stores whether the destination is snoopable
+ * @is_routable: stores whether the destination is routable
*
* Checks whether the given IPv4 packet has the potential to be forwarded with a
* mode more optimal than classic flooding.
@@ -989,7 +990,8 @@ static bool batadv_mcast_is_report_ipv4(struct sk_buff *skb)
*/
static int batadv_mcast_forw_mode_check_ipv4(struct batadv_priv *bat_priv,
struct sk_buff *skb,
- bool *is_unsnoopable)
+ bool *is_unsnoopable,
+ int *is_routable)
{
struct iphdr *iphdr;
@@ -1002,16 +1004,13 @@ static int batadv_mcast_forw_mode_check_ipv4(struct batadv_priv *bat_priv,
iphdr = ip_hdr(skb);
- /* TODO: Implement Multicast Router Discovery (RFC4286),
- * then allow scope > link local, too
- */
- if (!ipv4_is_local_multicast(iphdr->daddr))
- return -EINVAL;
-
/* link-local multicast listeners behind a bridge are
* not snoopable (see RFC4541, section 2.1.2.2)
*/
- *is_unsnoopable = true;
+ if (ipv4_is_local_multicast(iphdr->daddr))
+ *is_unsnoopable = true;
+ else
+ *is_routable = ETH_P_IP;
return 0;
}
@@ -1046,6 +1045,7 @@ static bool batadv_mcast_is_report_ipv6(struct sk_buff *skb)
* @bat_priv: the bat priv with all the soft interface information
* @skb: the IPv6 packet to check
* @is_unsnoopable: stores whether the destination is snoopable
+ * @is_routable: stores whether the destination is routable
*
* Checks whether the given IPv6 packet has the potential to be forwarded with a
* mode more optimal than classic flooding.
@@ -1054,7 +1054,8 @@ static bool batadv_mcast_is_report_ipv6(struct sk_buff *skb)
*/
static int batadv_mcast_forw_mode_check_ipv6(struct batadv_priv *bat_priv,
struct sk_buff *skb,
- bool *is_unsnoopable)
+ bool *is_unsnoopable,
+ int *is_routable)
{
struct ipv6hdr *ip6hdr;
@@ -1067,10 +1068,7 @@ static int batadv_mcast_forw_mode_check_ipv6(struct batadv_priv *bat_priv,
ip6hdr = ipv6_hdr(skb);
- /* TODO: Implement Multicast Router Discovery (RFC4286),
- * then allow scope > link local, too
- */
- if (IPV6_ADDR_MC_SCOPE(&ip6hdr->daddr) != IPV6_ADDR_SCOPE_LINKLOCAL)
+ if (IPV6_ADDR_MC_SCOPE(&ip6hdr->daddr) < IPV6_ADDR_SCOPE_LINKLOCAL)
return -EINVAL;
/* link-local-all-nodes multicast listeners behind a bridge are
@@ -1078,6 +1076,8 @@ static int batadv_mcast_forw_mode_check_ipv6(struct batadv_priv *bat_priv,
*/
if (ipv6_addr_is_ll_all_nodes(&ip6hdr->daddr))
*is_unsnoopable = true;
+ else if (IPV6_ADDR_MC_SCOPE(&ip6hdr->daddr) > IPV6_ADDR_SCOPE_LINKLOCAL)
+ *is_routable = ETH_P_IPV6;
return 0;
}
@@ -1087,6 +1087,7 @@ static int batadv_mcast_forw_mode_check_ipv6(struct batadv_priv *bat_priv,
* @bat_priv: the bat priv with all the soft interface information
* @skb: the multicast frame to check
* @is_unsnoopable: stores whether the destination is snoopable
+ * @is_routable: stores whether the destination is routable
*
* Checks whether the given multicast ethernet frame has the potential to be
* forwarded with a mode more optimal than classic flooding.
@@ -1095,7 +1096,8 @@ static int batadv_mcast_forw_mode_check_ipv6(struct batadv_priv *bat_priv,
*/
static int batadv_mcast_forw_mode_check(struct batadv_priv *bat_priv,
struct sk_buff *skb,
- bool *is_unsnoopable)
+ bool *is_unsnoopable,
+ int *is_routable)
{
struct ethhdr *ethhdr = eth_hdr(skb);
@@ -1105,13 +1107,15 @@ static int batadv_mcast_forw_mode_check(struct batadv_priv *bat_priv,
switch (ntohs(ethhdr->h_proto)) {
case ETH_P_IP:
return batadv_mcast_forw_mode_check_ipv4(bat_priv, skb,
- is_unsnoopable);
+ is_unsnoopable,
+ is_routable);
case ETH_P_IPV6:
if (!IS_ENABLED(CONFIG_IPV6))
return -EINVAL;
return batadv_mcast_forw_mode_check_ipv6(bat_priv, skb,
- is_unsnoopable);
+ is_unsnoopable,
+ is_routable);
default:
return -EINVAL;
}
@@ -1142,6 +1146,29 @@ static int batadv_mcast_forw_want_all_ip_count(struct batadv_priv *bat_priv,
}
/**
+ * batadv_mcast_forw_rtr_count() - count nodes with a multicast router
+ * @bat_priv: the bat priv with all the soft interface information
+ * @protocol: the ethernet protocol type to count multicast routers for
+ *
+ * Return: the number of nodes which want all routable IPv4 multicast traffic
+ * if the protocol is ETH_P_IP or the number of nodes which want all routable
+ * IPv6 traffic if the protocol is ETH_P_IPV6. Otherwise returns 0.
+ */
+
+static int batadv_mcast_forw_rtr_count(struct batadv_priv *bat_priv,
+ int protocol)
+{
+ switch (protocol) {
+ case ETH_P_IP:
+ return atomic_read(&bat_priv->mcast.num_want_all_rtr4);
+ case ETH_P_IPV6:
+ return atomic_read(&bat_priv->mcast.num_want_all_rtr6);
+ default:
+ return 0;
+ }
+}
+
+/**
* batadv_mcast_forw_tt_node_get() - get a multicast tt node
* @bat_priv: the bat priv with all the soft interface information
* @ethhdr: the ether header containing the multicast destination
@@ -1263,6 +1290,84 @@ batadv_mcast_forw_unsnoop_node_get(struct batadv_priv *bat_priv)
}
/**
+ * batadv_mcast_forw_rtr4_node_get() - get a node with an ipv4 mcast router flag
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Return: an orig_node which has the BATADV_MCAST_WANT_NO_RTR4 flag unset and
+ * increases its refcount.
+ */
+static struct batadv_orig_node *
+batadv_mcast_forw_rtr4_node_get(struct batadv_priv *bat_priv)
+{
+ struct batadv_orig_node *tmp_orig_node, *orig_node = NULL;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(tmp_orig_node,
+ &bat_priv->mcast.want_all_rtr4_list,
+ mcast_want_all_rtr4_node) {
+ if (!kref_get_unless_zero(&tmp_orig_node->refcount))
+ continue;
+
+ orig_node = tmp_orig_node;
+ break;
+ }
+ rcu_read_unlock();
+
+ return orig_node;
+}
+
+/**
+ * batadv_mcast_forw_rtr6_node_get() - get a node with an ipv6 mcast router flag
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Return: an orig_node which has the BATADV_MCAST_WANT_NO_RTR6 flag unset
+ * and increases its refcount.
+ */
+static struct batadv_orig_node *
+batadv_mcast_forw_rtr6_node_get(struct batadv_priv *bat_priv)
+{
+ struct batadv_orig_node *tmp_orig_node, *orig_node = NULL;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(tmp_orig_node,
+ &bat_priv->mcast.want_all_rtr6_list,
+ mcast_want_all_rtr6_node) {
+ if (!kref_get_unless_zero(&tmp_orig_node->refcount))
+ continue;
+
+ orig_node = tmp_orig_node;
+ break;
+ }
+ rcu_read_unlock();
+
+ return orig_node;
+}
+
+/**
+ * batadv_mcast_forw_rtr_node_get() - get a node with an ipv4/ipv6 router flag
+ * @bat_priv: the bat priv with all the soft interface information
+ * @ethhdr: an ethernet header to determine the protocol family from
+ *
+ * Return: an orig_node which has no BATADV_MCAST_WANT_NO_RTR4 or
+ * BATADV_MCAST_WANT_NO_RTR6 flag, depending on the provided ethhdr, set and
+ * increases its refcount.
+ */
+static struct batadv_orig_node *
+batadv_mcast_forw_rtr_node_get(struct batadv_priv *bat_priv,
+ struct ethhdr *ethhdr)
+{
+ switch (ntohs(ethhdr->h_proto)) {
+ case ETH_P_IP:
+ return batadv_mcast_forw_rtr4_node_get(bat_priv);
+ case ETH_P_IPV6:
+ return batadv_mcast_forw_rtr6_node_get(bat_priv);
+ default:
+ /* we shouldn't be here... */
+ return NULL;
+ }
+}
+
+/**
* batadv_mcast_forw_mode() - check on how to forward a multicast packet
* @bat_priv: the bat priv with all the soft interface information
* @skb: The multicast packet to check
@@ -1280,8 +1385,11 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
bool is_unsnoopable = false;
unsigned int mcast_fanout;
struct ethhdr *ethhdr;
+ int is_routable = 0;
+ int rtr_count = 0;
- ret = batadv_mcast_forw_mode_check(bat_priv, skb, &is_unsnoopable);
+ ret = batadv_mcast_forw_mode_check(bat_priv, skb, &is_unsnoopable,
+ &is_routable);
if (ret == -ENOMEM)
return BATADV_FORW_NONE;
else if (ret < 0)
@@ -1294,8 +1402,9 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
ip_count = batadv_mcast_forw_want_all_ip_count(bat_priv, ethhdr);
unsnoop_count = !is_unsnoopable ? 0 :
atomic_read(&bat_priv->mcast.num_want_all_unsnoopables);
+ rtr_count = batadv_mcast_forw_rtr_count(bat_priv, is_routable);
- total_count = tt_count + ip_count + unsnoop_count;
+ total_count = tt_count + ip_count + unsnoop_count + rtr_count;
switch (total_count) {
case 1:
@@ -1305,6 +1414,9 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
*orig = batadv_mcast_forw_ip_node_get(bat_priv, ethhdr);
else if (unsnoop_count)
*orig = batadv_mcast_forw_unsnoop_node_get(bat_priv);
+ else if (rtr_count)
+ *orig = batadv_mcast_forw_rtr_node_get(bat_priv,
+ ethhdr);
if (*orig)
return BATADV_FORW_SINGLE;
@@ -1476,6 +1588,111 @@ batadv_mcast_forw_want_all(struct batadv_priv *bat_priv,
}
/**
+ * batadv_mcast_forw_want_all_rtr4() - forward to nodes with want-all-rtr4
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the multicast packet to transmit
+ * @vid: the vlan identifier
+ *
+ * Sends copies of a frame with multicast destination to any node with a
+ * BATADV_MCAST_WANT_NO_RTR4 flag unset. A transmission is performed via a
+ * batman-adv unicast packet for each such destination node.
+ *
+ * Return: NET_XMIT_DROP on memory allocation failure, NET_XMIT_SUCCESS
+ * otherwise.
+ */
+static int
+batadv_mcast_forw_want_all_rtr4(struct batadv_priv *bat_priv,
+ struct sk_buff *skb, unsigned short vid)
+{
+ struct batadv_orig_node *orig_node;
+ int ret = NET_XMIT_SUCCESS;
+ struct sk_buff *newskb;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(orig_node,
+ &bat_priv->mcast.want_all_rtr4_list,
+ mcast_want_all_rtr4_node) {
+ newskb = skb_copy(skb, GFP_ATOMIC);
+ if (!newskb) {
+ ret = NET_XMIT_DROP;
+ break;
+ }
+
+ batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0,
+ orig_node, vid);
+ }
+ rcu_read_unlock();
+ return ret;
+}
+
+/**
+ * batadv_mcast_forw_want_all_rtr6() - forward to nodes with want-all-rtr6
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: The multicast packet to transmit
+ * @vid: the vlan identifier
+ *
+ * Sends copies of a frame with multicast destination to any node with a
+ * BATADV_MCAST_WANT_NO_RTR6 flag unset. A transmission is performed via a
+ * batman-adv unicast packet for each such destination node.
+ *
+ * Return: NET_XMIT_DROP on memory allocation failure, NET_XMIT_SUCCESS
+ * otherwise.
+ */
+static int
+batadv_mcast_forw_want_all_rtr6(struct batadv_priv *bat_priv,
+ struct sk_buff *skb, unsigned short vid)
+{
+ struct batadv_orig_node *orig_node;
+ int ret = NET_XMIT_SUCCESS;
+ struct sk_buff *newskb;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(orig_node,
+ &bat_priv->mcast.want_all_rtr6_list,
+ mcast_want_all_rtr6_node) {
+ newskb = skb_copy(skb, GFP_ATOMIC);
+ if (!newskb) {
+ ret = NET_XMIT_DROP;
+ break;
+ }
+
+ batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0,
+ orig_node, vid);
+ }
+ rcu_read_unlock();
+ return ret;
+}
+
+/**
+ * batadv_mcast_forw_want_rtr() - forward packet to nodes in a want-all-rtr list
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the multicast packet to transmit
+ * @vid: the vlan identifier
+ *
+ * Sends copies of a frame with multicast destination to any node with a
+ * BATADV_MCAST_WANT_NO_RTR4 or BATADV_MCAST_WANT_NO_RTR6 flag unset. A
+ * transmission is performed via a batman-adv unicast packet for each such
+ * destination node.
+ *
+ * Return: NET_XMIT_DROP on memory allocation failure or if the protocol family
+ * is neither IPv4 nor IPv6. NET_XMIT_SUCCESS otherwise.
+ */
+static int
+batadv_mcast_forw_want_rtr(struct batadv_priv *bat_priv,
+ struct sk_buff *skb, unsigned short vid)
+{
+ switch (ntohs(eth_hdr(skb)->h_proto)) {
+ case ETH_P_IP:
+ return batadv_mcast_forw_want_all_rtr4(bat_priv, skb, vid);
+ case ETH_P_IPV6:
+ return batadv_mcast_forw_want_all_rtr6(bat_priv, skb, vid);
+ default:
+ /* we shouldn't be here... */
+ return NET_XMIT_DROP;
+ }
+}
+
+/**
* batadv_mcast_forw_send() - send packet to any detected multicast recpient
* @bat_priv: the bat priv with all the soft interface information
* @skb: the multicast packet to transmit
@@ -1508,6 +1725,12 @@ int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb,
return ret;
}
+ ret = batadv_mcast_forw_want_rtr(bat_priv, skb, vid);
+ if (ret != NET_XMIT_SUCCESS) {
+ kfree_skb(skb);
+ return ret;
+ }
+
consume_skb(skb);
return ret;
}
--
2.11.0
^ permalink raw reply related
* [PATCH 05/10] batman-adv: mcast: shorten multicast tt/tvlv worker spinlock section
From: Simon Wunderlich @ 2019-06-28 13:55 UTC (permalink / raw)
To: davem
Cc: netdev, b.a.t.m.a.n, Linus Lüssing, Sven Eckelmann,
Simon Wunderlich
In-Reply-To: <20190628135604.11581-1-sw@simonwunderlich.de>
From: Linus Lüssing <linus.luessing@c0d3.blue>
It is not necessary to hold the mla_lock spinlock during the whole
multicast tt/tvlv worker callback. Just holding it during the checks and
updates of the bat_priv stored multicast flags and mla_list is enough.
Therefore this patch splits batadv_mcast_mla_tvlv_update() in two:
batadv_mcast_mla_flags_get() at the beginning of the worker to gather
and calculate the new multicast flags, which does not need any locking
as it neither reads from nor writes to bat_priv->mcast.
And batadv_mcast_mla_flags_update() at the end of the worker which
commits the newly calculated flags and lists to bat_priv->mcast and
therefore needs the lock.
Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
net/batman-adv/multicast.c | 272 +++++++++++++++++++++-------------------
net/batman-adv/soft-interface.c | 5 -
net/batman-adv/types.h | 38 +++---
3 files changed, 164 insertions(+), 151 deletions(-)
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index ec54e236e345..af0e2ce8d38e 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -72,6 +72,80 @@ static void batadv_mcast_start_timer(struct batadv_priv *bat_priv)
}
/**
+ * batadv_mcast_has_bridge() - check whether the soft-iface is bridged
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Checks whether there is a bridge on top of our soft interface.
+ *
+ * Return: true if there is a bridge, false otherwise.
+ */
+static bool batadv_mcast_has_bridge(struct batadv_priv *bat_priv)
+{
+ struct net_device *upper = bat_priv->soft_iface;
+
+ rcu_read_lock();
+ do {
+ upper = netdev_master_upper_dev_get_rcu(upper);
+ } while (upper && !(upper->priv_flags & IFF_EBRIDGE));
+ rcu_read_unlock();
+
+ return upper;
+}
+
+/**
+ * batadv_mcast_mla_flags_get() - get the new multicast flags
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Return: A set of flags for the current/next TVLV, querier and
+ * bridge state.
+ */
+static struct batadv_mcast_mla_flags
+batadv_mcast_mla_flags_get(struct batadv_priv *bat_priv)
+{
+ struct net_device *dev = bat_priv->soft_iface;
+ struct batadv_mcast_querier_state *qr4, *qr6;
+ struct batadv_mcast_mla_flags mla_flags;
+
+ memset(&mla_flags, 0, sizeof(mla_flags));
+ mla_flags.enabled = 1;
+
+ if (!batadv_mcast_has_bridge(bat_priv))
+ return mla_flags;
+
+ mla_flags.bridged = 1;
+ qr4 = &mla_flags.querier_ipv4;
+ qr6 = &mla_flags.querier_ipv6;
+
+ if (!IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING))
+ pr_warn_once("No bridge IGMP snooping compiled - multicast optimizations disabled\n");
+
+ qr4->exists = br_multicast_has_querier_anywhere(dev, ETH_P_IP);
+ qr4->shadowing = br_multicast_has_querier_adjacent(dev, ETH_P_IP);
+
+ qr6->exists = br_multicast_has_querier_anywhere(dev, ETH_P_IPV6);
+ qr6->shadowing = br_multicast_has_querier_adjacent(dev, ETH_P_IPV6);
+
+ mla_flags.tvlv_flags |= BATADV_MCAST_WANT_ALL_UNSNOOPABLES;
+
+ /* 1) If no querier exists at all, then multicast listeners on
+ * our local TT clients behind the bridge will keep silent.
+ * 2) If the selected querier is on one of our local TT clients,
+ * behind the bridge, then this querier might shadow multicast
+ * listeners on our local TT clients, behind this bridge.
+ *
+ * In both cases, we will signalize other batman nodes that
+ * we need all multicast traffic of the according protocol.
+ */
+ if (!qr4->exists || qr4->shadowing)
+ mla_flags.tvlv_flags |= BATADV_MCAST_WANT_ALL_IPV4;
+
+ if (!qr6->exists || qr6->shadowing)
+ mla_flags.tvlv_flags |= BATADV_MCAST_WANT_ALL_IPV6;
+
+ return mla_flags;
+}
+
+/**
* batadv_mcast_get_bridge() - get the bridge on top of the softif if it exists
* @soft_iface: netdev struct of the mesh interface
*
@@ -127,9 +201,9 @@ static bool batadv_mcast_addr_is_ipv6(const u8 *addr)
/**
* batadv_mcast_mla_softif_get() - get softif multicast listeners
- * @bat_priv: the bat priv with all the soft interface information
* @dev: the device to collect multicast addresses from
* @mcast_list: a list to put found addresses into
+ * @flags: flags indicating the new multicast state
*
* Collects multicast addresses of multicast listeners residing
* on this kernel on the given soft interface, dev, in
@@ -144,12 +218,13 @@ static bool batadv_mcast_addr_is_ipv6(const u8 *addr)
* Return: -ENOMEM on memory allocation error or the number of
* items added to the mcast_list otherwise.
*/
-static int batadv_mcast_mla_softif_get(struct batadv_priv *bat_priv,
- struct net_device *dev,
- struct hlist_head *mcast_list)
+static int
+batadv_mcast_mla_softif_get(struct net_device *dev,
+ struct hlist_head *mcast_list,
+ struct batadv_mcast_mla_flags *flags)
{
- bool all_ipv4 = bat_priv->mcast.flags & BATADV_MCAST_WANT_ALL_IPV4;
- bool all_ipv6 = bat_priv->mcast.flags & BATADV_MCAST_WANT_ALL_IPV6;
+ bool all_ipv4 = flags->tvlv_flags & BATADV_MCAST_WANT_ALL_IPV4;
+ bool all_ipv6 = flags->tvlv_flags & BATADV_MCAST_WANT_ALL_IPV6;
struct net_device *bridge = batadv_mcast_get_bridge(dev);
struct netdev_hw_addr *mc_list_entry;
struct batadv_hw_addr *new;
@@ -227,9 +302,9 @@ static void batadv_mcast_mla_br_addr_cpy(char *dst, const struct br_ip *src)
/**
* batadv_mcast_mla_bridge_get() - get bridged-in multicast listeners
- * @bat_priv: the bat priv with all the soft interface information
* @dev: a bridge slave whose bridge to collect multicast addresses from
* @mcast_list: a list to put found addresses into
+ * @flags: flags indicating the new multicast state
*
* Collects multicast addresses of multicast listeners residing
* on foreign, non-mesh devices which we gave access to our mesh via
@@ -239,13 +314,13 @@ static void batadv_mcast_mla_br_addr_cpy(char *dst, const struct br_ip *src)
* Return: -ENOMEM on memory allocation error or the number of
* items added to the mcast_list otherwise.
*/
-static int batadv_mcast_mla_bridge_get(struct batadv_priv *bat_priv,
- struct net_device *dev,
- struct hlist_head *mcast_list)
+static int batadv_mcast_mla_bridge_get(struct net_device *dev,
+ struct hlist_head *mcast_list,
+ struct batadv_mcast_mla_flags *flags)
{
struct list_head bridge_mcast_list = LIST_HEAD_INIT(bridge_mcast_list);
- bool all_ipv4 = bat_priv->mcast.flags & BATADV_MCAST_WANT_ALL_IPV4;
- bool all_ipv6 = bat_priv->mcast.flags & BATADV_MCAST_WANT_ALL_IPV6;
+ bool all_ipv4 = flags->tvlv_flags & BATADV_MCAST_WANT_ALL_IPV4;
+ bool all_ipv6 = flags->tvlv_flags & BATADV_MCAST_WANT_ALL_IPV6;
struct br_ip_list *br_ip_entry, *tmp;
struct batadv_hw_addr *new;
u8 mcast_addr[ETH_ALEN];
@@ -370,27 +445,6 @@ static void batadv_mcast_mla_tt_add(struct batadv_priv *bat_priv,
}
/**
- * batadv_mcast_has_bridge() - check whether the soft-iface is bridged
- * @bat_priv: the bat priv with all the soft interface information
- *
- * Checks whether there is a bridge on top of our soft interface.
- *
- * Return: true if there is a bridge, false otherwise.
- */
-static bool batadv_mcast_has_bridge(struct batadv_priv *bat_priv)
-{
- struct net_device *upper = bat_priv->soft_iface;
-
- rcu_read_lock();
- do {
- upper = netdev_master_upper_dev_get_rcu(upper);
- } while (upper && !(upper->priv_flags & IFF_EBRIDGE));
- rcu_read_unlock();
-
- return upper;
-}
-
-/**
* batadv_mcast_querier_log() - debug output regarding the querier status on
* link
* @bat_priv: the bat priv with all the soft interface information
@@ -424,7 +478,7 @@ batadv_mcast_querier_log(struct batadv_priv *bat_priv, char *str_proto,
batadv_info(bat_priv->soft_iface,
"%s Querier disappeared - multicast optimizations disabled\n",
str_proto);
- else if (!bat_priv->mcast.bridged && !new_state->exists)
+ else if (!bat_priv->mcast.mla_flags.bridged && !new_state->exists)
batadv_info(bat_priv->soft_iface,
"No %s Querier present - multicast optimizations disabled\n",
str_proto);
@@ -446,9 +500,7 @@ batadv_mcast_querier_log(struct batadv_priv *bat_priv, char *str_proto,
* batadv_mcast_bridge_log() - debug output for topology changes in bridged
* setups
* @bat_priv: the bat priv with all the soft interface information
- * @bridged: a flag about whether the soft interface is currently bridged or not
- * @querier_ipv4: (maybe) new status of a potential, selected IGMP querier
- * @querier_ipv6: (maybe) new status of a potential, selected MLD querier
+ * @new_flags: flags indicating the new multicast state
*
* If no bridges are ever used on this node, then this function does nothing.
*
@@ -461,38 +513,40 @@ batadv_mcast_querier_log(struct batadv_priv *bat_priv, char *str_proto,
* multicast flags this node is going to set.
*/
static void
-batadv_mcast_bridge_log(struct batadv_priv *bat_priv, bool bridged,
- struct batadv_mcast_querier_state *querier_ipv4,
- struct batadv_mcast_querier_state *querier_ipv6)
+batadv_mcast_bridge_log(struct batadv_priv *bat_priv,
+ struct batadv_mcast_mla_flags *new_flags)
{
- if (!bat_priv->mcast.bridged && bridged)
+ struct batadv_mcast_mla_flags *old_flags = &bat_priv->mcast.mla_flags;
+
+ if (!old_flags->bridged && new_flags->bridged)
batadv_dbg(BATADV_DBG_MCAST, bat_priv,
"Bridge added: Setting Unsnoopables(U)-flag\n");
- else if (bat_priv->mcast.bridged && !bridged)
+ else if (old_flags->bridged && !new_flags->bridged)
batadv_dbg(BATADV_DBG_MCAST, bat_priv,
"Bridge removed: Unsetting Unsnoopables(U)-flag\n");
- if (bridged) {
+ if (new_flags->bridged) {
batadv_mcast_querier_log(bat_priv, "IGMP",
- &bat_priv->mcast.querier_ipv4,
- querier_ipv4);
+ &old_flags->querier_ipv4,
+ &new_flags->querier_ipv4);
batadv_mcast_querier_log(bat_priv, "MLD",
- &bat_priv->mcast.querier_ipv6,
- querier_ipv6);
+ &old_flags->querier_ipv6,
+ &new_flags->querier_ipv6);
}
}
/**
* batadv_mcast_flags_logs() - output debug information about mcast flag changes
* @bat_priv: the bat priv with all the soft interface information
- * @flags: flags indicating the new multicast state
+ * @flags: TVLV flags indicating the new multicast state
*
- * Whenever the multicast flags this nodes announces changes (@mcast_flags vs.
- * bat_priv->mcast.flags), this notifies userspace via the 'mcast' log level.
+ * Whenever the multicast TVLV flags this nodes announces change this notifies
+ * userspace via the 'mcast' log level.
*/
static void batadv_mcast_flags_log(struct batadv_priv *bat_priv, u8 flags)
{
- u8 old_flags = bat_priv->mcast.flags;
+ bool old_enabled = bat_priv->mcast.mla_flags.enabled;
+ u8 old_flags = bat_priv->mcast.mla_flags.tvlv_flags;
char str_old_flags[] = "[...]";
sprintf(str_old_flags, "[%c%c%c]",
@@ -502,85 +556,39 @@ static void batadv_mcast_flags_log(struct batadv_priv *bat_priv, u8 flags)
batadv_dbg(BATADV_DBG_MCAST, bat_priv,
"Changing multicast flags from '%s' to '[%c%c%c]'\n",
- bat_priv->mcast.enabled ? str_old_flags : "<undefined>",
+ old_enabled ? str_old_flags : "<undefined>",
(flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.',
(flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.',
(flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.');
}
/**
- * batadv_mcast_mla_tvlv_update() - update multicast tvlv
+ * batadv_mcast_mla_flags_update() - update multicast flags
* @bat_priv: the bat priv with all the soft interface information
+ * @flags: flags indicating the new multicast state
*
* Updates the own multicast tvlv with our current multicast related settings,
* capabilities and inabilities.
- *
- * Return: false if we want all IPv4 && IPv6 multicast traffic and true
- * otherwise.
*/
-static bool batadv_mcast_mla_tvlv_update(struct batadv_priv *bat_priv)
+static void
+batadv_mcast_mla_flags_update(struct batadv_priv *bat_priv,
+ struct batadv_mcast_mla_flags *flags)
{
struct batadv_tvlv_mcast_data mcast_data;
- struct batadv_mcast_querier_state querier4 = {false, false};
- struct batadv_mcast_querier_state querier6 = {false, false};
- struct net_device *dev = bat_priv->soft_iface;
- bool bridged;
-
- mcast_data.flags = BATADV_NO_FLAGS;
- memset(mcast_data.reserved, 0, sizeof(mcast_data.reserved));
-
- bridged = batadv_mcast_has_bridge(bat_priv);
- if (!bridged)
- goto update;
-
- if (!IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING))
- pr_warn_once("No bridge IGMP snooping compiled - multicast optimizations disabled\n");
-
- querier4.exists = br_multicast_has_querier_anywhere(dev, ETH_P_IP);
- querier4.shadowing = br_multicast_has_querier_adjacent(dev, ETH_P_IP);
-
- querier6.exists = br_multicast_has_querier_anywhere(dev, ETH_P_IPV6);
- querier6.shadowing = br_multicast_has_querier_adjacent(dev, ETH_P_IPV6);
-
- mcast_data.flags |= BATADV_MCAST_WANT_ALL_UNSNOOPABLES;
-
- /* 1) If no querier exists at all, then multicast listeners on
- * our local TT clients behind the bridge will keep silent.
- * 2) If the selected querier is on one of our local TT clients,
- * behind the bridge, then this querier might shadow multicast
- * listeners on our local TT clients, behind this bridge.
- *
- * In both cases, we will signalize other batman nodes that
- * we need all multicast traffic of the according protocol.
- */
- if (!querier4.exists || querier4.shadowing)
- mcast_data.flags |= BATADV_MCAST_WANT_ALL_IPV4;
- if (!querier6.exists || querier6.shadowing)
- mcast_data.flags |= BATADV_MCAST_WANT_ALL_IPV6;
-
-update:
- batadv_mcast_bridge_log(bat_priv, bridged, &querier4, &querier6);
-
- bat_priv->mcast.querier_ipv4.exists = querier4.exists;
- bat_priv->mcast.querier_ipv4.shadowing = querier4.shadowing;
+ if (!memcmp(flags, &bat_priv->mcast.mla_flags, sizeof(*flags)))
+ return;
- bat_priv->mcast.querier_ipv6.exists = querier6.exists;
- bat_priv->mcast.querier_ipv6.shadowing = querier6.shadowing;
+ batadv_mcast_bridge_log(bat_priv, flags);
+ batadv_mcast_flags_log(bat_priv, flags->tvlv_flags);
- bat_priv->mcast.bridged = bridged;
+ mcast_data.flags = flags->tvlv_flags;
+ memset(mcast_data.reserved, 0, sizeof(mcast_data.reserved));
- if (!bat_priv->mcast.enabled ||
- mcast_data.flags != bat_priv->mcast.flags) {
- batadv_mcast_flags_log(bat_priv, mcast_data.flags);
- batadv_tvlv_container_register(bat_priv, BATADV_TVLV_MCAST, 2,
- &mcast_data, sizeof(mcast_data));
- bat_priv->mcast.flags = mcast_data.flags;
- bat_priv->mcast.enabled = true;
- }
+ batadv_tvlv_container_register(bat_priv, BATADV_TVLV_MCAST, 2,
+ &mcast_data, sizeof(mcast_data));
- return !(mcast_data.flags & BATADV_MCAST_WANT_ALL_IPV4 &&
- mcast_data.flags & BATADV_MCAST_WANT_ALL_IPV6);
+ bat_priv->mcast.mla_flags = *flags;
}
/**
@@ -599,22 +607,24 @@ static void __batadv_mcast_mla_update(struct batadv_priv *bat_priv)
{
struct net_device *soft_iface = bat_priv->soft_iface;
struct hlist_head mcast_list = HLIST_HEAD_INIT;
+ struct batadv_mcast_mla_flags flags;
int ret;
- if (!batadv_mcast_mla_tvlv_update(bat_priv))
- goto update;
+ flags = batadv_mcast_mla_flags_get(bat_priv);
- ret = batadv_mcast_mla_softif_get(bat_priv, soft_iface, &mcast_list);
+ ret = batadv_mcast_mla_softif_get(soft_iface, &mcast_list, &flags);
if (ret < 0)
goto out;
- ret = batadv_mcast_mla_bridge_get(bat_priv, soft_iface, &mcast_list);
+ ret = batadv_mcast_mla_bridge_get(soft_iface, &mcast_list, &flags);
if (ret < 0)
goto out;
-update:
+ spin_lock(&bat_priv->mcast.mla_lock);
batadv_mcast_mla_tt_retract(bat_priv, &mcast_list);
batadv_mcast_mla_tt_add(bat_priv, &mcast_list);
+ batadv_mcast_mla_flags_update(bat_priv, &flags);
+ spin_unlock(&bat_priv->mcast.mla_lock);
out:
batadv_mcast_mla_list_free(&mcast_list);
@@ -639,10 +649,7 @@ static void batadv_mcast_mla_update(struct work_struct *work)
priv_mcast = container_of(delayed_work, struct batadv_priv_mcast, work);
bat_priv = container_of(priv_mcast, struct batadv_priv, mcast);
- spin_lock(&bat_priv->mcast.mla_lock);
__batadv_mcast_mla_update(bat_priv);
- spin_unlock(&bat_priv->mcast.mla_lock);
-
batadv_mcast_start_timer(bat_priv);
}
@@ -1417,15 +1424,16 @@ void batadv_mcast_init(struct batadv_priv *bat_priv)
static void batadv_mcast_flags_print_header(struct batadv_priv *bat_priv,
struct seq_file *seq)
{
- u8 flags = bat_priv->mcast.flags;
+ struct batadv_mcast_mla_flags *mla_flags = &bat_priv->mcast.mla_flags;
char querier4, querier6, shadowing4, shadowing6;
- bool bridged = bat_priv->mcast.bridged;
+ bool bridged = mla_flags->bridged;
+ u8 flags = mla_flags->tvlv_flags;
if (bridged) {
- querier4 = bat_priv->mcast.querier_ipv4.exists ? '.' : '4';
- querier6 = bat_priv->mcast.querier_ipv6.exists ? '.' : '6';
- shadowing4 = bat_priv->mcast.querier_ipv4.shadowing ? '4' : '.';
- shadowing6 = bat_priv->mcast.querier_ipv6.shadowing ? '6' : '.';
+ querier4 = mla_flags->querier_ipv4.exists ? '.' : '4';
+ querier6 = mla_flags->querier_ipv6.exists ? '.' : '6';
+ shadowing4 = mla_flags->querier_ipv4.shadowing ? '4' : '.';
+ shadowing6 = mla_flags->querier_ipv6.shadowing ? '6' : '.';
} else {
querier4 = '?';
querier6 = '?';
@@ -1517,19 +1525,19 @@ int batadv_mcast_flags_seq_print_text(struct seq_file *seq, void *offset)
int batadv_mcast_mesh_info_put(struct sk_buff *msg,
struct batadv_priv *bat_priv)
{
- u32 flags = bat_priv->mcast.flags;
+ u32 flags = bat_priv->mcast.mla_flags.tvlv_flags;
u32 flags_priv = BATADV_NO_FLAGS;
- if (bat_priv->mcast.bridged) {
+ if (bat_priv->mcast.mla_flags.bridged) {
flags_priv |= BATADV_MCAST_FLAGS_BRIDGED;
- if (bat_priv->mcast.querier_ipv4.exists)
+ if (bat_priv->mcast.mla_flags.querier_ipv4.exists)
flags_priv |= BATADV_MCAST_FLAGS_QUERIER_IPV4_EXISTS;
- if (bat_priv->mcast.querier_ipv6.exists)
+ if (bat_priv->mcast.mla_flags.querier_ipv6.exists)
flags_priv |= BATADV_MCAST_FLAGS_QUERIER_IPV6_EXISTS;
- if (bat_priv->mcast.querier_ipv4.shadowing)
+ if (bat_priv->mcast.mla_flags.querier_ipv4.shadowing)
flags_priv |= BATADV_MCAST_FLAGS_QUERIER_IPV4_SHADOWING;
- if (bat_priv->mcast.querier_ipv6.shadowing)
+ if (bat_priv->mcast.mla_flags.querier_ipv6.shadowing)
flags_priv |= BATADV_MCAST_FLAGS_QUERIER_IPV6_SHADOWING;
}
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 499afbce44dc..c7a2e77ca1da 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -804,11 +804,6 @@ static int batadv_softif_init_late(struct net_device *dev)
atomic_set(&bat_priv->distributed_arp_table, 1);
#endif
#ifdef CONFIG_BATMAN_ADV_MCAST
- bat_priv->mcast.querier_ipv4.exists = false;
- bat_priv->mcast.querier_ipv4.shadowing = false;
- bat_priv->mcast.querier_ipv6.exists = false;
- bat_priv->mcast.querier_ipv6.shadowing = false;
- bat_priv->mcast.flags = BATADV_NO_FLAGS;
atomic_set(&bat_priv->multicast_mode, 1);
atomic_set(&bat_priv->multicast_fanout, 16);
atomic_set(&bat_priv->mcast.num_want_all_unsnoopables, 0);
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 581f93c0e974..72f65b3769d0 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -1171,6 +1171,26 @@ struct batadv_mcast_querier_state {
};
/**
+ * struct batadv_mcast_mla_flags - flags for the querier, bridge and tvlv state
+ */
+struct batadv_mcast_mla_flags {
+ /** @querier_ipv4: the current state of an IGMP querier in the mesh */
+ struct batadv_mcast_querier_state querier_ipv4;
+
+ /** @querier_ipv6: the current state of an MLD querier in the mesh */
+ struct batadv_mcast_querier_state querier_ipv6;
+
+ /** @enabled: whether the multicast tvlv is currently enabled */
+ unsigned char enabled:1;
+
+ /** @bridged: whether the soft interface has a bridge on top */
+ unsigned char bridged:1;
+
+ /** @tvlv_flags: the flags we have last sent in our mcast tvlv */
+ u8 tvlv_flags;
+};
+
+/**
* struct batadv_priv_mcast - per mesh interface mcast data
*/
struct batadv_priv_mcast {
@@ -1198,20 +1218,10 @@ struct batadv_priv_mcast {
*/
struct hlist_head want_all_ipv6_list;
- /** @querier_ipv4: the current state of an IGMP querier in the mesh */
- struct batadv_mcast_querier_state querier_ipv4;
-
- /** @querier_ipv6: the current state of an MLD querier in the mesh */
- struct batadv_mcast_querier_state querier_ipv6;
-
- /** @flags: the flags we have last sent in our mcast tvlv */
- u8 flags;
-
- /** @enabled: whether the multicast tvlv is currently enabled */
- unsigned char enabled:1;
-
- /** @bridged: whether the soft interface has a bridge on top */
- unsigned char bridged:1;
+ /**
+ * @mla_flags: flags for the querier, bridge and tvlv state
+ */
+ struct batadv_mcast_mla_flags mla_flags;
/**
* @mla_lock: a lock protecting mla_list and mla_flags
--
2.11.0
^ permalink raw reply related
* [PATCH 07/10] batman-adv: mcast: avoid redundant multicast TT entries with bridges
From: Simon Wunderlich @ 2019-06-28 13:56 UTC (permalink / raw)
To: davem
Cc: netdev, b.a.t.m.a.n, Linus Lüssing, Sven Eckelmann,
Simon Wunderlich
In-Reply-To: <20190628135604.11581-1-sw@simonwunderlich.de>
From: Linus Lüssing <linus.luessing@c0d3.blue>
When a bridge is added on top of bat0 we set the WANT_ALL_UNSNOOPABLES
flag. Which means we sign up for all traffic for ff02::1/128 and
224.0.0.0/24.
When the node itself had IPv6 enabled or joined a group in 224.0.0.0/24
itself then so far this would result in a multicast TT entry which is
redundant to the WANT_ALL_UNSNOOPABLES.
With this patch such redundant TT entries are avoided.
Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
net/batman-adv/multicast.c | 33 +++++++++++++++++++++++++++------
1 file changed, 27 insertions(+), 6 deletions(-)
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index ca9e2e67bdc6..d4e7474022e3 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -230,6 +230,10 @@ batadv_mcast_mla_softif_get_ipv4(struct net_device *dev,
for (pmc = rcu_dereference(in_dev->mc_list); pmc;
pmc = rcu_dereference(pmc->next_rcu)) {
+ if (flags->tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES &&
+ ipv4_is_local_multicast(pmc->multiaddr))
+ continue;
+
ip_eth_mc_map(pmc->multiaddr, mcast_addr);
if (batadv_mcast_mla_is_duplicate(mcast_addr, mcast_list))
@@ -293,6 +297,10 @@ batadv_mcast_mla_softif_get_ipv6(struct net_device *dev,
IPV6_ADDR_SCOPE_LINKLOCAL)
continue;
+ if (flags->tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES &&
+ ipv6_addr_is_ll_all_nodes(&pmc6->mca_addr))
+ continue;
+
ipv6_eth_mc_map(&pmc6->mca_addr, mcast_addr);
if (batadv_mcast_mla_is_duplicate(mcast_addr, mcast_list))
@@ -413,9 +421,8 @@ static int batadv_mcast_mla_bridge_get(struct net_device *dev,
struct batadv_mcast_mla_flags *flags)
{
struct list_head bridge_mcast_list = LIST_HEAD_INIT(bridge_mcast_list);
- bool all_ipv4 = flags->tvlv_flags & BATADV_MCAST_WANT_ALL_IPV4;
- bool all_ipv6 = flags->tvlv_flags & BATADV_MCAST_WANT_ALL_IPV6;
struct br_ip_list *br_ip_entry, *tmp;
+ u8 tvlv_flags = flags->tvlv_flags;
struct batadv_hw_addr *new;
u8 mcast_addr[ETH_ALEN];
int ret;
@@ -428,11 +435,25 @@ static int batadv_mcast_mla_bridge_get(struct net_device *dev,
goto out;
list_for_each_entry(br_ip_entry, &bridge_mcast_list, list) {
- if (all_ipv4 && br_ip_entry->addr.proto == htons(ETH_P_IP))
- continue;
+ if (br_ip_entry->addr.proto == htons(ETH_P_IP)) {
+ if (tvlv_flags & BATADV_MCAST_WANT_ALL_IPV4)
+ continue;
- if (all_ipv6 && br_ip_entry->addr.proto == htons(ETH_P_IPV6))
- continue;
+ if (tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES &&
+ ipv4_is_local_multicast(br_ip_entry->addr.u.ip4))
+ continue;
+ }
+
+#if IS_ENABLED(CONFIG_IPV6)
+ if (br_ip_entry->addr.proto == htons(ETH_P_IPV6)) {
+ if (tvlv_flags & BATADV_MCAST_WANT_ALL_IPV6)
+ continue;
+
+ if (tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES &&
+ ipv6_addr_is_ll_all_nodes(&br_ip_entry->addr.u.ip6))
+ continue;
+ }
+#endif
batadv_mcast_mla_br_addr_cpy(mcast_addr, &br_ip_entry->addr);
if (batadv_mcast_mla_is_duplicate(mcast_addr, mcast_list))
--
2.11.0
^ permalink raw reply related
* [PATCH 09/10] batman-adv: mcast: detect, distribute and maintain multicast router presence
From: Simon Wunderlich @ 2019-06-28 13:56 UTC (permalink / raw)
To: davem
Cc: netdev, b.a.t.m.a.n, Linus Lüssing, Sven Eckelmann,
Simon Wunderlich
In-Reply-To: <20190628135604.11581-1-sw@simonwunderlich.de>
From: Linus Lüssing <linus.luessing@c0d3.blue>
To be able to apply our group aware multicast optimizations to packets
with a scope greater than link-local we need to not only keep track of
multicast listeners but also multicast routers.
With this patch a node detects the presence of multicast routers on
its segment by checking if
/proc/sys/net/ipv{4,6}/conf/<bat0|br0(bat)>/mc_forwarding is set for one
thing. This option is enabled by multicast routing daemons and needed
for the kernel's multicast routing tables to receive and route packets.
For another thing if a bridge is configured on top of bat0 then the
presence of an IPv6 multicast router behind this bridge is currently
detected by checking for an IPv6 multicast "All Routers Address"
(ff02::2). This should later be replaced by querying the bridge, which
performs proper, RFC4286 compliant Multicast Router Discovery (our
simplified approach includes more hosts than necessary, most notably
not just multicast routers but also unicast ones and is not applicable
for IPv4).
If no multicast router is detected then this is signalized via the new
BATADV_MCAST_WANT_NO_RTR4 and BATADV_MCAST_WANT_NO_RTR6
multicast tvlv flags.
Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
include/uapi/linux/batadv_packet.h | 8 +
net/batman-adv/multicast.c | 412 ++++++++++++++++++++++++++++++++-----
net/batman-adv/originator.c | 4 +-
net/batman-adv/types.h | 29 +++
4 files changed, 399 insertions(+), 54 deletions(-)
diff --git a/include/uapi/linux/batadv_packet.h b/include/uapi/linux/batadv_packet.h
index 4ebc2135e950..2a15f01c2243 100644
--- a/include/uapi/linux/batadv_packet.h
+++ b/include/uapi/linux/batadv_packet.h
@@ -107,12 +107,20 @@ enum batadv_icmp_packettype {
* @BATADV_MCAST_WANT_ALL_UNSNOOPABLES: we want all packets destined for
* 224.0.0.0/24 or ff02::1
* @BATADV_MCAST_WANT_ALL_IPV4: we want all IPv4 multicast packets
+ * (both link-local and routable ones)
* @BATADV_MCAST_WANT_ALL_IPV6: we want all IPv6 multicast packets
+ * (both link-local and routable ones)
+ * @BATADV_MCAST_WANT_NO_RTR4: we have no IPv4 multicast router and therefore
+ * only need routable IPv4 multicast packets we signed up for explicitly
+ * @BATADV_MCAST_WANT_NO_RTR6: we have no IPv6 multicast router and therefore
+ * only need routable IPv6 multicast packets we signed up for explicitly
*/
enum batadv_mcast_flags {
BATADV_MCAST_WANT_ALL_UNSNOOPABLES = 1UL << 0,
BATADV_MCAST_WANT_ALL_IPV4 = 1UL << 1,
BATADV_MCAST_WANT_ALL_IPV6 = 1UL << 2,
+ BATADV_MCAST_WANT_NO_RTR4 = 1UL << 3,
+ BATADV_MCAST_WANT_NO_RTR6 = 1UL << 4,
};
/* tt data subtypes */
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index d4e7474022e3..80d5f3c892cb 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -73,27 +73,201 @@ static void batadv_mcast_start_timer(struct batadv_priv *bat_priv)
}
/**
- * batadv_mcast_has_bridge() - check whether the soft-iface is bridged
- * @bat_priv: the bat priv with all the soft interface information
+ * batadv_mcast_get_bridge() - get the bridge on top of the softif if it exists
+ * @soft_iface: netdev struct of the mesh interface
*
- * Checks whether there is a bridge on top of our soft interface.
+ * If the given soft interface has a bridge on top then the refcount
+ * of the according net device is increased.
*
- * Return: true if there is a bridge, false otherwise.
+ * Return: NULL if no such bridge exists. Otherwise the net device of the
+ * bridge.
*/
-static bool batadv_mcast_has_bridge(struct batadv_priv *bat_priv)
+static struct net_device *batadv_mcast_get_bridge(struct net_device *soft_iface)
{
- struct net_device *upper = bat_priv->soft_iface;
+ struct net_device *upper = soft_iface;
rcu_read_lock();
do {
upper = netdev_master_upper_dev_get_rcu(upper);
} while (upper && !(upper->priv_flags & IFF_EBRIDGE));
+
+ if (upper)
+ dev_hold(upper);
rcu_read_unlock();
return upper;
}
/**
+ * batadv_mcast_mla_rtr_flags_softif_get_ipv4() - get mcast router flags from
+ * node for IPv4
+ * @dev: the interface to check
+ *
+ * Checks the presence of an IPv4 multicast router on this node.
+ *
+ * Caller needs to hold rcu read lock.
+ *
+ * Return: BATADV_NO_FLAGS if present, BATADV_MCAST_WANT_NO_RTR4 otherwise.
+ */
+static u8 batadv_mcast_mla_rtr_flags_softif_get_ipv4(struct net_device *dev)
+{
+ struct in_device *in_dev = __in_dev_get_rcu(dev);
+
+ if (in_dev && IN_DEV_MFORWARD(in_dev))
+ return BATADV_NO_FLAGS;
+ else
+ return BATADV_MCAST_WANT_NO_RTR4;
+}
+
+/**
+ * batadv_mcast_mla_rtr_flags_softif_get_ipv6() - get mcast router flags from
+ * node for IPv6
+ * @dev: the interface to check
+ *
+ * Checks the presence of an IPv6 multicast router on this node.
+ *
+ * Caller needs to hold rcu read lock.
+ *
+ * Return: BATADV_NO_FLAGS if present, BATADV_MCAST_WANT_NO_RTR6 otherwise.
+ */
+#if IS_ENABLED(CONFIG_IPV6_MROUTE)
+static u8 batadv_mcast_mla_rtr_flags_softif_get_ipv6(struct net_device *dev)
+{
+ struct inet6_dev *in6_dev = __in6_dev_get(dev);
+
+ if (in6_dev && in6_dev->cnf.mc_forwarding)
+ return BATADV_NO_FLAGS;
+ else
+ return BATADV_MCAST_WANT_NO_RTR6;
+}
+#else
+static inline u8
+batadv_mcast_mla_rtr_flags_softif_get_ipv6(struct net_device *dev)
+{
+ return BATADV_MCAST_WANT_NO_RTR6;
+}
+#endif
+
+/**
+ * batadv_mcast_mla_rtr_flags_softif_get() - get mcast router flags from node
+ * @bat_priv: the bat priv with all the soft interface information
+ * @bridge: bridge interface on top of the soft_iface if present,
+ * otherwise pass NULL
+ *
+ * Checks the presence of IPv4 and IPv6 multicast routers on this
+ * node.
+ *
+ * Return:
+ * BATADV_NO_FLAGS: Both an IPv4 and IPv6 multicast router is present
+ * BATADV_MCAST_WANT_NO_RTR4: No IPv4 multicast router is present
+ * BATADV_MCAST_WANT_NO_RTR6: No IPv6 multicast router is present
+ * The former two OR'd: no multicast router is present
+ */
+static u8 batadv_mcast_mla_rtr_flags_softif_get(struct batadv_priv *bat_priv,
+ struct net_device *bridge)
+{
+ struct net_device *dev = bridge ? bridge : bat_priv->soft_iface;
+ u8 flags = BATADV_NO_FLAGS;
+
+ rcu_read_lock();
+
+ flags |= batadv_mcast_mla_rtr_flags_softif_get_ipv4(dev);
+ flags |= batadv_mcast_mla_rtr_flags_softif_get_ipv6(dev);
+
+ rcu_read_unlock();
+
+ return flags;
+}
+
+/**
+ * batadv_mcast_mla_rtr_flags_bridge_get() - get mcast router flags from bridge
+ * @bat_priv: the bat priv with all the soft interface information
+ * @bridge: bridge interface on top of the soft_iface if present,
+ * otherwise pass NULL
+ *
+ * Checks the presence of IPv4 and IPv6 multicast routers behind a bridge.
+ *
+ * Return:
+ * BATADV_NO_FLAGS: Both an IPv4 and IPv6 multicast router is present
+ * BATADV_MCAST_WANT_NO_RTR4: No IPv4 multicast router is present
+ * BATADV_MCAST_WANT_NO_RTR6: No IPv6 multicast router is present
+ * The former two OR'd: no multicast router is present
+ */
+#if IS_ENABLED(CONFIG_IPV6)
+static u8 batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv,
+ struct net_device *bridge)
+{
+ struct list_head bridge_mcast_list = LIST_HEAD_INIT(bridge_mcast_list);
+ struct net_device *dev = bat_priv->soft_iface;
+ struct br_ip_list *br_ip_entry, *tmp;
+ u8 flags = BATADV_MCAST_WANT_NO_RTR6;
+ int ret;
+
+ if (!bridge)
+ return BATADV_MCAST_WANT_NO_RTR4 | BATADV_MCAST_WANT_NO_RTR6;
+
+ /* TODO: ask the bridge if a multicast router is present (the bridge
+ * is capable of performing proper RFC4286 multicast multicast router
+ * discovery) instead of searching for a ff02::2 listener here
+ */
+ ret = br_multicast_list_adjacent(dev, &bridge_mcast_list);
+ if (ret < 0)
+ return BATADV_NO_FLAGS;
+
+ list_for_each_entry_safe(br_ip_entry, tmp, &bridge_mcast_list, list) {
+ /* the bridge snooping does not maintain IPv4 link-local
+ * addresses - therefore we won't find any IPv4 multicast router
+ * address here, only IPv6 ones
+ */
+ if (br_ip_entry->addr.proto == htons(ETH_P_IPV6) &&
+ ipv6_addr_is_ll_all_routers(&br_ip_entry->addr.u.ip6))
+ flags &= ~BATADV_MCAST_WANT_NO_RTR6;
+
+ list_del(&br_ip_entry->list);
+ kfree(br_ip_entry);
+ }
+
+ return flags;
+}
+#else
+static inline u8
+batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv,
+ struct net_device *bridge)
+{
+ if (bridge)
+ return BATADV_NO_FLAGS;
+ else
+ return BATADV_MCAST_WANT_NO_RTR4 | BATADV_MCAST_WANT_NO_RTR6;
+}
+#endif
+
+/**
+ * batadv_mcast_mla_rtr_flags_get() - get multicast router flags
+ * @bat_priv: the bat priv with all the soft interface information
+ * @bridge: bridge interface on top of the soft_iface if present,
+ * otherwise pass NULL
+ *
+ * Checks the presence of IPv4 and IPv6 multicast routers on this
+ * node or behind its bridge.
+ *
+ * Return:
+ * BATADV_NO_FLAGS: Both an IPv4 and IPv6 multicast router is present
+ * BATADV_MCAST_WANT_NO_RTR4: No IPv4 multicast router is present
+ * BATADV_MCAST_WANT_NO_RTR6: No IPv6 multicast router is present
+ * The former two OR'd: no multicast router is present
+ */
+static u8 batadv_mcast_mla_rtr_flags_get(struct batadv_priv *bat_priv,
+ struct net_device *bridge)
+{
+ u8 flags = BATADV_MCAST_WANT_NO_RTR4 | BATADV_MCAST_WANT_NO_RTR6;
+
+ flags &= batadv_mcast_mla_rtr_flags_softif_get(bat_priv, bridge);
+ flags &= batadv_mcast_mla_rtr_flags_bridge_get(bat_priv, bridge);
+
+ return flags;
+}
+
+/**
* batadv_mcast_mla_flags_get() - get the new multicast flags
* @bat_priv: the bat priv with all the soft interface information
*
@@ -106,13 +280,20 @@ batadv_mcast_mla_flags_get(struct batadv_priv *bat_priv)
struct net_device *dev = bat_priv->soft_iface;
struct batadv_mcast_querier_state *qr4, *qr6;
struct batadv_mcast_mla_flags mla_flags;
+ struct net_device *bridge;
+
+ bridge = batadv_mcast_get_bridge(dev);
memset(&mla_flags, 0, sizeof(mla_flags));
mla_flags.enabled = 1;
+ mla_flags.tvlv_flags |= batadv_mcast_mla_rtr_flags_get(bat_priv,
+ bridge);
- if (!batadv_mcast_has_bridge(bat_priv))
+ if (!bridge)
return mla_flags;
+ dev_put(bridge);
+
mla_flags.bridged = 1;
qr4 = &mla_flags.querier_ipv4;
qr6 = &mla_flags.querier_ipv6;
@@ -137,42 +318,20 @@ batadv_mcast_mla_flags_get(struct batadv_priv *bat_priv)
* In both cases, we will signalize other batman nodes that
* we need all multicast traffic of the according protocol.
*/
- if (!qr4->exists || qr4->shadowing)
+ if (!qr4->exists || qr4->shadowing) {
mla_flags.tvlv_flags |= BATADV_MCAST_WANT_ALL_IPV4;
+ mla_flags.tvlv_flags &= ~BATADV_MCAST_WANT_NO_RTR4;
+ }
- if (!qr6->exists || qr6->shadowing)
+ if (!qr6->exists || qr6->shadowing) {
mla_flags.tvlv_flags |= BATADV_MCAST_WANT_ALL_IPV6;
+ mla_flags.tvlv_flags &= ~BATADV_MCAST_WANT_NO_RTR6;
+ }
return mla_flags;
}
/**
- * batadv_mcast_get_bridge() - get the bridge on top of the softif if it exists
- * @soft_iface: netdev struct of the mesh interface
- *
- * If the given soft interface has a bridge on top then the refcount
- * of the according net device is increased.
- *
- * Return: NULL if no such bridge exists. Otherwise the net device of the
- * bridge.
- */
-static struct net_device *batadv_mcast_get_bridge(struct net_device *soft_iface)
-{
- struct net_device *upper = soft_iface;
-
- rcu_read_lock();
- do {
- upper = netdev_master_upper_dev_get_rcu(upper);
- } while (upper && !(upper->priv_flags & IFF_EBRIDGE));
-
- if (upper)
- dev_hold(upper);
- rcu_read_unlock();
-
- return upper;
-}
-
-/**
* batadv_mcast_mla_is_duplicate() - check whether an address is in a list
* @mcast_addr: the multicast address to check
* @mcast_list: the list with multicast addresses to search in
@@ -234,6 +393,10 @@ batadv_mcast_mla_softif_get_ipv4(struct net_device *dev,
ipv4_is_local_multicast(pmc->multiaddr))
continue;
+ if (!(flags->tvlv_flags & BATADV_MCAST_WANT_NO_RTR4) &&
+ !ipv4_is_local_multicast(pmc->multiaddr))
+ continue;
+
ip_eth_mc_map(pmc->multiaddr, mcast_addr);
if (batadv_mcast_mla_is_duplicate(mcast_addr, mcast_list))
@@ -301,6 +464,11 @@ batadv_mcast_mla_softif_get_ipv6(struct net_device *dev,
ipv6_addr_is_ll_all_nodes(&pmc6->mca_addr))
continue;
+ if (!(flags->tvlv_flags & BATADV_MCAST_WANT_NO_RTR6) &&
+ IPV6_ADDR_MC_SCOPE(&pmc6->mca_addr) >
+ IPV6_ADDR_SCOPE_LINKLOCAL)
+ continue;
+
ipv6_eth_mc_map(&pmc6->mca_addr, mcast_addr);
if (batadv_mcast_mla_is_duplicate(mcast_addr, mcast_list))
@@ -442,6 +610,10 @@ static int batadv_mcast_mla_bridge_get(struct net_device *dev,
if (tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES &&
ipv4_is_local_multicast(br_ip_entry->addr.u.ip4))
continue;
+
+ if (!(tvlv_flags & BATADV_MCAST_WANT_NO_RTR4) &&
+ !ipv4_is_local_multicast(br_ip_entry->addr.u.ip4))
+ continue;
}
#if IS_ENABLED(CONFIG_IPV6)
@@ -452,6 +624,11 @@ static int batadv_mcast_mla_bridge_get(struct net_device *dev,
if (tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES &&
ipv6_addr_is_ll_all_nodes(&br_ip_entry->addr.u.ip6))
continue;
+
+ if (!(tvlv_flags & BATADV_MCAST_WANT_NO_RTR6) &&
+ IPV6_ADDR_MC_SCOPE(&br_ip_entry->addr.u.ip6) >
+ IPV6_ADDR_SCOPE_LINKLOCAL)
+ continue;
}
#endif
@@ -662,19 +839,23 @@ static void batadv_mcast_flags_log(struct batadv_priv *bat_priv, u8 flags)
{
bool old_enabled = bat_priv->mcast.mla_flags.enabled;
u8 old_flags = bat_priv->mcast.mla_flags.tvlv_flags;
- char str_old_flags[] = "[...]";
+ char str_old_flags[] = "[.... . ]";
- sprintf(str_old_flags, "[%c%c%c]",
+ sprintf(str_old_flags, "[%c%c%c%s%s]",
(old_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.',
(old_flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.',
- (old_flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.');
+ (old_flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.',
+ !(old_flags & BATADV_MCAST_WANT_NO_RTR4) ? "R4" : ". ",
+ !(old_flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". ");
batadv_dbg(BATADV_DBG_MCAST, bat_priv,
- "Changing multicast flags from '%s' to '[%c%c%c]'\n",
+ "Changing multicast flags from '%s' to '[%c%c%c%s%s]'\n",
old_enabled ? str_old_flags : "<undefined>",
(flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.',
(flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.',
- (flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.');
+ (flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.',
+ !(flags & BATADV_MCAST_WANT_NO_RTR4) ? "R4" : ". ",
+ !(flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". ");
}
/**
@@ -1467,6 +1648,127 @@ static void batadv_mcast_want_ipv6_update(struct batadv_priv *bat_priv,
}
/**
+ * batadv_mcast_want_rtr4_update() - update want-all-rtr4 counter and list
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig: the orig_node which multicast state might have changed of
+ * @mcast_flags: flags indicating the new multicast state
+ *
+ * If the BATADV_MCAST_WANT_NO_RTR4 flag of this originator, orig, has
+ * toggled then this method updates counter and list accordingly.
+ *
+ * Caller needs to hold orig->mcast_handler_lock.
+ */
+static void batadv_mcast_want_rtr4_update(struct batadv_priv *bat_priv,
+ struct batadv_orig_node *orig,
+ u8 mcast_flags)
+{
+ struct hlist_node *node = &orig->mcast_want_all_rtr4_node;
+ struct hlist_head *head = &bat_priv->mcast.want_all_rtr4_list;
+
+ lockdep_assert_held(&orig->mcast_handler_lock);
+
+ /* switched from flag set to unset */
+ if (!(mcast_flags & BATADV_MCAST_WANT_NO_RTR4) &&
+ orig->mcast_flags & BATADV_MCAST_WANT_NO_RTR4) {
+ atomic_inc(&bat_priv->mcast.num_want_all_rtr4);
+
+ spin_lock_bh(&bat_priv->mcast.want_lists_lock);
+ /* flag checks above + mcast_handler_lock prevents this */
+ WARN_ON(!hlist_unhashed(node));
+
+ hlist_add_head_rcu(node, head);
+ spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
+ /* switched from flag unset to set */
+ } else if (mcast_flags & BATADV_MCAST_WANT_NO_RTR4 &&
+ !(orig->mcast_flags & BATADV_MCAST_WANT_NO_RTR4)) {
+ atomic_dec(&bat_priv->mcast.num_want_all_rtr4);
+
+ spin_lock_bh(&bat_priv->mcast.want_lists_lock);
+ /* flag checks above + mcast_handler_lock prevents this */
+ WARN_ON(hlist_unhashed(node));
+
+ hlist_del_init_rcu(node);
+ spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
+ }
+}
+
+/**
+ * batadv_mcast_want_rtr6_update() - update want-all-rtr6 counter and list
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig: the orig_node which multicast state might have changed of
+ * @mcast_flags: flags indicating the new multicast state
+ *
+ * If the BATADV_MCAST_WANT_NO_RTR6 flag of this originator, orig, has
+ * toggled then this method updates counter and list accordingly.
+ *
+ * Caller needs to hold orig->mcast_handler_lock.
+ */
+static void batadv_mcast_want_rtr6_update(struct batadv_priv *bat_priv,
+ struct batadv_orig_node *orig,
+ u8 mcast_flags)
+{
+ struct hlist_node *node = &orig->mcast_want_all_rtr6_node;
+ struct hlist_head *head = &bat_priv->mcast.want_all_rtr6_list;
+
+ lockdep_assert_held(&orig->mcast_handler_lock);
+
+ /* switched from flag set to unset */
+ if (!(mcast_flags & BATADV_MCAST_WANT_NO_RTR6) &&
+ orig->mcast_flags & BATADV_MCAST_WANT_NO_RTR6) {
+ atomic_inc(&bat_priv->mcast.num_want_all_rtr6);
+
+ spin_lock_bh(&bat_priv->mcast.want_lists_lock);
+ /* flag checks above + mcast_handler_lock prevents this */
+ WARN_ON(!hlist_unhashed(node));
+
+ hlist_add_head_rcu(node, head);
+ spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
+ /* switched from flag unset to set */
+ } else if (mcast_flags & BATADV_MCAST_WANT_NO_RTR6 &&
+ !(orig->mcast_flags & BATADV_MCAST_WANT_NO_RTR6)) {
+ atomic_dec(&bat_priv->mcast.num_want_all_rtr6);
+
+ spin_lock_bh(&bat_priv->mcast.want_lists_lock);
+ /* flag checks above + mcast_handler_lock prevents this */
+ WARN_ON(hlist_unhashed(node));
+
+ hlist_del_init_rcu(node);
+ spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
+ }
+}
+
+/**
+ * batadv_mcast_tvlv_flags_get() - get multicast flags from an OGM TVLV
+ * @enabled: whether the originator has multicast TVLV support enabled
+ * @tvlv_value: tvlv buffer containing the multicast flags
+ * @tvlv_value_len: tvlv buffer length
+ *
+ * Return: multicast flags for the given tvlv buffer
+ */
+static u8
+batadv_mcast_tvlv_flags_get(bool enabled, void *tvlv_value, u16 tvlv_value_len)
+{
+ u8 mcast_flags = BATADV_NO_FLAGS;
+
+ if (enabled && tvlv_value && tvlv_value_len >= sizeof(mcast_flags))
+ mcast_flags = *(u8 *)tvlv_value;
+
+ if (!enabled) {
+ mcast_flags |= BATADV_MCAST_WANT_ALL_IPV4;
+ mcast_flags |= BATADV_MCAST_WANT_ALL_IPV6;
+ }
+
+ /* remove redundant flags to avoid sending duplicate packets later */
+ if (mcast_flags & BATADV_MCAST_WANT_ALL_IPV4)
+ mcast_flags |= BATADV_MCAST_WANT_NO_RTR4;
+
+ if (mcast_flags & BATADV_MCAST_WANT_ALL_IPV6)
+ mcast_flags |= BATADV_MCAST_WANT_NO_RTR6;
+
+ return mcast_flags;
+}
+
+/**
* batadv_mcast_tvlv_ogm_handler() - process incoming multicast tvlv container
* @bat_priv: the bat priv with all the soft interface information
* @orig: the orig_node of the ogm
@@ -1481,16 +1783,10 @@ static void batadv_mcast_tvlv_ogm_handler(struct batadv_priv *bat_priv,
u16 tvlv_value_len)
{
bool orig_mcast_enabled = !(flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND);
- u8 mcast_flags = BATADV_NO_FLAGS;
-
- if (orig_mcast_enabled && tvlv_value &&
- tvlv_value_len >= sizeof(mcast_flags))
- mcast_flags = *(u8 *)tvlv_value;
+ u8 mcast_flags;
- if (!orig_mcast_enabled) {
- mcast_flags |= BATADV_MCAST_WANT_ALL_IPV4;
- mcast_flags |= BATADV_MCAST_WANT_ALL_IPV6;
- }
+ mcast_flags = batadv_mcast_tvlv_flags_get(orig_mcast_enabled,
+ tvlv_value, tvlv_value_len);
spin_lock_bh(&orig->mcast_handler_lock);
@@ -1507,6 +1803,8 @@ static void batadv_mcast_tvlv_ogm_handler(struct batadv_priv *bat_priv,
batadv_mcast_want_unsnoop_update(bat_priv, orig, mcast_flags);
batadv_mcast_want_ipv4_update(bat_priv, orig, mcast_flags);
batadv_mcast_want_ipv6_update(bat_priv, orig, mcast_flags);
+ batadv_mcast_want_rtr4_update(bat_priv, orig, mcast_flags);
+ batadv_mcast_want_rtr6_update(bat_priv, orig, mcast_flags);
orig->mcast_flags = mcast_flags;
spin_unlock_bh(&orig->mcast_handler_lock);
@@ -1556,10 +1854,12 @@ static void batadv_mcast_flags_print_header(struct batadv_priv *bat_priv,
shadowing6 = '?';
}
- seq_printf(seq, "Multicast flags (own flags: [%c%c%c])\n",
+ seq_printf(seq, "Multicast flags (own flags: [%c%c%c%s%s])\n",
(flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.',
(flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.',
- (flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.');
+ (flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.',
+ !(flags & BATADV_MCAST_WANT_NO_RTR4) ? "R4" : ". ",
+ !(flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". ");
seq_printf(seq, "* Bridged [U]\t\t\t\t%c\n", bridged ? 'U' : '.');
seq_printf(seq, "* No IGMP/MLD Querier [4/6]:\t\t%c/%c\n",
querier4, querier6);
@@ -1613,13 +1913,17 @@ int batadv_mcast_flags_seq_print_text(struct seq_file *seq, void *offset)
flags = orig_node->mcast_flags;
- seq_printf(seq, "%pM [%c%c%c]\n", orig_node->orig,
+ seq_printf(seq, "%pM [%c%c%c%s%s]\n", orig_node->orig,
(flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES)
? 'U' : '.',
(flags & BATADV_MCAST_WANT_ALL_IPV4)
? '4' : '.',
(flags & BATADV_MCAST_WANT_ALL_IPV6)
- ? '6' : '.');
+ ? '6' : '.',
+ !(flags & BATADV_MCAST_WANT_NO_RTR4)
+ ? "R4" : ". ",
+ !(flags & BATADV_MCAST_WANT_NO_RTR6)
+ ? "R6" : ". ");
}
rcu_read_unlock();
}
@@ -1893,6 +2197,8 @@ void batadv_mcast_purge_orig(struct batadv_orig_node *orig)
batadv_mcast_want_unsnoop_update(bat_priv, orig, BATADV_NO_FLAGS);
batadv_mcast_want_ipv4_update(bat_priv, orig, BATADV_NO_FLAGS);
batadv_mcast_want_ipv6_update(bat_priv, orig, BATADV_NO_FLAGS);
+ batadv_mcast_want_rtr4_update(bat_priv, orig, BATADV_NO_FLAGS);
+ batadv_mcast_want_rtr6_update(bat_priv, orig, BATADV_NO_FLAGS);
spin_unlock_bh(&orig->mcast_handler_lock);
}
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 45db798a7297..38613487fb1b 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -27,6 +27,7 @@
#include <linux/stddef.h>
#include <linux/workqueue.h>
#include <net/sock.h>
+#include <uapi/linux/batadv_packet.h>
#include <uapi/linux/batman_adv.h>
#include "bat_algo.h"
@@ -1043,7 +1044,8 @@ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv,
orig_node->bcast_seqno_reset = reset_time;
#ifdef CONFIG_BATMAN_ADV_MCAST
- orig_node->mcast_flags = BATADV_NO_FLAGS;
+ orig_node->mcast_flags = BATADV_MCAST_WANT_NO_RTR4;
+ orig_node->mcast_flags |= BATADV_MCAST_WANT_NO_RTR6;
INIT_HLIST_NODE(&orig_node->mcast_want_all_unsnoopables_node);
INIT_HLIST_NODE(&orig_node->mcast_want_all_ipv4_node);
INIT_HLIST_NODE(&orig_node->mcast_want_all_ipv6_node);
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 72f65b3769d0..c2996296b953 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -404,6 +404,17 @@ struct batadv_orig_node {
* list
*/
struct hlist_node mcast_want_all_ipv6_node;
+
+ /**
+ * @mcast_want_all_rtr4_node: a list node for the mcast.want_all_rtr4
+ * list
+ */
+ struct hlist_node mcast_want_all_rtr4_node;
+ /**
+ * @mcast_want_all_rtr6_node: a list node for the mcast.want_all_rtr6
+ * list
+ */
+ struct hlist_node mcast_want_all_rtr6_node;
#endif
/** @capabilities: announced capabilities of this originator */
@@ -1219,6 +1230,18 @@ struct batadv_priv_mcast {
struct hlist_head want_all_ipv6_list;
/**
+ * @want_all_rtr4_list: a list of orig_nodes wanting all routable IPv4
+ * multicast traffic
+ */
+ struct hlist_head want_all_rtr4_list;
+
+ /**
+ * @want_all_rtr6_list: a list of orig_nodes wanting all routable IPv6
+ * multicast traffic
+ */
+ struct hlist_head want_all_rtr6_list;
+
+ /**
* @mla_flags: flags for the querier, bridge and tvlv state
*/
struct batadv_mcast_mla_flags mla_flags;
@@ -1240,6 +1263,12 @@ struct batadv_priv_mcast {
/** @num_want_all_ipv6: counter for items in want_all_ipv6_list */
atomic_t num_want_all_ipv6;
+ /** @num_want_all_rtr4: counter for items in want_all_rtr4_list */
+ atomic_t num_want_all_rtr4;
+
+ /** @num_want_all_rtr6: counter for items in want_all_rtr6_list */
+ atomic_t num_want_all_rtr6;
+
/**
* @want_lists_lock: lock for protecting modifications to mcasts
* want_all_{unsnoopables,ipv4,ipv6}_list (traversals are rcu-locked)
--
2.11.0
^ permalink raw reply related
* [PATCH 03/10] batman-adv: Add missing include for atomic functions
From: Simon Wunderlich @ 2019-06-28 13:55 UTC (permalink / raw)
To: davem; +Cc: netdev, b.a.t.m.a.n, Sven Eckelmann, Simon Wunderlich
In-Reply-To: <20190628135604.11581-1-sw@simonwunderlich.de>
From: Sven Eckelmann <sven@narfation.org>
main.h is using atomic_add_unless and log.h atomic_read. The main
header linux/atomic.h should be included for these files.
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
net/batman-adv/log.h | 1 +
net/batman-adv/main.h | 1 +
2 files changed, 2 insertions(+)
diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h
index 5504637e63d8..741cfa3719ff 100644
--- a/net/batman-adv/log.h
+++ b/net/batman-adv/log.h
@@ -9,6 +9,7 @@
#include "main.h"
+#include <linux/atomic.h>
#include <linux/bitops.h>
#include <linux/compiler.h>
#include <linux/printk.h>
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 11d051dbbda4..821a7de45256 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -205,6 +205,7 @@ enum batadv_uev_type {
/* Kernel headers */
+#include <linux/atomic.h>
#include <linux/compiler.h>
#include <linux/etherdevice.h>
#include <linux/if_vlan.h>
--
2.11.0
^ permalink raw reply related
* [PATCH 00/10] pull request for net-next: batman-adv 2019-06-27 v2
From: Simon Wunderlich @ 2019-06-28 13:55 UTC (permalink / raw)
To: davem; +Cc: netdev, b.a.t.m.a.n, Simon Wunderlich
Hi David,
here is the updated feature/cleanup pull request of batman-adv for net-next
from yesterday. Your change suggestions have been integrated into Patch 6
of the series, everything else is unchanged.
Please pull or let me know of any problem!
Thank you,
Simon
The following changes since commit a188339ca5a396acc588e5851ed7e19f66b0ebd9:
Linux 5.2-rc1 (2019-05-19 15:47:09 -0700)
are available in the git repository at:
git://git.open-mesh.org/linux-merge.git tags/batadv-next-for-davem-20190627v2
for you to fetch changes up to 11d458c1cb9b24ac899b1ec6284676f6b1914305:
batman-adv: mcast: apply optimizations for routable packets, too (2019-06-27 19:25:05 +0200)
----------------------------------------------------------------
This feature/cleanup patchset includes the following patches:
- bump version strings, by Simon Wunderlich
- fix includes for _MAX constants, atomic functions and fwdecls,
by Sven Eckelmann (3 patches)
- shorten multicast tt/tvlv worker spinlock section, by Linus Luessing
- routeable multicast preparations: implement MAC multicast filtering,
by Linus Luessing (2 patches, David Millers comments integrated)
- remove return value checks for debugfs_create, by Greg Kroah-Hartman
- add routable multicast optimizations, by Linus Luessing (2 patches)
----------------------------------------------------------------
Greg Kroah-Hartman (1):
batman-adv: no need to check return value of debugfs_create functions
Linus Lüssing (5):
batman-adv: mcast: shorten multicast tt/tvlv worker spinlock section
batman-adv: mcast: collect softif listeners from IP lists instead
batman-adv: mcast: avoid redundant multicast TT entries with bridges
batman-adv: mcast: detect, distribute and maintain multicast router presence
batman-adv: mcast: apply optimizations for routable packets, too
Simon Wunderlich (1):
batman-adv: Start new development cycle
Sven Eckelmann (3):
batman-adv: Fix includes for *_MAX constants
batman-adv: Add missing include for atomic functions
batman-adv: Use includes instead of fwdecls
include/uapi/linux/batadv_packet.h | 8 +
net/batman-adv/bat_algo.h | 7 +-
net/batman-adv/bat_v.c | 3 +-
net/batman-adv/bat_v_elp.h | 4 +-
net/batman-adv/bat_v_ogm.h | 3 +-
net/batman-adv/bridge_loop_avoidance.h | 9 +-
net/batman-adv/debugfs.c | 99 +--
net/batman-adv/debugfs.h | 9 +-
net/batman-adv/distributed-arp-table.h | 7 +-
net/batman-adv/fragmentation.h | 3 +-
net/batman-adv/gateway_client.h | 9 +-
net/batman-adv/gateway_common.c | 1 +
net/batman-adv/gateway_common.h | 3 +-
net/batman-adv/hard-interface.c | 7 +-
net/batman-adv/hard-interface.h | 5 +-
net/batman-adv/hash.h | 3 +-
net/batman-adv/icmp_socket.c | 20 +-
net/batman-adv/icmp_socket.h | 5 +-
net/batman-adv/log.c | 17 +-
net/batman-adv/log.h | 1 +
net/batman-adv/main.h | 12 +-
net/batman-adv/multicast.c | 1092 +++++++++++++++++++++++++-------
net/batman-adv/multicast.h | 6 +-
net/batman-adv/netlink.c | 4 +-
net/batman-adv/netlink.h | 3 +-
net/batman-adv/network-coding.c | 29 +-
net/batman-adv/network-coding.h | 14 +-
net/batman-adv/originator.c | 4 +-
net/batman-adv/originator.h | 7 +-
net/batman-adv/routing.h | 3 +-
net/batman-adv/send.h | 3 +-
net/batman-adv/soft-interface.c | 6 +-
net/batman-adv/soft-interface.h | 7 +-
net/batman-adv/sysfs.c | 1 +
net/batman-adv/sysfs.h | 5 +-
net/batman-adv/tp_meter.c | 1 +
net/batman-adv/tp_meter.h | 3 +-
net/batman-adv/translation-table.h | 9 +-
net/batman-adv/tvlv.h | 3 +-
net/batman-adv/types.h | 69 +-
40 files changed, 1041 insertions(+), 463 deletions(-)
^ permalink raw reply
* Re: [PATCH 1/2] tls: remove close callback sock unlock/lock and flush_sync
From: John Fastabend @ 2019-06-28 14:12 UTC (permalink / raw)
To: Jakub Kicinski, John Fastabend; +Cc: daniel, ast, netdev, edumazet, bpf
In-Reply-To: <20190627164402.31cbd466@cakuba.netronome.com>
Jakub Kicinski wrote:
> On Thu, 27 Jun 2019 10:36:42 -0700, John Fastabend wrote:
> > The tls close() callback currently drops the sock lock, makes a
> > cancel_delayed_work_sync() call, and then relocks the sock. This
> > seems suspect at best. The lock_sock() is applied to stop concurrent
> > operations on the socket while tearing the sock down. Further we
> > will need to add support for unhash() shortly and this complicates
> > matters because the lock may or may not be held then.
> >
> > So to fix the above situation and simplify the next patch to add
> > unhash this patch creates a function tls_sk_proto_cleanup() that
> > tears down the socket without calling lock_sock/release_sock. In
> > order to flush the workqueue then we do the following,
> >
> > - Add a new bit to ctx, BIT_TX_CLOSING that is set when the
> > tls resources are being removed.
> > - Check this bit before scheduling any new work. This way we
> > avoid queueing new work after tear down has started.
> > - With the BIT_TX_CLOSING ensuring no new work is being added
> > convert the cancel_delayed_work_sync to flush_delayed_work()
> > - Finally call tlx_tx_records() to complete any available records
> > before,
> > - releasing and removing tls ctx.
> >
> > The above is implemented for the software case namely any of
> > the following configurations from build_protos,
> >
> > prot[TLS_SW][TLS_BASE]
> > prot[TLS_BASE][TLS_SW]
> > prot[TLS_SW][TLS_SW]
> >
> > The implication is a follow up patch is needed to resolve the
> > hardware offload case.
> >
> > Tested with net selftests and bpf selftests.
> >
> > Signed-off-by: John Fastabend <john.fastabend@gmail.com>
> > ---
> > include/net/tls.h | 4 ++--
> > net/tls/tls_main.c | 54 ++++++++++++++++++++++++++--------------------------
> > net/tls/tls_sw.c | 50 ++++++++++++++++++++++++++++++++----------------
> > 3 files changed, 62 insertions(+), 46 deletions(-)
> >
> > diff --git a/include/net/tls.h b/include/net/tls.h
> > index 4a55ce6a303f..6fe1f5c96f4a 100644
> > --- a/include/net/tls.h
> > +++ b/include/net/tls.h
> > @@ -105,9 +105,7 @@ struct tls_device {
> > enum {
> > TLS_BASE,
> > TLS_SW,
> > -#ifdef CONFIG_TLS_DEVICE
> > TLS_HW,
> > -#endif
> > TLS_HW_RECORD,
> > TLS_NUM_CONFIG,
> > };
> > @@ -160,6 +158,7 @@ struct tls_sw_context_tx {
> > int async_capable;
> >
> > #define BIT_TX_SCHEDULED 0
>
> BTW do you understand why we track this bit separately? Just to avoid
> the irq operations in the workqueue code?
>
Sorry not sure I understand. You mean vs simply scheduling the work
without checking the bit? Presumably its better to avoid scheduling
unnecessary work.
> > +#define BIT_TX_CLOSING 1
>
> But since we do have the above, and I think it's tested everywhere,
> wouldn't setting SCHEDULED without accentually scheduling have
> effectively the same result?
It would block a send from calling tls_tx_records() but I guess that is
OK because this is a tear down operation and we are about to call
tls_tx_records anyways.
Sure we can do it this way might be slightly nicer to avoid checking
two bits.
>
> > unsigned long tx_bitmask;
> > };
> >
> > @@ -327,6 +326,7 @@ void tls_sw_close(struct sock *sk, long timeout);
> > void tls_sw_free_resources_tx(struct sock *sk);
> > void tls_sw_free_resources_rx(struct sock *sk);
> > void tls_sw_release_resources_rx(struct sock *sk);
> > +void tls_sw_release_strp_rx(struct tls_context *tls_ctx);
> > int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
> > int nonblock, int flags, int *addr_len);
> > bool tls_sw_stream_read(const struct sock *sk);
> > diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
> > index fc81ae18cc44..51cb19e24dd9 100644
> > --- a/net/tls/tls_main.c
> > +++ b/net/tls/tls_main.c
> > @@ -261,24 +261,9 @@ static void tls_ctx_free(struct tls_context *ctx)
> > kfree(ctx);
> > }
> >
> > -static void tls_sk_proto_close(struct sock *sk, long timeout)
> > +static void tls_sk_proto_cleanup(struct sock *sk,
> > + struct tls_context *ctx, long timeo)
> > {
> > - struct tls_context *ctx = tls_get_ctx(sk);
> > - long timeo = sock_sndtimeo(sk, 0);
> > - void (*sk_proto_close)(struct sock *sk, long timeout);
> > - bool free_ctx = false;
> > -
> > - lock_sock(sk);
> > - sk_proto_close = ctx->sk_proto_close;
> > -
> > - if (ctx->tx_conf == TLS_HW_RECORD && ctx->rx_conf == TLS_HW_RECORD)
> > - goto skip_tx_cleanup;
> > -
> > - if (ctx->tx_conf == TLS_BASE && ctx->rx_conf == TLS_BASE) {
> > - free_ctx = true;
> > - goto skip_tx_cleanup;
> > - }
> > -
> > if (!tls_complete_pending_work(sk, ctx, 0, &timeo))
> > tls_handle_open_record(sk, 0);
> >
> > @@ -299,22 +284,37 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
> > #ifdef CONFIG_TLS_DEVICE
> > if (ctx->rx_conf == TLS_HW)
> > tls_device_offload_cleanup_rx(sk);
> > -
> > - if (ctx->tx_conf != TLS_HW && ctx->rx_conf != TLS_HW) {
> > -#else
> > - {
> > #endif
> > - tls_ctx_free(ctx);
> > - ctx = NULL;
> > +}
> > +
> > +static void tls_sk_proto_close(struct sock *sk, long timeout)
> > +{
> > + struct tls_context *ctx = tls_get_ctx(sk);
> > + long timeo = sock_sndtimeo(sk, 0);
> > + void (*sk_proto_close)(struct sock *sk, long timeout);
> > + bool free_ctx = false;
>
> Set but not used?
>
Removed in second patch but right should be removed here.
> > +
> > + lock_sock(sk);
> > + sk_proto_close = ctx->sk_proto_close;
> > +
> > + if (ctx->tx_conf == TLS_HW_RECORD && ctx->rx_conf == TLS_HW_RECORD)
> > + goto skip_tx_cleanup;
> > +
> > + if (ctx->tx_conf == TLS_BASE && ctx->rx_conf == TLS_BASE) {
> > + free_ctx = true;
> > + goto skip_tx_cleanup;
> > }
> >
> > + tls_sk_proto_cleanup(sk, ctx, timeo);
> > +
> > skip_tx_cleanup:
> > release_sock(sk);
> > + if (ctx->rx_conf == TLS_SW)
> > + tls_sw_release_strp_rx(ctx);
> > sk_proto_close(sk, timeout);
> > - /* free ctx for TLS_HW_RECORD, used by tcp_set_state
> > - * for sk->sk_prot->unhash [tls_hw_unhash]
> > - */
> > - if (free_ctx)
> > +
> > + if (ctx->tx_conf != TLS_HW && ctx->rx_conf != TLS_HW &&
> > + ctx->tx_conf != TLS_HW_RECORD && ctx->rx_conf != TLS_HW_RECORD)
> > tls_ctx_free(ctx);
> > }
> >
> > diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
> > index 455a782c7658..d234a6b818e6 100644
> > --- a/net/tls/tls_sw.c
> > +++ b/net/tls/tls_sw.c
> > @@ -473,7 +473,8 @@ static void tls_encrypt_done(struct crypto_async_request *req, int err)
> > return;
> >
> > /* Schedule the transmission */
> > - if (!test_and_set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask))
> > + if (!test_and_set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask) &&
> > + !test_bit(BIT_TX_CLOSING, &ctx->tx_bitmask))
>
> Probably doesn't matter but seems like CLOSING test should be before
> the test_and_set().
>
Yea, looks like we can drop CLOSING bit and use SCHEDULED bit makes
these a bit nicer.
> > schedule_delayed_work(&ctx->tx_work.work, 1);
> > }
> >
> > @@ -2058,16 +2059,26 @@ void tls_sw_free_resources_tx(struct sock *sk)
> > struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
> > struct tls_rec *rec, *tmp;
> >
> > + /* Set TX CLOSING bit to stop tx_work from being scheduled
> > + * while tearing down TX context. We will flush any pending
> > + * work before free'ing ctx anyways. If already set then
> > + * another call is already free'ing resources.
> > + */
>
> Oh, can we get multiple calls here? Is this prep for unhash?
>
It was prep for unhash() but there is a nicer way to get this so
we can drop it and just ensure we reset the prot callbacks before.
> > + if (test_and_set_bit(BIT_TX_CLOSING, &ctx->tx_bitmask))
> > + return;
> > +
> > /* Wait for any pending async encryptions to complete */
> > smp_store_mb(ctx->async_notify, true);
> > if (atomic_read(&ctx->encrypt_pending))
> > crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
> >
> > - release_sock(sk);
> > - cancel_delayed_work_sync(&ctx->tx_work.work);
> > - lock_sock(sk);
> > -
> > - /* Tx whatever records we can transmit and abandon the rest */
> > + /* Flush work queue and then Tx whatever records we can
> > + * transmit and abandon the rest, lock_sock(sk) must be
> > + * held here. We ensure no further work is enqueue by
> > + * checking CLOSING bit before queueing new work and
> > + * setting it above.
> > + */
> > + flush_delayed_work(&ctx->tx_work.work);
> > tls_tx_records(sk, -1);
> >
> > /* Free up un-sent records in tx_list. First, free
> > @@ -2111,22 +2122,22 @@ void tls_sw_release_resources_rx(struct sock *sk)
> > write_lock_bh(&sk->sk_callback_lock);
> > sk->sk_data_ready = ctx->saved_data_ready;
> > write_unlock_bh(&sk->sk_callback_lock);
> > - release_sock(sk);
> > - strp_done(&ctx->strp);
> > - lock_sock(sk);
> > }
> > }
> >
> > -void tls_sw_free_resources_rx(struct sock *sk)
> > +void tls_sw_release_strp_rx(struct tls_context *tls_ctx)
> > {
> > - struct tls_context *tls_ctx = tls_get_ctx(sk);
> > struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
> >
> > - tls_sw_release_resources_rx(sk);
> > -
> > + strp_done(&ctx->strp);
> > kfree(ctx);
> > }
> >
> > +void tls_sw_free_resources_rx(struct sock *sk)
> > +{
> > + tls_sw_release_resources_rx(sk);
> > +}
>
> I don't understand the RX side well enough, but perhaps a separate
> patch would make sense here?
>
sure. Its actually its own fix I guess.
> > /* The work handler to transmitt the encrypted records in tx_list */
> > static void tx_work_handler(struct work_struct *work)
> > {
> > @@ -2140,9 +2151,14 @@ static void tx_work_handler(struct work_struct *work)
> > if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask))
> > return;
> >
> > - lock_sock(sk);
> > + /* If we are running from a socket close operation then the
> > + * lock is already held so we do not need to hold it.
> > + */
> > + if (likely(!test_bit(BIT_TX_CLOSING, &ctx->tx_bitmask)))
> > + lock_sock(sk);
>
> CPU 0 (free) CPU 1 (wq)
> test_bit()
> lock(sk)
> set_bit()
> lock(sk)
> flush_work()
>
> No?
>
Yeah seems possible although never seen in my testing. So I'll
move the test_bit() inside the lock and do a ctx check to ensure
still have the reference.
CPU 0 (free) CPU 1 (wq)
lock(sk)
lock(sk)
set_bit()
cancel_work()
release
ctx = tls_get_ctx(sk)
unlikely(!ctx) <- we may have free'd
test_bit()
...
release()
or
CPU 0 (free) CPU 1 (wq)
lock(sk)
lock(sk)
ctx = tls_get_ctx(sk)
unlikely(!ctx)
test_bit()
...
release()
set_bit()
cancel_work()
release
> > tls_tx_records(sk, -1);
> > - release_sock(sk);
> > + if (likely(!test_bit(BIT_TX_CLOSING, &ctx->tx_bitmask)))
> > + release_sock(sk);
> > }
> >
> > void tls_sw_write_space(struct sock *sk, struct tls_context *ctx)
> > @@ -2152,8 +2168,8 @@ void tls_sw_write_space(struct sock *sk, struct tls_context *ctx)
> > /* Schedule the transmission if tx list is ready */
> > if (is_tx_ready(tx_ctx) && !sk->sk_write_pending) {
> > /* Schedule the transmission */
> > - if (!test_and_set_bit(BIT_TX_SCHEDULED,
> > - &tx_ctx->tx_bitmask))
> > + if (!test_and_set_bit(BIT_TX_SCHEDULED, &tx_ctx->tx_bitmask) &&
> > + !test_bit(BIT_TX_CLOSING, &tx_ctx->tx_bitmask))
> > schedule_delayed_work(&tx_ctx->tx_work.work, 0);
> > }
> > }
> >
>
Thanks,
John
^ permalink raw reply
* Re: [PATCH] netlink: use 48 byte ctx instead of 6 signed longs for callback
From: Johannes Berg @ 2019-06-28 14:42 UTC (permalink / raw)
To: Jason A. Donenfeld, netdev, linux-kernel
In-Reply-To: <20190628144022.31376-1-Jason@zx2c4.com>
On Fri, 2019-06-28 at 16:40 +0200, Jason A. Donenfeld wrote:
> People are inclined to stuff random things into cb->args[n] because it
> looks like an array of integers. Sometimes people even put u64s in there
> with comments noting that a certain member takes up two slots. The
> horror! Really this should mirror the usage of skb->cb, which are just
> 48 opaque bytes suitable for casting a struct. Then people can create
> their usual casting macros for accessing strongly typed members of a
> struct.
>
> As a plus, this also gives us the same amount of space on 32bit and 64bit.
>
> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
> Cc: Johannes Berg <johannes@sipsolutions.net>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
I think this makes a lot of sense - we've got a mess here in many
places, e.g. look at struct nl80211_dump_wiphy_state in nl82011.c, I
think that could fit into the ctx[] since those don't all need to be
'long' (int or even shorter would be OK), we just want many more fields
and somehow it didn't occur to me to cast that "long args[]" array to
another struct ...
Thanks for doing this!
johannes
^ permalink raw reply
* pull-request: mac80211 2019-06-28
From: Johannes Berg @ 2019-06-28 14:44 UTC (permalink / raw)
To: David Miller; +Cc: netdev, linux-wireless
Hi Dave,
Just a single patch still for the current RC cycle, I debated
whether to send a pull request at all or just ask you to apply
the patch, but did it this way now.
Please pull and let me know if there's any problem.
Thanks,
johannes
The following changes since commit 556e2f6020bf90f63c5dd65e9a2254be6db3185b:
Merge tag 'clk-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux (2019-06-28 08:50:09 +0800)
are available in the Git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git tags/mac80211-for-davem-2019-06-28
for you to fetch changes up to d2ce8d6bfcfed014fd281e06c9b1d4638ddf3f1e:
nl80211: Fix undefined behavior in bit shift (2019-06-28 16:07:54 +0200)
----------------------------------------------------------------
Just a single patch:
* 1<<31 is undefined, use 1U<<31 in nl80211.h UAPI
----------------------------------------------------------------
Jiunn Chang (1):
nl80211: Fix undefined behavior in bit shift
include/uapi/linux/nl80211.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
^ permalink raw reply
* [PATCH] netlink: use 48 byte ctx instead of 6 signed longs for callback
From: Jason A. Donenfeld @ 2019-06-28 14:40 UTC (permalink / raw)
To: netdev, linux-kernel; +Cc: Jason A. Donenfeld, Johannes Berg
People are inclined to stuff random things into cb->args[n] because it
looks like an array of integers. Sometimes people even put u64s in there
with comments noting that a certain member takes up two slots. The
horror! Really this should mirror the usage of skb->cb, which are just
48 opaque bytes suitable for casting a struct. Then people can create
their usual casting macros for accessing strongly typed members of a
struct.
As a plus, this also gives us the same amount of space on 32bit and 64bit.
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
---
include/linux/netlink.h | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 593d1b9c33a8..205fa7b1f07a 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -192,7 +192,14 @@ struct netlink_callback {
bool strict_check;
u16 answer_flags;
unsigned int prev_seq, seq;
- long args[6];
+ union {
+ u8 ctx[48];
+
+ /* args is deprecated. Cast a struct over ctx instead
+ * for proper type safety.
+ */
+ long args[6];
+ };
};
struct netlink_notify {
--
2.21.0
^ permalink raw reply related
* Re: [PATCH 1/4] [v2] structleak: disable STRUCTLEAK_BYREF in combination with KASAN_STACK
From: Kees Cook @ 2019-06-28 14:48 UTC (permalink / raw)
To: Arnd Bergmann
Cc: James Morris, Serge E. Hallyn, James Smart, Dick Kennedy,
James E . J . Bottomley, Martin K . Petersen, Larry Finger,
Florian Schilhabel, Greg Kroah-Hartman, David S . Miller,
Wensong Zhang, Simon Horman, Julian Anastasov, Pablo Neira Ayuso,
linux-scsi, linux-kernel, devel, netdev, lvs-devel,
netfilter-devel, coreteam, Ard Biesheuvel, Masahiro Yamada,
Alexander Potapenko, Andrew Morton, Michal Hocko, Thomas Gleixner,
linux-security-module
In-Reply-To: <20190628123819.2785504-1-arnd@arndb.de>
On Fri, Jun 28, 2019 at 02:37:46PM +0200, Arnd Bergmann wrote:
> The combination of KASAN_STACK and GCC_PLUGIN_STRUCTLEAK_BYREF
> leads to much larger kernel stack usage, as seen from the warnings
> about functions that now exceed the 2048 byte limit:
>
> drivers/media/i2c/tvp5150.c:253:1: error: the frame size of 3936 bytes is larger than 2048 bytes
> drivers/media/tuners/r820t.c:1327:1: error: the frame size of 2816 bytes is larger than 2048 bytes
> drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c:16552:1: error: the frame size of 3144 bytes is larger than 2048 bytes [-Werror=frame-larger-than=]
> fs/ocfs2/aops.c:1892:1: error: the frame size of 2088 bytes is larger than 2048 bytes
> fs/ocfs2/dlm/dlmrecovery.c:737:1: error: the frame size of 2088 bytes is larger than 2048 bytes
> fs/ocfs2/namei.c:1677:1: error: the frame size of 2584 bytes is larger than 2048 bytes
> fs/ocfs2/super.c:1186:1: error: the frame size of 2640 bytes is larger than 2048 bytes
> fs/ocfs2/xattr.c:3678:1: error: the frame size of 2176 bytes is larger than 2048 bytes
> net/bluetooth/l2cap_core.c:7056:1: error: the frame size of 2144 bytes is larger than 2048 bytes [-Werror=frame-larger-than=]
> net/bluetooth/l2cap_core.c: In function 'l2cap_recv_frame':
> net/bridge/br_netlink.c:1505:1: error: the frame size of 2448 bytes is larger than 2048 bytes
> net/ieee802154/nl802154.c:548:1: error: the frame size of 2232 bytes is larger than 2048 bytes
> net/wireless/nl80211.c:1726:1: error: the frame size of 2224 bytes is larger than 2048 bytes
> net/wireless/nl80211.c:2357:1: error: the frame size of 4584 bytes is larger than 2048 bytes
> net/wireless/nl80211.c:5108:1: error: the frame size of 2760 bytes is larger than 2048 bytes
> net/wireless/nl80211.c:6472:1: error: the frame size of 2112 bytes is larger than 2048 bytes
>
> The structleak plugin was previously disabled for CONFIG_COMPILE_TEST,
> but meant we missed some bugs, so this time we should address them.
>
> The frame size warnings are distracting, and risking a kernel stack
> overflow is generally not beneficial to performance, so it may be best
> to disallow that particular combination. This can be done by turning
> off either one. I picked the dependency in GCC_PLUGIN_STRUCTLEAK_BYREF
> and GCC_PLUGIN_STRUCTLEAK_BYREF_ALL, as this option is designed to
> make uninitialized stack usage less harmful when enabled on its own,
> but it also prevents KASAN from detecting those cases in which it was
> in fact needed.
>
> KASAN_STACK is currently implied by KASAN on gcc, but could be made a
> user selectable option if we want to allow combining (non-stack) KASAN
> with GCC_PLUGIN_STRUCTLEAK_BYREF.
>
> Note that it would be possible to specifically address the files that
> print the warning, but presumably the overall stack usage is still
> significantly higher than in other configurations, so this would not
> address the full problem.
>
> I could not test this with CONFIG_INIT_STACK_ALL, which may or may not
> suffer from a similar problem.
>
> Fixes: 81a56f6dcd20 ("gcc-plugins: structleak: Generalize to all variable types")
> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Kees Cook <keescook@chromium.org>
-Kees
> ---
> [v2] do it for both GCC_PLUGIN_STRUCTLEAK_BYREF and GCC_PLUGIN_STRUCTLEAK_BYREF_ALL.
> ---
> security/Kconfig.hardening | 7 +++++++
> 1 file changed, 7 insertions(+)
>
> diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening
> index a1ffe2eb4d5f..af4c979b38ee 100644
> --- a/security/Kconfig.hardening
> +++ b/security/Kconfig.hardening
> @@ -61,6 +61,7 @@ choice
> config GCC_PLUGIN_STRUCTLEAK_BYREF
> bool "zero-init structs passed by reference (strong)"
> depends on GCC_PLUGINS
> + depends on !(KASAN && KASAN_STACK=1)
> select GCC_PLUGIN_STRUCTLEAK
> help
> Zero-initialize any structures on the stack that may
> @@ -70,9 +71,15 @@ choice
> exposures, like CVE-2017-1000410:
> https://git.kernel.org/linus/06e7e776ca4d3654
>
> + As a side-effect, this keeps a lot of variables on the
> + stack that can otherwise be optimized out, so combining
> + this with CONFIG_KASAN_STACK can lead to a stack overflow
> + and is disallowed.
> +
> config GCC_PLUGIN_STRUCTLEAK_BYREF_ALL
> bool "zero-init anything passed by reference (very strong)"
> depends on GCC_PLUGINS
> + depends on !(KASAN && KASAN_STACK=1)
> select GCC_PLUGIN_STRUCTLEAK
> help
> Zero-initialize any stack variables that may be passed
> --
> 2.20.0
>
--
Kees Cook
^ permalink raw reply
* [PATCH net-next] af_packet: convert pending frame counter to atomic_t
From: Neil Horman @ 2019-06-28 14:52 UTC (permalink / raw)
To: netdev; +Cc: Neil Horman, David S. Miller, Willem de Bruijn
The AF_PACKET protocol, when running as a memory mapped socket uses a
pending frame counter to track the number of skbs in flight during
transmission. It is incremented during the sendmsg call (via
tpacket_snd), and decremented (possibly asynchronously) in the skb
desructor during skb_free.
The counter is currently implemented as a percpu variable for each open
socket, but for reads (via packet_read_pending), we iterate over every
cpu variable, accumulating the total pending count.
Given that the socket transmit path is an exclusive path (locked via the
pg_vec_lock mutex), we do not have the ability to increment this counter
on multiple cpus in parallel. This implementation also seems to have
the potential to be broken, in that, should an skb be freed on a cpu
other than the one that it was initially transmitted on, we may
decrement a counter that was not initially incremented, leading to
underflow.
As such, adjust the packet socket struct to convert the per-cpu counter
to an atomic_t variable (to enforce consistency between the send path
and the skb free path). This saves us some space in the packet_sock
structure, prevents the possibility of underflow, and should reduce the
run time of packet_read_pending, as we only need to read a single
variable, instead of having to loop over every available cpu variable
instance.
Tested by myself by running a small program which sends frames via
AF_PACKET on multiple cpus in parallel, with good results.
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: Willem de Bruijn <willemb@google.com>
---
net/packet/af_packet.c | 40 +++++-----------------------------------
net/packet/internal.h | 2 +-
2 files changed, 6 insertions(+), 36 deletions(-)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 8d54f3047768..25ffb486fac9 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1154,43 +1154,17 @@ static void packet_increment_head(struct packet_ring_buffer *buff)
static void packet_inc_pending(struct packet_ring_buffer *rb)
{
- this_cpu_inc(*rb->pending_refcnt);
+ atomic_inc(&rb->pending_refcnt);
}
static void packet_dec_pending(struct packet_ring_buffer *rb)
{
- this_cpu_dec(*rb->pending_refcnt);
+ atomic_dec(&rb->pending_refcnt);
}
static unsigned int packet_read_pending(const struct packet_ring_buffer *rb)
{
- unsigned int refcnt = 0;
- int cpu;
-
- /* We don't use pending refcount in rx_ring. */
- if (rb->pending_refcnt == NULL)
- return 0;
-
- for_each_possible_cpu(cpu)
- refcnt += *per_cpu_ptr(rb->pending_refcnt, cpu);
-
- return refcnt;
-}
-
-static int packet_alloc_pending(struct packet_sock *po)
-{
- po->rx_ring.pending_refcnt = NULL;
-
- po->tx_ring.pending_refcnt = alloc_percpu(unsigned int);
- if (unlikely(po->tx_ring.pending_refcnt == NULL))
- return -ENOBUFS;
-
- return 0;
-}
-
-static void packet_free_pending(struct packet_sock *po)
-{
- free_percpu(po->tx_ring.pending_refcnt);
+ atomic_read(&rb->pending_refcnt);
}
#define ROOM_POW_OFF 2
@@ -3046,7 +3020,6 @@ static int packet_release(struct socket *sock)
/* Purge queues */
skb_queue_purge(&sk->sk_receive_queue);
- packet_free_pending(po);
sk_refcnt_debug_release(sk);
sock_put(sk);
@@ -3236,9 +3209,8 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
po->num = proto;
po->xmit = dev_queue_xmit;
- err = packet_alloc_pending(po);
- if (err)
- goto out2;
+ atomic_set(&po->tx_ring.pending_refcnt,0);
+ atomic_set(&po->rx_ring.pending_refcnt,0);
packet_cached_dev_reset(po);
@@ -3273,8 +3245,6 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
preempt_enable();
return 0;
-out2:
- sk_free(sk);
out:
return err;
}
diff --git a/net/packet/internal.h b/net/packet/internal.h
index 82fb2b10f790..b0fdb54bb91b 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -68,7 +68,7 @@ struct packet_ring_buffer {
unsigned int pg_vec_pages;
unsigned int pg_vec_len;
- unsigned int __percpu *pending_refcnt;
+ atomic_t pending_refcnt;
struct tpacket_kbdq_core prb_bdqc;
};
--
2.21.0
^ permalink raw reply related
* Re: [EXT] [PATCH net-next 03/16] qlge: Deduplicate lbq_buf_size
From: Willem de Bruijn @ 2019-06-28 14:56 UTC (permalink / raw)
To: Benjamin Poirier; +Cc: Manish Chopra, GR-Linux-NIC-Dev, netdev@vger.kernel.org
In-Reply-To: <20190628085713.GB14978@f1>
On Fri, Jun 28, 2019 at 4:57 AM Benjamin Poirier <bpoirier@suse.com> wrote:
>
> On 2019/06/26 11:42, Willem de Bruijn wrote:
> > On Wed, Jun 26, 2019 at 7:37 AM Benjamin Poirier <bpoirier@suse.com> wrote:
> > >
> > > On 2019/06/26 09:24, Manish Chopra wrote:
> > > > > -----Original Message-----
> > > > > From: Benjamin Poirier <bpoirier@suse.com>
> > > > > Sent: Monday, June 17, 2019 1:19 PM
> > > > > To: Manish Chopra <manishc@marvell.com>; GR-Linux-NIC-Dev <GR-Linux-
> > > > > NIC-Dev@marvell.com>; netdev@vger.kernel.org
> > > > > Subject: [EXT] [PATCH net-next 03/16] qlge: Deduplicate lbq_buf_size
> > > > >
> > > > > External Email
> > > > >
> > > > > ----------------------------------------------------------------------
> > > > > lbq_buf_size is duplicated to every rx_ring structure whereas lbq_buf_order is
> > > > > present once in the ql_adapter structure. All rings use the same buf size, keep
> > > > > only one copy of it. Also factor out the calculation of lbq_buf_size instead of
> > > > > having two copies.
> > > > >
> > > > > Signed-off-by: Benjamin Poirier <bpoirier@suse.com>
> > > > > ---
> > > [...]
> > > >
> > > > Not sure if this change is really required, I think fields relevant to rx_ring should be present in the rx_ring structure.
> > > > There are various other fields like "lbq_len" and "lbq_size" which would be same for all rx rings but still under the relevant rx_ring structure.
> >
> > The one argument against deduplicating might be if the original fields
> > are in a hot cacheline and the new location adds a cacheline access to
> > a hot path. Not sure if that is relevant here. But maybe something to
> > double check.
> >
>
> Thanks for the hint. I didn't check before because my hunch was that
> this driver is not near that level of optimization but I checked now and
> got the following results.
Thanks for the data. I didn't mean to ask you to do a lot of extra work.
Sorry if it resulted in that.
Fully agreed on your point about optimization (see also.. that 784B
struct with holes). I support the patch and meant to argue against the
previous response: this cleanup makes sense to me, just take a second
look at struct layout. To be more crystal clear:
Acked-by: Willem de Bruijn <willemb@google.com>
^ permalink raw reply
* [net-next 1/1] tipc: embed jiffies in macro TIPC_BC_RETR_LIM
From: Jon Maloy @ 2019-06-28 15:06 UTC (permalink / raw)
To: davem, netdev
Cc: gordan.mihaljevic, tung.q.nguyen, hoang.h.le, jon.maloy,
canh.d.luu, ying.xue, tipc-discussion
The macro TIPC_BC_RETR_LIM is always used in combination with 'jiffies',
so we can just as well perform the addition in the macro itself. This
way, we get a few shorter code lines and one less line break.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
---
net/tipc/link.c | 9 ++++-----
1 file changed, 4 insertions(+), 5 deletions(-)
diff --git a/net/tipc/link.c b/net/tipc/link.c
index f8bf63b..66d3a07 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -207,7 +207,7 @@ enum {
BC_NACK_SND_SUPPRESS,
};
-#define TIPC_BC_RETR_LIM msecs_to_jiffies(10) /* [ms] */
+#define TIPC_BC_RETR_LIM (jiffies + msecs_to_jiffies(10))
#define TIPC_UC_RETR_TIME (jiffies + msecs_to_jiffies(1))
/*
@@ -976,8 +976,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
__skb_queue_tail(transmq, skb);
/* next retransmit attempt */
if (link_is_bc_sndlink(l))
- TIPC_SKB_CB(skb)->nxt_retr =
- jiffies + TIPC_BC_RETR_LIM;
+ TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM;
__skb_queue_tail(xmitq, _skb);
TIPC_SKB_CB(skb)->ackers = l->ackers;
l->rcv_unacked = 0;
@@ -1027,7 +1026,7 @@ static void tipc_link_advance_backlog(struct tipc_link *l,
__skb_queue_tail(&l->transmq, skb);
/* next retransmit attempt */
if (link_is_bc_sndlink(l))
- TIPC_SKB_CB(skb)->nxt_retr = jiffies + TIPC_BC_RETR_LIM;
+ TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM;
__skb_queue_tail(xmitq, _skb);
TIPC_SKB_CB(skb)->ackers = l->ackers;
@@ -1123,7 +1122,7 @@ static int tipc_link_bc_retrans(struct tipc_link *l, struct tipc_link *r,
if (link_is_bc_sndlink(l)) {
if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr))
continue;
- TIPC_SKB_CB(skb)->nxt_retr = jiffies + TIPC_BC_RETR_LIM;
+ TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM;
}
_skb = __pskb_copy(skb, LL_MAX_HEADER + MIN_H_SIZE, GFP_ATOMIC);
if (!_skb)
--
2.1.4
^ permalink raw reply related
* Re: [PATCH net-next] af_packet: convert pending frame counter to atomic_t
From: Willem de Bruijn @ 2019-06-28 15:15 UTC (permalink / raw)
To: Neil Horman
Cc: Network Development, David S. Miller, Willem de Bruijn,
Daniel Borkmann
In-Reply-To: <20190628145206.13871-1-nhorman@tuxdriver.com>
On Fri, Jun 28, 2019 at 10:53 AM Neil Horman <nhorman@tuxdriver.com> wrote:
>
> The AF_PACKET protocol, when running as a memory mapped socket uses a
> pending frame counter to track the number of skbs in flight during
> transmission. It is incremented during the sendmsg call (via
> tpacket_snd), and decremented (possibly asynchronously) in the skb
> desructor during skb_free.
>
> The counter is currently implemented as a percpu variable for each open
> socket, but for reads (via packet_read_pending), we iterate over every
> cpu variable, accumulating the total pending count.
>
> Given that the socket transmit path is an exclusive path (locked via the
> pg_vec_lock mutex), we do not have the ability to increment this counter
> on multiple cpus in parallel. This implementation also seems to have
> the potential to be broken, in that, should an skb be freed on a cpu
> other than the one that it was initially transmitted on, we may
> decrement a counter that was not initially incremented, leading to
> underflow.
>
> As such, adjust the packet socket struct to convert the per-cpu counter
> to an atomic_t variable (to enforce consistency between the send path
> and the skb free path). This saves us some space in the packet_sock
> structure, prevents the possibility of underflow, and should reduce the
> run time of packet_read_pending, as we only need to read a single
> variable, instead of having to loop over every available cpu variable
> instance.
>
> Tested by myself by running a small program which sends frames via
> AF_PACKET on multiple cpus in parallel, with good results.
>
> Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
> CC: "David S. Miller" <davem@davemloft.net>
> CC: Willem de Bruijn <willemb@google.com>
> ---
This essentially is a revert of commit b013840810c2 ("packet: use
percpu mmap tx frame pending refcount"). That has some benchmark
numbers and also discusses the overflow issue.
I think more interesting would be to eschew the counter when
MSG_DONTWAIT, as it is only used to know when to exit the loop if
need_wait.
But, IMHO packet sockets are deprecated in favor of AF_XDP and
should be limited to bug fixes at this point.
> net/packet/af_packet.c | 40 +++++-----------------------------------
> net/packet/internal.h | 2 +-
> 2 files changed, 6 insertions(+), 36 deletions(-)
>
> diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
> index 8d54f3047768..25ffb486fac9 100644
> --- a/net/packet/af_packet.c
> +++ b/net/packet/af_packet.c
> @@ -1154,43 +1154,17 @@ static void packet_increment_head(struct packet_ring_buffer *buff)
>
> static void packet_inc_pending(struct packet_ring_buffer *rb)
> {
> - this_cpu_inc(*rb->pending_refcnt);
> + atomic_inc(&rb->pending_refcnt);
> }
If making this change, can also remove these helper functions. The
layer of indirection just hinders readability.
^ permalink raw reply
* Re: WARNING in is_bpf_text_address
From: Bart Van Assche @ 2019-06-28 15:17 UTC (permalink / raw)
To: syzbot, akpm, ast, bpf, daniel, davem, hawk, jakub.kicinski,
johannes.berg, johannes, john.fastabend, kafai, linux-kernel,
longman, mingo, netdev, paulmck, peterz, songliubraving,
syzkaller-bugs, tglx, tj, torvalds, will.deacon, xdp-newbies, yhs,
Dmitry Vyukov
In-Reply-To: <000000000000104b00058c61eda4@google.com>
On 6/28/19 6:05 AM, syzbot wrote:
> syzbot has bisected this bug to:
>
> commit a0b0fd53e1e67639b303b15939b9c653dbe7a8c4
> Author: Bart Van Assche <bvanassche@acm.org>
> Date: Thu Feb 14 23:00:46 2019 +0000
>
> locking/lockdep: Free lock classes that are no longer in use
>
> bisection log: https://syzkaller.appspot.com/x/bisect.txt?x=152f6a9da00000
> start commit: abf02e29 Merge tag 'pm-5.2-rc6' of
> git://git.kernel.org/pu..
> git tree: upstream
> final crash: https://syzkaller.appspot.com/x/report.txt?x=172f6a9da00000
> console output: https://syzkaller.appspot.com/x/log.txt?x=132f6a9da00000
> kernel config: https://syzkaller.appspot.com/x/.config?x=28ec3437a5394ee0
> dashboard link:
> https://syzkaller.appspot.com/bug?extid=bd3bba6ff3fcea7a6ec6
> syz repro: https://syzkaller.appspot.com/x/repro.syz?x=14ae828aa00000
>
> Reported-by: syzbot+bd3bba6ff3fcea7a6ec6@syzkaller.appspotmail.com
> Fixes: a0b0fd53e1e6 ("locking/lockdep: Free lock classes that are no
> longer in use")
>
> For information about bisection process see:
> https://goo.gl/tpsmEJ#bisection
Dmitry, this bisection result does not make any sense to me. Can I mark
this bisection result myself as invalid?
Thanks,
Bart.
^ permalink raw reply
* [PATCH v2 bpf-next 0/4] capture integers in BTF type info for map defs
From: Andrii Nakryiko @ 2019-06-28 15:25 UTC (permalink / raw)
To: andrii.nakryiko, ast, daniel, bpf, netdev, songliubraving; +Cc: Andrii Nakryiko
This patch set implements an update to how BTF-defined maps are specified. The
change is in how integer attributes, e.g., type, max_entries, map_flags, are
specified: now they are captured as part of map definition struct's BTF type
information (using array dimension), eliminating the need for compile-time
data initialization and keeping all the metadata in one place.
All existing selftests that were using BTF-defined maps are updated, along
with some other selftests, that were switched to new syntax.
v1->v2:
- split bpf_helpers.h change from libbpf change (Song).
Andrii Nakryiko (4):
libbpf: capture value in BTF type info for BTF-defined map defs
selftests/bpf: add __int and __type macro for BTF-defined maps
selftests/bpf: convert selftests using BTF-defined maps to new syntax
selftests/bpf: convert legacy BPF maps to BTF-defined ones
tools/lib/bpf/libbpf.c | 58 +++++----
tools/testing/selftests/bpf/bpf_helpers.h | 3 +
tools/testing/selftests/bpf/progs/bpf_flow.c | 28 ++---
.../selftests/bpf/progs/get_cgroup_id_kern.c | 26 ++---
.../testing/selftests/bpf/progs/netcnt_prog.c | 20 ++--
tools/testing/selftests/bpf/progs/pyperf.h | 90 +++++++-------
.../selftests/bpf/progs/sample_map_ret0.c | 24 ++--
.../selftests/bpf/progs/socket_cookie_prog.c | 13 +--
.../bpf/progs/sockmap_verdict_prog.c | 48 ++++----
.../testing/selftests/bpf/progs/strobemeta.h | 68 +++++------
.../selftests/bpf/progs/test_btf_newkv.c | 13 +--
.../bpf/progs/test_get_stack_rawtp.c | 39 +++----
.../selftests/bpf/progs/test_global_data.c | 37 +++---
tools/testing/selftests/bpf/progs/test_l4lb.c | 65 ++++-------
.../selftests/bpf/progs/test_l4lb_noinline.c | 65 ++++-------
.../selftests/bpf/progs/test_map_in_map.c | 30 ++---
.../selftests/bpf/progs/test_map_lock.c | 26 ++---
.../testing/selftests/bpf/progs/test_obj_id.c | 12 +-
.../bpf/progs/test_select_reuseport_kern.c | 67 ++++-------
.../bpf/progs/test_send_signal_kern.c | 26 ++---
.../bpf/progs/test_sock_fields_kern.c | 78 +++++--------
.../selftests/bpf/progs/test_spin_lock.c | 36 +++---
.../bpf/progs/test_stacktrace_build_id.c | 55 ++++-----
.../selftests/bpf/progs/test_stacktrace_map.c | 52 +++------
.../selftests/bpf/progs/test_tcp_estats.c | 13 +--
.../selftests/bpf/progs/test_tcpbpf_kern.c | 26 ++---
.../selftests/bpf/progs/test_tcpnotify_kern.c | 28 ++---
tools/testing/selftests/bpf/progs/test_xdp.c | 26 ++---
.../selftests/bpf/progs/test_xdp_loop.c | 26 ++---
.../selftests/bpf/progs/test_xdp_noinline.c | 81 +++++--------
.../selftests/bpf/progs/xdp_redirect_map.c | 12 +-
.../testing/selftests/bpf/progs/xdping_kern.c | 12 +-
.../selftests/bpf/test_queue_stack_map.h | 30 ++---
.../testing/selftests/bpf/test_sockmap_kern.h | 110 +++++++++---------
34 files changed, 571 insertions(+), 772 deletions(-)
--
2.17.1
^ permalink raw reply
* [PATCH v2 bpf-next 1/4] libbpf: capture value in BTF type info for BTF-defined map defs
From: Andrii Nakryiko @ 2019-06-28 15:25 UTC (permalink / raw)
To: andrii.nakryiko, ast, daniel, bpf, netdev, songliubraving; +Cc: Andrii Nakryiko
In-Reply-To: <20190628152539.3014719-1-andriin@fb.com>
Change BTF-defined map definitions to capture compile-time integer
values as part of BTF type definition, to avoid split of key/value type
information and actual type/size/flags initialization for maps.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
---
tools/lib/bpf/libbpf.c | 58 ++++++++++++++++++++----------------------
1 file changed, 28 insertions(+), 30 deletions(-)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 6e6ebef11ba3..9e099ecb2c2b 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1028,40 +1028,40 @@ static const struct btf_type *skip_mods_and_typedefs(const struct btf *btf,
}
}
-static bool get_map_field_int(const char *map_name,
- const struct btf *btf,
+/*
+ * Fetch integer attribute of BTF map definition. Such attributes are
+ * represented using a pointer to an array, in which dimensionality of array
+ * encodes specified integer value. E.g., int (*type)[BPF_MAP_TYPE_ARRAY];
+ * encodes `type => BPF_MAP_TYPE_ARRAY` key/value pair completely using BTF
+ * type definition, while using only sizeof(void *) space in ELF data section.
+ */
+static bool get_map_field_int(const char *map_name, const struct btf *btf,
const struct btf_type *def,
- const struct btf_member *m,
- const void *data, __u32 *res) {
+ const struct btf_member *m, __u32 *res) {
const struct btf_type *t = skip_mods_and_typedefs(btf, m->type);
const char *name = btf__name_by_offset(btf, m->name_off);
- __u32 int_info = *(const __u32 *)(const void *)(t + 1);
+ const struct btf_array *arr_info;
+ const struct btf_type *arr_t;
- if (BTF_INFO_KIND(t->info) != BTF_KIND_INT) {
- pr_warning("map '%s': attr '%s': expected INT, got %u.\n",
+ if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) {
+ pr_warning("map '%s': attr '%s': expected PTR, got %u.\n",
map_name, name, BTF_INFO_KIND(t->info));
return false;
}
- if (t->size != 4 || BTF_INT_BITS(int_info) != 32 ||
- BTF_INT_OFFSET(int_info)) {
- pr_warning("map '%s': attr '%s': expected 32-bit non-bitfield integer, "
- "got %u-byte (%d-bit) one with bit offset %d.\n",
- map_name, name, t->size, BTF_INT_BITS(int_info),
- BTF_INT_OFFSET(int_info));
- return false;
- }
- if (BTF_INFO_KFLAG(def->info) && BTF_MEMBER_BITFIELD_SIZE(m->offset)) {
- pr_warning("map '%s': attr '%s': bitfield is not supported.\n",
- map_name, name);
+
+ arr_t = btf__type_by_id(btf, t->type);
+ if (!arr_t) {
+ pr_warning("map '%s': attr '%s': type [%u] not found.\n",
+ map_name, name, t->type);
return false;
}
- if (m->offset % 32) {
- pr_warning("map '%s': attr '%s': unaligned fields are not supported.\n",
- map_name, name);
+ if (BTF_INFO_KIND(arr_t->info) != BTF_KIND_ARRAY) {
+ pr_warning("map '%s': attr '%s': expected ARRAY, got %u.\n",
+ map_name, name, BTF_INFO_KIND(arr_t->info));
return false;
}
-
- *res = *(const __u32 *)(data + m->offset / 8);
+ arr_info = (const void *)(arr_t + 1);
+ *res = arr_info->nelems;
return true;
}
@@ -1074,7 +1074,6 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
const struct btf_var_secinfo *vi;
const struct btf_var *var_extra;
const struct btf_member *m;
- const void *def_data;
const char *map_name;
struct bpf_map *map;
int vlen, i;
@@ -1131,7 +1130,6 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
pr_debug("map '%s': at sec_idx %d, offset %zu.\n",
map_name, map->sec_idx, map->sec_offset);
- def_data = data->d_buf + vi->offset;
vlen = BTF_INFO_VLEN(def->info);
m = (const void *)(def + 1);
for (i = 0; i < vlen; i++, m++) {
@@ -1144,19 +1142,19 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
}
if (strcmp(name, "type") == 0) {
if (!get_map_field_int(map_name, obj->btf, def, m,
- def_data, &map->def.type))
+ &map->def.type))
return -EINVAL;
pr_debug("map '%s': found type = %u.\n",
map_name, map->def.type);
} else if (strcmp(name, "max_entries") == 0) {
if (!get_map_field_int(map_name, obj->btf, def, m,
- def_data, &map->def.max_entries))
+ &map->def.max_entries))
return -EINVAL;
pr_debug("map '%s': found max_entries = %u.\n",
map_name, map->def.max_entries);
} else if (strcmp(name, "map_flags") == 0) {
if (!get_map_field_int(map_name, obj->btf, def, m,
- def_data, &map->def.map_flags))
+ &map->def.map_flags))
return -EINVAL;
pr_debug("map '%s': found map_flags = %u.\n",
map_name, map->def.map_flags);
@@ -1164,7 +1162,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
__u32 sz;
if (!get_map_field_int(map_name, obj->btf, def, m,
- def_data, &sz))
+ &sz))
return -EINVAL;
pr_debug("map '%s': found key_size = %u.\n",
map_name, sz);
@@ -1207,7 +1205,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
__u32 sz;
if (!get_map_field_int(map_name, obj->btf, def, m,
- def_data, &sz))
+ &sz))
return -EINVAL;
pr_debug("map '%s': found value_size = %u.\n",
map_name, sz);
--
2.17.1
^ permalink raw reply related
* [PATCH v2 bpf-next 2/4] selftests/bpf: add __int and __type macro for BTF-defined maps
From: Andrii Nakryiko @ 2019-06-28 15:25 UTC (permalink / raw)
To: andrii.nakryiko, ast, daniel, bpf, netdev, songliubraving; +Cc: Andrii Nakryiko
In-Reply-To: <20190628152539.3014719-1-andriin@fb.com>
Add simple __int and __type macro that hide details of how type and
integer values are captured in BTF-defined maps.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
---
tools/testing/selftests/bpf/bpf_helpers.h | 3 +++
1 file changed, 3 insertions(+)
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 1a5b1accf091..aa5ddf58c088 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -8,6 +8,9 @@
*/
#define SEC(NAME) __attribute__((section(NAME), used))
+#define __int(name, val) int (*name)[val]
+#define __type(name, val) val *name
+
/* helper macro to print out debug messages */
#define bpf_printk(fmt, ...) \
({ \
--
2.17.1
^ permalink raw reply related
* [PATCH v2 bpf-next 3/4] selftests/bpf: convert selftests using BTF-defined maps to new syntax
From: Andrii Nakryiko @ 2019-06-28 15:25 UTC (permalink / raw)
To: andrii.nakryiko, ast, daniel, bpf, netdev, songliubraving; +Cc: Andrii Nakryiko
In-Reply-To: <20190628152539.3014719-1-andriin@fb.com>
Convert all the existing selftests that are already using BTF-defined
maps to use new syntax (with no static data initialization).
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
---
tools/testing/selftests/bpf/progs/bpf_flow.c | 28 +++----
.../testing/selftests/bpf/progs/netcnt_prog.c | 20 ++---
.../selftests/bpf/progs/socket_cookie_prog.c | 13 ++-
.../selftests/bpf/progs/test_btf_newkv.c | 13 ++-
.../bpf/progs/test_get_stack_rawtp.c | 39 ++++-----
.../selftests/bpf/progs/test_global_data.c | 37 ++++-----
tools/testing/selftests/bpf/progs/test_l4lb.c | 65 ++++++---------
.../selftests/bpf/progs/test_l4lb_noinline.c | 65 ++++++---------
.../selftests/bpf/progs/test_map_lock.c | 26 +++---
.../bpf/progs/test_select_reuseport_kern.c | 67 ++++++---------
.../bpf/progs/test_send_signal_kern.c | 26 +++---
.../bpf/progs/test_sock_fields_kern.c | 78 +++++++-----------
.../selftests/bpf/progs/test_spin_lock.c | 36 ++++-----
.../bpf/progs/test_stacktrace_build_id.c | 55 +++++--------
.../selftests/bpf/progs/test_stacktrace_map.c | 52 +++++-------
.../selftests/bpf/progs/test_tcp_estats.c | 13 ++-
.../selftests/bpf/progs/test_tcpbpf_kern.c | 26 +++---
.../selftests/bpf/progs/test_tcpnotify_kern.c | 28 +++----
tools/testing/selftests/bpf/progs/test_xdp.c | 26 +++---
.../selftests/bpf/progs/test_xdp_noinline.c | 81 +++++++------------
20 files changed, 300 insertions(+), 494 deletions(-)
diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c
index 849f42e548b5..a5564a90525d 100644
--- a/tools/testing/selftests/bpf/progs/bpf_flow.c
+++ b/tools/testing/selftests/bpf/progs/bpf_flow.c
@@ -58,26 +58,18 @@ struct frag_hdr {
};
struct {
- __u32 type;
- __u32 max_entries;
- __u32 key_size;
- __u32 value_size;
-} jmp_table SEC(".maps") = {
- .type = BPF_MAP_TYPE_PROG_ARRAY,
- .max_entries = 8,
- .key_size = sizeof(__u32),
- .value_size = sizeof(__u32),
-};
+ __int(type, BPF_MAP_TYPE_PROG_ARRAY);
+ __int(max_entries, 8);
+ __int(key_size, sizeof(__u32));
+ __int(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- struct bpf_flow_keys *value;
-} last_dissection SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 1,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 1);
+ __type(key, __u32);
+ __type(value, struct bpf_flow_keys);
+} last_dissection SEC(".maps");
static __always_inline int export_flow_keys(struct bpf_flow_keys *keys,
int ret)
diff --git a/tools/testing/selftests/bpf/progs/netcnt_prog.c b/tools/testing/selftests/bpf/progs/netcnt_prog.c
index a25c82a5b7c8..31afe01ca52e 100644
--- a/tools/testing/selftests/bpf/progs/netcnt_prog.c
+++ b/tools/testing/selftests/bpf/progs/netcnt_prog.c
@@ -11,20 +11,16 @@
#define NS_PER_SEC 1000000000
struct {
- __u32 type;
- struct bpf_cgroup_storage_key *key;
- struct percpu_net_cnt *value;
-} percpu_netcnt SEC(".maps") = {
- .type = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
-};
+ __int(type, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE);
+ __type(key, struct bpf_cgroup_storage_key);
+ __type(value, struct percpu_net_cnt);
+} percpu_netcnt SEC(".maps");
struct {
- __u32 type;
- struct bpf_cgroup_storage_key *key;
- struct net_cnt *value;
-} netcnt SEC(".maps") = {
- .type = BPF_MAP_TYPE_CGROUP_STORAGE,
-};
+ __int(type, BPF_MAP_TYPE_CGROUP_STORAGE);
+ __type(key, struct bpf_cgroup_storage_key);
+ __type(value, struct net_cnt);
+} netcnt SEC(".maps");
SEC("cgroup/skb")
int bpf_nextcnt(struct __sk_buff *skb)
diff --git a/tools/testing/selftests/bpf/progs/socket_cookie_prog.c b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c
index 6aabb681fb9a..6cd0a9457175 100644
--- a/tools/testing/selftests/bpf/progs/socket_cookie_prog.c
+++ b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c
@@ -13,14 +13,11 @@ struct socket_cookie {
};
struct {
- __u32 type;
- __u32 map_flags;
- int *key;
- struct socket_cookie *value;
-} socket_cookies SEC(".maps") = {
- .type = BPF_MAP_TYPE_SK_STORAGE,
- .map_flags = BPF_F_NO_PREALLOC,
-};
+ __int(type, BPF_MAP_TYPE_SK_STORAGE);
+ __int(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, struct socket_cookie);
+} socket_cookies SEC(".maps");
SEC("cgroup/connect6")
int set_cookie(struct bpf_sock_addr *ctx)
diff --git a/tools/testing/selftests/bpf/progs/test_btf_newkv.c b/tools/testing/selftests/bpf/progs/test_btf_newkv.c
index 28c16bb583b6..572ee1050e61 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_newkv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c
@@ -21,14 +21,11 @@ struct bpf_map_def SEC("maps") btf_map_legacy = {
BPF_ANNOTATE_KV_PAIR(btf_map_legacy, int, struct ipv_counts);
struct {
- int *key;
- struct ipv_counts *value;
- unsigned int type;
- unsigned int max_entries;
-} btf_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 4,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 4);
+ __type(key, int);
+ __type(value, struct ipv_counts);
+} btf_map SEC(".maps");
struct dummy_tracepoint_args {
unsigned long long pad;
diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
index aaa6ec250e15..1bf73cf264b8 100644
--- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
+++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
@@ -16,26 +16,18 @@ struct stack_trace_t {
};
struct {
- __u32 type;
- __u32 max_entries;
- __u32 key_size;
- __u32 value_size;
-} perfmap SEC(".maps") = {
- .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
- .max_entries = 2,
- .key_size = sizeof(int),
- .value_size = sizeof(__u32),
-};
+ __int(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+ __int(max_entries, 2);
+ __int(key_size, sizeof(int));
+ __int(value_size, sizeof(__u32));
+} perfmap SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- struct stack_trace_t *value;
-} stackdata_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_PERCPU_ARRAY,
- .max_entries = 1,
-};
+ __int(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __int(max_entries, 1);
+ __type(key, __u32);
+ __type(value, struct stack_trace_t);
+} stackdata_map SEC(".maps");
/* Allocate per-cpu space twice the needed. For the code below
* usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK);
@@ -56,14 +48,11 @@ struct {
* This is an acceptable workaround since there is one entry here.
*/
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
+ __int(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __int(max_entries, 1);
+ __type(key, __u32);
__u64 (*value)[2 * MAX_STACK_RAWTP];
-} rawdata_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_PERCPU_ARRAY,
- .max_entries = 1,
-};
+} rawdata_map SEC(".maps");
SEC("tracepoint/raw_syscalls/sys_enter")
int bpf_prog1(void *ctx)
diff --git a/tools/testing/selftests/bpf/progs/test_global_data.c b/tools/testing/selftests/bpf/progs/test_global_data.c
index 866cc7ddbe43..aee3a3167d16 100644
--- a/tools/testing/selftests/bpf/progs/test_global_data.c
+++ b/tools/testing/selftests/bpf/progs/test_global_data.c
@@ -8,24 +8,18 @@
#include "bpf_helpers.h"
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- __u64 *value;
-} result_number SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 11,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 11);
+ __type(key, __u32);
+ __type(value, __u64);
+} result_number SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 5);
+ __type(key, __u32);
const char (*value)[32];
-} result_string SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 5,
-};
+} result_string SEC(".maps");
struct foo {
__u8 a;
@@ -34,14 +28,11 @@ struct foo {
};
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- struct foo *value;
-} result_struct SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 5,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 5);
+ __type(key, __u32);
+ __type(value, struct foo);
+} result_struct SEC(".maps");
/* Relocation tests for __u64s. */
static __u64 num0;
diff --git a/tools/testing/selftests/bpf/progs/test_l4lb.c b/tools/testing/selftests/bpf/progs/test_l4lb.c
index 848cbb90f581..6d6c5659f147 100644
--- a/tools/testing/selftests/bpf/progs/test_l4lb.c
+++ b/tools/testing/selftests/bpf/progs/test_l4lb.c
@@ -170,54 +170,39 @@ struct eth_hdr {
};
struct {
- __u32 type;
- __u32 max_entries;
- struct vip *key;
- struct vip_meta *value;
-} vip_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_HASH,
- .max_entries = MAX_VIPS,
-};
+ __int(type, BPF_MAP_TYPE_HASH);
+ __int(max_entries, MAX_VIPS);
+ __type(key, struct vip);
+ __type(value, struct vip_meta);
+} vip_map SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- __u32 *value;
-} ch_rings SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = CH_RINGS_SIZE,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, CH_RINGS_SIZE);
+ __type(key, __u32);
+ __type(value, __u32);
+} ch_rings SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- struct real_definition *value;
-} reals SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = MAX_REALS,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, MAX_REALS);
+ __type(key, __u32);
+ __type(value, struct real_definition);
+} reals SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- struct vip_stats *value;
-} stats SEC(".maps") = {
- .type = BPF_MAP_TYPE_PERCPU_ARRAY,
- .max_entries = MAX_VIPS,
-};
+ __int(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __int(max_entries, MAX_VIPS);
+ __type(key, __u32);
+ __type(value, struct vip_stats);
+} stats SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- struct ctl_value *value;
-} ctl_array SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = CTL_MAP_SIZE,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, CTL_MAP_SIZE);
+ __type(key, __u32);
+ __type(value, struct ctl_value);
+} ctl_array SEC(".maps");
static __always_inline __u32 get_packet_hash(struct packet_description *pckt,
bool ipv6)
diff --git a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c
index c63ecf3ca573..1780e92955be 100644
--- a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c
+++ b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c
@@ -166,54 +166,39 @@ struct eth_hdr {
};
struct {
- __u32 type;
- __u32 max_entries;
- struct vip *key;
- struct vip_meta *value;
-} vip_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_HASH,
- .max_entries = MAX_VIPS,
-};
+ __int(type, BPF_MAP_TYPE_HASH);
+ __int(max_entries, MAX_VIPS);
+ __type(key, struct vip);
+ __type(value, struct vip_meta);
+} vip_map SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- __u32 *value;
-} ch_rings SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = CH_RINGS_SIZE,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, CH_RINGS_SIZE);
+ __type(key, __u32);
+ __type(value, __u32);
+} ch_rings SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- struct real_definition *value;
-} reals SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = MAX_REALS,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, MAX_REALS);
+ __type(key, __u32);
+ __type(value, struct real_definition);
+} reals SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- struct vip_stats *value;
-} stats SEC(".maps") = {
- .type = BPF_MAP_TYPE_PERCPU_ARRAY,
- .max_entries = MAX_VIPS,
-};
+ __int(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __int(max_entries, MAX_VIPS);
+ __type(key, __u32);
+ __type(value, struct vip_stats);
+} stats SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- struct ctl_value *value;
-} ctl_array SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = CTL_MAP_SIZE,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, CTL_MAP_SIZE);
+ __type(key, __u32);
+ __type(value, struct ctl_value);
+} ctl_array SEC(".maps");
static __u32 get_packet_hash(struct packet_description *pckt,
bool ipv6)
diff --git a/tools/testing/selftests/bpf/progs/test_map_lock.c b/tools/testing/selftests/bpf/progs/test_map_lock.c
index 40d9c2853393..7cfd21477d29 100644
--- a/tools/testing/selftests/bpf/progs/test_map_lock.c
+++ b/tools/testing/selftests/bpf/progs/test_map_lock.c
@@ -12,14 +12,11 @@ struct hmap_elem {
};
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- struct hmap_elem *value;
-} hash_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_HASH,
- .max_entries = 1,
-};
+ __int(type, BPF_MAP_TYPE_HASH);
+ __int(max_entries, 1);
+ __type(key, __u32);
+ __type(value, struct hmap_elem);
+} hash_map SEC(".maps");
struct array_elem {
struct bpf_spin_lock lock;
@@ -27,14 +24,11 @@ struct array_elem {
};
struct {
- __u32 type;
- __u32 max_entries;
- int *key;
- struct array_elem *value;
-} array_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 1,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 1);
+ __type(key, int);
+ __type(value, struct array_elem);
+} array_map SEC(".maps");
SEC("map_lock_demo")
int bpf_map_lock_test(struct __sk_buff *skb)
diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
index 435a9527733e..4e7bca8c8239 100644
--- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
@@ -22,56 +22,39 @@ int _version SEC("version") = 1;
#endif
struct {
- __u32 type;
- __u32 max_entries;
- __u32 key_size;
- __u32 value_size;
-} outer_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
- .max_entries = 1,
- .key_size = sizeof(__u32),
- .value_size = sizeof(__u32),
-};
+ __int(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+ __int(max_entries, 1);
+ __int(key_size, sizeof(__u32));
+ __int(value_size, sizeof(__u32));
+} outer_map SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- __u32 *value;
-} result_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = NR_RESULTS,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, NR_RESULTS);
+ __type(key, __u32);
+ __type(value, __u32);
+} result_map SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- int *value;
-} tmp_index_ovr_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 1,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 1);
+ __type(key, __u32);
+ __type(value, int);
+} tmp_index_ovr_map SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- __u32 *value;
-} linum_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 1,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 1);
+ __type(key, __u32);
+ __type(value, __u32);
+} linum_map SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- struct data_check *value;
-} data_check_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 1,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 1);
+ __type(key, __u32);
+ __type(value, struct data_check);
+} data_check_map SEC(".maps");
#define GOTO_DONE(_result) ({ \
result = (_result); \
diff --git a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c
index 6ac68be5d68b..230c6c7e0928 100644
--- a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c
@@ -5,24 +5,18 @@
#include "bpf_helpers.h"
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- __u64 *value;
-} info_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 1,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 1);
+ __type(key, __u32);
+ __type(value, __u64);
+} info_map SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- __u64 *value;
-} status_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 1,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 1);
+ __type(key, __u32);
+ __type(value, __u64);
+} status_map SEC(".maps");
SEC("send_signal_demo")
int bpf_send_signal_test(void *ctx)
diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
index c3d383d650cb..472b7e637a7a 100644
--- a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
@@ -28,44 +28,32 @@ enum bpf_linum_array_idx {
};
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- struct sockaddr_in6 *value;
-} addr_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = __NR_BPF_ADDR_ARRAY_IDX,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, __NR_BPF_ADDR_ARRAY_IDX);
+ __type(key, __u32);
+ __type(value, struct sockaddr_in6);
+} addr_map SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- struct bpf_sock *value;
-} sock_result_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = __NR_BPF_RESULT_ARRAY_IDX,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, __NR_BPF_RESULT_ARRAY_IDX);
+ __type(key, __u32);
+ __type(value, struct bpf_sock);
+} sock_result_map SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- struct bpf_tcp_sock *value;
-} tcp_sock_result_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = __NR_BPF_RESULT_ARRAY_IDX,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, __NR_BPF_RESULT_ARRAY_IDX);
+ __type(key, __u32);
+ __type(value, struct bpf_tcp_sock);
+} tcp_sock_result_map SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- __u32 *value;
-} linum_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = __NR_BPF_LINUM_ARRAY_IDX,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, __NR_BPF_LINUM_ARRAY_IDX);
+ __type(key, __u32);
+ __type(value, __u32);
+} linum_map SEC(".maps");
struct bpf_spinlock_cnt {
struct bpf_spin_lock lock;
@@ -73,24 +61,18 @@ struct bpf_spinlock_cnt {
};
struct {
- __u32 type;
- __u32 map_flags;
- int *key;
- struct bpf_spinlock_cnt *value;
-} sk_pkt_out_cnt SEC(".maps") = {
- .type = BPF_MAP_TYPE_SK_STORAGE,
- .map_flags = BPF_F_NO_PREALLOC,
-};
+ __int(type, BPF_MAP_TYPE_SK_STORAGE);
+ __int(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, struct bpf_spinlock_cnt);
+} sk_pkt_out_cnt SEC(".maps");
struct {
- __u32 type;
- __u32 map_flags;
- int *key;
- struct bpf_spinlock_cnt *value;
-} sk_pkt_out_cnt10 SEC(".maps") = {
- .type = BPF_MAP_TYPE_SK_STORAGE,
- .map_flags = BPF_F_NO_PREALLOC,
-};
+ __int(type, BPF_MAP_TYPE_SK_STORAGE);
+ __int(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, struct bpf_spinlock_cnt);
+} sk_pkt_out_cnt10 SEC(".maps");
static bool is_loopback6(__u32 *a6)
{
diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock.c b/tools/testing/selftests/bpf/progs/test_spin_lock.c
index 0a77ae36d981..6341cec3fb49 100644
--- a/tools/testing/selftests/bpf/progs/test_spin_lock.c
+++ b/tools/testing/selftests/bpf/progs/test_spin_lock.c
@@ -11,14 +11,11 @@ struct hmap_elem {
};
struct {
- __u32 type;
- __u32 max_entries;
- int *key;
- struct hmap_elem *value;
-} hmap SEC(".maps") = {
- .type = BPF_MAP_TYPE_HASH,
- .max_entries = 1,
-};
+ __int(type, BPF_MAP_TYPE_HASH);
+ __int(max_entries, 1);
+ __type(key, int);
+ __type(value, struct hmap_elem);
+} hmap SEC(".maps");
struct cls_elem {
struct bpf_spin_lock lock;
@@ -26,12 +23,10 @@ struct cls_elem {
};
struct {
- __u32 type;
- struct bpf_cgroup_storage_key *key;
- struct cls_elem *value;
-} cls_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_CGROUP_STORAGE,
-};
+ __int(type, BPF_MAP_TYPE_CGROUP_STORAGE);
+ __type(key, struct bpf_cgroup_storage_key);
+ __type(value, struct cls_elem);
+} cls_map SEC(".maps");
struct bpf_vqueue {
struct bpf_spin_lock lock;
@@ -42,14 +37,11 @@ struct bpf_vqueue {
};
struct {
- __u32 type;
- __u32 max_entries;
- int *key;
- struct bpf_vqueue *value;
-} vqueue SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 1,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 1);
+ __type(key, int);
+ __type(value, struct bpf_vqueue);
+} vqueue SEC(".maps");
#define CREDIT_PER_NS(delta, rate) (((delta) * rate) >> 20)
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
index fcf2280bb60c..38697b58ae66 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
@@ -9,51 +9,36 @@
#endif
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- __u32 *value;
-} control_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 1,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 1);
+ __type(key, __u32);
+ __type(value, __u32);
+} control_map SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- __u32 *value;
-} stackid_hmap SEC(".maps") = {
- .type = BPF_MAP_TYPE_HASH,
- .max_entries = 16384,
-};
+ __int(type, BPF_MAP_TYPE_HASH);
+ __int(max_entries, 16384);
+ __type(key, __u32);
+ __type(value, __u32);
+} stackid_hmap SEC(".maps");
typedef struct bpf_stack_build_id stack_trace_t[PERF_MAX_STACK_DEPTH];
struct {
- __u32 type;
- __u32 max_entries;
- __u32 map_flags;
- __u32 key_size;
- __u32 value_size;
-} stackmap SEC(".maps") = {
- .type = BPF_MAP_TYPE_STACK_TRACE,
- .max_entries = 128,
- .map_flags = BPF_F_STACK_BUILD_ID,
- .key_size = sizeof(__u32),
- .value_size = sizeof(stack_trace_t),
-};
+ __int(type, BPF_MAP_TYPE_STACK_TRACE);
+ __int(max_entries, 128);
+ __int(map_flags, BPF_F_STACK_BUILD_ID);
+ __int(key_size, sizeof(__u32));
+ __int(value_size, sizeof(stack_trace_t));
+} stackmap SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 128);
+ __type(key, __u32);
/* there seems to be a bug in kernel not handling typedef properly */
struct bpf_stack_build_id (*value)[PERF_MAX_STACK_DEPTH];
-} stack_amap SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 128,
-};
+} stack_amap SEC(".maps");
/* taken from /sys/kernel/debug/tracing/events/random/urandom_read/format */
struct random_urandom_args {
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
index 7ad09adbf648..b3133855adff 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
@@ -9,48 +9,34 @@
#endif
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- __u32 *value;
-} control_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 1,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 1);
+ __type(key, __u32);
+ __type(value, __u32);
+} control_map SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- __u32 *value;
-} stackid_hmap SEC(".maps") = {
- .type = BPF_MAP_TYPE_HASH,
- .max_entries = 16384,
-};
+ __int(type, BPF_MAP_TYPE_HASH);
+ __int(max_entries, 16384);
+ __type(key, __u32);
+ __type(value, __u32);
+} stackid_hmap SEC(".maps");
typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH];
struct {
- __u32 type;
- __u32 max_entries;
- __u32 key_size;
- __u32 value_size;
-} stackmap SEC(".maps") = {
- .type = BPF_MAP_TYPE_STACK_TRACE,
- .max_entries = 16384,
- .key_size = sizeof(__u32),
- .value_size = sizeof(stack_trace_t),
-};
+ __int(type, BPF_MAP_TYPE_STACK_TRACE);
+ __int(max_entries, 16384);
+ __int(key_size, sizeof(__u32));
+ __int(value_size, sizeof(stack_trace_t));
+} stackmap SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 16384);
+ __type(key, __u32);
__u64 (*value)[PERF_MAX_STACK_DEPTH];
-} stack_amap SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 16384,
-};
+} stack_amap SEC(".maps");
/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
struct sched_switch_args {
diff --git a/tools/testing/selftests/bpf/progs/test_tcp_estats.c b/tools/testing/selftests/bpf/progs/test_tcp_estats.c
index df98f7e32832..9b0c1ddb2fdf 100644
--- a/tools/testing/selftests/bpf/progs/test_tcp_estats.c
+++ b/tools/testing/selftests/bpf/progs/test_tcp_estats.c
@@ -149,14 +149,11 @@ struct tcp_estats_basic_event {
};
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- struct tcp_estats_basic_event *value;
-} ev_record_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_HASH,
- .max_entries = 1024,
-};
+ __int(type, BPF_MAP_TYPE_HASH);
+ __int(max_entries, 1024);
+ __type(key, __u32);
+ __type(value, struct tcp_estats_basic_event);
+} ev_record_map SEC(".maps");
struct dummy_tracepoint_args {
unsigned long long pad;
diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
index 38e10c9fd996..229bc249bbb9 100644
--- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
@@ -15,24 +15,18 @@
#include "test_tcpbpf.h"
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- struct tcpbpf_globals *value;
-} global_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 4,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 4);
+ __type(key, __u32);
+ __type(value, struct tcpbpf_globals);
+} global_map SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- int *value;
-} sockopt_results SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 2,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 2);
+ __type(key, __u32);
+ __type(value, int);
+} sockopt_results SEC(".maps");
static inline void update_event_map(int event)
{
diff --git a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
index d073d37d4e27..68ea98f0384f 100644
--- a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
@@ -15,26 +15,18 @@
#include "test_tcpnotify.h"
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- struct tcpnotify_globals *value;
-} global_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 4,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 4);
+ __type(key, __u32);
+ __type(value, struct tcpnotify_globals);
+} global_map SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 key_size;
- __u32 value_size;
-} perf_event_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
- .max_entries = 2,
- .key_size = sizeof(int),
- .value_size = sizeof(__u32),
-};
+ __int(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+ __int(max_entries, 2);
+ __int(key_size, sizeof(int));
+ __int(value_size, sizeof(__u32));
+} perf_event_map SEC(".maps");
int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp.c b/tools/testing/selftests/bpf/progs/test_xdp.c
index ec3d2c1c8cf9..f1a29d7a17fd 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp.c
@@ -23,24 +23,18 @@
int _version SEC("version") = 1;
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- __u64 *value;
-} rxcnt SEC(".maps") = {
- .type = BPF_MAP_TYPE_PERCPU_ARRAY,
- .max_entries = 256,
-};
+ __int(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __int(max_entries, 256);
+ __type(key, __u32);
+ __type(value, __u64);
+} rxcnt SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- struct vip *key;
- struct iptnl_info *value;
-} vip2tnl SEC(".maps") = {
- .type = BPF_MAP_TYPE_HASH,
- .max_entries = MAX_IPTNL_ENTRIES,
-};
+ __int(type, BPF_MAP_TYPE_HASH);
+ __int(max_entries, MAX_IPTNL_ENTRIES);
+ __type(key, struct vip);
+ __type(value, struct iptnl_info);
+} vip2tnl SEC(".maps");
static __always_inline void count_tx(__u32 protocol)
{
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
index d2eddb5553d1..07a3148e44dc 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
@@ -164,66 +164,47 @@ struct lb_stats {
};
struct {
- __u32 type;
- __u32 max_entries;
- struct vip_definition *key;
- struct vip_meta *value;
-} vip_map SEC(".maps") = {
- .type = BPF_MAP_TYPE_HASH,
- .max_entries = 512,
-};
+ __int(type, BPF_MAP_TYPE_HASH);
+ __int(max_entries, 512);
+ __type(key, struct vip_definition);
+ __type(value, struct vip_meta);
+} vip_map SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 map_flags;
- struct flow_key *key;
- struct real_pos_lru *value;
-} lru_cache SEC(".maps") = {
- .type = BPF_MAP_TYPE_LRU_HASH,
- .max_entries = 300,
- .map_flags = 1U << 1,
-};
+ __int(type, BPF_MAP_TYPE_LRU_HASH);
+ __int(max_entries, 300);
+ __int(map_flags, 1U << 1);
+ __type(key, struct flow_key);
+ __type(value, struct real_pos_lru);
+} lru_cache SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- __u32 *value;
-} ch_rings SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 12 * 655,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 12 * 655);
+ __type(key, __u32);
+ __type(value, __u32);
+} ch_rings SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- struct real_definition *value;
-} reals SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 40,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 40);
+ __type(key, __u32);
+ __type(value, struct real_definition);
+} reals SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- struct lb_stats *value;
-} stats SEC(".maps") = {
- .type = BPF_MAP_TYPE_PERCPU_ARRAY,
- .max_entries = 515,
-};
+ __int(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __int(max_entries, 515);
+ __type(key, __u32);
+ __type(value, struct lb_stats);
+} stats SEC(".maps");
struct {
- __u32 type;
- __u32 max_entries;
- __u32 *key;
- struct ctl_value *value;
-} ctl_array SEC(".maps") = {
- .type = BPF_MAP_TYPE_ARRAY,
- .max_entries = 16,
-};
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 16);
+ __type(key, __u32);
+ __type(value, struct ctl_value);
+} ctl_array SEC(".maps");
struct eth_hdr {
unsigned char eth_dest[6];
--
2.17.1
^ permalink raw reply related
* [PATCH v2 bpf-next 4/4] selftests/bpf: convert legacy BPF maps to BTF-defined ones
From: Andrii Nakryiko @ 2019-06-28 15:25 UTC (permalink / raw)
To: andrii.nakryiko, ast, daniel, bpf, netdev, songliubraving; +Cc: Andrii Nakryiko
In-Reply-To: <20190628152539.3014719-1-andriin@fb.com>
Convert selftests that were originally left out and new ones added
recently to consistently use BTF-defined maps.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
---
.../selftests/bpf/progs/get_cgroup_id_kern.c | 26 ++---
tools/testing/selftests/bpf/progs/pyperf.h | 90 +++++++-------
.../selftests/bpf/progs/sample_map_ret0.c | 24 ++--
.../bpf/progs/sockmap_verdict_prog.c | 48 ++++----
.../testing/selftests/bpf/progs/strobemeta.h | 68 +++++------
.../selftests/bpf/progs/test_map_in_map.c | 30 ++---
.../testing/selftests/bpf/progs/test_obj_id.c | 12 +-
.../selftests/bpf/progs/test_xdp_loop.c | 26 ++---
.../selftests/bpf/progs/xdp_redirect_map.c | 12 +-
.../testing/selftests/bpf/progs/xdping_kern.c | 12 +-
.../selftests/bpf/test_queue_stack_map.h | 30 ++---
.../testing/selftests/bpf/test_sockmap_kern.h | 110 +++++++++---------
12 files changed, 240 insertions(+), 248 deletions(-)
diff --git a/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
index 014dba10b8a5..d7f4003ac3a2 100644
--- a/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
+++ b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
@@ -4,19 +4,19 @@
#include <linux/bpf.h>
#include "bpf_helpers.h"
-struct bpf_map_def SEC("maps") cg_ids = {
- .type = BPF_MAP_TYPE_ARRAY,
- .key_size = sizeof(__u32),
- .value_size = sizeof(__u64),
- .max_entries = 1,
-};
-
-struct bpf_map_def SEC("maps") pidmap = {
- .type = BPF_MAP_TYPE_ARRAY,
- .key_size = sizeof(__u32),
- .value_size = sizeof(__u32),
- .max_entries = 1,
-};
+struct {
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 1);
+ __type(key, __u32);
+ __type(value, __u64);
+} cg_ids SEC(".maps");
+
+struct {
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 1);
+ __type(key, __u32);
+ __type(value, __u32);
+} pidmap SEC(".maps");
SEC("tracepoint/syscalls/sys_enter_nanosleep")
int trace(void *ctx)
diff --git a/tools/testing/selftests/bpf/progs/pyperf.h b/tools/testing/selftests/bpf/progs/pyperf.h
index 6b0781391be5..f0c7250ab045 100644
--- a/tools/testing/selftests/bpf/progs/pyperf.h
+++ b/tools/testing/selftests/bpf/progs/pyperf.h
@@ -58,14 +58,6 @@ typedef struct {
} Event;
-struct bpf_elf_map {
- __u32 type;
- __u32 size_key;
- __u32 size_value;
- __u32 max_elem;
- __u32 flags;
-};
-
typedef int pid_t;
typedef struct {
@@ -119,47 +111,47 @@ get_frame_data(void* frame_ptr, PidData* pidData, FrameData* frame, Symbol* symb
return true;
}
-struct bpf_elf_map SEC("maps") pidmap = {
- .type = BPF_MAP_TYPE_HASH,
- .size_key = sizeof(int),
- .size_value = sizeof(PidData),
- .max_elem = 1,
-};
-
-struct bpf_elf_map SEC("maps") eventmap = {
- .type = BPF_MAP_TYPE_HASH,
- .size_key = sizeof(int),
- .size_value = sizeof(Event),
- .max_elem = 1,
-};
-
-struct bpf_elf_map SEC("maps") symbolmap = {
- .type = BPF_MAP_TYPE_HASH,
- .size_key = sizeof(Symbol),
- .size_value = sizeof(int),
- .max_elem = 1,
-};
-
-struct bpf_elf_map SEC("maps") statsmap = {
- .type = BPF_MAP_TYPE_ARRAY,
- .size_key = sizeof(Stats),
- .size_value = sizeof(int),
- .max_elem = 1,
-};
-
-struct bpf_elf_map SEC("maps") perfmap = {
- .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
- .size_key = sizeof(int),
- .size_value = sizeof(int),
- .max_elem = 32,
-};
-
-struct bpf_elf_map SEC("maps") stackmap = {
- .type = BPF_MAP_TYPE_STACK_TRACE,
- .size_key = sizeof(int),
- .size_value = sizeof(long long) * 127,
- .max_elem = 1000,
-};
+struct {
+ __int(type, BPF_MAP_TYPE_HASH);
+ __int(max_entries, 1);
+ __type(key, int);
+ __type(value, PidData);
+} pidmap SEC(".maps");
+
+struct {
+ __int(type, BPF_MAP_TYPE_HASH);
+ __int(max_entries, 1);
+ __type(key, int);
+ __type(value, Event);
+} eventmap SEC(".maps");
+
+struct {
+ __int(type, BPF_MAP_TYPE_HASH);
+ __int(max_entries, 1);
+ __type(key, Symbol);
+ __type(value, int);
+} symbolmap SEC(".maps");
+
+struct {
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 1);
+ __type(key, int);
+ __type(value, Stats);
+} statsmap SEC(".maps");
+
+struct {
+ __int(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+ __int(max_entries, 32);
+ __int(key_size, sizeof(int));
+ __int(value_size, sizeof(int));
+} perfmap SEC(".maps");
+
+struct {
+ __int(type, BPF_MAP_TYPE_STACK_TRACE);
+ __int(max_entries, 1000);
+ __int(key_size, sizeof(int));
+ __int(value_size, sizeof(long long) * 127);
+} stackmap SEC(".maps");
static inline __attribute__((__always_inline__)) int __on_event(struct pt_regs *ctx)
{
diff --git a/tools/testing/selftests/bpf/progs/sample_map_ret0.c b/tools/testing/selftests/bpf/progs/sample_map_ret0.c
index 0756303676ac..7099f3b847d7 100644
--- a/tools/testing/selftests/bpf/progs/sample_map_ret0.c
+++ b/tools/testing/selftests/bpf/progs/sample_map_ret0.c
@@ -2,19 +2,19 @@
#include <linux/bpf.h>
#include "bpf_helpers.h"
-struct bpf_map_def SEC("maps") htab = {
- .type = BPF_MAP_TYPE_HASH,
- .key_size = sizeof(__u32),
- .value_size = sizeof(long),
- .max_entries = 2,
-};
+struct {
+ __int(type, BPF_MAP_TYPE_HASH);
+ __int(max_entries, 2);
+ __type(key, __u32);
+ __type(value, long);
+} htab SEC(".maps");
-struct bpf_map_def SEC("maps") array = {
- .type = BPF_MAP_TYPE_ARRAY,
- .key_size = sizeof(__u32),
- .value_size = sizeof(long),
- .max_entries = 2,
-};
+struct {
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 2);
+ __type(key, __u32);
+ __type(value, long);
+} array SEC(".maps");
/* Sample program which should always load for testing control paths. */
SEC(".text") int func()
diff --git a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
index d85c874ef25e..e356d5095f99 100644
--- a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
+++ b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
@@ -4,33 +4,33 @@
int _version SEC("version") = 1;
-struct bpf_map_def SEC("maps") sock_map_rx = {
- .type = BPF_MAP_TYPE_SOCKMAP,
- .key_size = sizeof(int),
- .value_size = sizeof(int),
- .max_entries = 20,
-};
+struct {
+ __int(type, BPF_MAP_TYPE_SOCKMAP);
+ __int(max_entries, 20);
+ __int(key_size, sizeof(int));
+ __int(value_size, sizeof(int));
+} sock_map_rx SEC(".maps");
-struct bpf_map_def SEC("maps") sock_map_tx = {
- .type = BPF_MAP_TYPE_SOCKMAP,
- .key_size = sizeof(int),
- .value_size = sizeof(int),
- .max_entries = 20,
-};
+struct {
+ __int(type, BPF_MAP_TYPE_SOCKMAP);
+ __int(max_entries, 20);
+ __int(key_size, sizeof(int));
+ __int(value_size, sizeof(int));
+} sock_map_tx SEC(".maps");
-struct bpf_map_def SEC("maps") sock_map_msg = {
- .type = BPF_MAP_TYPE_SOCKMAP,
- .key_size = sizeof(int),
- .value_size = sizeof(int),
- .max_entries = 20,
-};
+struct {
+ __int(type, BPF_MAP_TYPE_SOCKMAP);
+ __int(max_entries, 20);
+ __int(key_size, sizeof(int));
+ __int(value_size, sizeof(int));
+} sock_map_msg SEC(".maps");
-struct bpf_map_def SEC("maps") sock_map_break = {
- .type = BPF_MAP_TYPE_ARRAY,
- .key_size = sizeof(int),
- .value_size = sizeof(int),
- .max_entries = 20,
-};
+struct {
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 20);
+ __type(key, int);
+ __type(value, int);
+} sock_map_break SEC(".maps");
SEC("sk_skb2")
int bpf_prog2(struct __sk_buff *skb)
diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h
index 1ff73f60a3e4..2a49fa61d0a3 100644
--- a/tools/testing/selftests/bpf/progs/strobemeta.h
+++ b/tools/testing/selftests/bpf/progs/strobemeta.h
@@ -204,40 +204,40 @@ struct strobelight_bpf_sample {
char dummy_safeguard;
};
-struct bpf_map_def SEC("maps") samples = {
- .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
- .key_size = sizeof(int),
- .value_size = sizeof(int),
- .max_entries = 32,
-};
-
-struct bpf_map_def SEC("maps") stacks_0 = {
- .type = BPF_MAP_TYPE_STACK_TRACE,
- .key_size = sizeof(uint32_t),
- .value_size = sizeof(uint64_t) * PERF_MAX_STACK_DEPTH,
- .max_entries = 16,
-};
-
-struct bpf_map_def SEC("maps") stacks_1 = {
- .type = BPF_MAP_TYPE_STACK_TRACE,
- .key_size = sizeof(uint32_t),
- .value_size = sizeof(uint64_t) * PERF_MAX_STACK_DEPTH,
- .max_entries = 16,
-};
-
-struct bpf_map_def SEC("maps") sample_heap = {
- .type = BPF_MAP_TYPE_PERCPU_ARRAY,
- .key_size = sizeof(uint32_t),
- .value_size = sizeof(struct strobelight_bpf_sample),
- .max_entries = 1,
-};
-
-struct bpf_map_def SEC("maps") strobemeta_cfgs = {
- .type = BPF_MAP_TYPE_PERCPU_ARRAY,
- .key_size = sizeof(pid_t),
- .value_size = sizeof(struct strobemeta_cfg),
- .max_entries = STROBE_MAX_CFGS,
-};
+struct {
+ __int(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+ __int(max_entries, 32);
+ __int(key_size, sizeof(int));
+ __int(value_size, sizeof(int));
+} samples SEC(".maps");
+
+struct {
+ __int(type, BPF_MAP_TYPE_STACK_TRACE);
+ __int(max_entries, 16);
+ __int(key_size, sizeof(uint32_t));
+ __int(value_size, sizeof(uint64_t) * PERF_MAX_STACK_DEPTH);
+} stacks_0 SEC(".maps");
+
+struct {
+ __int(type, BPF_MAP_TYPE_STACK_TRACE);
+ __int(max_entries, 16);
+ __int(key_size, sizeof(uint32_t));
+ __int(value_size, sizeof(uint64_t) * PERF_MAX_STACK_DEPTH);
+} stacks_1 SEC(".maps");
+
+struct {
+ __int(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __int(max_entries, 1);
+ __type(key, uint32_t);
+ __type(value, struct strobelight_bpf_sample);
+} sample_heap SEC(".maps");
+
+struct {
+ __int(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __int(max_entries, STROBE_MAX_CFGS);
+ __type(key, pid_t);
+ __type(value, struct strobemeta_cfg);
+} strobemeta_cfgs SEC(".maps");
/* Type for the dtv. */
/* https://github.com/lattera/glibc/blob/master/nptl/sysdeps/x86_64/tls.h#L34 */
diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c
index 2985f262846e..e0028b6457c1 100644
--- a/tools/testing/selftests/bpf/progs/test_map_in_map.c
+++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c
@@ -5,23 +5,23 @@
#include <linux/types.h>
#include "bpf_helpers.h"
-struct bpf_map_def SEC("maps") mim_array = {
- .type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
- .key_size = sizeof(int),
+struct {
+ __int(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+ __int(max_entries, 1);
+ __int(map_flags, 0);
+ __int(key_size, sizeof(__u32));
/* must be sizeof(__u32) for map in map */
- .value_size = sizeof(__u32),
- .max_entries = 1,
- .map_flags = 0,
-};
-
-struct bpf_map_def SEC("maps") mim_hash = {
- .type = BPF_MAP_TYPE_HASH_OF_MAPS,
- .key_size = sizeof(int),
+ __int(value_size, sizeof(__u32));
+} mim_array SEC(".maps");
+
+struct {
+ __int(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+ __int(max_entries, 1);
+ __int(map_flags, 0);
+ __int(key_size, sizeof(int));
/* must be sizeof(__u32) for map in map */
- .value_size = sizeof(__u32),
- .max_entries = 1,
- .map_flags = 0,
-};
+ __int(value_size, sizeof(__u32));
+} mim_hash SEC(".maps");
SEC("xdp_mimtest")
int xdp_mimtest0(struct xdp_md *ctx)
diff --git a/tools/testing/selftests/bpf/progs/test_obj_id.c b/tools/testing/selftests/bpf/progs/test_obj_id.c
index 726340fa6fe0..df3c3d9d251c 100644
--- a/tools/testing/selftests/bpf/progs/test_obj_id.c
+++ b/tools/testing/selftests/bpf/progs/test_obj_id.c
@@ -13,12 +13,12 @@
int _version SEC("version") = 1;
-struct bpf_map_def SEC("maps") test_map_id = {
- .type = BPF_MAP_TYPE_ARRAY,
- .key_size = sizeof(__u32),
- .value_size = sizeof(__u64),
- .max_entries = 1,
-};
+struct {
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 1);
+ __type(key, __u32);
+ __type(value, __u64);
+} test_map_id SEC(".maps");
SEC("test_obj_id_dummy")
int test_obj_id(struct __sk_buff *skb)
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_loop.c b/tools/testing/selftests/bpf/progs/test_xdp_loop.c
index 7fa4677df22e..45bd5ab25dfd 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_loop.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_loop.c
@@ -18,19 +18,19 @@
int _version SEC("version") = 1;
-struct bpf_map_def SEC("maps") rxcnt = {
- .type = BPF_MAP_TYPE_PERCPU_ARRAY,
- .key_size = sizeof(__u32),
- .value_size = sizeof(__u64),
- .max_entries = 256,
-};
-
-struct bpf_map_def SEC("maps") vip2tnl = {
- .type = BPF_MAP_TYPE_HASH,
- .key_size = sizeof(struct vip),
- .value_size = sizeof(struct iptnl_info),
- .max_entries = MAX_IPTNL_ENTRIES,
-};
+struct {
+ __int(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __int(max_entries, 256);
+ __type(key, __u32);
+ __type(value, __u64);
+} rxcnt SEC(".maps");
+
+struct {
+ __int(type, BPF_MAP_TYPE_HASH);
+ __int(max_entries, MAX_IPTNL_ENTRIES);
+ __type(key, struct vip);
+ __type(value, struct iptnl_info);
+} vip2tnl SEC(".maps");
static __always_inline void count_tx(__u32 protocol)
{
diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
index e87a985b9df9..8f05369b1034 100644
--- a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
+++ b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
@@ -3,12 +3,12 @@
#include <linux/bpf.h>
#include "bpf_helpers.h"
-struct bpf_map_def SEC("maps") tx_port = {
- .type = BPF_MAP_TYPE_DEVMAP,
- .key_size = sizeof(int),
- .value_size = sizeof(int),
- .max_entries = 8,
-};
+struct {
+ __int(type, BPF_MAP_TYPE_DEVMAP);
+ __int(max_entries, 8);
+ __int(key_size, sizeof(int));
+ __int(value_size, sizeof(int));
+} tx_port SEC(".maps");
SEC("redirect_map_0")
int xdp_redirect_map_0(struct xdp_md *xdp)
diff --git a/tools/testing/selftests/bpf/progs/xdping_kern.c b/tools/testing/selftests/bpf/progs/xdping_kern.c
index 87393e7c667c..3b0adfe8d685 100644
--- a/tools/testing/selftests/bpf/progs/xdping_kern.c
+++ b/tools/testing/selftests/bpf/progs/xdping_kern.c
@@ -17,12 +17,12 @@
#include "xdping.h"
-struct bpf_map_def SEC("maps") ping_map = {
- .type = BPF_MAP_TYPE_HASH,
- .key_size = sizeof(__u32),
- .value_size = sizeof(struct pinginfo),
- .max_entries = 256,
-};
+struct {
+ __int(type, BPF_MAP_TYPE_HASH);
+ __int(max_entries, 256);
+ __type(key, __u32);
+ __type(value, struct pinginfo);
+} ping_map SEC(".maps");
static __always_inline void swap_src_dst_mac(void *data)
{
diff --git a/tools/testing/selftests/bpf/test_queue_stack_map.h b/tools/testing/selftests/bpf/test_queue_stack_map.h
index 295b9b3bc5c7..5eb376bbbbb3 100644
--- a/tools/testing/selftests/bpf/test_queue_stack_map.h
+++ b/tools/testing/selftests/bpf/test_queue_stack_map.h
@@ -10,21 +10,21 @@
int _version SEC("version") = 1;
-struct bpf_map_def __attribute__ ((section("maps"), used)) map_in = {
- .type = MAP_TYPE,
- .key_size = 0,
- .value_size = sizeof(__u32),
- .max_entries = 32,
- .map_flags = 0,
-};
-
-struct bpf_map_def __attribute__ ((section("maps"), used)) map_out = {
- .type = MAP_TYPE,
- .key_size = 0,
- .value_size = sizeof(__u32),
- .max_entries = 32,
- .map_flags = 0,
-};
+struct {
+ __int(type, MAP_TYPE);
+ __int(max_entries, 32);
+ __int(map_flags, 0);
+ __int(key_size, 0);
+ __int(value_size, sizeof(__u32));
+} map_in SEC(".maps");
+
+struct {
+ __int(type, MAP_TYPE);
+ __int(max_entries, 32);
+ __int(map_flags, 0);
+ __int(key_size, 0);
+ __int(value_size, sizeof(__u32));
+} map_out SEC(".maps");
SEC("test")
int _test(struct __sk_buff *skb)
diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.h b/tools/testing/selftests/bpf/test_sockmap_kern.h
index 4e7d3da21357..d5e472780dcd 100644
--- a/tools/testing/selftests/bpf/test_sockmap_kern.h
+++ b/tools/testing/selftests/bpf/test_sockmap_kern.h
@@ -28,61 +28,61 @@
* are established and verdicts are decided.
*/
-struct bpf_map_def SEC("maps") sock_map = {
- .type = TEST_MAP_TYPE,
- .key_size = sizeof(int),
- .value_size = sizeof(int),
- .max_entries = 20,
-};
-
-struct bpf_map_def SEC("maps") sock_map_txmsg = {
- .type = TEST_MAP_TYPE,
- .key_size = sizeof(int),
- .value_size = sizeof(int),
- .max_entries = 20,
-};
-
-struct bpf_map_def SEC("maps") sock_map_redir = {
- .type = TEST_MAP_TYPE,
- .key_size = sizeof(int),
- .value_size = sizeof(int),
- .max_entries = 20,
-};
-
-struct bpf_map_def SEC("maps") sock_apply_bytes = {
- .type = BPF_MAP_TYPE_ARRAY,
- .key_size = sizeof(int),
- .value_size = sizeof(int),
- .max_entries = 1
-};
-
-struct bpf_map_def SEC("maps") sock_cork_bytes = {
- .type = BPF_MAP_TYPE_ARRAY,
- .key_size = sizeof(int),
- .value_size = sizeof(int),
- .max_entries = 1
-};
-
-struct bpf_map_def SEC("maps") sock_bytes = {
- .type = BPF_MAP_TYPE_ARRAY,
- .key_size = sizeof(int),
- .value_size = sizeof(int),
- .max_entries = 6
-};
-
-struct bpf_map_def SEC("maps") sock_redir_flags = {
- .type = BPF_MAP_TYPE_ARRAY,
- .key_size = sizeof(int),
- .value_size = sizeof(int),
- .max_entries = 1
-};
-
-struct bpf_map_def SEC("maps") sock_skb_opts = {
- .type = BPF_MAP_TYPE_ARRAY,
- .key_size = sizeof(int),
- .value_size = sizeof(int),
- .max_entries = 1
-};
+struct {
+ __int(type, TEST_MAP_TYPE);
+ __int(max_entries, 20);
+ __int(key_size, sizeof(int));
+ __int(value_size, sizeof(int));
+} sock_map SEC(".maps");
+
+struct {
+ __int(type, TEST_MAP_TYPE);
+ __int(max_entries, 20);
+ __int(key_size, sizeof(int));
+ __int(value_size, sizeof(int));
+} sock_map_txmsg SEC(".maps");
+
+struct {
+ __int(type, TEST_MAP_TYPE);
+ __int(max_entries, 20);
+ __int(key_size, sizeof(int));
+ __int(value_size, sizeof(int));
+} sock_map_redir SEC(".maps");
+
+struct {
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 1);
+ __type(key, int);
+ __type(value, int);
+} sock_apply_bytes SEC(".maps");
+
+struct {
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 1);
+ __type(key, int);
+ __type(value, int);
+} sock_cork_bytes SEC(".maps");
+
+struct {
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 6);
+ __type(key, int);
+ __type(value, int);
+} sock_bytes SEC(".maps");
+
+struct {
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 1);
+ __type(key, int);
+ __type(value, int);
+} sock_redir_flags SEC(".maps");
+
+struct {
+ __int(type, BPF_MAP_TYPE_ARRAY);
+ __int(max_entries, 1);
+ __type(key, int);
+ __type(value, int);
+} sock_skb_opts SEC(".maps");
SEC("sk_skb1")
int bpf_prog1(struct __sk_buff *skb)
--
2.17.1
^ permalink raw reply related
* Re: [PATCH 0/5] net: dsa: microchip: Further regmap cleanups
From: Vivien Didelot @ 2019-06-28 15:31 UTC (permalink / raw)
To: Marek Vasut
Cc: netdev, Marek Vasut, Andrew Lunn, Florian Fainelli, Tristram Ha,
Woojung Huh
In-Reply-To: <20190627215556.23768-1-marex@denx.de>
Hi Marek,
On Thu, 27 Jun 2019 23:55:51 +0200, Marek Vasut <marex@denx.de> wrote:
> This patchset cleans up KSZ9477 switch driver by replacing various
> ad-hoc polling implementations and register RMW with regmap functions.
>
> Each polling function is replaced separately to make it easier to review
> and possibly bisect, but maybe the patches can be squashed.
>
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Andrew Lunn <andrew@lunn.ch>
> Cc: Florian Fainelli <f.fainelli@gmail.com>
> Cc: Tristram Ha <Tristram.Ha@microchip.com>
> Cc: Woojung Huh <Woojung.Huh@microchip.com>
Please copy me next time, as per the MAINTAINERS file.
Thanks,
Vivien
^ permalink raw reply
* Re: [PATCH v3 1/4] kbuild: compile-test UAPI headers to ensure they are self-contained
From: Sam Ravnborg @ 2019-06-28 15:43 UTC (permalink / raw)
To: Masahiro Yamada
Cc: linux-kbuild, Jani Nikula, Song Liu, Alexei Starovoitov, netdev,
Yonghong Song, linux-kernel, linux-riscv, Michal Marek,
Martin KaFai Lau, Palmer Dabbelt, bpf, Daniel Borkmann, Albert Ou
In-Reply-To: <20190627163903.28398-2-yamada.masahiro@socionext.com>
Hi Masahiro.
On Fri, Jun 28, 2019 at 01:38:59AM +0900, Masahiro Yamada wrote:
> Multiple people have suggested compile-testing UAPI headers to ensure
> they can be really included from user-space. "make headers_check" is
> obviously not enough to catch bugs, and we often leak references to
> kernel-space definition to user-space.
>
> Use the new header-test-y syntax to implement it. Please note exported
> headers are compile-tested with a completely different set of compiler
> flags. The header search path is set to $(objtree)/usr/include since
> exported headers should not include unexported ones.
This patchset introduce a new set of tests for uapi headers.
Can we somehow consolidate so we have only one way to verify the uapi
headers?
It can be confusing for users that they see errors from testing the
uapi headers during normal build and a new class or error if they
run a "make headers_check" sometimes later.
This can be a next step to consolidate this.
With the suggestions below considered you can add my:
Reviewed-by: Sam Ravnborg <sam@ravnborg.org>
>
> We use -std=gnu89 for the kernel space since the kernel code highly
> depends on GNU extensions. On the other hand, UAPI headers should be
> written in more standardized C, so they are compiled with -std=c90.
> This will emit errors if C++ style comments, the keyword 'inline', etc.
> are used. Please use C style comments (/* ... */), '__inline__', etc.
> in UAPI headers.
>
> There is additional compiler requirement to enable this test because
> many of UAPI headers include <stdlib.h>, <sys/ioctl.h>, <sys/time.h>,
> etc. directly or indirectly. You cannot use kernel.org pre-built
> toolchains [1] since they lack <stdlib.h>.
>
> I added scripts/cc-system-headers.sh to check the system header
> availability, which CONFIG_UAPI_HEADER_TEST depends on.
>
> For now, a lot of headers need to be excluded because they cannot
> be compiled standalone, but this is a good start point.
>
> [1] https://mirrors.edge.kernel.org/pub/tools/crosstool/index.html
>
> Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
> ---
>
> Changes in v3: None
> Changes in v2:
> - Add CONFIG_CPU_{BIG,LITTLE}_ENDIAN guard to avoid build error
> - Use 'header-test-' instead of 'no-header-test'
> - Avoid weird 'find' warning when cleaning
>
> Makefile | 2 +-
> init/Kconfig | 11 +++
> scripts/cc-system-headers.sh | 8 +++
> usr/.gitignore | 1 -
> usr/Makefile | 2 +
> usr/include/.gitignore | 3 +
> usr/include/Makefile | 134 +++++++++++++++++++++++++++++++++++
> 7 files changed, 159 insertions(+), 2 deletions(-)
> create mode 100755 scripts/cc-system-headers.sh
> create mode 100644 usr/include/.gitignore
> create mode 100644 usr/include/Makefile
>
> diff --git a/Makefile b/Makefile
> index 1f35aca4fe05..f23516980796 100644
> --- a/Makefile
> +++ b/Makefile
> @@ -1363,7 +1363,7 @@ CLEAN_DIRS += $(MODVERDIR) include/ksym
> CLEAN_FILES += modules.builtin.modinfo
>
> # Directories & files removed with 'make mrproper'
> -MRPROPER_DIRS += include/config usr/include include/generated \
> +MRPROPER_DIRS += include/config include/generated \
> arch/$(SRCARCH)/include/generated .tmp_objdiff
> MRPROPER_FILES += .config .config.old .version \
> Module.symvers tags TAGS cscope* GPATH GTAGS GRTAGS GSYMS \
> diff --git a/init/Kconfig b/init/Kconfig
> index df5bba27e3fe..667d68e1cdf4 100644
> --- a/init/Kconfig
> +++ b/init/Kconfig
> @@ -105,6 +105,17 @@ config HEADER_TEST
> If you are a developer or tester and want to ensure the requested
> headers are self-contained, say Y here. Otherwise, choose N.
>
> +config UAPI_HEADER_TEST
> + bool "Compile test UAPI headers"
> + depends on HEADER_TEST && HEADERS_INSTALL
> + depends on $(success,$(srctree)/scripts/cc-system-headers.sh $(CC))
> + help
> + Compile test headers exported to user-space to ensure they are
> + self-contained, i.e. compilable as standalone units.
> +
> + If you are a developer or tester and want to ensure the exported
> + headers are self-contained, say Y here. Otherwise, choose N.
> +
> config LOCALVERSION
> string "Local version - append to kernel release"
> help
> diff --git a/scripts/cc-system-headers.sh b/scripts/cc-system-headers.sh
> new file mode 100755
> index 000000000000..1b3db369828c
> --- /dev/null
> +++ b/scripts/cc-system-headers.sh
> @@ -0,0 +1,8 @@
> +#!/bin/sh
> +# SPDX-License-Identifier: GPL-2.0-only
> +
> +cat << "END" | $@ -E -x c - -o /dev/null >/dev/null 2>&1
> +#include <stdlib.h>
> +#include <sys/ioctl.h>
> +#include <sys/time.h>
> +END
Add comment to this file that explains that it is used to verify that the
toolchain provides the minimal set of header-files required by uapi
headers.
> diff --git a/usr/.gitignore b/usr/.gitignore
> index 8e48117a3f3d..be5eae1df7eb 100644
> --- a/usr/.gitignore
> +++ b/usr/.gitignore
> @@ -7,4 +7,3 @@ initramfs_data.cpio.gz
> initramfs_data.cpio.bz2
> initramfs_data.cpio.lzma
> initramfs_list
> -include
> diff --git a/usr/Makefile b/usr/Makefile
> index 4a70ae43c9cb..6a89eb019275 100644
> --- a/usr/Makefile
> +++ b/usr/Makefile
> @@ -56,3 +56,5 @@ $(deps_initramfs): klibcdirs
> $(obj)/$(datafile_y): $(obj)/gen_init_cpio $(deps_initramfs) klibcdirs
> $(Q)$(initramfs) -l $(ramfs-input) > $(obj)/$(datafile_d_y)
> $(call if_changed,initfs)
> +
> +subdir-$(CONFIG_UAPI_HEADER_TEST) += include
> diff --git a/usr/include/.gitignore b/usr/include/.gitignore
> new file mode 100644
> index 000000000000..a0991ff4402b
> --- /dev/null
> +++ b/usr/include/.gitignore
> @@ -0,0 +1,3 @@
> +*
> +!.gitignore
> +!Makefile
> diff --git a/usr/include/Makefile b/usr/include/Makefile
> new file mode 100644
> index 000000000000..58ce96fa1701
> --- /dev/null
> +++ b/usr/include/Makefile
> @@ -0,0 +1,134 @@
> +# SPDX-License-Identifier: GPL-2.0-only
> +
> +# Unlike the kernel space, uapi headers are written in standard C.
> +# - Forbid C++ style comments
> +# - Use '__inline__', '__asm__' instead of 'inline', 'asm'
> +#
> +# -std=c90 (equivalent to -ansi) catches the violation of those.
> +# We cannot go as far as adding -Wpedantic since it emits too many warnings.
> +#
> +# REVISIT: re-consider the proper set of compiler flags for uapi compile-test.
> +
> +UAPI_CFLAGS := -std=c90 -Wall -Werror=implicit-function-declaration
> +
> +override c_flags = $(UAPI_CFLAGS) -Wp,-MD,$(depfile) -I$(objtree)/usr/include
> +
> +# The following are excluded for now because they fail to build.
> +# The cause of errors are mostly missing include directives.
> +# Check one by one, and send a patch to each subsystem.
> +#
> +# Do not add a new header to the blacklist without legitimate reason.
> +# Please consider to fix the header first.
Maybe add comment that the alphabetical sort by filename must be preserved.
Not too relevant, as we hopefully do not see files being added.
> +header-test- += asm/ipcbuf.h
> +header-test- += asm/msgbuf.h
Consider same syntax like in include/Makefile where you use
header-test-<tab><tab>...+= file
Then the alignment looks betters.
> +header-test- += asm/sembuf.h
> +header-test- += asm/shmbuf.h
> +header-test- += asm/signal.h
> +header-test- += asm/ucontext.h
> +header-test- += drm/vmwgfx_drm.h
> +header-test- += linux/am437x-vpfe.h
> +header-test- += linux/android/binderfs.h
> +header-test- += linux/android/binder.h
> +header-test-$(CONFIG_CPU_BIG_ENDIAN) += linux/byteorder/big_endian.h
> +header-test-$(CONFIG_CPU_LITTLE_ENDIAN) += linux/byteorder/little_endian.h
> +header-test- += linux/coda.h
...
List is shorter than I feared. Seems quite doable to get down to a
small number of files.
> +
> +# more headers are broken in some architectures
> +
> +ifeq ($(SRCARCH),arc)
> +header-test- += linux/bpf_perf_event.h
> +endif
Again a manageable number.
> +
> +
> +# asm-generic/*.h is used by asm/*.h, and should not be included directly
> +header-test- += asm-generic/%
> +
> +# The rest are compile-tested
> +header-test-y += $(filter-out $(header-test-), \
> + $(patsubst $(obj)/%,%, $(wildcard \
> + $(addprefix $(obj)/, *.h */*.h */*/*.h */*/*/*.h))))
Could you use header-test-pattern-y here?
Sam
^ permalink raw reply
* Re: [RFC] longer netdev names proposal
From: Stephen Hemminger @ 2019-06-28 15:44 UTC (permalink / raw)
To: Jiri Pirko
Cc: Andrew Lunn, Michal Kubecek, netdev, David Ahern, davem,
jakub.kicinski, mlxsw
In-Reply-To: <20190628135553.GA6640@nanopsycho>
On Fri, 28 Jun 2019 15:55:53 +0200
Jiri Pirko <jiri@resnulli.us> wrote:
> Fri, Jun 28, 2019 at 03:14:01PM CEST, andrew@lunn.ch wrote:
> >On Fri, Jun 28, 2019 at 01:12:16PM +0200, Jiri Pirko wrote:
> >> Thu, Jun 27, 2019 at 09:20:41PM CEST, stephen@networkplumber.org wrote:
> >> >On Thu, 27 Jun 2019 20:39:48 +0200
> >> >Michal Kubecek <mkubecek@suse.cz> wrote:
> >> >
> >> >> >
> >> >> > $ ip li set dev enp3s0 alias "Onboard Ethernet"
> >> >> > # ip link show "Onboard Ethernet"
> >> >> > Device "Onboard Ethernet" does not exist.
> >> >> >
> >> >> > So it does not really appear to be an alias, it is a label. To be
> >> >> > truly useful, it needs to be more than a label, it needs to be a real
> >> >> > alias which you can use.
> >> >>
> >> >> That's exactly what I meant: to be really useful, one should be able to
> >> >> use the alias(es) for setting device options, for adding routes, in
> >> >> netfilter rules etc.
> >> >>
> >> >> Michal
> >> >
> >> >The kernel doesn't enforce uniqueness of alias.
> >> >Also current kernel RTM_GETLINK doesn't do filter by alias (easily fixed).
> >> >
> >> >If it did, then handling it in iproute would be something like:
> >>
> >> I think that it is desired for kernel to work with "real alias" as a
> >> handle. Userspace could either pass ifindex, IFLA_NAME or "real alias".
> >> Userspace mapping like you did here might be perhaps okay for iproute2,
> >> but I think that we need something and easy to use for all.
> >>
> >> Let's call it "altname". Get would return:
> >>
> >> IFLA_NAME eth0
> >> IFLA_ALT_NAME_LIST
> >> IFLA_ALT_NAME eth0
> >> IFLA_ALT_NAME somethingelse
> >> IFLA_ALT_NAME somenamethatisreallylong
> >
> >Hi Jiri
> >
> >What is your user case for having multiple IFLA_ALT_NAME for the same
> >IFLA_NAME?
>
> I don't know about specific usecase for having more. Perhaps Michal
> does.
>
> From the implementation perspective it is handy to have the ifname as
> the first alt name in kernel, so the userspace would just pass
> IFLA_ALT_NAME always. Also for avoiding name collisions etc.
I like the alternate name proposal. The kernel would have to impose uniqueness.
Does alt_name have to be unique across both regular and alt_name?
Having multiple names list seems less interesting but it could be useful.
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox