| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Fri, 4 Feb 2022 14:00:10 +0100
From: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
To: Eric Dumazet <edumazet@...gle.com>
Cc: bpf <bpf@...r.kernel.org>, netdev <netdev@...r.kernel.org>,
"David S. Miller" <davem@...emloft.net>,
Alexei Starovoitov <ast@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>,
Jakub Kicinski <kuba@...nel.org>,
Jesper Dangaard Brouer <hawk@...nel.org>,
John Fastabend <john.fastabend@...il.com>,
Thomas Gleixner <tglx@...utronix.de>,
Peter Zijlstra <peterz@...radead.org>
Subject: [PATCH net-next v2 3/4] net: dev: Makes sure netif_rx() can be
invoked in any context.
Dave suggested a while ago (eleven years by now) "Let's make netif_rx()
work in all contexts and get rid of netif_rx_ni()". Eric agreed and
pointed out that modern devices should use netif_receive_skb() to avoid
the overhead.
In the meantime someone added another variant, netif_rx_any_context(),
which behaves as suggested.
netif_rx() must be invoked with disabled bottom halves to ensure that
pending softirqs, which were raised within the function, are handled.
netif_rx_ni() can be invoked only from process context (bottom halves
must be enabled) because the function handles pending softirqs without
checking if bottom halves were disabled or not.
netif_rx_any_context() invokes on the former functions by checking
in_interrupts().
netif_rx() could be taught to handle both cases (disabled and enabled
bottom halves) by simply disabling bottom halves while invoking
netif_rx_internal(). The local_bh_enable() invocation will then invoke
pending softirqs only if the BH-disable counter drops to zero.
Eric is concerned about the overhead of BH-disable+enable especially in
regard to the loopback driver. As critical as this driver is, it will
receive a shortcut to avoid the additional overhead which is not needed.
Add a local_bh_disable() section in netif_rx() to ensure softirqs are
handled if needed. Provide the internal bits as __netif_rx() which can
be used by the loopback driver. This function is not exported so it
can't be used by modules.
Make netif_rx_ni() and netif_rx_any_context() invoke netif_rx() so they
can be removed once they are no more users left.
Link: https://lkml.kernel.org/r/20100415.020246.218622820.davem@davemloft.net
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
---
v1…v2:
- Provide netif_rx() as in v1 and additionally __netif_rx() without
local_bh disable()+enable() for the loopback driver. __netif_rx() is
not exported (loopback is built-in only) so it won't be used
drivers. If this doesn't work then we can still export/ define a
wrapper as Eric suggested.
- Added a comment that netif_rx() considered legacy.
drivers/net/loopback.c | 2 +-
include/linux/netdevice.h | 14 ++++++++--
include/trace/events/net.h | 14 ----------
net/core/dev.c | 53 +++++++++++---------------------------
4 files changed, 28 insertions(+), 55 deletions(-)
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index ed0edf5884ef8..77f5b564382b6 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -86,7 +86,7 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb,
skb->protocol = eth_type_trans(skb, dev);
len = skb->len;
- if (likely(netif_rx(skb) == NET_RX_SUCCESS))
+ if (likely(__netif_rx(skb) == NET_RX_SUCCESS))
dev_lstats_add(dev, len);
return NETDEV_TX_OK;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e490b84732d16..c9e883104adb1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3669,8 +3669,18 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp,
void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog);
int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb);
int netif_rx(struct sk_buff *skb);
-int netif_rx_ni(struct sk_buff *skb);
-int netif_rx_any_context(struct sk_buff *skb);
+int __netif_rx(struct sk_buff *skb);
+
+static inline int netif_rx_ni(struct sk_buff *skb)
+{
+ return netif_rx(skb);
+}
+
+static inline int netif_rx_any_context(struct sk_buff *skb)
+{
+ return netif_rx(skb);
+}
+
int netif_receive_skb(struct sk_buff *skb);
int netif_receive_skb_core(struct sk_buff *skb);
void netif_receive_skb_list_internal(struct list_head *head);
diff --git a/include/trace/events/net.h b/include/trace/events/net.h
index 78c448c6ab4c5..032b431b987b6 100644
--- a/include/trace/events/net.h
+++ b/include/trace/events/net.h
@@ -260,13 +260,6 @@ DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_entry,
TP_ARGS(skb)
);
-DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_ni_entry,
-
- TP_PROTO(const struct sk_buff *skb),
-
- TP_ARGS(skb)
-);
-
DECLARE_EVENT_CLASS(net_dev_rx_exit_template,
TP_PROTO(int ret),
@@ -312,13 +305,6 @@ DEFINE_EVENT(net_dev_rx_exit_template, netif_rx_exit,
TP_ARGS(ret)
);
-DEFINE_EVENT(net_dev_rx_exit_template, netif_rx_ni_exit,
-
- TP_PROTO(int ret),
-
- TP_ARGS(ret)
-);
-
DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_list_exit,
TP_PROTO(int ret),
diff --git a/net/core/dev.c b/net/core/dev.c
index 5ef77b53507d4..b7578f47e151c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4829,6 +4829,16 @@ static int netif_rx_internal(struct sk_buff *skb)
return ret;
}
+int __netif_rx(struct sk_buff *skb)
+{
+ int ret;
+
+ trace_netif_rx_entry(skb);
+ ret = netif_rx_internal(skb);
+ trace_netif_rx_exit(ret);
+ return ret;
+}
+
/**
* netif_rx - post buffer to the network code
* @skb: buffer to post
@@ -4837,58 +4847,25 @@ static int netif_rx_internal(struct sk_buff *skb)
* the upper (protocol) levels to process. It always succeeds. The buffer
* may be dropped during processing for congestion control or by the
* protocol layers.
+ * This interface is considered legacy. Modern NIC driver should use NAPI
+ * and GRO.
*
* return values:
* NET_RX_SUCCESS (no congestion)
* NET_RX_DROP (packet was dropped)
*
*/
-
int netif_rx(struct sk_buff *skb)
{
int ret;
- trace_netif_rx_entry(skb);
-
- ret = netif_rx_internal(skb);
- trace_netif_rx_exit(ret);
-
+ local_bh_disable();
+ ret = __netif_rx(skb);
+ local_bh_enable();
return ret;
}
EXPORT_SYMBOL(netif_rx);
-int netif_rx_ni(struct sk_buff *skb)
-{
- int err;
-
- trace_netif_rx_ni_entry(skb);
-
- preempt_disable();
- err = netif_rx_internal(skb);
- if (local_softirq_pending())
- do_softirq();
- preempt_enable();
- trace_netif_rx_ni_exit(err);
-
- return err;
-}
-EXPORT_SYMBOL(netif_rx_ni);
-
-int netif_rx_any_context(struct sk_buff *skb)
-{
- /*
- * If invoked from contexts which do not invoke bottom half
- * processing either at return from interrupt or when softrqs are
- * reenabled, use netif_rx_ni() which invokes bottomhalf processing
- * directly.
- */
- if (in_interrupt())
- return netif_rx(skb);
- else
- return netif_rx_ni(skb);
-}
-EXPORT_SYMBOL(netif_rx_any_context);
-
static __latent_entropy void net_tx_action(struct softirq_action *h)
{
struct softnet_data *sd = this_cpu_ptr(&softnet_data);
--
2.34.1
Powered by blists - more mailing lists