* Re: [PATCH 1/2] net-ipv4: remove 2 always zero parameters from ipv4_update_pmtu()
From: David Ahern @ 2018-09-26 0:52 UTC (permalink / raw)
To: Maciej Żenczykowski, Maciej Żenczykowski,
David S . Miller, Eric Dumazet
Cc: netdev
In-Reply-To: <20180926004137.163699-1-zenczykowski@gmail.com>
On 9/25/18 6:41 PM, Maciej Żenczykowski wrote:
> From: Maciej Żenczykowski <maze@google.com>
>
A summary here of which 2 parameters are always 0 would be nice.
> Signed-off-by: Maciej Żenczykowski <maze@google.com>
> ---
> include/net/route.h | 2 +-
> net/ipv4/ah4.c | 2 +-
> net/ipv4/esp4.c | 2 +-
> net/ipv4/icmp.c | 2 +-
> net/ipv4/ip_gre.c | 2 +-
> net/ipv4/ip_vti.c | 2 +-
> net/ipv4/ipcomp.c | 2 +-
> net/ipv4/ipip.c | 3 +--
> net/ipv4/route.c | 8 +++-----
> net/ipv6/sit.c | 2 +-
> net/netfilter/ipvs/ip_vs_core.c | 3 +--
> net/xfrm/xfrm_interface.c | 2 +-
> 12 files changed, 14 insertions(+), 18 deletions(-)
>
Reviewed-by: David Ahern <dsahern@gmail.com>
^ permalink raw reply
* [PATCH 2/2] net-ipv4: remove 2 always zero parameters from ipv4_redirect()
From: Maciej Żenczykowski @ 2018-09-26 0:41 UTC (permalink / raw)
To: Maciej Żenczykowski, David S . Miller, Eric Dumazet; +Cc: netdev
In-Reply-To: <20180926004137.163699-1-zenczykowski@gmail.com>
From: Maciej Żenczykowski <maze@google.com>
Signed-off-by: Maciej Żenczykowski <maze@google.com>
---
include/net/route.h | 3 +--
net/ipv4/ah4.c | 2 +-
net/ipv4/esp4.c | 2 +-
net/ipv4/icmp.c | 2 +-
net/ipv4/ip_gre.c | 4 ++--
net/ipv4/ip_vti.c | 2 +-
net/ipv4/ipcomp.c | 2 +-
net/ipv4/ipip.c | 2 +-
net/ipv4/route.c | 4 ++--
net/ipv6/sit.c | 4 ++--
net/xfrm/xfrm_interface.c | 2 +-
11 files changed, 14 insertions(+), 15 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index 73c605bdd6d8..9883dc82f723 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -203,8 +203,7 @@ static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif,
u8 protocol);
void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu);
-void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark,
- u8 protocol, int flow_flags);
+void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u8 protocol);
void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk);
void ip_rt_send_redirect(struct sk_buff *skb);
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 8811fe30282a..c01fa791260d 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -463,7 +463,7 @@ static int ah4_err(struct sk_buff *skb, u32 info)
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, IPPROTO_AH);
else
- ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0);
+ ipv4_redirect(skb, net, 0, IPPROTO_AH);
xfrm_state_put(x);
return 0;
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 2d0274441923..071533dd33c2 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -822,7 +822,7 @@ static int esp4_err(struct sk_buff *skb, u32 info)
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, IPPROTO_ESP);
else
- ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0);
+ ipv4_redirect(skb, net, 0, IPPROTO_ESP);
xfrm_state_put(x);
return 0;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 8013b37b598f..d832beed6e3a 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -1100,7 +1100,7 @@ void icmp_err(struct sk_buff *skb, u32 info)
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
ipv4_update_pmtu(skb, net, info, 0, IPPROTO_ICMP);
else if (type == ICMP_REDIRECT)
- ipv4_redirect(skb, net, 0, 0, IPPROTO_ICMP, 0);
+ ipv4_redirect(skb, net, 0, IPPROTO_ICMP);
}
/*
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 83b80fafd8f2..38befe829caf 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -243,8 +243,8 @@ static void gre_err(struct sk_buff *skb, u32 info)
return;
}
if (type == ICMP_REDIRECT) {
- ipv4_redirect(skb, dev_net(skb->dev), skb->dev->ifindex, 0,
- IPPROTO_GRE, 0);
+ ipv4_redirect(skb, dev_net(skb->dev), skb->dev->ifindex,
+ IPPROTO_GRE);
return;
}
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 1b5571cb3282..de31b302d69c 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -320,7 +320,7 @@ static int vti4_err(struct sk_buff *skb, u32 info)
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, protocol);
else
- ipv4_redirect(skb, net, 0, 0, protocol, 0);
+ ipv4_redirect(skb, net, 0, protocol);
xfrm_state_put(x);
return 0;
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index 04049d1330a2..9119d012ba46 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -50,7 +50,7 @@ static int ipcomp4_err(struct sk_buff *skb, u32 info)
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, IPPROTO_COMP);
else
- ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0);
+ ipv4_redirect(skb, net, 0, IPPROTO_COMP);
xfrm_state_put(x);
return 0;
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 6ff008e5818d..e65287c27e3d 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -180,7 +180,7 @@ static int ipip_err(struct sk_buff *skb, u32 info)
}
if (type == ICMP_REDIRECT) {
- ipv4_redirect(skb, net, t->parms.link, 0, iph->protocol, 0);
+ ipv4_redirect(skb, net, t->parms.link, iph->protocol);
goto out;
}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 7bbe3fc80b90..dce2ed66ebe1 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1130,14 +1130,14 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu);
void ipv4_redirect(struct sk_buff *skb, struct net *net,
- int oif, u32 mark, u8 protocol, int flow_flags)
+ int oif, u8 protocol)
{
const struct iphdr *iph = (const struct iphdr *) skb->data;
struct flowi4 fl4;
struct rtable *rt;
__build_flow_key(net, &fl4, NULL, iph, oif,
- RT_TOS(iph->tos), protocol, mark, flow_flags);
+ RT_TOS(iph->tos), protocol, 0, 0);
rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
__ip_do_redirect(rt, skb, &fl4, false);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 085c588ebfe0..51c9f75f34b9 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -539,8 +539,8 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
goto out;
}
if (type == ICMP_REDIRECT) {
- ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
- iph->protocol, 0);
+ ipv4_redirect(skb, dev_net(skb->dev), t->parms.link,
+ iph->protocol);
err = 0;
goto out;
}
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 16bc5ecb7869..4b4ef4f662d9 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -471,7 +471,7 @@ static int xfrmi4_err(struct sk_buff *skb, u32 info)
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, protocol);
else
- ipv4_redirect(skb, net, 0, 0, protocol, 0);
+ ipv4_redirect(skb, net, 0, protocol);
xfrm_state_put(x);
return 0;
--
2.19.0.605.g01d371f741-goog
^ permalink raw reply related
* [PATCH 1/2] net-ipv4: remove 2 always zero parameters from ipv4_update_pmtu()
From: Maciej Żenczykowski @ 2018-09-26 0:41 UTC (permalink / raw)
To: Maciej Żenczykowski, David S . Miller, Eric Dumazet; +Cc: netdev
From: Maciej Żenczykowski <maze@google.com>
Signed-off-by: Maciej Żenczykowski <maze@google.com>
---
include/net/route.h | 2 +-
net/ipv4/ah4.c | 2 +-
net/ipv4/esp4.c | 2 +-
net/ipv4/icmp.c | 2 +-
net/ipv4/ip_gre.c | 2 +-
net/ipv4/ip_vti.c | 2 +-
net/ipv4/ipcomp.c | 2 +-
net/ipv4/ipip.c | 3 +--
net/ipv4/route.c | 8 +++-----
net/ipv6/sit.c | 2 +-
net/netfilter/ipvs/ip_vs_core.c | 3 +--
net/xfrm/xfrm_interface.c | 2 +-
12 files changed, 14 insertions(+), 18 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index bb53cdba38dc..73c605bdd6d8 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -201,7 +201,7 @@ static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
}
void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif,
- u32 mark, u8 protocol, int flow_flags);
+ u8 protocol);
void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu);
void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark,
u8 protocol, int flow_flags);
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 4dd95cdd8070..8811fe30282a 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -461,7 +461,7 @@ static int ah4_err(struct sk_buff *skb, u32 info)
return 0;
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
- ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0);
+ ipv4_update_pmtu(skb, net, info, 0, IPPROTO_AH);
else
ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0);
xfrm_state_put(x);
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 97689012b357..2d0274441923 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -820,7 +820,7 @@ static int esp4_err(struct sk_buff *skb, u32 info)
return 0;
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
- ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0);
+ ipv4_update_pmtu(skb, net, info, 0, IPPROTO_ESP);
else
ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0);
xfrm_state_put(x);
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 695979b7ef6d..8013b37b598f 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -1098,7 +1098,7 @@ void icmp_err(struct sk_buff *skb, u32 info)
}
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
- ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ICMP, 0);
+ ipv4_update_pmtu(skb, net, info, 0, IPPROTO_ICMP);
else if (type == ICMP_REDIRECT)
ipv4_redirect(skb, net, 0, 0, IPPROTO_ICMP, 0);
}
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index c3385a84f8ff..83b80fafd8f2 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -239,7 +239,7 @@ static void gre_err(struct sk_buff *skb, u32 info)
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
ipv4_update_pmtu(skb, dev_net(skb->dev), info,
- skb->dev->ifindex, 0, IPPROTO_GRE, 0);
+ skb->dev->ifindex, IPPROTO_GRE);
return;
}
if (type == ICMP_REDIRECT) {
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index f38cb21d773d..1b5571cb3282 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -318,7 +318,7 @@ static int vti4_err(struct sk_buff *skb, u32 info)
return 0;
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
- ipv4_update_pmtu(skb, net, info, 0, 0, protocol, 0);
+ ipv4_update_pmtu(skb, net, info, 0, protocol);
else
ipv4_redirect(skb, net, 0, 0, protocol, 0);
xfrm_state_put(x);
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index d97f4f2787f5..04049d1330a2 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -48,7 +48,7 @@ static int ipcomp4_err(struct sk_buff *skb, u32 info)
return 0;
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
- ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0);
+ ipv4_update_pmtu(skb, net, info, 0, IPPROTO_COMP);
else
ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0);
xfrm_state_put(x);
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index c891235b4966..6ff008e5818d 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -175,8 +175,7 @@ static int ipip_err(struct sk_buff *skb, u32 info)
}
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
- ipv4_update_pmtu(skb, net, info, t->parms.link, 0,
- iph->protocol, 0);
+ ipv4_update_pmtu(skb, net, info, t->parms.link, iph->protocol);
goto out;
}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b678466da451..7bbe3fc80b90 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1040,17 +1040,15 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
}
void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
- int oif, u32 mark, u8 protocol, int flow_flags)
+ int oif, u8 protocol)
{
const struct iphdr *iph = (const struct iphdr *) skb->data;
struct flowi4 fl4;
struct rtable *rt;
-
- if (!mark)
- mark = IP4_REPLY_MARK(net, skb->mark);
+ u32 mark = IP4_REPLY_MARK(net, skb->mark);
__build_flow_key(net, &fl4, NULL, iph, oif,
- RT_TOS(iph->tos), protocol, mark, flow_flags);
+ RT_TOS(iph->tos), protocol, mark, 0);
rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
__ip_rt_update_pmtu(rt, &fl4, mtu);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index e9400ffa7875..085c588ebfe0 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -534,7 +534,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
ipv4_update_pmtu(skb, dev_net(skb->dev), info,
- t->parms.link, 0, iph->protocol, 0);
+ t->parms.link, iph->protocol);
err = 0;
goto out;
}
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 7ca926a03b81..fe9abf3cc10a 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1686,8 +1686,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
skb_reset_network_header(skb);
IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n",
&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu);
- ipv4_update_pmtu(skb, ipvs->net,
- mtu, 0, 0, 0, 0);
+ ipv4_update_pmtu(skb, ipvs->net, mtu, 0, 0);
/* Client uses PMTUD? */
if (!(frag_off & htons(IP_DF)))
goto ignore_ipip;
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 31acc6f33d98..16bc5ecb7869 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -469,7 +469,7 @@ static int xfrmi4_err(struct sk_buff *skb, u32 info)
}
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
- ipv4_update_pmtu(skb, net, info, 0, 0, protocol, 0);
+ ipv4_update_pmtu(skb, net, info, 0, protocol);
else
ipv4_redirect(skb, net, 0, 0, protocol, 0);
xfrm_state_put(x);
--
2.19.0.605.g01d371f741-goog
^ permalink raw reply related
* [PATCH] net-tcp: /proc/sys/net/ipv4/tcp_probe_interval is a u32 not int
From: Maciej Żenczykowski @ 2018-09-26 0:41 UTC (permalink / raw)
To: Maciej Żenczykowski, David S . Miller, Eric Dumazet; +Cc: netdev
From: Maciej Żenczykowski <maze@google.com>
(fix documentation and sysctl access to treat it as such)
Signed-off-by: Maciej Żenczykowski <maze@google.com>
---
Documentation/networking/ip-sysctl.txt | 2 +-
net/ipv4/sysctl_net_ipv4.c | 4 ++--
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 8313a636dd53..960de8fe3f40 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -425,7 +425,7 @@ tcp_mtu_probing - INTEGER
1 - Disabled by default, enabled when an ICMP black hole detected
2 - Always enabled, use initial MSS of tcp_base_mss.
-tcp_probe_interval - INTEGER
+tcp_probe_interval - UNSIGNED INTEGER
Controls how often to start TCP Packetization-Layer Path MTU
Discovery reprobe. The default is reprobing every 10 minutes as
per RFC4821.
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index b92f422f2fa8..c8fa935c3cdb 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -745,9 +745,9 @@ static struct ctl_table ipv4_net_table[] = {
{
.procname = "tcp_probe_interval",
.data = &init_net.ipv4.sysctl_tcp_probe_interval,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(u32),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_douintvec,
},
{
.procname = "igmp_link_local_mcast_reports",
--
2.19.0.605.g01d371f741-goog
^ permalink raw reply related
* ASAP
From: Margaret Kwan Wing Han @ 2018-09-26 0:05 UTC (permalink / raw)
To: Westnet Support
I have a deal for you reply for more details.
Kind Regards,
Ms Margaret KWAN Wing Han
^ permalink raw reply
* Re: [PATCH net 00/15] netpoll: avoid capture effects for NAPI drivers
From: Song Liu @ 2018-09-25 23:36 UTC (permalink / raw)
To: Eric Dumazet
Cc: David Miller, netdev, michael.chan@broadcom.com, Ariel Elior,
Eric Dumazet, Tariq Toukan, Saeed Mahameed, Jeff Kirsher,
jakub.kicinski@netronome.com, Jay Vosburgh, Veaceslav Falico,
Andy Gospodarek
In-Reply-To: <CANn89i+8mngtTLs8gzmEFjreW9ie64MPmZWaUDV+KRR7wgNfMA@mail.gmail.com>
> On Sep 24, 2018, at 8:30 AM, Eric Dumazet <edumazet@google.com> wrote:
>
> On Sun, Sep 23, 2018 at 10:04 PM David Miller <davem@davemloft.net> wrote:
>>
>> Series applied, thanks Eric.
>
> Thanks David.
>
> Song, would you please this additional patch ?
>
> diff --git a/net/core/netpoll.c b/net/core/netpoll.c
> index 3219a2932463096566ce8ff336ecdf699422dd65..2ad45babe621b2c979ad5496b7df4342e4efbaa6
> 100644
> --- a/net/core/netpoll.c
> +++ b/net/core/netpoll.c
> @@ -150,13 +150,6 @@ static void poll_one_napi(struct napi_struct *napi)
> {
> int work = 0;
>
> - /* net_rx_action's ->poll() invocations and our's are
> - * synchronized by this test which is only made while
> - * holding the napi->poll_lock.
> - */
> - if (!test_bit(NAPI_STATE_SCHED, &napi->state))
> - return;
> -
> /* If we set this bit but see that it has already been set,
> * that indicates that napi has been disabled and we need
> * to abort this operation
Reviewed-and-tested-by: Song Liu <songliubraving@fb.com>
^ permalink raw reply
* Re: [PATCH net RFT] bnxt_en: Fix TX timeout during netpoll.
From: Song Liu @ 2018-09-25 23:35 UTC (permalink / raw)
To: Michael Chan
Cc: edumazet@google.com, davem@davemloft.net, netdev@vger.kernel.org
In-Reply-To: <1537911099-4073-1-git-send-email-michael.chan@broadcom.com>
Thanks Michael!
This works well in my tests.
Reviewed-and-tested-by: Song Liu <songliubraving@fb.com>
> On Sep 25, 2018, at 2:31 PM, Michael Chan <michael.chan@broadcom.com> wrote:
>
> The current netpoll implementation in the bnxt_en driver has problems
> that may miss TX completion events. bnxt_poll_work() in effect is
> only handling at most 1 TX packet before exiting. In addition,
> there may be in flight TX completions that ->poll() may miss even
> after we fix bnxt_poll_work() to handle all visible TX completions.
> netpoll may not call ->poll() again and HW may not generate IRQ
> because the driver does not ARM the IRQ when the budget (0 for netpoll)
> is reached.
>
> We fix it by handling all TX completions and to always ARM the IRQ
> when we exit ->poll() with 0 budget.
>
> Reported-by: Song Liu <songliubraving@fb.com>
> Signed-off-by: Michael Chan <michael.chan@broadcom.com>
> ---
> drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 ++++++--
> 1 file changed, 6 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> index 61957b0..c981b53 100644
> --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> @@ -1913,7 +1913,7 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
> }
> raw_cons = NEXT_RAW_CMP(raw_cons);
>
> - if (rx_pkts == budget)
> + if (rx_pkts && rx_pkts == budget)
> break;
> }
>
> @@ -2027,8 +2027,12 @@ static int bnxt_poll(struct napi_struct *napi, int budget)
> while (1) {
> work_done += bnxt_poll_work(bp, bnapi, budget - work_done);
>
> - if (work_done >= budget)
> + if (work_done >= budget) {
> + if (!budget)
> + BNXT_CP_DB_REARM(cpr->cp_doorbell,
> + cpr->cp_raw_cons);
> break;
> + }
>
> if (!bnxt_has_work(bp, cpr)) {
> if (napi_complete_done(napi, work_done))
> --
> 2.5.1
>
^ permalink raw reply
* Re: [PATCH net RFT] bnxt_en: Fix TX timeout during netpoll.
From: Michael Chan @ 2018-09-25 23:11 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Song Liu, Eric Dumazet, David Miller, Netdev
In-Reply-To: <c496aa4a-0fc1-9305-abfa-c287680e944a@gmail.com>
On Tue, Sep 25, 2018 at 3:15 PM Eric Dumazet <eric.dumazet@gmail.com> wrote:
>
> It seems bnx2 should have a similar issue ?
>
Yes, I think so. The MSIX mode in bnx2 is also auto-masking, meaning
that MSIX will only assert once after it is ARMed. If we return from
->poll() when budget of 0 is reached without ARMing, we may not get
another MSIX.
I can work on a similar patch but I don't have bnx2 cards to test with
anymore. Thanks.
^ permalink raw reply
* [PATCH bpf-next] bpftool: Fix bpftool net output
From: Andrey Ignatov @ 2018-09-25 22:20 UTC (permalink / raw)
To: netdev; +Cc: Andrey Ignatov, ast, daniel, yhs
Print `bpftool net` output to stdout instead of stderr. Only errors
should be printed to stderr. Regular output should go to stdout and this
is what all other subcommands of bpftool do, including --json and
--pretty formats of `bpftool net` itself.
Fixes: commit f6f3bac08ff9 ("tools/bpf: bpftool: add net support")
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
---
tools/bpf/bpftool/netlink_dumper.h | 18 +++++++++---------
1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/tools/bpf/bpftool/netlink_dumper.h b/tools/bpf/bpftool/netlink_dumper.h
index 0788cfbbed0e..e3516b586a34 100644
--- a/tools/bpf/bpftool/netlink_dumper.h
+++ b/tools/bpf/bpftool/netlink_dumper.h
@@ -16,7 +16,7 @@
jsonw_name(json_wtr, name); \
jsonw_start_object(json_wtr); \
} else { \
- fprintf(stderr, "%s {", name); \
+ fprintf(stdout, "%s {", name); \
} \
}
@@ -25,7 +25,7 @@
if (json_output) \
jsonw_start_object(json_wtr); \
else \
- fprintf(stderr, "{"); \
+ fprintf(stdout, "{"); \
}
#define NET_END_OBJECT_NESTED \
@@ -33,7 +33,7 @@
if (json_output) \
jsonw_end_object(json_wtr); \
else \
- fprintf(stderr, "}"); \
+ fprintf(stdout, "}"); \
}
#define NET_END_OBJECT \
@@ -47,7 +47,7 @@
if (json_output) \
jsonw_end_object(json_wtr); \
else \
- fprintf(stderr, "\n"); \
+ fprintf(stdout, "\n"); \
}
#define NET_START_ARRAY(name, fmt_str) \
@@ -56,7 +56,7 @@
jsonw_name(json_wtr, name); \
jsonw_start_array(json_wtr); \
} else { \
- fprintf(stderr, fmt_str, name); \
+ fprintf(stdout, fmt_str, name); \
} \
}
@@ -65,7 +65,7 @@
if (json_output) \
jsonw_end_array(json_wtr); \
else \
- fprintf(stderr, "%s", endstr); \
+ fprintf(stdout, "%s", endstr); \
}
#define NET_DUMP_UINT(name, fmt_str, val) \
@@ -73,7 +73,7 @@
if (json_output) \
jsonw_uint_field(json_wtr, name, val); \
else \
- fprintf(stderr, fmt_str, val); \
+ fprintf(stdout, fmt_str, val); \
}
#define NET_DUMP_STR(name, fmt_str, str) \
@@ -81,7 +81,7 @@
if (json_output) \
jsonw_string_field(json_wtr, name, str);\
else \
- fprintf(stderr, fmt_str, str); \
+ fprintf(stdout, fmt_str, str); \
}
#define NET_DUMP_STR_ONLY(str) \
@@ -89,7 +89,7 @@
if (json_output) \
jsonw_string(json_wtr, str); \
else \
- fprintf(stderr, "%s ", str); \
+ fprintf(stdout, "%s ", str); \
}
#endif
--
2.17.1
^ permalink raw reply related
* Re: [PATCH net RFT] bnxt_en: Fix TX timeout during netpoll.
From: Eric Dumazet @ 2018-09-25 22:15 UTC (permalink / raw)
To: Michael Chan, songliubraving, edumazet, davem; +Cc: netdev
In-Reply-To: <1537911099-4073-1-git-send-email-michael.chan@broadcom.com>
On 09/25/2018 02:31 PM, Michael Chan wrote:
> The current netpoll implementation in the bnxt_en driver has problems
> that may miss TX completion events. bnxt_poll_work() in effect is
> only handling at most 1 TX packet before exiting. In addition,
> there may be in flight TX completions that ->poll() may miss even
> after we fix bnxt_poll_work() to handle all visible TX completions.
> netpoll may not call ->poll() again and HW may not generate IRQ
> because the driver does not ARM the IRQ when the budget (0 for netpoll)
> is reached.
>
> We fix it by handling all TX completions and to always ARM the IRQ
> when we exit ->poll() with 0 budget.
>
> Reported-by: Song Liu <songliubraving@fb.com>
> Signed-off-by: Michael Chan <michael.chan@broadcom.com>
> ---
> drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 ++++++--
> 1 file changed, 6 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> index 61957b0..c981b53 100644
> --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> @@ -1913,7 +1913,7 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
> }
> raw_cons = NEXT_RAW_CMP(raw_cons);
>
> - if (rx_pkts == budget)
> + if (rx_pkts && rx_pkts == budget)
> break;
> }
>
> @@ -2027,8 +2027,12 @@ static int bnxt_poll(struct napi_struct *napi, int budget)
> while (1) {
> work_done += bnxt_poll_work(bp, bnapi, budget - work_done);
>
> - if (work_done >= budget)
> + if (work_done >= budget) {
> + if (!budget)
> + BNXT_CP_DB_REARM(cpr->cp_doorbell,
> + cpr->cp_raw_cons);
> break;
> + }
>
> if (!bnxt_has_work(bp, cpr)) {
> if (napi_complete_done(napi, work_done))
>
Hi Michael, thanks for the patch.
It seems bnx2 should have a similar issue ?
^ permalink raw reply
* Dobrodelna loterija zmagovalec.
From: Welch, Michael K @ 2018-09-25 21:59 UTC (permalink / raw)
Dobrodelna loterija zmagovalec.
Vaš e-poštni naslov je pravkar zmaga (One Hundred in petdeset tisoč. Evrov) € 150.000,00 v programu UPLIFT International Charity. Zap: SP / 229 / 0-01 / 07 / 5-02 / EC. Lucky št: 9/11/13/24/40.
Za dodatne informacije in zahtevek stiku postopku;
CAPITAL CLAIM AGENCY
Mr. John Carlos.
E-pošta: infocapitas@aim.com
Tel: + 34-634-027-588 (Govorite samo v angleščini)
S svojim polnim imenom, naslovom, starost, poklic, telefonske številke.
Pošlji odgovor na to E-pošta: infocapitas@aim.com
Opomba: To je mednarodni program loteriji. To sporočilo je bilo samodejno prevedena iz angleščine v Sloveniji.
Čestitke!!!.
-----------------------------------------------------------
Winner.
Your email address has just won € 150,000.00 (One Hundred and Fifty Thousand Euros) in the Uplift International Charity Lottery Program. Reference No: Sp / 229 / 0-01 / 07 / 5-02 / ES. Lucky No: 9/11/13/24/40.
For more information and claim procedure contact below.
CAPITAL CLAIM AGENCY
Mr. John Carlos.
Email: infocapitas@aim.com
Tel: + 34-634-027-588.
Your full name, address, age, occupation, phone numbers
Submit Reply to Email: infocapitas@aim.com
Congratulations!!!.
^ permalink raw reply
* Re: [net 1/1] tipc: lock wakeup & inputq at tipc_link_reset()
From: David Miller @ 2018-09-26 3:49 UTC (permalink / raw)
To: jon.maloy; +Cc: netdev, tipc-discussion
In-Reply-To: <1537906150-30955-1-git-send-email-jon.maloy@ericsson.com>
From: Jon Maloy <jon.maloy@ericsson.com>
Date: Tue, 25 Sep 2018 22:09:10 +0200
> From: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
>
> In tipc_link_reset() we copy the wakeup queue to input queue using
> skb_queue_splice_init(link->wakeupq, link->inputq).
> This is performed without holding any locks. The lists might be
> simultaneously be accessed by other cpu threads in tipc_sk_rcv(),
> something leading to to random missing packets.
>
> Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Applied.
^ permalink raw reply
* Re: [net 1/1] tipc: reset bearer if device carrier not ok
From: David Miller @ 2018-09-26 3:49 UTC (permalink / raw)
To: jon.maloy; +Cc: netdev, tipc-discussion
In-Reply-To: <1537905417-30804-1-git-send-email-jon.maloy@ericsson.com>
From: Jon Maloy <jon.maloy@ericsson.com>
Date: Tue, 25 Sep 2018 21:56:57 +0200
> From: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
>
> If we detect that under lying carrier detects errors and goes down,
> we reset the bearer.
>
> Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Applied.
^ permalink raw reply
* [PATCH net-next] bridge: br_arp_nd_proxy: set icmp6_router if neigh has NTF_ROUTER
From: Roopa Prabhu @ 2018-09-25 21:39 UTC (permalink / raw)
To: davem; +Cc: netdev
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Fixes: ed842faeb2bd ("bridge: suppress nd pkts on BR_NEIGH_SUPPRESS ports")
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
---
net/bridge/br_arp_nd_proxy.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c
index 2cf7716..d42e390 100644
--- a/net/bridge/br_arp_nd_proxy.c
+++ b/net/bridge/br_arp_nd_proxy.c
@@ -311,7 +311,7 @@ static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p,
/* Neighbor Advertisement */
memset(na, 0, sizeof(*na) + na_olen);
na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT;
- na->icmph.icmp6_router = 0; /* XXX: should be 1 ? */
+ na->icmph.icmp6_router = (n->flags & NTF_ROUTER) ? 1 : 0;
na->icmph.icmp6_override = 1;
na->icmph.icmp6_solicited = 1;
na->target = ns->target;
--
2.1.4
^ permalink raw reply related
* [PATCH net RFT] bnxt_en: Fix TX timeout during netpoll.
From: Michael Chan @ 2018-09-25 21:31 UTC (permalink / raw)
To: songliubraving, edumazet, davem; +Cc: netdev
The current netpoll implementation in the bnxt_en driver has problems
that may miss TX completion events. bnxt_poll_work() in effect is
only handling at most 1 TX packet before exiting. In addition,
there may be in flight TX completions that ->poll() may miss even
after we fix bnxt_poll_work() to handle all visible TX completions.
netpoll may not call ->poll() again and HW may not generate IRQ
because the driver does not ARM the IRQ when the budget (0 for netpoll)
is reached.
We fix it by handling all TX completions and to always ARM the IRQ
when we exit ->poll() with 0 budget.
Reported-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 61957b0..c981b53 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1913,7 +1913,7 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
}
raw_cons = NEXT_RAW_CMP(raw_cons);
- if (rx_pkts == budget)
+ if (rx_pkts && rx_pkts == budget)
break;
}
@@ -2027,8 +2027,12 @@ static int bnxt_poll(struct napi_struct *napi, int budget)
while (1) {
work_done += bnxt_poll_work(bp, bnapi, budget - work_done);
- if (work_done >= budget)
+ if (work_done >= budget) {
+ if (!budget)
+ BNXT_CP_DB_REARM(cpr->cp_doorbell,
+ cpr->cp_raw_cons);
break;
+ }
if (!bnxt_has_work(bp, cpr)) {
if (napi_complete_done(napi, work_done))
--
2.5.1
^ permalink raw reply related
* Urgent,
From: Juliet Muhammad @ 2018-09-25 21:06 UTC (permalink / raw)
To: Recipients
Hello
i have been trying to contact you i have a transaction for you.
^ permalink raw reply
* Re: bond: take rcu lock in bond_poll_controller
From: Cong Wang @ 2018-09-25 21:18 UTC (permalink / raw)
To: Dave Jones; +Cc: Linux Kernel Network Developers
In-Reply-To: <20180924192317.wghbs34ld7klqpi6@codemonkey.org.uk>
On Mon, Sep 24, 2018 at 1:08 PM Dave Jones <davej@codemonkey.org.uk> wrote:
>
> Callers of bond_for_each_slave_rcu are expected to hold the rcu lock,
> otherwise a trace like below is shown
Interesting, netpoll_send_skb_on_dev() already assumes RCU read lock
when it calls rcu_dereference_bh()...
I wonder how it can't catch such a warning before the one you reported.
^ permalink raw reply
* Re: [PATCH net-next 0/2] net: phy: Eliminate unnecessary soft
From: David Miller @ 2018-09-26 3:27 UTC (permalink / raw)
To: f.fainelli
Cc: netdev, andrew, linux-kernel, dongsheng.wang, cphealy,
clemens.gruber, hkallweit1, nbd, harini.katakam
In-Reply-To: <20180925182846.30042-1-f.fainelli@gmail.com>
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 25 Sep 2018 11:28:44 -0700
> This patch series eliminates unnecessary software resets of the PHY.
> This should hopefully not break anybody's hardware; but I would
> appreciate testing to make sure this is is the case.
>
> Sorry for this long email list, I wanted to make sure I reached out to
> all people who made changes to the Marvell PHY driver.
>
> Thank you!
>
> Changes since RFT:
>
> - added Tested-by tags from Wang, Dongsheng, Andrew, Chris and Clemens
Series applied.
^ permalink raw reply
* [PATCH iproute2 net-next] ipneigh: support setting of NTF_ROUTER on neigh entries
From: Roopa Prabhu @ 2018-09-25 21:15 UTC (permalink / raw)
To: dsahern; +Cc: netdev
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
---
ip/ipneigh.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/ip/ipneigh.c b/ip/ipneigh.c
index a0af705..5747152 100644
--- a/ip/ipneigh.c
+++ b/ip/ipneigh.c
@@ -139,6 +139,8 @@ static int ipneigh_modify(int cmd, int flags, int argc, char **argv)
dst_ok = 1;
dev_ok = 1;
req.ndm.ndm_flags |= NTF_PROXY;
+ } else if (strcmp(*argv, "router") == 0) {
+ req.ndm.ndm_flags |= NTF_ROUTER;
} else if (strcmp(*argv, "dev") == 0) {
NEXT_ARG();
dev = *argv;
--
2.1.4
^ permalink raw reply related
* Re: [PATCH net 00/15] netpoll: avoid capture effects for NAPI drivers
From: Michael Chan @ 2018-09-25 21:09 UTC (permalink / raw)
To: Song Liu
Cc: Eric Dumazet, David Miller, Netdev, Ariel Elior, Eric Dumazet,
tariqt, Saeed Mahameed, jeffrey.t.kirsher, Jakub Kicinski,
Jay Vosburgh, vfalico, Andy Gospodarek
In-Reply-To: <1D56BFAC-CC8A-49F2-BEC6-86B51C5BF5B7@fb.com>
On Tue, Sep 25, 2018 at 11:25 AM Song Liu <songliubraving@fb.com> wrote:
>
> Hi Michael,
>
> This may not be related. But I am looking at this:
>
> bnxt_poll_work() {
>
> while (1) {
> ....
> if (rx_pkts == budget)
> return
> }
> }
>
> With budget of 0, the loop will terminate after processing one packet.
> But I think the expectation is to finish all tx packets. So it doesn't
> feel right. Could you please confirm?
>
Right, this in effect is processing only 1 TX packet so it will be
inefficient at least.
But I think fixing it here still will not fix all the issues, because
even if we process all the TX packets here, we may still miss some
that are in flight. When we exit poll, netpoll may not call us back
again and there may be no interrupts because we don't ARM the IRQ when
budget of 0 is reached. I will send a test patch shortly for review
and testing. Thanks.
^ permalink raw reply
* I have been trying to contact you
From: Fridman Mikhail @ 2018-09-25 20:54 UTC (permalink / raw)
To: Recipients
I have been trying to contact you
^ permalink raw reply
* pull-request: bpf-next 2018-09-25
From: Daniel Borkmann @ 2018-09-25 20:43 UTC (permalink / raw)
To: davem; +Cc: daniel, ast, netdev
Hi David,
The following pull-request contains BPF updates for your *net-next* tree.
The main changes are:
1) Allow for RX stack hardening by implementing the kernel's flow
dissector in BPF. Idea was originally presented at netconf 2017 [0].
Quote from merge commit:
[...] Because of the rigorous checks of the BPF verifier, this
provides significant security guarantees. In particular, the BPF
flow dissector cannot get inside of an infinite loop, as with
CVE-2013-4348, because BPF programs are guaranteed to terminate.
It cannot read outside of packet bounds, because all memory accesses
are checked. Also, with BPF the administrator can decide which
protocols to support, reducing potential attack surface. Rarely
encountered protocols can be excluded from dissection and the
program can be updated without kernel recompile or reboot if a
bug is discovered. [...]
Also, a sample flow dissector has been implemented in BPF as part
of this work, from Petar and Willem.
[0] http://vger.kernel.org/netconf2017_files/rx_hardening_and_udp_gso.pdf
2) Add support for bpftool to list currently active attachment
points of BPF networking programs providing a quick overview
similar to bpftool's perf subcommand, from Yonghong.
3) Fix a verifier pruning instability bug where a union member
from the register state was not cleared properly leading to
branches not being pruned despite them being valid candidates,
from Alexei.
4) Various smaller fast-path optimizations in XDP's map redirect
code, from Jesper.
5) Enable to recognize BPF_MAP_TYPE_REUSEPORT_SOCKARRAY maps
in bpftool, from Roman.
6) Remove a duplicate check in libbpf that probes for function
storage, from Taeung.
7) Fix an issue in test_progs by avoid checking for errno since
on success its value should not be checked, from Mauricio.
8) Fix unused variable warning in bpf_getsockopt() helper when
CONFIG_INET is not configured, from Anders.
9) Fix a compilation failure in the BPF sample code's use of
bpf_flow_keys, from Prashant.
10) Minor cleanups in BPF code, from Yue and Zhong.
Please consider pulling these changes from:
git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git
Thanks a lot!
----------------------------------------------------------------
The following changes since commit 428f944bd58607021b5a1f85d145c0b50f908c6f:
netlink: Make groups check less stupid in netlink_bind() (2018-09-05 22:11:33 -0700)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git
for you to fetch changes up to d0e13a1488ad30dc3c2c9347b931cb10f892e3a4:
flow_dissector: lookup netns by skb->sk if skb->dev is NULL (2018-09-25 17:31:19 +0200)
----------------------------------------------------------------
Alexei Starovoitov (4):
bpf/verifier: fix verifier instability
Merge branch 'progarray_mapinmap_dump'
Merge branch 'bpf-flow-dissector'
selftests/bpf: fix bpf_flow.c build
Anders Roxell (1):
net/core/filter: fix unused-variable warning
Jesper Dangaard Brouer (3):
xdp: unlikely instrumentation for xdp map redirect
xdp: explicit inline __xdp_map_lookup_elem
xdp: split code for map vs non-map redirect
Mauricio Vasquez B (2):
selftests/bpf: add missing executables to .gitignore
selftests/bpf/test_progs: do not check errno == 0
Petar Penkov (5):
flow_dissector: implements flow dissector BPF hook
bpf: sync bpf.h uapi with tools/
bpf: support flow dissector in libbpf and bpftool
flow_dissector: implements eBPF parser
selftests/bpf: test bpf flow dissection
Prashant Bhole (1):
samples/bpf: fix compilation failure
Roman Gushchin (1):
bpftool: add support for BPF_MAP_TYPE_REUSEPORT_SOCKARRAY maps
Taeung Song (1):
libbpf: Remove the duplicate checking of function storage
Willem de Bruijn (2):
flow_dissector: fix build failure without CONFIG_NET
flow_dissector: lookup netns by skb->sk if skb->dev is NULL
Yonghong Song (9):
tools/bpf: sync kernel uapi header if_link.h to tools
tools/bpf: move bpf/lib netlink related functions into a new file
tools/bpf: add more netlink functionalities in lib/bpf
tools/bpf: bpftool: add net support
bpf: add bpffs pretty print for program array map
tools/bpf: bpftool: support prog array map and map of maps
tools/bpf: fix a netlink recv issue
tools/bpf: bpftool: improve output format for bpftool net
samples/bpf: fix a compilation failure
YueHaibing (1):
samples/bpf: remove duplicated includes
zhong jiang (1):
bpf: remove redundant null pointer check before consume_skb
include/linux/bpf.h | 1 +
include/linux/bpf_types.h | 1 +
include/linux/skbuff.h | 20 +
include/net/net_namespace.h | 3 +
include/net/sch_generic.h | 12 +-
include/uapi/linux/bpf.h | 26 +
kernel/bpf/arraymap.c | 25 +-
kernel/bpf/sockmap.c | 6 +-
kernel/bpf/syscall.c | 8 +
kernel/bpf/verifier.c | 48 +-
net/core/filter.c | 139 +++-
net/core/flow_dissector.c | 140 ++++
samples/bpf/bpf_load.c | 1 -
samples/bpf/sampleip_user.c | 1 -
samples/bpf/sockex2_kern.c | 11 +-
samples/bpf/sockex3_kern.c | 8 +-
samples/bpf/sockex3_user.c | 4 +-
samples/bpf/test_current_task_under_cgroup_user.c | 1 -
tools/bpf/bpftool/Documentation/bpftool-net.rst | 139 ++++
tools/bpf/bpftool/Documentation/bpftool.rst | 6 +-
tools/bpf/bpftool/bash-completion/bpftool | 17 +-
tools/bpf/bpftool/main.c | 3 +-
tools/bpf/bpftool/main.h | 8 +
tools/bpf/bpftool/map.c | 12 +-
tools/bpf/bpftool/net.c | 272 +++++++
tools/bpf/bpftool/netlink_dumper.c | 174 +++++
tools/bpf/bpftool/netlink_dumper.h | 95 +++
tools/bpf/bpftool/prog.c | 1 +
tools/include/uapi/linux/bpf.h | 26 +
tools/include/uapi/linux/if_link.h | 17 +
tools/lib/bpf/Build | 2 +-
tools/lib/bpf/bpf.c | 129 ----
tools/lib/bpf/libbpf.c | 4 +-
tools/lib/bpf/libbpf.h | 16 +
tools/lib/bpf/libbpf_errno.c | 1 +
tools/lib/bpf/netlink.c | 331 +++++++++
tools/lib/bpf/nlattr.c | 33 +-
tools/lib/bpf/nlattr.h | 38 +
tools/testing/selftests/bpf/.gitignore | 6 +
tools/testing/selftests/bpf/Makefile | 8 +-
tools/testing/selftests/bpf/bpf_flow.c | 373 ++++++++++
tools/testing/selftests/bpf/config | 1 +
tools/testing/selftests/bpf/flow_dissector_load.c | 140 ++++
tools/testing/selftests/bpf/test_flow_dissector.c | 782 +++++++++++++++++++++
tools/testing/selftests/bpf/test_flow_dissector.sh | 115 +++
tools/testing/selftests/bpf/test_progs.c | 20 +-
tools/testing/selftests/bpf/with_addr.sh | 54 ++
tools/testing/selftests/bpf/with_tunnels.sh | 36 +
48 files changed, 3083 insertions(+), 231 deletions(-)
create mode 100644 tools/bpf/bpftool/Documentation/bpftool-net.rst
create mode 100644 tools/bpf/bpftool/net.c
create mode 100644 tools/bpf/bpftool/netlink_dumper.c
create mode 100644 tools/bpf/bpftool/netlink_dumper.h
create mode 100644 tools/lib/bpf/netlink.c
create mode 100644 tools/testing/selftests/bpf/bpf_flow.c
create mode 100644 tools/testing/selftests/bpf/flow_dissector_load.c
create mode 100644 tools/testing/selftests/bpf/test_flow_dissector.c
create mode 100755 tools/testing/selftests/bpf/test_flow_dissector.sh
create mode 100755 tools/testing/selftests/bpf/with_addr.sh
create mode 100755 tools/testing/selftests/bpf/with_tunnels.sh
^ permalink raw reply
* [net-next 06/10] i40e: Remove unused msglen parameter from virtchnl functions
From: Jeff Kirsher @ 2018-09-25 20:20 UTC (permalink / raw)
To: davem; +Cc: Patryk Małek, netdev, nhorman, sassmann, jogreene,
Jeff Kirsher
In-Reply-To: <20180925202004.27726-1-jeffrey.t.kirsher@intel.com>
From: Patryk Małek <patryk.malek@intel.com>
msglen parameter seems to be unused in several virtchnl function.
This patch removes it from signatures of those functions.
Signed-off-by: Patryk Małek <patryk.malek@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
.../ethernet/intel/i40e/i40e_virtchnl_pf.c | 96 +++++++------------
1 file changed, 37 insertions(+), 59 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 5d5ffde1e93b..f4bb2779f03a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1973,13 +1973,11 @@ static inline int i40e_getnum_vf_vsi_vlan_filters(struct i40e_vsi *vsi)
* i40e_vc_config_promiscuous_mode_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* called from the VF to configure the promiscuous mode of
* VF vsis
**/
-static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf,
- u8 *msg, u16 msglen)
+static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_promisc_info *info =
(struct virtchnl_promisc_info *)msg;
@@ -2034,12 +2032,11 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf,
* i40e_vc_config_queues_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* called from the VF to configure the rx/tx
* queues
**/
-static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_vsi_queue_config_info *qci =
(struct virtchnl_vsi_queue_config_info *)msg;
@@ -2152,12 +2149,11 @@ static int i40e_validate_queue_map(struct i40e_vf *vf, u16 vsi_id,
* i40e_vc_config_irq_map_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* called from the VF to configure the irq to
* queue map
**/
-static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_irq_map_info *irqmap_info =
(struct virtchnl_irq_map_info *)msg;
@@ -2249,11 +2245,10 @@ static int i40e_ctrl_vf_rx_rings(struct i40e_vsi *vsi, unsigned long q_map,
* i40e_vc_enable_queues_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* called from the VF to enable all or specific queue(s)
**/
-static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_queue_select *vqs =
(struct virtchnl_queue_select *)msg;
@@ -2308,12 +2303,11 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
* i40e_vc_disable_queues_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* called from the VF to disable all or specific
* queue(s)
**/
-static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_queue_select *vqs =
(struct virtchnl_queue_select *)msg;
@@ -2356,14 +2350,13 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
* i40e_vc_request_queues_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* VFs get a default number of queues but can use this message to request a
* different number. If the request is successful, PF will reset the VF and
* return 0. If unsuccessful, PF will send message informing VF of number of
* available queues and return result of sending VF a message.
**/
-static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg, int msglen)
+static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_vf_res_request *vfres =
(struct virtchnl_vf_res_request *)msg;
@@ -2407,11 +2400,10 @@ static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg, int msglen)
* i40e_vc_get_stats_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* called from the VF to get vsi stats
**/
-static int i40e_vc_get_stats_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_get_stats_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_queue_select *vqs =
(struct virtchnl_queue_select *)msg;
@@ -2517,11 +2509,10 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf,
* i40e_vc_add_mac_addr_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* add guest mac address filter
**/
-static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_ether_addr_list *al =
(struct virtchnl_ether_addr_list *)msg;
@@ -2588,11 +2579,10 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
* i40e_vc_del_mac_addr_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* remove guest mac address filter
**/
-static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_ether_addr_list *al =
(struct virtchnl_ether_addr_list *)msg;
@@ -2658,11 +2648,10 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
* i40e_vc_add_vlan_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* program guest vlan id
**/
-static int i40e_vc_add_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_add_vlan_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_vlan_filter_list *vfl =
(struct virtchnl_vlan_filter_list *)msg;
@@ -2731,11 +2720,10 @@ static int i40e_vc_add_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
* i40e_vc_remove_vlan_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* remove programmed guest vlan id
**/
-static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_vlan_filter_list *vfl =
(struct virtchnl_vlan_filter_list *)msg;
@@ -2818,13 +2806,11 @@ static int i40e_vc_iwarp_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
* i40e_vc_iwarp_qvmap_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
* @config: config qvmap or release it
*
* called from the VF for the iwarp msgs
**/
-static int i40e_vc_iwarp_qvmap_msg(struct i40e_vf *vf, u8 *msg, u16 msglen,
- bool config)
+static int i40e_vc_iwarp_qvmap_msg(struct i40e_vf *vf, u8 *msg, bool config)
{
struct virtchnl_iwarp_qvlist_info *qvlist_info =
(struct virtchnl_iwarp_qvlist_info *)msg;
@@ -2855,11 +2841,10 @@ static int i40e_vc_iwarp_qvmap_msg(struct i40e_vf *vf, u8 *msg, u16 msglen,
* i40e_vc_config_rss_key
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* Configure the VF's RSS key
**/
-static int i40e_vc_config_rss_key(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_config_rss_key(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_rss_key *vrk =
(struct virtchnl_rss_key *)msg;
@@ -2887,11 +2872,10 @@ static int i40e_vc_config_rss_key(struct i40e_vf *vf, u8 *msg, u16 msglen)
* i40e_vc_config_rss_lut
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* Configure the VF's RSS LUT
**/
-static int i40e_vc_config_rss_lut(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_config_rss_lut(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_rss_lut *vrl =
(struct virtchnl_rss_lut *)msg;
@@ -2919,11 +2903,10 @@ static int i40e_vc_config_rss_lut(struct i40e_vf *vf, u8 *msg, u16 msglen)
* i40e_vc_get_rss_hena
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* Return the RSS HENA bits allowed by the hardware
**/
-static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_rss_hena *vrh = NULL;
struct i40e_pf *pf = vf->pf;
@@ -2955,11 +2938,10 @@ static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg, u16 msglen)
* i40e_vc_set_rss_hena
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* Set the RSS HENA bits for the VF
**/
-static int i40e_vc_set_rss_hena(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_set_rss_hena(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_rss_hena *vrh =
(struct virtchnl_rss_hena *)msg;
@@ -2984,12 +2966,10 @@ static int i40e_vc_set_rss_hena(struct i40e_vf *vf, u8 *msg, u16 msglen)
* i40e_vc_enable_vlan_stripping
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* Enable vlan header stripping for the VF
**/
-static int i40e_vc_enable_vlan_stripping(struct i40e_vf *vf, u8 *msg,
- u16 msglen)
+static int i40e_vc_enable_vlan_stripping(struct i40e_vf *vf, u8 *msg)
{
struct i40e_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx];
i40e_status aq_ret = 0;
@@ -3011,12 +2991,10 @@ static int i40e_vc_enable_vlan_stripping(struct i40e_vf *vf, u8 *msg,
* i40e_vc_disable_vlan_stripping
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* Disable vlan header stripping for the VF
**/
-static int i40e_vc_disable_vlan_stripping(struct i40e_vf *vf, u8 *msg,
- u16 msglen)
+static int i40e_vc_disable_vlan_stripping(struct i40e_vf *vf, u8 *msg)
{
struct i40e_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx];
i40e_status aq_ret = 0;
@@ -3716,65 +3694,65 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode,
ret = 0;
break;
case VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE:
- ret = i40e_vc_config_promiscuous_mode_msg(vf, msg, msglen);
+ ret = i40e_vc_config_promiscuous_mode_msg(vf, msg);
break;
case VIRTCHNL_OP_CONFIG_VSI_QUEUES:
- ret = i40e_vc_config_queues_msg(vf, msg, msglen);
+ ret = i40e_vc_config_queues_msg(vf, msg);
break;
case VIRTCHNL_OP_CONFIG_IRQ_MAP:
- ret = i40e_vc_config_irq_map_msg(vf, msg, msglen);
+ ret = i40e_vc_config_irq_map_msg(vf, msg);
break;
case VIRTCHNL_OP_ENABLE_QUEUES:
- ret = i40e_vc_enable_queues_msg(vf, msg, msglen);
+ ret = i40e_vc_enable_queues_msg(vf, msg);
i40e_vc_notify_vf_link_state(vf);
break;
case VIRTCHNL_OP_DISABLE_QUEUES:
- ret = i40e_vc_disable_queues_msg(vf, msg, msglen);
+ ret = i40e_vc_disable_queues_msg(vf, msg);
break;
case VIRTCHNL_OP_ADD_ETH_ADDR:
- ret = i40e_vc_add_mac_addr_msg(vf, msg, msglen);
+ ret = i40e_vc_add_mac_addr_msg(vf, msg);
break;
case VIRTCHNL_OP_DEL_ETH_ADDR:
- ret = i40e_vc_del_mac_addr_msg(vf, msg, msglen);
+ ret = i40e_vc_del_mac_addr_msg(vf, msg);
break;
case VIRTCHNL_OP_ADD_VLAN:
- ret = i40e_vc_add_vlan_msg(vf, msg, msglen);
+ ret = i40e_vc_add_vlan_msg(vf, msg);
break;
case VIRTCHNL_OP_DEL_VLAN:
- ret = i40e_vc_remove_vlan_msg(vf, msg, msglen);
+ ret = i40e_vc_remove_vlan_msg(vf, msg);
break;
case VIRTCHNL_OP_GET_STATS:
- ret = i40e_vc_get_stats_msg(vf, msg, msglen);
+ ret = i40e_vc_get_stats_msg(vf, msg);
break;
case VIRTCHNL_OP_IWARP:
ret = i40e_vc_iwarp_msg(vf, msg, msglen);
break;
case VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP:
- ret = i40e_vc_iwarp_qvmap_msg(vf, msg, msglen, true);
+ ret = i40e_vc_iwarp_qvmap_msg(vf, msg, true);
break;
case VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP:
- ret = i40e_vc_iwarp_qvmap_msg(vf, msg, msglen, false);
+ ret = i40e_vc_iwarp_qvmap_msg(vf, msg, false);
break;
case VIRTCHNL_OP_CONFIG_RSS_KEY:
- ret = i40e_vc_config_rss_key(vf, msg, msglen);
+ ret = i40e_vc_config_rss_key(vf, msg);
break;
case VIRTCHNL_OP_CONFIG_RSS_LUT:
- ret = i40e_vc_config_rss_lut(vf, msg, msglen);
+ ret = i40e_vc_config_rss_lut(vf, msg);
break;
case VIRTCHNL_OP_GET_RSS_HENA_CAPS:
- ret = i40e_vc_get_rss_hena(vf, msg, msglen);
+ ret = i40e_vc_get_rss_hena(vf, msg);
break;
case VIRTCHNL_OP_SET_RSS_HENA:
- ret = i40e_vc_set_rss_hena(vf, msg, msglen);
+ ret = i40e_vc_set_rss_hena(vf, msg);
break;
case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING:
- ret = i40e_vc_enable_vlan_stripping(vf, msg, msglen);
+ ret = i40e_vc_enable_vlan_stripping(vf, msg);
break;
case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING:
- ret = i40e_vc_disable_vlan_stripping(vf, msg, msglen);
+ ret = i40e_vc_disable_vlan_stripping(vf, msg);
break;
case VIRTCHNL_OP_REQUEST_QUEUES:
- ret = i40e_vc_request_queues_msg(vf, msg, msglen);
+ ret = i40e_vc_request_queues_msg(vf, msg);
break;
case VIRTCHNL_OP_ENABLE_CHANNELS:
ret = i40e_vc_add_qch_msg(vf, msg);
--
2.17.1
^ permalink raw reply related
* [net-next 09/10] i40e: clean zero-copy XDP Rx ring on shutdown/reset
From: Jeff Kirsher @ 2018-09-25 20:20 UTC (permalink / raw)
To: davem
Cc: Björn Töpel, netdev, nhorman, sassmann, jogreene,
Jeff Kirsher
In-Reply-To: <20180925202004.27726-1-jeffrey.t.kirsher@intel.com>
From: Björn Töpel <bjorn.topel@intel.com>
Outstanding Rx descriptors are temporarily stored on a stash/reuse
queue. When/if the HW rings comes up again, entries from the stash are
used to re-populate the ring.
The latter required some restructuring of the allocation scheme for
the AF_XDP zero-copy implementation. There is now a fast, and a slow
allocation. The "fast allocation" is used from the fast-path and
obtains free buffers from the fill ring and the internal recycle
mechanism. The "slow allocation" is only used in ring setup, and
obtains buffers from the fill ring and the stash (if any).
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_txrx.c | 4 +-
.../ethernet/intel/i40e/i40e_txrx_common.h | 1 +
drivers/net/ethernet/intel/i40e/i40e_xsk.c | 100 ++++++++++++++++--
3 files changed, 96 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 7f85d4ba8b54..740ea58ba938 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1355,8 +1355,10 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
rx_ring->skb = NULL;
}
- if (rx_ring->xsk_umem)
+ if (rx_ring->xsk_umem) {
+ i40e_xsk_clean_rx_ring(rx_ring);
goto skip_free;
+ }
/* Free all the Rx ring sk_buffs */
for (i = 0; i < rx_ring->count; i++) {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
index 29c68b29d36f..8d46acff6f2e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
@@ -87,6 +87,7 @@ static inline void i40e_arm_wb(struct i40e_ring *tx_ring,
}
}
+void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring);
void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring);
#endif /* I40E_TXRX_COMMON_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index d5a9f5b7cfa9..386703883713 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -140,6 +140,7 @@ static void i40e_xsk_umem_dma_unmap(struct i40e_vsi *vsi, struct xdp_umem *umem)
static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
u16 qid)
{
+ struct xdp_umem_fq_reuse *reuseq;
bool if_running;
int err;
@@ -156,6 +157,12 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
return -EBUSY;
}
+ reuseq = xsk_reuseq_prepare(vsi->rx_rings[0]->count);
+ if (!reuseq)
+ return -ENOMEM;
+
+ xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq));
+
err = i40e_xsk_umem_dma_map(vsi, umem);
if (err)
return err;
@@ -353,16 +360,46 @@ static bool i40e_alloc_buffer_zc(struct i40e_ring *rx_ring,
}
/**
- * i40e_alloc_rx_buffers_zc - Allocates a number of Rx buffers
+ * i40e_alloc_buffer_slow_zc - Allocates an i40e_rx_buffer
* @rx_ring: Rx ring
- * @count: The number of buffers to allocate
+ * @bi: Rx buffer to populate
*
- * This function allocates a number of Rx buffers and places them on
- * the Rx ring.
+ * This function allocates an Rx buffer. The buffer can come from fill
+ * queue, or via the reuse queue.
*
* Returns true for a successful allocation, false otherwise
**/
-bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count)
+static bool i40e_alloc_buffer_slow_zc(struct i40e_ring *rx_ring,
+ struct i40e_rx_buffer *bi)
+{
+ struct xdp_umem *umem = rx_ring->xsk_umem;
+ u64 handle, hr;
+
+ if (!xsk_umem_peek_addr_rq(umem, &handle)) {
+ rx_ring->rx_stats.alloc_page_failed++;
+ return false;
+ }
+
+ handle &= rx_ring->xsk_umem->chunk_mask;
+
+ hr = umem->headroom + XDP_PACKET_HEADROOM;
+
+ bi->dma = xdp_umem_get_dma(umem, handle);
+ bi->dma += hr;
+
+ bi->addr = xdp_umem_get_data(umem, handle);
+ bi->addr += hr;
+
+ bi->handle = handle + umem->headroom;
+
+ xsk_umem_discard_addr_rq(umem);
+ return true;
+}
+
+static __always_inline bool
+__i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count,
+ bool alloc(struct i40e_ring *rx_ring,
+ struct i40e_rx_buffer *bi))
{
u16 ntu = rx_ring->next_to_use;
union i40e_rx_desc *rx_desc;
@@ -372,7 +409,7 @@ bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count)
rx_desc = I40E_RX_DESC(rx_ring, ntu);
bi = &rx_ring->rx_bi[ntu];
do {
- if (!i40e_alloc_buffer_zc(rx_ring, bi)) {
+ if (!alloc(rx_ring, bi)) {
ok = false;
goto no_buffers;
}
@@ -404,6 +441,38 @@ bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count)
return ok;
}
+/**
+ * i40e_alloc_rx_buffers_zc - Allocates a number of Rx buffers
+ * @rx_ring: Rx ring
+ * @count: The number of buffers to allocate
+ *
+ * This function allocates a number of Rx buffers from the reuse queue
+ * or fill ring and places them on the Rx ring.
+ *
+ * Returns true for a successful allocation, false otherwise
+ **/
+bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count)
+{
+ return __i40e_alloc_rx_buffers_zc(rx_ring, count,
+ i40e_alloc_buffer_slow_zc);
+}
+
+/**
+ * i40e_alloc_rx_buffers_fast_zc - Allocates a number of Rx buffers
+ * @rx_ring: Rx ring
+ * @count: The number of buffers to allocate
+ *
+ * This function allocates a number of Rx buffers from the fill ring
+ * or the internal recycle mechanism and places them on the Rx ring.
+ *
+ * Returns true for a successful allocation, false otherwise
+ **/
+static bool i40e_alloc_rx_buffers_fast_zc(struct i40e_ring *rx_ring, u16 count)
+{
+ return __i40e_alloc_rx_buffers_zc(rx_ring, count,
+ i40e_alloc_buffer_zc);
+}
+
/**
* i40e_get_rx_buffer_zc - Return the current Rx buffer
* @rx_ring: Rx ring
@@ -571,8 +640,8 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
if (cleaned_count >= I40E_RX_BUFFER_WRITE) {
failure = failure ||
- !i40e_alloc_rx_buffers_zc(rx_ring,
- cleaned_count);
+ !i40e_alloc_rx_buffers_fast_zc(rx_ring,
+ cleaned_count);
cleaned_count = 0;
}
@@ -831,6 +900,21 @@ int i40e_xsk_async_xmit(struct net_device *dev, u32 queue_id)
return 0;
}
+void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring)
+{
+ u16 i;
+
+ for (i = 0; i < rx_ring->count; i++) {
+ struct i40e_rx_buffer *rx_bi = &rx_ring->rx_bi[i];
+
+ if (!rx_bi->addr)
+ continue;
+
+ xsk_umem_fq_reuse(rx_ring->xsk_umem, rx_bi->handle);
+ rx_bi->addr = NULL;
+ }
+}
+
/**
* i40e_xsk_clean_xdp_ring - Clean the XDP Tx ring on shutdown
* @xdp_ring: XDP Tx ring
--
2.17.1
^ permalink raw reply related
* [net-next 07/10] i40e: clean zero-copy XDP Tx ring on shutdown/reset
From: Jeff Kirsher @ 2018-09-25 20:20 UTC (permalink / raw)
To: davem
Cc: Björn Töpel, netdev, nhorman, sassmann, jogreene,
Jeff Kirsher
In-Reply-To: <20180925202004.27726-1-jeffrey.t.kirsher@intel.com>
From: Björn Töpel <bjorn.topel@intel.com>
When the zero-copy enabled XDP Tx ring is torn down, due to
configuration changes, outstanding frames on the hardware descriptor
ring are queued on the completion ring.
The completion ring has a back-pressure mechanism that will guarantee
that there is sufficient space on the ring.
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_txrx.c | 17 +++++++----
.../ethernet/intel/i40e/i40e_txrx_common.h | 2 ++
drivers/net/ethernet/intel/i40e/i40e_xsk.c | 30 +++++++++++++++++++
3 files changed, 43 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 37bd4e50ccde..7f85d4ba8b54 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -636,13 +636,18 @@ void i40e_clean_tx_ring(struct i40e_ring *tx_ring)
unsigned long bi_size;
u16 i;
- /* ring already cleared, nothing to do */
- if (!tx_ring->tx_bi)
- return;
+ if (ring_is_xdp(tx_ring) && tx_ring->xsk_umem) {
+ i40e_xsk_clean_tx_ring(tx_ring);
+ } else {
+ /* ring already cleared, nothing to do */
+ if (!tx_ring->tx_bi)
+ return;
- /* Free all the Tx ring sk_buffs */
- for (i = 0; i < tx_ring->count; i++)
- i40e_unmap_and_free_tx_resource(tx_ring, &tx_ring->tx_bi[i]);
+ /* Free all the Tx ring sk_buffs */
+ for (i = 0; i < tx_ring->count; i++)
+ i40e_unmap_and_free_tx_resource(tx_ring,
+ &tx_ring->tx_bi[i]);
+ }
bi_size = sizeof(struct i40e_tx_buffer) * tx_ring->count;
memset(tx_ring->tx_bi, 0, bi_size);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
index b5afd479a9c5..29c68b29d36f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
@@ -87,4 +87,6 @@ static inline void i40e_arm_wb(struct i40e_ring *tx_ring,
}
}
+void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring);
+
#endif /* I40E_TXRX_COMMON_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 2ebfc78bbd09..d5a9f5b7cfa9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -830,3 +830,33 @@ int i40e_xsk_async_xmit(struct net_device *dev, u32 queue_id)
return 0;
}
+
+/**
+ * i40e_xsk_clean_xdp_ring - Clean the XDP Tx ring on shutdown
+ * @xdp_ring: XDP Tx ring
+ **/
+void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring)
+{
+ u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use;
+ struct xdp_umem *umem = tx_ring->xsk_umem;
+ struct i40e_tx_buffer *tx_bi;
+ u32 xsk_frames = 0;
+
+ while (ntc != ntu) {
+ tx_bi = &tx_ring->tx_bi[ntc];
+
+ if (tx_bi->xdpf)
+ i40e_clean_xdp_tx_buffer(tx_ring, tx_bi);
+ else
+ xsk_frames++;
+
+ tx_bi->xdpf = NULL;
+
+ ntc++;
+ if (ntc >= tx_ring->count)
+ ntc = 0;
+ }
+
+ if (xsk_frames)
+ xsk_umem_complete_tx(umem, xsk_frames);
+}
--
2.17.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox