* [PATCH net-next 2/3] net: act_tunnel_key: support for tunnel type
From: Pablo Neira Ayuso @ 2018-10-09 22:24 UTC (permalink / raw)
To: netfilter-devel
Cc: davem, netdev, roopa, amir, pshelar, u9012063, daniel,
jakub.kicinski
In-Reply-To: <20181009222439.29399-1-pablo@netfilter.org>
This patch allows you to set an explicit tunnel driver type in the
metadata template. In case of misconfiguration, ie. if the packets ends
up in the wrong tunnel device, the packet is dropped.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/uapi/linux/tc_act/tc_tunnel_key.h | 1 +
net/sched/act_tunnel_key.c | 9 +++++++++
2 files changed, 10 insertions(+)
diff --git a/include/uapi/linux/tc_act/tc_tunnel_key.h b/include/uapi/linux/tc_act/tc_tunnel_key.h
index be384d63e1b5..b9822433e7f1 100644
--- a/include/uapi/linux/tc_act/tc_tunnel_key.h
+++ b/include/uapi/linux/tc_act/tc_tunnel_key.h
@@ -41,6 +41,7 @@ enum {
*/
TCA_TUNNEL_KEY_ENC_TOS, /* u8 */
TCA_TUNNEL_KEY_ENC_TTL, /* u8 */
+ TCA_TUNNEL_KEY_ENC_TYPE, /* u32 */
__TCA_TUNNEL_KEY_MAX,
};
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 4cca8f274662..7852715603e9 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -195,6 +195,7 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = {
[TCA_TUNNEL_KEY_ENC_OPTS] = { .type = NLA_NESTED },
[TCA_TUNNEL_KEY_ENC_TOS] = { .type = NLA_U8 },
[TCA_TUNNEL_KEY_ENC_TTL] = { .type = NLA_U8 },
+ [TCA_TUNNEL_KEY_ENC_TYPE] = { .type = NLA_U32 },
};
static int tunnel_key_init(struct net *net, struct nlattr *nla,
@@ -215,6 +216,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
__be16 flags;
u8 tos, ttl;
int ret = 0;
+ u32 type;
int err;
if (!nla) {
@@ -278,6 +280,10 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
if (tb[TCA_TUNNEL_KEY_ENC_TTL])
ttl = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_TTL]);
+ type = TUNNEL_TYPE_UNSPEC;
+ if (tb[TCA_TUNNEL_KEY_ENC_TYPE])
+ type = nla_get_u32(tb[TCA_TUNNEL_KEY_ENC_TYPE]);
+
if (tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC] &&
tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]) {
__be32 saddr;
@@ -320,6 +326,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
goto release_tun_meta;
}
+ metadata->u.tun_info.type = type;
metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX;
break;
default:
@@ -522,6 +529,8 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a,
if (key->ttl && nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_TTL, key->ttl))
goto nla_put_failure;
+ if (nla_put_u32(skb, TCA_TUNNEL_KEY_ENC_TYPE, info->type))
+ goto nla_put_failure;
}
tcf_tm_dump(&tm, &t->tcf_tm);
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 1/3] ip_tunnel: add type field to struct ip_tunnel_info
From: Pablo Neira Ayuso @ 2018-10-09 22:24 UTC (permalink / raw)
To: netfilter-devel
Cc: davem, netdev, roopa, amir, pshelar, u9012063, daniel,
jakub.kicinski
In-Reply-To: <20181009222439.29399-1-pablo@netfilter.org>
This new field allows you to restrict the metadata template for a given
tunnel driver. This is convenient in scenarios that combine different
tunneling drivers, eg. vxlan and erspan. This helps you deal with
possible incorrect configurations. Default value is TUNNEL_TYPE_UNSPEC,
to retain the existing behaviour. This also implicitly exposes what
drivers are currently supported in the TUNNEL_INFO_TX mode.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
drivers/net/geneve.c | 3 ++-
drivers/net/vxlan.c | 13 +++++++------
include/net/dst_metadata.h | 1 +
include/net/ip_tunnels.h | 8 ++++++++
include/uapi/linux/if_tunnel.h | 13 ++++++++++++-
net/core/filter.c | 1 +
net/ipv4/ip_gre.c | 2 ++
net/ipv4/ip_tunnel.c | 3 ++-
net/ipv6/ip6_gre.c | 2 ++
net/ipv6/ip6_tunnel.c | 6 ++++--
net/openvswitch/flow_netlink.c | 1 +
11 files changed, 42 insertions(+), 11 deletions(-)
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 82eccc930c5c..e4fd2acb6732 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -920,7 +920,8 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
if (geneve->collect_md) {
info = skb_tunnel_info(skb);
- if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) {
+ if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX) ||
+ !ip_tunnel_type(info, TUNNEL_TYPE_GENEVE))) {
err = -EINVAL;
netdev_dbg(dev, "no tunnel metadata\n");
goto tx_error;
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index fb0cdbba8d76..c279c50816cf 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2296,14 +2296,15 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
skb_reset_mac_header(skb);
if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) {
- if (info && info->mode & IP_TUNNEL_INFO_BRIDGE &&
- info->mode & IP_TUNNEL_INFO_TX) {
+ if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX) ||
+ !ip_tunnel_type(info, TUNNEL_TYPE_VXLAN))) {
+ kfree_skb(skb);
+ return NETDEV_TX_OK;
+ }
+ if (info->mode & IP_TUNNEL_INFO_BRIDGE) {
vni = tunnel_id_to_key32(info->key.tun_id);
} else {
- if (info && info->mode & IP_TUNNEL_INFO_TX)
- vxlan_xmit_one(skb, dev, vni, NULL, false);
- else
- kfree_skb(skb);
+ vxlan_xmit_one(skb, dev, vni, NULL, false);
return NETDEV_TX_OK;
}
}
diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
index 56cb3c38569a..fb3865b2f038 100644
--- a/include/net/dst_metadata.h
+++ b/include/net/dst_metadata.h
@@ -100,6 +100,7 @@ static inline struct metadata_dst *tun_rx_dst(int md_size)
if (!tun_dst)
return NULL;
+ tun_dst->u.tun_info.type = TUNNEL_TYPE_UNSPEC;
tun_dst->u.tun_info.options_len = 0;
tun_dst->u.tun_info.mode = 0;
return tun_dst;
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index b0d022ff6ea1..34d748ca8b30 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -67,6 +67,7 @@ struct ip_tunnel_key {
options_len) * BITS_PER_BYTE) - 1, 0)
struct ip_tunnel_info {
+ enum tunnel_type type;
struct ip_tunnel_key key;
#ifdef CONFIG_DST_CACHE
struct dst_cache dst_cache;
@@ -75,6 +76,13 @@ struct ip_tunnel_info {
u8 mode;
};
+static inline bool ip_tunnel_type(const struct ip_tunnel_info *tun_info,
+ enum tunnel_type type)
+{
+ return tun_info->type == TUNNEL_TYPE_UNSPEC ||
+ tun_info->type == type;
+}
+
/* 6rd prefix/relay information */
#ifdef CONFIG_IPV6_SIT_6RD
struct ip_tunnel_6rd_parm {
diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index 1b3d148c4560..1659b81fbae6 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -158,6 +158,17 @@ enum {
IFLA_VTI_FWMARK,
__IFLA_VTI_MAX,
};
-
#define IFLA_VTI_MAX (__IFLA_VTI_MAX - 1)
+
+enum tunnel_type {
+ TUNNEL_TYPE_UNSPEC = 0,
+ TUNNEL_TYPE_GRE,
+ TUNNEL_TYPE_VXLAN,
+ TUNNEL_TYPE_GENEVE,
+ TUNNEL_TYPE_ERSPAN,
+ TUNNEL_TYPE_IPIP,
+ TUNNEL_TYPE_IPIP6,
+ TUNNEL_TYPE_IP6IP6,
+};
+
#endif /* _UAPI_IF_TUNNEL_H_ */
diff --git a/net/core/filter.c b/net/core/filter.c
index 4bbc6567fcb8..2e75e1b014df 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3654,6 +3654,7 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb,
info = &md->u.tun_info;
memset(info, 0, sizeof(*info));
info->mode = IP_TUNNEL_INFO_TX;
+ info->type = TUNNEL_TYPE_UNSPEC;
info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE;
if (flags & BPF_F_DONT_FRAGMENT)
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 38befe829caf..ab5de3901bc3 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -534,6 +534,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev,
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
+ !ip_tunnel_type(tun_info, TUNNEL_TYPE_GRE) ||
ip_tunnel_info_af(tun_info) != AF_INET))
goto err_free_skb;
@@ -585,6 +586,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev,
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
+ !ip_tunnel_type(tun_info, TUNNEL_TYPE_ERSPAN) ||
ip_tunnel_info_af(tun_info) != AF_INET))
goto err_free_skb;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 284a22154b4e..b62b424183b4 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -562,7 +562,8 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto)
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
- ip_tunnel_info_af(tun_info) != AF_INET))
+ ip_tunnel_info_af(tun_info) != AF_INET) ||
+ !ip_tunnel_type(tun_info, TUNNEL_TYPE_IPIP))
goto tx_error;
key = &tun_info->key;
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 515adbdba1d2..7ff469652e6f 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -732,6 +732,7 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info ||
!(tun_info->mode & IP_TUNNEL_INFO_TX) ||
+ !ip_tunnel_type(tun_info, TUNNEL_TYPE_GRE) ||
ip_tunnel_info_af(tun_info) != AF_INET6))
return -EINVAL;
@@ -960,6 +961,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info ||
!(tun_info->mode & IP_TUNNEL_INFO_TX) ||
+ !ip_tunnel_type(tun_info, TUNNEL_TYPE_ERSPAN) ||
ip_tunnel_info_af(tun_info) != AF_INET6))
return -EINVAL;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index a0b6932c3afd..819abbcd2ebe 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1259,7 +1259,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
- ip_tunnel_info_af(tun_info) != AF_INET6))
+ ip_tunnel_info_af(tun_info) != AF_INET6) ||
+ !ip_tunnel_type(tun_info, TUNNEL_TYPE_IPIP6))
return -1;
key = &tun_info->key;
memset(&fl6, 0, sizeof(fl6));
@@ -1335,7 +1336,8 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
- ip_tunnel_info_af(tun_info) != AF_INET6))
+ ip_tunnel_info_af(tun_info) != AF_INET6 ||
+ !ip_tunnel_type(tun_info, TUNNEL_TYPE_IP6IP6)))
return -1;
key = &tun_info->key;
memset(&fl6, 0, sizeof(fl6));
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index a70097ecf33c..29623ad54611 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2602,6 +2602,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
ovs_tun->tun_dst = tun_dst;
tun_info = &tun_dst->u.tun_info;
+ tun_info->type = TUNNEL_TYPE_UNSPEC;
tun_info->mode = IP_TUNNEL_INFO_TX;
if (key.tun_proto == AF_INET6)
tun_info->mode |= IP_TUNNEL_INFO_IPV6;
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 0/3] ip_tunnel: specify tunnel type via template
From: Pablo Neira Ayuso @ 2018-10-09 22:24 UTC (permalink / raw)
To: netfilter-devel
Cc: davem, netdev, roopa, amir, pshelar, u9012063, daniel,
jakub.kicinski
Hi,
The following patchset adds a new field to the tunnel metadata template.
This new field allows us to restrict the configuration to a given tunnel
driver in order to catch incorrect configuration that may result in
packets going to the wrong tunnel driver.
Changes with regards to initial RFC [1] are:
1) Explicit tunnel type initialization to TUNNEL_TYPE_UNSPEC in existing
clients for this code, as requested by Daniel.
2) Add TUNNEL_TYPE_* definition through enum tunnel_type in
uapi/linux/if_tunnel.h, so we don't need to redefine this in every
client of this infrastructure.
3) Add TUNNEL_TYPE_IPIP, TUNNEL_TYPE_IPIP6 and TUNNEL_TYPE_IP6IP6, which
were missing in the original RFC.
Let me know if you any more comments, thanks.
[1] https://marc.info/?l=netfilter-devel&m=153861145204094&w=2
Pablo Neira Ayuso (3):
ip_tunnel: add type field to struct ip_tunnel_info
net: act_tunnel_key: support for tunnel type
netfilter: nft_tunnel: support for tunnel type
drivers/net/geneve.c | 3 ++-
drivers/net/vxlan.c | 13 +++++++------
include/net/dst_metadata.h | 1 +
include/net/ip_tunnels.h | 8 ++++++++
include/uapi/linux/if_tunnel.h | 13 ++++++++++++-
include/uapi/linux/netfilter/nf_tables.h | 1 +
include/uapi/linux/tc_act/tc_tunnel_key.h | 1 +
net/core/filter.c | 1 +
net/ipv4/ip_gre.c | 2 ++
net/ipv4/ip_tunnel.c | 3 ++-
net/ipv6/ip6_gre.c | 2 ++
net/ipv6/ip6_tunnel.c | 6 ++++--
net/netfilter/nft_tunnel.c | 9 ++++++++-
net/openvswitch/flow_netlink.c | 1 +
net/sched/act_tunnel_key.c | 9 +++++++++
15 files changed, 61 insertions(+), 12 deletions(-)
^ permalink raw reply
* [PATCH net-next] net: sched: avoid writing on noop_qdisc
From: Eric Dumazet @ 2018-10-09 22:20 UTC (permalink / raw)
To: David S . Miller; +Cc: netdev, John Fastabend, Eric Dumazet, Eric Dumazet
While noop_qdisc.gso_skb and noop_qdisc.skb_bad_txq are not used
in other places, it seems not correct to overwrite their fields
in dev_init_scheduler_queue().
noop_qdisc is essentially a shared and read-only object, even if
it is not marked as const because of some implementation detail.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
net/sched/sch_generic.c | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 3023929852e8c4aaa4172861d2d0beff17e25f27..de1663f7d3ad6e2c06cd2e031036cef5979366a5 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -572,6 +572,18 @@ struct Qdisc noop_qdisc = {
.dev_queue = &noop_netdev_queue,
.running = SEQCNT_ZERO(noop_qdisc.running),
.busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock),
+ .gso_skb = {
+ .next = (struct sk_buff *)&noop_qdisc.gso_skb,
+ .prev = (struct sk_buff *)&noop_qdisc.gso_skb,
+ .qlen = 0,
+ .lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.gso_skb.lock),
+ },
+ .skb_bad_txq = {
+ .next = (struct sk_buff *)&noop_qdisc.skb_bad_txq,
+ .prev = (struct sk_buff *)&noop_qdisc.skb_bad_txq,
+ .qlen = 0,
+ .lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.skb_bad_txq.lock),
+ },
};
EXPORT_SYMBOL(noop_qdisc);
@@ -1273,8 +1285,6 @@ static void dev_init_scheduler_queue(struct net_device *dev,
rcu_assign_pointer(dev_queue->qdisc, qdisc);
dev_queue->qdisc_sleeping = qdisc;
- __skb_queue_head_init(&qdisc->gso_skb);
- __skb_queue_head_init(&qdisc->skb_bad_txq);
}
void dev_init_scheduler(struct net_device *dev)
--
2.19.0.605.g01d371f741-goog
^ permalink raw reply related
* Re: [PATCH bpf-next 0/6] Consistent prefixes for libbpf interfaces
From: Daniel Borkmann @ 2018-10-09 22:17 UTC (permalink / raw)
To: Yonghong Song, Andrey Ignatov, netdev@vger.kernel.org
Cc: ast@kernel.org, Kernel Team
In-Reply-To: <73d17896-e452-de4a-4cf6-d251bb0ef24c@fb.com>
On 10/09/2018 08:43 AM, Yonghong Song wrote:
> On 10/4/18 7:22 AM, Daniel Borkmann wrote:
>> [ +Yonghong ]
>>
>> On 10/04/2018 12:26 AM, Andrey Ignatov wrote:
>>> This patch set renames a few interfaces in libbpf, mostly netlink related,
>>> so that all symbols provided by the library have only three possible
>>> prefixes:
>>>
>>> % nm -D tools/lib/bpf/libbpf.so | \
>>> awk '$2 == "T" {sub(/[_\(].*/, "", $3); if ($3) print $3}' | \
>>> sort | \
>>> uniq -c
>>> 91 bpf
>>> 8 btf
>>> 14 libbpf
>>>
>>> libbpf is used more and more outside kernel tree. That means the library
>>> should follow good practices in library design and implementation to
>>> play well with third party code that uses it.
>>>
>>> One of such practices is to have a common prefix (or a few) for every
>>> interface, function or data structure, library provides. It helps to
>>> avoid name conflicts with other libraries and keeps API/ABI consistent.
>>>
>>> Inconsistent names in libbpf already cause problems in real life. E.g.
>>> an application can't use both libbpf and libnl due to conflicting
>>> symbols (specifically nla_parse, nla_parse_nested and a few others).
>>>
>>> Some of problematic global symbols are not part of ABI and can be
>>> restricted from export with either visibility attribute/pragma or export
>>> map (what is useful by itself and can be done in addition). That won't
>>> solve the problem for those that are part of ABI though. Also export
>>> restrictions would help only in DSO case. If third party application links
>>> libbpf statically it won't help, and people do it (e.g. Facebook links
>>> most of libraries statically, including libbpf).
>>>
>>> libbpf already uses the following prefixes for its interfaces:
>>> * bpf_ for bpf system call wrappers, program/map/elf-object
>>> abstractions and a few other things;
>>> * btf_ for BTF related API;
>>> * libbpf_ for everything else.
>>>
>>> The patch adds libbpf_ prefix to interfaces that use none of mentioned
>>> above prefixes and don't fit well into the first two categories.
>>>
>>> Long term benefits of having common prefix should outweigh possible
>>> inconvenience of changing API for those functions now.
>>>
>>> Patches 2-4 add libbpf_ prefix to libbpf interfaces: separate patch per
>>> header. Other patches are simple improvements in API.
>>>
>>>
>>> Andrey Ignatov (6):
>>> libbpf: Move __dump_nlmsg_t from API to implementation
>>> libbpf: Consistent prefixes for interfaces in libbpf.h.
>>> libbpf: Consistent prefixes for interfaces in nlattr.h.
>>> libbpf: Consistent prefixes for interfaces in str_error.h.
>>> libbpf: Make include guards consistent
>>> libbpf: Use __u32 instead of u32 in bpf_program__load
>>>
>>> tools/bpf/bpftool/net.c | 41 ++++++++++---------
>>> tools/bpf/bpftool/netlink_dumper.c | 32 ++++++++-------
>>> tools/lib/bpf/bpf.h | 6 +--
>>> tools/lib/bpf/btf.h | 6 +--
>>> tools/lib/bpf/libbpf.c | 22 +++++-----
>>> tools/lib/bpf/libbpf.h | 31 +++++++-------
>>> tools/lib/bpf/netlink.c | 48 ++++++++++++----------
>>> tools/lib/bpf/nlattr.c | 64 +++++++++++++++--------------
>>> tools/lib/bpf/nlattr.h | 65 +++++++++++++++---------------
>>> tools/lib/bpf/str_error.c | 2 +-
>>> tools/lib/bpf/str_error.h | 8 ++--
>>> 11 files changed, 171 insertions(+), 154 deletions(-)
>>
>> Overall agree that this is needed, and I've therefore applied the
>> set, thanks for cleaning up, Andrey!
>>
>> But, I would actually like to see this going one step further, in
>> particular, we should keep all the netlink related stuff inside
>> libbpf-/only/. Meaning, the goal of libbpf is not to provide yet
>> another set of netlink primitives but instead e.g. for the bpftool
>> dumper this should be abstracted away such that we pass in a callback
>> from bpftool side and have an iterator object which will then be
>> populated from inside the libbpf logic, meaning, bpftool shouldn't
>> even be aware of anything netlink there.
>
> Agreed. This indeed make sense, the user really only cares a few fields
> like devname/id, attachment_type, prog_id, etc. I will take a look at
> this later if nobody works on it.
Awesome, that would be great, thanks!
^ permalink raw reply
* Re: [PATCH net v2] net/sched: cls_api: add missing validation of netlink attributes
From: Cong Wang @ 2018-10-09 22:12 UTC (permalink / raw)
To: Davide Caratti
Cc: David Miller, David Ahern, Jamal Hadi Salim,
Linux Kernel Network Developers
In-Reply-To: <25a127708c97408a747c08a328441dee1d652f79.1539120141.git.dcaratti@redhat.com>
On Tue, Oct 9, 2018 at 2:26 PM Davide Caratti <dcaratti@redhat.com> wrote:
> --- a/net/sched/sch_api.c
> +++ b/net/sched/sch_api.c
> @@ -1322,6 +1322,7 @@ const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = {
> [TCA_INGRESS_BLOCK] = { .type = NLA_U32 },
> [TCA_EGRESS_BLOCK] = { .type = NLA_U32 },
> };
> +EXPORT_SYMBOL(rtm_tca_policy);
cls_api.c is not a module, so you don't need to export it.
^ permalink raw reply
* Re: [PATCH] bpf: btf: Fix a missing check bug
From: Alexei Starovoitov @ 2018-10-10 4:47 UTC (permalink / raw)
To: Song Liu
Cc: valdis.kletnieks, wang6495, kjlu, Alexei Starovoitov,
Daniel Borkmann, Networking, open list
In-Reply-To: <CAPhsuW7-Xa=_2BTATEhthWnyfETPv173p_cG2YrcCZ0BOsS9ow@mail.gmail.com>
On Mon, Oct 08, 2018 at 11:55:15PM -0700, Song Liu wrote:
> On Mon, Oct 8, 2018 at 6:07 PM <valdis.kletnieks@vt.edu> wrote:
> >
> > On Mon, 08 Oct 2018 17:44:46 -0700, Song Liu said:
> >
> > > I think I get the security concept here. However, hdr_len here is only used to
> > > copy the whole header into kernel space, and it is not used in other
> > > logic at all.
> > > I cannot image any security flaw with either hdr_len > btf->hdr->hdr_len case or
> > > hdr_len < btf->hdr->hdr_len. Could you please provide more insights on what
> > > would break by malicious user space?
> >
> > Say the biggest allowed value for hdr_len is 128. We check the value, the user has 98.
> > They then stuff 16,383 into there.
> >
> > Now here's the problem - hdr_len is a local variable, and evaporates when the function
> > returns. From here on out, anybody who cares about the header length will use the
> > value in btf->hdr_len....
> >
> > (And yes, somebody *does* care about the length, otherwise we wouldn't need a field
> > saying what the length was....)
> >
> > Now think how many ways that can go pear-shaped. You copied in 98 bytes, but outside
> > the function, they think that header is almost 4 pages long. Does that ever get used as
> > a length for kmemcpy()? Or a limit for a 'for (i=start; i< (start+hdr->hdr_len); i++)' that
> > walks across a variable length header?
> >
> > Can you cook up a way to have a good chance to oops the kernel when it walks off the
> > page you allocated the 98 bytes on? Can you use it to export chunks of memory out to
> > userspace? Lots and lots of ways for this to kersplat a kernel...;
>
> In current code, I don't thing any malicious hdr_len value could pass
> btf_check_sec_info().
> On the other hand, I agree this is a good-to-have check.
>
> Acked-by: Song Liu <songliubraving@fb.com>
I agree with Song's analysis that the current shape of code in
btf_check_sec_info() has us covered, but it's a good coding style
to check for TOCTOU like this, hence applied to bpf-next.
^ permalink raw reply
* [PATCH net-next] net/ipv6: Add knob to skip DELROUTE message on device down
From: David Ahern @ 2018-10-09 21:27 UTC (permalink / raw)
To: netdev, davem; +Cc: roopa, David Ahern
From: David Ahern <dsahern@gmail.com>
Another difference between IPv4 and IPv6 is the generation of RTM_DELROUTE
notifications when a device is taken down (admin down) or deleted. IPv4
does not generate a message for routes evicted by the down or delete;
IPv6 does. A NOS at scale really needs to avoid these messages and have
IPv4 and IPv6 behave similarly, relying on userspace to handle link
notifications and evict the routes.
At this point existing user behavior needs to be preserved. Since
notifications are a global action (not per app) the only way to preserve
existing behavior and allow the messages to be skipped is to add a new
sysctl (net/ipv6/route/skip_notify_on_dev_down) which can be set to
disable the notificatioons.
IPv6 route code already supports the option to skip the message (it is
used for multipath routes for example). Besides the new sysctl we need
to pass the skip_notify setting through the generic fib6_clean and
fib6_walk functions to fib6_clean_node and to set skip_notify on calls
to __ip_del_rt for the addrconf_ifdown path.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
Documentation/networking/ip-sysctl.txt | 8 +++++++
include/net/addrconf.h | 3 ++-
include/net/ip6_fib.h | 3 +++
include/net/ip6_route.h | 1 +
include/net/netns/ipv6.h | 1 +
net/ipv6/addrconf.c | 44 ++++++++++++++++++++++------------
net/ipv6/anycast.c | 10 +++++---
net/ipv6/ip6_fib.c | 20 ++++++++++++----
net/ipv6/route.c | 30 ++++++++++++++++++++++-
9 files changed, 95 insertions(+), 25 deletions(-)
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 960de8fe3f40..163b5ff1073c 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1442,6 +1442,14 @@ max_hbh_length - INTEGER
header.
Default: INT_MAX (unlimited)
+skip_notify_on_dev_down - BOOLEAN
+ Controls whether an RTM_DELROUTE message is generated for routes
+ removed when a device is taken down or deleted. IPv4 does not
+ generate this message; IPv6 does by default. Setting this sysctl
+ to true skips the message, making IPv4 and IPv6 on par in relying
+ on userspace caches to track link events and evict routes.
+ Default: false (generate message)
+
IPv6 Fragmentation:
ip6frag_high_thresh - INTEGER
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 6def0351bcc3..ee6292f64c86 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -306,7 +306,8 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex,
void ipv6_sock_ac_close(struct sock *sk);
int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr);
-int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr);
+int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr,
+ bool skip_notify);
void ipv6_ac_destroy_dev(struct inet6_dev *idev);
bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev,
const struct in6_addr *addr);
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index f06e968f1992..caabfd84a098 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -407,6 +407,9 @@ struct fib6_node *fib6_locate(struct fib6_node *root,
void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *arg),
void *arg);
+void fib6_clean_all_skip_notify(struct net *net,
+ int (*func)(struct fib6_info *, void *arg),
+ void *arg);
int fib6_add(struct fib6_node *root, struct fib6_info *rt,
struct nl_info *info, struct netlink_ext_ack *extack);
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index cef186dbd2ce..7c140cb2eeb0 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -104,6 +104,7 @@ int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,
struct netlink_ext_ack *extack);
int ip6_ins_rt(struct net *net, struct fib6_info *f6i);
int ip6_del_rt(struct net *net, struct fib6_info *f6i);
+int ip6_del_rt_skip_notify(struct net *net, struct fib6_info *f6i);
void rt6_flush_exceptions(struct fib6_info *f6i);
void rt6_age_exceptions(struct fib6_info *f6i, struct fib6_gc_args *gc_args,
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index f0e396ab9bec..ef1ed529f33c 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -45,6 +45,7 @@ struct netns_sysctl_ipv6 {
int max_dst_opts_len;
int max_hbh_opts_len;
int seg6_flowlabel;
+ bool skip_notify_on_dev_down;
};
struct netns_ipv6 {
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 2496b12bf721..cf591cf66884 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -164,7 +164,7 @@ static struct workqueue_struct *addrconf_wq;
static DECLARE_DELAYED_WORK(addr_chk_work, addrconf_verify_work);
static void addrconf_join_anycast(struct inet6_ifaddr *ifp);
-static void addrconf_leave_anycast(struct inet6_ifaddr *ifp);
+static void addrconf_leave_anycast(struct inet6_ifaddr *ifp, bool skip_notify);
static void addrconf_type_change(struct net_device *dev,
unsigned long event);
@@ -181,7 +181,8 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id,
bool send_na);
static void addrconf_dad_run(struct inet6_dev *idev);
static void addrconf_rs_timer(struct timer_list *t);
-static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
+static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa,
+ bool skip_notify);
static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
static void inet6_prefix_notify(int event, struct inet6_dev *idev,
@@ -779,7 +780,7 @@ static void dev_forward_change(struct inet6_dev *idev)
if (idev->cnf.forwarding)
addrconf_join_anycast(ifa);
else
- addrconf_leave_anycast(ifa);
+ addrconf_leave_anycast(ifa, false);
}
inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
NETCONFA_FORWARDING,
@@ -2141,7 +2142,7 @@ static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
}
/* caller must hold RTNL */
-static void addrconf_leave_anycast(struct inet6_ifaddr *ifp)
+static void addrconf_leave_anycast(struct inet6_ifaddr *ifp, bool skip_notify)
{
struct in6_addr addr;
@@ -2150,7 +2151,7 @@ static void addrconf_leave_anycast(struct inet6_ifaddr *ifp)
ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
if (ipv6_addr_any(&addr))
return;
- __ipv6_dev_ac_dec(ifp->idev, &addr);
+ __ipv6_dev_ac_dec(ifp->idev, &addr, skip_notify);
}
static int addrconf_ifid_6lowpan(u8 *eui, struct net_device *dev)
@@ -3655,6 +3656,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
{
unsigned long event = how ? NETDEV_UNREGISTER : NETDEV_DOWN;
struct net *net = dev_net(dev);
+ bool skip_notify = net->ipv6.sysctl.skip_notify_on_dev_down;
struct inet6_dev *idev;
struct inet6_ifaddr *ifa, *tmp;
bool keep_addr = false;
@@ -3772,15 +3774,19 @@ static int addrconf_ifdown(struct net_device *dev, int how)
spin_unlock_bh(&ifa->lock);
- if (rt)
- ip6_del_rt(net, rt);
+ if (rt) {
+ if (skip_notify)
+ ip6_del_rt_skip_notify(net, rt);
+ else
+ ip6_del_rt(net, rt);
+ }
if (state != INET6_IFADDR_STATE_DEAD) {
- __ipv6_ifa_notify(RTM_DELADDR, ifa);
+ __ipv6_ifa_notify(RTM_DELADDR, ifa, skip_notify);
inet6addr_notifier_call_chain(NETDEV_DOWN, ifa);
} else {
if (idev->cnf.forwarding)
- addrconf_leave_anycast(ifa);
+ addrconf_leave_anycast(ifa, skip_notify);
addrconf_leave_solict(ifa->idev, &ifa->addr);
}
@@ -5830,7 +5836,8 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev,
rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err);
}
-static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
+static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp,
+ bool skip_notify)
{
struct net *net = dev_net(ifp->idev->dev);
@@ -5858,18 +5865,25 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
break;
case RTM_DELADDR:
if (ifp->idev->cnf.forwarding)
- addrconf_leave_anycast(ifp);
+ addrconf_leave_anycast(ifp, skip_notify);
addrconf_leave_solict(ifp->idev, &ifp->addr);
if (!ipv6_addr_any(&ifp->peer_addr)) {
struct fib6_info *rt;
rt = addrconf_get_prefix_route(&ifp->peer_addr, 128,
ifp->idev->dev, 0, 0);
- if (rt)
- ip6_del_rt(net, rt);
+ if (rt) {
+ if (skip_notify)
+ ip6_del_rt_skip_notify(net, rt);
+ else
+ ip6_del_rt(net, rt);
+ }
}
if (ifp->rt) {
- ip6_del_rt(net, ifp->rt);
+ if (skip_notify)
+ ip6_del_rt_skip_notify(net, ifp->rt);
+ else
+ ip6_del_rt(net, ifp->rt);
ifp->rt = NULL;
}
rt_genid_bump_ipv6(net);
@@ -5882,7 +5896,7 @@ static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
{
rcu_read_lock_bh();
if (likely(ifp->idev->dead == 0))
- __ipv6_ifa_notify(event, ifp);
+ __ipv6_ifa_notify(event, ifp, false);
rcu_read_unlock_bh();
}
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 4e0ff7031edd..762fb1de58a8 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -299,7 +299,8 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
/*
* device anycast group decrement
*/
-int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr)
+int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr,
+ bool skip_notify)
{
struct ifacaddr6 *aca, *prev_aca;
@@ -327,7 +328,10 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr)
write_unlock_bh(&idev->lock);
addrconf_leave_solict(idev, &aca->aca_addr);
- ip6_del_rt(dev_net(idev->dev), aca->aca_rt);
+ if (skip_notify)
+ ip6_del_rt_skip_notify(dev_net(idev->dev), aca->aca_rt);
+ else
+ ip6_del_rt(dev_net(idev->dev), aca->aca_rt);
aca_put(aca);
return 0;
@@ -340,7 +344,7 @@ static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr)
if (!idev)
return -ENODEV;
- return __ipv6_dev_ac_dec(idev, addr);
+ return __ipv6_dev_ac_dec(idev, addr, false);
}
void ipv6_ac_destroy_dev(struct inet6_dev *idev)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index e14d244c551f..9ba72d94d60f 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -47,6 +47,7 @@ struct fib6_cleaner {
int (*func)(struct fib6_info *, void *arg);
int sernum;
void *arg;
+ bool skip_notify;
};
#ifdef CONFIG_IPV6_SUBTREES
@@ -1956,6 +1957,7 @@ static int fib6_clean_node(struct fib6_walker *w)
struct fib6_cleaner *c = container_of(w, struct fib6_cleaner, w);
struct nl_info info = {
.nl_net = c->net,
+ .skip_notify = c->skip_notify,
};
if (c->sernum != FIB6_NO_SERNUM_CHANGE &&
@@ -2007,7 +2009,7 @@ static int fib6_clean_node(struct fib6_walker *w)
static void fib6_clean_tree(struct net *net, struct fib6_node *root,
int (*func)(struct fib6_info *, void *arg),
- int sernum, void *arg)
+ int sernum, void *arg, bool skip_notify)
{
struct fib6_cleaner c;
@@ -2019,13 +2021,14 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root,
c.sernum = sernum;
c.arg = arg;
c.net = net;
+ c.skip_notify = skip_notify;
fib6_walk(net, &c.w);
}
static void __fib6_clean_all(struct net *net,
int (*func)(struct fib6_info *, void *),
- int sernum, void *arg)
+ int sernum, void *arg, bool skip_notify)
{
struct fib6_table *table;
struct hlist_head *head;
@@ -2037,7 +2040,7 @@ static void __fib6_clean_all(struct net *net,
hlist_for_each_entry_rcu(table, head, tb6_hlist) {
spin_lock_bh(&table->tb6_lock);
fib6_clean_tree(net, &table->tb6_root,
- func, sernum, arg);
+ func, sernum, arg, skip_notify);
spin_unlock_bh(&table->tb6_lock);
}
}
@@ -2047,14 +2050,21 @@ static void __fib6_clean_all(struct net *net,
void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *),
void *arg)
{
- __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg);
+ __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg, false);
+}
+
+void fib6_clean_all_skip_notify(struct net *net,
+ int (*func)(struct fib6_info *, void *),
+ void *arg)
+{
+ __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg, true);
}
static void fib6_flush_trees(struct net *net)
{
int new_sernum = fib6_new_sernum(net);
- __fib6_clean_all(net, NULL, new_sernum, NULL);
+ __fib6_clean_all(net, NULL, new_sernum, NULL, false);
}
/*
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 7c38e0e058ae..de161808c540 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3143,6 +3143,16 @@ static int __ip6_del_rt(struct fib6_info *rt, struct nl_info *info)
return err;
}
+int ip6_del_rt_skip_notify(struct net *net, struct fib6_info *rt)
+{
+ struct nl_info info = {
+ .nl_net = net,
+ .skip_notify = true,
+ };
+
+ return __ip6_del_rt(rt, &info);
+}
+
int ip6_del_rt(struct net *net, struct fib6_info *rt)
{
struct nl_info info = { .nl_net = net };
@@ -4026,8 +4036,12 @@ void rt6_sync_down_dev(struct net_device *dev, unsigned long event)
.event = event,
},
};
+ struct net *net = dev_net(dev);
- fib6_clean_all(dev_net(dev), fib6_ifdown, &arg);
+ if (net->ipv6.sysctl.skip_notify_on_dev_down)
+ fib6_clean_all_skip_notify(net, fib6_ifdown, &arg);
+ else
+ fib6_clean_all(net, fib6_ifdown, &arg);
}
void rt6_disable_ip(struct net_device *dev, unsigned long event)
@@ -5031,6 +5045,9 @@ int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write,
return 0;
}
+static int zero;
+static int one = 1;
+
struct ctl_table ipv6_route_table_template[] = {
{
.procname = "flush",
@@ -5102,6 +5119,15 @@ struct ctl_table ipv6_route_table_template[] = {
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
},
+ {
+ .procname = "skip_notify_on_dev_down",
+ .data = &init_net.ipv6.sysctl.skip_notify_on_dev_down,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
{ }
};
@@ -5125,6 +5151,7 @@ struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net)
table[7].data = &net->ipv6.sysctl.ip6_rt_mtu_expires;
table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss;
table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval;
+ table[10].data = &net->ipv6.sysctl.skip_notify_on_dev_down;
/* Don't export sysctls to unprivileged users */
if (net->user_ns != &init_user_ns)
@@ -5189,6 +5216,7 @@ static int __net_init ip6_route_net_init(struct net *net)
net->ipv6.sysctl.ip6_rt_gc_elasticity = 9;
net->ipv6.sysctl.ip6_rt_mtu_expires = 10*60*HZ;
net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40;
+ net->ipv6.sysctl.skip_notify_on_dev_down = 0;
net->ipv6.ip6_rt_gc_expire = 30*HZ;
--
2.11.0
^ permalink raw reply related
* [PATCH net v2] net/sched: cls_api: add missing validation of netlink attributes
From: Davide Caratti @ 2018-10-09 21:24 UTC (permalink / raw)
To: David S. Miller, David Ahern, Jamal Hadi Salim; +Cc: netdev
Similarly to what has been done in 8b4c3cdd9dd8 ("net: sched: Add policy
validation for tc attributes"), fix classifier code to add validation of
TCA_CHAIN and TCA_KIND netlink attributes.
tested with:
# ./tdc.py -c filter
v2: let sch_api and cls_api share nla_policy they have in common, thanks
to David Ahern
Fixes: 5bc1701881e39 ("net: sched: introduce multichain support for filters")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
---
include/net/sch_generic.h | 2 ++
net/sched/cls_api.c | 11 ++++++-----
net/sched/sch_api.c | 1 +
3 files changed, 9 insertions(+), 5 deletions(-)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index a6d00093f35e..8f4335c0a6c8 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -487,6 +487,8 @@ extern struct Qdisc_ops pfifo_fast_ops;
extern struct Qdisc_ops mq_qdisc_ops;
extern struct Qdisc_ops noqueue_qdisc_ops;
extern const struct Qdisc_ops *default_qdisc_ops;
+extern const struct nla_policy rtm_tca_policy[];
+
static inline const struct Qdisc_ops *
get_default_qdisc_ops(const struct net_device *dev, int ntx)
{
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 0a75cb2e5e7b..5f72190bf36c 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1211,7 +1211,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
replay:
tp_created = 0;
- err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
+ err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack);
if (err < 0)
return err;
@@ -1360,7 +1360,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
return -EPERM;
- err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
+ err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack);
if (err < 0)
return err;
@@ -1475,7 +1475,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
void *fh = NULL;
int err;
- err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
+ err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack);
if (err < 0)
return err;
@@ -1838,7 +1838,7 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
return -EPERM;
replay:
- err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
+ err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack);
if (err < 0)
return err;
@@ -1949,7 +1949,8 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
if (nlmsg_len(cb->nlh) < sizeof(*tcm))
return skb->len;
- err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL);
+ err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy,
+ NULL);
if (err)
return err;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 85e73f48e48f..99eae8007567 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1322,6 +1322,7 @@ const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = {
[TCA_INGRESS_BLOCK] = { .type = NLA_U32 },
[TCA_EGRESS_BLOCK] = { .type = NLA_U32 },
};
+EXPORT_SYMBOL(rtm_tca_policy);
static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
struct netlink_ext_ack *extack)
--
2.17.1
^ permalink raw reply related
* Re: [PATCH v2 1/2] net/ncsi: Add NCSI Broadcom OEM command
From: Samuel Mendoza-Jonas @ 2018-10-10 4:39 UTC (permalink / raw)
To: Vijay Khemka, David S. Miller, netdev, linux-kernel
Cc: openbmc @ lists . ozlabs . org, Justin.Lee1, joel, linux-aspeed
In-Reply-To: <20181009174806.404791-1-vijaykhemka@fb.com>
On Tue, 2018-10-09 at 10:48 -0700, Vijay Khemka wrote:
> This patch adds OEM Broadcom commands and response handling. It also
> defines OEM Get MAC Address handler to get and configure the device.
>
> ncsi_oem_gma_handler_bcm: This handler send NCSI broadcom command for
> getting mac address.
> ncsi_rsp_handler_oem_bcm: This handles response received for all
> broadcom OEM commands.
> ncsi_rsp_handler_oem_bcm_gma: This handles get mac address response and
> set it to device.
>
> Signed-off-by: Vijay Khemka <vijaykhemka@fb.com>
> ---
> net/ncsi/Kconfig | 6 ++++
> net/ncsi/internal.h | 8 +++++
> net/ncsi/ncsi-manage.c | 70 +++++++++++++++++++++++++++++++++++++++++-
> net/ncsi/ncsi-pkt.h | 8 +++++
> net/ncsi/ncsi-rsp.c | 40 +++++++++++++++++++++++-
> 5 files changed, 130 insertions(+), 2 deletions(-)
>
<snip>
> static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
> {
> struct ncsi_dev *nd = &ndp->ndev;
> @@ -643,9 +676,10 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
> struct ncsi_channel *nc = ndp->active_channel;
> struct ncsi_channel *hot_nc = NULL;
> struct ncsi_cmd_arg nca;
> + struct ncsi_oem_gma_handler *nch = NULL;
> unsigned char index;
> unsigned long flags;
> - int ret;
> + int ret, i;
>
I just noticed that if CONFIG_NCSI_OEM_CMD_GET_MAC is not set then this
generates unused variable warnings for i and nch. Otherwise all looking good!
Regards,
Sam
^ permalink raw reply
* Re: [PATCH V1 net-next 00/12] Improving performance and reducing latencies, by using latest capabilities exposed in ENA device
From: Bshara, Saeed @ 2018-10-09 21:18 UTC (permalink / raw)
To: Bshara, Nafea, Jesper Dangaard Brouer, Kiyanovski, Arthur
Cc: davem@davemloft.net, netdev@vger.kernel.org, Woodhouse, David,
Machulsky, Zorik, Matushevsky, Alexander, Wilson, Matt,
Liguori, Anthony, Tzalik, Guy, Belgazal, Netanel, Saidi, Ali,
Björn Töpel
In-Reply-To: <6383D812-919A-45FC-9A30-2409D805843E@amazon.com>
Jesper,
currently the driver allocate page per rx buffer, but we are considering to support mode where page split to 2 buffers in order to overcome memory fragmentation issue on low memory systems. but, this won't work with XDP, right?
what's your advice?
From: Bshara, Nafea
Sent: Tuesday, October 9, 2018 10:33 PM
To: Jesper Dangaard Brouer; Kiyanovski, Arthur
Cc: davem@davemloft.net; netdev@vger.kernel.org; Woodhouse, David; Machulsky, Zorik; Matushevsky, Alexander; Bshara, Saeed; Wilson, Matt; Liguori, Anthony; Tzalik, Guy; Belgazal, Netanel; Saidi, Ali; Björn Töpel
Subject: Re: [PATCH V1 net-next 00/12] Improving performance and reducing latencies, by using latest capabilities exposed in ENA device
It is high priority for us right after this major release get merged.
On 10/9/18, 12:31 PM, "Jesper Dangaard Brouer" <brouer@redhat.com> wrote:
On Tue, 9 Oct 2018 21:44:57 +0300 <akiyano@amazon.com> wrote:
> From: Arthur Kiyanovski <akiyano@amazon.com>
>
> This patchset introduces the following:
> 1. A new placement policy of Tx headers and descriptors, which takes
> advantage of an option to place headers + descriptors in device memory
> space. This is sometimes referred to as LLQ - low latency queue.
> The patch set defines the admin capability, maps the device memory as
> write-combined, and adds a mode in transmit datapath to do header +
> descriptor placement on the device.
> 2. Support for RX checksum offloading
> 3. Miscelaneous small improvements and code cleanups
What are your plans for XDP?
You are unsure ask your-colleague David Woodhouse, who I've discussed
this with when he attended my talk at Kernel-Recipes[1], slide[2].
[1] https://kernel-recipes.org/en/2018/talks/xdp-a-new-programmable-network-layer/
[2] http://people.netfilter.org/hawk/presentations/KernelRecipes2018/XDP_Kernel_Recipes_2018.pdf
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
LinkedIn: http://www.linkedin.com/in/brouer
^ permalink raw reply
* Re: [PATCH V1 net-next 00/12] Improving performance and reducing latencies, by using latest capabilities exposed in ENA device
From: Machulsky, Zorik @ 2018-10-09 20:54 UTC (permalink / raw)
To: Kiyanovski, Arthur, davem@davemloft.net, netdev@vger.kernel.org
Cc: Woodhouse, David, Matushevsky, Alexander, Bshara, Saeed,
Wilson, Matt, Liguori, Anthony, Bshara, Nafea, Tzalik, Guy,
Belgazal, Netanel, Saidi, Ali
In-Reply-To: <1539110709-31954-1-git-send-email-akiyano@amazon.com>
Acked-by: Zorik Machulsky <zorik@amazon.com>
On 10/9/18, 11:45 AM, "akiyano@amazon.com" <akiyano@amazon.com> wrote:
From: Arthur Kiyanovski <akiyano@amazon.com>
This patchset introduces the following:
1. A new placement policy of Tx headers and descriptors, which takes
advantage of an option to place headers + descriptors in device memory
space. This is sometimes referred to as LLQ - low latency queue.
The patch set defines the admin capability, maps the device memory as
write-combined, and adds a mode in transmit datapath to do header +
descriptor placement on the device.
2. Support for RX checksum offloading
3. Miscelaneous small improvements and code cleanups
Arthur Kiyanovski (12):
net: ena: minor performance improvement
net: ena: complete host info to match latest ENA spec
net: ena: introduce Low Latency Queues data structures according to
ENA spec
net: ena: add functions for handling Low Latency Queues in ena_com
net: ena: add functions for handling Low Latency Queues in ena_netdev
net: ena: use CSUM_CHECKED device indication to report skb's checksum
status
net: ena: explicit casting and initialization, and clearer error
handling
net: ena: limit refill Rx threshold to 256 to avoid latency issues
net: ena: change rx copybreak default to reduce kernel memory pressure
net: ena: remove redundant parameter in ena_com_admin_init()
net: ena: update driver version to 2.0.1
net: ena: fix indentations in ena_defs for better readability
drivers/net/ethernet/amazon/ena/ena_admin_defs.h | 425 ++++++++++++---------
drivers/net/ethernet/amazon/ena/ena_com.c | 302 +++++++++++++--
drivers/net/ethernet/amazon/ena/ena_com.h | 71 +++-
drivers/net/ethernet/amazon/ena/ena_common_defs.h | 4 +-
drivers/net/ethernet/amazon/ena/ena_eth_com.c | 277 +++++++++-----
drivers/net/ethernet/amazon/ena/ena_eth_com.h | 72 +++-
drivers/net/ethernet/amazon/ena/ena_eth_io_defs.h | 229 ++++++-----
drivers/net/ethernet/amazon/ena/ena_ethtool.c | 2 +
drivers/net/ethernet/amazon/ena/ena_netdev.c | 446 ++++++++++++++--------
drivers/net/ethernet/amazon/ena/ena_netdev.h | 42 +-
drivers/net/ethernet/amazon/ena/ena_regs_defs.h | 206 +++++-----
11 files changed, 1334 insertions(+), 742 deletions(-)
--
2.7.4
^ permalink raw reply
* Re: [PATCH net-next v2] net: core: change bool members of struct net_device to bitfield members
From: Eric Dumazet @ 2018-10-09 20:52 UTC (permalink / raw)
To: Heiner Kallweit, David Ahern, David Miller
Cc: netdev@vger.kernel.org, David Laight
In-Reply-To: <ded0a778-ca20-4e0f-223d-da3eb5cd71b2@gmail.com>
On 10/09/2018 01:24 PM, Heiner Kallweit wrote:
> Reordering the struct members to fill the holes could be a little tricky
> and could have side effects because it may make a performance difference
> whether certain members are in one cacheline or not.
> And whether it's worth to spend this effort (incl. the related risks)
> just to save a few bytes (also considering that typically we have quite
> few instances of struct net_device)?
Not really.
In fact we probably should spend time reordering fields for performance,
since some new fields were added a bit randomly, breaking the goal of data locality.
Some fields are used in control path only can could be moved out of the cache lines
needed in data path (fast path).
^ permalink raw reply
* Re: [PATCH net-next v2] net: core: change bool members of struct net_device to bitfield members
From: David Ahern @ 2018-10-09 20:43 UTC (permalink / raw)
To: Heiner Kallweit, David Miller; +Cc: netdev@vger.kernel.org, David Laight
In-Reply-To: <ded0a778-ca20-4e0f-223d-da3eb5cd71b2@gmail.com>
On 10/9/18 2:24 PM, Heiner Kallweit wrote:
> Reordering the struct members to fill the holes could be a little tricky
> and could have side effects because it may make a performance difference
> whether certain members are in one cacheline or not.
> And whether it's worth to spend this effort (incl. the related risks)
> just to save a few bytes (also considering that typically we have quite
> few instances of struct net_device)?
>
It would be good to get net_device below 2048 without affecting
performance. Anything else is just moving elements around for the same
end allocation (rounds up to 4096).
^ permalink raw reply
* Re: [PATCH net-next v2] net: core: change bool members of struct net_device to bitfield members
From: Heiner Kallweit @ 2018-10-09 20:24 UTC (permalink / raw)
To: David Ahern, David Miller; +Cc: netdev@vger.kernel.org, David Laight
In-Reply-To: <35349fe9-94ac-e2d0-f02c-078c9fd58090@gmail.com>
On 09.10.2018 17:20, David Ahern wrote:
> On 10/8/18 2:17 PM, Heiner Kallweit wrote:
>> bool is good as parameter type or function return type, but if used
>> for struct members it consumes more memory than needed.
>> Changing the bool members of struct net_device to bitfield members
>> allows to decrease the memory footprint of this struct.
>
> What does pahole show for the size of the struct before and after? I
> suspect you have not really changed the size and certainly not the
> actual memory allocated.
>
>
Thanks for the hint to use pahole. Indeed we gain nothing,
so there's no justification for this patch.
before:
/* size: 2496, cachelines: 39, members: 116 */
/* sum members: 2396, holes: 8, sum holes: 80 */
/* padding: 20 */
/* paddings: 4, sum paddings: 19 */
/* bit_padding: 31 bits */
after:
/* size: 2496, cachelines: 39, members: 116 */
/* sum members: 2394, holes: 8, sum holes: 82 */
/* bit holes: 1, sum bit holes: 8 bits */
/* padding: 20 */
/* paddings: 4, sum paddings: 19 */
/* bit_padding: 27 bits */
The biggest hole is here, because _tx is annotated to be cacheline-aligned.
struct hlist_node index_hlist; /* 888 16 */
/* XXX 56 bytes hole, try to pack */
/* --- cacheline 15 boundary (960 bytes) --- */
struct netdev_queue * _tx; /* 960 8 */
Reordering the struct members to fill the holes could be a little tricky
and could have side effects because it may make a performance difference
whether certain members are in one cacheline or not.
And whether it's worth to spend this effort (incl. the related risks)
just to save a few bytes (also considering that typically we have quite
few instances of struct net_device)?
^ permalink raw reply
* Re: [sky2 driver] 88E8056 PCI-E Gigabit Ethernet Controller not working after suspend
From: Stephen Hemminger @ 2018-10-09 20:09 UTC (permalink / raw)
To: Laurent Bigonville; +Cc: netdev
In-Reply-To: <01fd5a94-37d5-f029-d215-ce143516ab84@bigon.be>
On Tue, 9 Oct 2018 19:30:30 +0200
Laurent Bigonville <bigon@bigon.be> wrote:
> Hello,
>
> On my desktop (Asus MB with dual Ethernet port), when waking up after
> suspend, the network card is not detecting the link.
>
> I have to rmmod the sky2 driver and then modprobing it again.
>
> lspci shows me:
>
> 04:00.0 Ethernet controller: Marvell Technology Group Ltd. 88E8056 PCI-E
> Gigabit Ethernet Controller (rev 12)
> 05:00.0 Ethernet controller: Marvell Technology Group Ltd. 88E8056 PCI-E
> Gigabit Ethernet Controller (rev 12)
>
> An idea what's wrong here?
>
> Kind regards,
>
> Laurent Bigonville
>
I used to have that motherboard (about 8 years ago). Long dead by now.
There was some issue with how the power management worked. Forgot the workaround,
you might have to dig in the mailing list archive.
^ permalink raw reply
* Inquiry 09-10-2018
From: Daniel Murray @ 2018-10-09 14:18 UTC (permalink / raw)
To: netdev
Hi,friend,
This is Daniel Murray and i am from Sinara Group Co.Ltd Group Co.,LTD in Russia.
We are glad to know about your company from the web and we are interested in your products.
Could you kindly send us your Latest catalog and price list for our trial order.
Best Regards,
Daniel Murray
Purchasing Manager
^ permalink raw reply
* Re: [PATCH v3 2/2] treewide: use bus_find_device_by_fwnode
From: Silesh C V @ 2018-10-10 2:58 UTC (permalink / raw)
To: Mathieu Poirier
Cc: Greg Kroah-Hartman, Rafael J. Wysocki, linux-kernel,
linux-arm-kernel, linux-i2c, linux-rdma, netdev, devicetree,
linux-spi, Wolfram Sang, Lijun Ou, Wei Hu(Xavier), Yisen Zhuang,
Salil Mehta, Srinivas Kandagatla, Andrew Lunn, Florian Fainelli,
Rob Herring, Frank Rowand, Mark Brown, David S. Miller
In-Reply-To: <20181009174428.GB2182@xps15>
Hello Mathieu,
On Tue, Oct 9, 2018 at 11:14 PM Mathieu Poirier
<mathieu.poirier@linaro.org> wrote:
>
>
> This doesn't apply on linux-next. This late in the cycle you may want to rebase
> your work on that tree.
OK. Will send v4 after rebasing onto linux-next.
>
> Otherwise and for the coresight part:
>
> Tested-by: Mathieu Poirier <mathieu.poirier@linaro.org>
>
Thanks.
Regards,
Silesh.
^ permalink raw reply
* Re: [PATCH V1 net-next 00/12] Improving performance and reducing latencies, by using latest capabilities exposed in ENA device
From: Bshara, Nafea @ 2018-10-09 19:33 UTC (permalink / raw)
To: Jesper Dangaard Brouer, Kiyanovski, Arthur
Cc: davem@davemloft.net, netdev@vger.kernel.org, Woodhouse, David,
Machulsky, Zorik, Matushevsky, Alexander, Bshara, Saeed,
Wilson, Matt, Liguori, Anthony, Tzalik, Guy, Belgazal, Netanel,
Saidi, Ali, Björn Töpel
In-Reply-To: <20181009213017.653ed630@redhat.com>
It is high priority for us right after this major release get merged.
On 10/9/18, 12:31 PM, "Jesper Dangaard Brouer" <brouer@redhat.com> wrote:
On Tue, 9 Oct 2018 21:44:57 +0300 <akiyano@amazon.com> wrote:
> From: Arthur Kiyanovski <akiyano@amazon.com>
>
> This patchset introduces the following:
> 1. A new placement policy of Tx headers and descriptors, which takes
> advantage of an option to place headers + descriptors in device memory
> space. This is sometimes referred to as LLQ - low latency queue.
> The patch set defines the admin capability, maps the device memory as
> write-combined, and adds a mode in transmit datapath to do header +
> descriptor placement on the device.
> 2. Support for RX checksum offloading
> 3. Miscelaneous small improvements and code cleanups
What are your plans for XDP?
You are unsure ask your-colleague David Woodhouse, who I've discussed
this with when he attended my talk at Kernel-Recipes[1], slide[2].
[1] https://kernel-recipes.org/en/2018/talks/xdp-a-new-programmable-network-layer/
[2] http://people.netfilter.org/hawk/presentations/KernelRecipes2018/XDP_Kernel_Recipes_2018.pdf
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
LinkedIn: http://www.linkedin.com/in/brouer
^ permalink raw reply
* Re: [PATCH v3 1/2] Driver core: add bus_find_device_by_fwnode
From: Silesh C V @ 2018-10-10 2:49 UTC (permalink / raw)
To: Wolfram Sang
Cc: Greg Kroah-Hartman, Rafael J. Wysocki, linux-kernel,
linux-arm-kernel, linux-i2c, linux-rdma, netdev, devicetree,
linux-spi, Mathieu Poirier, Lijun Ou, Wei Hu(Xavier),
Yisen Zhuang, Salil Mehta, Srinivas Kandagatla, Andrew Lunn,
Florian Fainelli, Rob Herring, Frank Rowand, Mark Brown,
David S. Miller
In-Reply-To: <20181009110210.i6xphyuy5jkcfaug@katana>
Hello Wolfram,
On Tue, Oct 9, 2018 at 4:32 PM Wolfram Sang <wsa@the-dreams.de> wrote:
>
> On Tue, Oct 09, 2018 at 03:47:24PM +0530, Silesh C V wrote:
> > Some drivers need to find the device on a bus having a specific firmware
> > node. Currently, such drivers have their own implementations to do this.
> > Provide a helper similar to bus_find_device_by_name so that each driver
> > does not have to reinvent this.
> >
> > Signed-off-by: Silesh C V <svellattu@mvista.com>
>
> Looks good in general, however:
>
> We recently had this discussion in I2C world about using the parent if
> the (logical) device has a NULL fw_node [1]. I don't know if the other
> subsystems you modify use logical devices as well? If no, it seems we
> need an additional check for the parent in the I2C core only. If yes,
> this might be considered in your patchset?
We can add an additional check for dev_fwnode(dev->parent) if match
for dev_fwnode(dev) fails in match_fwnode callback. Please correct me
if I am wrong. But then, we will be doing these two comparisons for
each device (until a match is found) on a bus for a bus_find_device
iteration(mostly unnecessarily because I could not find any "match
node" callbacks (for bus_find_device) currently doing this). So,
wouldn't it be better to add this check in exceptional cases (like in
the case of I2C) in the respective subsystems itself ?
Thanks,
Silesh
^ permalink raw reply
* Re: [PATCH V1 net-next 00/12] Improving performance and reducing latencies, by using latest capabilities exposed in ENA device
From: Jesper Dangaard Brouer @ 2018-10-09 19:30 UTC (permalink / raw)
To: akiyano
Cc: brouer, davem, netdev, David Woodhouse, zorik, matua, saeedb, msw,
aliguori, nafea, gtzalik, netanel, alisaidi,
Björn Töpel
In-Reply-To: <1539110709-31954-1-git-send-email-akiyano@amazon.com>
On Tue, 9 Oct 2018 21:44:57 +0300 <akiyano@amazon.com> wrote:
> From: Arthur Kiyanovski <akiyano@amazon.com>
>
> This patchset introduces the following:
> 1. A new placement policy of Tx headers and descriptors, which takes
> advantage of an option to place headers + descriptors in device memory
> space. This is sometimes referred to as LLQ - low latency queue.
> The patch set defines the admin capability, maps the device memory as
> write-combined, and adds a mode in transmit datapath to do header +
> descriptor placement on the device.
> 2. Support for RX checksum offloading
> 3. Miscelaneous small improvements and code cleanups
What are your plans for XDP?
You are unsure ask your-colleague David Woodhouse, who I've discussed
this with when he attended my talk at Kernel-Recipes[1], slide[2].
[1] https://kernel-recipes.org/en/2018/talks/xdp-a-new-programmable-network-layer/
[2] http://people.netfilter.org/hawk/presentations/KernelRecipes2018/XDP_Kernel_Recipes_2018.pdf
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
LinkedIn: http://www.linkedin.com/in/brouer
^ permalink raw reply
* Inquiry 09-10-2018
From: Daniel Murray @ 2018-10-09 18:58 UTC (permalink / raw)
To: netdev
Hi,friend,
This is Daniel Murray and i am from Sinara Group Co.Ltd Group Co.,LTD in Russia.
We are glad to know about your company from the web and we are interested in your products.
Could you kindly send us your Latest catalog and price list for our trial order.
Best Regards,
Daniel Murray
Purchasing Manager
^ permalink raw reply
* Re: [bpf-next V2 PATCH 0/3] bpf/xdp: fix generic-XDP and demonstrate VLAN manipulation
From: Song Liu @ 2018-10-09 18:47 UTC (permalink / raw)
To: Jesper Dangaard Brouer
Cc: Networking, Daniel Borkmann, yoel, Alexei Starovoitov,
John Fastabend
In-Reply-To: <153907945478.9484.16223890803803124822.stgit@firesoul>
For the series:
Acked-by: Song Liu <songliubraving@fb.com>
On Tue, Oct 9, 2018 at 3:04 AM Jesper Dangaard Brouer <brouer@redhat.com> wrote:
>
> While implementing PoC building blocks for eBPF code XDP+TC that can
> manipulate VLANs headers, I discovered a bug in generic-XDP.
>
> The fix should be backported to stable kernels. Even-though
> generic-XDP was introduced in v4.12, I think the bug is not exposed
> until v4.14 in the mentined fixes commit.
>
> ---
>
> Jesper Dangaard Brouer (3):
> net: fix generic XDP to handle if eth header was mangled
> bpf: make TC vlan bpf_helpers avail to selftests
> selftests/bpf: add XDP selftests for modifying and popping VLAN headers
>
>
> net/core/dev.c | 14 +
> tools/testing/selftests/bpf/Makefile | 6 -
> tools/testing/selftests/bpf/bpf_helpers.h | 4
> tools/testing/selftests/bpf/test_xdp_vlan.c | 292 ++++++++++++++++++++++++++
> tools/testing/selftests/bpf/test_xdp_vlan.sh | 195 +++++++++++++++++
> 5 files changed, 509 insertions(+), 2 deletions(-)
> create mode 100644 tools/testing/selftests/bpf/test_xdp_vlan.c
> create mode 100755 tools/testing/selftests/bpf/test_xdp_vlan.sh
>
> --
^ permalink raw reply
* [PATCH V1 net-next 12/12] net: ena: fix indentations in ena_defs for better readability
From: akiyano @ 2018-10-09 18:45 UTC (permalink / raw)
To: davem, netdev
Cc: Arthur Kiyanovski, dwmw, zorik, matua, saeedb, msw, aliguori,
nafea, gtzalik, netanel, alisaidi
In-Reply-To: <1539110709-31954-1-git-send-email-akiyano@amazon.com>
From: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
---
drivers/net/ethernet/amazon/ena/ena_admin_defs.h | 334 +++++++++-------------
drivers/net/ethernet/amazon/ena/ena_eth_io_defs.h | 223 +++++++--------
drivers/net/ethernet/amazon/ena/ena_regs_defs.h | 206 +++++++------
3 files changed, 338 insertions(+), 425 deletions(-)
diff --git a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
index b439ec1..9f80b73 100644
--- a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
@@ -32,119 +32,81 @@
#ifndef _ENA_ADMIN_H_
#define _ENA_ADMIN_H_
-enum ena_admin_aq_opcode {
- ENA_ADMIN_CREATE_SQ = 1,
-
- ENA_ADMIN_DESTROY_SQ = 2,
-
- ENA_ADMIN_CREATE_CQ = 3,
-
- ENA_ADMIN_DESTROY_CQ = 4,
-
- ENA_ADMIN_GET_FEATURE = 8,
- ENA_ADMIN_SET_FEATURE = 9,
-
- ENA_ADMIN_GET_STATS = 11,
+enum ena_admin_aq_opcode {
+ ENA_ADMIN_CREATE_SQ = 1,
+ ENA_ADMIN_DESTROY_SQ = 2,
+ ENA_ADMIN_CREATE_CQ = 3,
+ ENA_ADMIN_DESTROY_CQ = 4,
+ ENA_ADMIN_GET_FEATURE = 8,
+ ENA_ADMIN_SET_FEATURE = 9,
+ ENA_ADMIN_GET_STATS = 11,
};
enum ena_admin_aq_completion_status {
- ENA_ADMIN_SUCCESS = 0,
-
- ENA_ADMIN_RESOURCE_ALLOCATION_FAILURE = 1,
-
- ENA_ADMIN_BAD_OPCODE = 2,
-
- ENA_ADMIN_UNSUPPORTED_OPCODE = 3,
-
- ENA_ADMIN_MALFORMED_REQUEST = 4,
-
+ ENA_ADMIN_SUCCESS = 0,
+ ENA_ADMIN_RESOURCE_ALLOCATION_FAILURE = 1,
+ ENA_ADMIN_BAD_OPCODE = 2,
+ ENA_ADMIN_UNSUPPORTED_OPCODE = 3,
+ ENA_ADMIN_MALFORMED_REQUEST = 4,
/* Additional status is provided in ACQ entry extended_status */
- ENA_ADMIN_ILLEGAL_PARAMETER = 5,
-
- ENA_ADMIN_UNKNOWN_ERROR = 6,
-
- ENA_ADMIN_RESOURCE_BUSY = 7,
+ ENA_ADMIN_ILLEGAL_PARAMETER = 5,
+ ENA_ADMIN_UNKNOWN_ERROR = 6,
+ ENA_ADMIN_RESOURCE_BUSY = 7,
};
enum ena_admin_aq_feature_id {
- ENA_ADMIN_DEVICE_ATTRIBUTES = 1,
-
- ENA_ADMIN_MAX_QUEUES_NUM = 2,
-
- ENA_ADMIN_HW_HINTS = 3,
-
- ENA_ADMIN_LLQ = 4,
-
- ENA_ADMIN_RSS_HASH_FUNCTION = 10,
-
- ENA_ADMIN_STATELESS_OFFLOAD_CONFIG = 11,
-
- ENA_ADMIN_RSS_REDIRECTION_TABLE_CONFIG = 12,
-
- ENA_ADMIN_MTU = 14,
-
- ENA_ADMIN_RSS_HASH_INPUT = 18,
-
- ENA_ADMIN_INTERRUPT_MODERATION = 20,
-
- ENA_ADMIN_AENQ_CONFIG = 26,
-
- ENA_ADMIN_LINK_CONFIG = 27,
-
- ENA_ADMIN_HOST_ATTR_CONFIG = 28,
-
- ENA_ADMIN_FEATURES_OPCODE_NUM = 32,
+ ENA_ADMIN_DEVICE_ATTRIBUTES = 1,
+ ENA_ADMIN_MAX_QUEUES_NUM = 2,
+ ENA_ADMIN_HW_HINTS = 3,
+ ENA_ADMIN_LLQ = 4,
+ ENA_ADMIN_RSS_HASH_FUNCTION = 10,
+ ENA_ADMIN_STATELESS_OFFLOAD_CONFIG = 11,
+ ENA_ADMIN_RSS_REDIRECTION_TABLE_CONFIG = 12,
+ ENA_ADMIN_MTU = 14,
+ ENA_ADMIN_RSS_HASH_INPUT = 18,
+ ENA_ADMIN_INTERRUPT_MODERATION = 20,
+ ENA_ADMIN_AENQ_CONFIG = 26,
+ ENA_ADMIN_LINK_CONFIG = 27,
+ ENA_ADMIN_HOST_ATTR_CONFIG = 28,
+ ENA_ADMIN_FEATURES_OPCODE_NUM = 32,
};
enum ena_admin_placement_policy_type {
/* descriptors and headers are in host memory */
- ENA_ADMIN_PLACEMENT_POLICY_HOST = 1,
-
+ ENA_ADMIN_PLACEMENT_POLICY_HOST = 1,
/* descriptors and headers are in device memory (a.k.a Low Latency
* Queue)
*/
- ENA_ADMIN_PLACEMENT_POLICY_DEV = 3,
+ ENA_ADMIN_PLACEMENT_POLICY_DEV = 3,
};
enum ena_admin_link_types {
- ENA_ADMIN_LINK_SPEED_1G = 0x1,
-
- ENA_ADMIN_LINK_SPEED_2_HALF_G = 0x2,
-
- ENA_ADMIN_LINK_SPEED_5G = 0x4,
-
- ENA_ADMIN_LINK_SPEED_10G = 0x8,
-
- ENA_ADMIN_LINK_SPEED_25G = 0x10,
-
- ENA_ADMIN_LINK_SPEED_40G = 0x20,
-
- ENA_ADMIN_LINK_SPEED_50G = 0x40,
-
- ENA_ADMIN_LINK_SPEED_100G = 0x80,
-
- ENA_ADMIN_LINK_SPEED_200G = 0x100,
-
- ENA_ADMIN_LINK_SPEED_400G = 0x200,
+ ENA_ADMIN_LINK_SPEED_1G = 0x1,
+ ENA_ADMIN_LINK_SPEED_2_HALF_G = 0x2,
+ ENA_ADMIN_LINK_SPEED_5G = 0x4,
+ ENA_ADMIN_LINK_SPEED_10G = 0x8,
+ ENA_ADMIN_LINK_SPEED_25G = 0x10,
+ ENA_ADMIN_LINK_SPEED_40G = 0x20,
+ ENA_ADMIN_LINK_SPEED_50G = 0x40,
+ ENA_ADMIN_LINK_SPEED_100G = 0x80,
+ ENA_ADMIN_LINK_SPEED_200G = 0x100,
+ ENA_ADMIN_LINK_SPEED_400G = 0x200,
};
enum ena_admin_completion_policy_type {
/* completion queue entry for each sq descriptor */
- ENA_ADMIN_COMPLETION_POLICY_DESC = 0,
-
+ ENA_ADMIN_COMPLETION_POLICY_DESC = 0,
/* completion queue entry upon request in sq descriptor */
- ENA_ADMIN_COMPLETION_POLICY_DESC_ON_DEMAND = 1,
-
+ ENA_ADMIN_COMPLETION_POLICY_DESC_ON_DEMAND = 1,
/* current queue head pointer is updated in OS memory upon sq
* descriptor request
*/
- ENA_ADMIN_COMPLETION_POLICY_HEAD_ON_DEMAND = 2,
-
+ ENA_ADMIN_COMPLETION_POLICY_HEAD_ON_DEMAND = 2,
/* current queue head pointer is updated in OS memory for each sq
* descriptor
*/
- ENA_ADMIN_COMPLETION_POLICY_HEAD = 3,
+ ENA_ADMIN_COMPLETION_POLICY_HEAD = 3,
};
/* basic stats return ena_admin_basic_stats while extanded stats return a
@@ -152,15 +114,13 @@ enum ena_admin_completion_policy_type {
* device id
*/
enum ena_admin_get_stats_type {
- ENA_ADMIN_GET_STATS_TYPE_BASIC = 0,
-
- ENA_ADMIN_GET_STATS_TYPE_EXTENDED = 1,
+ ENA_ADMIN_GET_STATS_TYPE_BASIC = 0,
+ ENA_ADMIN_GET_STATS_TYPE_EXTENDED = 1,
};
enum ena_admin_get_stats_scope {
- ENA_ADMIN_SPECIFIC_QUEUE = 0,
-
- ENA_ADMIN_ETH_TRAFFIC = 1,
+ ENA_ADMIN_SPECIFIC_QUEUE = 0,
+ ENA_ADMIN_ETH_TRAFFIC = 1,
};
struct ena_admin_aq_common_desc {
@@ -231,7 +191,9 @@ struct ena_admin_acq_common_desc {
u16 extended_status;
- /* serves as a hint what AQ entries can be revoked */
+ /* indicates to the driver which AQ entry has been consumed by the
+ * device and could be reused
+ */
u16 sq_head_indx;
};
@@ -300,9 +262,8 @@ struct ena_admin_aq_create_sq_cmd {
};
enum ena_admin_sq_direction {
- ENA_ADMIN_SQ_DIRECTION_TX = 1,
-
- ENA_ADMIN_SQ_DIRECTION_RX = 2,
+ ENA_ADMIN_SQ_DIRECTION_TX = 1,
+ ENA_ADMIN_SQ_DIRECTION_RX = 2,
};
struct ena_admin_acq_create_sq_resp_desc {
@@ -664,9 +625,8 @@ struct ena_admin_feature_offload_desc {
};
enum ena_admin_hash_functions {
- ENA_ADMIN_TOEPLITZ = 1,
-
- ENA_ADMIN_CRC32 = 2,
+ ENA_ADMIN_TOEPLITZ = 1,
+ ENA_ADMIN_CRC32 = 2,
};
struct ena_admin_feature_rss_flow_hash_control {
@@ -692,50 +652,35 @@ struct ena_admin_feature_rss_flow_hash_function {
/* RSS flow hash protocols */
enum ena_admin_flow_hash_proto {
- ENA_ADMIN_RSS_TCP4 = 0,
-
- ENA_ADMIN_RSS_UDP4 = 1,
-
- ENA_ADMIN_RSS_TCP6 = 2,
-
- ENA_ADMIN_RSS_UDP6 = 3,
-
- ENA_ADMIN_RSS_IP4 = 4,
-
- ENA_ADMIN_RSS_IP6 = 5,
-
- ENA_ADMIN_RSS_IP4_FRAG = 6,
-
- ENA_ADMIN_RSS_NOT_IP = 7,
-
+ ENA_ADMIN_RSS_TCP4 = 0,
+ ENA_ADMIN_RSS_UDP4 = 1,
+ ENA_ADMIN_RSS_TCP6 = 2,
+ ENA_ADMIN_RSS_UDP6 = 3,
+ ENA_ADMIN_RSS_IP4 = 4,
+ ENA_ADMIN_RSS_IP6 = 5,
+ ENA_ADMIN_RSS_IP4_FRAG = 6,
+ ENA_ADMIN_RSS_NOT_IP = 7,
/* TCPv6 with extension header */
- ENA_ADMIN_RSS_TCP6_EX = 8,
-
+ ENA_ADMIN_RSS_TCP6_EX = 8,
/* IPv6 with extension header */
- ENA_ADMIN_RSS_IP6_EX = 9,
-
- ENA_ADMIN_RSS_PROTO_NUM = 16,
+ ENA_ADMIN_RSS_IP6_EX = 9,
+ ENA_ADMIN_RSS_PROTO_NUM = 16,
};
/* RSS flow hash fields */
enum ena_admin_flow_hash_fields {
/* Ethernet Dest Addr */
- ENA_ADMIN_RSS_L2_DA = BIT(0),
-
+ ENA_ADMIN_RSS_L2_DA = BIT(0),
/* Ethernet Src Addr */
- ENA_ADMIN_RSS_L2_SA = BIT(1),
-
+ ENA_ADMIN_RSS_L2_SA = BIT(1),
/* ipv4/6 Dest Addr */
- ENA_ADMIN_RSS_L3_DA = BIT(2),
-
+ ENA_ADMIN_RSS_L3_DA = BIT(2),
/* ipv4/6 Src Addr */
- ENA_ADMIN_RSS_L3_SA = BIT(3),
-
+ ENA_ADMIN_RSS_L3_SA = BIT(3),
/* tcp/udp Dest Port */
- ENA_ADMIN_RSS_L4_DP = BIT(4),
-
+ ENA_ADMIN_RSS_L4_DP = BIT(4),
/* tcp/udp Src Port */
- ENA_ADMIN_RSS_L4_SP = BIT(5),
+ ENA_ADMIN_RSS_L4_SP = BIT(5),
};
struct ena_admin_proto_input {
@@ -774,19 +719,13 @@ struct ena_admin_feature_rss_flow_hash_input {
};
enum ena_admin_os_type {
- ENA_ADMIN_OS_LINUX = 1,
-
- ENA_ADMIN_OS_WIN = 2,
-
- ENA_ADMIN_OS_DPDK = 3,
-
- ENA_ADMIN_OS_FREEBSD = 4,
-
- ENA_ADMIN_OS_IPXE = 5,
-
- ENA_ADMIN_OS_ESXI = 6,
-
- ENA_ADMIN_OS_GROUPS_NUM = 6,
+ ENA_ADMIN_OS_LINUX = 1,
+ ENA_ADMIN_OS_WIN = 2,
+ ENA_ADMIN_OS_DPDK = 3,
+ ENA_ADMIN_OS_FREEBSD = 4,
+ ENA_ADMIN_OS_IPXE = 5,
+ ENA_ADMIN_OS_ESXI = 6,
+ ENA_ADMIN_OS_GROUPS_NUM = 6,
};
struct ena_admin_host_info {
@@ -981,25 +920,18 @@ struct ena_admin_aenq_common_desc {
/* asynchronous event notification groups */
enum ena_admin_aenq_group {
- ENA_ADMIN_LINK_CHANGE = 0,
-
- ENA_ADMIN_FATAL_ERROR = 1,
-
- ENA_ADMIN_WARNING = 2,
-
- ENA_ADMIN_NOTIFICATION = 3,
-
- ENA_ADMIN_KEEP_ALIVE = 4,
-
- ENA_ADMIN_AENQ_GROUPS_NUM = 5,
+ ENA_ADMIN_LINK_CHANGE = 0,
+ ENA_ADMIN_FATAL_ERROR = 1,
+ ENA_ADMIN_WARNING = 2,
+ ENA_ADMIN_NOTIFICATION = 3,
+ ENA_ADMIN_KEEP_ALIVE = 4,
+ ENA_ADMIN_AENQ_GROUPS_NUM = 5,
};
enum ena_admin_aenq_notification_syndrom {
- ENA_ADMIN_SUSPEND = 0,
-
- ENA_ADMIN_RESUME = 1,
-
- ENA_ADMIN_UPDATE_HINTS = 2,
+ ENA_ADMIN_SUSPEND = 0,
+ ENA_ADMIN_RESUME = 1,
+ ENA_ADMIN_UPDATE_HINTS = 2,
};
struct ena_admin_aenq_entry {
@@ -1034,27 +966,27 @@ struct ena_admin_ena_mmio_req_read_less_resp {
};
/* aq_common_desc */
-#define ENA_ADMIN_AQ_COMMON_DESC_COMMAND_ID_MASK GENMASK(11, 0)
-#define ENA_ADMIN_AQ_COMMON_DESC_PHASE_MASK BIT(0)
-#define ENA_ADMIN_AQ_COMMON_DESC_CTRL_DATA_SHIFT 1
-#define ENA_ADMIN_AQ_COMMON_DESC_CTRL_DATA_MASK BIT(1)
-#define ENA_ADMIN_AQ_COMMON_DESC_CTRL_DATA_INDIRECT_SHIFT 2
-#define ENA_ADMIN_AQ_COMMON_DESC_CTRL_DATA_INDIRECT_MASK BIT(2)
+#define ENA_ADMIN_AQ_COMMON_DESC_COMMAND_ID_MASK GENMASK(11, 0)
+#define ENA_ADMIN_AQ_COMMON_DESC_PHASE_MASK BIT(0)
+#define ENA_ADMIN_AQ_COMMON_DESC_CTRL_DATA_SHIFT 1
+#define ENA_ADMIN_AQ_COMMON_DESC_CTRL_DATA_MASK BIT(1)
+#define ENA_ADMIN_AQ_COMMON_DESC_CTRL_DATA_INDIRECT_SHIFT 2
+#define ENA_ADMIN_AQ_COMMON_DESC_CTRL_DATA_INDIRECT_MASK BIT(2)
/* sq */
-#define ENA_ADMIN_SQ_SQ_DIRECTION_SHIFT 5
-#define ENA_ADMIN_SQ_SQ_DIRECTION_MASK GENMASK(7, 5)
+#define ENA_ADMIN_SQ_SQ_DIRECTION_SHIFT 5
+#define ENA_ADMIN_SQ_SQ_DIRECTION_MASK GENMASK(7, 5)
/* acq_common_desc */
-#define ENA_ADMIN_ACQ_COMMON_DESC_COMMAND_ID_MASK GENMASK(11, 0)
-#define ENA_ADMIN_ACQ_COMMON_DESC_PHASE_MASK BIT(0)
+#define ENA_ADMIN_ACQ_COMMON_DESC_COMMAND_ID_MASK GENMASK(11, 0)
+#define ENA_ADMIN_ACQ_COMMON_DESC_PHASE_MASK BIT(0)
/* aq_create_sq_cmd */
-#define ENA_ADMIN_AQ_CREATE_SQ_CMD_SQ_DIRECTION_SHIFT 5
-#define ENA_ADMIN_AQ_CREATE_SQ_CMD_SQ_DIRECTION_MASK GENMASK(7, 5)
-#define ENA_ADMIN_AQ_CREATE_SQ_CMD_PLACEMENT_POLICY_MASK GENMASK(3, 0)
-#define ENA_ADMIN_AQ_CREATE_SQ_CMD_COMPLETION_POLICY_SHIFT 4
-#define ENA_ADMIN_AQ_CREATE_SQ_CMD_COMPLETION_POLICY_MASK GENMASK(6, 4)
+#define ENA_ADMIN_AQ_CREATE_SQ_CMD_SQ_DIRECTION_SHIFT 5
+#define ENA_ADMIN_AQ_CREATE_SQ_CMD_SQ_DIRECTION_MASK GENMASK(7, 5)
+#define ENA_ADMIN_AQ_CREATE_SQ_CMD_PLACEMENT_POLICY_MASK GENMASK(3, 0)
+#define ENA_ADMIN_AQ_CREATE_SQ_CMD_COMPLETION_POLICY_SHIFT 4
+#define ENA_ADMIN_AQ_CREATE_SQ_CMD_COMPLETION_POLICY_MASK GENMASK(6, 4)
#define ENA_ADMIN_AQ_CREATE_SQ_CMD_IS_PHYSICALLY_CONTIGUOUS_MASK BIT(0)
/* aq_create_cq_cmd */
@@ -1063,12 +995,12 @@ struct ena_admin_ena_mmio_req_read_less_resp {
#define ENA_ADMIN_AQ_CREATE_CQ_CMD_CQ_ENTRY_SIZE_WORDS_MASK GENMASK(4, 0)
/* get_set_feature_common_desc */
-#define ENA_ADMIN_GET_SET_FEATURE_COMMON_DESC_SELECT_MASK GENMASK(1, 0)
+#define ENA_ADMIN_GET_SET_FEATURE_COMMON_DESC_SELECT_MASK GENMASK(1, 0)
/* get_feature_link_desc */
-#define ENA_ADMIN_GET_FEATURE_LINK_DESC_AUTONEG_MASK BIT(0)
-#define ENA_ADMIN_GET_FEATURE_LINK_DESC_DUPLEX_SHIFT 1
-#define ENA_ADMIN_GET_FEATURE_LINK_DESC_DUPLEX_MASK BIT(1)
+#define ENA_ADMIN_GET_FEATURE_LINK_DESC_AUTONEG_MASK BIT(0)
+#define ENA_ADMIN_GET_FEATURE_LINK_DESC_DUPLEX_SHIFT 1
+#define ENA_ADMIN_GET_FEATURE_LINK_DESC_DUPLEX_MASK BIT(1)
/* feature_offload_desc */
#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_TX_L3_CSUM_IPV4_MASK BIT(0)
@@ -1080,19 +1012,19 @@ struct ena_admin_ena_mmio_req_read_less_resp {
#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_TX_L4_IPV6_CSUM_PART_MASK BIT(3)
#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_TX_L4_IPV6_CSUM_FULL_SHIFT 4
#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_TX_L4_IPV6_CSUM_FULL_MASK BIT(4)
-#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_TSO_IPV4_SHIFT 5
-#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_TSO_IPV4_MASK BIT(5)
-#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_TSO_IPV6_SHIFT 6
-#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_TSO_IPV6_MASK BIT(6)
-#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_TSO_ECN_SHIFT 7
-#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_TSO_ECN_MASK BIT(7)
+#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_TSO_IPV4_SHIFT 5
+#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_TSO_IPV4_MASK BIT(5)
+#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_TSO_IPV6_SHIFT 6
+#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_TSO_IPV6_MASK BIT(6)
+#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_TSO_ECN_SHIFT 7
+#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_TSO_ECN_MASK BIT(7)
#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_RX_L3_CSUM_IPV4_MASK BIT(0)
#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_RX_L4_IPV4_CSUM_SHIFT 1
#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_RX_L4_IPV4_CSUM_MASK BIT(1)
#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_RX_L4_IPV6_CSUM_SHIFT 2
#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_RX_L4_IPV6_CSUM_MASK BIT(2)
-#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_RX_HASH_SHIFT 3
-#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_RX_HASH_MASK BIT(3)
+#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_RX_HASH_SHIFT 3
+#define ENA_ADMIN_FEATURE_OFFLOAD_DESC_RX_HASH_MASK BIT(3)
/* feature_rss_flow_hash_function */
#define ENA_ADMIN_FEATURE_RSS_FLOW_HASH_FUNCTION_FUNCS_MASK GENMASK(7, 0)
@@ -1100,32 +1032,32 @@ struct ena_admin_ena_mmio_req_read_less_resp {
/* feature_rss_flow_hash_input */
#define ENA_ADMIN_FEATURE_RSS_FLOW_HASH_INPUT_L3_SORT_SHIFT 1
-#define ENA_ADMIN_FEATURE_RSS_FLOW_HASH_INPUT_L3_SORT_MASK BIT(1)
+#define ENA_ADMIN_FEATURE_RSS_FLOW_HASH_INPUT_L3_SORT_MASK BIT(1)
#define ENA_ADMIN_FEATURE_RSS_FLOW_HASH_INPUT_L4_SORT_SHIFT 2
-#define ENA_ADMIN_FEATURE_RSS_FLOW_HASH_INPUT_L4_SORT_MASK BIT(2)
+#define ENA_ADMIN_FEATURE_RSS_FLOW_HASH_INPUT_L4_SORT_MASK BIT(2)
#define ENA_ADMIN_FEATURE_RSS_FLOW_HASH_INPUT_ENABLE_L3_SORT_SHIFT 1
#define ENA_ADMIN_FEATURE_RSS_FLOW_HASH_INPUT_ENABLE_L3_SORT_MASK BIT(1)
#define ENA_ADMIN_FEATURE_RSS_FLOW_HASH_INPUT_ENABLE_L4_SORT_SHIFT 2
#define ENA_ADMIN_FEATURE_RSS_FLOW_HASH_INPUT_ENABLE_L4_SORT_MASK BIT(2)
/* host_info */
-#define ENA_ADMIN_HOST_INFO_MAJOR_MASK GENMASK(7, 0)
-#define ENA_ADMIN_HOST_INFO_MINOR_SHIFT 8
-#define ENA_ADMIN_HOST_INFO_MINOR_MASK GENMASK(15, 8)
-#define ENA_ADMIN_HOST_INFO_SUB_MINOR_SHIFT 16
-#define ENA_ADMIN_HOST_INFO_SUB_MINOR_MASK GENMASK(23, 16)
-#define ENA_ADMIN_HOST_INFO_MODULE_TYPE_SHIFT 24
-#define ENA_ADMIN_HOST_INFO_MODULE_TYPE_MASK GENMASK(31, 24)
-#define ENA_ADMIN_HOST_INFO_FUNCTION_MASK GENMASK(2, 0)
-#define ENA_ADMIN_HOST_INFO_DEVICE_SHIFT 3
-#define ENA_ADMIN_HOST_INFO_DEVICE_MASK GENMASK(7, 3)
-#define ENA_ADMIN_HOST_INFO_BUS_SHIFT 8
-#define ENA_ADMIN_HOST_INFO_BUS_MASK GENMASK(15, 8)
+#define ENA_ADMIN_HOST_INFO_MAJOR_MASK GENMASK(7, 0)
+#define ENA_ADMIN_HOST_INFO_MINOR_SHIFT 8
+#define ENA_ADMIN_HOST_INFO_MINOR_MASK GENMASK(15, 8)
+#define ENA_ADMIN_HOST_INFO_SUB_MINOR_SHIFT 16
+#define ENA_ADMIN_HOST_INFO_SUB_MINOR_MASK GENMASK(23, 16)
+#define ENA_ADMIN_HOST_INFO_MODULE_TYPE_SHIFT 24
+#define ENA_ADMIN_HOST_INFO_MODULE_TYPE_MASK GENMASK(31, 24)
+#define ENA_ADMIN_HOST_INFO_FUNCTION_MASK GENMASK(2, 0)
+#define ENA_ADMIN_HOST_INFO_DEVICE_SHIFT 3
+#define ENA_ADMIN_HOST_INFO_DEVICE_MASK GENMASK(7, 3)
+#define ENA_ADMIN_HOST_INFO_BUS_SHIFT 8
+#define ENA_ADMIN_HOST_INFO_BUS_MASK GENMASK(15, 8)
/* aenq_common_desc */
-#define ENA_ADMIN_AENQ_COMMON_DESC_PHASE_MASK BIT(0)
+#define ENA_ADMIN_AENQ_COMMON_DESC_PHASE_MASK BIT(0)
/* aenq_link_change_desc */
-#define ENA_ADMIN_AENQ_LINK_CHANGE_DESC_LINK_STATUS_MASK BIT(0)
+#define ENA_ADMIN_AENQ_LINK_CHANGE_DESC_LINK_STATUS_MASK BIT(0)
#endif /*_ENA_ADMIN_H_ */
diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_io_defs.h b/drivers/net/ethernet/amazon/ena/ena_eth_io_defs.h
index 4c5ccaa..00e0f05 100644
--- a/drivers/net/ethernet/amazon/ena/ena_eth_io_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_eth_io_defs.h
@@ -33,25 +33,18 @@
#define _ENA_ETH_IO_H_
enum ena_eth_io_l3_proto_index {
- ENA_ETH_IO_L3_PROTO_UNKNOWN = 0,
-
- ENA_ETH_IO_L3_PROTO_IPV4 = 8,
-
- ENA_ETH_IO_L3_PROTO_IPV6 = 11,
-
- ENA_ETH_IO_L3_PROTO_FCOE = 21,
-
- ENA_ETH_IO_L3_PROTO_ROCE = 22,
+ ENA_ETH_IO_L3_PROTO_UNKNOWN = 0,
+ ENA_ETH_IO_L3_PROTO_IPV4 = 8,
+ ENA_ETH_IO_L3_PROTO_IPV6 = 11,
+ ENA_ETH_IO_L3_PROTO_FCOE = 21,
+ ENA_ETH_IO_L3_PROTO_ROCE = 22,
};
enum ena_eth_io_l4_proto_index {
- ENA_ETH_IO_L4_PROTO_UNKNOWN = 0,
-
- ENA_ETH_IO_L4_PROTO_TCP = 12,
-
- ENA_ETH_IO_L4_PROTO_UDP = 13,
-
- ENA_ETH_IO_L4_PROTO_ROUTEABLE_ROCE = 23,
+ ENA_ETH_IO_L4_PROTO_UNKNOWN = 0,
+ ENA_ETH_IO_L4_PROTO_TCP = 12,
+ ENA_ETH_IO_L4_PROTO_UDP = 13,
+ ENA_ETH_IO_L4_PROTO_ROUTEABLE_ROCE = 23,
};
struct ena_eth_io_tx_desc {
@@ -307,116 +300,116 @@ struct ena_eth_io_numa_node_cfg_reg {
};
/* tx_desc */
-#define ENA_ETH_IO_TX_DESC_LENGTH_MASK GENMASK(15, 0)
-#define ENA_ETH_IO_TX_DESC_REQ_ID_HI_SHIFT 16
-#define ENA_ETH_IO_TX_DESC_REQ_ID_HI_MASK GENMASK(21, 16)
-#define ENA_ETH_IO_TX_DESC_META_DESC_SHIFT 23
-#define ENA_ETH_IO_TX_DESC_META_DESC_MASK BIT(23)
-#define ENA_ETH_IO_TX_DESC_PHASE_SHIFT 24
-#define ENA_ETH_IO_TX_DESC_PHASE_MASK BIT(24)
-#define ENA_ETH_IO_TX_DESC_FIRST_SHIFT 26
-#define ENA_ETH_IO_TX_DESC_FIRST_MASK BIT(26)
-#define ENA_ETH_IO_TX_DESC_LAST_SHIFT 27
-#define ENA_ETH_IO_TX_DESC_LAST_MASK BIT(27)
-#define ENA_ETH_IO_TX_DESC_COMP_REQ_SHIFT 28
-#define ENA_ETH_IO_TX_DESC_COMP_REQ_MASK BIT(28)
-#define ENA_ETH_IO_TX_DESC_L3_PROTO_IDX_MASK GENMASK(3, 0)
-#define ENA_ETH_IO_TX_DESC_DF_SHIFT 4
-#define ENA_ETH_IO_TX_DESC_DF_MASK BIT(4)
-#define ENA_ETH_IO_TX_DESC_TSO_EN_SHIFT 7
-#define ENA_ETH_IO_TX_DESC_TSO_EN_MASK BIT(7)
-#define ENA_ETH_IO_TX_DESC_L4_PROTO_IDX_SHIFT 8
-#define ENA_ETH_IO_TX_DESC_L4_PROTO_IDX_MASK GENMASK(12, 8)
-#define ENA_ETH_IO_TX_DESC_L3_CSUM_EN_SHIFT 13
-#define ENA_ETH_IO_TX_DESC_L3_CSUM_EN_MASK BIT(13)
-#define ENA_ETH_IO_TX_DESC_L4_CSUM_EN_SHIFT 14
-#define ENA_ETH_IO_TX_DESC_L4_CSUM_EN_MASK BIT(14)
-#define ENA_ETH_IO_TX_DESC_ETHERNET_FCS_DIS_SHIFT 15
-#define ENA_ETH_IO_TX_DESC_ETHERNET_FCS_DIS_MASK BIT(15)
-#define ENA_ETH_IO_TX_DESC_L4_CSUM_PARTIAL_SHIFT 17
-#define ENA_ETH_IO_TX_DESC_L4_CSUM_PARTIAL_MASK BIT(17)
-#define ENA_ETH_IO_TX_DESC_REQ_ID_LO_SHIFT 22
-#define ENA_ETH_IO_TX_DESC_REQ_ID_LO_MASK GENMASK(31, 22)
-#define ENA_ETH_IO_TX_DESC_ADDR_HI_MASK GENMASK(15, 0)
-#define ENA_ETH_IO_TX_DESC_HEADER_LENGTH_SHIFT 24
-#define ENA_ETH_IO_TX_DESC_HEADER_LENGTH_MASK GENMASK(31, 24)
+#define ENA_ETH_IO_TX_DESC_LENGTH_MASK GENMASK(15, 0)
+#define ENA_ETH_IO_TX_DESC_REQ_ID_HI_SHIFT 16
+#define ENA_ETH_IO_TX_DESC_REQ_ID_HI_MASK GENMASK(21, 16)
+#define ENA_ETH_IO_TX_DESC_META_DESC_SHIFT 23
+#define ENA_ETH_IO_TX_DESC_META_DESC_MASK BIT(23)
+#define ENA_ETH_IO_TX_DESC_PHASE_SHIFT 24
+#define ENA_ETH_IO_TX_DESC_PHASE_MASK BIT(24)
+#define ENA_ETH_IO_TX_DESC_FIRST_SHIFT 26
+#define ENA_ETH_IO_TX_DESC_FIRST_MASK BIT(26)
+#define ENA_ETH_IO_TX_DESC_LAST_SHIFT 27
+#define ENA_ETH_IO_TX_DESC_LAST_MASK BIT(27)
+#define ENA_ETH_IO_TX_DESC_COMP_REQ_SHIFT 28
+#define ENA_ETH_IO_TX_DESC_COMP_REQ_MASK BIT(28)
+#define ENA_ETH_IO_TX_DESC_L3_PROTO_IDX_MASK GENMASK(3, 0)
+#define ENA_ETH_IO_TX_DESC_DF_SHIFT 4
+#define ENA_ETH_IO_TX_DESC_DF_MASK BIT(4)
+#define ENA_ETH_IO_TX_DESC_TSO_EN_SHIFT 7
+#define ENA_ETH_IO_TX_DESC_TSO_EN_MASK BIT(7)
+#define ENA_ETH_IO_TX_DESC_L4_PROTO_IDX_SHIFT 8
+#define ENA_ETH_IO_TX_DESC_L4_PROTO_IDX_MASK GENMASK(12, 8)
+#define ENA_ETH_IO_TX_DESC_L3_CSUM_EN_SHIFT 13
+#define ENA_ETH_IO_TX_DESC_L3_CSUM_EN_MASK BIT(13)
+#define ENA_ETH_IO_TX_DESC_L4_CSUM_EN_SHIFT 14
+#define ENA_ETH_IO_TX_DESC_L4_CSUM_EN_MASK BIT(14)
+#define ENA_ETH_IO_TX_DESC_ETHERNET_FCS_DIS_SHIFT 15
+#define ENA_ETH_IO_TX_DESC_ETHERNET_FCS_DIS_MASK BIT(15)
+#define ENA_ETH_IO_TX_DESC_L4_CSUM_PARTIAL_SHIFT 17
+#define ENA_ETH_IO_TX_DESC_L4_CSUM_PARTIAL_MASK BIT(17)
+#define ENA_ETH_IO_TX_DESC_REQ_ID_LO_SHIFT 22
+#define ENA_ETH_IO_TX_DESC_REQ_ID_LO_MASK GENMASK(31, 22)
+#define ENA_ETH_IO_TX_DESC_ADDR_HI_MASK GENMASK(15, 0)
+#define ENA_ETH_IO_TX_DESC_HEADER_LENGTH_SHIFT 24
+#define ENA_ETH_IO_TX_DESC_HEADER_LENGTH_MASK GENMASK(31, 24)
/* tx_meta_desc */
-#define ENA_ETH_IO_TX_META_DESC_REQ_ID_LO_MASK GENMASK(9, 0)
-#define ENA_ETH_IO_TX_META_DESC_EXT_VALID_SHIFT 14
-#define ENA_ETH_IO_TX_META_DESC_EXT_VALID_MASK BIT(14)
-#define ENA_ETH_IO_TX_META_DESC_MSS_HI_SHIFT 16
-#define ENA_ETH_IO_TX_META_DESC_MSS_HI_MASK GENMASK(19, 16)
-#define ENA_ETH_IO_TX_META_DESC_ETH_META_TYPE_SHIFT 20
-#define ENA_ETH_IO_TX_META_DESC_ETH_META_TYPE_MASK BIT(20)
-#define ENA_ETH_IO_TX_META_DESC_META_STORE_SHIFT 21
-#define ENA_ETH_IO_TX_META_DESC_META_STORE_MASK BIT(21)
-#define ENA_ETH_IO_TX_META_DESC_META_DESC_SHIFT 23
-#define ENA_ETH_IO_TX_META_DESC_META_DESC_MASK BIT(23)
-#define ENA_ETH_IO_TX_META_DESC_PHASE_SHIFT 24
-#define ENA_ETH_IO_TX_META_DESC_PHASE_MASK BIT(24)
-#define ENA_ETH_IO_TX_META_DESC_FIRST_SHIFT 26
-#define ENA_ETH_IO_TX_META_DESC_FIRST_MASK BIT(26)
-#define ENA_ETH_IO_TX_META_DESC_LAST_SHIFT 27
-#define ENA_ETH_IO_TX_META_DESC_LAST_MASK BIT(27)
-#define ENA_ETH_IO_TX_META_DESC_COMP_REQ_SHIFT 28
-#define ENA_ETH_IO_TX_META_DESC_COMP_REQ_MASK BIT(28)
-#define ENA_ETH_IO_TX_META_DESC_REQ_ID_HI_MASK GENMASK(5, 0)
-#define ENA_ETH_IO_TX_META_DESC_L3_HDR_LEN_MASK GENMASK(7, 0)
-#define ENA_ETH_IO_TX_META_DESC_L3_HDR_OFF_SHIFT 8
-#define ENA_ETH_IO_TX_META_DESC_L3_HDR_OFF_MASK GENMASK(15, 8)
-#define ENA_ETH_IO_TX_META_DESC_L4_HDR_LEN_IN_WORDS_SHIFT 16
-#define ENA_ETH_IO_TX_META_DESC_L4_HDR_LEN_IN_WORDS_MASK GENMASK(21, 16)
-#define ENA_ETH_IO_TX_META_DESC_MSS_LO_SHIFT 22
-#define ENA_ETH_IO_TX_META_DESC_MSS_LO_MASK GENMASK(31, 22)
+#define ENA_ETH_IO_TX_META_DESC_REQ_ID_LO_MASK GENMASK(9, 0)
+#define ENA_ETH_IO_TX_META_DESC_EXT_VALID_SHIFT 14
+#define ENA_ETH_IO_TX_META_DESC_EXT_VALID_MASK BIT(14)
+#define ENA_ETH_IO_TX_META_DESC_MSS_HI_SHIFT 16
+#define ENA_ETH_IO_TX_META_DESC_MSS_HI_MASK GENMASK(19, 16)
+#define ENA_ETH_IO_TX_META_DESC_ETH_META_TYPE_SHIFT 20
+#define ENA_ETH_IO_TX_META_DESC_ETH_META_TYPE_MASK BIT(20)
+#define ENA_ETH_IO_TX_META_DESC_META_STORE_SHIFT 21
+#define ENA_ETH_IO_TX_META_DESC_META_STORE_MASK BIT(21)
+#define ENA_ETH_IO_TX_META_DESC_META_DESC_SHIFT 23
+#define ENA_ETH_IO_TX_META_DESC_META_DESC_MASK BIT(23)
+#define ENA_ETH_IO_TX_META_DESC_PHASE_SHIFT 24
+#define ENA_ETH_IO_TX_META_DESC_PHASE_MASK BIT(24)
+#define ENA_ETH_IO_TX_META_DESC_FIRST_SHIFT 26
+#define ENA_ETH_IO_TX_META_DESC_FIRST_MASK BIT(26)
+#define ENA_ETH_IO_TX_META_DESC_LAST_SHIFT 27
+#define ENA_ETH_IO_TX_META_DESC_LAST_MASK BIT(27)
+#define ENA_ETH_IO_TX_META_DESC_COMP_REQ_SHIFT 28
+#define ENA_ETH_IO_TX_META_DESC_COMP_REQ_MASK BIT(28)
+#define ENA_ETH_IO_TX_META_DESC_REQ_ID_HI_MASK GENMASK(5, 0)
+#define ENA_ETH_IO_TX_META_DESC_L3_HDR_LEN_MASK GENMASK(7, 0)
+#define ENA_ETH_IO_TX_META_DESC_L3_HDR_OFF_SHIFT 8
+#define ENA_ETH_IO_TX_META_DESC_L3_HDR_OFF_MASK GENMASK(15, 8)
+#define ENA_ETH_IO_TX_META_DESC_L4_HDR_LEN_IN_WORDS_SHIFT 16
+#define ENA_ETH_IO_TX_META_DESC_L4_HDR_LEN_IN_WORDS_MASK GENMASK(21, 16)
+#define ENA_ETH_IO_TX_META_DESC_MSS_LO_SHIFT 22
+#define ENA_ETH_IO_TX_META_DESC_MSS_LO_MASK GENMASK(31, 22)
/* tx_cdesc */
-#define ENA_ETH_IO_TX_CDESC_PHASE_MASK BIT(0)
+#define ENA_ETH_IO_TX_CDESC_PHASE_MASK BIT(0)
/* rx_desc */
-#define ENA_ETH_IO_RX_DESC_PHASE_MASK BIT(0)
-#define ENA_ETH_IO_RX_DESC_FIRST_SHIFT 2
-#define ENA_ETH_IO_RX_DESC_FIRST_MASK BIT(2)
-#define ENA_ETH_IO_RX_DESC_LAST_SHIFT 3
-#define ENA_ETH_IO_RX_DESC_LAST_MASK BIT(3)
-#define ENA_ETH_IO_RX_DESC_COMP_REQ_SHIFT 4
-#define ENA_ETH_IO_RX_DESC_COMP_REQ_MASK BIT(4)
+#define ENA_ETH_IO_RX_DESC_PHASE_MASK BIT(0)
+#define ENA_ETH_IO_RX_DESC_FIRST_SHIFT 2
+#define ENA_ETH_IO_RX_DESC_FIRST_MASK BIT(2)
+#define ENA_ETH_IO_RX_DESC_LAST_SHIFT 3
+#define ENA_ETH_IO_RX_DESC_LAST_MASK BIT(3)
+#define ENA_ETH_IO_RX_DESC_COMP_REQ_SHIFT 4
+#define ENA_ETH_IO_RX_DESC_COMP_REQ_MASK BIT(4)
/* rx_cdesc_base */
-#define ENA_ETH_IO_RX_CDESC_BASE_L3_PROTO_IDX_MASK GENMASK(4, 0)
-#define ENA_ETH_IO_RX_CDESC_BASE_SRC_VLAN_CNT_SHIFT 5
-#define ENA_ETH_IO_RX_CDESC_BASE_SRC_VLAN_CNT_MASK GENMASK(6, 5)
-#define ENA_ETH_IO_RX_CDESC_BASE_L4_PROTO_IDX_SHIFT 8
-#define ENA_ETH_IO_RX_CDESC_BASE_L4_PROTO_IDX_MASK GENMASK(12, 8)
-#define ENA_ETH_IO_RX_CDESC_BASE_L3_CSUM_ERR_SHIFT 13
-#define ENA_ETH_IO_RX_CDESC_BASE_L3_CSUM_ERR_MASK BIT(13)
-#define ENA_ETH_IO_RX_CDESC_BASE_L4_CSUM_ERR_SHIFT 14
-#define ENA_ETH_IO_RX_CDESC_BASE_L4_CSUM_ERR_MASK BIT(14)
-#define ENA_ETH_IO_RX_CDESC_BASE_IPV4_FRAG_SHIFT 15
-#define ENA_ETH_IO_RX_CDESC_BASE_IPV4_FRAG_MASK BIT(15)
-#define ENA_ETH_IO_RX_CDESC_BASE_L4_CSUM_CHECKED_SHIFT 16
-#define ENA_ETH_IO_RX_CDESC_BASE_L4_CSUM_CHECKED_MASK BIT(16)
-#define ENA_ETH_IO_RX_CDESC_BASE_PHASE_SHIFT 24
-#define ENA_ETH_IO_RX_CDESC_BASE_PHASE_MASK BIT(24)
-#define ENA_ETH_IO_RX_CDESC_BASE_L3_CSUM2_SHIFT 25
-#define ENA_ETH_IO_RX_CDESC_BASE_L3_CSUM2_MASK BIT(25)
-#define ENA_ETH_IO_RX_CDESC_BASE_FIRST_SHIFT 26
-#define ENA_ETH_IO_RX_CDESC_BASE_FIRST_MASK BIT(26)
-#define ENA_ETH_IO_RX_CDESC_BASE_LAST_SHIFT 27
-#define ENA_ETH_IO_RX_CDESC_BASE_LAST_MASK BIT(27)
-#define ENA_ETH_IO_RX_CDESC_BASE_BUFFER_SHIFT 30
-#define ENA_ETH_IO_RX_CDESC_BASE_BUFFER_MASK BIT(30)
+#define ENA_ETH_IO_RX_CDESC_BASE_L3_PROTO_IDX_MASK GENMASK(4, 0)
+#define ENA_ETH_IO_RX_CDESC_BASE_SRC_VLAN_CNT_SHIFT 5
+#define ENA_ETH_IO_RX_CDESC_BASE_SRC_VLAN_CNT_MASK GENMASK(6, 5)
+#define ENA_ETH_IO_RX_CDESC_BASE_L4_PROTO_IDX_SHIFT 8
+#define ENA_ETH_IO_RX_CDESC_BASE_L4_PROTO_IDX_MASK GENMASK(12, 8)
+#define ENA_ETH_IO_RX_CDESC_BASE_L3_CSUM_ERR_SHIFT 13
+#define ENA_ETH_IO_RX_CDESC_BASE_L3_CSUM_ERR_MASK BIT(13)
+#define ENA_ETH_IO_RX_CDESC_BASE_L4_CSUM_ERR_SHIFT 14
+#define ENA_ETH_IO_RX_CDESC_BASE_L4_CSUM_ERR_MASK BIT(14)
+#define ENA_ETH_IO_RX_CDESC_BASE_IPV4_FRAG_SHIFT 15
+#define ENA_ETH_IO_RX_CDESC_BASE_IPV4_FRAG_MASK BIT(15)
+#define ENA_ETH_IO_RX_CDESC_BASE_L4_CSUM_CHECKED_SHIFT 16
+#define ENA_ETH_IO_RX_CDESC_BASE_L4_CSUM_CHECKED_MASK BIT(16)
+#define ENA_ETH_IO_RX_CDESC_BASE_PHASE_SHIFT 24
+#define ENA_ETH_IO_RX_CDESC_BASE_PHASE_MASK BIT(24)
+#define ENA_ETH_IO_RX_CDESC_BASE_L3_CSUM2_SHIFT 25
+#define ENA_ETH_IO_RX_CDESC_BASE_L3_CSUM2_MASK BIT(25)
+#define ENA_ETH_IO_RX_CDESC_BASE_FIRST_SHIFT 26
+#define ENA_ETH_IO_RX_CDESC_BASE_FIRST_MASK BIT(26)
+#define ENA_ETH_IO_RX_CDESC_BASE_LAST_SHIFT 27
+#define ENA_ETH_IO_RX_CDESC_BASE_LAST_MASK BIT(27)
+#define ENA_ETH_IO_RX_CDESC_BASE_BUFFER_SHIFT 30
+#define ENA_ETH_IO_RX_CDESC_BASE_BUFFER_MASK BIT(30)
/* intr_reg */
-#define ENA_ETH_IO_INTR_REG_RX_INTR_DELAY_MASK GENMASK(14, 0)
-#define ENA_ETH_IO_INTR_REG_TX_INTR_DELAY_SHIFT 15
-#define ENA_ETH_IO_INTR_REG_TX_INTR_DELAY_MASK GENMASK(29, 15)
-#define ENA_ETH_IO_INTR_REG_INTR_UNMASK_SHIFT 30
-#define ENA_ETH_IO_INTR_REG_INTR_UNMASK_MASK BIT(30)
+#define ENA_ETH_IO_INTR_REG_RX_INTR_DELAY_MASK GENMASK(14, 0)
+#define ENA_ETH_IO_INTR_REG_TX_INTR_DELAY_SHIFT 15
+#define ENA_ETH_IO_INTR_REG_TX_INTR_DELAY_MASK GENMASK(29, 15)
+#define ENA_ETH_IO_INTR_REG_INTR_UNMASK_SHIFT 30
+#define ENA_ETH_IO_INTR_REG_INTR_UNMASK_MASK BIT(30)
/* numa_node_cfg_reg */
-#define ENA_ETH_IO_NUMA_NODE_CFG_REG_NUMA_MASK GENMASK(7, 0)
-#define ENA_ETH_IO_NUMA_NODE_CFG_REG_ENABLED_SHIFT 31
-#define ENA_ETH_IO_NUMA_NODE_CFG_REG_ENABLED_MASK BIT(31)
+#define ENA_ETH_IO_NUMA_NODE_CFG_REG_NUMA_MASK GENMASK(7, 0)
+#define ENA_ETH_IO_NUMA_NODE_CFG_REG_ENABLED_SHIFT 31
+#define ENA_ETH_IO_NUMA_NODE_CFG_REG_ENABLED_MASK BIT(31)
#endif /*_ENA_ETH_IO_H_ */
diff --git a/drivers/net/ethernet/amazon/ena/ena_regs_defs.h b/drivers/net/ethernet/amazon/ena/ena_regs_defs.h
index 48ca97f..04fcafc 100644
--- a/drivers/net/ethernet/amazon/ena/ena_regs_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_regs_defs.h
@@ -33,137 +33,125 @@
#define _ENA_REGS_H_
enum ena_regs_reset_reason_types {
- ENA_REGS_RESET_NORMAL = 0,
-
- ENA_REGS_RESET_KEEP_ALIVE_TO = 1,
-
- ENA_REGS_RESET_ADMIN_TO = 2,
-
- ENA_REGS_RESET_MISS_TX_CMPL = 3,
-
- ENA_REGS_RESET_INV_RX_REQ_ID = 4,
-
- ENA_REGS_RESET_INV_TX_REQ_ID = 5,
-
- ENA_REGS_RESET_TOO_MANY_RX_DESCS = 6,
-
- ENA_REGS_RESET_INIT_ERR = 7,
-
- ENA_REGS_RESET_DRIVER_INVALID_STATE = 8,
-
- ENA_REGS_RESET_OS_TRIGGER = 9,
-
- ENA_REGS_RESET_OS_NETDEV_WD = 10,
-
- ENA_REGS_RESET_SHUTDOWN = 11,
-
- ENA_REGS_RESET_USER_TRIGGER = 12,
-
- ENA_REGS_RESET_GENERIC = 13,
-
- ENA_REGS_RESET_MISS_INTERRUPT = 14,
+ ENA_REGS_RESET_NORMAL = 0,
+ ENA_REGS_RESET_KEEP_ALIVE_TO = 1,
+ ENA_REGS_RESET_ADMIN_TO = 2,
+ ENA_REGS_RESET_MISS_TX_CMPL = 3,
+ ENA_REGS_RESET_INV_RX_REQ_ID = 4,
+ ENA_REGS_RESET_INV_TX_REQ_ID = 5,
+ ENA_REGS_RESET_TOO_MANY_RX_DESCS = 6,
+ ENA_REGS_RESET_INIT_ERR = 7,
+ ENA_REGS_RESET_DRIVER_INVALID_STATE = 8,
+ ENA_REGS_RESET_OS_TRIGGER = 9,
+ ENA_REGS_RESET_OS_NETDEV_WD = 10,
+ ENA_REGS_RESET_SHUTDOWN = 11,
+ ENA_REGS_RESET_USER_TRIGGER = 12,
+ ENA_REGS_RESET_GENERIC = 13,
+ ENA_REGS_RESET_MISS_INTERRUPT = 14,
};
/* ena_registers offsets */
-#define ENA_REGS_VERSION_OFF 0x0
-#define ENA_REGS_CONTROLLER_VERSION_OFF 0x4
-#define ENA_REGS_CAPS_OFF 0x8
-#define ENA_REGS_CAPS_EXT_OFF 0xc
-#define ENA_REGS_AQ_BASE_LO_OFF 0x10
-#define ENA_REGS_AQ_BASE_HI_OFF 0x14
-#define ENA_REGS_AQ_CAPS_OFF 0x18
-#define ENA_REGS_ACQ_BASE_LO_OFF 0x20
-#define ENA_REGS_ACQ_BASE_HI_OFF 0x24
-#define ENA_REGS_ACQ_CAPS_OFF 0x28
-#define ENA_REGS_AQ_DB_OFF 0x2c
-#define ENA_REGS_ACQ_TAIL_OFF 0x30
-#define ENA_REGS_AENQ_CAPS_OFF 0x34
-#define ENA_REGS_AENQ_BASE_LO_OFF 0x38
-#define ENA_REGS_AENQ_BASE_HI_OFF 0x3c
-#define ENA_REGS_AENQ_HEAD_DB_OFF 0x40
-#define ENA_REGS_AENQ_TAIL_OFF 0x44
-#define ENA_REGS_INTR_MASK_OFF 0x4c
-#define ENA_REGS_DEV_CTL_OFF 0x54
-#define ENA_REGS_DEV_STS_OFF 0x58
-#define ENA_REGS_MMIO_REG_READ_OFF 0x5c
-#define ENA_REGS_MMIO_RESP_LO_OFF 0x60
-#define ENA_REGS_MMIO_RESP_HI_OFF 0x64
-#define ENA_REGS_RSS_IND_ENTRY_UPDATE_OFF 0x68
+
+/* 0 base */
+#define ENA_REGS_VERSION_OFF 0x0
+#define ENA_REGS_CONTROLLER_VERSION_OFF 0x4
+#define ENA_REGS_CAPS_OFF 0x8
+#define ENA_REGS_CAPS_EXT_OFF 0xc
+#define ENA_REGS_AQ_BASE_LO_OFF 0x10
+#define ENA_REGS_AQ_BASE_HI_OFF 0x14
+#define ENA_REGS_AQ_CAPS_OFF 0x18
+#define ENA_REGS_ACQ_BASE_LO_OFF 0x20
+#define ENA_REGS_ACQ_BASE_HI_OFF 0x24
+#define ENA_REGS_ACQ_CAPS_OFF 0x28
+#define ENA_REGS_AQ_DB_OFF 0x2c
+#define ENA_REGS_ACQ_TAIL_OFF 0x30
+#define ENA_REGS_AENQ_CAPS_OFF 0x34
+#define ENA_REGS_AENQ_BASE_LO_OFF 0x38
+#define ENA_REGS_AENQ_BASE_HI_OFF 0x3c
+#define ENA_REGS_AENQ_HEAD_DB_OFF 0x40
+#define ENA_REGS_AENQ_TAIL_OFF 0x44
+#define ENA_REGS_INTR_MASK_OFF 0x4c
+#define ENA_REGS_DEV_CTL_OFF 0x54
+#define ENA_REGS_DEV_STS_OFF 0x58
+#define ENA_REGS_MMIO_REG_READ_OFF 0x5c
+#define ENA_REGS_MMIO_RESP_LO_OFF 0x60
+#define ENA_REGS_MMIO_RESP_HI_OFF 0x64
+#define ENA_REGS_RSS_IND_ENTRY_UPDATE_OFF 0x68
/* version register */
-#define ENA_REGS_VERSION_MINOR_VERSION_MASK 0xff
-#define ENA_REGS_VERSION_MAJOR_VERSION_SHIFT 8
-#define ENA_REGS_VERSION_MAJOR_VERSION_MASK 0xff00
+#define ENA_REGS_VERSION_MINOR_VERSION_MASK 0xff
+#define ENA_REGS_VERSION_MAJOR_VERSION_SHIFT 8
+#define ENA_REGS_VERSION_MAJOR_VERSION_MASK 0xff00
/* controller_version register */
-#define ENA_REGS_CONTROLLER_VERSION_SUBMINOR_VERSION_MASK 0xff
-#define ENA_REGS_CONTROLLER_VERSION_MINOR_VERSION_SHIFT 8
-#define ENA_REGS_CONTROLLER_VERSION_MINOR_VERSION_MASK 0xff00
-#define ENA_REGS_CONTROLLER_VERSION_MAJOR_VERSION_SHIFT 16
-#define ENA_REGS_CONTROLLER_VERSION_MAJOR_VERSION_MASK 0xff0000
-#define ENA_REGS_CONTROLLER_VERSION_IMPL_ID_SHIFT 24
-#define ENA_REGS_CONTROLLER_VERSION_IMPL_ID_MASK 0xff000000
+#define ENA_REGS_CONTROLLER_VERSION_SUBMINOR_VERSION_MASK 0xff
+#define ENA_REGS_CONTROLLER_VERSION_MINOR_VERSION_SHIFT 8
+#define ENA_REGS_CONTROLLER_VERSION_MINOR_VERSION_MASK 0xff00
+#define ENA_REGS_CONTROLLER_VERSION_MAJOR_VERSION_SHIFT 16
+#define ENA_REGS_CONTROLLER_VERSION_MAJOR_VERSION_MASK 0xff0000
+#define ENA_REGS_CONTROLLER_VERSION_IMPL_ID_SHIFT 24
+#define ENA_REGS_CONTROLLER_VERSION_IMPL_ID_MASK 0xff000000
/* caps register */
-#define ENA_REGS_CAPS_CONTIGUOUS_QUEUE_REQUIRED_MASK 0x1
-#define ENA_REGS_CAPS_RESET_TIMEOUT_SHIFT 1
-#define ENA_REGS_CAPS_RESET_TIMEOUT_MASK 0x3e
-#define ENA_REGS_CAPS_DMA_ADDR_WIDTH_SHIFT 8
-#define ENA_REGS_CAPS_DMA_ADDR_WIDTH_MASK 0xff00
-#define ENA_REGS_CAPS_ADMIN_CMD_TO_SHIFT 16
-#define ENA_REGS_CAPS_ADMIN_CMD_TO_MASK 0xf0000
+#define ENA_REGS_CAPS_CONTIGUOUS_QUEUE_REQUIRED_MASK 0x1
+#define ENA_REGS_CAPS_RESET_TIMEOUT_SHIFT 1
+#define ENA_REGS_CAPS_RESET_TIMEOUT_MASK 0x3e
+#define ENA_REGS_CAPS_DMA_ADDR_WIDTH_SHIFT 8
+#define ENA_REGS_CAPS_DMA_ADDR_WIDTH_MASK 0xff00
+#define ENA_REGS_CAPS_ADMIN_CMD_TO_SHIFT 16
+#define ENA_REGS_CAPS_ADMIN_CMD_TO_MASK 0xf0000
/* aq_caps register */
-#define ENA_REGS_AQ_CAPS_AQ_DEPTH_MASK 0xffff
-#define ENA_REGS_AQ_CAPS_AQ_ENTRY_SIZE_SHIFT 16
-#define ENA_REGS_AQ_CAPS_AQ_ENTRY_SIZE_MASK 0xffff0000
+#define ENA_REGS_AQ_CAPS_AQ_DEPTH_MASK 0xffff
+#define ENA_REGS_AQ_CAPS_AQ_ENTRY_SIZE_SHIFT 16
+#define ENA_REGS_AQ_CAPS_AQ_ENTRY_SIZE_MASK 0xffff0000
/* acq_caps register */
-#define ENA_REGS_ACQ_CAPS_ACQ_DEPTH_MASK 0xffff
-#define ENA_REGS_ACQ_CAPS_ACQ_ENTRY_SIZE_SHIFT 16
-#define ENA_REGS_ACQ_CAPS_ACQ_ENTRY_SIZE_MASK 0xffff0000
+#define ENA_REGS_ACQ_CAPS_ACQ_DEPTH_MASK 0xffff
+#define ENA_REGS_ACQ_CAPS_ACQ_ENTRY_SIZE_SHIFT 16
+#define ENA_REGS_ACQ_CAPS_ACQ_ENTRY_SIZE_MASK 0xffff0000
/* aenq_caps register */
-#define ENA_REGS_AENQ_CAPS_AENQ_DEPTH_MASK 0xffff
-#define ENA_REGS_AENQ_CAPS_AENQ_ENTRY_SIZE_SHIFT 16
-#define ENA_REGS_AENQ_CAPS_AENQ_ENTRY_SIZE_MASK 0xffff0000
+#define ENA_REGS_AENQ_CAPS_AENQ_DEPTH_MASK 0xffff
+#define ENA_REGS_AENQ_CAPS_AENQ_ENTRY_SIZE_SHIFT 16
+#define ENA_REGS_AENQ_CAPS_AENQ_ENTRY_SIZE_MASK 0xffff0000
/* dev_ctl register */
-#define ENA_REGS_DEV_CTL_DEV_RESET_MASK 0x1
-#define ENA_REGS_DEV_CTL_AQ_RESTART_SHIFT 1
-#define ENA_REGS_DEV_CTL_AQ_RESTART_MASK 0x2
-#define ENA_REGS_DEV_CTL_QUIESCENT_SHIFT 2
-#define ENA_REGS_DEV_CTL_QUIESCENT_MASK 0x4
-#define ENA_REGS_DEV_CTL_IO_RESUME_SHIFT 3
-#define ENA_REGS_DEV_CTL_IO_RESUME_MASK 0x8
-#define ENA_REGS_DEV_CTL_RESET_REASON_SHIFT 28
-#define ENA_REGS_DEV_CTL_RESET_REASON_MASK 0xf0000000
+#define ENA_REGS_DEV_CTL_DEV_RESET_MASK 0x1
+#define ENA_REGS_DEV_CTL_AQ_RESTART_SHIFT 1
+#define ENA_REGS_DEV_CTL_AQ_RESTART_MASK 0x2
+#define ENA_REGS_DEV_CTL_QUIESCENT_SHIFT 2
+#define ENA_REGS_DEV_CTL_QUIESCENT_MASK 0x4
+#define ENA_REGS_DEV_CTL_IO_RESUME_SHIFT 3
+#define ENA_REGS_DEV_CTL_IO_RESUME_MASK 0x8
+#define ENA_REGS_DEV_CTL_RESET_REASON_SHIFT 28
+#define ENA_REGS_DEV_CTL_RESET_REASON_MASK 0xf0000000
/* dev_sts register */
-#define ENA_REGS_DEV_STS_READY_MASK 0x1
-#define ENA_REGS_DEV_STS_AQ_RESTART_IN_PROGRESS_SHIFT 1
-#define ENA_REGS_DEV_STS_AQ_RESTART_IN_PROGRESS_MASK 0x2
-#define ENA_REGS_DEV_STS_AQ_RESTART_FINISHED_SHIFT 2
-#define ENA_REGS_DEV_STS_AQ_RESTART_FINISHED_MASK 0x4
-#define ENA_REGS_DEV_STS_RESET_IN_PROGRESS_SHIFT 3
-#define ENA_REGS_DEV_STS_RESET_IN_PROGRESS_MASK 0x8
-#define ENA_REGS_DEV_STS_RESET_FINISHED_SHIFT 4
-#define ENA_REGS_DEV_STS_RESET_FINISHED_MASK 0x10
-#define ENA_REGS_DEV_STS_FATAL_ERROR_SHIFT 5
-#define ENA_REGS_DEV_STS_FATAL_ERROR_MASK 0x20
-#define ENA_REGS_DEV_STS_QUIESCENT_STATE_IN_PROGRESS_SHIFT 6
-#define ENA_REGS_DEV_STS_QUIESCENT_STATE_IN_PROGRESS_MASK 0x40
-#define ENA_REGS_DEV_STS_QUIESCENT_STATE_ACHIEVED_SHIFT 7
-#define ENA_REGS_DEV_STS_QUIESCENT_STATE_ACHIEVED_MASK 0x80
+#define ENA_REGS_DEV_STS_READY_MASK 0x1
+#define ENA_REGS_DEV_STS_AQ_RESTART_IN_PROGRESS_SHIFT 1
+#define ENA_REGS_DEV_STS_AQ_RESTART_IN_PROGRESS_MASK 0x2
+#define ENA_REGS_DEV_STS_AQ_RESTART_FINISHED_SHIFT 2
+#define ENA_REGS_DEV_STS_AQ_RESTART_FINISHED_MASK 0x4
+#define ENA_REGS_DEV_STS_RESET_IN_PROGRESS_SHIFT 3
+#define ENA_REGS_DEV_STS_RESET_IN_PROGRESS_MASK 0x8
+#define ENA_REGS_DEV_STS_RESET_FINISHED_SHIFT 4
+#define ENA_REGS_DEV_STS_RESET_FINISHED_MASK 0x10
+#define ENA_REGS_DEV_STS_FATAL_ERROR_SHIFT 5
+#define ENA_REGS_DEV_STS_FATAL_ERROR_MASK 0x20
+#define ENA_REGS_DEV_STS_QUIESCENT_STATE_IN_PROGRESS_SHIFT 6
+#define ENA_REGS_DEV_STS_QUIESCENT_STATE_IN_PROGRESS_MASK 0x40
+#define ENA_REGS_DEV_STS_QUIESCENT_STATE_ACHIEVED_SHIFT 7
+#define ENA_REGS_DEV_STS_QUIESCENT_STATE_ACHIEVED_MASK 0x80
/* mmio_reg_read register */
-#define ENA_REGS_MMIO_REG_READ_REQ_ID_MASK 0xffff
-#define ENA_REGS_MMIO_REG_READ_REG_OFF_SHIFT 16
-#define ENA_REGS_MMIO_REG_READ_REG_OFF_MASK 0xffff0000
+#define ENA_REGS_MMIO_REG_READ_REQ_ID_MASK 0xffff
+#define ENA_REGS_MMIO_REG_READ_REG_OFF_SHIFT 16
+#define ENA_REGS_MMIO_REG_READ_REG_OFF_MASK 0xffff0000
/* rss_ind_entry_update register */
-#define ENA_REGS_RSS_IND_ENTRY_UPDATE_INDEX_MASK 0xffff
-#define ENA_REGS_RSS_IND_ENTRY_UPDATE_CQ_IDX_SHIFT 16
-#define ENA_REGS_RSS_IND_ENTRY_UPDATE_CQ_IDX_MASK 0xffff0000
+#define ENA_REGS_RSS_IND_ENTRY_UPDATE_INDEX_MASK 0xffff
+#define ENA_REGS_RSS_IND_ENTRY_UPDATE_CQ_IDX_SHIFT 16
+#define ENA_REGS_RSS_IND_ENTRY_UPDATE_CQ_IDX_MASK 0xffff0000
#endif /*_ENA_REGS_H_ */
--
2.7.4
^ permalink raw reply related
* [PATCH V1 net-next 11/12] net: ena: update driver version to 2.0.1
From: akiyano @ 2018-10-09 18:45 UTC (permalink / raw)
To: davem, netdev
Cc: Arthur Kiyanovski, dwmw, zorik, matua, saeedb, msw, aliguori,
nafea, gtzalik, netanel, alisaidi
In-Reply-To: <1539110709-31954-1-git-send-email-akiyano@amazon.com>
From: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
---
drivers/net/ethernet/amazon/ena/ena_netdev.h | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index d241dfc..5218736 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -43,9 +43,9 @@
#include "ena_com.h"
#include "ena_eth_com.h"
-#define DRV_MODULE_VER_MAJOR 1
-#define DRV_MODULE_VER_MINOR 5
-#define DRV_MODULE_VER_SUBMINOR 0
+#define DRV_MODULE_VER_MAJOR 2
+#define DRV_MODULE_VER_MINOR 0
+#define DRV_MODULE_VER_SUBMINOR 1
#define DRV_MODULE_NAME "ena"
#ifndef DRV_MODULE_VERSION
--
2.7.4
^ 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