* [PATCHv6 net-next 03/15] net: cls_bpf: add support for marking filters as hardware-only
From: Jakub Kicinski @ 2016-09-18 15:09 UTC (permalink / raw)
To: netdev; +Cc: ast, daniel, Jakub Kicinski
In-Reply-To: <1474211365-20088-1-git-send-email-jakub.kicinski@netronome.com>
Add cls_bpf support for the TCA_CLS_FLAGS_SKIP_SW flag.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
---
net/sched/cls_bpf.c | 34 +++++++++++++++++++++++++---------
1 file changed, 25 insertions(+), 9 deletions(-)
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 46af423a8a8f..18f9869cd4da 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -28,7 +28,7 @@ MODULE_DESCRIPTION("TC BPF based classifier");
#define CLS_BPF_NAME_LEN 256
#define CLS_BPF_SUPPORTED_GEN_FLAGS \
- TCA_CLS_FLAGS_SKIP_HW
+ (TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW)
struct cls_bpf_head {
struct list_head plist;
@@ -95,7 +95,9 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
qdisc_skb_cb(skb)->tc_classid = prog->res.classid;
- if (at_ingress) {
+ if (tc_skip_sw(prog->gen_flags)) {
+ filter_res = prog->exts_integrated ? TC_ACT_UNSPEC : 0;
+ } else if (at_ingress) {
/* It is safe to push/pull even if skb_shared() */
__skb_push(skb, skb->mac_len);
bpf_compute_data_end(skb);
@@ -163,32 +165,42 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog,
tp->protocol, &offload);
}
-static void cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog,
- struct cls_bpf_prog *oldprog)
+static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog,
+ struct cls_bpf_prog *oldprog)
{
struct net_device *dev = tp->q->dev_queue->dev;
struct cls_bpf_prog *obj = prog;
enum tc_clsbpf_command cmd;
+ bool skip_sw;
+ int ret;
+
+ skip_sw = tc_skip_sw(prog->gen_flags) ||
+ (oldprog && tc_skip_sw(oldprog->gen_flags));
if (oldprog && oldprog->offloaded) {
if (tc_should_offload(dev, tp, prog->gen_flags)) {
cmd = TC_CLSBPF_REPLACE;
- } else {
+ } else if (!tc_skip_sw(prog->gen_flags)) {
obj = oldprog;
cmd = TC_CLSBPF_DESTROY;
+ } else {
+ return -EINVAL;
}
} else {
if (!tc_should_offload(dev, tp, prog->gen_flags))
- return;
+ return skip_sw ? -EINVAL : 0;
cmd = TC_CLSBPF_ADD;
}
- if (cls_bpf_offload_cmd(tp, obj, cmd))
- return;
+ ret = cls_bpf_offload_cmd(tp, obj, cmd);
+ if (ret)
+ return skip_sw ? ret : 0;
obj->offloaded = true;
if (oldprog)
oldprog->offloaded = false;
+
+ return 0;
}
static void cls_bpf_stop_offload(struct tcf_proto *tp,
@@ -496,7 +508,11 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
if (ret < 0)
goto errout;
- cls_bpf_offload(tp, prog, oldprog);
+ ret = cls_bpf_offload(tp, prog, oldprog);
+ if (ret) {
+ cls_bpf_delete_prog(tp, prog);
+ return ret;
+ }
if (oldprog) {
list_replace_rcu(&oldprog->link, &prog->link);
--
1.9.1
^ permalink raw reply related
* [PATCHv6 net-next 02/15] net: cls_bpf: limit hardware offload by software-only flag
From: Jakub Kicinski @ 2016-09-18 15:09 UTC (permalink / raw)
To: netdev; +Cc: ast, daniel, Jakub Kicinski
In-Reply-To: <1474211365-20088-1-git-send-email-jakub.kicinski@netronome.com>
Add cls_bpf support for the TCA_CLS_FLAGS_SKIP_HW flag.
Unlike U32 and flower cls_bpf already has some netlink
flags defined. Create a new attribute to be able to use
the same flag values as the above.
Unlike U32 and flower reject unknown flags.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
---
v3:
- reject (instead of clear) unsupported flags;
- fix error handling.
v2:
- rename TCA_BPF_GEN_TCA_FLAGS -> TCA_BPF_FLAGS_GEN;
- add comment about clearing unsupported flags;
- validate flags after clearing unsupported.
---
include/net/pkt_cls.h | 1 +
include/uapi/linux/pkt_cls.h | 1 +
net/sched/cls_bpf.c | 22 ++++++++++++++++++++--
3 files changed, 22 insertions(+), 2 deletions(-)
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 41e8071dff87..57af9f3032ff 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -498,6 +498,7 @@ struct tc_cls_bpf_offload {
struct bpf_prog *prog;
const char *name;
bool exts_integrated;
+ u32 gen_flags;
};
#endif
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 8915b61bbf83..8fd715f806a2 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -396,6 +396,7 @@ enum {
TCA_BPF_FD,
TCA_BPF_NAME,
TCA_BPF_FLAGS,
+ TCA_BPF_FLAGS_GEN,
__TCA_BPF_MAX,
};
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 3ca9502a881c..46af423a8a8f 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -27,6 +27,8 @@ MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>");
MODULE_DESCRIPTION("TC BPF based classifier");
#define CLS_BPF_NAME_LEN 256
+#define CLS_BPF_SUPPORTED_GEN_FLAGS \
+ TCA_CLS_FLAGS_SKIP_HW
struct cls_bpf_head {
struct list_head plist;
@@ -40,6 +42,7 @@ struct cls_bpf_prog {
struct tcf_result res;
bool exts_integrated;
bool offloaded;
+ u32 gen_flags;
struct tcf_exts exts;
u32 handle;
union {
@@ -55,6 +58,7 @@ struct cls_bpf_prog {
static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = {
[TCA_BPF_CLASSID] = { .type = NLA_U32 },
[TCA_BPF_FLAGS] = { .type = NLA_U32 },
+ [TCA_BPF_FLAGS_GEN] = { .type = NLA_U32 },
[TCA_BPF_FD] = { .type = NLA_U32 },
[TCA_BPF_NAME] = { .type = NLA_NUL_STRING, .len = CLS_BPF_NAME_LEN },
[TCA_BPF_OPS_LEN] = { .type = NLA_U16 },
@@ -153,6 +157,7 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog,
bpf_offload.prog = prog->filter;
bpf_offload.name = prog->bpf_name;
bpf_offload.exts_integrated = prog->exts_integrated;
+ bpf_offload.gen_flags = prog->gen_flags;
return dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
tp->protocol, &offload);
@@ -166,14 +171,14 @@ static void cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog,
enum tc_clsbpf_command cmd;
if (oldprog && oldprog->offloaded) {
- if (tc_should_offload(dev, tp, 0)) {
+ if (tc_should_offload(dev, tp, prog->gen_flags)) {
cmd = TC_CLSBPF_REPLACE;
} else {
obj = oldprog;
cmd = TC_CLSBPF_DESTROY;
}
} else {
- if (!tc_should_offload(dev, tp, 0))
+ if (!tc_should_offload(dev, tp, prog->gen_flags))
return;
cmd = TC_CLSBPF_ADD;
}
@@ -369,6 +374,7 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
{
bool is_bpf, is_ebpf, have_exts = false;
struct tcf_exts exts;
+ u32 gen_flags = 0;
int ret;
is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS];
@@ -393,8 +399,17 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
have_exts = bpf_flags & TCA_BPF_FLAG_ACT_DIRECT;
}
+ if (tb[TCA_BPF_FLAGS_GEN]) {
+ gen_flags = nla_get_u32(tb[TCA_BPF_FLAGS_GEN]);
+ if (gen_flags & ~CLS_BPF_SUPPORTED_GEN_FLAGS ||
+ !tc_flags_valid(gen_flags)) {
+ ret = -EINVAL;
+ goto errout;
+ }
+ }
prog->exts_integrated = have_exts;
+ prog->gen_flags = gen_flags;
ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) :
cls_bpf_prog_from_efd(tb, prog, tp);
@@ -566,6 +581,9 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
bpf_flags |= TCA_BPF_FLAG_ACT_DIRECT;
if (bpf_flags && nla_put_u32(skb, TCA_BPF_FLAGS, bpf_flags))
goto nla_put_failure;
+ if (prog->gen_flags &&
+ nla_put_u32(skb, TCA_BPF_FLAGS_GEN, prog->gen_flags))
+ goto nla_put_failure;
nla_nest_end(skb, nest);
--
1.9.1
^ permalink raw reply related
* [PATCHv6 net-next 01/15] net: cls_bpf: add hardware offload
From: Jakub Kicinski @ 2016-09-18 15:09 UTC (permalink / raw)
To: netdev; +Cc: ast, daniel, Jakub Kicinski
In-Reply-To: <1474211365-20088-1-git-send-email-jakub.kicinski@netronome.com>
This patch adds hardware offload capability to cls_bpf classifier,
similar to what have been done with U32 and flower.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
---
v3:
- s/filter/prog/ in struct tc_cls_bpf_offload.
v2:
- drop unnecessary WARN_ON;
- reformat error handling a bit.
---
include/linux/netdevice.h | 2 ++
include/net/pkt_cls.h | 14 ++++++++++
net/sched/cls_bpf.c | 70 +++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 86 insertions(+)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2095b6ab3661..3c50db29a114 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -789,6 +789,7 @@ enum {
TC_SETUP_CLSU32,
TC_SETUP_CLSFLOWER,
TC_SETUP_MATCHALL,
+ TC_SETUP_CLSBPF,
};
struct tc_cls_u32_offload;
@@ -800,6 +801,7 @@ struct tc_to_netdev {
struct tc_cls_u32_offload *cls_u32;
struct tc_cls_flower_offload *cls_flower;
struct tc_cls_matchall_offload *cls_mall;
+ struct tc_cls_bpf_offload *cls_bpf;
};
};
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index a459be5fe1c2..41e8071dff87 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -486,4 +486,18 @@ struct tc_cls_matchall_offload {
unsigned long cookie;
};
+enum tc_clsbpf_command {
+ TC_CLSBPF_ADD,
+ TC_CLSBPF_REPLACE,
+ TC_CLSBPF_DESTROY,
+};
+
+struct tc_cls_bpf_offload {
+ enum tc_clsbpf_command command;
+ struct tcf_exts *exts;
+ struct bpf_prog *prog;
+ const char *name;
+ bool exts_integrated;
+};
+
#endif
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 1d92d4d3f222..3ca9502a881c 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -39,6 +39,7 @@ struct cls_bpf_prog {
struct list_head link;
struct tcf_result res;
bool exts_integrated;
+ bool offloaded;
struct tcf_exts exts;
u32 handle;
union {
@@ -137,6 +138,71 @@ static bool cls_bpf_is_ebpf(const struct cls_bpf_prog *prog)
return !prog->bpf_ops;
}
+static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog,
+ enum tc_clsbpf_command cmd)
+{
+ struct net_device *dev = tp->q->dev_queue->dev;
+ struct tc_cls_bpf_offload bpf_offload = {};
+ struct tc_to_netdev offload;
+
+ offload.type = TC_SETUP_CLSBPF;
+ offload.cls_bpf = &bpf_offload;
+
+ bpf_offload.command = cmd;
+ bpf_offload.exts = &prog->exts;
+ bpf_offload.prog = prog->filter;
+ bpf_offload.name = prog->bpf_name;
+ bpf_offload.exts_integrated = prog->exts_integrated;
+
+ return dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
+ tp->protocol, &offload);
+}
+
+static void cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog,
+ struct cls_bpf_prog *oldprog)
+{
+ struct net_device *dev = tp->q->dev_queue->dev;
+ struct cls_bpf_prog *obj = prog;
+ enum tc_clsbpf_command cmd;
+
+ if (oldprog && oldprog->offloaded) {
+ if (tc_should_offload(dev, tp, 0)) {
+ cmd = TC_CLSBPF_REPLACE;
+ } else {
+ obj = oldprog;
+ cmd = TC_CLSBPF_DESTROY;
+ }
+ } else {
+ if (!tc_should_offload(dev, tp, 0))
+ return;
+ cmd = TC_CLSBPF_ADD;
+ }
+
+ if (cls_bpf_offload_cmd(tp, obj, cmd))
+ return;
+
+ obj->offloaded = true;
+ if (oldprog)
+ oldprog->offloaded = false;
+}
+
+static void cls_bpf_stop_offload(struct tcf_proto *tp,
+ struct cls_bpf_prog *prog)
+{
+ int err;
+
+ if (!prog->offloaded)
+ return;
+
+ err = cls_bpf_offload_cmd(tp, prog, TC_CLSBPF_DESTROY);
+ if (err) {
+ pr_err("Stopping hardware offload failed: %d\n", err);
+ return;
+ }
+
+ prog->offloaded = false;
+}
+
static int cls_bpf_init(struct tcf_proto *tp)
{
struct cls_bpf_head *head;
@@ -176,6 +242,7 @@ static int cls_bpf_delete(struct tcf_proto *tp, unsigned long arg)
{
struct cls_bpf_prog *prog = (struct cls_bpf_prog *) arg;
+ cls_bpf_stop_offload(tp, prog);
list_del_rcu(&prog->link);
tcf_unbind_filter(tp, &prog->res);
call_rcu(&prog->rcu, __cls_bpf_delete_prog);
@@ -192,6 +259,7 @@ static bool cls_bpf_destroy(struct tcf_proto *tp, bool force)
return false;
list_for_each_entry_safe(prog, tmp, &head->plist, link) {
+ cls_bpf_stop_offload(tp, prog);
list_del_rcu(&prog->link);
tcf_unbind_filter(tp, &prog->res);
call_rcu(&prog->rcu, __cls_bpf_delete_prog);
@@ -413,6 +481,8 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
if (ret < 0)
goto errout;
+ cls_bpf_offload(tp, prog, oldprog);
+
if (oldprog) {
list_replace_rcu(&oldprog->link, &prog->link);
tcf_unbind_filter(tp, &oldprog->res);
--
1.9.1
^ permalink raw reply related
* [PATCHv6 net-next 00/15] BPF hardware offload (cls_bpf for now)
From: Jakub Kicinski @ 2016-09-18 15:09 UTC (permalink / raw)
To: netdev; +Cc: ast, daniel, Jakub Kicinski
Hi!
As spotted by Daniel JIT might have accessed indexes past the end
of verifier's reg_state array.
v6 (patch 8 only):
- explicitly check for registers >= MAX_BPF_REG;
- fix leaky error path.
v5:
- fix names of guard defines in bpf_verfier.h.
v4:
- rename parser -> analyzer;
- reorganize the analyzer patches a bit;
- use bitfield.h directly.
--- merge blurb:
In the last year a lot of progress have been made on offloading
simpler TC classifiers. There is also growing interest in using
BPF for generic high-speed packet processing in the kernel.
It seems beneficial to tie those two trends together and think
about hardware offloads of BPF programs. This patch set presents
such offload to Netronome smart NICs. cls_bpf is extended with
hardware offload capabilities and NFP driver gets a JIT translator
which in presence of capable firmware can be used to offload
the BPF program onto the card.
BPF JIT implementation is not 100% complete (e.g. missing instructions)
but it is functional. Encouragingly it should be possible to
offload most (if not all) advanced BPF features onto the NIC -
including packet modification, maps, tunnel encap/decap etc.
Example of basic tests I used:
__section_cls_entry
int cls_entry(struct __sk_buff *skb)
{
if (load_byte(skb, 0) != 0x0)
return 0;
if (load_byte(skb, 4) != 0x1)
return 0;
skb->mark = 0xcafe;
if (load_byte(skb, 50) != 0xff)
return 0;
return ~0U;
}
Above code can be compiled with Clang and loaded like this:
# ethtool -K p1p1 hw-tc-offload on
# tc qdisc add dev p1p1 ingress
# tc filter add dev p1p1 parent ffff: bpf obj prog.o action drop
This set implements the basic transparent offload, the skip_{sw,hw}
flags and reporting statistics for cls_bpf.
Jakub Kicinski (15):
net: cls_bpf: add hardware offload
net: cls_bpf: limit hardware offload by software-only flag
net: cls_bpf: add support for marking filters as hardware-only
bpf: don't (ab)use instructions to store state
bpf: expose internal verfier structures
bpf: enable non-core use of the verfier
bpf: recognize 64bit immediate loads as consts
nfp: add BPF to NFP code translator
nfp: bpf: add hardware bpf offload
net: cls_bpf: allow offloaded filters to update stats
nfp: bpf: allow offloaded filters to update stats
nfp: bpf: add packet marking support
net: act_mirred: allow statistic updates from offloaded actions
nfp: bpf: add support for legacy redirect action
nfp: bpf: add offload of TC direct action mode
drivers/net/ethernet/netronome/nfp/Makefile | 7 +
drivers/net/ethernet/netronome/nfp/nfp_asm.h | 233 +++
drivers/net/ethernet/netronome/nfp/nfp_bpf.h | 212 +++
drivers/net/ethernet/netronome/nfp/nfp_bpf_jit.c | 1811 ++++++++++++++++++++
.../net/ethernet/netronome/nfp/nfp_bpf_verifier.c | 171 ++
drivers/net/ethernet/netronome/nfp/nfp_net.h | 47 +-
.../net/ethernet/netronome/nfp/nfp_net_common.c | 134 +-
drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h | 51 +-
.../net/ethernet/netronome/nfp/nfp_net_ethtool.c | 12 +
.../net/ethernet/netronome/nfp/nfp_net_offload.c | 291 ++++
.../net/ethernet/netronome/nfp/nfp_netvf_main.c | 2 +-
include/linux/bpf_verifier.h | 89 +
include/linux/netdevice.h | 2 +
include/net/pkt_cls.h | 16 +
include/uapi/linux/pkt_cls.h | 1 +
kernel/bpf/verifier.c | 384 +++--
net/sched/act_mirred.c | 8 +
net/sched/cls_bpf.c | 117 +-
18 files changed, 3382 insertions(+), 206 deletions(-)
create mode 100644 drivers/net/ethernet/netronome/nfp/nfp_asm.h
create mode 100644 drivers/net/ethernet/netronome/nfp/nfp_bpf.h
create mode 100644 drivers/net/ethernet/netronome/nfp/nfp_bpf_jit.c
create mode 100644 drivers/net/ethernet/netronome/nfp/nfp_bpf_verifier.c
create mode 100644 drivers/net/ethernet/netronome/nfp/nfp_net_offload.c
create mode 100644 include/linux/bpf_verifier.h
--
1.9.1
^ permalink raw reply
* [PATCH 2/2] net: ethernet: broadcom: bcm63xx: use new api ethtool_{get|set}_link_ksettings
From: Philippe Reynes @ 2016-09-18 14:59 UTC (permalink / raw)
To: f.fainelli, davem, andrew, treding, ivecera, xypron.glpk, simon
Cc: bcm-kernel-feedback-list, netdev, linux-arm-kernel, linux-kernel,
Philippe Reynes
In-Reply-To: <1474210747-19627-1-git-send-email-tremyfr@gmail.com>
The ethtool api {get|set}_settings is deprecated.
We move this driver to new api {get|set}_link_ksettings.
Signed-off-by: Philippe Reynes <tremyfr@gmail.com>
---
drivers/net/ethernet/broadcom/bcm63xx_enet.c | 52 ++++++++++++++------------
1 files changed, 28 insertions(+), 24 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index 082f3f0..ae364c7 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -1442,39 +1442,40 @@ static int bcm_enet_nway_reset(struct net_device *dev)
return -EOPNOTSUPP;
}
-static int bcm_enet_get_settings(struct net_device *dev,
- struct ethtool_cmd *cmd)
+static int bcm_enet_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct bcm_enet_priv *priv;
+ u32 supported, advertising;
priv = netdev_priv(dev);
- cmd->maxrxpkt = 0;
- cmd->maxtxpkt = 0;
-
if (priv->has_phy) {
if (!dev->phydev)
return -ENODEV;
- return phy_ethtool_gset(dev->phydev, cmd);
+ return phy_ethtool_ksettings_get(dev->phydev, cmd);
} else {
- cmd->autoneg = 0;
- ethtool_cmd_speed_set(cmd, ((priv->force_speed_100)
- ? SPEED_100 : SPEED_10));
- cmd->duplex = (priv->force_duplex_full) ?
+ cmd->base.autoneg = 0;
+ cmd->base.speed = (priv->force_speed_100) ?
+ SPEED_100 : SPEED_10;
+ cmd->base.duplex = (priv->force_duplex_full) ?
DUPLEX_FULL : DUPLEX_HALF;
- cmd->supported = ADVERTISED_10baseT_Half |
+ supported = ADVERTISED_10baseT_Half |
ADVERTISED_10baseT_Full |
ADVERTISED_100baseT_Half |
ADVERTISED_100baseT_Full;
- cmd->advertising = 0;
- cmd->port = PORT_MII;
- cmd->transceiver = XCVR_EXTERNAL;
+ advertising = 0;
+ ethtool_convert_legacy_u32_to_link_mode(
+ cmd->link_modes.supported, supported);
+ ethtool_convert_legacy_u32_to_link_mode(
+ cmd->link_modes.advertising, advertising);
+ cmd->base.port = PORT_MII;
}
return 0;
}
-static int bcm_enet_set_settings(struct net_device *dev,
- struct ethtool_cmd *cmd)
+static int bcm_enet_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct bcm_enet_priv *priv;
@@ -1482,16 +1483,19 @@ static int bcm_enet_set_settings(struct net_device *dev,
if (priv->has_phy) {
if (!dev->phydev)
return -ENODEV;
- return phy_ethtool_sset(dev->phydev, cmd);
+ return phy_ethtool_ksettings_set(dev->phydev, cmd);
} else {
- if (cmd->autoneg ||
- (cmd->speed != SPEED_100 && cmd->speed != SPEED_10) ||
- cmd->port != PORT_MII)
+ if (cmd->base.autoneg ||
+ (cmd->base.speed != SPEED_100 &&
+ cmd->base.speed != SPEED_10) ||
+ cmd->base.port != PORT_MII)
return -EINVAL;
- priv->force_speed_100 = (cmd->speed == SPEED_100) ? 1 : 0;
- priv->force_duplex_full = (cmd->duplex == DUPLEX_FULL) ? 1 : 0;
+ priv->force_speed_100 =
+ (cmd->base.speed == SPEED_100) ? 1 : 0;
+ priv->force_duplex_full =
+ (cmd->base.duplex == DUPLEX_FULL) ? 1 : 0;
if (netif_running(dev))
bcm_enet_adjust_link(dev);
@@ -1585,14 +1589,14 @@ static const struct ethtool_ops bcm_enet_ethtool_ops = {
.get_sset_count = bcm_enet_get_sset_count,
.get_ethtool_stats = bcm_enet_get_ethtool_stats,
.nway_reset = bcm_enet_nway_reset,
- .get_settings = bcm_enet_get_settings,
- .set_settings = bcm_enet_set_settings,
.get_drvinfo = bcm_enet_get_drvinfo,
.get_link = ethtool_op_get_link,
.get_ringparam = bcm_enet_get_ringparam,
.set_ringparam = bcm_enet_set_ringparam,
.get_pauseparam = bcm_enet_get_pauseparam,
.set_pauseparam = bcm_enet_set_pauseparam,
+ .get_link_ksettings = bcm_enet_get_link_ksettings,
+ .set_link_ksettings = bcm_enet_set_link_ksettings,
};
static int bcm_enet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
--
1.7.4.4
^ permalink raw reply related
* [PATCH 1/2] net: ethernet: broadcom: bcm63xx: use phydev from struct net_device
From: Philippe Reynes @ 2016-09-18 14:59 UTC (permalink / raw)
To: f.fainelli, davem, andrew, treding, ivecera, xypron.glpk, simon
Cc: bcm-kernel-feedback-list, netdev, linux-arm-kernel, linux-kernel,
Philippe Reynes
The private structure contain a pointer to phydev, but the structure
net_device already contain such pointer. So we can remove the pointer
phydev in the private structure, and update the driver to use the
one contained in struct net_device.
Signed-off-by: Philippe Reynes <tremyfr@gmail.com>
---
drivers/net/ethernet/broadcom/bcm63xx_enet.c | 31 +++++++++++--------------
drivers/net/ethernet/broadcom/bcm63xx_enet.h | 1 -
2 files changed, 14 insertions(+), 18 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index 6c8bc5f..082f3f0 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -791,7 +791,7 @@ static void bcm_enet_adjust_phy_link(struct net_device *dev)
int status_changed;
priv = netdev_priv(dev);
- phydev = priv->phydev;
+ phydev = dev->phydev;
status_changed = 0;
if (priv->old_link != phydev->link) {
@@ -913,7 +913,6 @@ static int bcm_enet_open(struct net_device *dev)
priv->old_link = 0;
priv->old_duplex = -1;
priv->old_pause = -1;
- priv->phydev = phydev;
}
/* mask all interrupts and request them */
@@ -1085,7 +1084,7 @@ static int bcm_enet_open(struct net_device *dev)
ENETDMAC_IRMASK, priv->tx_chan);
if (priv->has_phy)
- phy_start(priv->phydev);
+ phy_start(phydev);
else
bcm_enet_adjust_link(dev);
@@ -1127,7 +1126,7 @@ out_freeirq:
free_irq(dev->irq, dev);
out_phy_disconnect:
- phy_disconnect(priv->phydev);
+ phy_disconnect(phydev);
return ret;
}
@@ -1190,7 +1189,7 @@ static int bcm_enet_stop(struct net_device *dev)
netif_stop_queue(dev);
napi_disable(&priv->napi);
if (priv->has_phy)
- phy_stop(priv->phydev);
+ phy_stop(dev->phydev);
del_timer_sync(&priv->rx_timeout);
/* mask all interrupts */
@@ -1234,10 +1233,8 @@ static int bcm_enet_stop(struct net_device *dev)
free_irq(dev->irq, dev);
/* release phy */
- if (priv->has_phy) {
- phy_disconnect(priv->phydev);
- priv->phydev = NULL;
- }
+ if (priv->has_phy)
+ phy_disconnect(dev->phydev);
return 0;
}
@@ -1437,9 +1434,9 @@ static int bcm_enet_nway_reset(struct net_device *dev)
priv = netdev_priv(dev);
if (priv->has_phy) {
- if (!priv->phydev)
+ if (!dev->phydev)
return -ENODEV;
- return genphy_restart_aneg(priv->phydev);
+ return genphy_restart_aneg(dev->phydev);
}
return -EOPNOTSUPP;
@@ -1456,9 +1453,9 @@ static int bcm_enet_get_settings(struct net_device *dev,
cmd->maxtxpkt = 0;
if (priv->has_phy) {
- if (!priv->phydev)
+ if (!dev->phydev)
return -ENODEV;
- return phy_ethtool_gset(priv->phydev, cmd);
+ return phy_ethtool_gset(dev->phydev, cmd);
} else {
cmd->autoneg = 0;
ethtool_cmd_speed_set(cmd, ((priv->force_speed_100)
@@ -1483,9 +1480,9 @@ static int bcm_enet_set_settings(struct net_device *dev,
priv = netdev_priv(dev);
if (priv->has_phy) {
- if (!priv->phydev)
+ if (!dev->phydev)
return -ENODEV;
- return phy_ethtool_sset(priv->phydev, cmd);
+ return phy_ethtool_sset(dev->phydev, cmd);
} else {
if (cmd->autoneg ||
@@ -1604,9 +1601,9 @@ static int bcm_enet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
priv = netdev_priv(dev);
if (priv->has_phy) {
- if (!priv->phydev)
+ if (!dev->phydev)
return -ENODEV;
- return phy_mii_ioctl(priv->phydev, rq, cmd);
+ return phy_mii_ioctl(dev->phydev, rq, cmd);
} else {
struct mii_if_info mii;
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.h b/drivers/net/ethernet/broadcom/bcm63xx_enet.h
index f55af43..0a1b7b2 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.h
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.h
@@ -290,7 +290,6 @@ struct bcm_enet_priv {
/* used when a phy is connected (phylib used) */
struct mii_bus *mii_bus;
- struct phy_device *phydev;
int old_link;
int old_duplex;
int old_pause;
--
1.7.4.4
^ permalink raw reply related
* [net-next:master 136/385] net/sched/cls_route.c:565:22-26: ERROR: f is NULL but dereferenced.
From: kbuild test robot @ 2016-09-18 14:57 UTC (permalink / raw)
To: WANG Cong; +Cc: kbuild-all, netdev
tree: https://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git master
head: fd9527f404d51e50f40dac0d9a69f2eff3dac33e
commit: b9a24bb76bf611a5268ceffe04219e6ad264559b [136/385] net_sched: properly handle failure case of tcf_exts_init()
coccinelle warnings: (new ones prefixed by >>)
>> net/sched/cls_route.c:565:22-26: ERROR: f is NULL but dereferenced.
vim +565 net/sched/cls_route.c
549 *fp = f->next;
550 break;
551 }
552 }
553 }
554 }
555
556 route4_reset_fastmap(head);
557 *arg = (unsigned long)f;
558 if (fold) {
559 tcf_unbind_filter(tp, &fold->res);
560 call_rcu(&fold->rcu, route4_delete_filter);
561 }
562 return 0;
563
564 errout:
> 565 tcf_exts_destroy(&f->exts);
566 kfree(f);
567 return err;
568 }
569
570 static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg)
571 {
572 struct route4_head *head = rtnl_dereference(tp->root);
573 unsigned int h, h1;
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
^ permalink raw reply
* Re: [net-next PATCH] net: netlink messages for HW addr programming
From: Roopa Prabhu @ 2016-09-18 14:51 UTC (permalink / raw)
To: Patrick Ruddy
Cc: netdev, davem, jiri, alexander.h.duyck, stephen, lboccass, sven
In-Reply-To: <1473958082-30982-1-git-send-email-pruddy@brocade.com>
On 9/15/16, 9:48 AM, Patrick Ruddy wrote:
> Add RTM_NEWADDR and RTM_DELADDR netlink messages with family
> AF_UNSPEC to indicate interest in specific unicast and multicast
> hardware addresses. These messages are sent when addresses are
> added or deleted from the appropriate interface driver.
> Added AF_UNSPEC GETADDR function to allow the netlink notifications
> to be replayed to avoid loss of state due to application start
> ordering or restart.
>
> Signed-off-by: Patrick Ruddy <pruddy@brocade.com>
> ---
RTM_NEWADDR and RTM_DELADDR are not used to add these entries to the kernel.
so, it seems a bit wrong to use RTM_NEWADDR and RTM_DELADDR to notify them to
userspace and also to request a special dump of these addresses.
This could just be a new nested netlink attribute in the existing link dump ?
^ permalink raw reply
* [PATCH net-next 2/2] net/sched: act_vlan: Introduce TCA_VLAN_ACT_MODIFY vlan action
From: Shmulik Ladkani @ 2016-09-18 14:33 UTC (permalink / raw)
To: David S . Miller; +Cc: Jiri Pirko, Jamal Hadi Salim, netdev, Shmulik Ladkani
In-Reply-To: <1474209225-23665-1-git-send-email-shmulik.ladkani@gmail.com>
TCA_VLAN_ACT_MODIFY allows one to change an existing tag.
It accepts same attributes as TCA_VLAN_ACT_PUSH (protocol, id,
priority).
If packet is vlan tagged, then the tag gets overwritten according to
user specified attributes.
For example, this allows user to replace a tag's vid while preserving
its priority bits (as opposed to "action vlan pop pipe action vlan push").
Signed-off-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
---
include/uapi/linux/tc_act/tc_vlan.h | 1 +
net/sched/act_vlan.c | 29 ++++++++++++++++++++++++++++-
2 files changed, 29 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/tc_act/tc_vlan.h b/include/uapi/linux/tc_act/tc_vlan.h
index be72b6e384..bddb272b84 100644
--- a/include/uapi/linux/tc_act/tc_vlan.h
+++ b/include/uapi/linux/tc_act/tc_vlan.h
@@ -16,6 +16,7 @@
#define TCA_VLAN_ACT_POP 1
#define TCA_VLAN_ACT_PUSH 2
+#define TCA_VLAN_ACT_MODIFY 3
struct tc_vlan {
tc_gen;
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 59a8d3150a..e5eeaa7a01 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -30,6 +30,7 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a,
struct tcf_vlan *v = to_vlan(a);
int action;
int err;
+ u16 tci;
spin_lock(&v->tcf_lock);
tcf_lastuse_update(&v->tcf_tm);
@@ -48,6 +49,30 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a,
if (err)
goto drop;
break;
+ case TCA_VLAN_ACT_MODIFY:
+ if (!skb_vlan_tagged(skb))
+ goto unlock;
+ /* extract existing tag (and guarantee no hwaccel tag) */
+ if (skb_vlan_tag_present(skb)) {
+ tci = skb_vlan_tag_get(skb);
+ skb->vlan_tci = 0;
+ } else {
+ if (skb->mac_len < VLAN_ETH_HLEN)
+ goto unlock;
+ err = __skb_vlan_pop(skb, &tci);
+ if (err)
+ goto drop;
+ }
+ /* replace the vid */
+ tci = (tci & ~VLAN_VID_MASK) | v->tcfv_push_vid;
+ /* replace prio bits, if tcfv_push_prio specified */
+ if (v->tcfv_push_prio) {
+ tci &= ~VLAN_PRIO_MASK;
+ tci |= v->tcfv_push_prio << VLAN_PRIO_SHIFT;
+ }
+ /* put updated tci as hwaccel tag */
+ __vlan_hwaccel_put_tag(skb, v->tcfv_push_proto, tci);
+ break;
default:
BUG();
}
@@ -102,6 +127,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
case TCA_VLAN_ACT_POP:
break;
case TCA_VLAN_ACT_PUSH:
+ case TCA_VLAN_ACT_MODIFY:
if (!tb[TCA_VLAN_PUSH_VLAN_ID]) {
if (exists)
tcf_hash_release(*a, bind);
@@ -185,7 +211,8 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a,
if (nla_put(skb, TCA_VLAN_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
- if (v->tcfv_action == TCA_VLAN_ACT_PUSH &&
+ if ((v->tcfv_action == TCA_VLAN_ACT_PUSH ||
+ v->tcfv_action == TCA_VLAN_ACT_MODIFY) &&
(nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, v->tcfv_push_vid) ||
nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL,
v->tcfv_push_proto) ||
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 1/2] net: skbuff: Export __skb_vlan_pop
From: Shmulik Ladkani @ 2016-09-18 14:33 UTC (permalink / raw)
To: David S . Miller; +Cc: Jiri Pirko, Jamal Hadi Salim, netdev, Shmulik Ladkani
In-Reply-To: <1474209225-23665-1-git-send-email-shmulik.ladkani@gmail.com>
This exports the functionality of extracting the tag from the payload,
without moving next vlan tag into hw accel tag.
Signed-off-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
---
include/linux/skbuff.h | 1 +
net/core/skbuff.c | 7 +++++--
2 files changed, 6 insertions(+), 2 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 4c5662f05b..000c5301b8 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3075,6 +3075,7 @@ bool skb_gso_validate_mtu(const struct sk_buff *skb, unsigned int mtu);
struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features);
struct sk_buff *skb_vlan_untag(struct sk_buff *skb);
int skb_ensure_writable(struct sk_buff *skb, int write_len);
+int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci);
int skb_vlan_pop(struct sk_buff *skb);
int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index cc2c004838..2937088844 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4493,8 +4493,10 @@ int skb_ensure_writable(struct sk_buff *skb, int write_len)
}
EXPORT_SYMBOL(skb_ensure_writable);
-/* remove VLAN header from packet and update csum accordingly. */
-static int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci)
+/* remove VLAN header from packet and update csum accordingly.
+ * expects a non skb_vlan_tag_present skb with a vlan tag payload
+ */
+int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci)
{
struct vlan_hdr *vhdr;
unsigned int offset = skb->data - skb_mac_header(skb);
@@ -4525,6 +4527,7 @@ pull:
return err;
}
+EXPORT_SYMBOL(__skb_vlan_pop);
int skb_vlan_pop(struct sk_buff *skb)
{
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 0/2] act_vlan: Introduce TCA_VLAN_ACT_MODIFY vlan action
From: Shmulik Ladkani @ 2016-09-18 14:33 UTC (permalink / raw)
To: David S . Miller; +Cc: Jiri Pirko, Jamal Hadi Salim, netdev, Shmulik Ladkani
TCA_VLAN_ACT_MODIFY allows one to change an existing tag.
It accepts same attributes as TCA_VLAN_ACT_PUSH (protocol, id,
priority).
If packet is vlan tagged, then the tag gets overwritten according to
user specified attributes.
For example, this allows user to replace a tag's vid while preserving
its priority bits (as opposed to "action vlan pop pipe action vlan push").
Shmulik Ladkani (2):
net: skbuff: Export __skb_vlan_pop
net/sched: act_vlan: Introduce TCA_VLAN_ACT_MODIFY vlan action
include/linux/skbuff.h | 1 +
include/uapi/linux/tc_act/tc_vlan.h | 1 +
net/core/skbuff.c | 7 +++++--
net/sched/act_vlan.c | 29 ++++++++++++++++++++++++++++-
4 files changed, 35 insertions(+), 3 deletions(-)
--
2.7.4
^ permalink raw reply
* Re: [PATCH 2/2] iw_cxgb4: add fast-path for small REG_MR operations
From: Leon Romanovsky @ 2016-09-18 14:22 UTC (permalink / raw)
To: Steve Wise; +Cc: dledford, davem, netdev, linux-rdma
In-Reply-To: <3153440ff068cc56a517af2ba6be2b0de0f4dd99.1474037695.git.swise@opengridcomputing.com>
[-- Attachment #1: Type: text/plain, Size: 1109 bytes --]
On Fri, Sep 16, 2016 at 07:54:52AM -0700, Steve Wise wrote:
> When processing a REG_MR work request, if fw supports the
> FW_RI_NSMR_TPTE_WR work request, and if the page list for this
> registration is <= 2 pages, and the current state of the mr is INVALID,
> then use FW_RI_NSMR_TPTE_WR to pass down a fully populated TPTE for FW
> to write. This avoids FW having to do an async read of the TPTE blocking
> the SQ until the read completes.
>
> To know if the current MR state is INVALID or not, iw_cxgb4 must track the
> state of each fastreg MR. The c4iw_mr struct state is updated as REG_MR
> and LOCAL_INV WRs are posted and completed, when a reg_mr is destroyed,
> and when RECV completions are processed that include a local invalidation.
>
> This optimization increases small IO IOPS for both iSER and NVMF.
>
> Signed-off-by: Steve Wise <swise@opengridcomputing.com>
> ---
<...>
> + struct ib_reg_wr *wr, struct c4iw_mr *mhp,
> + u8 *len16)
> +{
> + __be64 *p = (__be64 *)fr->pbl;
> +
> + fr->r2 = cpu_to_be32(0);
Is there any difference between the line above and "fr->r2 = 0"?
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]
^ permalink raw reply
* Re: [PATCH v2 net-next 2/2] net sched ife action: Introduce skb tcindex metadata encap decap
From: Jamal Hadi Salim @ 2016-09-18 14:11 UTC (permalink / raw)
To: kbuild test robot; +Cc: kbuild-all, davem, netdev, xiyou.wangcong
In-Reply-To: <201609182107.clJdf9s2%fengguang.wu@intel.com>
On 16-09-18 09:45 AM, kbuild test robot wrote:
> Hi Jamal,
>
> [auto build test ERROR on net-next/master]
Hi monsieur/madame Bot,
fixed in v3.
cheers,
jamal
^ permalink raw reply
* [PATCH 2/2] mac80211: Use rhltable instead of rhashtable
From: Herbert Xu @ 2016-09-18 13:54 UTC (permalink / raw)
To: Johannes Berg, David S. Miller, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-wireless-u79uwXL29TY76Z2rM5mHXA, Thomas Graf,
tom-BjP2VixgY4xUbtYUoyoikg, Ben Greear
In-Reply-To: <20160918135030.GA7062@gondor.apana.org.au>
mac80211 currently uses rhashtable with insecure_elasticity set
to true. The latter is because of duplicate objects. What's
more, mac80211 walks the rhashtable chains by hand which is broken
as rhashtable may contain multiple tables due to resizing or
rehashing.
This patch fixes it by converting it to the newly added rhltable
interface which is designed for use with duplicate objects.
With rhltable a lookup returns a list of objects instead of a
single one. This is then fed into the existing for_each_sta_info
macro.
This patch also deletes the sta_addr_hash function since rhashtable
defaults to jhash.
Signed-off-by: Herbert Xu <herbert-lOAM2aK0SrRLBo1qDEOMRrpzq4S04n8Q@public.gmane.org>
---
net/mac80211/ieee80211_i.h | 2 -
net/mac80211/rx.c | 7 +-----
net/mac80211/sta_info.c | 52 ++++++++++++++++++---------------------------
net/mac80211/sta_info.h | 19 ++++++----------
net/mac80211/status.c | 7 +-----
5 files changed, 33 insertions(+), 54 deletions(-)
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index f56d342..1a52cd4 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1208,7 +1208,7 @@ struct ieee80211_local {
spinlock_t tim_lock;
unsigned long num_sta;
struct list_head sta_list;
- struct rhashtable sta_hash;
+ struct rhltable sta_hash;
struct timer_list sta_cleanup;
int sta_generation;
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 9dce3b1..5e26dc6 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -3940,7 +3940,7 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw,
__le16 fc;
struct ieee80211_rx_data rx;
struct ieee80211_sub_if_data *prev;
- struct rhash_head *tmp;
+ struct rhlist_head *tmp;
int err = 0;
fc = ((struct ieee80211_hdr *)skb->data)->frame_control;
@@ -3983,13 +3983,10 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw,
goto out;
} else if (ieee80211_is_data(fc)) {
struct sta_info *sta, *prev_sta;
- const struct bucket_table *tbl;
prev_sta = NULL;
- tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash);
-
- for_each_sta_info(local, tbl, hdr->addr2, sta, tmp) {
+ for_each_sta_info(local, hdr->addr2, sta, tmp) {
if (!prev_sta) {
prev_sta = sta;
continue;
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 19f14c9..198d0bd 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -67,12 +67,10 @@
static const struct rhashtable_params sta_rht_params = {
.nelem_hint = 3, /* start small */
- .insecure_elasticity = true, /* Disable chain-length checks. */
.automatic_shrinking = true,
.head_offset = offsetof(struct sta_info, hash_node),
.key_offset = offsetof(struct sta_info, addr),
.key_len = ETH_ALEN,
- .hashfn = sta_addr_hash,
.max_size = CONFIG_MAC80211_STA_HASH_MAX_SIZE,
};
@@ -80,8 +78,8 @@ static const struct rhashtable_params sta_rht_params = {
static int sta_info_hash_del(struct ieee80211_local *local,
struct sta_info *sta)
{
- return rhashtable_remove_fast(&local->sta_hash, &sta->hash_node,
- sta_rht_params);
+ return rhltable_remove(&local->sta_hash, &sta->hash_node,
+ sta_rht_params);
}
static void __cleanup_single_sta(struct sta_info *sta)
@@ -157,19 +155,22 @@ static void cleanup_single_sta(struct sta_info *sta)
sta_info_free(local, sta);
}
+struct rhlist_head *sta_info_hash_lookup(struct ieee80211_local *local,
+ const u8 *addr)
+{
+ return rhltable_lookup(&local->sta_hash, addr, sta_rht_params);
+}
+
/* protected by RCU */
struct sta_info *sta_info_get(struct ieee80211_sub_if_data *sdata,
const u8 *addr)
{
struct ieee80211_local *local = sdata->local;
+ struct rhlist_head *tmp;
struct sta_info *sta;
- struct rhash_head *tmp;
- const struct bucket_table *tbl;
rcu_read_lock();
- tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash);
-
- for_each_sta_info(local, tbl, addr, sta, tmp) {
+ for_each_sta_info(local, addr, sta, tmp) {
if (sta->sdata == sdata) {
rcu_read_unlock();
/* this is safe as the caller must already hold
@@ -190,14 +191,11 @@ struct sta_info *sta_info_get_bss(struct ieee80211_sub_if_data *sdata,
const u8 *addr)
{
struct ieee80211_local *local = sdata->local;
+ struct rhlist_head *tmp;
struct sta_info *sta;
- struct rhash_head *tmp;
- const struct bucket_table *tbl;
rcu_read_lock();
- tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash);
-
- for_each_sta_info(local, tbl, addr, sta, tmp) {
+ for_each_sta_info(local, addr, sta, tmp) {
if (sta->sdata == sdata ||
(sta->sdata->bss && sta->sdata->bss == sdata->bss)) {
rcu_read_unlock();
@@ -263,8 +261,8 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
static int sta_info_hash_add(struct ieee80211_local *local,
struct sta_info *sta)
{
- return rhashtable_insert_fast(&local->sta_hash, &sta->hash_node,
- sta_rht_params);
+ return rhltable_insert(&local->sta_hash, &sta->hash_node,
+ sta_rht_params);
}
static void sta_deliver_ps_frames(struct work_struct *wk)
@@ -450,9 +448,9 @@ static int sta_info_insert_check(struct sta_info *sta)
is_multicast_ether_addr(sta->sta.addr)))
return -EINVAL;
- /* Strictly speaking this isn't necessary as we hold the mutex, but
- * the rhashtable code can't really deal with that distinction. We
- * do require the mutex for correctness though.
+ /* The RCU read lock is required by rhashtable due to
+ * asynchronous resize/rehash. We also require the mutex
+ * for correctness.
*/
rcu_read_lock();
lockdep_assert_held(&sdata->local->sta_mtx);
@@ -1040,16 +1038,11 @@ static void sta_info_cleanup(unsigned long data)
round_jiffies(jiffies + STA_INFO_CLEANUP_INTERVAL));
}
-u32 sta_addr_hash(const void *key, u32 length, u32 seed)
-{
- return jhash(key, ETH_ALEN, seed);
-}
-
int sta_info_init(struct ieee80211_local *local)
{
int err;
- err = rhashtable_init(&local->sta_hash, &sta_rht_params);
+ err = rhltable_init(&local->sta_hash, &sta_rht_params);
if (err)
return err;
@@ -1065,7 +1058,7 @@ int sta_info_init(struct ieee80211_local *local)
void sta_info_stop(struct ieee80211_local *local)
{
del_timer_sync(&local->sta_cleanup);
- rhashtable_destroy(&local->sta_hash);
+ rhltable_destroy(&local->sta_hash);
}
@@ -1135,17 +1128,14 @@ struct ieee80211_sta *ieee80211_find_sta_by_ifaddr(struct ieee80211_hw *hw,
const u8 *localaddr)
{
struct ieee80211_local *local = hw_to_local(hw);
+ struct rhlist_head *tmp;
struct sta_info *sta;
- struct rhash_head *tmp;
- const struct bucket_table *tbl;
-
- tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash);
/*
* Just return a random station if localaddr is NULL
* ... first in list.
*/
- for_each_sta_info(local, tbl, addr, sta, tmp) {
+ for_each_sta_info(local, addr, sta, tmp) {
if (localaddr &&
!ether_addr_equal(sta->sdata->vif.addr, localaddr))
continue;
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 0556be3..d347ab5 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -452,7 +452,7 @@ struct sta_info {
/* General information, mostly static */
struct list_head list, free_list;
struct rcu_head rcu_head;
- struct rhash_head hash_node;
+ struct rhlist_head hash_node;
u8 addr[ETH_ALEN];
struct ieee80211_local *local;
struct ieee80211_sub_if_data *sdata;
@@ -635,6 +635,9 @@ rcu_dereference_protected_tid_tx(struct sta_info *sta, int tid)
*/
#define STA_INFO_CLEANUP_INTERVAL (10 * HZ)
+struct rhlist_head *sta_info_hash_lookup(struct ieee80211_local *local,
+ const u8 *addr);
+
/*
* Get a STA info, must be under RCU read lock.
*/
@@ -644,17 +647,9 @@ struct sta_info *sta_info_get(struct ieee80211_sub_if_data *sdata,
struct sta_info *sta_info_get_bss(struct ieee80211_sub_if_data *sdata,
const u8 *addr);
-u32 sta_addr_hash(const void *key, u32 length, u32 seed);
-
-#define _sta_bucket_idx(_tbl, _a) \
- rht_bucket_index(_tbl, sta_addr_hash(_a, ETH_ALEN, (_tbl)->hash_rnd))
-
-#define for_each_sta_info(local, tbl, _addr, _sta, _tmp) \
- rht_for_each_entry_rcu(_sta, _tmp, tbl, \
- _sta_bucket_idx(tbl, _addr), \
- hash_node) \
- /* compare address and run code only if it matches */ \
- if (ether_addr_equal(_sta->addr, (_addr)))
+#define for_each_sta_info(local, _addr, _sta, _tmp) \
+ rhl_for_each_entry_rcu(_sta, _tmp, \
+ sta_info_hash_lookup(local, _addr), hash_node)
/*
* Get STA info by index, BROKEN!
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index a2a6826..6361709 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -740,8 +740,8 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
__le16 fc;
struct ieee80211_supported_band *sband;
+ struct rhlist_head *tmp;
struct sta_info *sta;
- struct rhash_head *tmp;
int retry_count;
int rates_idx;
bool send_to_cooked;
@@ -749,7 +749,6 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
struct ieee80211_bar *bar;
int shift = 0;
int tid = IEEE80211_NUM_TIDS;
- const struct bucket_table *tbl;
rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count);
@@ -758,9 +757,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
sband = local->hw.wiphy->bands[info->band];
fc = hdr->frame_control;
- tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash);
^ permalink raw reply related
* [PATCH 1/2] rhashtable: Add rhlist interface
From: Herbert Xu @ 2016-09-18 13:53 UTC (permalink / raw)
To: Johannes Berg, David S. Miller, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-wireless-u79uwXL29TY76Z2rM5mHXA, Thomas Graf,
tom-BjP2VixgY4xUbtYUoyoikg, Ben Greear
In-Reply-To: <20160918135030.GA7062@gondor.apana.org.au>
The insecure_elasticity setting is an ugly wart brought out by
users who need to insert duplicate objects (that is, distinct
objects with identical keys) into the same table.
In fact, those users have a much bigger problem. Once those
duplicate objects are inserted, they don't have an interface to
find them (unless you count the walker interface which walks
over the entire table).
Some users have resorted to doing a manual walk over the hash
table which is of course broken because they don't handle the
potential existence of multiple hash tables. The result is that
they will break sporadically when they encounter a hash table
resize/rehash.
This patch provides a way out for those users, at the expense
of an extra pointer per object. Essentially each object is now
a list of objects carrying the same key. The hash table will
only see the lists so nothing changes as far as rhashtable is
concerned.
To use this new interface, you need to insert a struct rhlist_head
into your objects instead of struct rhash_head. While the hash
table is unchanged, for type-safety you'll need to use struct
rhltable instead of struct rhashtable. All the existing interfaces
have been duplicated for rhlist, including the hash table walker.
One missing feature is nulls marking because AFAIK the only potential
user of it does not need duplicate objects. Should anyone need
this it shouldn't be too hard to add.
Signed-off-by: Herbert Xu <herbert-lOAM2aK0SrRLBo1qDEOMRrpzq4S04n8Q@public.gmane.org>
---
include/linux/rhashtable.h | 490 ++++++++++++++++++++++++++++++++++-----------
lib/rhashtable.c | 231 ++++++++++++++++-----
2 files changed, 560 insertions(+), 161 deletions(-)
diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index fd82584..dc7bea6 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -1,7 +1,7 @@
/*
* Resizable, Scalable, Concurrent Hash Table
*
- * Copyright (c) 2015 Herbert Xu <herbert-lOAM2aK0SrRLBo1qDEOMRrpzq4S04n8Q@public.gmane.org>
+ * Copyright (c) 2015-2016 Herbert Xu <herbert-lOAM2aK0SrRLBo1qDEOMRrpzq4S04n8Q@public.gmane.org>
* Copyright (c) 2014-2015 Thomas Graf <tgraf-G/eBtMaohhA@public.gmane.org>
* Copyright (c) 2008-2014 Patrick McHardy <kaber-dcUjhNyLwpNeoWH0uzbU5w@public.gmane.org>
*
@@ -53,6 +53,11 @@ struct rhash_head {
struct rhash_head __rcu *next;
};
+struct rhlist_head {
+ struct rhash_head rhead;
+ struct rhlist_head __rcu *next;
+};
+
/**
* struct bucket_table - Table of hash buckets
* @size: Number of hash buckets
@@ -137,6 +142,7 @@ struct rhashtable_params {
* @key_len: Key length for hashfn
* @elasticity: Maximum chain length before rehash
* @p: Configuration parameters
+ * @rhlist: True if this is an rhltable
* @run_work: Deferred worker to expand/shrink asynchronously
* @mutex: Mutex to protect current/future table swapping
* @lock: Spin lock to protect walker list
@@ -147,12 +153,21 @@ struct rhashtable {
unsigned int key_len;
unsigned int elasticity;
struct rhashtable_params p;
+ bool rhlist;
struct work_struct run_work;
struct mutex mutex;
spinlock_t lock;
};
/**
+ * struct rhltable - Hash table with duplicate objects in a list
+ * @ht: Underlying rhtable
+ */
+struct rhltable {
+ struct rhashtable ht;
+};
+
+/**
* struct rhashtable_walker - Hash table walker
* @list: List entry on list of walkers
* @tbl: The table that we were walking over
@@ -163,9 +178,10 @@ struct rhashtable_walker {
};
/**
- * struct rhashtable_iter - Hash table iterator, fits into netlink cb
+ * struct rhashtable_iter - Hash table iterator
* @ht: Table to iterate through
* @p: Current pointer
+ * @list: Current hash list pointer
* @walker: Associated rhashtable walker
* @slot: Current slot
* @skip: Number of entries to skip in slot
@@ -173,6 +189,7 @@ struct rhashtable_walker {
struct rhashtable_iter {
struct rhashtable *ht;
struct rhash_head *p;
+ struct rhlist_head *list;
struct rhashtable_walker walker;
unsigned int slot;
unsigned int skip;
@@ -339,13 +356,11 @@ static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl,
int rhashtable_init(struct rhashtable *ht,
const struct rhashtable_params *params);
+int rhltable_init(struct rhltable *hlt,
+ const struct rhashtable_params *params);
-struct bucket_table *rhashtable_insert_slow(struct rhashtable *ht,
- const void *key,
- struct rhash_head *obj,
- struct bucket_table *old_tbl,
- void **data);
-int rhashtable_insert_rehash(struct rhashtable *ht, struct bucket_table *tbl);
+void *rhashtable_insert_slow(struct rhashtable *ht, const void *key,
+ struct rhash_head *obj);
void rhashtable_walk_enter(struct rhashtable *ht,
struct rhashtable_iter *iter);
@@ -507,6 +522,31 @@ void rhashtable_destroy(struct rhashtable *ht);
rht_for_each_entry_rcu_continue(tpos, pos, (tbl)->buckets[hash],\
tbl, hash, member)
+/**
+ * rhl_for_each_rcu - iterate over rcu hash table list
+ * @pos: the &struct rlist_head to use as a loop cursor.
+ * @list: the head of the list
+ *
+ * This hash chain list-traversal primitive should be used on the
+ * list returned by rhltable_lookup.
+ */
+#define rhl_for_each_rcu(pos, list) \
+ for (pos = list; pos; pos = rcu_dereference_raw(pos->next))
+
+/**
+ * rhl_for_each_entry_rcu - iterate over rcu hash table list of given type
+ * @tpos: the type * to use as a loop cursor.
+ * @pos: the &struct rlist_head to use as a loop cursor.
+ * @list: the head of the list
+ * @member: name of the &struct rlist_head within the hashable struct.
+ *
+ * This hash chain list-traversal primitive should be used on the
+ * list returned by rhltable_lookup.
+ */
+#define rhl_for_each_entry_rcu(tpos, pos, list, member) \
+ for (pos = list; pos && rht_entry(tpos, pos, member); \
+ pos = rcu_dereference_raw(pos->next))
+
static inline int rhashtable_compare(struct rhashtable_compare_arg *arg,
const void *obj)
{
@@ -516,18 +556,8 @@ static inline int rhashtable_compare(struct rhashtable_compare_arg *arg,
return memcmp(ptr + ht->p.key_offset, arg->key, ht->p.key_len);
}
-/**
- * rhashtable_lookup_fast - search hash table, inlined version
- * @ht: hash table
- * @key: the pointer to the key
- * @params: hash table parameters
- *
- * Computes the hash value for the key and traverses the bucket chain looking
- * for a entry with an identical key. The first matching entry is returned.
- *
- * Returns the first entry on which the compare function returned true.
- */
-static inline void *rhashtable_lookup_fast(
+/* Internal function, do not use. */
+static inline struct rhash_head *__rhashtable_lookup(
struct rhashtable *ht, const void *key,
const struct rhashtable_params params)
{
@@ -539,8 +569,6 @@ static inline void *rhashtable_lookup_fast(
struct rhash_head *he;
unsigned int hash;
- rcu_read_lock();
-
tbl = rht_dereference_rcu(ht->tbl, ht);
restart:
hash = rht_key_hashfn(ht, tbl, key, params);
@@ -549,8 +577,7 @@ restart:
params.obj_cmpfn(&arg, rht_obj(ht, he)) :
rhashtable_compare(&arg, rht_obj(ht, he)))
continue;
- rcu_read_unlock();
- return rht_obj(ht, he);
+ return he;
}
/* Ensure we see any new tables. */
@@ -559,96 +586,165 @@ restart:
tbl = rht_dereference_rcu(tbl->future_tbl, ht);
if (unlikely(tbl))
goto restart;
- rcu_read_unlock();
return NULL;
}
+/**
+ * rhashtable_lookup - search hash table
+ * @ht: hash table
+ * @key: the pointer to the key
+ * @params: hash table parameters
+ *
+ * Computes the hash value for the key and traverses the bucket chain looking
+ * for a entry with an identical key. The first matching entry is returned.
+ *
+ * This must only be called under the RCU read lock.
+ *
+ * Returns the first entry on which the compare function returned true.
+ */
+static inline void *rhashtable_lookup(
+ struct rhashtable *ht, const void *key,
+ const struct rhashtable_params params)
+{
+ struct rhash_head *he = __rhashtable_lookup(ht, key, params);
+
+ return he ? rht_obj(ht, he) : NULL;
+}
+
+/**
+ * rhashtable_lookup_fast - search hash table, without RCU read lock
+ * @ht: hash table
+ * @key: the pointer to the key
+ * @params: hash table parameters
+ *
+ * Computes the hash value for the key and traverses the bucket chain looking
+ * for a entry with an identical key. The first matching entry is returned.
+ *
+ * Only use this function when you have other mechanisms guaranteeing
+ * that the object won't go away after the RCU read lock is released.
+ *
+ * Returns the first entry on which the compare function returned true.
+ */
+static inline void *rhashtable_lookup_fast(
+ struct rhashtable *ht, const void *key,
+ const struct rhashtable_params params)
+{
+ void *obj;
+
+ rcu_read_lock();
+ obj = rhashtable_lookup(ht, key, params);
+ rcu_read_unlock();
+
+ return obj;
+}
+
+/**
+ * rhltable_lookup - search hash list table
+ * @hlt: hash table
+ * @key: the pointer to the key
+ * @params: hash table parameters
+ *
+ * Computes the hash value for the key and traverses the bucket chain looking
+ * for a entry with an identical key. All matching entries are returned
+ * in a list.
+ *
+ * This must only be called under the RCU read lock.
+ *
+ * Returns the list of entries that match the given key.
+ */
+static inline struct rhlist_head *rhltable_lookup(
+ struct rhltable *hlt, const void *key,
+ const struct rhashtable_params params)
+{
+ struct rhash_head *he = __rhashtable_lookup(&hlt->ht, key, params);
+
+ return he ? container_of(he, struct rhlist_head, rhead) : NULL;
+}
+
/* Internal function, please use rhashtable_insert_fast() instead. This
* function returns the existing element already in hashes in there is a clash,
* otherwise it returns an error via ERR_PTR().
*/
static inline void *__rhashtable_insert_fast(
struct rhashtable *ht, const void *key, struct rhash_head *obj,
- const struct rhashtable_params params)
+ const struct rhashtable_params params, bool rhlist)
{
struct rhashtable_compare_arg arg = {
.ht = ht,
.key = key,
};
- struct bucket_table *tbl, *new_tbl;
+ struct rhash_head __rcu **pprev;
+ struct bucket_table *tbl;
struct rhash_head *head;
spinlock_t *lock;
- unsigned int elasticity;
unsigned int hash;
- void *data = NULL;
- int err;
+ int elasticity;
+ void *data;
-restart:
rcu_read_lock();
tbl = rht_dereference_rcu(ht->tbl, ht);
+ hash = rht_head_hashfn(ht, tbl, obj, params);
+ lock = rht_bucket_lock(tbl, hash);
+ spin_lock_bh(lock);
- /* All insertions must grab the oldest table containing
- * the hashed bucket that is yet to be rehashed.
- */
- for (;;) {
- hash = rht_head_hashfn(ht, tbl, obj, params);
- lock = rht_bucket_lock(tbl, hash);
- spin_lock_bh(lock);
-
- if (tbl->rehash <= hash)
- break;
-
+ if (unlikely(rht_dereference_bucket(tbl->future_tbl, tbl, hash))) {
+slow_path:
spin_unlock_bh(lock);
- tbl = rht_dereference_rcu(tbl->future_tbl, ht);
+ rcu_read_unlock();
+ return rhashtable_insert_slow(ht, key, obj);
}
- new_tbl = rht_dereference_rcu(tbl->future_tbl, ht);
- if (unlikely(new_tbl)) {
- tbl = rhashtable_insert_slow(ht, key, obj, new_tbl, &data);
- if (!IS_ERR_OR_NULL(tbl))
- goto slow_path;
+ elasticity = ht->elasticity;
+ pprev = &tbl->buckets[hash];
+ rht_for_each(head, tbl, hash) {
+ struct rhlist_head *plist;
+ struct rhlist_head *list;
+
+ elasticity--;
+ if (!key ||
+ (params.obj_cmpfn ?
+ params.obj_cmpfn(&arg, rht_obj(ht, head)) :
+ rhashtable_compare(&arg, rht_obj(ht, head))))
+ continue;
+
+ data = rht_obj(ht, head);
- err = PTR_ERR(tbl);
- if (err == -EEXIST)
- err = 0;
+ if (!rhlist)
+ goto out;
- goto out;
- }
- err = -E2BIG;
- if (unlikely(rht_grow_above_max(ht, tbl)))
- goto out;
+ list = container_of(obj, struct rhlist_head, rhead);
+ plist = container_of(head, struct rhlist_head, rhead);
- if (unlikely(rht_grow_above_100(ht, tbl))) {
-slow_path:
- spin_unlock_bh(lock);
- err = rhashtable_insert_rehash(ht, tbl);
- rcu_read_unlock();
- if (err)
- return ERR_PTR(err);
+ RCU_INIT_POINTER(list->next, plist);
+ head = rht_dereference_bucket(head->next, tbl, hash);
+ RCU_INIT_POINTER(list->rhead.next, head);
+ rcu_assign_pointer(*pprev, obj);
- goto restart;
+ goto good;
}
- err = 0;
- elasticity = ht->elasticity;
- rht_for_each(head, tbl, hash) {
- if (key &&
- unlikely(!(params.obj_cmpfn ?
- params.obj_cmpfn(&arg, rht_obj(ht, head)) :
- rhashtable_compare(&arg, rht_obj(ht, head))))) {
- data = rht_obj(ht, head);
- goto out;
- }
- if (!--elasticity)
- goto slow_path;
- }
+ if (elasticity <= 0)
+ goto slow_path;
+
+ data = ERR_PTR(-E2BIG);
+ if (unlikely(rht_grow_above_max(ht, tbl)))
+ goto out;
+
+ if (unlikely(rht_grow_above_100(ht, tbl)))
+ goto slow_path;
head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash);
RCU_INIT_POINTER(obj->next, head);
+ if (rhlist) {
+ struct rhlist_head *list;
+
+ list = container_of(obj, struct rhlist_head, rhead);
+ RCU_INIT_POINTER(list->next, NULL);
+ }
rcu_assign_pointer(tbl->buckets[hash], obj);
@@ -656,11 +752,14 @@ slow_path:
if (rht_grow_above_75(ht, tbl))
schedule_work(&ht->run_work);
+good:
+ data = NULL;
+
out:
spin_unlock_bh(lock);
rcu_read_unlock();
- return err ? ERR_PTR(err) : data;
+ return data;
}
/**
@@ -685,7 +784,7 @@ static inline int rhashtable_insert_fast(
{
void *ret;
- ret = __rhashtable_insert_fast(ht, NULL, obj, params);
+ ret = __rhashtable_insert_fast(ht, NULL, obj, params, false);
if (IS_ERR(ret))
return PTR_ERR(ret);
@@ -693,6 +792,58 @@ static inline int rhashtable_insert_fast(
}
/**
+ * rhltable_insert_key - insert object into hash list table
+ * @hlt: hash list table
+ * @key: the pointer to the key
+ * @list: pointer to hash list head inside object
+ * @params: hash table parameters
+ *
+ * Will take a per bucket spinlock to protect against mutual mutations
+ * on the same bucket. Multiple insertions may occur in parallel unless
+ * they map to the same bucket lock.
+ *
+ * It is safe to call this function from atomic context.
+ *
+ * Will trigger an automatic deferred table resizing if the size grows
+ * beyond the watermark indicated by grow_decision() which can be passed
+ * to rhashtable_init().
+ */
+static inline int rhltable_insert_key(
+ struct rhltable *hlt, const void *key, struct rhlist_head *list,
+ const struct rhashtable_params params)
+{
+ return PTR_ERR(__rhashtable_insert_fast(&hlt->ht, key, &list->rhead,
+ params, true));
+}
+
+/**
+ * rhltable_insert - insert object into hash list table
+ * @hlt: hash list table
+ * @list: pointer to hash list head inside object
+ * @params: hash table parameters
+ *
+ * Will take a per bucket spinlock to protect against mutual mutations
+ * on the same bucket. Multiple insertions may occur in parallel unless
+ * they map to the same bucket lock.
+ *
+ * It is safe to call this function from atomic context.
+ *
+ * Will trigger an automatic deferred table resizing if the size grows
+ * beyond the watermark indicated by grow_decision() which can be passed
+ * to rhashtable_init().
+ */
+static inline int rhltable_insert(
+ struct rhltable *hlt, struct rhlist_head *list,
+ const struct rhashtable_params params)
+{
+ const char *key = rht_obj(&hlt->ht, &list->rhead);
+
+ key += params.key_offset;
+
+ return rhltable_insert_key(hlt, key, list, params);
+}
+
+/**
* rhashtable_lookup_insert_fast - lookup and insert object into hash table
* @ht: hash table
* @obj: pointer to hash head inside object
@@ -722,7 +873,8 @@ static inline int rhashtable_lookup_insert_fast(
BUG_ON(ht->p.obj_hashfn);
- ret = __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, params);
+ ret = __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, params,
+ false);
if (IS_ERR(ret))
return PTR_ERR(ret);
@@ -759,7 +911,7 @@ static inline int rhashtable_lookup_insert_key(
BUG_ON(!ht->p.obj_hashfn || !key);
- ret = __rhashtable_insert_fast(ht, key, obj, params);
+ ret = __rhashtable_insert_fast(ht, key, obj, params, false);
if (IS_ERR(ret))
return PTR_ERR(ret);
@@ -783,13 +935,14 @@ static inline void *rhashtable_lookup_get_insert_key(
{
BUG_ON(!ht->p.obj_hashfn || !key);
- return __rhashtable_insert_fast(ht, key, obj, params);
+ return __rhashtable_insert_fast(ht, key, obj, params, false);
}
/* Internal function, please use rhashtable_remove_fast() instead */
-static inline int __rhashtable_remove_fast(
+static inline int __rhashtable_remove_fast_one(
struct rhashtable *ht, struct bucket_table *tbl,
- struct rhash_head *obj, const struct rhashtable_params params)
+ struct rhash_head *obj, const struct rhashtable_params params,
+ bool rhlist)
{
struct rhash_head __rcu **pprev;
struct rhash_head *he;
@@ -804,39 +957,65 @@ static inline int __rhashtable_remove_fast(
pprev = &tbl->buckets[hash];
rht_for_each(he, tbl, hash) {
+ struct rhlist_head *list;
+
+ list = container_of(he, struct rhlist_head, rhead);
+
if (he != obj) {
+ struct rhlist_head __rcu **lpprev;
+
pprev = &he->next;
- continue;
+
+ if (!rhlist)
+ continue;
+
+ do {
+ lpprev = &list->next;
+ list = rht_dereference_bucket(list->next,
+ tbl, hash);
+ } while (list && obj != &list->rhead);
+
+ if (!list)
+ continue;
+
+ list = rht_dereference_bucket(list->next, tbl, hash);
+ RCU_INIT_POINTER(*lpprev, list);
+ err = 0;
+ break;
}
- rcu_assign_pointer(*pprev, obj->next);
- err = 0;
+ obj = rht_dereference_bucket(obj->next, tbl, hash);
+
+ if (rhlist) {
+ list = rht_dereference_bucket(list->next, tbl, hash);
+ if (list) {
+ RCU_INIT_POINTER(list->rhead.next, obj);
+ obj = &list->rhead;
+ }
+ }
+
+ rcu_assign_pointer(*pprev, obj);
+ err = 1;
break;
}
spin_unlock_bh(lock);
+ if (err > 0) {
+ atomic_dec(&ht->nelems);
+ if (unlikely(ht->p.automatic_shrinking &&
+ rht_shrink_below_30(ht, tbl)))
+ schedule_work(&ht->run_work);
+ err = 0;
+ }
+
return err;
}
-/**
- * rhashtable_remove_fast - remove object from hash table
- * @ht: hash table
- * @obj: pointer to hash head inside object
- * @params: hash table parameters
- *
- * Since the hash chain is single linked, the removal operation needs to
- * walk the bucket chain upon removal. The removal operation is thus
- * considerable slow if the hash table is not correctly sized.
- *
- * Will automatically shrink the table via rhashtable_expand() if the
- * shrink_decision function specified at rhashtable_init() returns true.
- *
- * Returns zero on success, -ENOENT if the entry could not be found.
- */
-static inline int rhashtable_remove_fast(
+/* Internal function, please use rhashtable_remove_fast() instead */
+static inline int __rhashtable_remove_fast(
struct rhashtable *ht, struct rhash_head *obj,
- const struct rhashtable_params params)
+ const struct rhashtable_params params, bool rhlist)
{
struct bucket_table *tbl;
int err;
@@ -850,24 +1029,60 @@ static inline int rhashtable_remove_fast(
* visible then that guarantees the entry to still be in
* the old tbl if it exists.
*/
- while ((err = __rhashtable_remove_fast(ht, tbl, obj, params)) &&
+ while ((err = __rhashtable_remove_fast_one(ht, tbl, obj, params,
+ rhlist)) &&
(tbl = rht_dereference_rcu(tbl->future_tbl, ht)))
;
- if (err)
- goto out;
-
- atomic_dec(&ht->nelems);
- if (unlikely(ht->p.automatic_shrinking &&
- rht_shrink_below_30(ht, tbl)))
- schedule_work(&ht->run_work);
-
-out:
rcu_read_unlock();
return err;
}
+/**
+ * rhashtable_remove_fast - remove object from hash table
+ * @ht: hash table
+ * @obj: pointer to hash head inside object
+ * @params: hash table parameters
+ *
+ * Since the hash chain is single linked, the removal operation needs to
+ * walk the bucket chain upon removal. The removal operation is thus
+ * considerable slow if the hash table is not correctly sized.
+ *
+ * Will automatically shrink the table via rhashtable_expand() if the
+ * shrink_decision function specified at rhashtable_init() returns true.
+ *
+ * Returns zero on success, -ENOENT if the entry could not be found.
+ */
+static inline int rhashtable_remove_fast(
+ struct rhashtable *ht, struct rhash_head *obj,
+ const struct rhashtable_params params)
+{
+ return __rhashtable_remove_fast(ht, obj, params, false);
+}
+
+/**
+ * rhltable_remove - remove object from hash list table
+ * @hlt: hash list table
+ * @list: pointer to hash list head inside object
+ * @params: hash table parameters
+ *
+ * Since the hash chain is single linked, the removal operation needs to
+ * walk the bucket chain upon removal. The removal operation is thus
+ * considerable slow if the hash table is not correctly sized.
+ *
+ * Will automatically shrink the table via rhashtable_expand() if the
+ * shrink_decision function specified at rhashtable_init() returns true.
+ *
+ * Returns zero on success, -ENOENT if the entry could not be found.
+ */
+static inline int rhltable_remove(
+ struct rhltable *hlt, struct rhlist_head *list,
+ const struct rhashtable_params params)
+{
+ return __rhashtable_remove_fast(&hlt->ht, &list->rhead, params, true);
+}
+
/* Internal function, please use rhashtable_replace_fast() instead */
static inline int __rhashtable_replace_fast(
struct rhashtable *ht, struct bucket_table *tbl,
@@ -958,4 +1173,51 @@ static inline int rhashtable_walk_init(struct rhashtable *ht,
return 0;
}
+/**
+ * rhltable_walk_enter - Initialise an iterator
+ * @hlt: Table to walk over
+ * @iter: Hash table Iterator
+ *
+ * This function prepares a hash table walk.
+ *
+ * Note that if you restart a walk after rhashtable_walk_stop you
+ * may see the same object twice. Also, you may miss objects if
+ * there are removals in between rhashtable_walk_stop and the next
+ * call to rhashtable_walk_start.
+ *
+ * For a completely stable walk you should construct your own data
+ * structure outside the hash table.
+ *
+ * This function may sleep so you must not call it from interrupt
+ * context or with spin locks held.
+ *
+ * You must call rhashtable_walk_exit after this function returns.
+ */
+static inline void rhltable_walk_enter(struct rhltable *hlt,
+ struct rhashtable_iter *iter)
+{
+ return rhashtable_walk_enter(&hlt->ht, iter);
+}
+
+/**
+ * rhltable_free_and_destroy - free elements and destroy hash list table
+ * @hlt: the hash list table to destroy
+ * @free_fn: callback to release resources of element
+ * @arg: pointer passed to free_fn
+ *
+ * See documentation for rhashtable_free_and_destroy.
+ */
+static inline void rhltable_free_and_destroy(struct rhltable *hlt,
+ void (*free_fn)(void *ptr,
+ void *arg),
+ void *arg)
+{
+ return rhashtable_free_and_destroy(&hlt->ht, free_fn, arg);
+}
+
+static inline void rhltable_destroy(struct rhltable *hlt)
+{
+ return rhltable_free_and_destroy(hlt, NULL, NULL);
+}
+
#endif /* _LINUX_RHASHTABLE_H */
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 06c2872..185fc14 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -378,22 +378,8 @@ static void rht_deferred_worker(struct work_struct *work)
schedule_work(&ht->run_work);
}
-static bool rhashtable_check_elasticity(struct rhashtable *ht,
- struct bucket_table *tbl,
- unsigned int hash)
-{
- unsigned int elasticity = ht->elasticity;
- struct rhash_head *head;
-
- rht_for_each(head, tbl, hash)
- if (!--elasticity)
- return true;
-
- return false;
-}
-
-int rhashtable_insert_rehash(struct rhashtable *ht,
- struct bucket_table *tbl)
+static int rhashtable_insert_rehash(struct rhashtable *ht,
+ struct bucket_table *tbl)
{
struct bucket_table *old_tbl;
struct bucket_table *new_tbl;
@@ -439,57 +425,148 @@ fail:
return err;
}
-EXPORT_SYMBOL_GPL(rhashtable_insert_rehash);
-struct bucket_table *rhashtable_insert_slow(struct rhashtable *ht,
- const void *key,
- struct rhash_head *obj,
- struct bucket_table *tbl,
- void **data)
+static void *rhashtable_insert_one(struct rhashtable *ht,
+ struct bucket_table *tbl, unsigned int hash,
+ const void *key, struct rhash_head *obj)
{
+ struct rhashtable_compare_arg arg = {
+ .ht = ht,
+ .key = key,
+ };
+ struct rhash_head __rcu **pprev;
+ struct rhash_head *head;
+ int elasticity;
+
+ elasticity = ht->elasticity;
+ pprev = &tbl->buckets[hash];
+ rht_for_each(head, tbl, hash) {
+ struct rhlist_head *list;
+ struct rhlist_head *plist;
+
+ elasticity--;
+ if (!key ||
+ (ht->p.obj_cmpfn ?
+ ht->p.obj_cmpfn(&arg, rht_obj(ht, head)) :
+ rhashtable_compare(&arg, rht_obj(ht, head))))
+ continue;
+
+ if (!ht->rhlist)
+ return rht_obj(ht, head);
+
+ list = container_of(obj, struct rhlist_head, rhead);
+ plist = container_of(head, struct rhlist_head, rhead);
+
+ RCU_INIT_POINTER(list->next, plist);
+ head = rht_dereference_bucket(head->next, tbl, hash);
+ RCU_INIT_POINTER(list->rhead.next, head);
+ rcu_assign_pointer(*pprev, obj);
+
+ return NULL;
+ }
+
+ if (elasticity <= 0)
+ return ERR_PTR(-EAGAIN);
+
+ return ERR_PTR(-ENOENT);
+}
+
+static void *rhashtable_try_insert(struct rhashtable *ht, const void *key,
+ struct rhash_head *obj)
+{
+ struct bucket_table *tbl;
struct rhash_head *head;
unsigned int hash;
- int err;
+ spinlock_t *lock;
+ void *data;
- tbl = rhashtable_last_table(ht, tbl);
- hash = head_hashfn(ht, tbl, obj);
- spin_lock_nested(rht_bucket_lock(tbl, hash), SINGLE_DEPTH_NESTING);
-
- err = -EEXIST;
- if (key) {
- *data = rhashtable_lookup_fast(ht, key, ht->p);
- if (*data)
- goto exit;
+ tbl = rht_dereference_rcu(ht->tbl, ht);
+
+ /* All insertions must grab the oldest table containing
+ * the hashed bucket that is yet to be rehashed.
+ */
+ for (;;) {
+ hash = rht_head_hashfn(ht, tbl, obj, ht->p);
+ lock = rht_bucket_lock(tbl, hash);
+ spin_lock_bh(lock);
+
+ if (tbl->rehash <= hash)
+ break;
+
+ spin_unlock_bh(lock);
+ tbl = rht_dereference_rcu(tbl->future_tbl, ht);
+ }
+
+ data = rhashtable_insert_one(ht, tbl, hash, key, obj);
+
+ while (PTR_ERR(data) == -ENOENT || PTR_ERR(data) == -EAGAIN) {
+ struct bucket_table *new_tbl;
+
+ new_tbl = rht_dereference_rcu(tbl->future_tbl, ht);
+ if (!new_tbl)
+ break;
+
+ tbl = new_tbl;
+ hash = rht_head_hashfn(ht, tbl, obj, ht->p);
+ spin_lock_nested(rht_bucket_lock(tbl, hash),
+ SINGLE_DEPTH_NESTING);
+
+ data = rhashtable_insert_one(ht, tbl, hash, key, obj);
+
+ spin_unlock(rht_bucket_lock(tbl, hash));
}
- err = -E2BIG;
+ if (PTR_ERR(data) != -ENOENT)
+ goto exit;
+
+ data = ERR_PTR(-E2BIG);
if (unlikely(rht_grow_above_max(ht, tbl)))
goto exit;
- err = -EAGAIN;
- if (rhashtable_check_elasticity(ht, tbl, hash) ||
- rht_grow_above_100(ht, tbl))
+ data = ERR_PTR(-EAGAIN);
+ if (unlikely(rht_grow_above_100(ht, tbl)))
goto exit;
- err = 0;
+ data = NULL;
head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash);
RCU_INIT_POINTER(obj->next, head);
+ if (ht->rhlist) {
+ struct rhlist_head *list;
+
+ list = container_of(obj, struct rhlist_head, rhead);
+ RCU_INIT_POINTER(list->next, NULL);
+ }
rcu_assign_pointer(tbl->buckets[hash], obj);
atomic_inc(&ht->nelems);
+ if (rht_grow_above_75(ht, tbl))
+ schedule_work(&ht->run_work);
exit:
- spin_unlock(rht_bucket_lock(tbl, hash));
+ spin_unlock_bh(lock);
- if (err == 0)
- return NULL;
- else if (err == -EAGAIN)
- return tbl;
- else
- return ERR_PTR(err);
+ if (PTR_ERR(data) == -EAGAIN)
+ data = ERR_PTR(rhashtable_insert_rehash(ht, tbl) ?:
+ -EAGAIN);
+
+ return data;
+}
+
+void *rhashtable_insert_slow(struct rhashtable *ht, const void *key,
+ struct rhash_head *obj)
+{
+ void *data;
+
+ do {
+ rcu_read_lock();
+ data = rhashtable_try_insert(ht, key, obj);
+ rcu_read_unlock();
+ } while (PTR_ERR(data) == -EAGAIN);
+
+ return data;
}
EXPORT_SYMBOL_GPL(rhashtable_insert_slow);
@@ -593,11 +670,16 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_start);
void *rhashtable_walk_next(struct rhashtable_iter *iter)
{
struct bucket_table *tbl = iter->walker.tbl;
+ struct rhlist_head *list = iter->list;
struct rhashtable *ht = iter->ht;
struct rhash_head *p = iter->p;
+ bool rhlist = ht->rhlist;
if (p) {
- p = rht_dereference_bucket_rcu(p->next, tbl, iter->slot);
+ if (!rhlist || !(list = rcu_dereference(list->next))) {
+ p = rcu_dereference(p->next);
+ list = container_of(p, struct rhlist_head, rhead);
+ }
goto next;
}
@@ -605,6 +687,18 @@ void *rhashtable_walk_next(struct rhashtable_iter *iter)
int skip = iter->skip;
rht_for_each_rcu(p, tbl, iter->slot) {
+ if (rhlist) {
+ list = container_of(p, struct rhlist_head,
+ rhead);
+ do {
+ if (!skip)
+ goto next;
+ skip--;
+ list = rcu_dereference(list->next);
+ } while (list);
+
+ continue;
+ }
if (!skip)
break;
skip--;
@@ -614,7 +708,8 @@ next:
if (!rht_is_a_nulls(p)) {
iter->skip++;
iter->p = p;
- return rht_obj(ht, p);
+ iter->list = list;
+ return rht_obj(ht, rhlist ? &list->rhead : p);
}
iter->skip = 0;
@@ -803,6 +898,48 @@ int rhashtable_init(struct rhashtable *ht,
EXPORT_SYMBOL_GPL(rhashtable_init);
/**
+ * rhltable_init - initialize a new hash list table
+ * @hlt: hash list table to be initialized
+ * @params: configuration parameters
+ *
+ * Initializes a new hash list table.
+ *
+ * See documentation for rhashtable_init.
+ */
+int rhltable_init(struct rhltable *hlt, const struct rhashtable_params *params)
+{
+ int err;
+
+ /* No rhlist NULLs marking for now. */
+ if (params->nulls_base)
+ return -EINVAL;
+
+ err = rhashtable_init(&hlt->ht, params);
+ hlt->ht.rhlist = true;
+ return err;
+}
+EXPORT_SYMBOL_GPL(rhltable_init);
+
+static void rhashtable_free_one(struct rhashtable *ht, struct rhash_head *obj,
+ void (*free_fn)(void *ptr, void *arg),
+ void *arg)
+{
+ struct rhlist_head *list;
+
+ if (!ht->rhlist) {
+ free_fn(rht_obj(ht, obj), arg);
+ return;
+ }
+
+ list = container_of(obj, struct rhlist_head, rhead);
+ do {
+ obj = &list->rhead;
+ list = rht_dereference(list->next, ht);
+ free_fn(rht_obj(ht, obj), arg);
+ } while (list);
+}
+
+/**
* rhashtable_free_and_destroy - free elements and destroy hash table
* @ht: the hash table to destroy
* @free_fn: callback to release resources of element
@@ -839,7 +976,7 @@ void rhashtable_free_and_destroy(struct rhashtable *ht,
pos = next,
next = !rht_is_a_nulls(pos) ?
rht_dereference(pos->next, ht) : NULL)
- free_fn(rht_obj(ht, pos), arg);
+ rhashtable_free_one(ht, pos, free_fn, arg);
}
}
^ permalink raw reply related
* [PATCH 0/2] rhashtable: rhashtable with duplicate objects
From: Herbert Xu @ 2016-09-18 13:50 UTC (permalink / raw)
To: Johannes Berg
Cc: David S. Miller, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-wireless-u79uwXL29TY76Z2rM5mHXA, Thomas Graf,
tom-BjP2VixgY4xUbtYUoyoikg
In-Reply-To: <1470394233.2977.37.camel-cdvu00un1VgdHxzADdlk8Q@public.gmane.org>
On Fri, Aug 05, 2016 at 12:50:33PM +0200, Johannes Berg wrote:
> > My plan is to build support for this directly into rhashtable.
> > So I'm adding a struct rhlist_head that would be used in place
> > of rhash_head for these cases and it'll carry an extra pointer
> > for the list of identical entries.
> >
> > I will then add an additional layer of insert/lookup interfaces
> > for rhlist_head.
>
> Oh, ok.
OK, it's finally ready now.
This series contains one two patches. The first adds the rhlist
interface and the second converts mac80211 to use it. If this works
out I'll then proceed to convert the other insecure_elasticity
users over to this.
I've tested the rhlist code with test_rhashtable but I haven't
tested the mac80211 conversion. So please give it a go and see
if it still works.
Thanks!
--
Email: Herbert Xu <herbert-lOAM2aK0SrRLBo1qDEOMRrpzq4S04n8Q@public.gmane.org>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply
* Re: [PATCH v2 net-next 2/2] net sched ife action: Introduce skb tcindex metadata encap decap
From: kbuild test robot @ 2016-09-18 13:45 UTC (permalink / raw)
To: Jamal Hadi Salim
Cc: kbuild-all, davem, netdev, xiyou.wangcong, Jamal Hadi Salim
In-Reply-To: <1474197676-10512-2-git-send-email-jhs@emojatatu.com>
[-- Attachment #1: Type: text/plain, Size: 743 bytes --]
Hi Jamal,
[auto build test ERROR on net-next/master]
url: https://github.com/0day-ci/linux/commits/Jamal-Hadi-Salim/net-sched-ife-action-add-16-bit-helpers/20160918-192521
config: i386-allmodconfig (attached as .config)
compiler: gcc-6 (Debian 6.2.0-3) 6.2.0 20160901
reproduce:
# save the attached .config to linux build tree
make ARCH=i386
All errors (new ones prefixed by >>):
>> make[3]: *** No rule to make target 'net/sched/act_meta_skbtcindex.c', needed by 'net/sched/act_meta_skbtcindex.o'.
make[3]: Target '__build' not remade because of errors.
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 55973 bytes --]
^ permalink raw reply
* [PATCH 1/1] ixgbe: replace defined with IS_ENABLED
From: zyjzyj2000 @ 2016-09-14 15:26 UTC (permalink / raw)
To: netdev, intel-wired-lan, jeffrey.t.kirsher, zyjzyj2000,
e1000-devel
From: Zhu Yanjun <zyjzyj2000@gmail.com>
Replace defined macro with IS_ENABLED in ixgbe.h file
Signed-off-by: Zhu Yanjun <zyjzyj2000@gmail.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 9475ff9..f8bc1d0 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -45,7 +45,7 @@
#include "ixgbe_type.h"
#include "ixgbe_common.h"
#include "ixgbe_dcb.h"
-#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+#if IS_ENABLED(CONFIG_FCOE)
#define IXGBE_FCOE
#include "ixgbe_fcoe.h"
#endif /* CONFIG_FCOE or CONFIG_FCOE_MODULE */
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 1/1] net sched: stylistic cleanups
From: Jamal Hadi Salim @ 2016-09-18 12:45 UTC (permalink / raw)
To: davem; +Cc: netdev, Jamal Hadi Salim
From: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
net/sched/act_api.c | 16 ++++++----------
net/sched/act_csum.c | 36 ++++++++++++++++++------------------
net/sched/act_gact.c | 3 ++-
net/sched/act_mirred.c | 3 ++-
net/sched/act_police.c | 10 ++++------
net/sched/cls_api.c | 18 ++++++++++--------
net/sched/cls_bpf.c | 6 ++++--
net/sched/cls_flow.c | 21 ++++++++++++++-------
net/sched/cls_flower.c | 3 ++-
net/sched/cls_fw.c | 10 +++++-----
net/sched/cls_route.c | 9 +++------
net/sched/cls_tcindex.c | 12 ++++++------
net/sched/cls_u32.c | 30 ++++++++++++------------------
net/sched/sch_api.c | 41 ++++++++++++++++++++++++++---------------
14 files changed, 114 insertions(+), 104 deletions(-)
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index d09d068..d0aceb1 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -592,9 +592,8 @@ err_out:
return ERR_PTR(err);
}
-int tcf_action_init(struct net *net, struct nlattr *nla,
- struct nlattr *est, char *name, int ovr,
- int bind, struct list_head *actions)
+int tcf_action_init(struct net *net, struct nlattr *nla, struct nlattr *est,
+ char *name, int ovr, int bind, struct list_head *actions)
{
struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
struct tc_action *act;
@@ -923,9 +922,8 @@ tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
return err;
}
-static int
-tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
- u32 portid, int ovr)
+static int tcf_action_add(struct net *net, struct nlattr *nla,
+ struct nlmsghdr *n, u32 portid, int ovr)
{
int ret = 0;
LIST_HEAD(actions);
@@ -988,8 +986,7 @@ replay:
return ret;
}
-static struct nlattr *
-find_dump_kind(const struct nlmsghdr *n)
+static struct nlattr *find_dump_kind(const struct nlmsghdr *n)
{
struct nlattr *tb1, *tb2[TCA_ACT_MAX + 1];
struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
@@ -1016,8 +1013,7 @@ find_dump_kind(const struct nlmsghdr *n)
return kind;
}
-static int
-tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb)
+static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
struct nlmsghdr *nlh;
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index b5dbf63..e0defce 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -116,8 +116,8 @@ static void *tcf_csum_skb_nextlayer(struct sk_buff *skb,
return (void *)(skb_network_header(skb) + ihl);
}
-static int tcf_csum_ipv4_icmp(struct sk_buff *skb,
- unsigned int ihl, unsigned int ipl)
+static int tcf_csum_ipv4_icmp(struct sk_buff *skb, unsigned int ihl,
+ unsigned int ipl)
{
struct icmphdr *icmph;
@@ -152,8 +152,8 @@ static int tcf_csum_ipv4_igmp(struct sk_buff *skb,
return 1;
}
-static int tcf_csum_ipv6_icmp(struct sk_buff *skb,
- unsigned int ihl, unsigned int ipl)
+static int tcf_csum_ipv6_icmp(struct sk_buff *skb, unsigned int ihl,
+ unsigned int ipl)
{
struct icmp6hdr *icmp6h;
const struct ipv6hdr *ip6h;
@@ -174,8 +174,8 @@ static int tcf_csum_ipv6_icmp(struct sk_buff *skb,
return 1;
}
-static int tcf_csum_ipv4_tcp(struct sk_buff *skb,
- unsigned int ihl, unsigned int ipl)
+static int tcf_csum_ipv4_tcp(struct sk_buff *skb, unsigned int ihl,
+ unsigned int ipl)
{
struct tcphdr *tcph;
const struct iphdr *iph;
@@ -195,8 +195,8 @@ static int tcf_csum_ipv4_tcp(struct sk_buff *skb,
return 1;
}
-static int tcf_csum_ipv6_tcp(struct sk_buff *skb,
- unsigned int ihl, unsigned int ipl)
+static int tcf_csum_ipv6_tcp(struct sk_buff *skb, unsigned int ihl,
+ unsigned int ipl)
{
struct tcphdr *tcph;
const struct ipv6hdr *ip6h;
@@ -217,8 +217,8 @@ static int tcf_csum_ipv6_tcp(struct sk_buff *skb,
return 1;
}
-static int tcf_csum_ipv4_udp(struct sk_buff *skb,
- unsigned int ihl, unsigned int ipl, int udplite)
+static int tcf_csum_ipv4_udp(struct sk_buff *skb, unsigned int ihl,
+ unsigned int ipl, int udplite)
{
struct udphdr *udph;
const struct iphdr *iph;
@@ -270,8 +270,8 @@ ignore_obscure_skb:
return 1;
}
-static int tcf_csum_ipv6_udp(struct sk_buff *skb,
- unsigned int ihl, unsigned int ipl, int udplite)
+static int tcf_csum_ipv6_udp(struct sk_buff *skb, unsigned int ihl,
+ unsigned int ipl, int udplite)
{
struct udphdr *udph;
const struct ipv6hdr *ip6h;
@@ -380,8 +380,8 @@ fail:
return 0;
}
-static int tcf_csum_ipv6_hopopts(struct ipv6_opt_hdr *ip6xh,
- unsigned int ixhl, unsigned int *pl)
+static int tcf_csum_ipv6_hopopts(struct ipv6_opt_hdr *ip6xh, unsigned int ixhl,
+ unsigned int *pl)
{
int off, len, optlen;
unsigned char *xh = (void *)ip6xh;
@@ -494,8 +494,8 @@ fail:
return 0;
}
-static int tcf_csum(struct sk_buff *skb,
- const struct tc_action *a, struct tcf_result *res)
+static int tcf_csum(struct sk_buff *skb, const struct tc_action *a,
+ struct tcf_result *res)
{
struct tcf_csum *p = to_tcf_csum(a);
int action;
@@ -531,8 +531,8 @@ drop:
return TC_ACT_SHOT;
}
-static int tcf_csum_dump(struct sk_buff *skb,
- struct tc_action *a, int bind, int ref)
+static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind,
+ int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_csum *p = to_tcf_csum(a);
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index e24a409..e0aa30f 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -156,7 +156,8 @@ static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets,
int action = READ_ONCE(gact->tcf_action);
struct tcf_t *tm = &gact->tcf_tm;
- _bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats), bytes, packets);
+ _bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats), bytes,
+ packets);
if (action == TC_ACT_SHOT)
this_cpu_ptr(gact->common.cpu_qstats)->drops += packets;
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 6038c85..1c76387 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -204,7 +204,8 @@ out:
return retval;
}
-static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
+static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind,
+ int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_mirred *m = to_mirred(a);
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index ba7074b..d1bd248 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -263,8 +263,8 @@ static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a,
return police->tcf_action;
}
-static int
-tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
+static int tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a,
+ int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_police *police = to_police(a);
@@ -349,14 +349,12 @@ static struct pernet_operations police_net_ops = {
.size = sizeof(struct tc_action_net),
};
-static int __init
-police_init_module(void)
+static int __init police_init_module(void)
{
return tcf_register_action(&act_police_ops, &police_net_ops);
}
-static void __exit
-police_cleanup_module(void)
+static void __exit police_cleanup_module(void)
{
tcf_unregister_action(&act_police_ops, &police_net_ops);
}
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index a7c5645..11da7da 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -344,13 +344,15 @@ replay:
if (err == 0) {
struct tcf_proto *next = rtnl_dereference(tp->next);
- tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER);
+ tfilter_notify(net, skb, n, tp, fh,
+ RTM_DELTFILTER);
if (tcf_destroy(tp, false))
RCU_INIT_POINTER(*back, next);
}
goto errout;
case RTM_GETTFILTER:
- err = tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER);
+ err = tfilter_notify(net, skb, n, tp, fh,
+ RTM_NEWTFILTER);
goto errout;
default:
err = -EINVAL;
@@ -448,7 +450,8 @@ static int tcf_node_dump(struct tcf_proto *tp, unsigned long n,
struct net *net = sock_net(a->skb->sk);
return tcf_fill_node(net, a->skb, tp, n, NETLINK_CB(a->cb->skb).portid,
- a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER);
+ a->cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ RTM_NEWTFILTER);
}
/* called with RTNL */
@@ -552,7 +555,7 @@ void tcf_exts_destroy(struct tcf_exts *exts)
EXPORT_SYMBOL(tcf_exts_destroy);
int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
- struct nlattr *rate_tlv, struct tcf_exts *exts, bool ovr)
+ struct nlattr *rate_tlv, struct tcf_exts *exts, bool ovr)
{
#ifdef CONFIG_NET_CLS_ACT
{
@@ -560,8 +563,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
if (exts->police && tb[exts->police]) {
act = tcf_action_init_1(net, tb[exts->police], rate_tlv,
- "police", ovr,
- TCA_ACT_BIND);
+ "police", ovr, TCA_ACT_BIND);
if (IS_ERR(act))
return PTR_ERR(act);
@@ -573,8 +575,8 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
int err, i = 0;
err = tcf_action_init(net, tb[exts->action], rate_tlv,
- NULL, ovr,
- TCA_ACT_BIND, &actions);
+ NULL, ovr, TCA_ACT_BIND,
+ &actions);
if (err)
return err;
list_for_each_entry(act, &actions, list)
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 1d92d4d..c6f7a47 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -55,7 +55,8 @@ static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = {
[TCA_BPF_CLASSID] = { .type = NLA_U32 },
[TCA_BPF_FLAGS] = { .type = NLA_U32 },
[TCA_BPF_FD] = { .type = NLA_U32 },
- [TCA_BPF_NAME] = { .type = NLA_NUL_STRING, .len = CLS_BPF_NAME_LEN },
+ [TCA_BPF_NAME] = { .type = NLA_NUL_STRING,
+ .len = CLS_BPF_NAME_LEN },
[TCA_BPF_OPS_LEN] = { .type = NLA_U16 },
[TCA_BPF_OPS] = { .type = NLA_BINARY,
.len = sizeof(struct sock_filter) * BPF_MAXINSNS },
@@ -409,7 +410,8 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
goto errout;
}
- ret = cls_bpf_modify_existing(net, tp, prog, base, tb, tca[TCA_RATE], ovr);
+ ret = cls_bpf_modify_existing(net, tp, prog, base, tb, tca[TCA_RATE],
+ ovr);
if (ret < 0)
goto errout;
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index a379bae..e396723 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -87,12 +87,14 @@ static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow)
return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb);
}
-static u32 flow_get_proto(const struct sk_buff *skb, const struct flow_keys *flow)
+static u32 flow_get_proto(const struct sk_buff *skb,
+ const struct flow_keys *flow)
{
return flow->basic.ip_proto;
}
-static u32 flow_get_proto_src(const struct sk_buff *skb, const struct flow_keys *flow)
+static u32 flow_get_proto_src(const struct sk_buff *skb,
+ const struct flow_keys *flow)
{
if (flow->ports.ports)
return ntohs(flow->ports.src);
@@ -100,7 +102,8 @@ static u32 flow_get_proto_src(const struct sk_buff *skb, const struct flow_keys
return addr_fold(skb->sk);
}
-static u32 flow_get_proto_dst(const struct sk_buff *skb, const struct flow_keys *flow)
+static u32 flow_get_proto_dst(const struct sk_buff *skb,
+ const struct flow_keys *flow)
{
if (flow->ports.ports)
return ntohs(flow->ports.dst);
@@ -149,7 +152,8 @@ static u32 flow_get_nfct(const struct sk_buff *skb)
})
#endif
-static u32 flow_get_nfct_src(const struct sk_buff *skb, const struct flow_keys *flow)
+static u32 flow_get_nfct_src(const struct sk_buff *skb,
+ const struct flow_keys *flow)
{
switch (tc_skb_protocol(skb)) {
case htons(ETH_P_IP):
@@ -161,7 +165,8 @@ fallback:
return flow_get_src(skb, flow);
}
-static u32 flow_get_nfct_dst(const struct sk_buff *skb, const struct flow_keys *flow)
+static u32 flow_get_nfct_dst(const struct sk_buff *skb,
+ const struct flow_keys *flow)
{
switch (tc_skb_protocol(skb)) {
case htons(ETH_P_IP):
@@ -173,14 +178,16 @@ fallback:
return flow_get_dst(skb, flow);
}
-static u32 flow_get_nfct_proto_src(const struct sk_buff *skb, const struct flow_keys *flow)
+static u32 flow_get_nfct_proto_src(const struct sk_buff *skb,
+ const struct flow_keys *flow)
{
return ntohs(CTTUPLE(skb, src.u.all));
fallback:
return flow_get_proto_src(skb, flow);
}
-static u32 flow_get_nfct_proto_dst(const struct sk_buff *skb, const struct flow_keys *flow)
+static u32 flow_get_nfct_proto_dst(const struct sk_buff *skb,
+ const struct flow_keys *flow)
{
return ntohs(CTTUPLE(skb, dst.u.all));
fallback:
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index a3f4c70..2af09c8 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -241,7 +241,8 @@ static int fl_hw_replace_filter(struct tcf_proto *tp,
tc.type = TC_SETUP_CLSFLOWER;
tc.cls_flower = &offload;
- err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc);
+ err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol,
+ &tc);
if (tc_skip_sw(flags))
return err;
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index cc0bda9..9dc63d5 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -57,7 +57,7 @@ static u32 fw_hash(u32 handle)
}
static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp,
- struct tcf_result *res)
+ struct tcf_result *res)
{
struct fw_head *head = rcu_dereference_bh(tp->root);
struct fw_filter *f;
@@ -188,7 +188,8 @@ static const struct nla_policy fw_policy[TCA_FW_MAX + 1] = {
static int
fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f,
- struct nlattr **tb, struct nlattr **tca, unsigned long base, bool ovr)
+ struct nlattr **tb, struct nlattr **tca, unsigned long base,
+ bool ovr)
{
struct fw_head *head = rtnl_dereference(tp->root);
struct tcf_exts e;
@@ -237,9 +238,8 @@ errout:
static int fw_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
- u32 handle,
- struct nlattr **tca,
- unsigned long *arg, bool ovr)
+ u32 handle, struct nlattr **tca, unsigned long *arg,
+ bool ovr)
{
struct fw_head *head = rtnl_dereference(tp->root);
struct fw_filter *f = (struct fw_filter *) *arg;
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index c91e65d..a4ce39b 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -268,8 +268,7 @@ static int route4_init(struct tcf_proto *tp)
return 0;
}
-static void
-route4_delete_filter(struct rcu_head *head)
+static void route4_delete_filter(struct rcu_head *head)
{
struct route4_filter *f = container_of(head, struct route4_filter, rcu);
@@ -474,10 +473,8 @@ errout:
}
static int route4_change(struct net *net, struct sk_buff *in_skb,
- struct tcf_proto *tp, unsigned long base,
- u32 handle,
- struct nlattr **tca,
- unsigned long *arg, bool ovr)
+ struct tcf_proto *tp, unsigned long base, u32 handle,
+ struct nlattr **tca, unsigned long *arg, bool ovr)
{
struct route4_head *head = rtnl_dereference(tp->root);
struct route4_filter __rcu **fp;
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index d950070..96144bd 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -50,14 +50,13 @@ struct tcindex_data {
struct rcu_head rcu;
};
-static inline int
-tcindex_filter_is_set(struct tcindex_filter_result *r)
+static inline int tcindex_filter_is_set(struct tcindex_filter_result *r)
{
return tcf_exts_is_predicative(&r->exts) || r->res.classid;
}
-static struct tcindex_filter_result *
-tcindex_lookup(struct tcindex_data *p, u16 key)
+static struct tcindex_filter_result *tcindex_lookup(struct tcindex_data *p,
+ u16 key)
{
if (p->perfect) {
struct tcindex_filter_result *f = p->perfect + key;
@@ -144,7 +143,8 @@ static void tcindex_destroy_rexts(struct rcu_head *head)
static void tcindex_destroy_fexts(struct rcu_head *head)
{
- struct tcindex_filter *f = container_of(head, struct tcindex_filter, rcu);
+ struct tcindex_filter *f = container_of(head, struct tcindex_filter,
+ rcu);
tcf_exts_destroy(&f->result.exts);
kfree(f);
@@ -550,7 +550,7 @@ static bool tcindex_destroy(struct tcf_proto *tp, bool force)
static int tcindex_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
- struct sk_buff *skb, struct tcmsg *t)
+ struct sk_buff *skb, struct tcmsg *t)
{
struct tcindex_data *p = rtnl_dereference(tp->root);
struct tcindex_filter_result *r = (struct tcindex_filter_result *) fh;
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index a29263a..ae83c3ae 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -104,7 +104,8 @@ static inline unsigned int u32_hash_fold(__be32 key,
return h;
}
-static int u32_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res)
+static int u32_classify(struct sk_buff *skb, const struct tcf_proto *tp,
+ struct tcf_result *res)
{
struct {
struct tc_u_knode *knode;
@@ -256,8 +257,7 @@ deadloop:
return -1;
}
-static struct tc_u_hnode *
-u32_lookup_ht(struct tc_u_common *tp_c, u32 handle)
+static struct tc_u_hnode *u32_lookup_ht(struct tc_u_common *tp_c, u32 handle)
{
struct tc_u_hnode *ht;
@@ -270,8 +270,7 @@ u32_lookup_ht(struct tc_u_common *tp_c, u32 handle)
return ht;
}
-static struct tc_u_knode *
-u32_lookup_key(struct tc_u_hnode *ht, u32 handle)
+static struct tc_u_knode *u32_lookup_key(struct tc_u_hnode *ht, u32 handle)
{
unsigned int sel;
struct tc_u_knode *n = NULL;
@@ -360,8 +359,7 @@ static int u32_init(struct tcf_proto *tp)
return 0;
}
-static int u32_destroy_key(struct tcf_proto *tp,
- struct tc_u_knode *n,
+static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n,
bool free_pf)
{
tcf_exts_destroy(&n->exts);
@@ -448,9 +446,8 @@ static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle)
}
}
-static int u32_replace_hw_hnode(struct tcf_proto *tp,
- struct tc_u_hnode *h,
- u32 flags)
+static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h,
+ u32 flags)
{
struct net_device *dev = tp->q->dev_queue->dev;
struct tc_cls_u32_offload u32_offload = {0};
@@ -496,9 +493,8 @@ static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h)
}
}
-static int u32_replace_hw_knode(struct tcf_proto *tp,
- struct tc_u_knode *n,
- u32 flags)
+static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n,
+ u32 flags)
{
struct net_device *dev = tp->q->dev_queue->dev;
struct tc_cls_u32_offload u32_offload = {0};
@@ -763,8 +759,7 @@ errout:
return err;
}
-static void u32_replace_knode(struct tcf_proto *tp,
- struct tc_u_common *tp_c,
+static void u32_replace_knode(struct tcf_proto *tp, struct tc_u_common *tp_c,
struct tc_u_knode *n)
{
struct tc_u_knode __rcu **ins;
@@ -845,8 +840,7 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp,
static int u32_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base, u32 handle,
- struct nlattr **tca,
- unsigned long *arg, bool ovr)
+ struct nlattr **tca, unsigned long *arg, bool ovr)
{
struct tc_u_common *tp_c = tp->data;
struct tc_u_hnode *ht;
@@ -1088,7 +1082,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg)
}
static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
- struct sk_buff *skb, struct tcmsg *t)
+ struct sk_buff *skb, struct tcmsg *t)
{
struct tc_u_knode *n = (struct tc_u_knode *)fh;
struct tc_u_hnode *ht_up, *ht_down;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index d677b34..206dc24 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -389,7 +389,8 @@ static __u8 __detect_linklayer(struct tc_ratespec *r, __u32 *rtab)
static struct qdisc_rate_table *qdisc_rtab_list;
-struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab)
+struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r,
+ struct nlattr *tab)
{
struct qdisc_rate_table *rtab;
@@ -541,7 +542,8 @@ nla_put_failure:
return -1;
}
-void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab)
+void __qdisc_calculate_pkt_len(struct sk_buff *skb,
+ const struct qdisc_size_table *stab)
{
int pkt_len, slot;
@@ -888,10 +890,10 @@ static struct lock_class_key qdisc_rx_lock;
Parameters are passed via opt.
*/
-static struct Qdisc *
-qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
- struct Qdisc *p, u32 parent, u32 handle,
- struct nlattr **tca, int *errp)
+static struct Qdisc *qdisc_create(struct net_device *dev,
+ struct netdev_queue *dev_queue,
+ struct Qdisc *p, u32 parent, u32 handle,
+ struct nlattr **tca, int *errp)
{
int err;
struct nlattr *kind = tca[TCA_KIND];
@@ -1073,7 +1075,8 @@ struct check_loop_arg {
int depth;
};
-static int check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w);
+static int check_loop_fn(struct Qdisc *q, unsigned long cl,
+ struct qdisc_walker *w);
static int check_loop(struct Qdisc *q, struct Qdisc *p, int depth)
{
@@ -1450,7 +1453,8 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb,
} else {
if (!tc_qdisc_dump_ignore(q) &&
tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0)
+ cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ RTM_NEWQDISC) <= 0)
goto done;
q_idx++;
}
@@ -1471,7 +1475,8 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb,
}
if (!tc_qdisc_dump_ignore(q) &&
tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0)
+ cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ RTM_NEWQDISC) <= 0)
goto done;
q_idx++;
}
@@ -1505,7 +1510,8 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb)
s_q_idx = 0;
q_idx = 0;
- if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx, true) < 0)
+ if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx,
+ true) < 0)
goto done;
dev_queue = dev_ingress_queue(dev);
@@ -1640,7 +1646,8 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n)
if (cops->delete)
err = cops->delete(q, cl);
if (err == 0)
- tclass_notify(net, skb, n, q, cl, RTM_DELTCLASS);
+ tclass_notify(net, skb, n, q, cl,
+ RTM_DELTCLASS);
goto out;
case RTM_GETTCLASS:
err = tclass_notify(net, skb, n, q, cl, RTM_NEWTCLASS);
@@ -1738,12 +1745,14 @@ struct qdisc_dump_args {
struct netlink_callback *cb;
};
-static int qdisc_class_dump(struct Qdisc *q, unsigned long cl, struct qdisc_walker *arg)
+static int qdisc_class_dump(struct Qdisc *q, unsigned long cl,
+ struct qdisc_walker *arg)
{
struct qdisc_dump_args *a = (struct qdisc_dump_args *)arg;
return tc_fill_tclass(a->skb, q, cl, NETLINK_CB(a->cb->skb).portid,
- a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTCLASS);
+ a->cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ RTM_NEWTCLASS);
}
static int tc_dump_tclass_qdisc(struct Qdisc *q, struct sk_buff *skb,
@@ -1976,10 +1985,12 @@ static int __init pktsched_init(void)
rtnl_register(PF_UNSPEC, RTM_NEWQDISC, tc_modify_qdisc, NULL, NULL);
rtnl_register(PF_UNSPEC, RTM_DELQDISC, tc_get_qdisc, NULL, NULL);
- rtnl_register(PF_UNSPEC, RTM_GETQDISC, tc_get_qdisc, tc_dump_qdisc, NULL);
+ rtnl_register(PF_UNSPEC, RTM_GETQDISC, tc_get_qdisc, tc_dump_qdisc,
+ NULL);
rtnl_register(PF_UNSPEC, RTM_NEWTCLASS, tc_ctl_tclass, NULL, NULL);
rtnl_register(PF_UNSPEC, RTM_DELTCLASS, tc_ctl_tclass, NULL, NULL);
- rtnl_register(PF_UNSPEC, RTM_GETTCLASS, tc_ctl_tclass, tc_dump_tclass, NULL);
+ rtnl_register(PF_UNSPEC, RTM_GETTCLASS, tc_ctl_tclass, tc_dump_tclass,
+ NULL);
return 0;
}
--
1.9.1
^ permalink raw reply related
* eBPF: how to check the flow table
From: Eric Leblond @ 2016-09-18 12:02 UTC (permalink / raw)
To: netdev; +Cc: Alexei Starovoitov, daniel
Hello,
I'm currently testing a code implementing AF_PACKET bypass for
Suricata. The idea is that Suricata is updating a hash table containing
a list of flows it does not want to see anymore.
I want to check flow timeout from the userspace, so my current
algorithm is doing:
while (bpf_get_next_key(mapfd, &key, &next_key) == 0) {
bpf_lookup_elem(mapfd, &next_key, &value);
FlowCallback(mapfd, &next_key, &value, data);
key = next_key;
}
In the FlowCallback, I check the timing in the flow entry and I remove
the key if the flow is timeout.
This is currently working well when there is only a few flows but on a
real system with log of insertion in the table, the loop is never
returning because we dequeue slower than we enqueue.
Is there a better algorithm or an other way to do it ?
BR,
--
Eric Leblond <eric@regit.org>
Blog: https://home.regit.org/
^ permalink raw reply
* Re: [PATCH] net: mvneta: mark symbols static where possible
From: Sergei Shtylyov @ 2016-09-18 12:05 UTC (permalink / raw)
To: Baoyou Xie, thomas.petazzoni; +Cc: netdev, linux-kernel, arnd, xie.baoyou
In-Reply-To: <1474190445-5887-1-git-send-email-baoyou.xie@linaro.org>
Hello.
On 9/18/2016 12:20 PM, Baoyou Xie wrote:
> We get 2 warnings when building kernel with W=1:
> drivers/net/ethernet/marvell/mvneta.c:639:27: warning: no previous prototype for 'mvneta_get_stats64' [-Wmissing-prototypes]
> drivers/net/ethernet/marvell/mvneta.c:3529:5: warning: no previous prototype for 'mvneta_ethtool_set_link_ksettings' [-Wmissing-prototypes]
>
> In fact, these functions are only used in the file in which they are
> declared and don't need a declaration, but can be made static.
> so this patch marks these functions with 'static'.
>
> Signed-off-by: Baoyou Xie <baoyou.xie@linaro.org>
> ---
> drivers/net/ethernet/marvell/mvneta.c | 10 ++++++----
> 1 file changed, 6 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
> index 32f0cc4..03be592 100644
> --- a/drivers/net/ethernet/marvell/mvneta.c
> +++ b/drivers/net/ethernet/marvell/mvneta.c
> @@ -636,8 +636,9 @@ static void mvneta_mib_counters_clear(struct mvneta_port *pp)
> }
>
> /* Get System Network Statistics */
> -struct rtnl_link_stats64 *mvneta_get_stats64(struct net_device *dev,
> - struct rtnl_link_stats64 *stats)
> +static struct
> +rtnl_link_stats64 *mvneta_get_stats64(struct net_device *dev,
I'd break the line after * heren not where you did it. This way the
function type would remain all in one line.
> + struct rtnl_link_stats64 *stats)
> {
> struct mvneta_port *pp = netdev_priv(dev);
> unsigned int start;
[...]
MBR, Sergei
^ permalink raw reply
* [PATCH net-next 1/1] net sched actions police: peg drop stats for conforming traffic
From: Jamal Hadi Salim @ 2016-09-18 11:53 UTC (permalink / raw)
To: davem; +Cc: netdev, Roman Mashak, Jamal Hadi Salim
From: Roman Mashak <mrv@mojatatu.com>
setting conforming action to drop is a valid policy.
When it is set we need to at least see the stats indicating it
for debugging.
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
net/sched/act_police.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 8a3be1d..ba7074b 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -249,6 +249,8 @@ static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a,
police->tcfp_t_c = now;
police->tcfp_toks = toks;
police->tcfp_ptoks = ptoks;
+ if (police->tcfp_result == TC_ACT_SHOT)
+ police->tcf_qstats.drops++;
spin_unlock(&police->tcf_lock);
return police->tcfp_result;
}
--
1.9.1
^ permalink raw reply related
* Re: [PATCH net-next 11/11] rxrpc: Add config to inject packet loss
From: Sergei Shtylyov @ 2016-09-18 11:47 UTC (permalink / raw)
To: David Howells, netdev; +Cc: linux-afs, linux-kernel
In-Reply-To: <147415456698.18436.9557149460694248243.stgit@warthog.procyon.org.uk>
Hello.
On 9/18/2016 2:22 AM, David Howells wrote:
> Add a configuration option to inject packet loss by discarding
> approximately every 8th packet received and approximately every 8th DATA
> packet transmitted.
>
> Note that no locking is used, but it shouldn't really matter.
>
> Signed-off-by: David Howells <dhowells@redhat.com>
[...]
> diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
> index 84bb16d47b85..7ac1edf3aac7 100644
> --- a/net/rxrpc/input.c
> +++ b/net/rxrpc/input.c
> @@ -712,6 +712,14 @@ void rxrpc_data_ready(struct sock *udp_sk)
> skb_orphan(skb);
> sp = rxrpc_skb(skb);
>
> + if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) {
> + static int lose;
IIRC, scripts/checkpatch.pl complains now if there's no empty line after
declaration...
> + if ((lose++ & 7) == 7) {
> + rxrpc_lose_skb(skb, rxrpc_skb_rx_lost);
> + return;
> + }
> + }
> +
> _net("Rx UDP packet from %08x:%04hu",
> ntohl(ip_hdr(skb)->saddr), ntohs(udp_hdr(skb)->source));
>
> diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
> index a2cad5ce7416..16e18a94ffa6 100644
> --- a/net/rxrpc/output.c
> +++ b/net/rxrpc/output.c
> @@ -225,6 +225,15 @@ int rxrpc_send_data_packet(struct rxrpc_connection *conn, struct sk_buff *skb)
> msg.msg_controllen = 0;
> msg.msg_flags = 0;
>
> + if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) {
> + static int lose;
Same here.
> + if ((lose++ & 7) == 7) {
> + rxrpc_lose_skb(skb, rxrpc_skb_tx_lost);
> + _leave(" = 0 [lose]");
> + return 0;
> + }
> + }
> +
> /* send the packet with the don't fragment bit set if we currently
> * think it's small enough */
> if (skb->len - sizeof(struct rxrpc_wire_header) < conn->params.peer->maxdata) {
MBR, Sergei
^ permalink raw reply
* Re: [PATCH] net: mvneta: mark symbols static where possible
From: Thomas Petazzoni @ 2016-09-18 11:33 UTC (permalink / raw)
To: Baoyou Xie; +Cc: netdev, linux-kernel, arnd, xie.baoyou
In-Reply-To: <1474190445-5887-1-git-send-email-baoyou.xie@linaro.org>
Hello,
On Sun, 18 Sep 2016 17:20:45 +0800, Baoyou Xie wrote:
> We get 2 warnings when building kernel with W=1:
> drivers/net/ethernet/marvell/mvneta.c:639:27: warning: no previous prototype for 'mvneta_get_stats64' [-Wmissing-prototypes]
> drivers/net/ethernet/marvell/mvneta.c:3529:5: warning: no previous prototype for 'mvneta_ethtool_set_link_ksettings' [-Wmissing-prototypes]
>
> In fact, these functions are only used in the file in which they are
> declared and don't need a declaration, but can be made static.
> so this patch marks these functions with 'static'.
>
> Signed-off-by: Baoyou Xie <baoyou.xie@linaro.org>
Acked-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
--
Thomas Petazzoni, CTO, Free Electrons
Embedded Linux and Kernel engineering
http://free-electrons.com
^ permalink raw reply
* [PATCH v3 net-next 2/2] net sched ife action: Introduce skb tcindex metadata encap decap
From: Jamal Hadi Salim @ 2016-09-18 11:31 UTC (permalink / raw)
To: davem; +Cc: netdev, xiyou.wangcong, Jamal Hadi Salim
In-Reply-To: <1474198303-10645-1-git-send-email-jhs@emojatatu.com>
From: Jamal Hadi Salim <jhs@mojatatu.com>
Sample use case of how this is encoded:
user space via tuntap (or a connected VM/Machine/container)
encodes the tcindex TLV.
Sample use case of decoding:
IFE action decodes it and the skb->tc_index is then used to classify.
So something like this for encoded ICMP packets:
.. first decode then reclassify... skb->tcindex will be set
sudo $TC filter add dev $ETH parent ffff: prio 2 protocol 0xbeef \
u32 match u32 0 0 flowid 1:1 \
action ife decode reclassify
...next match the decode icmp packet...
sudo $TC filter add dev $ETH parent ffff: prio 4 protocol ip \
u32 match ip protocol 1 0xff flowid 1:1 \
action continue
... last classify it using the tcindex classifier and do someaction..
sudo $TC filter add dev $ETH parent ffff: prio 5 protocol ip \
handle 0x11 tcindex classid 1:1 \
action blah..
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
include/uapi/linux/tc_act/tc_ife.h | 3 +-
net/sched/Kconfig | 5 +++
net/sched/Makefile | 1 +
net/sched/act_meta_skbtcindex.c | 79 ++++++++++++++++++++++++++++++++++++++
4 files changed, 87 insertions(+), 1 deletion(-)
create mode 100644 net/sched/act_meta_skbtcindex.c
diff --git a/include/uapi/linux/tc_act/tc_ife.h b/include/uapi/linux/tc_act/tc_ife.h
index 4ece02a..cd18360 100644
--- a/include/uapi/linux/tc_act/tc_ife.h
+++ b/include/uapi/linux/tc_act/tc_ife.h
@@ -32,8 +32,9 @@ enum {
#define IFE_META_HASHID 2
#define IFE_META_PRIO 3
#define IFE_META_QMAP 4
+#define IFE_META_TCINDEX 5
/*Can be overridden at runtime by module option*/
-#define __IFE_META_MAX 5
+#define __IFE_META_MAX 6
#define IFE_META_MAX (__IFE_META_MAX - 1)
#endif
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 7795d5a..87956a7 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -793,6 +793,11 @@ config NET_IFE_SKBPRIO
depends on NET_ACT_IFE
---help---
+config NET_IFE_SKBTCINDEX
+ tristate "Support to encoding decoding skb tcindex on IFE action"
+ depends on NET_ACT_IFE
+ ---help---
+
config NET_CLS_IND
bool "Incoming device classification"
depends on NET_CLS_U32 || NET_CLS_FW
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 148ae0d..4bdda36 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_NET_ACT_SKBMOD) += act_skbmod.o
obj-$(CONFIG_NET_ACT_IFE) += act_ife.o
obj-$(CONFIG_NET_IFE_SKBMARK) += act_meta_mark.o
obj-$(CONFIG_NET_IFE_SKBPRIO) += act_meta_skbprio.o
+obj-$(CONFIG_NET_IFE_SKBTCINDEX) += act_meta_skbtcindex.o
obj-$(CONFIG_NET_ACT_TUNNEL_KEY)+= act_tunnel_key.o
obj-$(CONFIG_NET_SCH_FIFO) += sch_fifo.o
obj-$(CONFIG_NET_SCH_CBQ) += sch_cbq.o
diff --git a/net/sched/act_meta_skbtcindex.c b/net/sched/act_meta_skbtcindex.c
new file mode 100644
index 0000000..3b35774
--- /dev/null
+++ b/net/sched/act_meta_skbtcindex.c
@@ -0,0 +1,79 @@
+/*
+ * net/sched/act_meta_tc_index.c IFE skb->tc_index metadata module
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * copyright Jamal Hadi Salim (2016)
+ *
+*/
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+#include <uapi/linux/tc_act/tc_ife.h>
+#include <net/tc_act/tc_ife.h>
+#include <linux/rtnetlink.h>
+
+static int skbtcindex_encode(struct sk_buff *skb, void *skbdata,
+ struct tcf_meta_info *e)
+{
+ u32 ifetc_index = skb->tc_index;
+
+ return ife_encode_meta_u16(ifetc_index, skbdata, e);
+}
+
+static int skbtcindex_decode(struct sk_buff *skb, void *data, u16 len)
+{
+ u16 ifetc_index = *(u16 *)data;
+
+ skb->tc_index = ntohs(ifetc_index);
+ return 0;
+}
+
+static int skbtcindex_check(struct sk_buff *skb, struct tcf_meta_info *e)
+{
+ return ife_check_meta_u16(skb->tc_index, e);
+}
+
+static struct tcf_meta_ops ife_skbtcindex_ops = {
+ .metaid = IFE_META_TCINDEX,
+ .metatype = NLA_U16,
+ .name = "tc_index",
+ .synopsis = "skb tc_index 16 bit metadata",
+ .check_presence = skbtcindex_check,
+ .encode = skbtcindex_encode,
+ .decode = skbtcindex_decode,
+ .get = ife_get_meta_u16,
+ .alloc = ife_alloc_meta_u16,
+ .release = ife_release_meta_gen,
+ .validate = ife_validate_meta_u16,
+ .owner = THIS_MODULE,
+};
+
+static int __init ifetc_index_init_module(void)
+{
+ return register_ife_op(&ife_skbtcindex_ops);
+}
+
+static void __exit ifetc_index_cleanup_module(void)
+{
+ unregister_ife_op(&ife_skbtcindex_ops);
+}
+
+module_init(ifetc_index_init_module);
+module_exit(ifetc_index_cleanup_module);
+
+MODULE_AUTHOR("Jamal Hadi Salim(2016)");
+MODULE_DESCRIPTION("Inter-FE skb tc_index metadata module");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_IFE_META(IFE_META_SKBTCINDEX);
--
1.9.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox