* [PATCH net-next v4 0/3] make skip_sw actually skip software
@ 2024-03-25 20:47 Asbjørn Sloth Tønnesen
2024-03-25 20:47 ` [PATCH net-next v4 1/3] net: sched: cls_api: add skip_sw counter Asbjørn Sloth Tønnesen
` (3 more replies)
0 siblings, 4 replies; 11+ messages in thread
From: Asbjørn Sloth Tønnesen @ 2024-03-25 20:47 UTC (permalink / raw
To: Jamal Hadi Salim, Cong Wang, Jiri Pirko
Cc: Asbjørn Sloth Tønnesen, Daniel Borkmann,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Vlad Buslov, Marcelo Ricardo Leitner, netdev, linux-kernel, llu
Hi,
During development of flower-route[1], which I
recently presented at FOSDEM[2], I noticed that
CPU usage, would increase the more rules I installed
into the hardware for IP forwarding offloading.
Since we use TC flower offload for the hottest
prefixes, and leave the long tail to the normal (non-TC)
Linux network stack for slow-path IP forwarding.
We therefore need both the hardware and software
datapath to perform well.
I found that skip_sw rules, are quite expensive
in the kernel datapath, since they must be evaluated
and matched upon, before the kernel checks the
skip_sw flag.
This patchset optimizes the case where all rules
are skip_sw, by implementing a TC bypass for these
cases, where TC is only used as a control plane
for the hardware path.
v4:
- Rebased onto net-next, now that net-next is open again
v3: https://lore.kernel.org/netdev/20240306165813.656931-1-ast@fiberby.net/
- Patch 3:
- Fix source_inline
- Fix build failure, when CONFIG_NET_CLS without CONFIG_NET_CLS_ACT.
v2: https://lore.kernel.org/netdev/20240305144404.569632-1-ast@fiberby.net/
- Patch 1:
- Add Reviewed-By from Jiri Pirko
- Patch 2:
- Move code, to avoid forward declaration (Jiri).
- Patch 3
- Refactor to use a static key.
- Add performance data for trapping, or sending
a packet to a non-existent chain (as suggested by Marcelo).
v1: https://lore.kernel.org/netdev/20240215160458.1727237-1-ast@fiberby.net/
[1] flower-route
https://github.com/fiberby-dk/flower-route
[2] FOSDEM talk
https://fosdem.org/2024/schedule/event/fosdem-2024-3337-flying-higher-hardware-offloading-with-bird/
Asbjørn Sloth Tønnesen (3):
net: sched: cls_api: add skip_sw counter
net: sched: cls_api: add filter counter
net: sched: make skip_sw actually skip software
include/net/pkt_cls.h | 9 +++++++++
include/net/sch_generic.h | 4 ++++
net/core/dev.c | 10 ++++++++++
net/sched/cls_api.c | 41 +++++++++++++++++++++++++++++++++++++++
4 files changed, 64 insertions(+)
--
2.43.0
^ permalink raw reply [flat|nested] 11+ messages in thread
* [PATCH net-next v4 1/3] net: sched: cls_api: add skip_sw counter
2024-03-25 20:47 [PATCH net-next v4 0/3] make skip_sw actually skip software Asbjørn Sloth Tønnesen
@ 2024-03-25 20:47 ` Asbjørn Sloth Tønnesen
2024-03-27 13:51 ` Simon Horman
2024-03-28 0:46 ` Marcelo Ricardo Leitner
2024-03-25 20:47 ` [PATCH net-next v4 2/3] net: sched: cls_api: add filter counter Asbjørn Sloth Tønnesen
` (2 subsequent siblings)
3 siblings, 2 replies; 11+ messages in thread
From: Asbjørn Sloth Tønnesen @ 2024-03-25 20:47 UTC (permalink / raw
To: Jamal Hadi Salim, Cong Wang, Jiri Pirko
Cc: Asbjørn Sloth Tønnesen, Daniel Borkmann,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Vlad Buslov, Marcelo Ricardo Leitner, netdev, linux-kernel, llu,
Jiri Pirko
Maintain a count of skip_sw filters.
This counter is protected by the cb_lock, and is updated
at the same time as offloadcnt.
Signed-off-by: Asbjørn Sloth Tønnesen <ast@fiberby.net>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
include/net/sch_generic.h | 1 +
net/sched/cls_api.c | 4 ++++
2 files changed, 5 insertions(+)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index cefe0c4bdae3..120a4ca6ec9b 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -471,6 +471,7 @@ struct tcf_block {
struct flow_block flow_block;
struct list_head owner_list;
bool keep_dst;
+ atomic_t skipswcnt; /* Number of skip_sw filters */
atomic_t offloadcnt; /* Number of oddloaded filters */
unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */
unsigned int lockeddevcnt; /* Number of devs that require rtnl lock. */
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index ca5676b2668e..397c3d29659c 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3483,6 +3483,8 @@ static void tcf_block_offload_inc(struct tcf_block *block, u32 *flags)
if (*flags & TCA_CLS_FLAGS_IN_HW)
return;
*flags |= TCA_CLS_FLAGS_IN_HW;
+ if (tc_skip_sw(*flags))
+ atomic_inc(&block->skipswcnt);
atomic_inc(&block->offloadcnt);
}
@@ -3491,6 +3493,8 @@ static void tcf_block_offload_dec(struct tcf_block *block, u32 *flags)
if (!(*flags & TCA_CLS_FLAGS_IN_HW))
return;
*flags &= ~TCA_CLS_FLAGS_IN_HW;
+ if (tc_skip_sw(*flags))
+ atomic_dec(&block->skipswcnt);
atomic_dec(&block->offloadcnt);
}
--
2.43.0
^ permalink raw reply related [flat|nested] 11+ messages in thread
* [PATCH net-next v4 2/3] net: sched: cls_api: add filter counter
2024-03-25 20:47 [PATCH net-next v4 0/3] make skip_sw actually skip software Asbjørn Sloth Tønnesen
2024-03-25 20:47 ` [PATCH net-next v4 1/3] net: sched: cls_api: add skip_sw counter Asbjørn Sloth Tønnesen
@ 2024-03-25 20:47 ` Asbjørn Sloth Tønnesen
2024-03-27 13:51 ` Simon Horman
2024-03-28 0:46 ` Marcelo Ricardo Leitner
2024-03-25 20:47 ` [PATCH net-next v4 3/3] net: sched: make skip_sw actually skip software Asbjørn Sloth Tønnesen
2024-03-29 9:50 ` [PATCH net-next v4 0/3] " patchwork-bot+netdevbpf
3 siblings, 2 replies; 11+ messages in thread
From: Asbjørn Sloth Tønnesen @ 2024-03-25 20:47 UTC (permalink / raw
To: Jamal Hadi Salim, Cong Wang, Jiri Pirko
Cc: Asbjørn Sloth Tønnesen, Daniel Borkmann,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Vlad Buslov, Marcelo Ricardo Leitner, netdev, linux-kernel, llu
Maintain a count of filters per block.
Counter updates are protected by cb_lock, which is
also used to protect the offload counters.
Signed-off-by: Asbjørn Sloth Tønnesen <ast@fiberby.net>
---
include/net/sch_generic.h | 2 ++
net/sched/cls_api.c | 19 +++++++++++++++++++
2 files changed, 21 insertions(+)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 120a4ca6ec9b..eb3872c22fcd 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -422,6 +422,7 @@ struct tcf_proto {
*/
spinlock_t lock;
bool deleting;
+ bool counted;
refcount_t refcnt;
struct rcu_head rcu;
struct hlist_node destroy_ht_node;
@@ -471,6 +472,7 @@ struct tcf_block {
struct flow_block flow_block;
struct list_head owner_list;
bool keep_dst;
+ atomic_t filtercnt; /* Number of filters */
atomic_t skipswcnt; /* Number of skip_sw filters */
atomic_t offloadcnt; /* Number of oddloaded filters */
unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 397c3d29659c..304a46ab0e0b 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -410,12 +410,30 @@ static void tcf_proto_get(struct tcf_proto *tp)
refcount_inc(&tp->refcnt);
}
+static void tcf_block_filter_cnt_update(struct tcf_block *block, bool *counted, bool add)
+{
+ lockdep_assert_not_held(&block->cb_lock);
+
+ down_write(&block->cb_lock);
+ if (*counted != add) {
+ if (add) {
+ atomic_inc(&block->filtercnt);
+ *counted = true;
+ } else {
+ atomic_dec(&block->filtercnt);
+ *counted = false;
+ }
+ }
+ up_write(&block->cb_lock);
+}
+
static void tcf_chain_put(struct tcf_chain *chain);
static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held,
bool sig_destroy, struct netlink_ext_ack *extack)
{
tp->ops->destroy(tp, rtnl_held, extack);
+ tcf_block_filter_cnt_update(tp->chain->block, &tp->counted, false);
if (sig_destroy)
tcf_proto_signal_destroyed(tp->chain, tp);
tcf_chain_put(tp->chain);
@@ -2364,6 +2382,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh,
flags, extack);
if (err == 0) {
+ tcf_block_filter_cnt_update(block, &tp->counted, true);
tfilter_notify(net, skb, n, tp, block, q, parent, fh,
RTM_NEWTFILTER, false, rtnl_held, extack);
tfilter_put(tp, fh);
--
2.43.0
^ permalink raw reply related [flat|nested] 11+ messages in thread
* [PATCH net-next v4 3/3] net: sched: make skip_sw actually skip software
2024-03-25 20:47 [PATCH net-next v4 0/3] make skip_sw actually skip software Asbjørn Sloth Tønnesen
2024-03-25 20:47 ` [PATCH net-next v4 1/3] net: sched: cls_api: add skip_sw counter Asbjørn Sloth Tønnesen
2024-03-25 20:47 ` [PATCH net-next v4 2/3] net: sched: cls_api: add filter counter Asbjørn Sloth Tønnesen
@ 2024-03-25 20:47 ` Asbjørn Sloth Tønnesen
2024-03-27 13:52 ` Simon Horman
2024-03-28 0:46 ` Marcelo Ricardo Leitner
2024-03-29 9:50 ` [PATCH net-next v4 0/3] " patchwork-bot+netdevbpf
3 siblings, 2 replies; 11+ messages in thread
From: Asbjørn Sloth Tønnesen @ 2024-03-25 20:47 UTC (permalink / raw
To: Jamal Hadi Salim, Cong Wang, Jiri Pirko
Cc: Asbjørn Sloth Tønnesen, Daniel Borkmann,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Vlad Buslov, Marcelo Ricardo Leitner, netdev, linux-kernel, llu
TC filters come in 3 variants:
- no flag (try to process in hardware, but fallback to software))
- skip_hw (do not process filter by hardware)
- skip_sw (do not process filter by software)
However skip_sw is implemented so that the skip_sw
flag can first be checked, after it has been matched.
IMHO it's common when using skip_sw, to use it on all rules.
So if all filters in a block is skip_sw filters, then
we can bail early, we can thus avoid having to match
the filters, just to check for the skip_sw flag.
This patch adds a bypass, for when only TC skip_sw rules
are used. The bypass is guarded by a static key, to avoid
harming other workloads.
There are 3 ways that a packet from a skip_sw ruleset, can
end up in the kernel path. Although the send packets to a
non-existent chain way is only improved a few percents, then
I believe it's worth optimizing the trap and fall-though
use-cases.
+----------------------------+--------+--------+--------+
| Test description | Pre- | Post- | Rel. |
| | kpps | kpps | chg. |
+----------------------------+--------+--------+--------+
| basic forwarding + notrack | 3589.3 | 3587.9 | 1.00x |
| switch to eswitch mode | 3081.8 | 3094.7 | 1.00x |
| add ingress qdisc | 3042.9 | 3063.6 | 1.01x |
| tc forward in hw / skip_sw |37024.7 |37028.4 | 1.00x |
| tc forward in sw / skip_hw | 3245.0 | 3245.3 | 1.00x |
+----------------------------+--------+--------+--------+
| tests with only skip_sw rules below: |
+----------------------------+--------+--------+--------+
| 1 non-matching rule | 2694.7 | 3058.7 | 1.14x |
| 1 n-m rule, match trap | 2611.2 | 3323.1 | 1.27x |
| 1 n-m rule, goto non-chain | 2886.8 | 2945.9 | 1.02x |
| 5 non-matching rules | 1958.2 | 3061.3 | 1.56x |
| 5 n-m rules, match trap | 1911.9 | 3327.0 | 1.74x |
| 5 n-m rules, goto non-chain| 2883.1 | 2947.5 | 1.02x |
| 10 non-matching rules | 1466.3 | 3062.8 | 2.09x |
| 10 n-m rules, match trap | 1444.3 | 3317.9 | 2.30x |
| 10 n-m rules,goto non-chain| 2883.1 | 2939.5 | 1.02x |
| 25 non-matching rules | 838.5 | 3058.9 | 3.65x |
| 25 n-m rules, match trap | 824.5 | 3323.0 | 4.03x |
| 25 n-m rules,goto non-chain| 2875.8 | 2944.7 | 1.02x |
| 50 non-matching rules | 488.1 | 3054.7 | 6.26x |
| 50 n-m rules, match trap | 484.9 | 3318.5 | 6.84x |
| 50 n-m rules,goto non-chain| 2884.1 | 2939.7 | 1.02x |
+----------------------------+--------+--------+--------+
perf top (25 n-m skip_sw rules - pre patch):
20.39% [kernel] [k] __skb_flow_dissect
16.43% [kernel] [k] rhashtable_jhash2
10.58% [kernel] [k] fl_classify
10.23% [kernel] [k] fl_mask_lookup
4.79% [kernel] [k] memset_orig
2.58% [kernel] [k] tcf_classify
1.47% [kernel] [k] __x86_indirect_thunk_rax
1.42% [kernel] [k] __dev_queue_xmit
1.36% [kernel] [k] nft_do_chain
1.21% [kernel] [k] __rcu_read_lock
perf top (25 n-m skip_sw rules - post patch):
5.12% [kernel] [k] __dev_queue_xmit
4.77% [kernel] [k] nft_do_chain
3.65% [kernel] [k] dev_gro_receive
3.41% [kernel] [k] check_preemption_disabled
3.14% [kernel] [k] mlx5e_skb_from_cqe_mpwrq_nonlinear
2.88% [kernel] [k] __netif_receive_skb_core.constprop.0
2.49% [kernel] [k] mlx5e_xmit
2.15% [kernel] [k] ip_forward
1.95% [kernel] [k] mlx5e_tc_restore_tunnel
1.92% [kernel] [k] vlan_gro_receive
Test setup:
DUT: Intel Xeon D-1518 (2.20GHz) w/ Nvidia/Mellanox ConnectX-6 Dx 2x100G
Data rate measured on switch (Extreme X690), and DUT connected as
a router on a stick, with pktgen and pktsink as VLANs.
Pktgen-dpdk was in range 36.6-37.7 Mpps 64B packets across all tests.
Full test data at https://files.fiberby.net/ast/2024/tc_skip_sw/v2_tests/
Signed-off-by: Asbjørn Sloth Tønnesen <ast@fiberby.net>
---
include/net/pkt_cls.h | 9 +++++++++
include/net/sch_generic.h | 1 +
net/core/dev.c | 10 ++++++++++
net/sched/cls_api.c | 18 ++++++++++++++++++
4 files changed, 38 insertions(+)
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index a4ee43f493bb..41297bd38dff 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -74,6 +74,15 @@ static inline bool tcf_block_non_null_shared(struct tcf_block *block)
return block && block->index;
}
+#ifdef CONFIG_NET_CLS_ACT
+DECLARE_STATIC_KEY_FALSE(tcf_bypass_check_needed_key);
+
+static inline bool tcf_block_bypass_sw(struct tcf_block *block)
+{
+ return block && block->bypass_wanted;
+}
+#endif
+
static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
{
WARN_ON(tcf_block_shared(block));
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index eb3872c22fcd..76db6be16083 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -472,6 +472,7 @@ struct tcf_block {
struct flow_block flow_block;
struct list_head owner_list;
bool keep_dst;
+ bool bypass_wanted;
atomic_t filtercnt; /* Number of filters */
atomic_t skipswcnt; /* Number of skip_sw filters */
atomic_t offloadcnt; /* Number of oddloaded filters */
diff --git a/net/core/dev.c b/net/core/dev.c
index 9a67003e49db..53f36991ea8e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2057,6 +2057,11 @@ void net_dec_egress_queue(void)
EXPORT_SYMBOL_GPL(net_dec_egress_queue);
#endif
+#ifdef CONFIG_NET_CLS_ACT
+DEFINE_STATIC_KEY_FALSE(tcf_bypass_check_needed_key);
+EXPORT_SYMBOL(tcf_bypass_check_needed_key);
+#endif
+
DEFINE_STATIC_KEY_FALSE(netstamp_needed_key);
EXPORT_SYMBOL(netstamp_needed_key);
#ifdef CONFIG_JUMP_LABEL
@@ -3911,6 +3916,11 @@ static int tc_run(struct tcx_entry *entry, struct sk_buff *skb,
if (!miniq)
return ret;
+ if (static_branch_unlikely(&tcf_bypass_check_needed_key)) {
+ if (tcf_block_bypass_sw(miniq->block))
+ return ret;
+ }
+
tc_skb_cb(skb)->mru = 0;
tc_skb_cb(skb)->post_ct = false;
tcf_set_drop_reason(skb, *drop_reason);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 304a46ab0e0b..db0653993632 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -410,6 +410,23 @@ static void tcf_proto_get(struct tcf_proto *tp)
refcount_inc(&tp->refcnt);
}
+static void tcf_maintain_bypass(struct tcf_block *block)
+{
+ int filtercnt = atomic_read(&block->filtercnt);
+ int skipswcnt = atomic_read(&block->skipswcnt);
+ bool bypass_wanted = filtercnt > 0 && filtercnt == skipswcnt;
+
+ if (bypass_wanted != block->bypass_wanted) {
+#ifdef CONFIG_NET_CLS_ACT
+ if (bypass_wanted)
+ static_branch_inc(&tcf_bypass_check_needed_key);
+ else
+ static_branch_dec(&tcf_bypass_check_needed_key);
+#endif
+ block->bypass_wanted = bypass_wanted;
+ }
+}
+
static void tcf_block_filter_cnt_update(struct tcf_block *block, bool *counted, bool add)
{
lockdep_assert_not_held(&block->cb_lock);
@@ -424,6 +441,7 @@ static void tcf_block_filter_cnt_update(struct tcf_block *block, bool *counted,
*counted = false;
}
}
+ tcf_maintain_bypass(block);
up_write(&block->cb_lock);
}
--
2.43.0
^ permalink raw reply related [flat|nested] 11+ messages in thread
* Re: [PATCH net-next v4 1/3] net: sched: cls_api: add skip_sw counter
2024-03-25 20:47 ` [PATCH net-next v4 1/3] net: sched: cls_api: add skip_sw counter Asbjørn Sloth Tønnesen
@ 2024-03-27 13:51 ` Simon Horman
2024-03-28 0:46 ` Marcelo Ricardo Leitner
1 sibling, 0 replies; 11+ messages in thread
From: Simon Horman @ 2024-03-27 13:51 UTC (permalink / raw
To: Asbjørn Sloth Tønnesen
Cc: Jamal Hadi Salim, Cong Wang, Jiri Pirko, Daniel Borkmann,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Vlad Buslov, Marcelo Ricardo Leitner, netdev, linux-kernel, llu,
Jiri Pirko
On Mon, Mar 25, 2024 at 08:47:34PM +0000, Asbjørn Sloth Tønnesen wrote:
> Maintain a count of skip_sw filters.
>
> This counter is protected by the cb_lock, and is updated
> at the same time as offloadcnt.
>
> Signed-off-by: Asbjørn Sloth Tønnesen <ast@fiberby.net>
> Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [PATCH net-next v4 2/3] net: sched: cls_api: add filter counter
2024-03-25 20:47 ` [PATCH net-next v4 2/3] net: sched: cls_api: add filter counter Asbjørn Sloth Tønnesen
@ 2024-03-27 13:51 ` Simon Horman
2024-03-28 0:46 ` Marcelo Ricardo Leitner
1 sibling, 0 replies; 11+ messages in thread
From: Simon Horman @ 2024-03-27 13:51 UTC (permalink / raw
To: Asbjørn Sloth Tønnesen
Cc: Jamal Hadi Salim, Cong Wang, Jiri Pirko, Daniel Borkmann,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Vlad Buslov, Marcelo Ricardo Leitner, netdev, linux-kernel, llu
On Mon, Mar 25, 2024 at 08:47:35PM +0000, Asbjørn Sloth Tønnesen wrote:
> Maintain a count of filters per block.
>
> Counter updates are protected by cb_lock, which is
> also used to protect the offload counters.
>
> Signed-off-by: Asbjørn Sloth Tønnesen <ast@fiberby.net>
Reviewed-by: Simon Horman <horms@kernel.org>
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [PATCH net-next v4 3/3] net: sched: make skip_sw actually skip software
2024-03-25 20:47 ` [PATCH net-next v4 3/3] net: sched: make skip_sw actually skip software Asbjørn Sloth Tønnesen
@ 2024-03-27 13:52 ` Simon Horman
2024-03-28 0:46 ` Marcelo Ricardo Leitner
1 sibling, 0 replies; 11+ messages in thread
From: Simon Horman @ 2024-03-27 13:52 UTC (permalink / raw
To: Asbjørn Sloth Tønnesen
Cc: Jamal Hadi Salim, Cong Wang, Jiri Pirko, Daniel Borkmann,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Vlad Buslov, Marcelo Ricardo Leitner, netdev, linux-kernel, llu
On Mon, Mar 25, 2024 at 08:47:36PM +0000, Asbjørn Sloth Tønnesen wrote:
> TC filters come in 3 variants:
> - no flag (try to process in hardware, but fallback to software))
> - skip_hw (do not process filter by hardware)
> - skip_sw (do not process filter by software)
>
> However skip_sw is implemented so that the skip_sw
> flag can first be checked, after it has been matched.
>
> IMHO it's common when using skip_sw, to use it on all rules.
>
> So if all filters in a block is skip_sw filters, then
> we can bail early, we can thus avoid having to match
> the filters, just to check for the skip_sw flag.
>
> This patch adds a bypass, for when only TC skip_sw rules
> are used. The bypass is guarded by a static key, to avoid
> harming other workloads.
>
> There are 3 ways that a packet from a skip_sw ruleset, can
> end up in the kernel path. Although the send packets to a
> non-existent chain way is only improved a few percents, then
> I believe it's worth optimizing the trap and fall-though
> use-cases.
>
> +----------------------------+--------+--------+--------+
> | Test description | Pre- | Post- | Rel. |
> | | kpps | kpps | chg. |
> +----------------------------+--------+--------+--------+
> | basic forwarding + notrack | 3589.3 | 3587.9 | 1.00x |
> | switch to eswitch mode | 3081.8 | 3094.7 | 1.00x |
> | add ingress qdisc | 3042.9 | 3063.6 | 1.01x |
> | tc forward in hw / skip_sw |37024.7 |37028.4 | 1.00x |
> | tc forward in sw / skip_hw | 3245.0 | 3245.3 | 1.00x |
> +----------------------------+--------+--------+--------+
> | tests with only skip_sw rules below: |
> +----------------------------+--------+--------+--------+
> | 1 non-matching rule | 2694.7 | 3058.7 | 1.14x |
> | 1 n-m rule, match trap | 2611.2 | 3323.1 | 1.27x |
> | 1 n-m rule, goto non-chain | 2886.8 | 2945.9 | 1.02x |
> | 5 non-matching rules | 1958.2 | 3061.3 | 1.56x |
> | 5 n-m rules, match trap | 1911.9 | 3327.0 | 1.74x |
> | 5 n-m rules, goto non-chain| 2883.1 | 2947.5 | 1.02x |
> | 10 non-matching rules | 1466.3 | 3062.8 | 2.09x |
> | 10 n-m rules, match trap | 1444.3 | 3317.9 | 2.30x |
> | 10 n-m rules,goto non-chain| 2883.1 | 2939.5 | 1.02x |
> | 25 non-matching rules | 838.5 | 3058.9 | 3.65x |
> | 25 n-m rules, match trap | 824.5 | 3323.0 | 4.03x |
> | 25 n-m rules,goto non-chain| 2875.8 | 2944.7 | 1.02x |
> | 50 non-matching rules | 488.1 | 3054.7 | 6.26x |
> | 50 n-m rules, match trap | 484.9 | 3318.5 | 6.84x |
> | 50 n-m rules,goto non-chain| 2884.1 | 2939.7 | 1.02x |
> +----------------------------+--------+--------+--------+
>
> perf top (25 n-m skip_sw rules - pre patch):
> 20.39% [kernel] [k] __skb_flow_dissect
> 16.43% [kernel] [k] rhashtable_jhash2
> 10.58% [kernel] [k] fl_classify
> 10.23% [kernel] [k] fl_mask_lookup
> 4.79% [kernel] [k] memset_orig
> 2.58% [kernel] [k] tcf_classify
> 1.47% [kernel] [k] __x86_indirect_thunk_rax
> 1.42% [kernel] [k] __dev_queue_xmit
> 1.36% [kernel] [k] nft_do_chain
> 1.21% [kernel] [k] __rcu_read_lock
>
> perf top (25 n-m skip_sw rules - post patch):
> 5.12% [kernel] [k] __dev_queue_xmit
> 4.77% [kernel] [k] nft_do_chain
> 3.65% [kernel] [k] dev_gro_receive
> 3.41% [kernel] [k] check_preemption_disabled
> 3.14% [kernel] [k] mlx5e_skb_from_cqe_mpwrq_nonlinear
> 2.88% [kernel] [k] __netif_receive_skb_core.constprop.0
> 2.49% [kernel] [k] mlx5e_xmit
> 2.15% [kernel] [k] ip_forward
> 1.95% [kernel] [k] mlx5e_tc_restore_tunnel
> 1.92% [kernel] [k] vlan_gro_receive
>
> Test setup:
> DUT: Intel Xeon D-1518 (2.20GHz) w/ Nvidia/Mellanox ConnectX-6 Dx 2x100G
> Data rate measured on switch (Extreme X690), and DUT connected as
> a router on a stick, with pktgen and pktsink as VLANs.
> Pktgen-dpdk was in range 36.6-37.7 Mpps 64B packets across all tests.
> Full test data at https://files.fiberby.net/ast/2024/tc_skip_sw/v2_tests/
>
> Signed-off-by: Asbjørn Sloth Tønnesen <ast@fiberby.net>
Reviewed-by: Simon Horman <horms@kernel.org>
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [PATCH net-next v4 3/3] net: sched: make skip_sw actually skip software
2024-03-25 20:47 ` [PATCH net-next v4 3/3] net: sched: make skip_sw actually skip software Asbjørn Sloth Tønnesen
2024-03-27 13:52 ` Simon Horman
@ 2024-03-28 0:46 ` Marcelo Ricardo Leitner
1 sibling, 0 replies; 11+ messages in thread
From: Marcelo Ricardo Leitner @ 2024-03-28 0:46 UTC (permalink / raw
To: Asbjørn Sloth Tønnesen
Cc: Jamal Hadi Salim, Cong Wang, Jiri Pirko, Daniel Borkmann,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Vlad Buslov, netdev, linux-kernel, llu
On Mon, Mar 25, 2024 at 08:47:36PM +0000, Asbjørn Sloth Tønnesen wrote:
...
> +----------------------------+--------+--------+--------+
> | tests with only skip_sw rules below: |
> +----------------------------+--------+--------+--------+
> | 1 non-matching rule | 2694.7 | 3058.7 | 1.14x |
> | 1 n-m rule, match trap | 2611.2 | 3323.1 | 1.27x |
> | 1 n-m rule, goto non-chain | 2886.8 | 2945.9 | 1.02x |
> | 5 non-matching rules | 1958.2 | 3061.3 | 1.56x |
> | 5 n-m rules, match trap | 1911.9 | 3327.0 | 1.74x |
> | 5 n-m rules, goto non-chain| 2883.1 | 2947.5 | 1.02x |
> | 10 non-matching rules | 1466.3 | 3062.8 | 2.09x |
> | 10 n-m rules, match trap | 1444.3 | 3317.9 | 2.30x |
> | 10 n-m rules,goto non-chain| 2883.1 | 2939.5 | 1.02x |
> | 25 non-matching rules | 838.5 | 3058.9 | 3.65x |
> | 25 n-m rules, match trap | 824.5 | 3323.0 | 4.03x |
> | 25 n-m rules,goto non-chain| 2875.8 | 2944.7 | 1.02x |
> | 50 non-matching rules | 488.1 | 3054.7 | 6.26x |
[A]
> | 50 n-m rules, match trap | 484.9 | 3318.5 | 6.84x |
Interesting. I can't explain why it consistently got 10% better than
[A] after the patch. If you check tcf_classify(), even though it
resumes to action, it still searches for the right chain. Maybe
something works differently in the driver.
In on the logs,
https://files.fiberby.net/ast/2024/tc_skip_sw/v2_tests/test_runs/netnext/tests/non_matching_and_trap_007/tc.txt
filter protocol 802.1Q pref 8 flower chain 0
filter protocol 802.1Q pref 8 flower chain 0 handle 0x1
vlan_ethtype ip
eth_type ipv4
dst_ip 10.53.22.3
skip_sw
in_hw in_hw_count 1
action order 1: gact action trap
random type none pass val 0
index 8 ref 1 bind 1 installed 20 sec used 0 sec
Action statistics:
Sent 29894330340 bytes 439622505 pkt (dropped 0, overlimits 0 requeues 0)
Sent software 0 bytes 0 pkt
Sent hardware 29894330340 bytes 439622505 pkt
backlog 0b 0p requeues 0
used_hw_stats delayed
It matched nicely.
> | 50 n-m rules,goto non-chain| 2884.1 | 2939.7 | 1.02x |
[B]
If we compare [A] and [B], there's still a 5.9% increase, plus
not requiring somewhat hacky rules.
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [PATCH net-next v4 1/3] net: sched: cls_api: add skip_sw counter
2024-03-25 20:47 ` [PATCH net-next v4 1/3] net: sched: cls_api: add skip_sw counter Asbjørn Sloth Tønnesen
2024-03-27 13:51 ` Simon Horman
@ 2024-03-28 0:46 ` Marcelo Ricardo Leitner
1 sibling, 0 replies; 11+ messages in thread
From: Marcelo Ricardo Leitner @ 2024-03-28 0:46 UTC (permalink / raw
To: Asbjørn Sloth Tønnesen
Cc: Jamal Hadi Salim, Cong Wang, Jiri Pirko, Daniel Borkmann,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Vlad Buslov, netdev, linux-kernel, llu, Jiri Pirko
On Mon, Mar 25, 2024 at 08:47:34PM +0000, Asbjørn Sloth Tønnesen wrote:
> Maintain a count of skip_sw filters.
>
> This counter is protected by the cb_lock, and is updated
> at the same time as offloadcnt.
>
> Signed-off-by: Asbjørn Sloth Tønnesen <ast@fiberby.net>
> Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [PATCH net-next v4 2/3] net: sched: cls_api: add filter counter
2024-03-25 20:47 ` [PATCH net-next v4 2/3] net: sched: cls_api: add filter counter Asbjørn Sloth Tønnesen
2024-03-27 13:51 ` Simon Horman
@ 2024-03-28 0:46 ` Marcelo Ricardo Leitner
1 sibling, 0 replies; 11+ messages in thread
From: Marcelo Ricardo Leitner @ 2024-03-28 0:46 UTC (permalink / raw
To: Asbjørn Sloth Tønnesen
Cc: Jamal Hadi Salim, Cong Wang, Jiri Pirko, Daniel Borkmann,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Vlad Buslov, netdev, linux-kernel, llu
On Mon, Mar 25, 2024 at 08:47:35PM +0000, Asbjørn Sloth Tønnesen wrote:
> Maintain a count of filters per block.
>
> Counter updates are protected by cb_lock, which is
> also used to protect the offload counters.
>
> Signed-off-by: Asbjørn Sloth Tønnesen <ast@fiberby.net>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [PATCH net-next v4 0/3] make skip_sw actually skip software
2024-03-25 20:47 [PATCH net-next v4 0/3] make skip_sw actually skip software Asbjørn Sloth Tønnesen
` (2 preceding siblings ...)
2024-03-25 20:47 ` [PATCH net-next v4 3/3] net: sched: make skip_sw actually skip software Asbjørn Sloth Tønnesen
@ 2024-03-29 9:50 ` patchwork-bot+netdevbpf
3 siblings, 0 replies; 11+ messages in thread
From: patchwork-bot+netdevbpf @ 2024-03-29 9:50 UTC (permalink / raw
To: =?utf-8?b?QXNiasO4cm4gU2xvdGggVMO4bm5lc2VuIDxhc3RAZmliZXJieS5uZXQ+?=
Cc: jhs, xiyou.wangcong, jiri, daniel, davem, edumazet, kuba, pabeni,
vladbu, mleitner, netdev, linux-kernel, llu
Hello:
This series was applied to netdev/net-next.git (main)
by David S. Miller <davem@davemloft.net>:
On Mon, 25 Mar 2024 20:47:33 +0000 you wrote:
> Hi,
>
> During development of flower-route[1], which I
> recently presented at FOSDEM[2], I noticed that
> CPU usage, would increase the more rules I installed
> into the hardware for IP forwarding offloading.
>
> [...]
Here is the summary with links:
- [net-next,v4,1/3] net: sched: cls_api: add skip_sw counter
https://git.kernel.org/netdev/net-next/c/f631ef39d819
- [net-next,v4,2/3] net: sched: cls_api: add filter counter
https://git.kernel.org/netdev/net-next/c/2081fd3445fe
- [net-next,v4,3/3] net: sched: make skip_sw actually skip software
https://git.kernel.org/netdev/net-next/c/047f340b36fc
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
^ permalink raw reply [flat|nested] 11+ messages in thread
end of thread, other threads:[~2024-03-29 9:50 UTC | newest]
Thread overview: 11+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2024-03-25 20:47 [PATCH net-next v4 0/3] make skip_sw actually skip software Asbjørn Sloth Tønnesen
2024-03-25 20:47 ` [PATCH net-next v4 1/3] net: sched: cls_api: add skip_sw counter Asbjørn Sloth Tønnesen
2024-03-27 13:51 ` Simon Horman
2024-03-28 0:46 ` Marcelo Ricardo Leitner
2024-03-25 20:47 ` [PATCH net-next v4 2/3] net: sched: cls_api: add filter counter Asbjørn Sloth Tønnesen
2024-03-27 13:51 ` Simon Horman
2024-03-28 0:46 ` Marcelo Ricardo Leitner
2024-03-25 20:47 ` [PATCH net-next v4 3/3] net: sched: make skip_sw actually skip software Asbjørn Sloth Tønnesen
2024-03-27 13:52 ` Simon Horman
2024-03-28 0:46 ` Marcelo Ricardo Leitner
2024-03-29 9:50 ` [PATCH net-next v4 0/3] " patchwork-bot+netdevbpf
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.