Message-ID: <87le4cd2ws.fsf@toke.dk>
Date: Tue, 14 May 2024 13:54:43 +0200
From: Toke Høiland-Jørgensen <toke@...hat.com>
To: Sebastian Andrzej Siewior <bigeasy@...utronix.de>, Jesper Dangaard
 Brouer <hawk@...nel.org>
Cc: Alexei Starovoitov <alexei.starovoitov@...il.com>, LKML
 <linux-kernel@...r.kernel.org>, Network Development
 <netdev@...r.kernel.org>, "David S. Miller" <davem@...emloft.net>, Boqun
 Feng <boqun.feng@...il.com>, Daniel Borkmann <daniel@...earbox.net>, Eric
 Dumazet <edumazet@...gle.com>, Frederic Weisbecker <frederic@...nel.org>,
 Ingo Molnar <mingo@...hat.com>, Jakub Kicinski <kuba@...nel.org>, Paolo
 Abeni <pabeni@...hat.com>, Peter Zijlstra <peterz@...radead.org>, Thomas
 Gleixner <tglx@...utronix.de>, Waiman Long <longman@...hat.com>, Will
 Deacon <will@...nel.org>, Alexei Starovoitov <ast@...nel.org>, Andrii
 Nakryiko <andrii@...nel.org>, Eduard Zingerman <eddyz87@...il.com>, Hao
 Luo <haoluo@...gle.com>, Jiri Olsa <jolsa@...nel.org>, John Fastabend
 <john.fastabend@...il.com>, KP Singh <kpsingh@...nel.org>, Martin KaFai
 Lau <martin.lau@...ux.dev>, Song Liu <song@...nel.org>, Stanislav Fomichev
 <sdf@...gle.com>, Yonghong Song <yonghong.song@...ux.dev>, bpf
 <bpf@...r.kernel.org>
Subject: Re: [PATCH net-next 14/15 v2] net: Reference bpf_redirect_info via
 task_struct on PREEMPT_RT.

Sebastian Andrzej Siewior <bigeasy@...utronix.de> writes:

> The XDP redirect process is two staged:
> - bpf_prog_run_xdp() is invoked to run a eBPF program which inspects the
>   packet and makes decisions. While doing that, the per-CPU variable
>   bpf_redirect_info is used.
>
> - Afterwards xdp_do_redirect() is invoked and accesses bpf_redirect_info
>   and it may also access other per-CPU variables like xskmap_flush_list.
>
> At the very end of the NAPI callback, xdp_do_flush() is invoked which
> does not access bpf_redirect_info but will touch the individual per-CPU
> lists.
>
> The per-CPU variables are only used in the NAPI callback hence disabling
> bottom halves is the only protection mechanism. Users from preemptible
> context (like cpu_map_kthread_run()) explicitly disable bottom halves
> for protections reasons.
> Without locking in local_bh_disable() on PREEMPT_RT this data structure
> requires explicit locking.
>
> PREEMPT_RT has forced-threaded interrupts enabled and every
> NAPI-callback runs in a thread. If each thread has its own data
> structure then locking can be avoided.
>
> Create a struct bpf_net_context which contains struct bpf_redirect_info.
> Define the variable on stack, use bpf_net_ctx_set() to save a pointer to
> it. Use the __free() annotation to automatically reset the pointer once
> function returns.
> The bpf_net_ctx_set() may nest. For instance a function can be used from
> within NET_RX_SOFTIRQ/ net_rx_action which uses bpf_net_ctx_set() and
> NET_TX_SOFTIRQ which does not. Therefore only the first invocations
> updates the pointer.
> Use bpf_net_ctx_get_ri() as a wrapper to retrieve the current struct
> bpf_redirect_info.
>
> On PREEMPT_RT the pointer to bpf_net_context is saved task's
> task_struct. On non-PREEMPT_RT builds the pointer saved in a per-CPU
> variable (which is always NODE-local memory). Using always the
> bpf_net_context approach has the advantage that there is almost zero
> differences between PREEMPT_RT and non-PREEMPT_RT builds.
>
> Cc: Alexei Starovoitov <ast@...nel.org>
> Cc: Andrii Nakryiko <andrii@...nel.org>
> Cc: Eduard Zingerman <eddyz87@...il.com>
> Cc: Hao Luo <haoluo@...gle.com>
> Cc: Jesper Dangaard Brouer <hawk@...nel.org>
> Cc: Jiri Olsa <jolsa@...nel.org>
> Cc: John Fastabend <john.fastabend@...il.com>
> Cc: KP Singh <kpsingh@...nel.org>
> Cc: Martin KaFai Lau <martin.lau@...ux.dev>
> Cc: Song Liu <song@...nel.org>
> Cc: Stanislav Fomichev <sdf@...gle.com>
> Cc: Toke Høiland-Jørgensen <toke@...hat.com>
> Cc: Yonghong Song <yonghong.song@...ux.dev>
> Cc: bpf@...r.kernel.org
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
> ---
>  include/linux/filter.h | 42 ++++++++++++++++++++++++++++++++-----
>  include/linux/sched.h  |  3 +++
>  kernel/bpf/cpumap.c    |  3 +++
>  kernel/fork.c          |  1 +
>  net/bpf/test_run.c     | 11 +++++++++-
>  net/core/dev.c         | 19 ++++++++++++++++-
>  net/core/filter.c      | 47 +++++++++++++++++++-----------------------
>  net/core/lwt_bpf.c     |  3 +++
>  8 files changed, 96 insertions(+), 33 deletions(-)
>
> diff --git a/include/linux/filter.h b/include/linux/filter.h
> index d5fea03cb6e61..6db5a68db6ee1 100644
> --- a/include/linux/filter.h
> +++ b/include/linux/filter.h
> @@ -744,7 +744,39 @@ struct bpf_redirect_info {
>  	struct bpf_nh_params nh;
>  };
>  
> -DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
> +struct bpf_net_context {
> +	struct bpf_redirect_info ri;
> +};
> +
> +static inline struct bpf_net_context *bpf_net_ctx_set(struct bpf_net_context *bpf_net_ctx)
> +{
> +	struct task_struct *tsk = current;
> +
> +	if (tsk->bpf_net_context != NULL)
> +		return NULL;
> +	tsk->bpf_net_context = bpf_net_ctx;
> +	return bpf_net_ctx;
> +}
> +
> +static inline void bpf_net_ctx_clear(struct bpf_net_context *bpf_net_ctx)
> +{
> +	if (bpf_net_ctx)
> +		current->bpf_net_context = NULL;
> +}
> +
> +static inline struct bpf_net_context *bpf_net_ctx_get(void)
> +{
> +	return current->bpf_net_context;
> +}
> +
> +static inline struct bpf_redirect_info *bpf_net_ctx_get_ri(void)
> +{
> +	struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get();
> +
> +	return &bpf_net_ctx->ri;
> +}
> +
> +DEFINE_FREE(bpf_net_ctx_clear, struct bpf_net_context *, bpf_net_ctx_clear(_T));
>  
>  /* flags for bpf_redirect_info kern_flags */
>  #define BPF_RI_F_RF_NO_DIRECT	BIT(0)	/* no napi_direct on return_frame */
> @@ -1021,21 +1053,21 @@ void bpf_clear_redirect_map(struct bpf_map *map);
>  
>  static inline bool xdp_return_frame_no_direct(void)
>  {
> -	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
> +	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
>  
>  	return ri->kern_flags & BPF_RI_F_RF_NO_DIRECT;
>  }
>  
>  static inline void xdp_set_return_frame_no_direct(void)
>  {
> -	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
> +	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
>  
>  	ri->kern_flags |= BPF_RI_F_RF_NO_DIRECT;
>  }
>  
>  static inline void xdp_clear_return_frame_no_direct(void)
>  {
> -	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
> +	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
>  
>  	ri->kern_flags &= ~BPF_RI_F_RF_NO_DIRECT;
>  }
> @@ -1591,7 +1623,7 @@ static __always_inline long __bpf_xdp_redirect_map(struct bpf_map *map, u64 inde
>  						   u64 flags, const u64 flag_mask,
>  						   void *lookup_elem(struct bpf_map *map, u32 key))
>  {
> -	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
> +	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
>  	const u64 action_mask = XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX;
>  
>  	/* Lower bits of the flags are used as return code on lookup failure */
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index 6779d3b8f2578..cc9be45de6606 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -53,6 +53,7 @@ struct bio_list;
>  struct blk_plug;
>  struct bpf_local_storage;
>  struct bpf_run_ctx;
> +struct bpf_net_context;
>  struct capture_control;
>  struct cfs_rq;
>  struct fs_struct;
> @@ -1504,6 +1505,8 @@ struct task_struct {
>  	/* Used for BPF run context */
>  	struct bpf_run_ctx		*bpf_ctx;
>  #endif
> +	/* Used by BPF for per-TASK xdp storage */
> +	struct bpf_net_context		*bpf_net_context;

Okay, so if we are going the route of always putting this in 'current',
why not just embed the whole struct bpf_net_context inside task_struct,
instead of mucking about with the stack-allocated structures and
setting/clearing of pointers?

-Toke

Powered by blists - more mailing lists