From a9e3760b0838299649c0d57cca44daaf40ba3c33 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 14 Sep 2026 22:12:34 -1000 Subject: sched_ext: Maintain an online cid mask in the scheduler arena Schedulers on the default cid mapping treat [0, nr_online_cids) as the online set and restart on hotplug. Schedulers that install their own mapping with scx_bpf_cid_override() have no way to learn which cids are online: the count no longer identifies members and the CPU-form cpumask is unusable from cid programs. This is an obvious hole in the cid API. Add scx_bpf_online_cmask(), a kernel-maintained cmask in the scheduler's arena, allocated alongside the per-CPU scratch masks and populated after the cid mapping is finalized and before ops.init(), for child schedulers too. The pointer stays valid through ops.exit() with no reference to take. It is the arena offset as a void pointer, the same form struct_ops arena arguments arrive in. The verifier types the void return as a scalar for the program's arena cast. The mask follows the SCX hotplug notifications: seeded from cpu_active_mask and updated before ops.cid_online/offline() runs, so it lags cpu_online_mask only inside a hotplug transition. Updates walk the scheduler list under the lock that also serializes unlinking. Reads are live, not atomic snapshots. Root initialization excludes hotplug. v2: Reworded the getter kerneldoc (Andrea Righi). Signed-off-by: Tejun Heo Reviewed-by: Andrea Righi --- include/net/strparser.h | 170 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 170 insertions(+) create mode 100644 include/net/strparser.h (limited to 'include/net/strparser.h') diff --git a/include/net/strparser.h b/include/net/strparser.h new file mode 100644 index 000000000..0ed73e364 --- /dev/null +++ b/include/net/strparser.h @@ -0,0 +1,170 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Stream Parser + * + * Copyright (c) 2016 Tom Herbert + */ + +#ifndef __NET_STRPARSER_H_ +#define __NET_STRPARSER_H_ + +#include +#include + +#define STRP_STATS_ADD(stat, count) ((stat) += (count)) +#define STRP_STATS_INCR(stat) ((stat)++) + +struct strp_stats { + unsigned long long msgs; + unsigned long long bytes; + unsigned int mem_fail; + unsigned int need_more_hdr; + unsigned int msg_too_big; + unsigned int msg_timeouts; + unsigned int bad_hdr_len; +}; + +struct strp_aggr_stats { + unsigned long long msgs; + unsigned long long bytes; + unsigned int mem_fail; + unsigned int need_more_hdr; + unsigned int msg_too_big; + unsigned int msg_timeouts; + unsigned int bad_hdr_len; + unsigned int aborts; + unsigned int interrupted; + unsigned int unrecov_intr; +}; + +struct strparser; + +/* Callbacks are called with lock held for the attached socket */ +struct strp_callbacks { + int (*parse_msg)(struct strparser *strp, struct sk_buff *skb); + void (*rcv_msg)(struct strparser *strp, struct sk_buff *skb); + int (*read_sock)(struct strparser *strp, read_descriptor_t *desc, + sk_read_actor_t recv_actor); + int (*read_sock_done)(struct strparser *strp, int err); + void (*abort_parser)(struct strparser *strp, int err); + void (*lock)(struct strparser *strp); + void (*unlock)(struct strparser *strp); +}; + +struct strp_msg { + int full_len; + int offset; +}; + +struct _strp_msg { + /* Internal cb structure. struct strp_msg must be first for passing + * to upper layer. + */ + struct strp_msg strp; + int accum_len; +}; + +struct sk_skb_cb { +#define SK_SKB_CB_PRIV_LEN 20 + unsigned char data[SK_SKB_CB_PRIV_LEN]; + /* align strp on cache line boundary within skb->cb[] */ + unsigned char pad[4]; + struct _strp_msg strp; + + /* strp users' data follows */ + struct tls_msg { + u8 control; + } tls; + /* temp_reg is a temporary register used for bpf_convert_data_end_access + * when dst_reg == src_reg. + */ + u64 temp_reg; +}; + +static inline struct strp_msg *strp_msg(struct sk_buff *skb) +{ + return (struct strp_msg *)((void *)skb->cb + + offsetof(struct sk_skb_cb, strp)); +} + +/* Structure for an attached lower socket */ +struct strparser { + struct sock *sk; + + u32 stopped : 1; + u32 paused : 1; + u32 aborted : 1; + u32 interrupted : 1; + u32 unrecov_intr : 1; + + struct sk_buff **skb_nextp; + struct sk_buff *skb_head; + unsigned int need_bytes; + struct delayed_work msg_timer_work; + struct work_struct work; + struct strp_stats stats; + struct strp_callbacks cb; +}; + +/* Must be called with lock held for attached socket */ +static inline void strp_pause(struct strparser *strp) +{ + strp->paused = 1; +} + +/* May be called without holding lock for attached socket */ +void strp_unpause(struct strparser *strp); + +static inline void save_strp_stats(struct strparser *strp, + struct strp_aggr_stats *agg_stats) +{ + /* Save psock statistics in the mux when psock is being unattached. */ + +#define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += \ + strp->stats._stat) + SAVE_PSOCK_STATS(msgs); + SAVE_PSOCK_STATS(bytes); + SAVE_PSOCK_STATS(mem_fail); + SAVE_PSOCK_STATS(need_more_hdr); + SAVE_PSOCK_STATS(msg_too_big); + SAVE_PSOCK_STATS(msg_timeouts); + SAVE_PSOCK_STATS(bad_hdr_len); +#undef SAVE_PSOCK_STATS + + if (strp->aborted) + agg_stats->aborts++; + if (strp->interrupted) + agg_stats->interrupted++; + if (strp->unrecov_intr) + agg_stats->unrecov_intr++; +} + +static inline void aggregate_strp_stats(struct strp_aggr_stats *stats, + struct strp_aggr_stats *agg_stats) +{ +#define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += stats->_stat) + SAVE_PSOCK_STATS(msgs); + SAVE_PSOCK_STATS(bytes); + SAVE_PSOCK_STATS(mem_fail); + SAVE_PSOCK_STATS(need_more_hdr); + SAVE_PSOCK_STATS(msg_too_big); + SAVE_PSOCK_STATS(msg_timeouts); + SAVE_PSOCK_STATS(bad_hdr_len); + SAVE_PSOCK_STATS(aborts); + SAVE_PSOCK_STATS(interrupted); + SAVE_PSOCK_STATS(unrecov_intr); +#undef SAVE_PSOCK_STATS + +} + +void strp_done(struct strparser *strp); +void strp_stop(struct strparser *strp); +void strp_check_rcv(struct strparser *strp); +int strp_init(struct strparser *strp, struct sock *sk, + const struct strp_callbacks *cb); +void strp_data_ready(struct strparser *strp); +int strp_process(struct strparser *strp, struct sk_buff *orig_skb, + unsigned int orig_offset, size_t orig_len, + size_t max_msg_size, long timeo); + +#endif /* __NET_STRPARSER_H_ */ -- cgit v1.3.1