From 12628ffaf98b708a80857a462613119b9e16de4c Mon Sep 17 00:00:00 2001 From: Mykyta Yatsenko Date: Wed, 22 Apr 2026 12:41:07 -0700 Subject: bpf: Add bpf_prog_run_array_sleepable() Add bpf_prog_run_array_sleepable() for running BPF program arrays on faultable tracepoints. Unlike bpf_prog_run_array_uprobe(), it includes per-program recursion checking for private stack safety and hardcodes is_uprobe to false. Skip dummy_bpf_prog at the top of the loop. When bpf_prog_array_delete_safe() replaces a detached program with dummy_bpf_prog on allocation failure, the dummy is statically allocated and has NULL active, stats, and aux fields. Identify it by prog->len == 0, since every real program has at least one instruction. Keep bpf_prog_run_array_uprobe() unchanged for uprobe callers. Signed-off-by: Mykyta Yatsenko Acked-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/bpf/20260422-sleepable_tracepoints-v13-2-99005dff21ef@meta.com Signed-off-by: Kumar Kartikeya Dwivedi --- include/linux/bpf.h | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3cb6b9e70080..d3aea3931b85 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -3079,6 +3079,56 @@ void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr); void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr); void bpf_prog_report_arena_violation(bool write, unsigned long addr, unsigned long fault_ip); +static __always_inline u32 +bpf_prog_run_array_sleepable(const struct bpf_prog_array *array, + const void *ctx, bpf_prog_run_fn run_prog) +{ + const struct bpf_prog_array_item *item; + struct bpf_prog *prog; + struct bpf_run_ctx *old_run_ctx; + struct bpf_trace_run_ctx run_ctx; + u32 ret = 1; + + if (unlikely(!array)) + return ret; + + migrate_disable(); + + run_ctx.is_uprobe = false; + + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); + item = &array->items[0]; + while ((prog = READ_ONCE(item->prog))) { + /* Skip dummy_bpf_prog placeholder (len == 0) */ + if (unlikely(!prog->len)) { + item++; + continue; + } + + if (unlikely(!bpf_prog_get_recursion_context(prog))) { + bpf_prog_inc_misses_counter(prog); + bpf_prog_put_recursion_context(prog); + item++; + continue; + } + + run_ctx.bpf_cookie = item->bpf_cookie; + + if (!prog->sleepable) { + guard(rcu)(); + ret &= run_prog(prog, ctx); + } else { + ret &= run_prog(prog, ctx); + } + + bpf_prog_put_recursion_context(prog); + item++; + } + bpf_reset_run_ctx(old_run_ctx); + migrate_enable(); + return ret; +} + #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { -- cgit v1.2.3 From 57918341dd19e5ca8a77622ffae3db19e5ba4cc7 Mon Sep 17 00:00:00 2001 From: Mykyta Yatsenko Date: Wed, 22 Apr 2026 12:41:08 -0700 Subject: bpf: Add sleepable support for classic tracepoint programs Add trace_call_bpf_faultable(), a variant of trace_call_bpf() for faultable tracepoints that supports sleepable BPF programs. It uses rcu_tasks_trace for lifetime protection and bpf_prog_run_array_sleepable() for per-program RCU flavor selection, following the uprobe_prog_run() pattern. Restructure perf_syscall_enter() and perf_syscall_exit() to run BPF programs before perf event processing. Previously, BPF ran after the per-cpu perf trace buffer was allocated under preempt_disable, requiring cleanup via perf_swevent_put_recursion_context() on filter. Now BPF runs in faultable context before preempt_disable, reading syscall arguments from local variables instead of the per-cpu trace record, removing the dependency on buffer allocation. This allows sleepable BPF programs to execute and avoids unnecessary buffer allocation when BPF filters the event. The perf event submission path (buffer allocation, fill, submit) remains under preempt_disable as before. Since BPF no longer runs within the buffer allocation context, the fake_regs output parameter to perf_trace_buf_alloc() is no longer needed and is replaced with NULL. Add an attach-time check in __perf_event_set_bpf_prog() to reject sleepable BPF_PROG_TYPE_TRACEPOINT programs on non-syscall tracepoints, since only syscall tracepoints run in faultable context. This prepares the classic tracepoint runtime and attach paths for sleepable programs. The verifier changes to allow loading sleepable BPF_PROG_TYPE_TRACEPOINT programs are in a subsequent patch. To: Peter Zijlstra To: Steven Rostedt Signed-off-by: Mykyta Yatsenko Acked-by: Kumar Kartikeya Dwivedi # for BPF bits Acked-by: Steven Rostedt Link: https://lore.kernel.org/bpf/20260422-sleepable_tracepoints-v13-3-99005dff21ef@meta.com Signed-off-by: Kumar Kartikeya Dwivedi --- include/linux/trace_events.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 40a43a4c7caf..d49338c44014 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -770,6 +770,7 @@ trace_trigger_soft_disabled(struct trace_event_file *file) #ifdef CONFIG_BPF_EVENTS unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx); +unsigned int trace_call_bpf_faultable(struct trace_event_call *call, void *ctx); int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie); void perf_event_detach_bpf_prog(struct perf_event *event); int perf_event_query_prog_array(struct perf_event *event, void __user *info); @@ -792,6 +793,11 @@ static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *c return 1; } +static inline unsigned int trace_call_bpf_faultable(struct trace_event_call *call, void *ctx) +{ + return 1; +} + static inline int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie) { -- cgit v1.2.3