From a7e745e082462d017bf95009775ba4a0542f0c3f Mon Sep 17 00:00:00 2001 From: Tao Chen Date: Mon, 10 Nov 2025 00:35:57 +0800 Subject: [PATCH 1/3] perf: Refactor get_perf_callchain From BPF stack map, we want to ensure that the callchain buffer will not be overwritten by other preemptive tasks. Peter suggested provide more flexible stack-sampling APIs, which can be used in BPF, and we can still use the perf callchain entry with the help of these APIs. The next patch will modify the BPF part. In the future, these APIs will also make it convenient for us to add stack-sampling kfuncs in the eBPF subsystem, just as Andrii and Alexei discussed earlier. Signed-off-by: Peter Zijlstra Signed-off-by: Tao Chen --- include/linux/perf_event.h | 9 +++++ kernel/events/callchain.c | 73 ++++++++++++++++++++++++-------------- 2 files changed, 56 insertions(+), 26 deletions(-) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index fd1d91017b99b..edd3058e4d839 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -67,6 +67,7 @@ struct perf_callchain_entry_ctx { u32 nr; short contexts; bool contexts_maxed; + bool add_mark; }; typedef unsigned long (*perf_copy_f)(void *dst, const void *src, @@ -1718,6 +1719,14 @@ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry); extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); + +extern void __init_perf_callchain_ctx(struct perf_callchain_entry_ctx *ctx, + struct perf_callchain_entry *entry, + u32 max_stack, bool add_mark); + +extern void __get_perf_callchain_kernel(struct perf_callchain_entry_ctx *ctx, struct pt_regs *regs); +extern void __get_perf_callchain_user(struct perf_callchain_entry_ctx *ctx, struct pt_regs *regs); + extern struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark); diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index 808c0d7a31faf..fb1f26be29749 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -216,13 +216,54 @@ static void fixup_uretprobe_trampoline_entries(struct perf_callchain_entry *entr #endif } +void __init_perf_callchain_ctx(struct perf_callchain_entry_ctx *ctx, + struct perf_callchain_entry *entry, + u32 max_stack, bool add_mark) + +{ + ctx->entry = entry; + ctx->max_stack = max_stack; + ctx->nr = entry->nr = 0; + ctx->contexts = 0; + ctx->contexts_maxed = false; + ctx->add_mark = add_mark; +} + +void __get_perf_callchain_kernel(struct perf_callchain_entry_ctx *ctx, struct pt_regs *regs) +{ + if (user_mode(regs)) + return; + + if (ctx->add_mark) + perf_callchain_store_context(ctx, PERF_CONTEXT_KERNEL); + perf_callchain_kernel(ctx, regs); +} + +void __get_perf_callchain_user(struct perf_callchain_entry_ctx *ctx, struct pt_regs *regs) +{ + int start_entry_idx; + + if (!user_mode(regs)) { + if (current->flags & (PF_KTHREAD | PF_USER_WORKER)) + return; + regs = task_pt_regs(current); + } + + if (ctx->add_mark) + perf_callchain_store_context(ctx, PERF_CONTEXT_USER); + + start_entry_idx = ctx->nr; + perf_callchain_user(ctx, regs); + fixup_uretprobe_trampoline_entries(ctx->entry, start_entry_idx); +} + struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark) { struct perf_callchain_entry *entry; struct perf_callchain_entry_ctx ctx; - int rctx, start_entry_idx; + int rctx; /* crosstask is not supported for user stacks */ if (crosstask && user && !kernel) @@ -232,34 +273,14 @@ get_perf_callchain(struct pt_regs *regs, bool kernel, bool user, if (!entry) return NULL; - ctx.entry = entry; - ctx.max_stack = max_stack; - ctx.nr = entry->nr = 0; - ctx.contexts = 0; - ctx.contexts_maxed = false; + __init_perf_callchain_ctx(&ctx, entry, max_stack, add_mark); - if (kernel && !user_mode(regs)) { - if (add_mark) - perf_callchain_store_context(&ctx, PERF_CONTEXT_KERNEL); - perf_callchain_kernel(&ctx, regs); - } - - if (user && !crosstask) { - if (!user_mode(regs)) { - if (current->flags & (PF_KTHREAD | PF_USER_WORKER)) - goto exit_put; - regs = task_pt_regs(current); - } + if (kernel) + __get_perf_callchain_kernel(&ctx, regs); - if (add_mark) - perf_callchain_store_context(&ctx, PERF_CONTEXT_USER); - - start_entry_idx = entry->nr; - perf_callchain_user(&ctx, regs); - fixup_uretprobe_trampoline_entries(entry, start_entry_idx); - } + if (user && !crosstask) + __get_perf_callchain_user(&ctx, regs); -exit_put: put_callchain_entry(rctx); return entry; From 43580de1683b7c39c3ca790811aaaa9ed5e56dec Mon Sep 17 00:00:00 2001 From: Tao Chen Date: Mon, 10 Nov 2025 00:35:58 +0800 Subject: [PATCH 2/3] perf: Add atomic operation in get_recursion_context From BPF side, preemption usually is enabled. Yonghong said, it is possible that both tasks (at process level) may reach right before "recursion[rctx]++;". In such cases, both tasks will be able to get buffer and this is not right. Signed-off-by: Yonghong Song Signed-off-by: Tao Chen --- kernel/events/internal.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/kernel/events/internal.h b/kernel/events/internal.h index d9cc570830918..684bde972bad5 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -214,12 +214,9 @@ static inline int get_recursion_context(u8 *recursion) { unsigned char rctx = interrupt_context_level(); - if (recursion[rctx]) + if (cmpxchg(&recursion[rctx], 0, 1) != 0) return -1; - recursion[rctx]++; - barrier(); - return rctx; } From feac7848785de45ef88cbc9ceb6e4d1d0cc119a7 Mon Sep 17 00:00:00 2001 From: Tao Chen Date: Mon, 10 Nov 2025 00:35:59 +0800 Subject: [PATCH 3/3] bpf: Hold the perf callchain entry until used completely As Alexei noted, get_perf_callchain() return values may be reused if a task is preempted after the BPF program enters migrate disable mode. The perf_callchain_entres has a small stack of entries, and we can reuse it as follows: 1. get the perf callchain entry 2. BPF use... 3. put the perf callchain entry Signed-off-by: Tao Chen --- kernel/bpf/stackmap.c | 62 ++++++++++++++++++++++++++++++++++--------- 1 file changed, 50 insertions(+), 12 deletions(-) diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 2365541c81dd1..58b4432ab00e1 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -210,13 +210,12 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, } static struct perf_callchain_entry * -get_callchain_entry_for_task(struct task_struct *task, u32 max_depth) +get_callchain_entry_for_task(int *rctx, struct task_struct *task, u32 max_depth) { #ifdef CONFIG_STACKTRACE struct perf_callchain_entry *entry; - int rctx; - entry = get_callchain_entry(&rctx); + entry = get_callchain_entry(rctx); if (!entry) return NULL; @@ -238,8 +237,6 @@ get_callchain_entry_for_task(struct task_struct *task, u32 max_depth) to[i] = (u64)(from[i]); } - put_callchain_entry(rctx); - return entry; #else /* CONFIG_STACKTRACE */ return NULL; @@ -320,6 +317,31 @@ static long __bpf_get_stackid(struct bpf_map *map, return id; } +static struct perf_callchain_entry * +bpf_get_perf_callchain(int *rctx, struct pt_regs *regs, bool kernel, bool user, + int max_stack, bool crosstask) +{ + struct perf_callchain_entry_ctx ctx; + struct perf_callchain_entry *entry; + + entry = get_callchain_entry(rctx); + if (unlikely(!entry)) + return NULL; + + __init_perf_callchain_ctx(&ctx, entry, max_stack, false); + if (kernel) + __get_perf_callchain_kernel(&ctx, regs); + if (user && !crosstask) + __get_perf_callchain_user(&ctx, regs); + + return entry; +} + +static void bpf_put_perf_callchain(int rctx) +{ + put_callchain_entry(rctx); +} + BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, u64, flags) { @@ -328,20 +350,24 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, struct perf_callchain_entry *trace; bool kernel = !user; u32 max_depth; + int rctx, ret; if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID))) return -EINVAL; max_depth = stack_map_calculate_max_depth(map->value_size, elem_size, flags); - trace = get_perf_callchain(regs, kernel, user, max_depth, - false, false); + trace = bpf_get_perf_callchain(&rctx, regs, kernel, user, max_depth, + false); if (unlikely(!trace)) /* couldn't fetch the stack trace */ return -EFAULT; - return __bpf_get_stackid(map, trace, flags); + ret = __bpf_get_stackid(map, trace, flags); + bpf_put_perf_callchain(rctx); + + return ret; } const struct bpf_func_proto bpf_get_stackid_proto = { @@ -435,6 +461,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, bool kernel = !user; int err = -EINVAL; u64 *ips; + int rctx; if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | BPF_F_USER_BUILD_ID))) @@ -467,18 +494,26 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, trace = trace_in; trace->nr = min_t(u32, trace->nr, max_depth); } else if (kernel && task) { - trace = get_callchain_entry_for_task(task, max_depth); + trace = get_callchain_entry_for_task(&rctx, task, max_depth); } else { - trace = get_perf_callchain(regs, kernel, user, max_depth, - crosstask, false); + trace = bpf_get_perf_callchain(&rctx, regs, kernel, user, max_depth, + crosstask); } - if (unlikely(!trace) || trace->nr < skip) { + if (unlikely(!trace)) { if (may_fault) rcu_read_unlock(); goto err_fault; } + if (trace->nr < skip) { + if (may_fault) + rcu_read_unlock(); + if (!trace_in) + bpf_put_perf_callchain(rctx); + goto err_fault; + } + trace_nr = trace->nr - skip; copy_len = trace_nr * elem_size; @@ -497,6 +532,9 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, if (may_fault) rcu_read_unlock(); + if (!trace_in) + bpf_put_perf_callchain(rctx); + if (user_build_id) stack_map_get_build_id_offset(buf, trace_nr, user, may_fault);