When tracing user functions with uprobe functionality, it's common to install the probe (e.g., a BPF program) at the first instruction of the function. This is often going to be `push %rbp` instruction in function preamble, which means that within that function frame pointer hasn't been established yet. This leads to consistently missing an actual caller of the traced function, because perf_callchain_user() only records current IP (capturing traced function) and then following frame pointer chain (which would be caller's frame, containing the address of caller's caller).
So when we have target_1 -> target_2 -> target_3 call chain and we are tracing an entry to target_3, captured stack trace will report target_1 -> target_3 call chain, which is wrong and confusing. This patch proposes a x86-64-specific heuristic to detect `push %rbp` (`push %ebp` on 32-bit architecture) instruction being traced. Given entire kernel implementation of user space stack trace capturing works under assumption that user space code was compiled with frame pointer register (%rbp/%ebp) preservation, it seems pretty reasonable to use this instruction as a strong indicator that this is the entry to the function. In that case, return address is still pointed to by %rsp/%esp, so we fetch it and add to stack trace before proceeding to unwind the rest using frame pointer-based logic. Signed-off-by: Andrii Nakryiko <and...@kernel.org> --- v1->v2: - use native unsigned long for ret_addr (Peter); - add same logic for compat logic in perf_callchain_user32 (Peter). arch/x86/events/core.c | 33 +++++++++++++++++++++++++++++++++ include/linux/uprobes.h | 2 ++ kernel/events/uprobes.c | 2 ++ 3 files changed, 37 insertions(+) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 5b0dd07b1ef1..60821c1ff2f3 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2833,6 +2833,19 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent fp = compat_ptr(ss_base + regs->bp); pagefault_disable(); + +#ifdef CONFIG_UPROBES + /* see perf_callchain_user() below for why we do this */ + if (current->utask) { + struct arch_uprobe *auprobe = current->utask->auprobe; + u32 ret_addr; + + if (auprobe && auprobe->insn[0] == 0x55 /* push %ebp */ && + !__get_user(ret_addr, (const u32 __user *)regs->sp)) + perf_callchain_store(entry, ret_addr); + } +#endif + while (entry->nr < entry->max_stack) { if (!valid_user_frame(fp, sizeof(frame))) break; @@ -2884,6 +2897,26 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs return; pagefault_disable(); + +#ifdef CONFIG_UPROBES + /* + * If we are called from uprobe handler, and we are indeed at the very + * entry to user function (which is normally a `push %rbp` instruction, + * under assumption of application being compiled with frame pointers), + * we should read return address from *regs->sp before proceeding + * to follow frame pointers, otherwise we'll skip immediate caller + * as %rbp is not yet setup. + */ + if (current->utask) { + struct arch_uprobe *auprobe = current->utask->auprobe; + unsigned long ret_addr; + + if (auprobe && auprobe->insn[0] == 0x55 /* push %rbp/%ebp */ && + !__get_user(ret_addr, (const unsigned long __user *)regs->sp)) + perf_callchain_store(entry, ret_addr); + } +#endif + while (entry->nr < entry->max_stack) { if (!valid_user_frame(fp, sizeof(frame))) break; diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index b503fafb7fb3..a270a5892ab4 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -76,6 +76,8 @@ struct uprobe_task { struct uprobe *active_uprobe; unsigned long xol_vaddr; + struct arch_uprobe *auprobe; + struct return_instance *return_instances; unsigned int depth; }; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 99be2adedbc0..6e22e4d80f1e 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -2082,6 +2082,7 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs) bool need_prep = false; /* prepare return uprobe, when needed */ down_read(&uprobe->register_rwsem); + current->utask->auprobe = &uprobe->arch; for (uc = uprobe->consumers; uc; uc = uc->next) { int rc = 0; @@ -2096,6 +2097,7 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs) remove &= rc; } + current->utask->auprobe = NULL; if (need_prep && !remove) prepare_uretprobe(uprobe, regs); /* put bp at return */ -- 2.43.0