From: "Steven Rostedt (Google)" <rostedt@xxxxxxxxxxx> If an unused weak function was traced, it's call to fentry will still exist, which gets added into the __mcount_loc table. Ftrace will use kallsyms to retrieve the name for each location in __mcount_loc to display it in the available_filter_functions and used to enable functions via the name matching in set_ftrace_filter/notrace. Enabling these functions do nothing but enable an unused call to ftrace_caller. If a traced weak function is overridden, the symbol of the function would be used for it, which will either created duplicate names, or if the previous function was not traced, it would be incorrectly listed in available_filter_functions as a function that can be traced. This became an issue with BPF[1] as there are tooling that enables the direct callers via ftrace but then checks to see if the functions were actually enabled. The case of one function that was marked notrace, but was followed by an unused weak function that was traced. The unused function's call to fentry was added to the __mcount_loc section, and kallsyms retrieved the untraced function's symbol as the weak function was overridden. Since the untraced function would not get traced, the BPF check would detect this and fail. The real fix would be to fix kallsyms to not show address of weak functions as the function before it. But that would require adding code in the build to add function size to kallsyms so that it can know when the function ends instead of just using the start of the next known symbol. In the mean time, this is a work around. Add a FTRACE_MCOUNT_MAX_OFFSET macro that if defined, ftrace will ignore any function that has its call to fentry/mcount that has an offset from the symbol that is greater than FTRACE_MCOUNT_MAX_OFFSET. If CONFIG_HAVE_FENTRY is defined for x86, define FTRACE_MCOUNT_MAX_OFFSET to zero (unless IBT is enabled), which will have ftrace ignore all locations that are not at the start of the function (or one after the ENDBR instruction). [1] https://lore.kernel.org/all/20220412094923.0abe90955e5db486b7bca279@xxxxxxxxxx/ Acked-by: Ingo Molnar <mingo@xxxxxxxxxx> Signed-off-by: Steven Rostedt (Google) <rostedt@xxxxxxxxxxx> --- Changes since v3: https://lore.kernel.org/all/20220526103810.026560dd@xxxxxxxxxxxxxxxxxx/ - Implemented Peter Zijlstra's suggestion of using offset of ENDBR_INSN_SIZE for max on x86. arch/x86/include/asm/ftrace.h | 8 ++++++ kernel/trace/ftrace.c | 50 +++++++++++++++++++++++++++++++++-- 2 files changed, 56 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 024d9797646e..4c9bfdf4dae7 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -9,6 +9,14 @@ # define MCOUNT_ADDR ((unsigned long)(__fentry__)) #define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */ +#include <asm/ibt.h> + +/* Ignore unused weak functions which will have non zero offsets */ +#ifdef CONFIG_HAVE_FENTRY +/* Add offset for endbr64 if IBT enabled */ +# define FTRACE_MCOUNT_MAX_OFFSET ENDBR_INSN_SIZE +#endif + #ifdef CONFIG_DYNAMIC_FTRACE #define ARCH_SUPPORTS_FTRACE_OPS 1 #endif diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index d653ef4febc5..4a04eaf6436d 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3654,6 +3654,31 @@ static void add_trampoline_func(struct seq_file *m, struct ftrace_ops *ops, seq_printf(m, " ->%pS", ptr); } +#ifdef FTRACE_MCOUNT_MAX_OFFSET +static int print_rec(struct seq_file *m, unsigned long ip) +{ + unsigned long offset; + char str[KSYM_SYMBOL_LEN]; + char *modname; + int ret; + + ret = kallsyms_lookup(ip, NULL, &offset, &modname, str); + if (!ret || offset > FTRACE_MCOUNT_MAX_OFFSET) + return -1; + + seq_puts(m, str); + if (modname) + seq_printf(m, " [%s]", modname); + return 0; +} +#else +static int print_rec(struct seq_file *m, unsigned long ip) +{ + seq_printf(m, "%ps", (void *)ip); + return 0; +} +#endif + static int t_show(struct seq_file *m, void *v) { struct ftrace_iterator *iter = m->private; @@ -3678,7 +3703,9 @@ static int t_show(struct seq_file *m, void *v) if (!rec) return 0; - seq_printf(m, "%ps", (void *)rec->ip); + if (print_rec(m, rec->ip)) + return 0; + if (iter->flags & FTRACE_ITER_ENABLED) { struct ftrace_ops *ops; @@ -3996,6 +4023,24 @@ add_rec_by_index(struct ftrace_hash *hash, struct ftrace_glob *func_g, return 0; } +#ifdef FTRACE_MCOUNT_MAX_OFFSET +static int lookup_ip(unsigned long ip, char **modname, char *str) +{ + unsigned long offset; + + kallsyms_lookup(ip, NULL, &offset, modname, str); + if (offset > FTRACE_MCOUNT_MAX_OFFSET) + return -1; + return 0; +} +#else +static int lookup_ip(unsigned long ip, char **modname, char *str) +{ + kallsyms_lookup(ip, NULL, NULL, modname, str); + return 0; +} +#endif + static int ftrace_match_record(struct dyn_ftrace *rec, struct ftrace_glob *func_g, struct ftrace_glob *mod_g, int exclude_mod) @@ -4003,7 +4048,8 @@ ftrace_match_record(struct dyn_ftrace *rec, struct ftrace_glob *func_g, char str[KSYM_SYMBOL_LEN]; char *modname; - kallsyms_lookup(rec->ip, NULL, NULL, &modname, str); + if (lookup_ip(rec->ip, &modname, str)) + return 0; if (mod_g) { int mod_matches = (modname) ? ftrace_match(modname, mod_g) : 0; -- 2.35.1
