On Wed, Apr 14, 2021 at 11:54 AM Florent Revest <revest@xxxxxxxxxxxx> wrote:
>
> Two helpers (trace_printk and seq_printf) have very similar
> implementations of format string parsing and a third one is coming
> (snprintf). To avoid code duplication and make the code easier to
> maintain, this moves the operations associated with format string
> parsing (validation and argument sanitization) into one generic
> function.
>
> The implementation of the two existing helpers already drifted quite a
> bit so unifying them entailed a lot of changes:
>
> - bpf_trace_printk always expected fmt[fmt_size] to be the terminating
> NULL character, this is no longer true, the first 0 is terminating.
> - bpf_trace_printk now supports %% (which produces the percentage char).
> - bpf_trace_printk now skips width formating fields.
> - bpf_trace_printk now supports the X modifier (capital hexadecimal).
> - bpf_trace_printk now supports %pK, %px, %pB, %pi4, %pI4, %pi6 and %pI6
> - argument casting on 32 bit has been simplified into one macro and
> using an enum instead of obscure int increments.
>
> - bpf_seq_printf now uses bpf_trace_copy_string instead of
> strncpy_from_kernel_nofault and handles the %pks %pus specifiers.
> - bpf_seq_printf now prints longs correctly on 32 bit architectures.
>
> - both were changed to use a global per-cpu tmp buffer instead of one
> stack buffer for trace_printk and 6 small buffers for seq_printf.
> - to avoid per-cpu buffer usage conflict, these helpers disable
> preemption while the per-cpu buffer is in use.
> - both helpers now support the %ps and %pS specifiers to print symbols.
>
> The implementation is also moved from bpf_trace.c to helpers.c because
> the upcoming bpf_snprintf helper will be made available to all BPF
> programs and will need it.
>
> Signed-off-by: Florent Revest <revest@xxxxxxxxxxxx>
> ---
> include/linux/bpf.h | 20 +++
> kernel/bpf/helpers.c | 254 +++++++++++++++++++++++++++
> kernel/trace/bpf_trace.c | 371 ++++-----------------------------------
> 3 files changed, 311 insertions(+), 334 deletions(-)
>
[...]
> +static int try_get_fmt_tmp_buf(char **tmp_buf)
> +{
> + struct bpf_printf_buf *bufs;
> + int used;
> +
> + if (*tmp_buf)
> + return 0;
> +
> + preempt_disable();
> + used = this_cpu_inc_return(bpf_printf_buf_used);
> + if (WARN_ON_ONCE(used > 1)) {
> + this_cpu_dec(bpf_printf_buf_used);
this makes me uncomfortable. If used > 1, you won't preempt_enable()
here, but you'll decrease count. Then later bpf_printf_cleanup() will
be called (inside bpf_printf_prepare()) and will further decrease
count (which it didn't increase, so it's a mess now).
> + return -EBUSY;
> + }
> + bufs = this_cpu_ptr(&bpf_printf_buf);
> + *tmp_buf = bufs->tmp_buf;
> +
> + return 0;
> +}
> +
[...]
> + i += 2;
> + if (!final_args)
> + goto fmt_next;
> +
> + if (try_get_fmt_tmp_buf(&tmp_buf)) {
> + err = -EBUSY;
> + goto out;
this probably should bypass doing bpf_printf_cleanup() and
try_get_fmt_tmp_buf() should enable preemption internally on error.
> + }
> +
> + copy_size = (fmt[i + 2] == '4') ? 4 : 16;
> + if (tmp_buf_len < copy_size) {
> + err = -ENOSPC;
> + goto out;
> + }
> +
[...]
> -static __printf(1, 0) int bpf_do_trace_printk(const char *fmt, ...)
> +BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
> + u64, arg2, u64, arg3)
> {
> + u64 args[MAX_TRACE_PRINTK_VARARGS] = { arg1, arg2, arg3 };
> + enum bpf_printf_mod_type mod[MAX_TRACE_PRINTK_VARARGS];
> static char buf[BPF_TRACE_PRINTK_SIZE];
> unsigned long flags;
> - va_list ap;
> int ret;
>
> - raw_spin_lock_irqsave(&trace_printk_lock, flags);
> - va_start(ap, fmt);
> - ret = vsnprintf(buf, sizeof(buf), fmt, ap);
> - va_end(ap);
> - /* vsnprintf() will not append null for zero-length strings */
> + ret = bpf_printf_prepare(fmt, fmt_size, args, args, mod,
> + MAX_TRACE_PRINTK_VARARGS);
> + if (ret < 0)
> + return ret;
> +
> + ret = snprintf(buf, sizeof(buf), fmt, BPF_CAST_FMT_ARG(0, args, mod),
> + BPF_CAST_FMT_ARG(1, args, mod), BPF_CAST_FMT_ARG(2, args, mod));
> + /* snprintf() will not append null for zero-length strings */
> if (ret == 0)
> buf[0] = '\0';
> +
> + raw_spin_lock_irqsave(&trace_printk_lock, flags);
> trace_bpf_trace_printk(buf);
> raw_spin_unlock_irqrestore(&trace_printk_lock, flags);
>
> - return ret;
see here, no + 1 :(
> -}
> -
> -/*
> - * Only limited trace_printk() conversion specifiers allowed:
> - * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %pB %pks %pus %s
> - */
[...]
