bpf: add support for %s specifier to bpf_trace_printk()

%s specifier makes bpf program and kernel debugging easier.
To make sure that trace_printk won't crash the unsafe string
is copied into stack and unsafe pointer is substituted.

The following C program:
 #include <linux/fs.h>
int foo(struct pt_regs *ctx, struct filename *filename)
{
  void *name = 0;

  bpf_probe_read(&name, sizeof(name), &filename->name);
  bpf_trace_printk("executed %s\n", name);
  return 0;
}

when attached to kprobe do_execve()
will produce output in /sys/kernel/debug/tracing/trace_pipe :
    make-13492 [002] d..1  3250.997277: : executed /bin/sh
      sh-13493 [004] d..1  3250.998716: : executed /usr/bin/gcc
     gcc-13494 [002] d..1  3250.999822: : executed /usr/lib/gcc/x86_64-linux-gnu/4.7/cc1
     gcc-13495 [002] d..1  3251.006731: : executed /usr/bin/as
     gcc-13496 [002] d..1  3251.011831: : executed /usr/lib/gcc/x86_64-linux-gnu/4.7/collect2
collect2-13497 [000] d..1  3251.012941: : executed /usr/bin/ld

Suggested-by: Brendan Gregg <brendan.d.gregg@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index ef9936df1b0491b5621501a495e5a20991aac4a7..0fe96c7c8803c759b963411198fa18153a539f46 100644 (file)
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -81,13 +81,16 @@ static const struct bpf_func_proto bpf_probe_read_proto = {
 
 /*
  * limited trace_printk()
- * only %d %u %x %ld %lu %lx %lld %llu %llx %p conversion specifiers allowed
+ * only %d %u %x %ld %lu %lx %lld %llu %llx %p %s conversion specifiers allowed
  */
 static u64 bpf_trace_printk(u64 r1, u64 fmt_size, u64 r3, u64 r4, u64 r5)
 {
        char *fmt = (char *) (long) r1;
+       bool str_seen = false;
        int mod[3] = {};
        int fmt_cnt = 0;
+       u64 unsafe_addr;
+       char buf[64];
        int i;
 
        /*
@@ -114,12 +117,37 @@ static u64 bpf_trace_printk(u64 r1, u64 fmt_size, u64 r3, u64 r4, u64 r5)
                if (fmt[i] == 'l') {
                        mod[fmt_cnt]++;
                        i++;
-               } else if (fmt[i] == 'p') {
+               } else if (fmt[i] == 'p' || fmt[i] == 's') {
                        mod[fmt_cnt]++;
                        i++;
                        if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0)
                                return -EINVAL;
                        fmt_cnt++;
+                       if (fmt[i - 1] == 's') {
+                               if (str_seen)
+                                       /* allow only one '%s' per fmt string */
+                                       return -EINVAL;
+                               str_seen = true;
+
+                               switch (fmt_cnt) {
+                               case 1:
+                                       unsafe_addr = r3;
+                                       r3 = (long) buf;
+                                       break;
+                               case 2:
+                                       unsafe_addr = r4;
+                                       r4 = (long) buf;
+                                       break;
+                               case 3:
+                                       unsafe_addr = r5;
+                                       r5 = (long) buf;
+                                       break;
+                               }
+                               buf[0] = 0;
+                               strncpy_from_unsafe(buf,
+                                                   (void *) (long) unsafe_addr,
+                                                   sizeof(buf));
+                       }
                        continue;
                }