UPSTREAM: bpf: Fix nested bpf_bprintf_prepare with more per-cpu buffers

The bpf_seq_printf, bpf_trace_printk and bpf_snprintf helpers share one
per-cpu buffer that they use to store temporary data (arguments to
bprintf). They "get" that buffer with try_get_fmt_tmp_buf and "put" it
by the end of their scope with bpf_bprintf_cleanup.

If one of these helpers gets called within the scope of one of these
helpers, for example: a first bpf program gets called, uses
bpf_trace_printk which calls raw_spin_lock_irqsave which is traced by
another bpf program that calls bpf_snprintf, then the second "get"
fails. Essentially, these helpers are not re-entrant. They would return
-EBUSY and print a warning message once.

This patch triples the number of bprintf buffers to allow three levels
of nesting. This is very similar to what was done for tracepoints in
"9594dc3c7e7 bpf: fix nested bpf tracepoints with per-cpu data"

Fixes: d9c9e4db186a ("bpf: Factorize bpf_trace_printk and bpf_seq_printf")
Reported-by: syzbot+63122d0bc347f18c1884@syzkaller.appspotmail.com
Signed-off-by: Florent Revest <revest@chromium.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210511081054.2125874-1-revest@chromium.org
(cherry picked from commit e2d5b2bb769fa5f500760caba76436ba3a10a895)
Signed-off-by: Brendan Jackman <jackmanb@google.com>

SOURCE=UPSTREAM(e2d5b2bb769fa5f500760caba76436ba3a10a895)
BUG=b:217368493

Change-Id: Icfdcaeb3239ab365b2b4d0e8f17d18b131d88a41
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 6893bde..5636cbd 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -697,34 +697,35 @@
  */
 #define MAX_PRINTF_BUF_LEN	512
 
-struct bpf_printf_buf {
-	char tmp_buf[MAX_PRINTF_BUF_LEN];
+/* Support executing three nested bprintf helper calls on a given CPU */
+struct bpf_bprintf_buffers {
+	char tmp_bufs[3][MAX_PRINTF_BUF_LEN];
 };
-static DEFINE_PER_CPU(struct bpf_printf_buf, bpf_printf_buf);
-static DEFINE_PER_CPU(int, bpf_printf_buf_used);
+static DEFINE_PER_CPU(struct bpf_bprintf_buffers, bpf_bprintf_bufs);
+static DEFINE_PER_CPU(int, bpf_bprintf_nest_level);
 
 static int try_get_fmt_tmp_buf(char **tmp_buf)
 {
-	struct bpf_printf_buf *bufs;
-	int used;
+	struct bpf_bprintf_buffers *bufs;
+	int nest_level;
 
 	preempt_disable();
-	used = this_cpu_inc_return(bpf_printf_buf_used);
-	if (WARN_ON_ONCE(used > 1)) {
-		this_cpu_dec(bpf_printf_buf_used);
+	nest_level = this_cpu_inc_return(bpf_bprintf_nest_level);
+	if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(bufs->tmp_bufs))) {
+		this_cpu_dec(bpf_bprintf_nest_level);
 		preempt_enable();
 		return -EBUSY;
 	}
-	bufs = this_cpu_ptr(&bpf_printf_buf);
-	*tmp_buf = bufs->tmp_buf;
+	bufs = this_cpu_ptr(&bpf_bprintf_bufs);
+	*tmp_buf = bufs->tmp_bufs[nest_level - 1];
 
 	return 0;
 }
 
 void bpf_bprintf_cleanup(void)
 {
-	if (this_cpu_read(bpf_printf_buf_used)) {
-		this_cpu_dec(bpf_printf_buf_used);
+	if (this_cpu_read(bpf_bprintf_nest_level)) {
+		this_cpu_dec(bpf_bprintf_nest_level);
 		preempt_enable();
 	}
 }