[v6,bpf-next,3/9] bpf: add bpf_trace_vprintk helper

Commit Message

Dave Marchevsky Sept. 17, 2021, 6:29 p.m. UTC

This helper is meant to be "bpf_trace_printk, but with proper vararg
support". Follow bpf_snprintf's example and take a u64 pseudo-vararg
array. Write to /sys/kernel/debug/tracing/trace_pipe using the same
mechanism as bpf_trace_printk. The functionality of this helper was
requested in the libbpf issue tracker [0].

[0] Closes: https://github.com/libbpf/libbpf/issues/315

Signed-off-by: Dave Marchevsky <[e-mail]>
Acked-by: Andrii Nakryiko <[e-mail]>
---
 include/linux/bpf.h            |  1 +
 include/uapi/linux/bpf.h       | 11 +++++++
 kernel/bpf/core.c              |  5 ++++
 kernel/bpf/helpers.c           |  2 ++
 kernel/trace/bpf_trace.c       | 52 +++++++++++++++++++++++++++++++++-
 tools/include/uapi/linux/bpf.h | 11 +++++++
 6 files changed, 81 insertions(+), 1 deletion(-)

Patch

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index be8d57e6e78a..b6c45a6cbbba 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1088,6 +1088,7 @@  bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *f
 int bpf_prog_calc_tag(struct bpf_prog *fp);
 
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
+const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void);
 
 typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src,
 					unsigned long off, unsigned long len);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 3e9785f1064a..98ca79a67937 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4898,6 +4898,16 @@  union bpf_attr {
  *		**-EINVAL** if *flags* is not zero.
  *
  *		**-ENOENT** if architecture does not support branch records.
+ *
+ * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len)
+ *	Description
+ *		Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64
+ *		to format and can handle more format args as a result.
+ *
+ *		Arguments are to be used as in **bpf_seq_printf**\ () helper.
+ *	Return
+ *		The number of bytes written to the buffer, or a negative error
+ *		in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5077,6 +5087,7 @@  union bpf_attr {
 	FN(get_attach_cookie),		\
 	FN(task_pt_regs),		\
 	FN(get_branch_snapshot),	\
+	FN(trace_vprintk),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 9f4636d021b1..6fddc13fe67f 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2357,6 +2357,11 @@  const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
 	return NULL;
 }
 
+const struct bpf_func_proto * __weak bpf_get_trace_vprintk_proto(void)
+{
+	return NULL;
+}
+
 u64 __weak
 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 		 void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy)
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 8f9f392c1322..2c604ff8c7fb 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1435,6 +1435,8 @@  bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_snprintf_proto;
 	case BPF_FUNC_task_pt_regs:
 		return &bpf_task_pt_regs_proto;
+	case BPF_FUNC_trace_vprintk:
+		return bpf_get_trace_vprintk_proto();
 	default:
 		return NULL;
 	}
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 4ec779fa0c1d..6b3153841a33 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -398,7 +398,7 @@  static const struct bpf_func_proto bpf_trace_printk_proto = {
 	.arg2_type	= ARG_CONST_SIZE,
 };
 
-const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
+static void __set_printk_clr_event(void)
 {
 	/*
 	 * This program might be calling bpf_trace_printk,
@@ -410,10 +410,58 @@  const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
 	 */
 	if (trace_set_clr_event("bpf_trace", "bpf_trace_printk", 1))
 		pr_warn_ratelimited("could not enable bpf_trace_printk events");
+}
 
+const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
+{
+	__set_printk_clr_event();
 	return &bpf_trace_printk_proto;
 }
 
+BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, data,
+	   u32, data_len)
+{
+	static char buf[BPF_TRACE_PRINTK_SIZE];
+	unsigned long flags;
+	int ret, num_args;
+	u32 *bin_args;
+
+	if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 ||
+	    (data_len && !data))
+		return -EINVAL;
+	num_args = data_len / 8;
+
+	ret = bpf_bprintf_prepare(fmt, fmt_size, data, &bin_args, num_args);
+	if (ret < 0)
+		return ret;
+
+	raw_spin_lock_irqsave(&trace_printk_lock, flags);
+	ret = bstr_printf(buf, sizeof(buf), fmt, bin_args);
+
+	trace_bpf_trace_printk(buf);
+	raw_spin_unlock_irqrestore(&trace_printk_lock, flags);
+
+	bpf_bprintf_cleanup();
+
+	return ret;
+}
+
+static const struct bpf_func_proto bpf_trace_vprintk_proto = {
+	.func		= bpf_trace_vprintk,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_PTR_TO_MEM_OR_NULL,
+	.arg4_type	= ARG_CONST_SIZE_OR_ZERO,
+};
+
+const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void)
+{
+	__set_printk_clr_event();
+	return &bpf_trace_vprintk_proto;
+}
+
 BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size,
 	   const void *, data, u32, data_len)
 {
@@ -1160,6 +1208,8 @@  bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_func_ip_proto_tracing;
 	case BPF_FUNC_get_branch_snapshot:
 		return &bpf_get_branch_snapshot_proto;
+	case BPF_FUNC_trace_vprintk:
+		return bpf_get_trace_vprintk_proto();
 	default:
 		return bpf_base_func_proto(func_id);
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 3e9785f1064a..98ca79a67937 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4898,6 +4898,16 @@  union bpf_attr {
  *		**-EINVAL** if *flags* is not zero.
  *
  *		**-ENOENT** if architecture does not support branch records.
+ *
+ * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len)
+ *	Description
+ *		Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64
+ *		to format and can handle more format args as a result.
+ *
+ *		Arguments are to be used as in **bpf_seq_printf**\ () helper.
+ *	Return
+ *		The number of bytes written to the buffer, or a negative error
+ *		in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5077,6 +5087,7 @@  union bpf_attr {
 	FN(get_attach_cookie),		\
 	FN(task_pt_regs),		\
 	FN(get_branch_snapshot),	\
+	FN(trace_vprintk),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper