[v3,bpf-next,3/7] libbpf: Modify bpf_printk to choose helper based on arg count

Instead of being a thin wrapper which calls into bpf_trace_printk,
libbpf's bpf_printk convenience macro now chooses between
bpf_trace_printk and bpf_trace_vprintk. If the arg count (excluding
format string) is >3, use bpf_trace_vprintk, otherwise use the older
helper.

The motivation behind this added complexity - instead of migrating
entirely to bpf_trace_vprintk - is to maintain good developer experience
for users compiling against new libbpf but running on older kernels.
Users who are passing <=3 args to bpf_printk will see no change in their
bytecode.

__bpf_vprintk functions similarly to BPF_SEQ_PRINTF and BPF_SNPRINTF
macros elsewhere in the file - it allows use of bpf_trace_vprintk
without manual conversion of varargs to u64 array. Previous
implementation of bpf_printk macro is moved to __bpf_printk for use by
the new implementation.

This does change behavior of bpf_printk calls with >3 args in the "new
libbpf, old kernels" scenario. Before this patch, attempting to use 4
args to bpf_printk results in a compile-time error. After this patch,
using bpf_printk with 4 args results in a trace_vprintk helper call
being emitted and a load-time failure on older kernels.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
---
 tools/lib/bpf/bpf_helpers.h | 45 ++++++++++++++++++++++++++++++-------
 1 file changed, 37 insertions(+), 8 deletions(-)

On 8/28/21 1:20 AM, Dave Marchevsky wrote:   
> Instead of being a thin wrapper which calls into bpf_trace_printk,
> libbpf's bpf_printk convenience macro now chooses between
> bpf_trace_printk and bpf_trace_vprintk. If the arg count (excluding
> format string) is >3, use bpf_trace_vprintk, otherwise use the older
> helper.
> 
> The motivation behind this added complexity - instead of migrating
> entirely to bpf_trace_vprintk - is to maintain good developer experience
> for users compiling against new libbpf but running on older kernels.
> Users who are passing <=3 args to bpf_printk will see no change in their
> bytecode.
> 
> __bpf_vprintk functions similarly to BPF_SEQ_PRINTF and BPF_SNPRINTF
> macros elsewhere in the file - it allows use of bpf_trace_vprintk
> without manual conversion of varargs to u64 array. Previous
> implementation of bpf_printk macro is moved to __bpf_printk for use by
> the new implementation.
> 
> This does change behavior of bpf_printk calls with >3 args in the "new
> libbpf, old kernels" scenario. Before this patch, attempting to use 4
> args to bpf_printk results in a compile-time error. After this patch,
> using bpf_printk with 4 args results in a trace_vprintk helper call
> being emitted and a load-time failure on older kernels.
> 
> Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
> ---
>  tools/lib/bpf/bpf_helpers.h | 45 ++++++++++++++++++++++++++++++-------
>  1 file changed, 37 insertions(+), 8 deletions(-)
> 
> diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
> index b9987c3efa3c..5f087306cdfe 100644
> --- a/tools/lib/bpf/bpf_helpers.h
> +++ b/tools/lib/bpf/bpf_helpers.h
> @@ -14,14 +14,6 @@
>  #define __type(name, val) typeof(val) *name
>  #define __array(name, val) typeof(val) *name[]
>  
> -/* Helper macro to print out debug messages */
> -#define bpf_printk(fmt, ...)				\
> -({							\
> -	char ____fmt[] = fmt;				\
> -	bpf_trace_printk(____fmt, sizeof(____fmt),	\
> -			 ##__VA_ARGS__);		\
> -})
> -
>  /*
>   * Helper macro to place programs, maps, license in
>   * different sections in elf_bpf file. Section names
> @@ -224,4 +216,41 @@ enum libbpf_tristate {
>  		     ___param, sizeof(___param));		\
>  })
>  
> +/* Helper macro to print out debug messages */
> +#define __bpf_printk(fmt, ...)				\
> +({							\
> +	char ____fmt[] = fmt;				\
> +	bpf_trace_printk(____fmt, sizeof(____fmt),	\
> +			 ##__VA_ARGS__);		\
> +})
> +
> +/*
> + * __bpf_vprintk wraps the bpf_trace_vprintk helper with variadic arguments
> + * instead of an array of u64.
> + */
> +#define __bpf_vprintk(fmt, args...)				\
> +({								\
> +	static const char ___fmt[] = fmt;			\
> +	unsigned long long ___param[___bpf_narg(args)];		\
> +								\
> +	_Pragma("GCC diagnostic push")				\
> +	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")	\
> +	___bpf_fill(___param, args);				\
> +	_Pragma("GCC diagnostic pop")				\
> +								\
> +	bpf_trace_vprintk(___fmt, sizeof(___fmt),		\
> +		     ___param, sizeof(___param));		\
> +})
> +
> +#define ___bpf_pick_printk(...) \
> +	___bpf_nth(_, ##__VA_ARGS__, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk,	\
> +		__bpf_vprintk, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk,		\
> +		__bpf_vprintk, __bpf_vprintk, __bpf_printk, __bpf_printk,		\
> +		__bpf_printk, __bpf_printk)
> +
> +#define bpf_printk(fmt, args...)		\
> +({						\
> +	___bpf_pick_printk(args)(fmt, args);	\

While looking at test failure related to patch 4, noticed
that this isn't handling 0 format arg case correctly, resulting
in compilation error.

Need to fix and add a test as all extant selftests are doing
bpf_printk with at least 1 format arg.

> +})
> +
>  #endif
>