BPF Archive on lore.kernel.org
 help / color / Atom feed
From: Yonghong Song <yhs@fb.com>
To: "Daniel T. Lee" <danieltimlee@gmail.com>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Alexei Starovoitov <ast@kernel.org>
Cc: "netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	"bpf@vger.kernel.org" <bpf@vger.kernel.org>
Subject: Re: [bpf-next,v4] samples: bpf: add max_pckt_size option at xdp_adjust_tail
Date: Mon, 16 Sep 2019 16:07:10 +0000
Message-ID: <d6b935ae-64a7-a375-9825-72eaebafd8a4@fb.com> (raw)
In-Reply-To: <20190915124733.31134-1-danieltimlee@gmail.com>



On 9/15/19 1:47 PM, Daniel T. Lee wrote:
> Currently, at xdp_adjust_tail_kern.c, MAX_PCKT_SIZE is limited
> to 600. To make this size flexible, a new map 'pcktsz' is added.
> 
> By updating new packet size to this map from the userland,
> xdp_adjust_tail_kern.o will use this value as a new max_pckt_size.
> 
> If no '-P <MAX_PCKT_SIZE>' option is used, the size of maximum packet
> will be 600 as a default.
> 
> Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com>
> 
> ---
> Changes in v4:
>      - make pckt_size no less than ICMP_TOOBIG_SIZE
>      - Fix code style
> Changes in v2:
>      - Change the helper to fetch map from 'bpf_map__next' to
>      'bpf_object__find_map_fd_by_name'.
> 
>   samples/bpf/xdp_adjust_tail_kern.c | 23 +++++++++++++++++++----
>   samples/bpf/xdp_adjust_tail_user.c | 28 ++++++++++++++++++++++------
>   2 files changed, 41 insertions(+), 10 deletions(-)

LGTM except a minor comments below.
Acked-by: Yonghong Song <yhs@fb.com>

bpf-next is closed. Please resubmit the patch once it is opened
in around 2 weeks.

> 
> diff --git a/samples/bpf/xdp_adjust_tail_kern.c b/samples/bpf/xdp_adjust_tail_kern.c
> index 411fdb21f8bc..8869bbb160d2 100644
> --- a/samples/bpf/xdp_adjust_tail_kern.c
> +++ b/samples/bpf/xdp_adjust_tail_kern.c
> @@ -25,6 +25,13 @@
>   #define ICMP_TOOBIG_SIZE 98
>   #define ICMP_TOOBIG_PAYLOAD_SIZE 92
>   
> +struct bpf_map_def SEC("maps") pcktsz = {
> +	.type = BPF_MAP_TYPE_ARRAY,
> +	.key_size = sizeof(__u32),
> +	.value_size = sizeof(__u32),
> +	.max_entries = 1,
> +};
> +
>   struct bpf_map_def SEC("maps") icmpcnt = {
>   	.type = BPF_MAP_TYPE_ARRAY,
>   	.key_size = sizeof(__u32),
> @@ -64,7 +71,8 @@ static __always_inline void ipv4_csum(void *data_start, int data_size,
>   	*csum = csum_fold_helper(*csum);
>   }
>   
> -static __always_inline int send_icmp4_too_big(struct xdp_md *xdp)
> +static __always_inline int send_icmp4_too_big(struct xdp_md *xdp,
> +					      __u32 max_pckt_size)
>   {
>   	int headroom = (int)sizeof(struct iphdr) + (int)sizeof(struct icmphdr);
>   
> @@ -92,7 +100,7 @@ static __always_inline int send_icmp4_too_big(struct xdp_md *xdp)
>   	orig_iph = data + off;
>   	icmp_hdr->type = ICMP_DEST_UNREACH;
>   	icmp_hdr->code = ICMP_FRAG_NEEDED;
> -	icmp_hdr->un.frag.mtu = htons(MAX_PCKT_SIZE-sizeof(struct ethhdr));
> +	icmp_hdr->un.frag.mtu = htons(max_pckt_size - sizeof(struct ethhdr));
>   	icmp_hdr->checksum = 0;
>   	ipv4_csum(icmp_hdr, ICMP_TOOBIG_PAYLOAD_SIZE, &csum);
>   	icmp_hdr->checksum = csum;
> @@ -118,14 +126,21 @@ static __always_inline int handle_ipv4(struct xdp_md *xdp)
>   {
>   	void *data_end = (void *)(long)xdp->data_end;
>   	void *data = (void *)(long)xdp->data;
> +	__u32 max_pckt_size = MAX_PCKT_SIZE;
>   	int pckt_size = data_end - data;
> +	__u32 *pckt_sz;
> +	__u32 key = 0;
>   	int offset;
>   
> -	if (pckt_size > MAX_PCKT_SIZE) {
> +	pckt_sz = bpf_map_lookup_elem(&pcktsz, &key);
> +	if (pckt_sz && *pckt_sz)
> +		max_pckt_size = *pckt_sz;
> +
> +	if (pckt_size > max(max_pckt_size, ICMP_TOOBIG_SIZE)) {
>   		offset = pckt_size - ICMP_TOOBIG_SIZE;
>   		if (bpf_xdp_adjust_tail(xdp, 0 - offset))
>   			return XDP_PASS;
> -		return send_icmp4_too_big(xdp);
> +		return send_icmp4_too_big(xdp, max_pckt_size);
>   	}
>   	return XDP_PASS;
>   }
> diff --git a/samples/bpf/xdp_adjust_tail_user.c b/samples/bpf/xdp_adjust_tail_user.c
> index a3596b617c4c..99e965c68054 100644
> --- a/samples/bpf/xdp_adjust_tail_user.c
> +++ b/samples/bpf/xdp_adjust_tail_user.c
> @@ -23,6 +23,7 @@
>   #include "libbpf.h"
>   
>   #define STATS_INTERVAL_S 2U
> +#define MAX_PCKT_SIZE 600
>   
>   static int ifindex = -1;
>   static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
> @@ -72,6 +73,7 @@ static void usage(const char *cmd)
>   	printf("Usage: %s [...]\n", cmd);
>   	printf("    -i <ifname|ifindex> Interface\n");
>   	printf("    -T <stop-after-X-seconds> Default: 0 (forever)\n");
> +	printf("    -P <MAX_PCKT_SIZE> Default: %u\n", MAX_PCKT_SIZE);
>   	printf("    -S use skb-mode\n");
>   	printf("    -N enforce native mode\n");
>   	printf("    -F force loading prog\n");
> @@ -85,13 +87,14 @@ int main(int argc, char **argv)
>   		.prog_type	= BPF_PROG_TYPE_XDP,
>   	};
>   	unsigned char opt_flags[256] = {};
> -	const char *optstr = "i:T:SNFh";
> +	const char *optstr = "i:T:P:SNFh";
>   	struct bpf_prog_info info = {};
>   	__u32 info_len = sizeof(info);
> +	__u32 max_pckt_size = 0;
> +	__u32 key = 0;
>   	unsigned int kill_after_s = 0;
>   	int i, prog_fd, map_fd, opt;
>   	struct bpf_object *obj;
> -	struct bpf_map *map;
>   	char filename[256];
>   	int err;
>   
> @@ -110,6 +113,9 @@ int main(int argc, char **argv)
>   		case 'T':
>   			kill_after_s = atoi(optarg);
>   			break;
> +		case 'P':
> +			max_pckt_size = atoi(optarg);
> +			break;
>   		case 'S':
>   			xdp_flags |= XDP_FLAGS_SKB_MODE;
>   			break;
> @@ -150,12 +156,22 @@ int main(int argc, char **argv)
>   	if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
>   		return 1;
>   
> -	map = bpf_map__next(NULL, obj);
> -	if (!map) {
> -		printf("finding a map in obj file failed\n");
> +	/* update pcktsz map */
> +	if (max_pckt_size) {
> +		map_fd = bpf_object__find_map_fd_by_name(obj, "pcktsz");
> +		if (map_fd < 0) {
> +			printf("finding a pcktsz map in obj file failed\n");
> +			return 1;
> +		}
> +		bpf_map_update_elem(map_fd, &key, &max_pckt_size, BPF_ANY);
> +	}
> +
> +	/* fetch icmpcnt map */
> +	map_fd = bpf_object__find_map_fd_by_name(obj, "icmpcnt");
> +	if (map_fd < 0) {
> +		printf("finding a icmpcnt map in obj file failed\n");
>   		return 1;
>   	}
> -	map_fd = bpf_map__fd(map);
>   
>   	if (!prog_fd) {
>   		printf("load_bpf_file: %s\n", strerror(errno));

Could you move the 'if (!prog_fd) ...' right after 'bpf_prog_load_xattr'
for readability reason?

Could you also change the condition 'if (!prog_fd)' to 'if (prog_fd < 
0)'? You need to mention this fix in your commit message as well.

  reply index

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-09-15 12:47 Daniel T. Lee
2019-09-16 16:07 ` Yonghong Song [this message]
2019-09-16 16:55   ` Daniel T. Lee

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=d6b935ae-64a7-a375-9825-72eaebafd8a4@fb.com \
    --to=yhs@fb.com \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=danieltimlee@gmail.com \
    --cc=netdev@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

BPF Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/bpf/0 bpf/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 bpf bpf/ https://lore.kernel.org/bpf \
		bpf@vger.kernel.org
	public-inbox-index bpf

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.bpf


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git