| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Fri, 13 Sep 2019 22:34:02 +0000
From: Yonghong Song <yhs@...com>
To: "Daniel T. Lee" <danieltimlee@...il.com>,
Daniel Borkmann <daniel@...earbox.net>,
Alexei Starovoitov <ast@...nel.org>
CC: "netdev@...r.kernel.org" <netdev@...r.kernel.org>,
"bpf@...r.kernel.org" <bpf@...r.kernel.org>
Subject: Re: [bpf-next,v3] samples: bpf: add max_pckt_size option at
xdp_adjust_tail
On 9/11/19 8:02 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@...il.com>
>
> ---
> 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(-)
>
> diff --git a/samples/bpf/xdp_adjust_tail_kern.c b/samples/bpf/xdp_adjust_tail_kern.c
> index 411fdb21f8bc..d6d84ffe6a7a 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,
> +};
We have new map definition format like in
tools/testing/selftests/bpf/progs/bpf_flow.c.
But looks like most samples/bpf still use SEC("maps").
I guess we can leave it for now, and if needed,
later on a massive conversion for all samples/bpf/
bpf programs can be done.
> +
> 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;
> + __u32 *pckt_sz;
> + __u32 key = 0;
The above two new definitions may the code not in
reverse Christmas definition order, could you fix it?
> int pckt_size = data_end - data;
> 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_pckt_size) {
> offset = pckt_size - ICMP_TOOBIG_SIZE;
> if (bpf_xdp_adjust_tail(xdp, 0 - offset))
> return XDP_PASS;
We could have the following scenario:
max_pckt_size = 1
pckt_size = 2
offset = -96
bpf_xdp_adjust_tail return -EINVAL
so we return XDP_PASS now
Maybe you want to do
if (pckt_size > max(max_pckt_size, ICMP_TOOBIG_SIZE)) {
...
}
as in original code, bpf_xdp_adjust_tail(...) already succeeds.
> - 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..aef6c69a48a7 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) {
Let us test map_fd and below prog_fd with '< 0" instead of "!= 0'.
In this particular sample, "! = 0" is okay since we did not close
stdin. But in programs if stdin is closed, the fd 0 may be reused
for map_fd. Let us just keep good coding practice here.
> + 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) {
> + 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));
>
Powered by blists - more mailing lists