diff options
Diffstat (limited to 'samples/sockmap')
| -rw-r--r-- | samples/sockmap/Makefile | 2 | ||||
| -rw-r--r-- | samples/sockmap/sockmap_kern.c | 239 | ||||
| -rwxr-xr-x | samples/sockmap/sockmap_test.sh | 488 | ||||
| -rw-r--r-- | samples/sockmap/sockmap_user.c | 360 |
4 files changed, 1061 insertions, 28 deletions
diff --git a/samples/sockmap/Makefile b/samples/sockmap/Makefile index 73f1da4d116c..9bf2881bd11b 100644 --- a/samples/sockmap/Makefile +++ b/samples/sockmap/Makefile @@ -2,7 +2,7 @@ hostprogs-y := sockmap # Libbpf dependencies -LIBBPF := ../../tools/lib/bpf/bpf.o +LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o HOSTCFLAGS += -I$(objtree)/usr/include HOSTCFLAGS += -I$(srctree)/tools/lib/ diff --git a/samples/sockmap/sockmap_kern.c b/samples/sockmap/sockmap_kern.c index 52b0053274f4..9ff8bc5dc206 100644 --- a/samples/sockmap/sockmap_kern.c +++ b/samples/sockmap/sockmap_kern.c @@ -43,6 +43,55 @@ struct bpf_map_def SEC("maps") sock_map = { .max_entries = 20, }; +struct bpf_map_def SEC("maps") sock_map_txmsg = { + .type = BPF_MAP_TYPE_SOCKMAP, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 20, +}; + +struct bpf_map_def SEC("maps") sock_map_redir = { + .type = BPF_MAP_TYPE_SOCKMAP, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 20, +}; + +struct bpf_map_def SEC("maps") sock_apply_bytes = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1 +}; + +struct bpf_map_def SEC("maps") sock_cork_bytes = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1 +}; + +struct bpf_map_def SEC("maps") sock_pull_bytes = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 2 +}; + +struct bpf_map_def SEC("maps") sock_redir_flags = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1 +}; + +struct bpf_map_def SEC("maps") sock_skb_opts = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1 +}; + SEC("sk_skb1") int bpf_prog1(struct __sk_buff *skb) { @@ -54,15 +103,24 @@ int bpf_prog2(struct __sk_buff *skb) { __u32 lport = skb->local_port; __u32 rport = skb->remote_port; - int ret = 0; + int len, *f, ret, zero = 0; + __u64 flags = 0; if (lport == 10000) ret = 10; else ret = 1; - bpf_printk("sockmap: %d -> %d @ %d\n", lport, bpf_ntohl(rport), ret); - return bpf_sk_redirect_map(skb, &sock_map, ret, 0); + len = (__u32)skb->data_end - (__u32)skb->data; + f = bpf_map_lookup_elem(&sock_skb_opts, &zero); + if (f && *f) { + ret = 3; + flags = *f; + } + + bpf_printk("sk_skb2: redirect(%iB) flags=%i\n", + len, flags); + return bpf_sk_redirect_map(skb, &sock_map, ret, flags); } SEC("sockops") @@ -105,4 +163,179 @@ int bpf_sockmap(struct bpf_sock_ops *skops) return 0; } + +SEC("sk_msg1") +int bpf_prog4(struct sk_msg_md *msg) +{ + int *bytes, zero = 0, one = 1; + int *start, *end; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + bpf_msg_cork_bytes(msg, *bytes); + start = bpf_map_lookup_elem(&sock_pull_bytes, &zero); + end = bpf_map_lookup_elem(&sock_pull_bytes, &one); + if (start && end) + bpf_msg_pull_data(msg, *start, *end, 0); + return SK_PASS; +} + +SEC("sk_msg2") +int bpf_prog5(struct sk_msg_md *msg) +{ + int err1 = -1, err2 = -1, zero = 0, one = 1; + int *bytes, *start, *end, len1, len2; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + err1 = bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + err2 = bpf_msg_cork_bytes(msg, *bytes); + len1 = (__u64)msg->data_end - (__u64)msg->data; + start = bpf_map_lookup_elem(&sock_pull_bytes, &zero); + end = bpf_map_lookup_elem(&sock_pull_bytes, &one); + if (start && end) { + int err; + + bpf_printk("sk_msg2: pull(%i:%i)\n", + start ? *start : 0, end ? *end : 0); + err = bpf_msg_pull_data(msg, *start, *end, 0); + if (err) + bpf_printk("sk_msg2: pull_data err %i\n", + err); + len2 = (__u64)msg->data_end - (__u64)msg->data; + bpf_printk("sk_msg2: length update %i->%i\n", + len1, len2); + } + bpf_printk("sk_msg2: data length %i err1 %i err2 %i\n", + len1, err1, err2); + return SK_PASS; +} + +SEC("sk_msg3") +int bpf_prog6(struct sk_msg_md *msg) +{ + int *bytes, zero = 0, one = 1, key = 0; + int *start, *end, *f; + __u64 flags = 0; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + bpf_msg_cork_bytes(msg, *bytes); + start = bpf_map_lookup_elem(&sock_pull_bytes, &zero); + end = bpf_map_lookup_elem(&sock_pull_bytes, &one); + if (start && end) + bpf_msg_pull_data(msg, *start, *end, 0); + f = bpf_map_lookup_elem(&sock_redir_flags, &zero); + if (f && *f) { + key = 2; + flags = *f; + } + return bpf_msg_redirect_map(msg, &sock_map_redir, key, flags); +} + +SEC("sk_msg4") +int bpf_prog7(struct sk_msg_md *msg) +{ + int err1 = 0, err2 = 0, zero = 0, one = 1, key = 0; + int *f, *bytes, *start, *end, len1, len2; + __u64 flags = 0; + + int err; + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + err1 = bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + err2 = bpf_msg_cork_bytes(msg, *bytes); + len1 = (__u64)msg->data_end - (__u64)msg->data; + start = bpf_map_lookup_elem(&sock_pull_bytes, &zero); + end = bpf_map_lookup_elem(&sock_pull_bytes, &one); + if (start && end) { + + bpf_printk("sk_msg2: pull(%i:%i)\n", + start ? *start : 0, end ? *end : 0); + err = bpf_msg_pull_data(msg, *start, *end, 0); + if (err) + bpf_printk("sk_msg2: pull_data err %i\n", + err); + len2 = (__u64)msg->data_end - (__u64)msg->data; + bpf_printk("sk_msg2: length update %i->%i\n", + len1, len2); + } + f = bpf_map_lookup_elem(&sock_redir_flags, &zero); + if (f && *f) { + key = 2; + flags = *f; + } + bpf_printk("sk_msg3: redirect(%iB) flags=%i err=%i\n", + len1, flags, err1 ? err1 : err2); + err = bpf_msg_redirect_map(msg, &sock_map_redir, key, flags); + bpf_printk("sk_msg3: err %i\n", err); + return err; +} + +SEC("sk_msg5") +int bpf_prog8(struct sk_msg_md *msg) +{ + void *data_end = (void *)(long) msg->data_end; + void *data = (void *)(long) msg->data; + int ret = 0, *bytes, zero = 0; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) { + ret = bpf_msg_apply_bytes(msg, *bytes); + if (ret) + return SK_DROP; + } else { + return SK_DROP; + } + return SK_PASS; +} +SEC("sk_msg6") +int bpf_prog9(struct sk_msg_md *msg) +{ + void *data_end = (void *)(long) msg->data_end; + void *data = (void *)(long) msg->data; + int ret = 0, *bytes, zero = 0; + + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) { + if (((__u64)data_end - (__u64)data) >= *bytes) + return SK_PASS; + ret = bpf_msg_cork_bytes(msg, *bytes); + if (ret) + return SK_DROP; + } + return SK_PASS; +} + +SEC("sk_msg7") +int bpf_prog10(struct sk_msg_md *msg) +{ + int *bytes, zero = 0, one = 1; + int *start, *end; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + bpf_msg_cork_bytes(msg, *bytes); + start = bpf_map_lookup_elem(&sock_pull_bytes, &zero); + end = bpf_map_lookup_elem(&sock_pull_bytes, &one); + if (start && end) + bpf_msg_pull_data(msg, *start, *end, 0); + + return SK_DROP; +} + + char _license[] SEC("license") = "GPL"; diff --git a/samples/sockmap/sockmap_test.sh b/samples/sockmap/sockmap_test.sh new file mode 100755 index 000000000000..ace75f070eb8 --- /dev/null +++ b/samples/sockmap/sockmap_test.sh @@ -0,0 +1,488 @@ +#Test a bunch of positive cases to verify basic functionality +for prog in "--txmsg_redir --txmsg_skb" "--txmsg_redir --txmsg_ingress" "--txmsg" "--txmsg_redir" "--txmsg_redir --txmsg_ingress" "--txmsg_drop"; do +for t in "sendmsg" "sendpage"; do +for r in 1 10 100; do + for i in 1 10 100; do + for l in 1 10 100; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 + done + done +done +done +done + +#Test max iov +t="sendmsg" +r=1 +i=1024 +l=1 +prog="--txmsg" + +TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" +echo $TEST +$TEST +sleep 2 +prog="--txmsg_redir" +TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" +echo $TEST +$TEST + +# Test max iov with 1k send + +t="sendmsg" +r=1 +i=1024 +l=1024 +prog="--txmsg" + +TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" +echo $TEST +$TEST +sleep 2 +prog="--txmsg_redir" +TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" +echo $TEST +$TEST +sleep 2 + +# Test apply with 1B +r=1 +i=1024 +l=1024 +prog="--txmsg_apply 1" + +for t in "sendmsg" "sendpage"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +# Test apply with larger value than send +r=1 +i=8 +l=1024 +prog="--txmsg_apply 2048" + +for t in "sendmsg" "sendpage"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +# Test apply with apply that never reaches limit +r=1024 +i=1 +l=1 +prog="--txmsg_apply 2048" + +for t in "sendmsg" "sendpage"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +# Test apply and redirect with 1B +r=1 +i=1024 +l=1024 +prog="--txmsg_redir --txmsg_apply 1" + +for t in "sendmsg" "sendpage"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +prog="--txmsg_redir --txmsg_apply 1 --txmsg_ingress" + +for t in "sendmsg" "sendpage"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +prog="--txmsg_redir --txmsg_apply 1 --txmsg_skb" + +for t in "sendmsg" "sendpage"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + + +# Test apply and redirect with larger value than send +r=1 +i=8 +l=1024 +prog="--txmsg_redir --txmsg_apply 2048" + +for t in "sendmsg" "sendpage"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +prog="--txmsg_redir --txmsg_apply 2048 --txmsg_ingress" + +for t in "sendmsg" "sendpage"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +prog="--txmsg_redir --txmsg_apply 2048 --txmsg_skb" + +for t in "sendmsg" "sendpage"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + + +# Test apply and redirect with apply that never reaches limit +r=1024 +i=1 +l=1 +prog="--txmsg_apply 2048" + +for t in "sendmsg" "sendpage"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +# Test cork with 1B not really useful but test it anyways +r=1 +i=1024 +l=1024 +prog="--txmsg_cork 1" + +for t in "sendpage" "sendmsg"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +# Test cork with a more reasonable 100B +r=1 +i=1000 +l=1000 +prog="--txmsg_cork 100" + +for t in "sendpage" "sendmsg"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +# Test cork with larger value than send +r=1 +i=8 +l=1024 +prog="--txmsg_cork 2048" + +for t in "sendpage" "sendmsg"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +# Test cork with cork that never reaches limit +r=1024 +i=1 +l=1 +prog="--txmsg_cork 2048" + +for t in "sendpage" "sendmsg"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +r=1 +i=1024 +l=1024 +prog="--txmsg_redir --txmsg_cork 1" + +for t in "sendpage" "sendmsg"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +# Test cork with a more reasonable 100B +r=1 +i=1000 +l=1000 +prog="--txmsg_redir --txmsg_cork 100" + +for t in "sendpage" "sendmsg"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +# Test cork with larger value than send +r=1 +i=8 +l=1024 +prog="--txmsg_redir --txmsg_cork 2048" + +for t in "sendpage" "sendmsg"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +# Test cork with cork that never reaches limit +r=1024 +i=1 +l=1 +prog="--txmsg_cork 2048" + +for t in "sendpage" "sendmsg"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + + +# mix and match cork and apply not really useful but valid programs + +# Test apply < cork +r=100 +i=1 +l=5 +prog="--txmsg_apply 10 --txmsg_cork 100" +for t in "sendpage" "sendmsg"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +# Try again with larger sizes so we hit overflow case +r=100 +i=1000 +l=2048 +prog="--txmsg_apply 4096 --txmsg_cork 8096" +for t in "sendpage" "sendmsg"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +# Test apply > cork +r=100 +i=1 +l=5 +prog="--txmsg_apply 100 --txmsg_cork 10" +for t in "sendpage" "sendmsg"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +# Again with larger sizes so we hit overflow cases +r=100 +i=1000 +l=2048 +prog="--txmsg_apply 8096 --txmsg_cork 4096" +for t in "sendpage" "sendmsg"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + + +# Test apply = cork +r=100 +i=1 +l=5 +prog="--txmsg_apply 10 --txmsg_cork 10" +for t in "sendpage" "sendmsg"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +r=100 +i=1000 +l=2048 +prog="--txmsg_apply 4096 --txmsg_cork 4096" +for t in "sendpage" "sendmsg"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +# Test apply < cork +r=100 +i=1 +l=5 +prog="--txmsg_redir --txmsg_apply 10 --txmsg_cork 100" +for t in "sendpage" "sendmsg"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +# Try again with larger sizes so we hit overflow case +r=100 +i=1000 +l=2048 +prog="--txmsg_redir --txmsg_apply 4096 --txmsg_cork 8096" +for t in "sendpage" "sendmsg"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +# Test apply > cork +r=100 +i=1 +l=5 +prog="--txmsg_redir --txmsg_apply 100 --txmsg_cork 10" +for t in "sendpage" "sendmsg"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +# Again with larger sizes so we hit overflow cases +r=100 +i=1000 +l=2048 +prog="--txmsg_redir --txmsg_apply 8096 --txmsg_cork 4096" +for t in "sendpage" "sendmsg"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + + +# Test apply = cork +r=100 +i=1 +l=5 +prog="--txmsg_redir --txmsg_apply 10 --txmsg_cork 10" +for t in "sendpage" "sendmsg"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +r=100 +i=1000 +l=2048 +prog="--txmsg_redir --txmsg_apply 4096 --txmsg_cork 4096" +for t in "sendpage" "sendmsg"; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" + echo $TEST + $TEST + sleep 2 +done + +# Tests for bpf_msg_pull_data() +for i in `seq 99 100 1600`; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \ + --txmsg --txmsg_start 0 --txmsg_end $i --txmsg_cork 1600" + echo $TEST + $TEST + sleep 2 +done + +for i in `seq 199 100 1600`; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \ + --txmsg --txmsg_start 100 --txmsg_end $i --txmsg_cork 1600" + echo $TEST + $TEST + sleep 2 +done + +TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \ + --txmsg --txmsg_start 1500 --txmsg_end 1600 --txmsg_cork 1600" +echo $TEST +$TEST +sleep 2 + +TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \ + --txmsg --txmsg_start 1111 --txmsg_end 1112 --txmsg_cork 1600" +echo $TEST +$TEST +sleep 2 + +TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \ + --txmsg --txmsg_start 1111 --txmsg_end 0 --txmsg_cork 1600" +echo $TEST +$TEST +sleep 2 + +TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \ + --txmsg --txmsg_start 0 --txmsg_end 1601 --txmsg_cork 1600" +echo $TEST +$TEST +sleep 2 + +TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \ + --txmsg --txmsg_start 0 --txmsg_end 1601 --txmsg_cork 1602" +echo $TEST +$TEST +sleep 2 + +# Run through gamut again with start and end +for prog in "--txmsg" "--txmsg_redir" "--txmsg_drop"; do +for t in "sendmsg" "sendpage"; do +for r in 1 10 100; do + for i in 1 10 100; do + for l in 1 10 100; do + TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog --txmsg_start 1 --txmsg_end 2" + echo $TEST + $TEST + sleep 2 + done + done +done +done +done + +# Some specific tests to cover specific code paths +./sockmap --cgroup /mnt/cgroup2/ -t sendpage \ + -r 5 -i 1 -l 1 --txmsg_redir --txmsg_cork 5 --txmsg_apply 3 +./sockmap --cgroup /mnt/cgroup2/ -t sendmsg \ + -r 5 -i 1 -l 1 --txmsg_redir --txmsg_cork 5 --txmsg_apply 3 +./sockmap --cgroup /mnt/cgroup2/ -t sendpage \ + -r 5 -i 1 -l 1 --txmsg_redir --txmsg_cork 5 --txmsg_apply 5 +./sockmap --cgroup /mnt/cgroup2/ -t sendmsg \ + -r 5 -i 1 -l 1 --txmsg_redir --txmsg_cork 5 --txmsg_apply 5 diff --git a/samples/sockmap/sockmap_user.c b/samples/sockmap/sockmap_user.c index 7c25c0c112bc..6f2334912283 100644 --- a/samples/sockmap/sockmap_user.c +++ b/samples/sockmap/sockmap_user.c @@ -29,6 +29,7 @@ #include <sys/time.h> #include <sys/resource.h> #include <sys/types.h> +#include <sys/sendfile.h> #include <linux/netlink.h> #include <linux/socket.h> @@ -54,6 +55,18 @@ void running_handler(int a); /* global sockets */ int s1, s2, c1, c2, p1, p2; +int txmsg_pass; +int txmsg_noisy; +int txmsg_redir; +int txmsg_redir_noisy; +int txmsg_drop; +int txmsg_apply; +int txmsg_cork; +int txmsg_start; +int txmsg_end; +int txmsg_ingress; +int txmsg_skb; + static const struct option long_options[] = { {"help", no_argument, NULL, 'h' }, {"cgroup", required_argument, NULL, 'c' }, @@ -62,6 +75,18 @@ static const struct option long_options[] = { {"iov_count", required_argument, NULL, 'i' }, {"length", required_argument, NULL, 'l' }, {"test", required_argument, NULL, 't' }, + {"data_test", no_argument, NULL, 'd' }, + {"txmsg", no_argument, &txmsg_pass, 1 }, + {"txmsg_noisy", no_argument, &txmsg_noisy, 1 }, + {"txmsg_redir", no_argument, &txmsg_redir, 1 }, + {"txmsg_redir_noisy", no_argument, &txmsg_redir_noisy, 1}, + {"txmsg_drop", no_argument, &txmsg_drop, 1 }, + {"txmsg_apply", required_argument, NULL, 'a'}, + {"txmsg_cork", required_argument, NULL, 'k'}, + {"txmsg_start", required_argument, NULL, 's'}, + {"txmsg_end", required_argument, NULL, 'e'}, + {"txmsg_ingress", no_argument, &txmsg_ingress, 1 }, + {"txmsg_skb", no_argument, &txmsg_skb, 1 }, {0, 0, NULL, 0 } }; @@ -195,19 +220,71 @@ struct msg_stats { struct timespec end; }; +struct sockmap_options { + int verbose; + bool base; + bool sendpage; + bool data_test; + bool drop_expected; +}; + +static int msg_loop_sendpage(int fd, int iov_length, int cnt, + struct msg_stats *s, + struct sockmap_options *opt) +{ + bool drop = opt->drop_expected; + unsigned char k = 0; + FILE *file; + int i, fp; + + file = fopen(".sendpage_tst.tmp", "w+"); + for (i = 0; i < iov_length * cnt; i++, k++) + fwrite(&k, sizeof(char), 1, file); + fflush(file); + fseek(file, 0, SEEK_SET); + fclose(file); + + fp = open(".sendpage_tst.tmp", O_RDONLY); + clock_gettime(CLOCK_MONOTONIC, &s->start); + for (i = 0; i < cnt; i++) { + int sent = sendfile(fd, fp, NULL, iov_length); + + if (!drop && sent < 0) { + perror("send loop error:"); + close(fp); + return sent; + } else if (drop && sent >= 0) { + printf("sendpage loop error expected: %i\n", sent); + close(fp); + return -EIO; + } + + if (sent > 0) + s->bytes_sent += sent; + } + clock_gettime(CLOCK_MONOTONIC, &s->end); + close(fp); + return 0; +} + static int msg_loop(int fd, int iov_count, int iov_length, int cnt, - struct msg_stats *s, bool tx) + struct msg_stats *s, bool tx, + struct sockmap_options *opt) { struct msghdr msg = {0}; int err, i, flags = MSG_NOSIGNAL; struct iovec *iov; + unsigned char k; + bool data_test = opt->data_test; + bool drop = opt->drop_expected; iov = calloc(iov_count, sizeof(struct iovec)); if (!iov) return errno; + k = 0; for (i = 0; i < iov_count; i++) { - char *d = calloc(iov_length, sizeof(char)); + unsigned char *d = calloc(iov_length, sizeof(char)); if (!d) { fprintf(stderr, "iov_count %i/%i OOM\n", i, iov_count); @@ -215,21 +292,34 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, } iov[i].iov_base = d; iov[i].iov_len = iov_length; + + if (data_test && tx) { + int j; + + for (j = 0; j < iov_length; j++) + d[j] = k++; + } } msg.msg_iov = iov; msg.msg_iovlen = iov_count; + k = 0; if (tx) { clock_gettime(CLOCK_MONOTONIC, &s->start); for (i = 0; i < cnt; i++) { int sent = sendmsg(fd, &msg, flags); - if (sent < 0) { + if (!drop && sent < 0) { perror("send loop error:"); goto out_errno; + } else if (drop && sent >= 0) { + printf("send loop error expected: %i\n", sent); + errno = -EIO; + goto out_errno; } - s->bytes_sent += sent; + if (sent > 0) + s->bytes_sent += sent; } clock_gettime(CLOCK_MONOTONIC, &s->end); } else { @@ -272,6 +362,26 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, } s->bytes_recvd += recv; + + if (data_test) { + int j; + + for (i = 0; i < msg.msg_iovlen; i++) { + unsigned char *d = iov[i].iov_base; + + for (j = 0; + j < iov[i].iov_len && recv; j++) { + if (d[j] != k++) { + errno = -EIO; + fprintf(stderr, + "detected data corruption @iov[%i]:%i %02x != %02x, %02x ?= %02x\n", + i, j, d[j], k - 1, d[j+1], k + 1); + goto out_errno; + } + recv--; + } + } + } } clock_gettime(CLOCK_MONOTONIC, &s->end); } @@ -300,7 +410,7 @@ static inline float recvdBps(struct msg_stats s) } static int sendmsg_test(int iov_count, int iov_buf, int cnt, - int verbose, bool base) + struct sockmap_options *opt) { float sent_Bps = 0, recvd_Bps = 0; int rx_fd, txpid, rxpid, err = 0; @@ -309,14 +419,20 @@ static int sendmsg_test(int iov_count, int iov_buf, int cnt, errno = 0; - if (base) + if (opt->base) rx_fd = p1; else rx_fd = p2; rxpid = fork(); if (rxpid == 0) { - err = msg_loop(rx_fd, iov_count, iov_buf, cnt, &s, false); + if (opt->drop_expected) + exit(1); + + if (opt->sendpage) + iov_count = 1; + err = msg_loop(rx_fd, iov_count, iov_buf, + cnt, &s, false, opt); if (err) fprintf(stderr, "msg_loop_rx: iov_count %i iov_buf %i cnt %i err %i\n", @@ -339,7 +455,12 @@ static int sendmsg_test(int iov_count, int iov_buf, int cnt, txpid = fork(); if (txpid == 0) { - err = msg_loop(c1, iov_count, iov_buf, cnt, &s, true); + if (opt->sendpage) + err = msg_loop_sendpage(c1, iov_buf, cnt, &s, opt); + else + err = msg_loop(c1, iov_count, iov_buf, + cnt, &s, true, opt); + if (err) fprintf(stderr, "msg_loop_tx: iov_count %i iov_buf %i cnt %i err %i\n", @@ -364,7 +485,7 @@ static int sendmsg_test(int iov_count, int iov_buf, int cnt, return err; } -static int forever_ping_pong(int rate, int verbose) +static int forever_ping_pong(int rate, struct sockmap_options *opt) { struct timeval timeout; char buf[1024] = {0}; @@ -429,7 +550,7 @@ static int forever_ping_pong(int rate, int verbose) if (rate) sleep(rate); - if (verbose) { + if (opt->verbose) { printf("."); fflush(stdout); @@ -443,20 +564,34 @@ enum { PING_PONG, SENDMSG, BASE, + BASE_SENDPAGE, + SENDPAGE, }; int main(int argc, char **argv) { - int iov_count = 1, length = 1024, rate = 1, verbose = 0; + int iov_count = 1, length = 1024, rate = 1, tx_prog_fd; struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY}; int opt, longindex, err, cg_fd = 0; + struct sockmap_options options = {0}; int test = PING_PONG; char filename[256]; - while ((opt = getopt_long(argc, argv, "hvc:r:i:l:t:", + while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:", long_options, &longindex)) != -1) { switch (opt) { - /* Cgroup configuration */ + case 's': + txmsg_start = atoi(optarg); + break; + case 'e': + txmsg_end = atoi(optarg); + break; + case 'a': + txmsg_apply = atoi(optarg); + break; + case 'k': + txmsg_cork = atoi(optarg); + break; case 'c': cg_fd = open(optarg, O_DIRECTORY, O_RDONLY); if (cg_fd < 0) { @@ -470,7 +605,7 @@ int main(int argc, char **argv) rate = atoi(optarg); break; case 'v': - verbose = 1; + options.verbose = 1; break; case 'i': iov_count = atoi(optarg); @@ -478,6 +613,9 @@ int main(int argc, char **argv) case 'l': length = atoi(optarg); break; + case 'd': + options.data_test = true; + break; case 't': if (strcmp(optarg, "ping") == 0) { test = PING_PONG; @@ -485,11 +623,17 @@ int main(int argc, char **argv) test = SENDMSG; } else if (strcmp(optarg, "base") == 0) { test = BASE; + } else if (strcmp(optarg, "base_sendpage") == 0) { + test = BASE_SENDPAGE; + } else if (strcmp(optarg, "sendpage") == 0) { + test = SENDPAGE; } else { usage(argv); return -1; } break; + case 0: + break; case 'h': default: usage(argv); @@ -515,16 +659,16 @@ int main(int argc, char **argv) /* catch SIGINT */ signal(SIGINT, running_handler); - /* If base test skip BPF setup */ - if (test == BASE) - goto run; - if (load_bpf_file(filename)) { fprintf(stderr, "load_bpf_file: (%s) %s\n", filename, strerror(errno)); return 1; } + /* If base test skip BPF setup */ + if (test == BASE || test == BASE_SENDPAGE) + goto run; + /* Attach programs to sockmap */ err = bpf_prog_attach(prog_fd[0], map_fd[0], BPF_SK_SKB_STREAM_PARSER, 0); @@ -557,15 +701,183 @@ run: goto out; } - if (test == PING_PONG) - err = forever_ping_pong(rate, verbose); - else if (test == SENDMSG) - err = sendmsg_test(iov_count, length, rate, verbose, false); - else if (test == BASE) - err = sendmsg_test(iov_count, length, rate, verbose, true); + /* Attach txmsg program to sockmap */ + if (txmsg_pass) + tx_prog_fd = prog_fd[3]; + else if (txmsg_noisy) + tx_prog_fd = prog_fd[4]; + else if (txmsg_redir) + tx_prog_fd = prog_fd[5]; + else if (txmsg_redir_noisy) + tx_prog_fd = prog_fd[6]; + else if (txmsg_drop) + tx_prog_fd = prog_fd[9]; + /* apply and cork must be last */ + else if (txmsg_apply) + tx_prog_fd = prog_fd[7]; + else if (txmsg_cork) + tx_prog_fd = prog_fd[8]; else + tx_prog_fd = 0; + + if (tx_prog_fd) { + int redir_fd, i = 0; + + err = bpf_prog_attach(tx_prog_fd, + map_fd[1], BPF_SK_MSG_VERDICT, 0); + if (err) { + fprintf(stderr, + "ERROR: bpf_prog_attach (txmsg): %d (%s)\n", + err, strerror(errno)); + return err; + } + + err = bpf_map_update_elem(map_fd[1], &i, &c1, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg): %d (%s\n", + err, strerror(errno)); + return err; + } + + if (txmsg_redir || txmsg_redir_noisy) + redir_fd = c2; + else + redir_fd = c1; + + err = bpf_map_update_elem(map_fd[2], &i, &redir_fd, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg): %d (%s\n", + err, strerror(errno)); + return err; + } + + if (txmsg_apply) { + err = bpf_map_update_elem(map_fd[3], + &i, &txmsg_apply, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (apply_bytes): %d (%s\n", + err, strerror(errno)); + return err; + } + } + + if (txmsg_cork) { + err = bpf_map_update_elem(map_fd[4], + &i, &txmsg_cork, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (cork_bytes): %d (%s\n", + err, strerror(errno)); + return err; + } + } + + if (txmsg_start) { + err = bpf_map_update_elem(map_fd[5], + &i, &txmsg_start, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg_start): %d (%s)\n", + err, strerror(errno)); + return err; + } + } + + if (txmsg_end) { + i = 1; + err = bpf_map_update_elem(map_fd[5], + &i, &txmsg_end, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg_end): %d (%s)\n", + err, strerror(errno)); + return err; + } + } + + if (txmsg_ingress) { + int in = BPF_F_INGRESS; + + i = 0; + err = bpf_map_update_elem(map_fd[6], &i, &in, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg_ingress): %d (%s)\n", + err, strerror(errno)); + } + i = 1; + err = bpf_map_update_elem(map_fd[1], &i, &p1, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (p1 txmsg): %d (%s)\n", + err, strerror(errno)); + } + err = bpf_map_update_elem(map_fd[2], &i, &p1, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (p1 redir): %d (%s)\n", + err, strerror(errno)); + } + + i = 2; + err = bpf_map_update_elem(map_fd[2], &i, &p2, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (p2 txmsg): %d (%s)\n", + err, strerror(errno)); + } + } + + if (txmsg_skb) { + int skb_fd = (test == SENDMSG || test == SENDPAGE) ? p2 : p1; + int ingress = BPF_F_INGRESS; + + i = 0; + err = bpf_map_update_elem(map_fd[7], &i, &ingress, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg_ingress): %d (%s)\n", + err, strerror(errno)); + } + + i = 3; + err = bpf_map_update_elem(map_fd[0], &i, &skb_fd, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (c1 sockmap): %d (%s)\n", + err, strerror(errno)); + } + } + } + + if (txmsg_drop) + options.drop_expected = true; + + if (test == PING_PONG) + err = forever_ping_pong(rate, &options); + else if (test == SENDMSG) { + options.base = false; + options.sendpage = false; + err = sendmsg_test(iov_count, length, rate, &options); + } else if (test == SENDPAGE) { + options.base = false; + options.sendpage = true; + err = sendmsg_test(iov_count, length, rate, &options); + } else if (test == BASE) { + options.base = true; + options.sendpage = false; + err = sendmsg_test(iov_count, length, rate, &options); + } else if (test == BASE_SENDPAGE) { + options.base = true; + options.sendpage = true; + err = sendmsg_test(iov_count, length, rate, &options); + } else fprintf(stderr, "unknown test\n"); out: + bpf_prog_detach2(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS); close(s1); close(s2); close(p1); |