Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Daniel Borkmann says:

====================
pull-request: bpf 2018-05-03

The following pull-request contains BPF updates for your *net* tree.

The main changes are:

1) Several BPF sockmap fixes mostly related to bugs in error path
   handling, that is, a bug in updating the scatterlist length /
   offset accounting, a missing sk_mem_uncharge() in redirect
   error handling, and a bug where the outstanding bytes counter
   sg_size was not zeroed, from John.

2) Fix two memory leaks in the x86-64 BPF JIT, one in an error
   path where we still don't converge after image was allocated
   and another one where BPF calls are used and JIT passes don't
   converge, from Daniel.

3) Minor fix in BPF selftests where in test_stacktrace_build_id()
   we drop useless args in urandom_read and we need to add a missing
   newline in a CHECK() error message, from Song.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index abce27c..263c845 100644 (file)
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1236,6 +1236,7 @@ skip_init_addrs:
        for (pass = 0; pass < 20 || image; pass++) {
                proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
                if (proglen <= 0) {
+out_image:
                        image = NULL;
                        if (header)
                                bpf_jit_binary_free(header);
@@ -1246,8 +1247,7 @@ skip_init_addrs:
                        if (proglen != oldproglen) {
                                pr_err("bpf_jit: proglen=%d != oldproglen=%d\n",
                                       proglen, oldproglen);
-                               prog = orig_prog;
-                               goto out_addrs;
+                               goto out_image;
                        }
                        break;
                }
@@ -1283,7 +1283,7 @@ skip_init_addrs:
                prog = orig_prog;
        }
 
-       if (!prog->is_func || extra_pass) {
+       if (!image || !prog->is_func || extra_pass) {
 out_addrs:
                kfree(addrs);
                kfree(jit_data);

diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 634415c..098eca5 100644 (file)
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -326,6 +326,9 @@ retry:
                        if (ret > 0) {
                                if (apply)
                                        apply_bytes -= ret;
+
+                               sg->offset += ret;
+                               sg->length -= ret;
                                size -= ret;
                                offset += ret;
                                if (uncharge)
@@ -333,8 +336,6 @@ retry:
                                goto retry;
                        }
 
-                       sg->length = size;
-                       sg->offset = offset;
                        return ret;
                }
 
@@ -392,7 +393,8 @@ static void return_mem_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
        } while (i != md->sg_end);
 }
 
-static void free_bytes_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
+static void free_bytes_sg(struct sock *sk, int bytes,
+                         struct sk_msg_buff *md, bool charge)
 {
        struct scatterlist *sg = md->sg_data;
        int i = md->sg_start, free;
@@ -402,11 +404,13 @@ static void free_bytes_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
                if (bytes < free) {
                        sg[i].length -= bytes;
                        sg[i].offset += bytes;
-                       sk_mem_uncharge(sk, bytes);
+                       if (charge)
+                               sk_mem_uncharge(sk, bytes);
                        break;
                }
 
-               sk_mem_uncharge(sk, sg[i].length);
+               if (charge)
+                       sk_mem_uncharge(sk, sg[i].length);
                put_page(sg_page(&sg[i]));
                bytes -= sg[i].length;
                sg[i].length = 0;
@@ -417,6 +421,7 @@ static void free_bytes_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
                if (i == MAX_SKB_FRAGS)
                        i = 0;
        }
+       md->sg_start = i;
 }
 
 static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
@@ -575,10 +580,10 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
                                       struct sk_msg_buff *md,
                                       int flags)
 {
+       bool ingress = !!(md->flags & BPF_F_INGRESS);
        struct smap_psock *psock;
        struct scatterlist *sg;
-       int i, err, free = 0;
-       bool ingress = !!(md->flags & BPF_F_INGRESS);
+       int err = 0;
 
        sg = md->sg_data;
 
@@ -606,16 +611,8 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
 out_rcu:
        rcu_read_unlock();
 out:
-       i = md->sg_start;
-       while (sg[i].length) {
-               free += sg[i].length;
-               put_page(sg_page(&sg[i]));
-               sg[i].length = 0;
-               i++;
-               if (i == MAX_SKB_FRAGS)
-                       i = 0;
-       }
-       return free;
+       free_bytes_sg(NULL, send, md, false);
+       return err;
 }
 
 static inline void bpf_md_init(struct smap_psock *psock)
@@ -700,19 +697,26 @@ more_data:
                err = bpf_tcp_sendmsg_do_redirect(redir, send, m, flags);
                lock_sock(sk);
 
+               if (unlikely(err < 0)) {
+                       free_start_sg(sk, m);
+                       psock->sg_size = 0;
+                       if (!cork)
+                               *copied -= send;
+               } else {
+                       psock->sg_size -= send;
+               }
+
                if (cork) {
                        free_start_sg(sk, m);
+                       psock->sg_size = 0;
                        kfree(m);
                        m = NULL;
+                       err = 0;
                }
-               if (unlikely(err))
-                       *copied -= err;
-               else
-                       psock->sg_size -= send;
                break;
        case __SK_DROP:
        default:
-               free_bytes_sg(sk, send, m);
+               free_bytes_sg(sk, send, m, true);
                apply_bytes_dec(psock, send);
                *copied -= send;
                psock->sg_size -= send;

diff --git a/tools/bpf/bpf_dbg.c b/tools/bpf/bpf_dbg.c
index 4f254bc..61b9aa5 100644 (file)
--- a/tools/bpf/bpf_dbg.c
+++ b/tools/bpf/bpf_dbg.c
@@ -1063,7 +1063,7 @@ static int cmd_load_pcap(char *file)
 
 static int cmd_load(char *arg)
 {
-       char *subcmd, *cont, *tmp = strdup(arg);
+       char *subcmd, *cont = NULL, *tmp = strdup(arg);
        int ret = CMD_OK;
 
        subcmd = strtok_r(tmp, " ", &cont);
@@ -1073,7 +1073,10 @@ static int cmd_load(char *arg)
                bpf_reset();
                bpf_reset_breakpoints();
 
-               ret = cmd_load_bpf(cont);
+               if (!cont)
+                       ret = CMD_ERR;
+               else
+                       ret = cmd_load_bpf(cont);
        } else if (matches(subcmd, "pcap") == 0) {
                ret = cmd_load_pcap(cont);
        } else {

diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index faadbe2..4123d0a 100644 (file)
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -1108,7 +1108,7 @@ static void test_stacktrace_build_id(void)
 
        assert(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null")
               == 0);
-       assert(system("./urandom_read if=/dev/urandom of=/dev/zero count=4 2> /dev/null") == 0);
+       assert(system("./urandom_read") == 0);
        /* disable stack trace collection */
        key = 0;
        val = 1;
@@ -1158,7 +1158,7 @@ static void test_stacktrace_build_id(void)
        } while (bpf_map_get_next_key(stackmap_fd, &previous_key, &key) == 0);
 
        CHECK(build_id_matches < 1, "build id match",
-             "Didn't find expected build ID from the map");
+             "Didn't find expected build ID from the map\n");
 
 disable_pmu:
        ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);