summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-06-21 07:13:42 +0900
committerLinus Torvalds <torvalds@linux-foundation.org>2018-06-21 07:13:42 +0900
commitd8894a08d91e230c5af9eed3de80114c5aaa3ccf (patch)
treed7cf7cb1bc5bc85a5c0f00dcae0f624c1212d67d /kernel
parent81e97f01371f4e1701feeafe484665112cd9ddc2 (diff)
parent9887cba19978a5f288100ef90a37684cc8d5e0a6 (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller: 1) Fix crash on bpf_prog_load() errors, from Daniel Borkmann. 2) Fix ATM VCC memory accounting, from David Woodhouse. 3) fib6_info objects need RCU freeing, from Eric Dumazet. 4) Fix SO_BINDTODEVICE handling for TCP sockets, from David Ahern. 5) Fix clobbered error code in enic_open() failure path, from Govindarajulu Varadarajan. 6) Propagate dev_get_valid_name() error returns properly, from Li RongQing. 7) Fix suspend/resume in davinci_emac driver, from Bartosz Golaszewski. 8) Various act_ife fixes (recursive locking, IDR leaks, etc.) from Davide Caratti. 9) Fix buggy checksum handling in sungem driver, from Eric Dumazet. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (40 commits) ip: limit use of gso_size to udp stmmac: fix DMA channel hang in half-duplex mode net: stmmac: socfpga: add additional ocp reset line for Stratix10 net: sungem: fix rx checksum support bpfilter: ignore binary files bpfilter: fix build error net/usb/drivers: Remove useless hrtimer_active check net/sched: act_ife: preserve the action control in case of error net/sched: act_ife: fix recursive lock and idr leak net: ethernet: fix suspend/resume in davinci_emac net: propagate dev_get_valid_name return code enic: do not overwrite error code net/tcp: Fix socket lookups with SO_BINDTODEVICE ptp: replace getnstimeofday64() with ktime_get_real_ts64() net/ipv6: respect rcu grace period before freeing fib6_info net: net_failover: fix typo in net_failover_slave_register() ipvlan: use ETH_MAX_MTU as max mtu net: hamradio: use eth_broadcast_addr enic: initialize enic->rfs_h.lock in enic_probe MAINTAINERS: Add Sam as the maintainer for NCSI ...
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/core.c69
-rw-r--r--kernel/bpf/devmap.c14
-rw-r--r--kernel/bpf/syscall.c12
3 files changed, 79 insertions, 16 deletions
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 9f1493705f40..a9e6c04d0f4a 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -350,6 +350,20 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
return prog_adj;
}
+void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
+{
+ int i;
+
+ for (i = 0; i < fp->aux->func_cnt; i++)
+ bpf_prog_kallsyms_del(fp->aux->func[i]);
+}
+
+void bpf_prog_kallsyms_del_all(struct bpf_prog *fp)
+{
+ bpf_prog_kallsyms_del_subprogs(fp);
+ bpf_prog_kallsyms_del(fp);
+}
+
#ifdef CONFIG_BPF_JIT
/* All BPF JIT sysctl knobs here. */
int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON);
@@ -584,6 +598,8 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
bpf_fill_ill_insns(hdr, size);
hdr->pages = size / PAGE_SIZE;
+ hdr->locked = 0;
+
hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)),
PAGE_SIZE - sizeof(*hdr));
start = (get_random_int() % hole) & ~(alignment - 1);
@@ -1434,6 +1450,33 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
return 0;
}
+static int bpf_prog_check_pages_ro_locked(const struct bpf_prog *fp)
+{
+#ifdef CONFIG_ARCH_HAS_SET_MEMORY
+ int i, err;
+
+ for (i = 0; i < fp->aux->func_cnt; i++) {
+ err = bpf_prog_check_pages_ro_single(fp->aux->func[i]);
+ if (err)
+ return err;
+ }
+
+ return bpf_prog_check_pages_ro_single(fp);
+#endif
+ return 0;
+}
+
+static void bpf_prog_select_func(struct bpf_prog *fp)
+{
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
+ u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
+
+ fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
+#else
+ fp->bpf_func = __bpf_prog_ret0_warn;
+#endif
+}
+
/**
* bpf_prog_select_runtime - select exec runtime for BPF program
* @fp: bpf_prog populated with internal BPF program
@@ -1444,13 +1487,13 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
*/
struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
{
-#ifndef CONFIG_BPF_JIT_ALWAYS_ON
- u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
+ /* In case of BPF to BPF calls, verifier did all the prep
+ * work with regards to JITing, etc.
+ */
+ if (fp->bpf_func)
+ goto finalize;
- fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
-#else
- fp->bpf_func = __bpf_prog_ret0_warn;
-#endif
+ bpf_prog_select_func(fp);
/* eBPF JITs can rewrite the program in case constant
* blinding is active. However, in case of error during
@@ -1471,6 +1514,8 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
if (*err)
return fp;
}
+
+finalize:
bpf_prog_lock_ro(fp);
/* The tail call compatibility check can only be done at
@@ -1479,7 +1524,17 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
* all eBPF JITs might immediately support all features.
*/
*err = bpf_check_tail_call(fp);
-
+ if (*err)
+ return fp;
+
+ /* Checkpoint: at this point onwards any cBPF -> eBPF or
+ * native eBPF program is read-only. If we failed to change
+ * the page attributes (e.g. allocation failure from
+ * splitting large pages), then reject the whole program
+ * in order to guarantee not ending up with any W+X pages
+ * from BPF side in kernel.
+ */
+ *err = bpf_prog_check_pages_ro_locked(fp);
return fp;
}
EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index a7cc7b3494a9..642c97f6d1b8 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -345,6 +345,20 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
return bq_enqueue(dst, xdpf, dev_rx);
}
+int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog)
+{
+ int err;
+
+ err = __xdp_generic_ok_fwd_dev(skb, dst->dev);
+ if (unlikely(err))
+ return err;
+ skb->dev = dst->dev;
+ generic_xdp_tx(skb, xdp_prog);
+
+ return 0;
+}
+
static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0fa20624707f..35dc466641f2 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1034,14 +1034,9 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
{
if (atomic_dec_and_test(&prog->aux->refcnt)) {
- int i;
-
/* bpf_prog_free_id() must be called first */
bpf_prog_free_id(prog, do_idr_lock);
-
- for (i = 0; i < prog->aux->func_cnt; i++)
- bpf_prog_kallsyms_del(prog->aux->func[i]);
- bpf_prog_kallsyms_del(prog);
+ bpf_prog_kallsyms_del_all(prog);
call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
}
@@ -1358,9 +1353,7 @@ static int bpf_prog_load(union bpf_attr *attr)
if (err < 0)
goto free_used_maps;
- /* eBPF program is ready to be JITed */
- if (!prog->bpf_func)
- prog = bpf_prog_select_runtime(prog, &err);
+ prog = bpf_prog_select_runtime(prog, &err);
if (err < 0)
goto free_used_maps;
@@ -1384,6 +1377,7 @@ static int bpf_prog_load(union bpf_attr *attr)
return err;
free_used_maps:
+ bpf_prog_kallsyms_del_subprogs(prog);
free_used_maps(prog->aux);
free_prog:
bpf_prog_uncharge_memlock(prog);