From 28c486744e6de4d882a1d853aa63d99fcba4b7a6 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 30 Jan 2018 03:37:41 +0100 Subject: bpf: introduce BPF_JIT_ALWAYS_ON config [ upstream commit 290af86629b25ffd1ed6232c4e9107da031705cb ] The BPF interpreter has been used as part of the spectre 2 attack CVE-2017-5715. A quote from goolge project zero blog: "At this point, it would normally be necessary to locate gadgets in the host kernel code that can be used to actually leak data by reading from an attacker-controlled location, shifting and masking the result appropriately and then using the result of that as offset to an attacker-controlled address for a load. But piecing gadgets together and figuring out which ones work in a speculation context seems annoying. So instead, we decided to use the eBPF interpreter, which is built into the host kernel - while there is no legitimate way to invoke it from inside a VM, the presence of the code in the host kernel's text section is sufficient to make it usable for the attack, just like with ordinary ROP gadgets." To make attacker job harder introduce BPF_JIT_ALWAYS_ON config option that removes interpreter from the kernel in favor of JIT-only mode. So far eBPF JIT is supported by: x64, arm64, arm32, sparc64, s390, powerpc64, mips64 The start of JITed program is randomized and code page is marked as read-only. In addition "constant blinding" can be turned on with net.core.bpf_jit_harden v2->v3: - move __bpf_prog_ret0 under ifdef (Daniel) v1->v2: - fix init order, test_bpf and cBPF (Daniel's feedback) - fix offloaded bpf (Jakub's feedback) - add 'return 0' dummy in case something can invoke prog->bpf_func - retarget bpf tree. For bpf-next the patch would need one extra hunk. It will be sent when the trees are merged back to net-next Considered doing: int bpf_jit_enable __read_mostly = BPF_EBPF_JIT_DEFAULT; but it seems better to land the patch as-is and in bpf-next remove bpf_jit_enable global variable from all JITs, consolidate in one place and remove this jit_init() function. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Signed-off-by: Greg Kroah-Hartman --- net/Kconfig | 3 +++ net/core/filter.c | 4 +++- net/core/sysctl_net_core.c | 6 ++++++ net/socket.c | 9 +++++++++ 4 files changed, 21 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/Kconfig b/net/Kconfig index 127da94ae25e..6d94140beacc 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -388,3 +388,6 @@ endif # if NET # Used by archs to tell that they support BPF_JIT config HAVE_BPF_JIT bool + +config HAVE_EBPF_JIT + bool diff --git a/net/core/filter.c b/net/core/filter.c index e94355452166..229bf08ce7fa 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -984,7 +984,9 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) */ goto out_err_free; - bpf_prog_select_runtime(fp); + err = bpf_prog_select_runtime(fp); + if (err) + goto out_err_free; kfree(old_prog); return fp; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index f5ef2115871f..6578a0a2f708 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -292,7 +292,13 @@ static struct ctl_table net_core_table[] = { .data = &bpf_jit_enable, .maxlen = sizeof(int), .mode = 0644, +#ifndef CONFIG_BPF_JIT_ALWAYS_ON .proc_handler = proc_dointvec +#else + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &one, +#endif }, #endif { diff --git a/net/socket.c b/net/socket.c index 2cf4f25f5c2b..5b31e5baf3b5 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2534,6 +2534,15 @@ out_fs: core_initcall(sock_init); /* early initcall */ +static int __init jit_init(void) +{ +#ifdef CONFIG_BPF_JIT_ALWAYS_ON + bpf_jit_enable = 1; +#endif + return 0; +} +pure_initcall(jit_init); + #ifdef CONFIG_PROC_FS void socket_seq_show(struct seq_file *seq) { -- cgit v1.2.3 From 02662601a231f8721930168ce71d84bcfb8d9a96 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 30 Jan 2018 03:37:45 +0100 Subject: bpf: fix 32-bit divide by zero [ upstream commit 68fda450a7df51cff9e5a4d4a4d9d0d5f2589153 ] due to some JITs doing if (src_reg == 0) check in 64-bit mode for div/mod operations mask upper 32-bits of src register before doing the check Fixes: 622582786c9e ("net: filter: x86: internal BPF JIT") Fixes: 7a12b5031c6b ("sparc64: Add eBPF JIT.") Reported-by: syzbot+48340bb518e88849e2e3@syzkaller.appspotmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Signed-off-by: Greg Kroah-Hartman --- net/core/filter.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net') diff --git a/net/core/filter.c b/net/core/filter.c index 229bf08ce7fa..1a9ded6af138 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -430,6 +430,10 @@ do_pass: convert_bpf_extensions(fp, &insn)) break; + if (fp->code == (BPF_ALU | BPF_DIV | BPF_X) || + fp->code == (BPF_ALU | BPF_MOD | BPF_X)) + *insn++ = BPF_MOV32_REG(BPF_REG_X, BPF_REG_X); + *insn = BPF_RAW_INSN(fp->code, BPF_REG_A, BPF_REG_X, 0, fp->k); break; -- cgit v1.2.3 From 5acc065c6b3e389fa5520e1d171c79c7c5c701b8 Mon Sep 17 00:00:00 2001 From: zhangliping Date: Sat, 25 Nov 2017 22:02:12 +0800 Subject: openvswitch: fix the incorrect flow action alloc size [ Upstream commit 67c8d22a73128ff910e2287567132530abcf5b71 ] If we want to add a datapath flow, which has more than 500 vxlan outputs' action, we will get the following error reports: openvswitch: netlink: Flow action size 32832 bytes exceeds max openvswitch: netlink: Flow action size 32832 bytes exceeds max openvswitch: netlink: Actions may not be safe on all matching packets ... ... It seems that we can simply enlarge the MAX_ACTIONS_BUFSIZE to fix it, but this is not the root cause. For example, for a vxlan output action, we need about 60 bytes for the nlattr, but after it is converted to the flow action, it only occupies 24 bytes. This means that we can still support more than 1000 vxlan output actions for a single datapath flow under the the current 32k max limitation. So even if the nla_len(attr) is larger than MAX_ACTIONS_BUFSIZE, we shouldn't report EINVAL and keep it move on, as the judgement can be done by the reserve_sfa_size. Signed-off-by: zhangliping Acked-by: Pravin B Shelar Signed-off-by: David S. Miller Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- net/openvswitch/flow_netlink.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'net') diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index d26b28def310..21e4d339217e 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1672,14 +1672,11 @@ int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb) #define MAX_ACTIONS_BUFSIZE (32 * 1024) -static struct sw_flow_actions *nla_alloc_flow_actions(int size, bool log) +static struct sw_flow_actions *nla_alloc_flow_actions(int size) { struct sw_flow_actions *sfa; - if (size > MAX_ACTIONS_BUFSIZE) { - OVS_NLERR(log, "Flow action size %u bytes exceeds max", size); - return ERR_PTR(-EINVAL); - } + WARN_ON_ONCE(size > MAX_ACTIONS_BUFSIZE); sfa = kmalloc(sizeof(*sfa) + size, GFP_KERNEL); if (!sfa) @@ -1752,12 +1749,15 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa, new_acts_size = ksize(*sfa) * 2; if (new_acts_size > MAX_ACTIONS_BUFSIZE) { - if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) + if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) { + OVS_NLERR(log, "Flow action size exceeds max %u", + MAX_ACTIONS_BUFSIZE); return ERR_PTR(-EMSGSIZE); + } new_acts_size = MAX_ACTIONS_BUFSIZE; } - acts = nla_alloc_flow_actions(new_acts_size, log); + acts = nla_alloc_flow_actions(new_acts_size); if (IS_ERR(acts)) return (void *)acts; @@ -2369,7 +2369,7 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, { int err; - *sfa = nla_alloc_flow_actions(nla_len(attr), log); + *sfa = nla_alloc_flow_actions(min(nla_len(attr), MAX_ACTIONS_BUFSIZE)); if (IS_ERR(*sfa)) return PTR_ERR(*sfa); -- cgit v1.2.3 From 4870fb97221d3fd8d8868e26aa4e61f78ebb32b2 Mon Sep 17 00:00:00 2001 From: Chun-Yeow Yeoh Date: Tue, 14 Nov 2017 23:20:05 +0800 Subject: mac80211: fix the update of path metric for RANN frame [ Upstream commit fbbdad5edf0bb59786a51b94a9d006bc8c2da9a2 ] The previous path metric update from RANN frame has not considered the own link metric toward the transmitting mesh STA. Fix this. Reported-by: Michael65535 Signed-off-by: Chun-Yeow Yeoh Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- net/mac80211/mesh_hwmp.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index c6be0b4f4058..e68a409fc351 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -776,7 +776,7 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, struct mesh_path *mpath; u8 ttl, flags, hopcount; const u8 *orig_addr; - u32 orig_sn, metric, metric_txsta, interval; + u32 orig_sn, new_metric, orig_metric, last_hop_metric, interval; bool root_is_gate; ttl = rann->rann_ttl; @@ -787,7 +787,7 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, interval = le32_to_cpu(rann->rann_interval); hopcount = rann->rann_hopcount; hopcount++; - metric = le32_to_cpu(rann->rann_metric); + orig_metric = le32_to_cpu(rann->rann_metric); /* Ignore our own RANNs */ if (ether_addr_equal(orig_addr, sdata->vif.addr)) @@ -804,7 +804,10 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, return; } - metric_txsta = airtime_link_metric_get(local, sta); + last_hop_metric = airtime_link_metric_get(local, sta); + new_metric = orig_metric + last_hop_metric; + if (new_metric < orig_metric) + new_metric = MAX_METRIC; mpath = mesh_path_lookup(sdata, orig_addr); if (!mpath) { @@ -817,7 +820,7 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, } if (!(SN_LT(mpath->sn, orig_sn)) && - !(mpath->sn == orig_sn && metric < mpath->rann_metric)) { + !(mpath->sn == orig_sn && new_metric < mpath->rann_metric)) { rcu_read_unlock(); return; } @@ -835,7 +838,7 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, } mpath->sn = orig_sn; - mpath->rann_metric = metric + metric_txsta; + mpath->rann_metric = new_metric; mpath->is_root = true; /* Recording RANNs sender address to send individually * addressed PREQs destined for root mesh STA */ @@ -855,7 +858,7 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, mesh_path_sel_frame_tx(MPATH_RANN, flags, orig_addr, orig_sn, 0, NULL, 0, broadcast_addr, hopcount, ttl, interval, - metric + metric_txsta, 0, sdata); + new_metric, 0, sdata); } rcu_read_unlock(); -- cgit v1.2.3 From ff8417176a69482e40f30036b4e9eb07360ec759 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 24 Nov 2017 12:00:24 -0500 Subject: SUNRPC: Allow connect to return EHOSTUNREACH [ Upstream commit 4ba161a793d5f43757c35feff258d9f20a082940 ] Reported-by: Dmitry Vyukov Signed-off-by: Trond Myklebust Tested-by: Dmitry Vyukov Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- net/sunrpc/xprtsock.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 27b6f55fa43a..728d65fbab0c 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2360,6 +2360,7 @@ static void xs_tcp_setup_socket(struct work_struct *work) case -ECONNREFUSED: case -ECONNRESET: case -ENETUNREACH: + case -EHOSTUNREACH: case -EADDRINUSE: case -ENOBUFS: /* retry with existing socket, after a delay */ -- cgit v1.2.3