Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Another merge window, another set of networking changes.  I've heard
  rumblings that the lightweight tunnels infrastructure has been voted
  networking change of the year.  But what do I know?

   1) Add conntrack support to openvswitch, from Joe Stringer.

   2) Initial support for VRF (Virtual Routing and Forwarding), which
      allows the segmentation of routing paths without using multiple
      devices.  There are some semantic kinks to work out still, but
      this is a reasonably strong foundation.  From David Ahern.

   3) Remove spinlock fro act_bpf fast path, from Alexei Starovoitov.

   4) Ignore route nexthops with a link down state in ipv6, just like
      ipv4.  From Andy Gospodarek.

   5) Remove spinlock from fast path of act_gact and act_mirred, from
      Eric Dumazet.

   6) Document the DSA layer, from Florian Fainelli.

   7) Add netconsole support to bcmgenet, systemport, and DSA.  Also
      from Florian Fainelli.

   8) Add Mellanox Switch Driver and core infrastructure, from Jiri
      Pirko.

   9) Add support for "light weight tunnels", which allow for
      encapsulation and decapsulation without bearing the overhead of a
      full blown netdevice.  From Thomas Graf, Jiri Benc, and a cast of
      others.

  10) Add Identifier Locator Addressing support for ipv6, from Tom
      Herbert.

  11) Support fragmented SKBs in iwlwifi, from Johannes Berg.

  12) Allow perf PMUs to be accessed from eBPF programs, from Kaixu Xia.

  13) Add BQL support to 3c59x driver, from Loganaden Velvindron.

  14) Stop using a zero TX queue length to mean that a device shouldn't
      have a qdisc attached, use an explicit flag instead.  From Phil
      Sutter.

  15) Use generic geneve netdevice infrastructure in openvswitch, from
      Pravin B Shelar.

  16) Add infrastructure to avoid re-forwarding a packet in software
      that was already forwarded by a hardware switch.  From Scott
      Feldman.

  17) Allow AF_PACKET fanout function to be implemented in a bpf
      program, from Willem de Bruijn"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1458 commits)
  netfilter: nf_conntrack: make nf_ct_zone_dflt built-in
  netfilter: nf_dup{4, 6}: fix build error when nf_conntrack disabled
  net: fec: clear receive interrupts before processing a packet
  ipv6: fix exthdrs offload registration in out_rt path
  xen-netback: add support for multicast control
  bgmac: Update fixed_phy_register()
  sock, diag: fix panic in sock_diag_put_filterinfo
  flow_dissector: Use 'const' where possible.
  flow_dissector: Fix function argument ordering dependency
  ixgbe: Resolve "initialized field overwritten" warnings
  ixgbe: Remove bimodal SR-IOV disabling
  ixgbe: Add support for reporting 2.5G link speed
  ixgbe: fix bounds checking in ixgbe_setup_tc for 82598
  ixgbe: support for ethtool set_rxfh
  ixgbe: Avoid needless PHY access on copper phys
  ixgbe: cleanup to use cached mask value
  ixgbe: Remove second instance of lan_id variable
  ixgbe: use kzalloc for allocating one thing
  flow: Move __get_hash_from_flowi{4,6} into flow_dissector.c
  ixgbe: Remove unused PCI bus types
  ...

2 files changed, 65 insertions, 18 deletions

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 88a041adee90..0fe96c7c8803 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -81,13 +81,16 @@ static const struct bpf_func_proto bpf_probe_read_proto = {
 
 /*
  * limited trace_printk()
- * only %d %u %x %ld %lu %lx %lld %llu %llx %p conversion specifiers allowed
+ * only %d %u %x %ld %lu %lx %lld %llu %llx %p %s conversion specifiers allowed
  */
 static u64 bpf_trace_printk(u64 r1, u64 fmt_size, u64 r3, u64 r4, u64 r5)
 {
 	char *fmt = (char *) (long) r1;
+	bool str_seen = false;
 	int mod[3] = {};
 	int fmt_cnt = 0;
+	u64 unsafe_addr;
+	char buf[64];
 	int i;
 
 	/*
@@ -114,12 +117,37 @@ static u64 bpf_trace_printk(u64 r1, u64 fmt_size, u64 r3, u64 r4, u64 r5)
 		if (fmt[i] == 'l') {
 			mod[fmt_cnt]++;
 			i++;
-		} else if (fmt[i] == 'p') {
+		} else if (fmt[i] == 'p' || fmt[i] == 's') {
 			mod[fmt_cnt]++;
 			i++;
 			if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0)
 				return -EINVAL;
 			fmt_cnt++;
+			if (fmt[i - 1] == 's') {
+				if (str_seen)
+					/* allow only one '%s' per fmt string */
+					return -EINVAL;
+				str_seen = true;
+
+				switch (fmt_cnt) {
+				case 1:
+					unsafe_addr = r3;
+					r3 = (long) buf;
+					break;
+				case 2:
+					unsafe_addr = r4;
+					r4 = (long) buf;
+					break;
+				case 3:
+					unsafe_addr = r5;
+					r5 = (long) buf;
+					break;
+				}
+				buf[0] = 0;
+				strncpy_from_unsafe(buf,
+						    (void *) (long) unsafe_addr,
+						    sizeof(buf));
+			}
 			continue;
 		}
 
@@ -158,6 +186,35 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
 	return &bpf_trace_printk_proto;
 }
 
+static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5)
+{
+	struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct perf_event *event;
+
+	if (unlikely(index >= array->map.max_entries))
+		return -E2BIG;
+
+	event = (struct perf_event *)array->ptrs[index];
+	if (!event)
+		return -ENOENT;
+
+	/*
+	 * we don't know if the function is run successfully by the
+	 * return value. It can be judged in other places, such as
+	 * eBPF programs.
+	 */
+	return perf_event_read_local(event);
+}
+
+const struct bpf_func_proto bpf_perf_event_read_proto = {
+	.func		= bpf_perf_event_read,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
@@ -183,6 +240,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
 		return bpf_get_trace_printk_proto();
 	case BPF_FUNC_get_smp_processor_id:
 		return &bpf_get_smp_processor_id_proto;
+	case BPF_FUNC_perf_event_read:
+		return &bpf_perf_event_read_proto;
 	default:
 		return NULL;
 	}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index b7d0cdd9906c..c9956440d0e6 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -165,11 +165,9 @@ DEFINE_BASIC_FETCH_FUNCS(memory)
 static void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
 					    void *addr, void *dest)
 {
-	long ret;
 	int maxlen = get_rloc_len(*(u32 *)dest);
 	u8 *dst = get_rloc_data(dest);
-	u8 *src = addr;
-	mm_segment_t old_fs = get_fs();
+	long ret;
 
 	if (!maxlen)
 		return;
@@ -178,23 +176,13 @@ static void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
 	 * Try to get string again, since the string can be changed while
 	 * probing.
 	 */
-	set_fs(KERNEL_DS);
-	pagefault_disable();
-
-	do
-		ret = __copy_from_user_inatomic(dst++, src++, 1);
-	while (dst[-1] && ret == 0 && src - (u8 *)addr < maxlen);
-
-	dst[-1] = '\0';
-	pagefault_enable();
-	set_fs(old_fs);
+	ret = strncpy_from_unsafe(dst, addr, maxlen);
 
 	if (ret < 0) {	/* Failed to fetch string */
-		((u8 *)get_rloc_data(dest))[0] = '\0';
+		dst[0] = '\0';
 		*(u32 *)dest = make_data_rloc(0, get_rloc_offs(*(u32 *)dest));
 	} else {
-		*(u32 *)dest = make_data_rloc(src - (u8 *)addr,
-					      get_rloc_offs(*(u32 *)dest));
+		*(u32 *)dest = make_data_rloc(ret, get_rloc_offs(*(u32 *)dest));
 	}
 }
 NOKPROBE_SYMBOL(FETCH_FUNC_NAME(memory, string));