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

Pull networking updates from David Miller:
 "Highlights:

   1) Support TX_RING in AF_PACKET TPACKET_V3 mode, from Sowmini
      Varadhan.

   2) Simplify classifier state on sk_buff in order to shrink it a bit.
      From Willem de Bruijn.

   3) Introduce SIPHASH and it's usage for secure sequence numbers and
      syncookies. From Jason A. Donenfeld.

   4) Reduce CPU usage for ICMP replies we are going to limit or
      suppress, from Jesper Dangaard Brouer.

   5) Introduce Shared Memory Communications socket layer, from Ursula
      Braun.

   6) Add RACK loss detection and allow it to actually trigger fast
      recovery instead of just assisting after other algorithms have
      triggered it. From Yuchung Cheng.

   7) Add xmit_more and BQL support to mvneta driver, from Simon Guinot.

   8) skb_cow_data avoidance in esp4 and esp6, from Steffen Klassert.

   9) Export MPLS packet stats via netlink, from Robert Shearman.

  10) Significantly improve inet port bind conflict handling, especially
      when an application is restarted and changes it's setting of
      reuseport. From Josef Bacik.

  11) Implement TX batching in vhost_net, from Jason Wang.

  12) Extend the dummy device so that VF (virtual function) features,
      such as configuration, can be more easily tested. From Phil
      Sutter.

  13) Avoid two atomic ops per page on x86 in bnx2x driver, from Eric
      Dumazet.

  14) Add new bpf MAP, implementing a longest prefix match trie. From
      Daniel Mack.

  15) Packet sample offloading support in mlxsw driver, from Yotam Gigi.

  16) Add new aquantia driver, from David VomLehn.

  17) Add bpf tracepoints, from Daniel Borkmann.

  18) Add support for port mirroring to b53 and bcm_sf2 drivers, from
      Florian Fainelli.

  19) Remove custom busy polling in many drivers, it is done in the core
      networking since 4.5 times. From Eric Dumazet.

  20) Support XDP adjust_head in virtio_net, from John Fastabend.

  21) Fix several major holes in neighbour entry confirmation, from
      Julian Anastasov.

  22) Add XDP support to bnxt_en driver, from Michael Chan.

  23) VXLAN offloads for enic driver, from Govindarajulu Varadarajan.

  24) Add IPVTAP driver (IP-VLAN based tap driver) from Sainath Grandhi.

  25) Support GRO in IPSEC protocols, from Steffen Klassert"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1764 commits)
  Revert "ath10k: Search SMBIOS for OEM board file extension"
  net: socket: fix recvmmsg not returning error from sock_error
  bnxt_en: use eth_hw_addr_random()
  bpf: fix unlocking of jited image when module ronx not set
  arch: add ARCH_HAS_SET_MEMORY config
  net: napi_watchdog() can use napi_schedule_irqoff()
  tcp: Revert "tcp: tcp_probe: use spin_lock_bh()"
  net/hsr: use eth_hw_addr_random()
  net: mvpp2: enable building on 64-bit platforms
  net: mvpp2: switch to build_skb() in the RX path
  net: mvpp2: simplify MVPP2_PRS_RI_* definitions
  net: mvpp2: fix indentation of MVPP2_EXT_GLOBAL_CTRL_DEFAULT
  net: mvpp2: remove unused register definitions
  net: mvpp2: simplify mvpp2_bm_bufs_add()
  net: mvpp2: drop useless fields in mvpp2_bm_pool and related code
  net: mvpp2: remove unused 'tx_skb' field of 'struct mvpp2_tx_queue'
  net: mvpp2: release reference to txq_cpu[] entry after unmapping
  net: mvpp2: handle too large value in mvpp2_rx_time_coal_set()
  net: mvpp2: handle too large value handling in mvpp2_rx_pkts_coal_set()
  net: mvpp2: remove useless arguments in mvpp2_rx_{pkts, time}_coal_set
  ...

2 files changed, 77 insertions, 23 deletions

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index fa77311dadb2..cee9802cf3e0 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -76,8 +76,8 @@ static const struct bpf_func_proto bpf_probe_read_proto = {
 	.func		= bpf_probe_read,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_RAW_STACK,
-	.arg2_type	= ARG_CONST_STACK_SIZE,
+	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg2_type	= ARG_CONST_SIZE,
 	.arg3_type	= ARG_ANYTHING,
 };
 
@@ -109,8 +109,8 @@ static const struct bpf_func_proto bpf_probe_write_user_proto = {
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_ANYTHING,
-	.arg2_type	= ARG_PTR_TO_STACK,
-	.arg3_type	= ARG_CONST_STACK_SIZE,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
 };
 
 static const struct bpf_func_proto *bpf_get_probe_write_proto(void)
@@ -213,8 +213,8 @@ static const struct bpf_func_proto bpf_trace_printk_proto = {
 	.func		= bpf_trace_printk,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_STACK,
-	.arg2_type	= ARG_CONST_STACK_SIZE,
+	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_CONST_SIZE,
 };
 
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
@@ -329,8 +329,8 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_CONST_MAP_PTR,
 	.arg3_type	= ARG_ANYTHING,
-	.arg4_type	= ARG_PTR_TO_STACK,
-	.arg5_type	= ARG_CONST_STACK_SIZE,
+	.arg4_type	= ARG_PTR_TO_MEM,
+	.arg5_type	= ARG_CONST_SIZE,
 };
 
 static DEFINE_PER_CPU(struct pt_regs, bpf_pt_regs);
@@ -395,6 +395,36 @@ static const struct bpf_func_proto bpf_current_task_under_cgroup_proto = {
 	.arg2_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_3(bpf_probe_read_str, void *, dst, u32, size,
+	   const void *, unsafe_ptr)
+{
+	int ret;
+
+	/*
+	 * The strncpy_from_unsafe() call will likely not fill the entire
+	 * buffer, but that's okay in this circumstance as we're probing
+	 * arbitrary memory anyway similar to bpf_probe_read() and might
+	 * as well probe the stack. Thus, memory is explicitly cleared
+	 * only in error case, so that improper users ignoring return
+	 * code altogether don't copy garbage; otherwise length of string
+	 * is returned that can be used for bpf_perf_event_output() et al.
+	 */
+	ret = strncpy_from_unsafe(dst, unsafe_ptr, size);
+	if (unlikely(ret < 0))
+		memset(dst, 0, size);
+
+	return ret;
+}
+
+static const struct bpf_func_proto bpf_probe_read_str_proto = {
+	.func		= bpf_probe_read_str,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg2_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_ANYTHING,
+};
+
 static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
@@ -432,6 +462,8 @@ static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
 		return &bpf_current_task_under_cgroup_proto;
 	case BPF_FUNC_get_prandom_u32:
 		return &bpf_get_prandom_u32_proto;
+	case BPF_FUNC_probe_read_str:
+		return &bpf_probe_read_str_proto;
 	default:
 		return NULL;
 	}
@@ -459,6 +491,13 @@ static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type
 		return false;
 	if (off % size != 0)
 		return false;
+	/*
+	 * Assertion for 32 bit to make sure last 8 byte access
+	 * (BPF_DW) to the last 4 byte member is disallowed.
+	 */
+	if (off + size > sizeof(struct pt_regs))
+		return false;
+
 	return true;
 }
 
@@ -467,7 +506,7 @@ static const struct bpf_verifier_ops kprobe_prog_ops = {
 	.is_valid_access = kprobe_prog_is_valid_access,
 };
 
-static struct bpf_prog_type_list kprobe_tl = {
+static struct bpf_prog_type_list kprobe_tl __ro_after_init = {
 	.ops	= &kprobe_prog_ops,
 	.type	= BPF_PROG_TYPE_KPROBE,
 };
@@ -492,8 +531,8 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_tp = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_CONST_MAP_PTR,
 	.arg3_type	= ARG_ANYTHING,
-	.arg4_type	= ARG_PTR_TO_STACK,
-	.arg5_type	= ARG_CONST_STACK_SIZE,
+	.arg4_type	= ARG_PTR_TO_MEM,
+	.arg5_type	= ARG_CONST_SIZE,
 };
 
 BPF_CALL_3(bpf_get_stackid_tp, void *, tp_buff, struct bpf_map *, map,
@@ -540,6 +579,8 @@ static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type
 		return false;
 	if (off % size != 0)
 		return false;
+
+	BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(__u64));
 	return true;
 }
 
@@ -548,7 +589,7 @@ static const struct bpf_verifier_ops tracepoint_prog_ops = {
 	.is_valid_access = tp_prog_is_valid_access,
 };
 
-static struct bpf_prog_type_list tracepoint_tl = {
+static struct bpf_prog_type_list tracepoint_tl __ro_after_init = {
 	.ops	= &tracepoint_prog_ops,
 	.type	= BPF_PROG_TYPE_TRACEPOINT,
 };
@@ -572,28 +613,29 @@ static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type
 	return true;
 }
 
-static u32 pe_prog_convert_ctx_access(enum bpf_access_type type, int dst_reg,
-				      int src_reg, int ctx_off,
+static u32 pe_prog_convert_ctx_access(enum bpf_access_type type,
+				      const struct bpf_insn *si,
 				      struct bpf_insn *insn_buf,
 				      struct bpf_prog *prog)
 {
 	struct bpf_insn *insn = insn_buf;
 
-	switch (ctx_off) {
+	switch (si->off) {
 	case offsetof(struct bpf_perf_event_data, sample_period):
 		BUILD_BUG_ON(FIELD_SIZEOF(struct perf_sample_data, period) != sizeof(u64));
 
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern,
-						       data), dst_reg, src_reg,
+						       data), si->dst_reg, si->src_reg,
 				      offsetof(struct bpf_perf_event_data_kern, data));
-		*insn++ = BPF_LDX_MEM(BPF_DW, dst_reg, dst_reg,
+		*insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg,
 				      offsetof(struct perf_sample_data, period));
 		break;
 	default:
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern,
-						       regs), dst_reg, src_reg,
+						       regs), si->dst_reg, si->src_reg,
 				      offsetof(struct bpf_perf_event_data_kern, regs));
-		*insn++ = BPF_LDX_MEM(BPF_SIZEOF(long), dst_reg, dst_reg, ctx_off);
+		*insn++ = BPF_LDX_MEM(BPF_SIZEOF(long), si->dst_reg, si->dst_reg,
+				      si->off);
 		break;
 	}
 
@@ -606,7 +648,7 @@ static const struct bpf_verifier_ops perf_event_prog_ops = {
 	.convert_ctx_access	= pe_prog_convert_ctx_access,
 };
 
-static struct bpf_prog_type_list perf_event_tl = {
+static struct bpf_prog_type_list perf_event_tl __ro_after_init = {
 	.ops	= &perf_event_prog_ops,
 	.type	= BPF_PROG_TYPE_PERF_EVENT,
 };
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 5d33a7352919..aea6a1218c7d 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -162,15 +162,27 @@ trace_print_bitmask_seq(struct trace_seq *p, void *bitmask_ptr,
 }
 EXPORT_SYMBOL_GPL(trace_print_bitmask_seq);
 
+/**
+ * trace_print_hex_seq - print buffer as hex sequence
+ * @p: trace seq struct to write to
+ * @buf: The buffer to print
+ * @buf_len: Length of @buf in bytes
+ * @concatenate: Print @buf as single hex string or with spacing
+ *
+ * Prints the passed buffer as a hex sequence either as a whole,
+ * single hex string if @concatenate is true or with spacing after
+ * each byte in case @concatenate is false.
+ */
 const char *
-trace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len)
+trace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len,
+		    bool concatenate)
 {
 	int i;
 	const char *ret = trace_seq_buffer_ptr(p);
 
 	for (i = 0; i < buf_len; i++)
-		trace_seq_printf(p, "%s%2.2x", i == 0 ? "" : " ", buf[i]);
-
+		trace_seq_printf(p, "%s%2.2x", concatenate || i == 0 ? "" : " ",
+				 buf[i]);
 	trace_seq_putc(p, 0);
 
 	return ret;