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
  ...

10 files changed, 201 insertions, 12 deletions

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 4450fed..63e7d50 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -12,6 +12,7 @@ hostprogs-y += tracex2
 hostprogs-y += tracex3
 hostprogs-y += tracex4
 hostprogs-y += tracex5
+hostprogs-y += tracex6
 hostprogs-y += lathist
 
 test_verifier-objs := test_verifier.o libbpf.o
@@ -25,6 +26,7 @@ tracex2-objs := bpf_load.o libbpf.o tracex2_user.o
 tracex3-objs := bpf_load.o libbpf.o tracex3_user.o
 tracex4-objs := bpf_load.o libbpf.o tracex4_user.o
 tracex5-objs := bpf_load.o libbpf.o tracex5_user.o
+tracex6-objs := bpf_load.o libbpf.o tracex6_user.o
 lathist-objs := bpf_load.o libbpf.o lathist_user.o
 
 # Tell kbuild to always build the programs
@@ -37,6 +39,7 @@ always += tracex2_kern.o
 always += tracex3_kern.o
 always += tracex4_kern.o
 always += tracex5_kern.o
+always += tracex6_kern.o
 always += tcbpf1_kern.o
 always += lathist_kern.o
 
@@ -51,6 +54,7 @@ HOSTLOADLIBES_tracex2 += -lelf
 HOSTLOADLIBES_tracex3 += -lelf
 HOSTLOADLIBES_tracex4 += -lelf -lrt
 HOSTLOADLIBES_tracex5 += -lelf
+HOSTLOADLIBES_tracex6 += -lelf
 HOSTLOADLIBES_lathist += -lelf
 
 # point this to your LLVM backend with bpf support
diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
index bdf1c16..3a44d3a 100644
--- a/samples/bpf/bpf_helpers.h
+++ b/samples/bpf/bpf_helpers.h
@@ -31,6 +31,8 @@ static unsigned long long (*bpf_get_current_uid_gid)(void) =
 	(void *) BPF_FUNC_get_current_uid_gid;
 static int (*bpf_get_current_comm)(void *buf, int buf_size) =
 	(void *) BPF_FUNC_get_current_comm;
+static int (*bpf_perf_event_read)(void *map, int index) =
+	(void *) BPF_FUNC_perf_event_read;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
@@ -60,4 +62,29 @@ static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flag
 static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) =
 	(void *) BPF_FUNC_l4_csum_replace;
 
+#if defined(__x86_64__)
+
+#define PT_REGS_PARM1(x) ((x)->di)
+#define PT_REGS_PARM2(x) ((x)->si)
+#define PT_REGS_PARM3(x) ((x)->dx)
+#define PT_REGS_PARM4(x) ((x)->cx)
+#define PT_REGS_PARM5(x) ((x)->r8)
+#define PT_REGS_RET(x) ((x)->sp)
+#define PT_REGS_FP(x) ((x)->bp)
+#define PT_REGS_RC(x) ((x)->ax)
+#define PT_REGS_SP(x) ((x)->sp)
+
+#elif defined(__s390x__)
+
+#define PT_REGS_PARM1(x) ((x)->gprs[2])
+#define PT_REGS_PARM2(x) ((x)->gprs[3])
+#define PT_REGS_PARM3(x) ((x)->gprs[4])
+#define PT_REGS_PARM4(x) ((x)->gprs[5])
+#define PT_REGS_PARM5(x) ((x)->gprs[6])
+#define PT_REGS_RET(x) ((x)->gprs[14])
+#define PT_REGS_FP(x) ((x)->gprs[11]) /* Works only with CONFIG_FRAME_POINTER */
+#define PT_REGS_RC(x) ((x)->gprs[2])
+#define PT_REGS_SP(x) ((x)->gprs[15])
+
+#endif
 #endif
diff --git a/samples/bpf/test_verifier.c b/samples/bpf/test_verifier.c
index 6936059..ee0f110 100644
--- a/samples/bpf/test_verifier.c
+++ b/samples/bpf/test_verifier.c
@@ -822,6 +822,65 @@ static struct bpf_test tests[] = {
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
+	{
+		"PTR_TO_STACK store/load",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -10),
+			BPF_ST_MEM(BPF_DW, BPF_REG_1, 2, 0xfaceb00c),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 2),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+	},
+	{
+		"PTR_TO_STACK store/load - bad alignment on off",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+			BPF_ST_MEM(BPF_DW, BPF_REG_1, 2, 0xfaceb00c),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 2),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "misaligned access off -6 size 8",
+	},
+	{
+		"PTR_TO_STACK store/load - bad alignment on reg",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -10),
+			BPF_ST_MEM(BPF_DW, BPF_REG_1, 8, 0xfaceb00c),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 8),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "misaligned access off -2 size 8",
+	},
+	{
+		"PTR_TO_STACK store/load - out of bounds low",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -80000),
+			BPF_ST_MEM(BPF_DW, BPF_REG_1, 8, 0xfaceb00c),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 8),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid stack off=-79992 size=8",
+	},
+	{
+		"PTR_TO_STACK store/load - out of bounds high",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+			BPF_ST_MEM(BPF_DW, BPF_REG_1, 8, 0xfaceb00c),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 8),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid stack off=0 size=8",
+	},
 };
 
 static int probe_filter_length(struct bpf_insn *fp)
diff --git a/samples/bpf/tracex1_kern.c b/samples/bpf/tracex1_kern.c
index 3162046..3f450a8 100644
--- a/samples/bpf/tracex1_kern.c
+++ b/samples/bpf/tracex1_kern.c
@@ -29,7 +29,7 @@ int bpf_prog1(struct pt_regs *ctx)
 	int len;
 
 	/* non-portable! works for the given kernel only */
-	skb = (struct sk_buff *) ctx->di;
+	skb = (struct sk_buff *) PT_REGS_PARM1(ctx);
 
 	dev = _(skb->dev);
 
diff --git a/samples/bpf/tracex2_kern.c b/samples/bpf/tracex2_kern.c
index dc50f4f..b32367c 100644
--- a/samples/bpf/tracex2_kern.c
+++ b/samples/bpf/tracex2_kern.c
@@ -27,10 +27,10 @@ int bpf_prog2(struct pt_regs *ctx)
 	long init_val = 1;
 	long *value;
 
-	/* x64 specific: read ip of kfree_skb caller.
+	/* x64/s390x specific: read ip of kfree_skb caller.
 	 * non-portable version of __builtin_return_address(0)
 	 */
-	bpf_probe_read(&loc, sizeof(loc), (void *)ctx->sp);
+	bpf_probe_read(&loc, sizeof(loc), (void *)PT_REGS_RET(ctx));
 
 	value = bpf_map_lookup_elem(&my_map, &loc);
 	if (value)
@@ -79,7 +79,7 @@ struct bpf_map_def SEC("maps") my_hist_map = {
 SEC("kprobe/sys_write")
 int bpf_prog3(struct pt_regs *ctx)
 {
-	long write_size = ctx->dx; /* arg3 */
+	long write_size = PT_REGS_PARM3(ctx);
 	long init_val = 1;
 	long *value;
 	struct hist_key key = {};
diff --git a/samples/bpf/tracex3_kern.c b/samples/bpf/tracex3_kern.c
index 255ff27..bf337fb 100644
--- a/samples/bpf/tracex3_kern.c
+++ b/samples/bpf/tracex3_kern.c
@@ -23,7 +23,7 @@ struct bpf_map_def SEC("maps") my_map = {
 SEC("kprobe/blk_mq_start_request")
 int bpf_prog1(struct pt_regs *ctx)
 {
-	long rq = ctx->di;
+	long rq = PT_REGS_PARM1(ctx);
 	u64 val = bpf_ktime_get_ns();
 
 	bpf_map_update_elem(&my_map, &rq, &val, BPF_ANY);
@@ -51,7 +51,7 @@ struct bpf_map_def SEC("maps") lat_map = {
 SEC("kprobe/blk_update_request")
 int bpf_prog2(struct pt_regs *ctx)
 {
-	long rq = ctx->di;
+	long rq = PT_REGS_PARM1(ctx);
 	u64 *value, l, base;
 	u32 index;
 
diff --git a/samples/bpf/tracex4_kern.c b/samples/bpf/tracex4_kern.c
index 126b805..ac46714 100644
--- a/samples/bpf/tracex4_kern.c
+++ b/samples/bpf/tracex4_kern.c
@@ -27,7 +27,7 @@ struct bpf_map_def SEC("maps") my_map = {
 SEC("kprobe/kmem_cache_free")
 int bpf_prog1(struct pt_regs *ctx)
 {
-	long ptr = ctx->si;
+	long ptr = PT_REGS_PARM2(ctx);
 
 	bpf_map_delete_elem(&my_map, &ptr);
 	return 0;
@@ -36,11 +36,11 @@ int bpf_prog1(struct pt_regs *ctx)
 SEC("kretprobe/kmem_cache_alloc_node")
 int bpf_prog2(struct pt_regs *ctx)
 {
-	long ptr = ctx->ax;
+	long ptr = PT_REGS_RC(ctx);
 	long ip = 0;
 
 	/* get ip address of kmem_cache_alloc_node() caller */
-	bpf_probe_read(&ip, sizeof(ip), (void *)(ctx->bp + sizeof(ip)));
+	bpf_probe_read(&ip, sizeof(ip), (void *)(PT_REGS_FP(ctx) + sizeof(ip)));
 
 	struct pair v = {
 		.val = bpf_ktime_get_ns(),
diff --git a/samples/bpf/tracex5_kern.c b/samples/bpf/tracex5_kern.c
index b71fe07..b3f4295 100644
--- a/samples/bpf/tracex5_kern.c
+++ b/samples/bpf/tracex5_kern.c
@@ -24,7 +24,7 @@ int bpf_prog1(struct pt_regs *ctx)
 {
 	struct seccomp_data sd = {};
 
-	bpf_probe_read(&sd, sizeof(sd), (void *)ctx->di);
+	bpf_probe_read(&sd, sizeof(sd), (void *)PT_REGS_PARM1(ctx));
 
 	/* dispatch into next BPF program depending on syscall number */
 	bpf_tail_call(ctx, &progs, sd.nr);
@@ -42,7 +42,7 @@ PROG(__NR_write)(struct pt_regs *ctx)
 {
 	struct seccomp_data sd = {};
 
-	bpf_probe_read(&sd, sizeof(sd), (void *)ctx->di);
+	bpf_probe_read(&sd, sizeof(sd), (void *)PT_REGS_PARM1(ctx));
 	if (sd.args[2] == 512) {
 		char fmt[] = "write(fd=%d, buf=%p, size=%d)\n";
 		bpf_trace_printk(fmt, sizeof(fmt),
@@ -55,7 +55,7 @@ PROG(__NR_read)(struct pt_regs *ctx)
 {
 	struct seccomp_data sd = {};
 
-	bpf_probe_read(&sd, sizeof(sd), (void *)ctx->di);
+	bpf_probe_read(&sd, sizeof(sd), (void *)PT_REGS_PARM1(ctx));
 	if (sd.args[2] > 128 && sd.args[2] <= 1024) {
 		char fmt[] = "read(fd=%d, buf=%p, size=%d)\n";
 		bpf_trace_printk(fmt, sizeof(fmt),
diff --git a/samples/bpf/tracex6_kern.c b/samples/bpf/tracex6_kern.c
new file mode 100644
index 0000000..be479c4
--- /dev/null
+++ b/samples/bpf/tracex6_kern.c
@@ -0,0 +1,27 @@
+#include <linux/ptrace.h>
+#include <linux/version.h>
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+struct bpf_map_def SEC("maps") my_map = {
+	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(u32),
+	.max_entries = 32,
+};
+
+SEC("kprobe/sys_write")
+int bpf_prog1(struct pt_regs *ctx)
+{
+	u64 count;
+	u32 key = bpf_get_smp_processor_id();
+	char fmt[] = "CPU-%d   %llu\n";
+
+	count = bpf_perf_event_read(&my_map, key);
+	bpf_trace_printk(fmt, sizeof(fmt), key, count);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/tracex6_user.c b/samples/bpf/tracex6_user.c
new file mode 100644
index 0000000..8ea4976
--- /dev/null
+++ b/samples/bpf/tracex6_user.c
@@ -0,0 +1,72 @@
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <fcntl.h>
+#include <poll.h>
+#include <sys/ioctl.h>
+#include <linux/perf_event.h>
+#include <linux/bpf.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+
+#define SAMPLE_PERIOD  0x7fffffffffffffffULL
+
+static void test_bpf_perf_event(void)
+{
+	int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+	int *pmu_fd = malloc(nr_cpus * sizeof(int));
+	int status, i;
+
+	struct perf_event_attr attr_insn_pmu = {
+		.freq = 0,
+		.sample_period = SAMPLE_PERIOD,
+		.inherit = 0,
+		.type = PERF_TYPE_HARDWARE,
+		.read_format = 0,
+		.sample_type = 0,
+		.config = 0,/* PMU: cycles */
+	};
+
+	for (i = 0; i < nr_cpus; i++) {
+		pmu_fd[i] = perf_event_open(&attr_insn_pmu, -1/*pid*/, i/*cpu*/, -1/*group_fd*/, 0);
+		if (pmu_fd[i] < 0) {
+			printf("event syscall failed\n");
+			goto exit;
+		}
+
+		bpf_update_elem(map_fd[0], &i, &pmu_fd[i], BPF_ANY);
+		ioctl(pmu_fd[i], PERF_EVENT_IOC_ENABLE, 0);
+	}
+
+	status = system("ls > /dev/null");
+	if (status)
+		goto exit;
+	status = system("sleep 2");
+	if (status)
+		goto exit;
+
+exit:
+	for (i = 0; i < nr_cpus; i++)
+		close(pmu_fd[i]);
+	close(map_fd[0]);
+	free(pmu_fd);
+}
+
+int main(int argc, char **argv)
+{
+	char filename[256];
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	if (load_bpf_file(filename)) {
+		printf("%s", bpf_log_buf);
+		return 1;
+	}
+
+	test_bpf_perf_event();
+	read_trace_pipe();
+
+	return 0;
+}