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

Pull networking updates from David Miller:

 1) Unified UDP encapsulation offload methods for drivers, from
    Alexander Duyck.

 2) Make DSA binding more sane, from Andrew Lunn.

 3) Support QCA9888 chips in ath10k, from Anilkumar Kolli.

 4) Several workqueue usage cleanups, from Bhaktipriya Shridhar.

 5) Add XDP (eXpress Data Path), essentially running BPF programs on RX
    packets as soon as the device sees them, with the option to mirror
    the packet on TX via the same interface.  From Brenden Blanco and
    others.

 6) Allow qdisc/class stats dumps to run lockless, from Eric Dumazet.

 7) Add VLAN support to b53 and bcm_sf2, from Florian Fainelli.

 8) Simplify netlink conntrack entry layout, from Florian Westphal.

 9) Add ipv4 forwarding support to mlxsw spectrum driver, from Ido
    Schimmel, Yotam Gigi, and Jiri Pirko.

10) Add SKB array infrastructure and convert tun and macvtap over to it.
    From Michael S Tsirkin and Jason Wang.

11) Support qdisc packet injection in pktgen, from John Fastabend.

12) Add neighbour monitoring framework to TIPC, from Jon Paul Maloy.

13) Add NV congestion control support to TCP, from Lawrence Brakmo.

14) Add GSO support to SCTP, from Marcelo Ricardo Leitner.

15) Allow GRO and RPS to function on macsec devices, from Paolo Abeni.

16) Support MPLS over IPV4, from Simon Horman.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1622 commits)
  xgene: Fix build warning with ACPI disabled.
  be2net: perform temperature query in adapter regardless of its interface state
  l2tp: Correctly return -EBADF from pppol2tp_getname.
  net/mlx5_core/health: Remove deprecated create_singlethread_workqueue
  net: ipmr/ip6mr: update lastuse on entry change
  macsec: ensure rx_sa is set when validation is disabled
  tipc: dump monitor attributes
  tipc: add a function to get the bearer name
  tipc: get monitor threshold for the cluster
  tipc: make cluster size threshold for monitoring configurable
  tipc: introduce constants for tipc address validation
  net: neigh: disallow transition to NUD_STALE if lladdr is unchanged in neigh_update()
  MAINTAINERS: xgene: Add driver and documentation path
  Documentation: dtb: xgene: Add MDIO node
  dtb: xgene: Add MDIO node
  drivers: net: xgene: ethtool: Use phy_ethtool_gset and sset
  drivers: net: xgene: Use exported functions
  drivers: net: xgene: Enable MDIO driver
  drivers: net: xgene: Add backward compatibility
  drivers: net: phy: xgene: Add MDIO driver
  ...

1 files changed, 115 insertions, 49 deletions

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 26f603da7e26..b20438fdb029 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -81,6 +81,49 @@ static const struct bpf_func_proto bpf_probe_read_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+static u64 bpf_probe_write_user(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+	void *unsafe_ptr = (void *) (long) r1;
+	void *src = (void *) (long) r2;
+	int size = (int) r3;
+
+	/*
+	 * Ensure we're in user context which is safe for the helper to
+	 * run. This helper has no business in a kthread.
+	 *
+	 * access_ok() should prevent writing to non-user memory, but in
+	 * some situations (nommu, temporary switch, etc) access_ok() does
+	 * not provide enough validation, hence the check on KERNEL_DS.
+	 */
+
+	if (unlikely(in_interrupt() ||
+		     current->flags & (PF_KTHREAD | PF_EXITING)))
+		return -EPERM;
+	if (unlikely(segment_eq(get_fs(), KERNEL_DS)))
+		return -EPERM;
+	if (!access_ok(VERIFY_WRITE, unsafe_ptr, size))
+		return -EPERM;
+
+	return probe_kernel_write(unsafe_ptr, src, size);
+}
+
+static const struct bpf_func_proto bpf_probe_write_user_proto = {
+	.func		= bpf_probe_write_user,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_ANYTHING,
+	.arg2_type	= ARG_PTR_TO_STACK,
+	.arg3_type	= ARG_CONST_STACK_SIZE,
+};
+
+static const struct bpf_func_proto *bpf_get_probe_write_proto(void)
+{
+	pr_warn_ratelimited("%s[%d] is installing a program with bpf_probe_write_user helper that may corrupt user memory!",
+			    current->comm, task_pid_nr(current));
+
+	return &bpf_probe_write_user_proto;
+}
+
 /*
  * limited trace_printk()
  * only %d %u %x %ld %lu %lx %lld %llu %llx %p %s conversion specifiers allowed
@@ -188,31 +231,35 @@ 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)
+static u64 bpf_perf_event_read(u64 r1, u64 flags, 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);
+	unsigned int cpu = smp_processor_id();
+	u64 index = flags & BPF_F_INDEX_MASK;
+	struct bpf_event_entry *ee;
 	struct perf_event *event;
-	struct file *file;
 
+	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
+		return -EINVAL;
+	if (index == BPF_F_CURRENT_CPU)
+		index = cpu;
 	if (unlikely(index >= array->map.max_entries))
 		return -E2BIG;
 
-	file = READ_ONCE(array->ptrs[index]);
-	if (unlikely(!file))
+	ee = READ_ONCE(array->ptrs[index]);
+	if (!ee)
 		return -ENOENT;
 
-	event = file->private_data;
-
-	/* make sure event is local and doesn't have pmu::count */
-	if (event->oncpu != smp_processor_id() ||
-	    event->pmu->count)
-		return -EINVAL;
-
+	event = ee->event;
 	if (unlikely(event->attr.type != PERF_TYPE_HARDWARE &&
 		     event->attr.type != PERF_TYPE_RAW))
 		return -EINVAL;
 
+	/* make sure event is local and doesn't have pmu::count */
+	if (unlikely(event->oncpu != cpu || event->pmu->count))
+		return -EINVAL;
+
 	/*
 	 * we don't know if the function is run successfully by the
 	 * return value. It can be judged in other places, such as
@@ -229,47 +276,58 @@ static const struct bpf_func_proto bpf_perf_event_read_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
-static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size)
+static __always_inline u64
+__bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
+			u64 flags, struct perf_raw_record *raw)
 {
-	struct pt_regs *regs = (struct pt_regs *) (long) r1;
-	struct bpf_map *map = (struct bpf_map *) (long) r2;
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	unsigned int cpu = smp_processor_id();
 	u64 index = flags & BPF_F_INDEX_MASK;
-	void *data = (void *) (long) r4;
 	struct perf_sample_data sample_data;
+	struct bpf_event_entry *ee;
 	struct perf_event *event;
-	struct file *file;
-	struct perf_raw_record raw = {
-		.size = size,
-		.data = data,
-	};
 
-	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
-		return -EINVAL;
 	if (index == BPF_F_CURRENT_CPU)
-		index = raw_smp_processor_id();
+		index = cpu;
 	if (unlikely(index >= array->map.max_entries))
 		return -E2BIG;
 
-	file = READ_ONCE(array->ptrs[index]);
-	if (unlikely(!file))
+	ee = READ_ONCE(array->ptrs[index]);
+	if (!ee)
 		return -ENOENT;
 
-	event = file->private_data;
-
+	event = ee->event;
 	if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE ||
 		     event->attr.config != PERF_COUNT_SW_BPF_OUTPUT))
 		return -EINVAL;
 
-	if (unlikely(event->oncpu != smp_processor_id()))
+	if (unlikely(event->oncpu != cpu))
 		return -EOPNOTSUPP;
 
 	perf_sample_data_init(&sample_data, 0, 0);
-	sample_data.raw = &raw;
+	sample_data.raw = raw;
 	perf_event_output(event, &sample_data, regs);
 	return 0;
 }
 
+static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size)
+{
+	struct pt_regs *regs = (struct pt_regs *)(long) r1;
+	struct bpf_map *map  = (struct bpf_map *)(long) r2;
+	void *data = (void *)(long) r4;
+	struct perf_raw_record raw = {
+		.frag = {
+			.size = size,
+			.data = data,
+		},
+	};
+
+	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
+		return -EINVAL;
+
+	return __bpf_perf_event_output(regs, map, flags, &raw);
+}
+
 static const struct bpf_func_proto bpf_perf_event_output_proto = {
 	.func		= bpf_perf_event_output,
 	.gpl_only	= true,
@@ -283,31 +341,41 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = {
 
 static DEFINE_PER_CPU(struct pt_regs, bpf_pt_regs);
 
-static u64 bpf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size)
+u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
+		     void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy)
 {
 	struct pt_regs *regs = this_cpu_ptr(&bpf_pt_regs);
+	struct perf_raw_frag frag = {
+		.copy		= ctx_copy,
+		.size		= ctx_size,
+		.data		= ctx,
+	};
+	struct perf_raw_record raw = {
+		.frag = {
+			{
+				.next	= ctx_size ? &frag : NULL,
+			},
+			.size	= meta_size,
+			.data	= meta,
+		},
+	};
 
 	perf_fetch_caller_regs(regs);
 
-	return bpf_perf_event_output((long)regs, r2, flags, r4, size);
+	return __bpf_perf_event_output(regs, map, flags, &raw);
+}
+
+static u64 bpf_get_current_task(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+	return (long) current;
 }
 
-static const struct bpf_func_proto bpf_event_output_proto = {
-	.func		= bpf_event_output,
+static const struct bpf_func_proto bpf_get_current_task_proto = {
+	.func		= bpf_get_current_task,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
-	.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,
 };
 
-const struct bpf_func_proto *bpf_get_event_output_proto(void)
-{
-	return &bpf_event_output_proto;
-}
-
 static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
@@ -325,6 +393,8 @@ static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
 		return &bpf_tail_call_proto;
 	case BPF_FUNC_get_current_pid_tgid:
 		return &bpf_get_current_pid_tgid_proto;
+	case BPF_FUNC_get_current_task:
+		return &bpf_get_current_task_proto;
 	case BPF_FUNC_get_current_uid_gid:
 		return &bpf_get_current_uid_gid_proto;
 	case BPF_FUNC_get_current_comm:
@@ -335,6 +405,8 @@ static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
 		return &bpf_get_smp_processor_id_proto;
 	case BPF_FUNC_perf_event_read:
 		return &bpf_perf_event_read_proto;
+	case BPF_FUNC_probe_write_user:
+		return bpf_get_probe_write_proto();
 	default:
 		return NULL;
 	}
@@ -356,18 +428,12 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
 static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
 					enum bpf_reg_type *reg_type)
 {
-	/* check bounds */
 	if (off < 0 || off >= sizeof(struct pt_regs))
 		return false;
-
-	/* only read is allowed */
 	if (type != BPF_READ)
 		return false;
-
-	/* disallow misaligned access */
 	if (off % size != 0)
 		return false;
-
 	return true;
 }