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

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

4 files changed, 185 insertions, 35 deletions

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 95888ae6c263..a5580c670866 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -15,9 +15,11 @@
 #include <linux/ctype.h>
 #include "trace.h"
 
+u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
+
 /**
  * trace_call_bpf - invoke BPF program
- * @prog: BPF program
+ * @call: tracepoint event
  * @ctx: opaque context pointer
  *
  * kprobe handlers execute BPF programs via this helper.
@@ -29,7 +31,7 @@
  * 1 - store kprobe event into ring buffer
  * Other values are reserved and currently alias to 1
  */
-unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx)
+unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
 {
 	unsigned int ret;
 
@@ -49,9 +51,22 @@ unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx)
 		goto out;
 	}
 
-	rcu_read_lock();
-	ret = BPF_PROG_RUN(prog, ctx);
-	rcu_read_unlock();
+	/*
+	 * Instead of moving rcu_read_lock/rcu_dereference/rcu_read_unlock
+	 * to all call sites, we did a bpf_prog_array_valid() there to check
+	 * whether call->prog_array is empty or not, which is
+	 * a heurisitc to speed up execution.
+	 *
+	 * If bpf_prog_array_valid() fetched prog_array was
+	 * non-NULL, we go into trace_call_bpf() and do the actual
+	 * proper rcu_dereference() under RCU lock.
+	 * If it turns out that prog_array is NULL then, we bail out.
+	 * For the opposite, if the bpf_prog_array_valid() fetched pointer
+	 * was NULL, you'll skip the prog_array with the risk of missing
+	 * out of events when it was updated in between this and the
+	 * rcu_dereference() which is accepted risk.
+	 */
+	ret = BPF_PROG_RUN_ARRAY_CHECK(call->prog_array, ctx, BPF_PROG_RUN);
 
  out:
 	__this_cpu_dec(bpf_prog_active);
@@ -63,12 +78,16 @@ EXPORT_SYMBOL_GPL(trace_call_bpf);
 
 BPF_CALL_3(bpf_probe_read, void *, dst, u32, size, const void *, unsafe_ptr)
 {
-	int ret;
+	int ret = 0;
+
+	if (unlikely(size == 0))
+		goto out;
 
 	ret = probe_kernel_read(dst, unsafe_ptr, size);
 	if (unlikely(ret < 0))
 		memset(dst, 0, size);
 
+ out:
 	return ret;
 }
 
@@ -77,7 +96,7 @@ static const struct bpf_func_proto bpf_probe_read_proto = {
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
-	.arg2_type	= ARG_CONST_SIZE,
+	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg3_type	= ARG_ANYTHING,
 };
 
@@ -255,14 +274,14 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
 	return &bpf_trace_printk_proto;
 }
 
-BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags)
+static __always_inline int
+get_map_perf_counter(struct bpf_map *map, u64 flags,
+		     u64 *value, u64 *enabled, u64 *running)
 {
 	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;
-	u64 value = 0;
-	int err;
 
 	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
 		return -EINVAL;
@@ -275,7 +294,15 @@ BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags)
 	if (!ee)
 		return -ENOENT;
 
-	err = perf_event_read_local(ee->event, &value, NULL, NULL);
+	return perf_event_read_local(ee->event, value, enabled, running);
+}
+
+BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags)
+{
+	u64 value = 0;
+	int err;
+
+	err = get_map_perf_counter(map, flags, &value, NULL, NULL);
 	/*
 	 * this api is ugly since we miss [-22..-2] range of valid
 	 * counter values, but that's uapi
@@ -293,6 +320,33 @@ static const struct bpf_func_proto bpf_perf_event_read_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_4(bpf_perf_event_read_value, struct bpf_map *, map, u64, flags,
+	   struct bpf_perf_event_value *, buf, u32, size)
+{
+	int err = -EINVAL;
+
+	if (unlikely(size != sizeof(struct bpf_perf_event_value)))
+		goto clear;
+	err = get_map_perf_counter(map, flags, &buf->counter, &buf->enabled,
+				   &buf->running);
+	if (unlikely(err))
+		goto clear;
+	return 0;
+clear:
+	memset(buf, 0, size);
+	return err;
+}
+
+static const struct bpf_func_proto bpf_perf_event_read_value_proto = {
+	.func		= bpf_perf_event_read_value,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+};
+
 static DEFINE_PER_CPU(struct perf_sample_data, bpf_sd);
 
 static __always_inline u64
@@ -499,6 +553,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
 		return &bpf_perf_event_output_proto;
 	case BPF_FUNC_get_stackid:
 		return &bpf_get_stackid_proto;
+	case BPF_FUNC_perf_event_read_value:
+		return &bpf_perf_event_read_value_proto;
 	default:
 		return tracing_func_proto(func_id);
 	}
@@ -524,11 +580,14 @@ static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type
 	return true;
 }
 
-const struct bpf_verifier_ops kprobe_prog_ops = {
+const struct bpf_verifier_ops kprobe_verifier_ops = {
 	.get_func_proto  = kprobe_prog_func_proto,
 	.is_valid_access = kprobe_prog_is_valid_access,
 };
 
+const struct bpf_prog_ops kprobe_prog_ops = {
+};
+
 BPF_CALL_5(bpf_perf_event_output_tp, void *, tp_buff, struct bpf_map *, map,
 	   u64, flags, void *, data, u64, size)
 {
@@ -576,6 +635,32 @@ static const struct bpf_func_proto bpf_get_stackid_proto_tp = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_3(bpf_perf_prog_read_value_tp, struct bpf_perf_event_data_kern *, ctx,
+	   struct bpf_perf_event_value *, buf, u32, size)
+{
+	int err = -EINVAL;
+
+	if (unlikely(size != sizeof(struct bpf_perf_event_value)))
+		goto clear;
+	err = perf_event_read_local(ctx->event, &buf->counter, &buf->enabled,
+				    &buf->running);
+	if (unlikely(err))
+		goto clear;
+	return 0;
+clear:
+	memset(buf, 0, size);
+	return err;
+}
+
+static const struct bpf_func_proto bpf_perf_prog_read_value_proto_tp = {
+         .func           = bpf_perf_prog_read_value_tp,
+         .gpl_only       = true,
+         .ret_type       = RET_INTEGER,
+         .arg1_type      = ARG_PTR_TO_CTX,
+         .arg2_type      = ARG_PTR_TO_UNINIT_MEM,
+         .arg3_type      = ARG_CONST_SIZE,
+};
+
 static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
@@ -583,6 +668,8 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
 		return &bpf_perf_event_output_proto_tp;
 	case BPF_FUNC_get_stackid:
 		return &bpf_get_stackid_proto_tp;
+	case BPF_FUNC_perf_prog_read_value:
+		return &bpf_perf_prog_read_value_proto_tp;
 	default:
 		return tracing_func_proto(func_id);
 	}
@@ -602,11 +689,14 @@ static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type
 	return true;
 }
 
-const struct bpf_verifier_ops tracepoint_prog_ops = {
+const struct bpf_verifier_ops tracepoint_verifier_ops = {
 	.get_func_proto  = tp_prog_func_proto,
 	.is_valid_access = tp_prog_is_valid_access,
 };
 
+const struct bpf_prog_ops tracepoint_prog_ops = {
+};
+
 static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
 				    struct bpf_insn_access_aux *info)
 {
@@ -662,8 +752,67 @@ static u32 pe_prog_convert_ctx_access(enum bpf_access_type type,
 	return insn - insn_buf;
 }
 
-const struct bpf_verifier_ops perf_event_prog_ops = {
+const struct bpf_verifier_ops perf_event_verifier_ops = {
 	.get_func_proto		= tp_prog_func_proto,
 	.is_valid_access	= pe_prog_is_valid_access,
 	.convert_ctx_access	= pe_prog_convert_ctx_access,
 };
+
+const struct bpf_prog_ops perf_event_prog_ops = {
+};
+
+static DEFINE_MUTEX(bpf_event_mutex);
+
+int perf_event_attach_bpf_prog(struct perf_event *event,
+			       struct bpf_prog *prog)
+{
+	struct bpf_prog_array __rcu *old_array;
+	struct bpf_prog_array *new_array;
+	int ret = -EEXIST;
+
+	mutex_lock(&bpf_event_mutex);
+
+	if (event->prog)
+		goto unlock;
+
+	old_array = event->tp_event->prog_array;
+	ret = bpf_prog_array_copy(old_array, NULL, prog, &new_array);
+	if (ret < 0)
+		goto unlock;
+
+	/* set the new array to event->tp_event and set event->prog */
+	event->prog = prog;
+	rcu_assign_pointer(event->tp_event->prog_array, new_array);
+	bpf_prog_array_free(old_array);
+
+unlock:
+	mutex_unlock(&bpf_event_mutex);
+	return ret;
+}
+
+void perf_event_detach_bpf_prog(struct perf_event *event)
+{
+	struct bpf_prog_array __rcu *old_array;
+	struct bpf_prog_array *new_array;
+	int ret;
+
+	mutex_lock(&bpf_event_mutex);
+
+	if (!event->prog)
+		goto unlock;
+
+	old_array = event->tp_event->prog_array;
+	ret = bpf_prog_array_copy(old_array, event->prog, NULL, &new_array);
+	if (ret < 0) {
+		bpf_prog_array_delete_safe(old_array, event->prog);
+	} else {
+		rcu_assign_pointer(event->tp_event->prog_array, new_array);
+		bpf_prog_array_free(old_array);
+	}
+
+	bpf_prog_put(event->prog);
+	event->prog = NULL;
+
+unlock:
+	mutex_unlock(&bpf_event_mutex);
+}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 8a907e12b6b9..abf92e478cfb 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1174,13 +1174,12 @@ static void
 kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 {
 	struct trace_event_call *call = &tk->tp.call;
-	struct bpf_prog *prog = call->prog;
 	struct kprobe_trace_entry_head *entry;
 	struct hlist_head *head;
 	int size, __size, dsize;
 	int rctx;
 
-	if (prog && !trace_call_bpf(prog, regs))
+	if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs))
 		return;
 
 	head = this_cpu_ptr(call->perf_events);
@@ -1210,13 +1209,12 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 		    struct pt_regs *regs)
 {
 	struct trace_event_call *call = &tk->tp.call;
-	struct bpf_prog *prog = call->prog;
 	struct kretprobe_trace_entry_head *entry;
 	struct hlist_head *head;
 	int size, __size, dsize;
 	int rctx;
 
-	if (prog && !trace_call_bpf(prog, regs))
+	if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs))
 		return;
 
 	head = this_cpu_ptr(call->perf_events);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index a2a642f2c64f..19bcaaac884b 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -560,9 +560,10 @@ static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls);
 static int sys_perf_refcount_enter;
 static int sys_perf_refcount_exit;
 
-static int perf_call_bpf_enter(struct bpf_prog *prog, struct pt_regs *regs,
-			      struct syscall_metadata *sys_data,
-			      struct syscall_trace_enter *rec) {
+static int perf_call_bpf_enter(struct trace_event_call *call, struct pt_regs *regs,
+			       struct syscall_metadata *sys_data,
+			       struct syscall_trace_enter *rec)
+{
 	struct syscall_tp_t {
 		unsigned long long regs;
 		unsigned long syscall_nr;
@@ -574,7 +575,7 @@ static int perf_call_bpf_enter(struct bpf_prog *prog, struct pt_regs *regs,
 	param.syscall_nr = rec->nr;
 	for (i = 0; i < sys_data->nb_args; i++)
 		param.args[i] = rec->args[i];
-	return trace_call_bpf(prog, &param);
+	return trace_call_bpf(call, &param);
 }
 
 static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
@@ -582,7 +583,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	struct syscall_metadata *sys_data;
 	struct syscall_trace_enter *rec;
 	struct hlist_head *head;
-	struct bpf_prog *prog;
+	bool valid_prog_array;
 	int syscall_nr;
 	int rctx;
 	int size;
@@ -597,9 +598,9 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	if (!sys_data)
 		return;
 
-	prog = READ_ONCE(sys_data->enter_event->prog);
 	head = this_cpu_ptr(sys_data->enter_event->perf_events);
-	if (!prog && hlist_empty(head))
+	valid_prog_array = bpf_prog_array_valid(sys_data->enter_event);
+	if (!valid_prog_array && hlist_empty(head))
 		return;
 
 	/* get the size after alignment with the u32 buffer size field */
@@ -615,7 +616,8 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	syscall_get_arguments(current, regs, 0, sys_data->nb_args,
 			       (unsigned long *)&rec->args);
 
-	if ((prog && !perf_call_bpf_enter(prog, regs, sys_data, rec)) ||
+	if ((valid_prog_array &&
+	     !perf_call_bpf_enter(sys_data->enter_event, regs, sys_data, rec)) ||
 	    hlist_empty(head)) {
 		perf_swevent_put_recursion_context(rctx);
 		return;
@@ -660,8 +662,9 @@ static void perf_sysenter_disable(struct trace_event_call *call)
 	mutex_unlock(&syscall_trace_lock);
 }
 
-static int perf_call_bpf_exit(struct bpf_prog *prog, struct pt_regs *regs,
-			      struct syscall_trace_exit *rec) {
+static int perf_call_bpf_exit(struct trace_event_call *call, struct pt_regs *regs,
+			      struct syscall_trace_exit *rec)
+{
 	struct syscall_tp_t {
 		unsigned long long regs;
 		unsigned long syscall_nr;
@@ -671,7 +674,7 @@ static int perf_call_bpf_exit(struct bpf_prog *prog, struct pt_regs *regs,
 	*(struct pt_regs **)&param = regs;
 	param.syscall_nr = rec->nr;
 	param.ret = rec->ret;
-	return trace_call_bpf(prog, &param);
+	return trace_call_bpf(call, &param);
 }
 
 static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
@@ -679,7 +682,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	struct syscall_metadata *sys_data;
 	struct syscall_trace_exit *rec;
 	struct hlist_head *head;
-	struct bpf_prog *prog;
+	bool valid_prog_array;
 	int syscall_nr;
 	int rctx;
 	int size;
@@ -694,9 +697,9 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	if (!sys_data)
 		return;
 
-	prog = READ_ONCE(sys_data->exit_event->prog);
 	head = this_cpu_ptr(sys_data->exit_event->perf_events);
-	if (!prog && hlist_empty(head))
+	valid_prog_array = bpf_prog_array_valid(sys_data->exit_event);
+	if (!valid_prog_array && hlist_empty(head))
 		return;
 
 	/* We can probably do that at build time */
@@ -710,7 +713,8 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	rec->nr = syscall_nr;
 	rec->ret = syscall_get_return_value(current, regs);
 
-	if ((prog && !perf_call_bpf_exit(prog, regs, rec)) ||
+	if ((valid_prog_array &&
+	     !perf_call_bpf_exit(sys_data->exit_event, regs, rec)) ||
 	    hlist_empty(head)) {
 		perf_swevent_put_recursion_context(rctx);
 		return;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 4525e0271a53..153c0e411461 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1113,13 +1113,12 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 {
 	struct trace_event_call *call = &tu->tp.call;
 	struct uprobe_trace_entry_head *entry;
-	struct bpf_prog *prog = call->prog;
 	struct hlist_head *head;
 	void *data;
 	int size, esize;
 	int rctx;
 
-	if (prog && !trace_call_bpf(prog, regs))
+	if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs))
 		return;
 
 	esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));