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
  ...

10 files changed, 418 insertions, 144 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 76d5a79..633a650 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -328,8 +328,8 @@ static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key)
 }
 
 /* only called from syscall */
-static int fd_array_map_update_elem(struct bpf_map *map, void *key,
-				    void *value, u64 map_flags)
+int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
+				 void *key, void *value, u64 map_flags)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	void *new_ptr, *old_ptr;
@@ -342,7 +342,7 @@ static int fd_array_map_update_elem(struct bpf_map *map, void *key,
 		return -E2BIG;
 
 	ufd = *(u32 *)value;
-	new_ptr = map->ops->map_fd_get_ptr(map, ufd);
+	new_ptr = map->ops->map_fd_get_ptr(map, map_file, ufd);
 	if (IS_ERR(new_ptr))
 		return PTR_ERR(new_ptr);
 
@@ -371,10 +371,12 @@ static int fd_array_map_delete_elem(struct bpf_map *map, void *key)
 	}
 }
 
-static void *prog_fd_array_get_ptr(struct bpf_map *map, int fd)
+static void *prog_fd_array_get_ptr(struct bpf_map *map,
+				   struct file *map_file, int fd)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	struct bpf_prog *prog = bpf_prog_get(fd);
+
 	if (IS_ERR(prog))
 		return prog;
 
@@ -382,14 +384,13 @@ static void *prog_fd_array_get_ptr(struct bpf_map *map, int fd)
 		bpf_prog_put(prog);
 		return ERR_PTR(-EINVAL);
 	}
+
 	return prog;
 }
 
 static void prog_fd_array_put_ptr(void *ptr)
 {
-	struct bpf_prog *prog = ptr;
-
-	bpf_prog_put_rcu(prog);
+	bpf_prog_put(ptr);
 }
 
 /* decrement refcnt of all bpf_progs that are stored in this map */
@@ -407,7 +408,6 @@ static const struct bpf_map_ops prog_array_ops = {
 	.map_free = fd_array_map_free,
 	.map_get_next_key = array_map_get_next_key,
 	.map_lookup_elem = fd_array_map_lookup_elem,
-	.map_update_elem = fd_array_map_update_elem,
 	.map_delete_elem = fd_array_map_delete_elem,
 	.map_fd_get_ptr = prog_fd_array_get_ptr,
 	.map_fd_put_ptr = prog_fd_array_put_ptr,
@@ -425,59 +425,105 @@ static int __init register_prog_array_map(void)
 }
 late_initcall(register_prog_array_map);
 
-static void perf_event_array_map_free(struct bpf_map *map)
+static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
+						   struct file *map_file)
 {
-	bpf_fd_array_map_clear(map);
-	fd_array_map_free(map);
+	struct bpf_event_entry *ee;
+
+	ee = kzalloc(sizeof(*ee), GFP_ATOMIC);
+	if (ee) {
+		ee->event = perf_file->private_data;
+		ee->perf_file = perf_file;
+		ee->map_file = map_file;
+	}
+
+	return ee;
 }
 
-static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd)
+static void __bpf_event_entry_free(struct rcu_head *rcu)
 {
-	struct perf_event *event;
-	const struct perf_event_attr *attr;
-	struct file *file;
+	struct bpf_event_entry *ee;
 
-	file = perf_event_get(fd);
-	if (IS_ERR(file))
-		return file;
+	ee = container_of(rcu, struct bpf_event_entry, rcu);
+	fput(ee->perf_file);
+	kfree(ee);
+}
 
-	event = file->private_data;
+static void bpf_event_entry_free_rcu(struct bpf_event_entry *ee)
+{
+	call_rcu(&ee->rcu, __bpf_event_entry_free);
+}
 
-	attr = perf_event_attrs(event);
-	if (IS_ERR(attr))
-		goto err;
+static void *perf_event_fd_array_get_ptr(struct bpf_map *map,
+					 struct file *map_file, int fd)
+{
+	const struct perf_event_attr *attr;
+	struct bpf_event_entry *ee;
+	struct perf_event *event;
+	struct file *perf_file;
 
-	if (attr->inherit)
-		goto err;
+	perf_file = perf_event_get(fd);
+	if (IS_ERR(perf_file))
+		return perf_file;
 
-	if (attr->type == PERF_TYPE_RAW)
-		return file;
+	event = perf_file->private_data;
+	ee = ERR_PTR(-EINVAL);
 
-	if (attr->type == PERF_TYPE_HARDWARE)
-		return file;
+	attr = perf_event_attrs(event);
+	if (IS_ERR(attr) || attr->inherit)
+		goto err_out;
+
+	switch (attr->type) {
+	case PERF_TYPE_SOFTWARE:
+		if (attr->config != PERF_COUNT_SW_BPF_OUTPUT)
+			goto err_out;
+		/* fall-through */
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HARDWARE:
+		ee = bpf_event_entry_gen(perf_file, map_file);
+		if (ee)
+			return ee;
+		ee = ERR_PTR(-ENOMEM);
+		/* fall-through */
+	default:
+		break;
+	}
 
-	if (attr->type == PERF_TYPE_SOFTWARE &&
-	    attr->config == PERF_COUNT_SW_BPF_OUTPUT)
-		return file;
-err:
-	fput(file);
-	return ERR_PTR(-EINVAL);
+err_out:
+	fput(perf_file);
+	return ee;
 }
 
 static void perf_event_fd_array_put_ptr(void *ptr)
 {
-	fput((struct file *)ptr);
+	bpf_event_entry_free_rcu(ptr);
+}
+
+static void perf_event_fd_array_release(struct bpf_map *map,
+					struct file *map_file)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct bpf_event_entry *ee;
+	int i;
+
+	rcu_read_lock();
+	for (i = 0; i < array->map.max_entries; i++) {
+		ee = READ_ONCE(array->ptrs[i]);
+		if (ee && ee->map_file == map_file)
+			fd_array_map_delete_elem(map, &i);
+	}
+	rcu_read_unlock();
 }
 
 static const struct bpf_map_ops perf_event_array_ops = {
 	.map_alloc = fd_array_map_alloc,
-	.map_free = perf_event_array_map_free,
+	.map_free = fd_array_map_free,
 	.map_get_next_key = array_map_get_next_key,
 	.map_lookup_elem = fd_array_map_lookup_elem,
-	.map_update_elem = fd_array_map_update_elem,
 	.map_delete_elem = fd_array_map_delete_elem,
 	.map_fd_get_ptr = perf_event_fd_array_get_ptr,
 	.map_fd_put_ptr = perf_event_fd_array_put_ptr,
+	.map_release = perf_event_fd_array_release,
 };
 
 static struct bpf_map_type_list perf_event_array_type __read_mostly = {
@@ -491,3 +537,46 @@ static int __init register_perf_event_array_map(void)
 	return 0;
 }
 late_initcall(register_perf_event_array_map);
+
+#ifdef CONFIG_SOCK_CGROUP_DATA
+static void *cgroup_fd_array_get_ptr(struct bpf_map *map,
+				     struct file *map_file /* not used */,
+				     int fd)
+{
+	return cgroup_get_from_fd(fd);
+}
+
+static void cgroup_fd_array_put_ptr(void *ptr)
+{
+	/* cgroup_put free cgrp after a rcu grace period */
+	cgroup_put(ptr);
+}
+
+static void cgroup_fd_array_free(struct bpf_map *map)
+{
+	bpf_fd_array_map_clear(map);
+	fd_array_map_free(map);
+}
+
+static const struct bpf_map_ops cgroup_array_ops = {
+	.map_alloc = fd_array_map_alloc,
+	.map_free = cgroup_fd_array_free,
+	.map_get_next_key = array_map_get_next_key,
+	.map_lookup_elem = fd_array_map_lookup_elem,
+	.map_delete_elem = fd_array_map_delete_elem,
+	.map_fd_get_ptr = cgroup_fd_array_get_ptr,
+	.map_fd_put_ptr = cgroup_fd_array_put_ptr,
+};
+
+static struct bpf_map_type_list cgroup_array_type __read_mostly = {
+	.ops = &cgroup_array_ops,
+	.type = BPF_MAP_TYPE_CGROUP_ARRAY,
+};
+
+static int __init register_cgroup_array_map(void)
+{
+	bpf_register_map_type(&cgroup_array_type);
+	return 0;
+}
+late_initcall(register_cgroup_array_map);
+#endif
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index b94a365..03fd23d 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -719,14 +719,13 @@ select_insn:
 
 		if (unlikely(index >= array->map.max_entries))
 			goto out;
-
 		if (unlikely(tail_call_cnt > MAX_TAIL_CALL_CNT))
 			goto out;
 
 		tail_call_cnt++;
 
 		prog = READ_ONCE(array->ptrs[index]);
-		if (unlikely(!prog))
+		if (!prog)
 			goto out;
 
 		/* ARG1 at this point is guaranteed to point to CTX from
@@ -1055,9 +1054,11 @@ const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
 	return NULL;
 }
 
-const struct bpf_func_proto * __weak bpf_get_event_output_proto(void)
+u64 __weak
+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)
 {
-	return NULL;
+	return -ENOTSUPP;
 }
 
 /* Always built-in helper functions. */
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index ad7a057..1ea3afb 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -101,7 +101,7 @@ const struct bpf_func_proto bpf_get_prandom_u32_proto = {
 
 static u64 bpf_get_smp_processor_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 {
-	return raw_smp_processor_id();
+	return smp_processor_id();
 }
 
 const struct bpf_func_proto bpf_get_smp_processor_id_proto = {
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 318858e..5967b87 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -11,7 +11,7 @@
  * version 2 as published by the Free Software Foundation.
  */
 
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/magic.h>
 #include <linux/major.h>
 #include <linux/mount.h>
@@ -367,8 +367,6 @@ static struct file_system_type bpf_fs_type = {
 	.kill_sb	= kill_litter_super,
 };
 
-MODULE_ALIAS_FS("bpf");
-
 static int __init bpf_init(void)
 {
 	int ret;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 46ecce4..228f962 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -124,7 +124,12 @@ void bpf_map_put_with_uref(struct bpf_map *map)
 
 static int bpf_map_release(struct inode *inode, struct file *filp)
 {
-	bpf_map_put_with_uref(filp->private_data);
+	struct bpf_map *map = filp->private_data;
+
+	if (map->ops->map_release)
+		map->ops->map_release(map, filp);
+
+	bpf_map_put_with_uref(map);
 	return 0;
 }
 
@@ -387,6 +392,13 @@ static int map_update_elem(union bpf_attr *attr)
 		err = bpf_percpu_hash_update(map, key, value, attr->flags);
 	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
 		err = bpf_percpu_array_update(map, key, value, attr->flags);
+	} else if (map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY ||
+		   map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
+		   map->map_type == BPF_MAP_TYPE_CGROUP_ARRAY) {
+		rcu_read_lock();
+		err = bpf_fd_array_map_update_elem(map, f.file, key, value,
+						   attr->flags);
+		rcu_read_unlock();
 	} else {
 		rcu_read_lock();
 		err = map->ops->map_update_elem(map, key, value, attr->flags);
@@ -612,7 +624,7 @@ static void bpf_prog_uncharge_memlock(struct bpf_prog *prog)
 	free_uid(user);
 }
 
-static void __prog_put_common(struct rcu_head *rcu)
+static void __bpf_prog_put_rcu(struct rcu_head *rcu)
 {
 	struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);
 
@@ -621,17 +633,10 @@ static void __prog_put_common(struct rcu_head *rcu)
 	bpf_prog_free(aux->prog);
 }
 
-/* version of bpf_prog_put() that is called after a grace period */
-void bpf_prog_put_rcu(struct bpf_prog *prog)
-{
-	if (atomic_dec_and_test(&prog->aux->refcnt))
-		call_rcu(&prog->aux->rcu, __prog_put_common);
-}
-
 void bpf_prog_put(struct bpf_prog *prog)
 {
 	if (atomic_dec_and_test(&prog->aux->refcnt))
-		__prog_put_common(&prog->aux->rcu);
+		call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_put);
 
@@ -639,7 +644,7 @@ static int bpf_prog_release(struct inode *inode, struct file *filp)
 {
 	struct bpf_prog *prog = filp->private_data;
 
-	bpf_prog_put_rcu(prog);
+	bpf_prog_put(prog);
 	return 0;
 }
 
@@ -653,7 +658,7 @@ int bpf_prog_new_fd(struct bpf_prog *prog)
 				O_RDWR | O_CLOEXEC);
 }
 
-static struct bpf_prog *__bpf_prog_get(struct fd f)
+static struct bpf_prog *____bpf_prog_get(struct fd f)
 {
 	if (!f.file)
 		return ERR_PTR(-EBADF);
@@ -665,33 +670,50 @@ static struct bpf_prog *__bpf_prog_get(struct fd f)
 	return f.file->private_data;
 }
 
-struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
+struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i)
 {
-	if (atomic_inc_return(&prog->aux->refcnt) > BPF_MAX_REFCNT) {
-		atomic_dec(&prog->aux->refcnt);
+	if (atomic_add_return(i, &prog->aux->refcnt) > BPF_MAX_REFCNT) {
+		atomic_sub(i, &prog->aux->refcnt);
 		return ERR_PTR(-EBUSY);
 	}
 	return prog;
 }
+EXPORT_SYMBOL_GPL(bpf_prog_add);
 
-/* called by sockets/tracing/seccomp before attaching program to an event
- * pairs with bpf_prog_put()
- */
-struct bpf_prog *bpf_prog_get(u32 ufd)
+struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
+{
+	return bpf_prog_add(prog, 1);
+}
+
+static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type)
 {
 	struct fd f = fdget(ufd);
 	struct bpf_prog *prog;
 
-	prog = __bpf_prog_get(f);
+	prog = ____bpf_prog_get(f);
 	if (IS_ERR(prog))
 		return prog;
+	if (type && prog->type != *type) {
+		prog = ERR_PTR(-EINVAL);
+		goto out;
+	}
 
 	prog = bpf_prog_inc(prog);
+out:
 	fdput(f);
-
 	return prog;
 }
-EXPORT_SYMBOL_GPL(bpf_prog_get);
+
+struct bpf_prog *bpf_prog_get(u32 ufd)
+{
+	return __bpf_prog_get(ufd, NULL);
+}
+
+struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type)
+{
+	return __bpf_prog_get(ufd, &type);
+}
+EXPORT_SYMBOL_GPL(bpf_prog_get_type);
 
 /* last field in 'union bpf_attr' used by this command */
 #define	BPF_PROG_LOAD_LAST_FIELD kern_version
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index eec9f90..f72f23b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -653,6 +653,16 @@ static int check_map_access(struct verifier_env *env, u32 regno, int off,
 
 #define MAX_PACKET_OFF 0xffff
 
+static bool may_write_pkt_data(enum bpf_prog_type type)
+{
+	switch (type) {
+	case BPF_PROG_TYPE_XDP:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static int check_packet_access(struct verifier_env *env, u32 regno, int off,
 			       int size)
 {
@@ -713,6 +723,7 @@ static int check_ptr_alignment(struct verifier_env *env, struct reg_state *reg,
 	switch (env->prog->type) {
 	case BPF_PROG_TYPE_SCHED_CLS:
 	case BPF_PROG_TYPE_SCHED_ACT:
+	case BPF_PROG_TYPE_XDP:
 		break;
 	default:
 		verbose("verifier is misconfigured\n");
@@ -805,10 +816,15 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off,
 			err = check_stack_read(state, off, size, value_regno);
 		}
 	} else if (state->regs[regno].type == PTR_TO_PACKET) {
-		if (t == BPF_WRITE) {
+		if (t == BPF_WRITE && !may_write_pkt_data(env->prog->type)) {
 			verbose("cannot write into packet\n");
 			return -EACCES;
 		}
+		if (t == BPF_WRITE && value_regno >= 0 &&
+		    is_pointer_value(env, value_regno)) {
+			verbose("R%d leaks addr into packet\n", value_regno);
+			return -EACCES;
+		}
 		err = check_packet_access(env, regno, off, size);
 		if (!err && t == BPF_READ && value_regno >= 0)
 			mark_reg_unknown_value(state->regs, value_regno);
@@ -1035,6 +1051,10 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 		if (func_id != BPF_FUNC_get_stackid)
 			goto error;
 		break;
+	case BPF_MAP_TYPE_CGROUP_ARRAY:
+		if (func_id != BPF_FUNC_skb_in_cgroup)
+			goto error;
+		break;
 	default:
 		break;
 	}
@@ -1054,6 +1074,10 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 		if (map->map_type != BPF_MAP_TYPE_STACK_TRACE)
 			goto error;
 		break;
+	case BPF_FUNC_skb_in_cgroup:
+		if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY)
+			goto error;
+		break;
 	default:
 		break;
 	}
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 33a2f63..9624db8 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -61,6 +61,7 @@
 #include <linux/cpuset.h>
 #include <linux/proc_ns.h>
 #include <linux/nsproxy.h>
+#include <linux/file.h>
 #include <net/sock.h>
 
 /*
@@ -6204,6 +6205,40 @@ struct cgroup *cgroup_get_from_path(const char *path)
 }
 EXPORT_SYMBOL_GPL(cgroup_get_from_path);
 
+/**
+ * cgroup_get_from_fd - get a cgroup pointer from a fd
+ * @fd: fd obtained by open(cgroup2_dir)
+ *
+ * Find the cgroup from a fd which should be obtained
+ * by opening a cgroup directory.  Returns a pointer to the
+ * cgroup on success. ERR_PTR is returned if the cgroup
+ * cannot be found.
+ */
+struct cgroup *cgroup_get_from_fd(int fd)
+{
+	struct cgroup_subsys_state *css;
+	struct cgroup *cgrp;
+	struct file *f;
+
+	f = fget_raw(fd);
+	if (!f)
+		return ERR_PTR(-EBADF);
+
+	css = css_tryget_online_from_dir(f->f_path.dentry, NULL);
+	fput(f);
+	if (IS_ERR(css))
+		return ERR_CAST(css);
+
+	cgrp = css->cgroup;
+	if (!cgroup_on_dfl(cgrp)) {
+		cgroup_put(cgrp);
+		return ERR_PTR(-EBADF);
+	}
+
+	return cgrp;
+}
+EXPORT_SYMBOL_GPL(cgroup_get_from_fd);
+
 /*
  * sock->sk_cgrp_data handling.  For more info, see sock_cgroup_data
  * definition in cgroup-defs.h.
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 79dae18..09ae27b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5617,16 +5617,26 @@ void perf_output_sample(struct perf_output_handle *handle,
 	}
 
 	if (sample_type & PERF_SAMPLE_RAW) {
-		if (data->raw) {
-			u32 raw_size = data->raw->size;
-			u32 real_size = round_up(raw_size + sizeof(u32),
-						 sizeof(u64)) - sizeof(u32);
-			u64 zero = 0;
-
-			perf_output_put(handle, real_size);
-			__output_copy(handle, data->raw->data, raw_size);
-			if (real_size - raw_size)
-				__output_copy(handle, &zero, real_size - raw_size);
+		struct perf_raw_record *raw = data->raw;
+
+		if (raw) {
+			struct perf_raw_frag *frag = &raw->frag;
+
+			perf_output_put(handle, raw->size);
+			do {
+				if (frag->copy) {
+					__output_custom(handle, frag->copy,
+							frag->data, frag->size);
+				} else {
+					__output_copy(handle, frag->data,
+						      frag->size);
+				}
+				if (perf_raw_frag_last(frag))
+					break;
+				frag = frag->next;
+			} while (1);
+			if (frag->pad)
+				__output_skip(handle, NULL, frag->pad);
 		} else {
 			struct {
 				u32	size;
@@ -5751,14 +5761,28 @@ void perf_prepare_sample(struct perf_event_header *header,
 	}
 
 	if (sample_type & PERF_SAMPLE_RAW) {
-		int size = sizeof(u32);
-
-		if (data->raw)
-			size += data->raw->size;
-		else
-			size += sizeof(u32);
+		struct perf_raw_record *raw = data->raw;
+		int size;
+
+		if (raw) {
+			struct perf_raw_frag *frag = &raw->frag;
+			u32 sum = 0;
+
+			do {
+				sum += frag->size;
+				if (perf_raw_frag_last(frag))
+					break;
+				frag = frag->next;
+			} while (1);
+
+			size = round_up(sum + sizeof(u32), sizeof(u64));
+			raw->size = size - sizeof(u32);
+			frag->pad = raw->size - sum;
+		} else {
+			size = sizeof(u64);
+		}
 
-		header->size += round_up(size, sizeof(u64));
+		header->size += size;
 	}
 
 	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
@@ -7398,7 +7422,7 @@ static struct pmu perf_swevent = {
 static int perf_tp_filter_match(struct perf_event *event,
 				struct perf_sample_data *data)
 {
-	void *record = data->raw->data;
+	void *record = data->raw->frag.data;
 
 	/* only top level events have filters set */
 	if (event->parent)
@@ -7454,8 +7478,10 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 	struct perf_event *event;
 
 	struct perf_raw_record raw = {
-		.size = entry_size,
-		.data = record,
+		.frag = {
+			.size = entry_size,
+			.data = record,
+		},
 	};
 
 	perf_sample_data_init(&data, 0, 0);
@@ -7596,7 +7622,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event)
 	prog = event->tp_event->prog;
 	if (prog) {
 		event->tp_event->prog = NULL;
-		bpf_prog_put_rcu(prog);
+		bpf_prog_put(prog);
 	}
 }
 
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 05f9f6d..486fd78 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -123,21 +123,19 @@ static inline unsigned long perf_aux_size(struct ring_buffer *rb)
 	return rb->aux_nr_pages << PAGE_SHIFT;
 }
 
-#define DEFINE_OUTPUT_COPY(func_name, memcpy_func)			\
-static inline unsigned long						\
-func_name(struct perf_output_handle *handle,				\
-	  const void *buf, unsigned long len)				\
+#define __DEFINE_OUTPUT_COPY_BODY(advance_buf, memcpy_func, ...)	\
 {									\
 	unsigned long size, written;					\
 									\
 	do {								\
 		size    = min(handle->size, len);			\
-		written = memcpy_func(handle->addr, buf, size);		\
+		written = memcpy_func(__VA_ARGS__);			\
 		written = size - written;				\
 									\
 		len -= written;						\
 		handle->addr += written;				\
-		buf += written;						\
+		if (advance_buf)					\
+			buf += written;					\
 		handle->size -= written;				\
 		if (!handle->size) {					\
 			struct ring_buffer *rb = handle->rb;		\
@@ -152,6 +150,21 @@ func_name(struct perf_output_handle *handle,				\
 	return len;							\
 }
 
+#define DEFINE_OUTPUT_COPY(func_name, memcpy_func)			\
+static inline unsigned long						\
+func_name(struct perf_output_handle *handle,				\
+	  const void *buf, unsigned long len)				\
+__DEFINE_OUTPUT_COPY_BODY(true, memcpy_func, handle->addr, buf, size)
+
+static inline unsigned long
+__output_custom(struct perf_output_handle *handle, perf_copy_f copy_func,
+		const void *buf, unsigned long len)
+{
+	unsigned long orig_len = len;
+	__DEFINE_OUTPUT_COPY_BODY(false, copy_func, handle->addr, buf,
+				  orig_len - len, size)
+}
+
 static inline unsigned long
 memcpy_common(void *dst, const void *src, unsigned long n)
 {
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 26f603d..b20438f 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;
 }