Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2022-09-05

The following pull-request contains BPF updates for your *net-next* tree.

We've added 106 non-merge commits during the last 18 day(s) which contain
a total of 159 files changed, 5225 insertions(+), 1358 deletions(-).

There are two small merge conflicts, resolve them as follows:

1) tools/testing/selftests/bpf/DENYLIST.s390x

  Commit 27e23836ce ("selftests/bpf: Add lru_bug to s390x deny list") in
  bpf tree was needed to get BPF CI green on s390x, but it conflicted with
  newly added tests on bpf-next. Resolve by adding both hunks, result:

  [...]
  lru_bug                                  # prog 'printk': failed to auto-attach: -524
  setget_sockopt                           # attach unexpected error: -524                                               (trampoline)
  cb_refs                                  # expected error message unexpected error: -524                               (trampoline)
  cgroup_hierarchical_stats                # JIT does not support calling kernel function                                (kfunc)
  htab_update                              # failed to attach: ERROR: strerror_r(-524)=22                                (trampoline)
  [...]

2) net/core/filter.c

  Commit 1227c1771d ("net: Fix data-races around sysctl_[rw]mem_(max|default).")
  from net tree conflicts with commit 29003875bd ("bpf: Change bpf_setsockopt(SOL_SOCKET)
  to reuse sk_setsockopt()") from bpf-next tree. Take the code as it is from
  bpf-next tree, result:

  [...]
	if (getopt) {
		if (optname == SO_BINDTODEVICE)
			return -EINVAL;
		return sk_getsockopt(sk, SOL_SOCKET, optname,
				     KERNEL_SOCKPTR(optval),
				     KERNEL_SOCKPTR(optlen));
	}

	return sk_setsockopt(sk, SOL_SOCKET, optname,
			     KERNEL_SOCKPTR(optval), *optlen);
  [...]

The main changes are:

1) Add any-context BPF specific memory allocator which is useful in particular for BPF
   tracing with bonus of performance equal to full prealloc, from Alexei Starovoitov.

2) Big batch to remove duplicated code from bpf_{get,set}sockopt() helpers as an effort
   to reuse the existing core socket code as much as possible, from Martin KaFai Lau.

3) Extend BPF flow dissector for BPF programs to just augment the in-kernel dissector
   with custom logic. In other words, allow for partial replacement, from Shmulik Ladkani.

4) Add a new cgroup iterator to BPF with different traversal options, from Hao Luo.

5) Support for BPF to collect hierarchical cgroup statistics efficiently through BPF
   integration with the rstat framework, from Yosry Ahmed.

6) Support bpf_{g,s}et_retval() under more BPF cgroup hooks, from Stanislav Fomichev.

7) BPF hash table and local storages fixes under fully preemptible kernel, from Hou Tao.

8) Add various improvements to BPF selftests and libbpf for compilation with gcc BPF
   backend, from James Hilliard.

9) Fix verifier helper permissions and reference state management for synchronous
   callbacks, from Kumar Kartikeya Dwivedi.

10) Add support for BPF selftest's xskxceiver to also be used against real devices that
    support MAC loopback, from Maciej Fijalkowski.

11) Various fixes to the bpf-helpers(7) man page generation script, from Quentin Monnet.

12) Document BPF verifier's tnum_in(tnum_range(), ...) gotchas, from Shung-Hsi Yu.

13) Various minor misc improvements all over the place.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (106 commits)
  bpf: Optimize rcu_barrier usage between hash map and bpf_mem_alloc.
  bpf: Remove usage of kmem_cache from bpf_mem_cache.
  bpf: Remove prealloc-only restriction for sleepable bpf programs.
  bpf: Prepare bpf_mem_alloc to be used by sleepable bpf programs.
  bpf: Remove tracing program restriction on map types
  bpf: Convert percpu hash map to per-cpu bpf_mem_alloc.
  bpf: Add percpu allocation support to bpf_mem_alloc.
  bpf: Batch call_rcu callbacks instead of SLAB_TYPESAFE_BY_RCU.
  bpf: Adjust low/high watermarks in bpf_mem_cache
  bpf: Optimize call_rcu in non-preallocated hash map.
  bpf: Optimize element count in non-preallocated hash map.
  bpf: Relax the requirement to use preallocated hash maps in tracing progs.
  samples/bpf: Reduce syscall overhead in map_perf_test.
  selftests/bpf: Improve test coverage of test_maps
  bpf: Convert hash map to bpf_mem_alloc.
  bpf: Introduce any context BPF specific memory allocator.
  selftest/bpf: Add test for bpf_getsockopt()
  bpf: Change bpf_getsockopt(SOL_IPV6) to reuse do_ipv6_getsockopt()
  bpf: Change bpf_getsockopt(SOL_IP) to reuse do_ip_getsockopt()
  bpf: Change bpf_getsockopt(SOL_TCP) to reuse do_tcp_getsockopt()
  ...
====================

Link: https://lore.kernel.org/r/20220905161136.9150-1-daniel@iogearbox.net
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

arch/mips/net/bpf_jit_comp32.c

@@ -1376,12 +1376,20 @@ void build_prologue(struct jit_context *ctx)
 	const u8 *fp = bpf2mips32[BPF_REG_FP];
 	int stack, saved, locals, reserved;
 
+	/*
+	 * In the unlikely event that the TCC limit is raised to more
+	 * than 16 bits, it is clamped to the maximum value allowed for
+	 * the generated code (0xffff). It is better fail to compile
+	 * instead of degrading gracefully.
+	 */
+	BUILD_BUG_ON(MAX_TAIL_CALL_CNT > 0xffff);
+
 	/*
 	 * The first two instructions initialize TCC in the reserved (for us)
 	 * 16-byte area in the parent's stack frame. On a tail call, the
 	 * calling function jumps into the prologue after these instructions.
 	 */
-	emit(ctx, ori, MIPS_R_T9, MIPS_R_ZERO, min(MAX_TAIL_CALL_CNT, 0xffff));
+	emit(ctx, ori, MIPS_R_T9, MIPS_R_ZERO, MAX_TAIL_CALL_CNT);
 	emit(ctx, sw, MIPS_R_T9, 0, MIPS_R_SP);
 
 	/*

arch/mips/net/bpf_jit_comp64.c

@@ -547,12 +547,20 @@ void build_prologue(struct jit_context *ctx)
 	u8 zx = bpf2mips64[JIT_REG_ZX];
 	int stack, saved, locals, reserved;
 
+	/*
+	 * In the unlikely event that the TCC limit is raised to more
+	 * than 16 bits, it is clamped to the maximum value allowed for
+	 * the generated code (0xffff). It is better fail to compile
+	 * instead of degrading gracefully.
+	 */
+	BUILD_BUG_ON(MAX_TAIL_CALL_CNT > 0xffff);
+
 	/*
 	 * The first instruction initializes the tail call count register.
 	 * On a tail call, the calling function jumps into the prologue
 	 * after this instruction.
 	 */
-	emit(ctx, ori, tc, MIPS_R_ZERO, min(MAX_TAIL_CALL_CNT, 0xffff));
+	emit(ctx, ori, tc, MIPS_R_ZERO, MAX_TAIL_CALL_CNT);
 
 	/* === Entry-point for tail calls === */
 

include/linux/bpf-cgroup.h

@@ -414,6 +414,11 @@ int cgroup_bpf_prog_detach(const union bpf_attr *attr,
 int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 int cgroup_bpf_prog_query(const union bpf_attr *attr,
 			  union bpf_attr __user *uattr);
+
+const struct bpf_func_proto *
+cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog);
+const struct bpf_func_proto *
+cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog);
 #else
 
 static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
@@ -444,6 +449,18 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr,
 	return -EINVAL;
 }
 
+static inline const struct bpf_func_proto *
+cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+	return NULL;
+}
+
+static inline const struct bpf_func_proto *
+cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+	return NULL;
+}
+
 static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux,
 					    struct bpf_map *map) { return 0; }
 static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(

include/linux/bpf.h

@@ -48,6 +48,7 @@ struct mem_cgroup;
 struct module;
 struct bpf_func_state;
 struct ftrace_ops;
+struct cgroup;
 
 extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
@@ -1730,7 +1731,14 @@ int bpf_obj_get_user(const char __user *pathname, int flags);
 	int __init bpf_iter_ ## target(args) { return 0; }
 
 struct bpf_iter_aux_info {
+	/* for map_elem iter */
 	struct bpf_map *map;
+
+	/* for cgroup iter */
+	struct {
+		struct cgroup *start; /* starting cgroup */
+		enum bpf_cgroup_iter_order order;
+	} cgroup;
 };
 
 typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog,
@@ -1966,6 +1974,15 @@ static inline bool unprivileged_ebpf_enabled(void)
 	return !sysctl_unprivileged_bpf_disabled;
 }
 
+/* Not all bpf prog type has the bpf_ctx.
+ * For the bpf prog type that has initialized the bpf_ctx,
+ * this function can be used to decide if a kernel function
+ * is called by a bpf program.
+ */
+static inline bool has_current_bpf_ctx(void)
+{
+	return !!current->bpf_ctx;
+}
 #else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 {
@@ -2175,6 +2192,10 @@ static inline bool unprivileged_ebpf_enabled(void)
 	return false;
 }
 
+static inline bool has_current_bpf_ctx(void)
+{
+	return false;
+}
 #endif /* CONFIG_BPF_SYSCALL */
 
 void __bpf_free_used_btfs(struct bpf_prog_aux *aux,
@@ -2362,6 +2383,7 @@ extern const struct bpf_func_proto bpf_sock_map_update_proto;
 extern const struct bpf_func_proto bpf_sock_hash_update_proto;
 extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto;
 extern const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto;
+extern const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto;
 extern const struct bpf_func_proto bpf_msg_redirect_hash_proto;
 extern const struct bpf_func_proto bpf_msg_redirect_map_proto;
 extern const struct bpf_func_proto bpf_sk_redirect_hash_proto;

include/linux/bpf_mem_alloc.h

@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+#ifndef _BPF_MEM_ALLOC_H
+#define _BPF_MEM_ALLOC_H
+#include <linux/compiler_types.h>
+#include <linux/workqueue.h>
+
+struct bpf_mem_cache;
+struct bpf_mem_caches;
+
+struct bpf_mem_alloc {
+	struct bpf_mem_caches __percpu *caches;
+	struct bpf_mem_cache __percpu *cache;
+	struct work_struct work;
+};
+
+int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu);
+void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma);
+
+/* kmalloc/kfree equivalent: */
+void *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size);
+void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr);
+
+/* kmem_cache_alloc/free equivalent: */
+void *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma);
+void bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr);
+
+#endif /* _BPF_MEM_ALLOC_H */

include/linux/bpf_verifier.h

@@ -212,6 +212,17 @@ struct bpf_reference_state {
 	 * is used purely to inform the user of a reference leak.
 	 */
 	int insn_idx;
+	/* There can be a case like:
+	 * main (frame 0)
+	 *  cb (frame 1)
+	 *   func (frame 3)
+	 *    cb (frame 4)
+	 * Hence for frame 4, if callback_ref just stored boolean, it would be
+	 * impossible to distinguish nested callback refs. Hence store the
+	 * frameno and compare that to callback_ref in check_reference_leak when
+	 * exiting a callback function.
+	 */
+	int callback_ref;
 };
 
 /* state of the program:

include/linux/filter.h

@@ -900,8 +900,7 @@ int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk);
 int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk);
 void sk_reuseport_prog_free(struct bpf_prog *prog);
 int sk_detach_filter(struct sock *sk);
-int sk_get_filter(struct sock *sk, struct sock_filter __user *filter,
-		  unsigned int len);
+int sk_get_filter(struct sock *sk, sockptr_t optval, unsigned int len);
 
 bool sk_filter_charge(struct sock *sk, struct sk_filter *fp);
 void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp);

include/linux/igmp.h

@@ -118,9 +118,9 @@ extern int ip_mc_source(int add, int omode, struct sock *sk,
 		struct ip_mreq_source *mreqs, int ifindex);
 extern int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf,int ifindex);
 extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf,
-		struct ip_msfilter __user *optval, int __user *optlen);
+			sockptr_t optval, sockptr_t optlen);
 extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf,
-			struct sockaddr_storage __user *p);
+			sockptr_t optval, size_t offset);
 extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt,
 			  int dif, int sdif);
 extern void ip_mc_init_dev(struct in_device *);

include/linux/mroute.h

@@ -17,7 +17,7 @@ static inline int ip_mroute_opt(int opt)
 }
 
 int ip_mroute_setsockopt(struct sock *, int, sockptr_t, unsigned int);
-int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *);
+int ip_mroute_getsockopt(struct sock *, int, sockptr_t, sockptr_t);
 int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg);
 int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
 int ip_mr_init(void);
@@ -29,8 +29,8 @@ static inline int ip_mroute_setsockopt(struct sock *sock, int optname,
 	return -ENOPROTOOPT;
 }
 
-static inline int ip_mroute_getsockopt(struct sock *sock, int optname,
-				       char __user *optval, int __user *optlen)
+static inline int ip_mroute_getsockopt(struct sock *sk, int optname,
+				       sockptr_t optval, sockptr_t optlen)
 {
 	return -ENOPROTOOPT;
 }

include/linux/mroute6.h

@@ -27,7 +27,7 @@ struct sock;
 
 #ifdef CONFIG_IPV6_MROUTE
 extern int ip6_mroute_setsockopt(struct sock *, int, sockptr_t, unsigned int);
-extern int ip6_mroute_getsockopt(struct sock *, int, char __user *, int __user *);
+extern int ip6_mroute_getsockopt(struct sock *, int, sockptr_t, sockptr_t);
 extern int ip6_mr_input(struct sk_buff *skb);
 extern int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg);
 extern int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
@@ -42,7 +42,7 @@ static inline int ip6_mroute_setsockopt(struct sock *sock, int optname,
 
 static inline
 int ip6_mroute_getsockopt(struct sock *sock,
-			  int optname, char __user *optval, int __user *optlen)
+			  int optname, sockptr_t optval, sockptr_t optlen)
 {
 	return -ENOPROTOOPT;
 }

include/linux/skbuff.h

@@ -1461,8 +1461,8 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
 			     unsigned int key_count);
 
 struct bpf_flow_dissector;
-bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
-		      __be16 proto, int nhoff, int hlen, unsigned int flags);
+u32 bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
+		     __be16 proto, int nhoff, int hlen, unsigned int flags);
 
 bool __skb_flow_dissect(const struct net *net,
 			const struct sk_buff *skb,

include/linux/sockptr.h

@@ -64,6 +64,11 @@ static inline int copy_to_sockptr_offset(sockptr_t dst, size_t offset,
 	return 0;
 }
 
+static inline int copy_to_sockptr(sockptr_t dst, const void *src, size_t size)
+{
+	return copy_to_sockptr_offset(dst, 0, src, size);
+}
+
 static inline void *memdup_sockptr(sockptr_t src, size_t len)
 {
 	void *p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN);

include/linux/tnum.h

@@ -21,7 +21,12 @@ struct tnum {
 struct tnum tnum_const(u64 value);
 /* A completely unknown value */
 extern const struct tnum tnum_unknown;
-/* A value that's unknown except that @min <= value <= @max */
+/* An unknown value that is a superset of @min <= value <= @max.
+ *
+ * Could include values outside the range of [@min, @max].
+ * For example tnum_range(0, 2) is represented by {0, 1, 2, *3*},
+ * rather than the intended set of {0, 1, 2}.
+ */
 struct tnum tnum_range(u64 min, u64 max);
 
 /* Arithmetic and logical ops */
@@ -73,7 +78,18 @@ static inline bool tnum_is_unknown(struct tnum a)
  */
 bool tnum_is_aligned(struct tnum a, u64 size);
 
-/* Returns true if @b represents a subset of @a. */
+/* Returns true if @b represents a subset of @a.
+ *
+ * Note that using tnum_range() as @a requires extra cautions as tnum_in() may
+ * return true unexpectedly due to tnum limited ability to represent tight
+ * range, e.g.
+ *
+ *   tnum_in(tnum_range(0, 2), tnum_const(3)) == true
+ *
+ * As a rule of thumb, if @a is explicitly coded rather than coming from
+ * reg->var_off, it should be in form of tnum_const(), tnum_range(0, 2**n - 1),
+ * or tnum_range(2**n, 2**(n+1) - 1).
+ */
 bool tnum_in(struct tnum a, struct tnum b);
 
 /* Formatting functions.  These have snprintf-like semantics: they will write

include/net/ip.h

@@ -743,8 +743,12 @@ void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk,
 int ip_cmsg_send(struct sock *sk, struct msghdr *msg,
 		 struct ipcm_cookie *ipc, bool allow_ipv6);
 DECLARE_STATIC_KEY_FALSE(ip4_min_ttl);
+int do_ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
+		     unsigned int optlen);
 int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		  unsigned int optlen);
+int do_ip_getsockopt(struct sock *sk, int level, int optname,
+		     sockptr_t optval, sockptr_t optlen);
 int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
 		  int __user *optlen);
 int ip_ra_control(struct sock *sk, unsigned char on,

include/net/ipv6.h

@@ -1156,8 +1156,12 @@ struct in6_addr *fl6_update_dst(struct flowi6 *fl6,
  */
 DECLARE_STATIC_KEY_FALSE(ip6_min_hopcount);
 
+int do_ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
+		       unsigned int optlen);
 int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		    unsigned int optlen);
+int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
+		       sockptr_t optval, sockptr_t optlen);
 int ipv6_getsockopt(struct sock *sk, int level, int optname,
 		    char __user *optval, int __user *optlen);
 
@@ -1207,7 +1211,7 @@ int ip6_mc_source(int add, int omode, struct sock *sk,
 int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf,
 		  struct sockaddr_storage *list);
 int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
-		  struct sockaddr_storage __user *p);
+		  sockptr_t optval, size_t ss_offset);
 
 #ifdef CONFIG_PROC_FS
 int ac6_proc_init(struct net *net);

include/net/ipv6_stubs.h

@@ -81,6 +81,10 @@ struct ipv6_bpf_stub {
 				     const struct in6_addr *daddr, __be16 dport,
 				     int dif, int sdif, struct udp_table *tbl,
 				     struct sk_buff *skb);
+	int (*ipv6_setsockopt)(struct sock *sk, int level, int optname,
+			       sockptr_t optval, unsigned int optlen);
+	int (*ipv6_getsockopt)(struct sock *sk, int level, int optname,
+			       sockptr_t optval, sockptr_t optlen);
 };
 extern const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly;
 

include/net/sock.h

@@ -1788,6 +1788,11 @@ static inline void unlock_sock_fast(struct sock *sk, bool slow)
 	}
 }
 
+void sockopt_lock_sock(struct sock *sk);
+void sockopt_release_sock(struct sock *sk);
+bool sockopt_ns_capable(struct user_namespace *ns, int cap);
+bool sockopt_capable(int cap);
+
 /* Used by processes to "lock" a socket state, so that
  * interrupts and bottom half handlers won't change it
  * from under us. It essentially blocks any incoming
@@ -1862,9 +1867,13 @@ void sock_pfree(struct sk_buff *skb);
 #define sock_edemux sock_efree
 #endif
 
+int sk_setsockopt(struct sock *sk, int level, int optname,
+		  sockptr_t optval, unsigned int optlen);
 int sock_setsockopt(struct socket *sock, int level, int op,
 		    sockptr_t optval, unsigned int optlen);
 
+int sk_getsockopt(struct sock *sk, int level, int optname,
+		  sockptr_t optval, sockptr_t optlen);
 int sock_getsockopt(struct socket *sock, int level, int op,
 		    char __user *optval, int __user *optlen);
 int sock_gettstamp(struct socket *sock, void __user *userstamp,

include/net/tcp.h

@@ -402,9 +402,13 @@ void tcp_init_sock(struct sock *sk);
 void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb);
 __poll_t tcp_poll(struct file *file, struct socket *sock,
 		      struct poll_table_struct *wait);
+int do_tcp_getsockopt(struct sock *sk, int level,
+		      int optname, sockptr_t optval, sockptr_t optlen);
 int tcp_getsockopt(struct sock *sk, int level, int optname,
 		   char __user *optval, int __user *optlen);
 bool tcp_bpf_bypass_getsockopt(int level, int optname);
+int do_tcp_setsockopt(struct sock *sk, int level, int optname,
+		      sockptr_t optval, unsigned int optlen);
 int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		   unsigned int optlen);
 void tcp_set_keepalive(struct sock *sk, int val);

include/uapi/linux/bpf.h

@@ -87,10 +87,29 @@ struct bpf_cgroup_storage_key {
 	__u32	attach_type;		/* program attach type (enum bpf_attach_type) */
 };
 
+enum bpf_cgroup_iter_order {
+	BPF_CGROUP_ITER_ORDER_UNSPEC = 0,
+	BPF_CGROUP_ITER_SELF_ONLY,		/* process only a single object. */
+	BPF_CGROUP_ITER_DESCENDANTS_PRE,	/* walk descendants in pre-order. */
+	BPF_CGROUP_ITER_DESCENDANTS_POST,	/* walk descendants in post-order. */
+	BPF_CGROUP_ITER_ANCESTORS_UP,		/* walk ancestors upward. */
+};
+
 union bpf_iter_link_info {
 	struct {
 		__u32	map_fd;
 	} map;
+	struct {
+		enum bpf_cgroup_iter_order order;
+
+		/* At most one of cgroup_fd and cgroup_id can be non-zero. If
+		 * both are zero, the walk starts from the default cgroup v2
+		 * root. For walking v1 hierarchy, one should always explicitly
+		 * specify cgroup_fd.
+		 */
+		__u32	cgroup_fd;
+		__u64	cgroup_id;
+	} cgroup;
 };
 
 /* BPF syscall commands, see bpf(2) man-page for more details. */
@@ -4437,7 +4456,7 @@ union bpf_attr {
  *
  *		**-EEXIST** if the option already exists.
  *
- *		**-EFAULT** on failrue to parse the existing header options.
+ *		**-EFAULT** on failure to parse the existing header options.
  *
  *		**-EPERM** if the helper cannot be used under the current
  *		*skops*\ **->op**.
@@ -4646,7 +4665,7 @@ union bpf_attr {
  *		a *map* with *task* as the **key**.  From this
  *		perspective,  the usage is not much different from
  *		**bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this
- *		helper enforces the key must be an task_struct and the map must also
+ *		helper enforces the key must be a task_struct and the map must also
  *		be a **BPF_MAP_TYPE_TASK_STORAGE**.
  *
  *		Underneath, the value is stored locally at *task* instead of
@@ -4704,7 +4723,7 @@ union bpf_attr {
  *
  * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size)
  *	Description
- *		Returns the stored IMA hash of the *inode* (if it's avaialable).
+ *		Returns the stored IMA hash of the *inode* (if it's available).
  *		If the hash is larger than *size*, then only *size*
  *		bytes will be copied to *dst*
  *	Return
@@ -4728,12 +4747,12 @@ union bpf_attr {
  *
  *		The argument *len_diff* can be used for querying with a planned
  *		size change. This allows to check MTU prior to changing packet
- *		ctx. Providing an *len_diff* adjustment that is larger than the
+ *		ctx. Providing a *len_diff* adjustment that is larger than the
  *		actual packet size (resulting in negative packet size) will in
- *		principle not exceed the MTU, why it is not considered a
- *		failure.  Other BPF-helpers are needed for performing the
- *		planned size change, why the responsability for catch a negative
- *		packet size belong in those helpers.
+ *		principle not exceed the MTU, which is why it is not considered
+ *		a failure.  Other BPF helpers are needed for performing the
+ *		planned size change; therefore the responsibility for catching
+ *		a negative packet size belongs in those helpers.
  *
  *		Specifying *ifindex* zero means the MTU check is performed
  *		against the current net device.  This is practical if this isn't
@@ -5085,17 +5104,29 @@ union bpf_attr {
  *
  * int bpf_get_retval(void)
  *	Description
- *		Get the syscall's return value that will be returned to userspace.
+ *		Get the BPF program's return value that will be returned to the upper layers.
  *
- *		This helper is currently supported by cgroup programs only.
+ *		This helper is currently supported by cgroup programs and only by the hooks
+ *		where BPF program's return value is returned to the userspace via errno.
  *	Return
- *		The syscall's return value.
+ *		The BPF program's return value.
  *
  * int bpf_set_retval(int retval)
  *	Description
- *		Set the syscall's return value that will be returned to userspace.
+ *		Set the BPF program's return value that will be returned to the upper layers.
+ *
+ *		This helper is currently supported by cgroup programs and only by the hooks
+ *		where BPF program's return value is returned to the userspace via errno.
+ *
+ *		Note that there is the following corner case where the program exports an error
+ *		via bpf_set_retval but signals success via 'return 1':
+ *
+ *			bpf_set_retval(-EPERM);
+ *			return 1;
+ *
+ *		In this case, the BPF program's return value will use helper's -EPERM. This
+ *		still holds true for cgroup/bind{4,6} which supports extra 'return 3' success case.
  *
- *		This helper is currently supported by cgroup programs only.
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
@@ -5628,6 +5659,11 @@ enum {
 	BPF_F_SEQ_NUMBER		= (1ULL << 3),
 };
 
+/* BPF_FUNC_skb_get_tunnel_key flags. */
+enum {
+	BPF_F_TUNINFO_FLAGS		= (1ULL << 4),
+};
+
 /* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
  * BPF_FUNC_perf_event_read_value flags.
  */
@@ -5817,7 +5853,10 @@ struct bpf_tunnel_key {
 	};
 	__u8 tunnel_tos;
 	__u8 tunnel_ttl;
-	__u16 tunnel_ext;	/* Padding, future use. */
+	union {
+		__u16 tunnel_ext;	/* compat */
+		__be16 tunnel_flags;
+	};
 	__u32 tunnel_label;
 	union {
 		__u32 local_ipv4;
@@ -5861,6 +5900,11 @@ enum bpf_ret_code {
 	 *    represented by BPF_REDIRECT above).
 	 */
 	BPF_LWT_REROUTE = 128,
+	/* BPF_FLOW_DISSECTOR_CONTINUE: used by BPF_PROG_TYPE_FLOW_DISSECTOR
+	 *   to indicate that no custom dissection was performed, and
+	 *   fallback to standard dissector is requested.
+	 */
+	BPF_FLOW_DISSECTOR_CONTINUE = 129,
 };
 
 struct bpf_sock {
@@ -6159,11 +6203,22 @@ struct bpf_link_info {
 		struct {
 			__aligned_u64 target_name; /* in/out: target_name buffer ptr */
 			__u32 target_name_len;	   /* in/out: target_name buffer len */
+
+			/* If the iter specific field is 32 bits, it can be put
+			 * in the first or second union. Otherwise it should be
+			 * put in the second union.
+			 */
 			union {
 				struct {
 					__u32 map_id;
 				} map;
 			};
+			union {
+				struct {
+					__u64 cgroup_id;
+					__u32 order;
+				} cgroup;
+			};
 		} iter;
 		struct  {
 			__u32 netns_ino;

kernel/bpf/Makefile

@@ -13,7 +13,7 @@ obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o
 obj-${CONFIG_BPF_LSM}	  += bpf_inode_storage.o
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o
 obj-$(CONFIG_BPF_JIT) += trampoline.o
-obj-$(CONFIG_BPF_SYSCALL) += btf.o
+obj-$(CONFIG_BPF_SYSCALL) += btf.o memalloc.o
 obj-$(CONFIG_BPF_JIT) += dispatcher.o
 ifeq ($(CONFIG_NET),y)
 obj-$(CONFIG_BPF_SYSCALL) += devmap.o
@@ -24,6 +24,9 @@ endif
 ifeq ($(CONFIG_PERF_EVENTS),y)
 obj-$(CONFIG_BPF_SYSCALL) += stackmap.o
 endif
+ifeq ($(CONFIG_CGROUPS),y)
+obj-$(CONFIG_BPF_SYSCALL) += cgroup_iter.o
+endif
 obj-$(CONFIG_CGROUP_BPF) += cgroup.o
 ifeq ($(CONFIG_INET),y)
 obj-$(CONFIG_BPF_SYSCALL) += reuseport_array.o

kernel/bpf/bpf_iter.c

@@ -694,19 +694,24 @@ struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop)
 
 int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx)
 {
+	struct bpf_run_ctx run_ctx, *old_run_ctx;
 	int ret;
 
 	if (prog->aux->sleepable) {
 		rcu_read_lock_trace();
 		migrate_disable();
 		might_fault();
+		old_run_ctx = bpf_set_run_ctx(&run_ctx);
 		ret = bpf_prog_run(prog, ctx);
+		bpf_reset_run_ctx(old_run_ctx);
 		migrate_enable();
 		rcu_read_unlock_trace();
 	} else {
 		rcu_read_lock();
 		migrate_disable();
+		old_run_ctx = bpf_set_run_ctx(&run_ctx);
 		ret = bpf_prog_run(prog, ctx);
+		bpf_reset_run_ctx(old_run_ctx);
 		migrate_enable();
 		rcu_read_unlock();
 	}

kernel/bpf/bpf_local_storage.c

@@ -555,11 +555,11 @@ void bpf_local_storage_map_free(struct bpf_local_storage_map *smap,
 				struct bpf_local_storage_elem, map_node))) {
 			if (busy_counter) {
 				migrate_disable();
-				__this_cpu_inc(*busy_counter);
+				this_cpu_inc(*busy_counter);
 			}
 			bpf_selem_unlink(selem, false);
 			if (busy_counter) {
-				__this_cpu_dec(*busy_counter);
+				this_cpu_dec(*busy_counter);
 				migrate_enable();
 			}
 			cond_resched_rcu();

kernel/bpf/bpf_lsm.c

@@ -41,17 +41,21 @@ BTF_SET_END(bpf_lsm_hooks)
  */
 BTF_SET_START(bpf_lsm_current_hooks)
 /* operate on freshly allocated sk without any cgroup association */
+#ifdef CONFIG_SECURITY_NETWORK
 BTF_ID(func, bpf_lsm_sk_alloc_security)
 BTF_ID(func, bpf_lsm_sk_free_security)
+#endif
 BTF_SET_END(bpf_lsm_current_hooks)
 
 /* List of LSM hooks that trigger while the socket is properly locked.
  */
 BTF_SET_START(bpf_lsm_locked_sockopt_hooks)
+#ifdef CONFIG_SECURITY_NETWORK
 BTF_ID(func, bpf_lsm_socket_sock_rcv_skb)
 BTF_ID(func, bpf_lsm_sock_graft)
 BTF_ID(func, bpf_lsm_inet_csk_clone)
 BTF_ID(func, bpf_lsm_inet_conn_established)
+#endif
 BTF_SET_END(bpf_lsm_locked_sockopt_hooks)
 
 /* List of LSM hooks that trigger while the socket is _not_ locked,
@@ -59,8 +63,10 @@ BTF_SET_END(bpf_lsm_locked_sockopt_hooks)
  * in the early init phase.
  */
 BTF_SET_START(bpf_lsm_unlocked_sockopt_hooks)
+#ifdef CONFIG_SECURITY_NETWORK
 BTF_ID(func, bpf_lsm_socket_post_create)
 BTF_ID(func, bpf_lsm_socket_socketpair)
+#endif
 BTF_SET_END(bpf_lsm_unlocked_sockopt_hooks)
 
 #ifdef CONFIG_CGROUP_BPF
@@ -189,6 +195,14 @@ static const struct bpf_func_proto bpf_get_attach_cookie_proto = {
 static const struct bpf_func_proto *
 bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
+	const struct bpf_func_proto *func_proto;
+
+	if (prog->expected_attach_type == BPF_LSM_CGROUP) {
+		func_proto = cgroup_common_func_proto(func_id, prog);
+		if (func_proto)
+			return func_proto;
+	}
+
 	switch (func_id) {
 	case BPF_FUNC_inode_storage_get:
 		return &bpf_inode_storage_get_proto;
@@ -212,15 +226,6 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return prog->aux->sleepable ? &bpf_ima_file_hash_proto : NULL;
 	case BPF_FUNC_get_attach_cookie:
 		return bpf_prog_has_trampoline(prog) ? &bpf_get_attach_cookie_proto : NULL;
-	case BPF_FUNC_get_local_storage:
-		return prog->expected_attach_type == BPF_LSM_CGROUP ?
-			&bpf_get_local_storage_proto : NULL;
-	case BPF_FUNC_set_retval:
-		return prog->expected_attach_type == BPF_LSM_CGROUP ?
-			&bpf_set_retval_proto : NULL;
-	case BPF_FUNC_get_retval:
-		return prog->expected_attach_type == BPF_LSM_CGROUP ?
-			&bpf_get_retval_proto : NULL;
 #ifdef CONFIG_NET
 	case BPF_FUNC_setsockopt:
 		if (prog->expected_attach_type != BPF_LSM_CGROUP)

kernel/bpf/bpf_task_storage.c

@@ -26,20 +26,20 @@ static DEFINE_PER_CPU(int, bpf_task_storage_busy);
 static void bpf_task_storage_lock(void)
 {
 	migrate_disable();
-	__this_cpu_inc(bpf_task_storage_busy);
+	this_cpu_inc(bpf_task_storage_busy);
 }
 
 static void bpf_task_storage_unlock(void)
 {
-	__this_cpu_dec(bpf_task_storage_busy);
+	this_cpu_dec(bpf_task_storage_busy);
 	migrate_enable();
 }
 
 static bool bpf_task_storage_trylock(void)
 {
 	migrate_disable();
-	if (unlikely(__this_cpu_inc_return(bpf_task_storage_busy) != 1)) {
-		__this_cpu_dec(bpf_task_storage_busy);
+	if (unlikely(this_cpu_inc_return(bpf_task_storage_busy) != 1)) {
+		this_cpu_dec(bpf_task_storage_busy);
 		migrate_enable();
 		return false;
 	}

kernel/bpf/cgroup.c

@@ -1529,6 +1529,37 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 	return ret;
 }
 
+BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags)
+{
+	/* flags argument is not used now,
+	 * but provides an ability to extend the API.
+	 * verifier checks that its value is correct.
+	 */
+	enum bpf_cgroup_storage_type stype = cgroup_storage_type(map);
+	struct bpf_cgroup_storage *storage;
+	struct bpf_cg_run_ctx *ctx;
+	void *ptr;
+
+	/* get current cgroup storage from BPF run context */
+	ctx = container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx);
+	storage = ctx->prog_item->cgroup_storage[stype];
+
+	if (stype == BPF_CGROUP_STORAGE_SHARED)
+		ptr = &READ_ONCE(storage->buf)->data[0];
+	else
+		ptr = this_cpu_ptr(storage->percpu_buf);
+
+	return (unsigned long)ptr;
+}
+
+const struct bpf_func_proto bpf_get_local_storage_proto = {
+	.func		= bpf_get_local_storage,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_MAP_VALUE,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_0(bpf_get_retval)
 {
 	struct bpf_cg_run_ctx *ctx =
@@ -1560,32 +1591,26 @@ const struct bpf_func_proto bpf_set_retval_proto = {
 };
 
 static const struct bpf_func_proto *
-cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
+	const struct bpf_func_proto *func_proto;
+
+	func_proto = cgroup_common_func_proto(func_id, prog);
+	if (func_proto)
+		return func_proto;
+
+	func_proto = cgroup_current_func_proto(func_id, prog);
+	if (func_proto)
+		return func_proto;
+
 	switch (func_id) {
-	case BPF_FUNC_get_current_uid_gid:
-		return &bpf_get_current_uid_gid_proto;
-	case BPF_FUNC_get_local_storage:
-		return &bpf_get_local_storage_proto;
-	case BPF_FUNC_get_current_cgroup_id:
-		return &bpf_get_current_cgroup_id_proto;
 	case BPF_FUNC_perf_event_output:
 		return &bpf_event_output_data_proto;
-	case BPF_FUNC_get_retval:
-		return &bpf_get_retval_proto;
-	case BPF_FUNC_set_retval:
-		return &bpf_set_retval_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
 }
 
-static const struct bpf_func_proto *
-cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
-{
-	return cgroup_base_func_proto(func_id, prog);
-}
-
 static bool cgroup_dev_is_valid_access(int off, int size,
 				       enum bpf_access_type type,
 				       const struct bpf_prog *prog,
@@ -2098,11 +2123,17 @@ static const struct bpf_func_proto bpf_sysctl_set_new_value_proto = {
 static const struct bpf_func_proto *
 sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
+	const struct bpf_func_proto *func_proto;
+
+	func_proto = cgroup_common_func_proto(func_id, prog);
+	if (func_proto)
+		return func_proto;
+
+	func_proto = cgroup_current_func_proto(func_id, prog);
+	if (func_proto)
+		return func_proto;
+
 	switch (func_id) {
-	case BPF_FUNC_strtol:
-		return &bpf_strtol_proto;
-	case BPF_FUNC_strtoul:
-		return &bpf_strtoul_proto;
 	case BPF_FUNC_sysctl_get_name:
 		return &bpf_sysctl_get_name_proto;
 	case BPF_FUNC_sysctl_get_current_value:
@@ -2113,8 +2144,10 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sysctl_set_new_value_proto;
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
+	case BPF_FUNC_perf_event_output:
+		return &bpf_event_output_data_proto;
 	default:
-		return cgroup_base_func_proto(func_id, prog);
+		return bpf_base_func_proto(func_id);
 	}
 }
 
@@ -2235,6 +2268,16 @@ static const struct bpf_func_proto bpf_get_netns_cookie_sockopt_proto = {
 static const struct bpf_func_proto *
 cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
+	const struct bpf_func_proto *func_proto;
+
+	func_proto = cgroup_common_func_proto(func_id, prog);
+	if (func_proto)
+		return func_proto;
+
+	func_proto = cgroup_current_func_proto(func_id, prog);
+	if (func_proto)
+		return func_proto;
+
 	switch (func_id) {
 #ifdef CONFIG_NET
 	case BPF_FUNC_get_netns_cookie:
@@ -2256,8 +2299,10 @@ cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_tcp_sock:
 		return &bpf_tcp_sock_proto;
 #endif
+	case BPF_FUNC_perf_event_output:
+		return &bpf_event_output_data_proto;
 	default:
-		return cgroup_base_func_proto(func_id, prog);
+		return bpf_base_func_proto(func_id);
 	}
 }
 
@@ -2422,3 +2467,69 @@ const struct bpf_verifier_ops cg_sockopt_verifier_ops = {
 
 const struct bpf_prog_ops cg_sockopt_prog_ops = {
 };
+
+/* Common helpers for cgroup hooks. */
+const struct bpf_func_proto *
+cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+	switch (func_id) {
+	case BPF_FUNC_get_local_storage:
+		return &bpf_get_local_storage_proto;
+	case BPF_FUNC_get_retval:
+		switch (prog->expected_attach_type) {
+		case BPF_CGROUP_INET_INGRESS:
+		case BPF_CGROUP_INET_EGRESS:
+		case BPF_CGROUP_SOCK_OPS:
+		case BPF_CGROUP_UDP4_RECVMSG:
+		case BPF_CGROUP_UDP6_RECVMSG:
+		case BPF_CGROUP_INET4_GETPEERNAME:
+		case BPF_CGROUP_INET6_GETPEERNAME:
+		case BPF_CGROUP_INET4_GETSOCKNAME:
+		case BPF_CGROUP_INET6_GETSOCKNAME:
+			return NULL;
+		default:
+			return &bpf_get_retval_proto;
+		}
+	case BPF_FUNC_set_retval:
+		switch (prog->expected_attach_type) {
+		case BPF_CGROUP_INET_INGRESS:
+		case BPF_CGROUP_INET_EGRESS:
+		case BPF_CGROUP_SOCK_OPS:
+		case BPF_CGROUP_UDP4_RECVMSG:
+		case BPF_CGROUP_UDP6_RECVMSG:
+		case BPF_CGROUP_INET4_GETPEERNAME:
+		case BPF_CGROUP_INET6_GETPEERNAME:
+		case BPF_CGROUP_INET4_GETSOCKNAME:
+		case BPF_CGROUP_INET6_GETSOCKNAME:
+			return NULL;
+		default:
+			return &bpf_set_retval_proto;
+		}
+	default:
+		return NULL;
+	}
+}
+
+/* Common helpers for cgroup hooks with valid process context. */
+const struct bpf_func_proto *
+cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+	switch (func_id) {
+	case BPF_FUNC_get_current_uid_gid:
+		return &bpf_get_current_uid_gid_proto;
+	case BPF_FUNC_get_current_pid_tgid:
+		return &bpf_get_current_pid_tgid_proto;
+	case BPF_FUNC_get_current_comm:
+		return &bpf_get_current_comm_proto;
+	case BPF_FUNC_get_current_cgroup_id:
+		return &bpf_get_current_cgroup_id_proto;
+	case BPF_FUNC_get_current_ancestor_cgroup_id:
+		return &bpf_get_current_ancestor_cgroup_id_proto;
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	case BPF_FUNC_get_cgroup_classid:
+		return &bpf_get_cgroup_classid_curr_proto;
+#endif
+	default:
+		return NULL;
+	}
+}

kernel/bpf/cgroup_iter.c

@@ -0,0 +1,282 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2022 Google */
+#include <linux/bpf.h>
+#include <linux/btf_ids.h>
+#include <linux/cgroup.h>
+#include <linux/kernel.h>
+#include <linux/seq_file.h>
+
+#include "../cgroup/cgroup-internal.h"  /* cgroup_mutex and cgroup_is_dead */
+
+/* cgroup_iter provides four modes of traversal to the cgroup hierarchy.
+ *
+ *  1. Walk the descendants of a cgroup in pre-order.
+ *  2. Walk the descendants of a cgroup in post-order.
+ *  3. Walk the ancestors of a cgroup.
+ *  4. Show the given cgroup only.
+ *
+ * For walking descendants, cgroup_iter can walk in either pre-order or
+ * post-order. For walking ancestors, the iter walks up from a cgroup to
+ * the root.
+ *
+ * The iter program can terminate the walk early by returning 1. Walk
+ * continues if prog returns 0.
+ *
+ * The prog can check (seq->num == 0) to determine whether this is
+ * the first element. The prog may also be passed a NULL cgroup,
+ * which means the walk has completed and the prog has a chance to
+ * do post-processing, such as outputting an epilogue.
+ *
+ * Note: the iter_prog is called with cgroup_mutex held.
+ *
+ * Currently only one session is supported, which means, depending on the
+ * volume of data bpf program intends to send to user space, the number
+ * of cgroups that can be walked is limited. For example, given the current
+ * buffer size is 8 * PAGE_SIZE, if the program sends 64B data for each
+ * cgroup, assuming PAGE_SIZE is 4kb, the total number of cgroups that can
+ * be walked is 512. This is a limitation of cgroup_iter. If the output data
+ * is larger than the kernel buffer size, after all data in the kernel buffer
+ * is consumed by user space, the subsequent read() syscall will signal
+ * EOPNOTSUPP. In order to work around, the user may have to update their
+ * program to reduce the volume of data sent to output. For example, skip
+ * some uninteresting cgroups.
+ */
+
+struct bpf_iter__cgroup {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct cgroup *, cgroup);
+};
+
+struct cgroup_iter_priv {
+	struct cgroup_subsys_state *start_css;
+	bool visited_all;
+	bool terminate;
+	int order;
+};
+
+static void *cgroup_iter_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct cgroup_iter_priv *p = seq->private;
+
+	mutex_lock(&cgroup_mutex);
+
+	/* cgroup_iter doesn't support read across multiple sessions. */
+	if (*pos > 0) {
+		if (p->visited_all)
+			return NULL;
+
+		/* Haven't visited all, but because cgroup_mutex has dropped,
+		 * return -EOPNOTSUPP to indicate incomplete iteration.
+		 */
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	++*pos;
+	p->terminate = false;
+	p->visited_all = false;
+	if (p->order == BPF_CGROUP_ITER_DESCENDANTS_PRE)
+		return css_next_descendant_pre(NULL, p->start_css);
+	else if (p->order == BPF_CGROUP_ITER_DESCENDANTS_POST)
+		return css_next_descendant_post(NULL, p->start_css);
+	else /* BPF_CGROUP_ITER_SELF_ONLY and BPF_CGROUP_ITER_ANCESTORS_UP */
+		return p->start_css;
+}
+
+static int __cgroup_iter_seq_show(struct seq_file *seq,
+				  struct cgroup_subsys_state *css, int in_stop);
+
+static void cgroup_iter_seq_stop(struct seq_file *seq, void *v)
+{
+	struct cgroup_iter_priv *p = seq->private;
+
+	mutex_unlock(&cgroup_mutex);
+
+	/* pass NULL to the prog for post-processing */
+	if (!v) {
+		__cgroup_iter_seq_show(seq, NULL, true);
+		p->visited_all = true;
+	}
+}
+
+static void *cgroup_iter_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct cgroup_subsys_state *curr = (struct cgroup_subsys_state *)v;
+	struct cgroup_iter_priv *p = seq->private;
+
+	++*pos;
+	if (p->terminate)
+		return NULL;
+
+	if (p->order == BPF_CGROUP_ITER_DESCENDANTS_PRE)
+		return css_next_descendant_pre(curr, p->start_css);
+	else if (p->order == BPF_CGROUP_ITER_DESCENDANTS_POST)
+		return css_next_descendant_post(curr, p->start_css);
+	else if (p->order == BPF_CGROUP_ITER_ANCESTORS_UP)
+		return curr->parent;
+	else  /* BPF_CGROUP_ITER_SELF_ONLY */
+		return NULL;
+}
+
+static int __cgroup_iter_seq_show(struct seq_file *seq,
+				  struct cgroup_subsys_state *css, int in_stop)
+{
+	struct cgroup_iter_priv *p = seq->private;
+	struct bpf_iter__cgroup ctx;
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+	int ret = 0;
+
+	/* cgroup is dead, skip this element */
+	if (css && cgroup_is_dead(css->cgroup))
+		return 0;
+
+	ctx.meta = &meta;
+	ctx.cgroup = css ? css->cgroup : NULL;
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, in_stop);
+	if (prog)
+		ret = bpf_iter_run_prog(prog, &ctx);
+
+	/* if prog returns > 0, terminate after this element. */
+	if (ret != 0)
+		p->terminate = true;
+
+	return 0;
+}
+
+static int cgroup_iter_seq_show(struct seq_file *seq, void *v)
+{
+	return __cgroup_iter_seq_show(seq, (struct cgroup_subsys_state *)v,
+				      false);
+}
+
+static const struct seq_operations cgroup_iter_seq_ops = {
+	.start  = cgroup_iter_seq_start,
+	.next   = cgroup_iter_seq_next,
+	.stop   = cgroup_iter_seq_stop,
+	.show   = cgroup_iter_seq_show,
+};
+
+BTF_ID_LIST_SINGLE(bpf_cgroup_btf_id, struct, cgroup)
+
+static int cgroup_iter_seq_init(void *priv, struct bpf_iter_aux_info *aux)
+{
+	struct cgroup_iter_priv *p = (struct cgroup_iter_priv *)priv;
+	struct cgroup *cgrp = aux->cgroup.start;
+
+	p->start_css = &cgrp->self;
+	p->terminate = false;
+	p->visited_all = false;
+	p->order = aux->cgroup.order;
+	return 0;
+}
+
+static const struct bpf_iter_seq_info cgroup_iter_seq_info = {
+	.seq_ops		= &cgroup_iter_seq_ops,
+	.init_seq_private	= cgroup_iter_seq_init,
+	.seq_priv_size		= sizeof(struct cgroup_iter_priv),
+};
+
+static int bpf_iter_attach_cgroup(struct bpf_prog *prog,
+				  union bpf_iter_link_info *linfo,
+				  struct bpf_iter_aux_info *aux)
+{
+	int fd = linfo->cgroup.cgroup_fd;
+	u64 id = linfo->cgroup.cgroup_id;
+	int order = linfo->cgroup.order;
+	struct cgroup *cgrp;
+
+	if (order != BPF_CGROUP_ITER_DESCENDANTS_PRE &&
+	    order != BPF_CGROUP_ITER_DESCENDANTS_POST &&
+	    order != BPF_CGROUP_ITER_ANCESTORS_UP &&
+	    order != BPF_CGROUP_ITER_SELF_ONLY)
+		return -EINVAL;
+
+	if (fd && id)
+		return -EINVAL;
+
+	if (fd)
+		cgrp = cgroup_get_from_fd(fd);
+	else if (id)
+		cgrp = cgroup_get_from_id(id);
+	else /* walk the entire hierarchy by default. */
+		cgrp = cgroup_get_from_path("/");
+
+	if (IS_ERR(cgrp))
+		return PTR_ERR(cgrp);
+
+	aux->cgroup.start = cgrp;
+	aux->cgroup.order = order;
+	return 0;
+}
+
+static void bpf_iter_detach_cgroup(struct bpf_iter_aux_info *aux)
+{
+	cgroup_put(aux->cgroup.start);
+}
+
+static void bpf_iter_cgroup_show_fdinfo(const struct bpf_iter_aux_info *aux,
+					struct seq_file *seq)
+{
+	char *buf;
+
+	buf = kzalloc(PATH_MAX, GFP_KERNEL);
+	if (!buf) {
+		seq_puts(seq, "cgroup_path:\t<unknown>\n");
+		goto show_order;
+	}
+
+	/* If cgroup_path_ns() fails, buf will be an empty string, cgroup_path
+	 * will print nothing.
+	 *
+	 * Path is in the calling process's cgroup namespace.
+	 */
+	cgroup_path_ns(aux->cgroup.start, buf, PATH_MAX,
+		       current->nsproxy->cgroup_ns);
+	seq_printf(seq, "cgroup_path:\t%s\n", buf);
+	kfree(buf);
+
+show_order:
+	if (aux->cgroup.order == BPF_CGROUP_ITER_DESCENDANTS_PRE)
+		seq_puts(seq, "order: descendants_pre\n");
+	else if (aux->cgroup.order == BPF_CGROUP_ITER_DESCENDANTS_POST)
+		seq_puts(seq, "order: descendants_post\n");
+	else if (aux->cgroup.order == BPF_CGROUP_ITER_ANCESTORS_UP)
+		seq_puts(seq, "order: ancestors_up\n");
+	else /* BPF_CGROUP_ITER_SELF_ONLY */
+		seq_puts(seq, "order: self_only\n");
+}
+
+static int bpf_iter_cgroup_fill_link_info(const struct bpf_iter_aux_info *aux,
+					  struct bpf_link_info *info)
+{
+	info->iter.cgroup.order = aux->cgroup.order;
+	info->iter.cgroup.cgroup_id = cgroup_id(aux->cgroup.start);
+	return 0;
+}
+
+DEFINE_BPF_ITER_FUNC(cgroup, struct bpf_iter_meta *meta,
+		     struct cgroup *cgroup)
+
+static struct bpf_iter_reg bpf_cgroup_reg_info = {
+	.target			= "cgroup",
+	.feature		= BPF_ITER_RESCHED,
+	.attach_target		= bpf_iter_attach_cgroup,
+	.detach_target		= bpf_iter_detach_cgroup,
+	.show_fdinfo		= bpf_iter_cgroup_show_fdinfo,
+	.fill_link_info		= bpf_iter_cgroup_fill_link_info,
+	.ctx_arg_info_size	= 1,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__cgroup, cgroup),
+		  PTR_TO_BTF_ID_OR_NULL },
+	},
+	.seq_info		= &cgroup_iter_seq_info,
+};
+
+static int __init bpf_cgroup_iter_init(void)
+{
+	bpf_cgroup_reg_info.ctx_arg_info[0].btf_id = bpf_cgroup_btf_id[0];
+	return bpf_iter_reg_target(&bpf_cgroup_reg_info);
+}
+
+late_initcall(bpf_cgroup_iter_init);

kernel/bpf/hashtab.c

@@ -14,6 +14,7 @@
 #include "percpu_freelist.h"
 #include "bpf_lru_list.h"
 #include "map_in_map.h"
+#include <linux/bpf_mem_alloc.h>
 
 #define HTAB_CREATE_FLAG_MASK						\
 	(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE |	\
@@ -92,6 +93,8 @@ struct bucket {
 
 struct bpf_htab {
 	struct bpf_map map;
+	struct bpf_mem_alloc ma;
+	struct bpf_mem_alloc pcpu_ma;
 	struct bucket *buckets;
 	void *elems;
 	union {
@@ -99,7 +102,12 @@ struct bpf_htab {
 		struct bpf_lru lru;
 	};
 	struct htab_elem *__percpu *extra_elems;
-	atomic_t count;	/* number of elements in this hashtable */
+	/* number of elements in non-preallocated hashtable are kept
+	 * in either pcount or count
+	 */
+	struct percpu_counter pcount;
+	atomic_t count;
+	bool use_percpu_counter;
 	u32 n_buckets;	/* number of hash buckets */
 	u32 elem_size;	/* size of each element in bytes */
 	u32 hashrnd;
@@ -114,14 +122,14 @@ struct htab_elem {
 		struct {
 			void *padding;
 			union {
-				struct bpf_htab *htab;
 				struct pcpu_freelist_node fnode;
 				struct htab_elem *batch_flink;
 			};
 		};
 	};
 	union {
-		struct rcu_head rcu;
+		/* pointer to per-cpu pointer */
+		void *ptr_to_pptr;
 		struct bpf_lru_node lru_node;
 	};
 	u32 hash;
@@ -162,17 +170,25 @@ static inline int htab_lock_bucket(const struct bpf_htab *htab,
 				   unsigned long *pflags)
 {
 	unsigned long flags;
+	bool use_raw_lock;
 
 	hash = hash & HASHTAB_MAP_LOCK_MASK;
 
-	migrate_disable();
+	use_raw_lock = htab_use_raw_lock(htab);
+	if (use_raw_lock)
+		preempt_disable();
+	else
+		migrate_disable();
 	if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) {
 		__this_cpu_dec(*(htab->map_locked[hash]));
-		migrate_enable();
+		if (use_raw_lock)
+			preempt_enable();
+		else
+			migrate_enable();
 		return -EBUSY;
 	}
 
-	if (htab_use_raw_lock(htab))
+	if (use_raw_lock)
 		raw_spin_lock_irqsave(&b->raw_lock, flags);
 	else
 		spin_lock_irqsave(&b->lock, flags);
@@ -185,13 +201,18 @@ static inline void htab_unlock_bucket(const struct bpf_htab *htab,
 				      struct bucket *b, u32 hash,
 				      unsigned long flags)
 {
+	bool use_raw_lock = htab_use_raw_lock(htab);
+
 	hash = hash & HASHTAB_MAP_LOCK_MASK;
-	if (htab_use_raw_lock(htab))
+	if (use_raw_lock)
 		raw_spin_unlock_irqrestore(&b->raw_lock, flags);
 	else
 		spin_unlock_irqrestore(&b->lock, flags);
 	__this_cpu_dec(*(htab->map_locked[hash]));
-	migrate_enable();
+	if (use_raw_lock)
+		preempt_enable();
+	else
+		migrate_enable();
 }
 
 static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node);
@@ -428,8 +449,6 @@ static int htab_map_alloc_check(union bpf_attr *attr)
 	bool zero_seed = (attr->map_flags & BPF_F_ZERO_SEED);
 	int numa_node = bpf_map_attr_numa_node(attr);
 
-	BUILD_BUG_ON(offsetof(struct htab_elem, htab) !=
-		     offsetof(struct htab_elem, hash_node.pprev));
 	BUILD_BUG_ON(offsetof(struct htab_elem, fnode.next) !=
 		     offsetof(struct htab_elem, hash_node.pprev));
 
@@ -550,6 +569,29 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 
 	htab_init_buckets(htab);
 
+/* compute_batch_value() computes batch value as num_online_cpus() * 2
+ * and __percpu_counter_compare() needs
+ * htab->max_entries - cur_number_of_elems to be more than batch * num_online_cpus()
+ * for percpu_counter to be faster than atomic_t. In practice the average bpf
+ * hash map size is 10k, which means that a system with 64 cpus will fill
+ * hashmap to 20% of 10k before percpu_counter becomes ineffective. Therefore
+ * define our own batch count as 32 then 10k hash map can be filled up to 80%:
+ * 10k - 8k > 32 _batch_ * 64 _cpus_
+ * and __percpu_counter_compare() will still be fast. At that point hash map
+ * collisions will dominate its performance anyway. Assume that hash map filled
+ * to 50+% isn't going to be O(1) and use the following formula to choose
+ * between percpu_counter and atomic_t.
+ */
+#define PERCPU_COUNTER_BATCH 32
+	if (attr->max_entries / 2 > num_online_cpus() * PERCPU_COUNTER_BATCH)
+		htab->use_percpu_counter = true;
+
+	if (htab->use_percpu_counter) {
+		err = percpu_counter_init(&htab->pcount, 0, GFP_KERNEL);
+		if (err)
+			goto free_map_locked;
+	}
+
 	if (prealloc) {
 		err = prealloc_init(htab);
 		if (err)
@@ -563,6 +605,16 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 			if (err)
 				goto free_prealloc;
 		}
+	} else {
+		err = bpf_mem_alloc_init(&htab->ma, htab->elem_size, false);
+		if (err)
+			goto free_map_locked;
+		if (percpu) {
+			err = bpf_mem_alloc_init(&htab->pcpu_ma,
+						 round_up(htab->map.value_size, 8), true);
+			if (err)
+				goto free_map_locked;
+		}
 	}
 
 	return &htab->map;
@@ -573,6 +625,8 @@ free_map_locked:
 	for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++)
 		free_percpu(htab->map_locked[i]);
 	bpf_map_area_free(htab->buckets);
+	bpf_mem_alloc_destroy(&htab->pcpu_ma);
+	bpf_mem_alloc_destroy(&htab->ma);
 free_htab:
 	lockdep_unregister_key(&htab->lockdep_key);
 	bpf_map_area_free(htab);
@@ -847,17 +901,9 @@ find_first_elem:
 static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l)
 {
 	if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH)
-		free_percpu(htab_elem_get_ptr(l, htab->map.key_size));
+		bpf_mem_cache_free(&htab->pcpu_ma, l->ptr_to_pptr);
 	check_and_free_fields(htab, l);
-	kfree(l);
-}
-
-static void htab_elem_free_rcu(struct rcu_head *head)
-{
-	struct htab_elem *l = container_of(head, struct htab_elem, rcu);
-	struct bpf_htab *htab = l->htab;
-
-	htab_elem_free(htab, l);
+	bpf_mem_cache_free(&htab->ma, l);
 }
 
 static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l)
@@ -871,6 +917,31 @@ static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l)
 	}
 }
 
+static bool is_map_full(struct bpf_htab *htab)
+{
+	if (htab->use_percpu_counter)
+		return __percpu_counter_compare(&htab->pcount, htab->map.max_entries,
+						PERCPU_COUNTER_BATCH) >= 0;
+	return atomic_read(&htab->count) >= htab->map.max_entries;
+}
+
+static void inc_elem_count(struct bpf_htab *htab)
+{
+	if (htab->use_percpu_counter)
+		percpu_counter_add_batch(&htab->pcount, 1, PERCPU_COUNTER_BATCH);
+	else
+		atomic_inc(&htab->count);
+}
+
+static void dec_elem_count(struct bpf_htab *htab)
+{
+	if (htab->use_percpu_counter)
+		percpu_counter_add_batch(&htab->pcount, -1, PERCPU_COUNTER_BATCH);
+	else
+		atomic_dec(&htab->count);
+}
+
+
 static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
 {
 	htab_put_fd_value(htab, l);
@@ -879,9 +950,8 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
 		check_and_free_fields(htab, l);
 		__pcpu_freelist_push(&htab->freelist, &l->fnode);
 	} else {
-		atomic_dec(&htab->count);
-		l->htab = htab;
-		call_rcu(&l->rcu, htab_elem_free_rcu);
+		dec_elem_count(htab);
+		htab_elem_free(htab, l);
 	}
 }
 
@@ -906,13 +976,12 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr,
 static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr,
 			    void *value, bool onallcpus)
 {
-	/* When using prealloc and not setting the initial value on all cpus,
-	 * zero-fill element values for other cpus (just as what happens when
-	 * not using prealloc). Otherwise, bpf program has no way to ensure
+	/* When not setting the initial value on all cpus, zero-fill element
+	 * values for other cpus. Otherwise, bpf program has no way to ensure
 	 * known initial values for cpus other than current one
 	 * (onallcpus=false always when coming from bpf prog).
 	 */
-	if (htab_is_prealloc(htab) && !onallcpus) {
+	if (!onallcpus) {
 		u32 size = round_up(htab->map.value_size, 8);
 		int current_cpu = raw_smp_processor_id();
 		int cpu;
@@ -963,19 +1032,16 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 			l_new = container_of(l, struct htab_elem, fnode);
 		}
 	} else {
-		if (atomic_inc_return(&htab->count) > htab->map.max_entries)
-			if (!old_elem) {
+		if (is_map_full(htab))
+			if (!old_elem)
 				/* when map is full and update() is replacing
 				 * old element, it's ok to allocate, since
 				 * old element will be freed immediately.
 				 * Otherwise return an error
 				 */
-				l_new = ERR_PTR(-E2BIG);
-				goto dec_count;
-			}
-		l_new = bpf_map_kmalloc_node(&htab->map, htab->elem_size,
-					     GFP_NOWAIT | __GFP_NOWARN,
-					     htab->map.numa_node);
+				return ERR_PTR(-E2BIG);
+		inc_elem_count(htab);
+		l_new = bpf_mem_cache_alloc(&htab->ma);
 		if (!l_new) {
 			l_new = ERR_PTR(-ENOMEM);
 			goto dec_count;
@@ -986,18 +1052,18 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 
 	memcpy(l_new->key, key, key_size);
 	if (percpu) {
-		size = round_up(size, 8);
 		if (prealloc) {
 			pptr = htab_elem_get_ptr(l_new, key_size);
 		} else {
 			/* alloc_percpu zero-fills */
-			pptr = bpf_map_alloc_percpu(&htab->map, size, 8,
-						    GFP_NOWAIT | __GFP_NOWARN);
+			pptr = bpf_mem_cache_alloc(&htab->pcpu_ma);
 			if (!pptr) {
-				kfree(l_new);
+				bpf_mem_cache_free(&htab->ma, l_new);
 				l_new = ERR_PTR(-ENOMEM);
 				goto dec_count;
 			}
+			l_new->ptr_to_pptr = pptr;
+			pptr = *(void **)pptr;
 		}
 
 		pcpu_init_value(htab, pptr, value, onallcpus);
@@ -1016,7 +1082,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 	l_new->hash = hash;
 	return l_new;
 dec_count:
-	atomic_dec(&htab->count);
+	dec_elem_count(htab);
 	return l_new;
 }
 
@@ -1416,6 +1482,10 @@ static void delete_all_elements(struct bpf_htab *htab)
 {
 	int i;
 
+	/* It's called from a worker thread, so disable migration here,
+	 * since bpf_mem_cache_free() relies on that.
+	 */
+	migrate_disable();
 	for (i = 0; i < htab->n_buckets; i++) {
 		struct hlist_nulls_head *head = select_bucket(htab, i);
 		struct hlist_nulls_node *n;
@@ -1426,6 +1496,7 @@ static void delete_all_elements(struct bpf_htab *htab)
 			htab_elem_free(htab, l);
 		}
 	}
+	migrate_enable();
 }
 
 static void htab_free_malloced_timers(struct bpf_htab *htab)
@@ -1475,10 +1546,10 @@ static void htab_map_free(struct bpf_map *map)
 	 * There is no need to synchronize_rcu() here to protect map elements.
 	 */
 
-	/* some of free_htab_elem() callbacks for elements of this map may
-	 * not have executed. Wait for them.
+	/* htab no longer uses call_rcu() directly. bpf_mem_alloc does it
+	 * underneath and is reponsible for waiting for callbacks to finish
+	 * during bpf_mem_alloc_destroy().
 	 */
-	rcu_barrier();
 	if (!htab_is_prealloc(htab)) {
 		delete_all_elements(htab);
 	} else {
@@ -1489,6 +1560,10 @@ static void htab_map_free(struct bpf_map *map)
 	bpf_map_free_kptr_off_tab(map);
 	free_percpu(htab->extra_elems);
 	bpf_map_area_free(htab->buckets);
+	bpf_mem_alloc_destroy(&htab->pcpu_ma);
+	bpf_mem_alloc_destroy(&htab->ma);
+	if (htab->use_percpu_counter)
+		percpu_counter_destroy(&htab->pcount);
 	for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++)
 		free_percpu(htab->map_locked[i]);
 	lockdep_unregister_key(&htab->lockdep_key);
@@ -1691,8 +1766,11 @@ again_nocopy:
 	/* do not grab the lock unless need it (bucket_cnt > 0). */
 	if (locked) {
 		ret = htab_lock_bucket(htab, b, batch, &flags);
-		if (ret)
-			goto next_batch;
+		if (ret) {
+			rcu_read_unlock();
+			bpf_enable_instrumentation();
+			goto after_loop;
+		}
 	}
 
 	bucket_cnt = 0;

kernel/bpf/helpers.c

@@ -427,40 +427,7 @@ const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto = {
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_ANYTHING,
 };
-
-#ifdef CONFIG_CGROUP_BPF
-
-BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags)
-{
-	/* flags argument is not used now,
-	 * but provides an ability to extend the API.
-	 * verifier checks that its value is correct.
-	 */
-	enum bpf_cgroup_storage_type stype = cgroup_storage_type(map);
-	struct bpf_cgroup_storage *storage;
-	struct bpf_cg_run_ctx *ctx;
-	void *ptr;
-
-	/* get current cgroup storage from BPF run context */
-	ctx = container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx);
-	storage = ctx->prog_item->cgroup_storage[stype];
-
-	if (stype == BPF_CGROUP_STORAGE_SHARED)
-		ptr = &READ_ONCE(storage->buf)->data[0];
-	else
-		ptr = this_cpu_ptr(storage->percpu_buf);
-
-	return (unsigned long)ptr;
-}
-
-const struct bpf_func_proto bpf_get_local_storage_proto = {
-	.func		= bpf_get_local_storage,
-	.gpl_only	= false,
-	.ret_type	= RET_PTR_TO_MAP_VALUE,
-	.arg1_type	= ARG_CONST_MAP_PTR,
-	.arg2_type	= ARG_ANYTHING,
-};
-#endif
+#endif /* CONFIG_CGROUPS */
 
 #define BPF_STRTOX_BASE_MASK 0x1F
 
@@ -589,7 +556,6 @@ const struct bpf_func_proto bpf_strtoul_proto = {
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_PTR_TO_LONG,
 };
-#endif
 
 BPF_CALL_3(bpf_strncmp, const char *, s1, u32, s1_sz, const char *, s2)
 {
@@ -1647,12 +1613,12 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_ringbuf_submit_dynptr_proto;
 	case BPF_FUNC_ringbuf_discard_dynptr:
 		return &bpf_ringbuf_discard_dynptr_proto;
-	case BPF_FUNC_for_each_map_elem:
-		return &bpf_for_each_map_elem_proto;
-	case BPF_FUNC_loop:
-		return &bpf_loop_proto;
 	case BPF_FUNC_strncmp:
 		return &bpf_strncmp_proto;
+	case BPF_FUNC_strtol:
+		return &bpf_strtol_proto;
+	case BPF_FUNC_strtoul:
+		return &bpf_strtoul_proto;
 	case BPF_FUNC_dynptr_from_mem:
 		return &bpf_dynptr_from_mem_proto;
 	case BPF_FUNC_dynptr_read:
@@ -1689,6 +1655,10 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_timer_cancel_proto;
 	case BPF_FUNC_kptr_xchg:
 		return &bpf_kptr_xchg_proto;
+	case BPF_FUNC_for_each_map_elem:
+		return &bpf_for_each_map_elem_proto;
+	case BPF_FUNC_loop:
+		return &bpf_loop_proto;
 	default:
 		break;
 	}

kernel/bpf/memalloc.c

@@ -0,0 +1,634 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+#include <linux/mm.h>
+#include <linux/llist.h>
+#include <linux/bpf.h>
+#include <linux/irq_work.h>
+#include <linux/bpf_mem_alloc.h>
+#include <linux/memcontrol.h>
+#include <asm/local.h>
+
+/* Any context (including NMI) BPF specific memory allocator.
+ *
+ * Tracing BPF programs can attach to kprobe and fentry. Hence they
+ * run in unknown context where calling plain kmalloc() might not be safe.
+ *
+ * Front-end kmalloc() with per-cpu per-bucket cache of free elements.
+ * Refill this cache asynchronously from irq_work.
+ *
+ * CPU_0 buckets
+ * 16 32 64 96 128 196 256 512 1024 2048 4096
+ * ...
+ * CPU_N buckets
+ * 16 32 64 96 128 196 256 512 1024 2048 4096
+ *
+ * The buckets are prefilled at the start.
+ * BPF programs always run with migration disabled.
+ * It's safe to allocate from cache of the current cpu with irqs disabled.
+ * Free-ing is always done into bucket of the current cpu as well.
+ * irq_work trims extra free elements from buckets with kfree
+ * and refills them with kmalloc, so global kmalloc logic takes care
+ * of freeing objects allocated by one cpu and freed on another.
+ *
+ * Every allocated objected is padded with extra 8 bytes that contains
+ * struct llist_node.
+ */
+#define LLIST_NODE_SZ sizeof(struct llist_node)
+
+/* similar to kmalloc, but sizeof == 8 bucket is gone */
+static u8 size_index[24] __ro_after_init = {
+	3,	/* 8 */
+	3,	/* 16 */
+	4,	/* 24 */
+	4,	/* 32 */
+	5,	/* 40 */
+	5,	/* 48 */
+	5,	/* 56 */
+	5,	/* 64 */
+	1,	/* 72 */
+	1,	/* 80 */
+	1,	/* 88 */
+	1,	/* 96 */
+	6,	/* 104 */
+	6,	/* 112 */
+	6,	/* 120 */
+	6,	/* 128 */
+	2,	/* 136 */
+	2,	/* 144 */
+	2,	/* 152 */
+	2,	/* 160 */
+	2,	/* 168 */
+	2,	/* 176 */
+	2,	/* 184 */
+	2	/* 192 */
+};
+
+static int bpf_mem_cache_idx(size_t size)
+{
+	if (!size || size > 4096)
+		return -1;
+
+	if (size <= 192)
+		return size_index[(size - 1) / 8] - 1;
+
+	return fls(size - 1) - 1;
+}
+
+#define NUM_CACHES 11
+
+struct bpf_mem_cache {
+	/* per-cpu list of free objects of size 'unit_size'.
+	 * All accesses are done with interrupts disabled and 'active' counter
+	 * protection with __llist_add() and __llist_del_first().
+	 */
+	struct llist_head free_llist;
+	local_t active;
+
+	/* Operations on the free_list from unit_alloc/unit_free/bpf_mem_refill
+	 * are sequenced by per-cpu 'active' counter. But unit_free() cannot
+	 * fail. When 'active' is busy the unit_free() will add an object to
+	 * free_llist_extra.
+	 */
+	struct llist_head free_llist_extra;
+
+	struct irq_work refill_work;
+	struct obj_cgroup *objcg;
+	int unit_size;
+	/* count of objects in free_llist */
+	int free_cnt;
+	int low_watermark, high_watermark, batch;
+	int percpu_size;
+
+	struct rcu_head rcu;
+	struct llist_head free_by_rcu;
+	struct llist_head waiting_for_gp;
+	atomic_t call_rcu_in_progress;
+};
+
+struct bpf_mem_caches {
+	struct bpf_mem_cache cache[NUM_CACHES];
+};
+
+static struct llist_node notrace *__llist_del_first(struct llist_head *head)
+{
+	struct llist_node *entry, *next;
+
+	entry = head->first;
+	if (!entry)
+		return NULL;
+	next = entry->next;
+	head->first = next;
+	return entry;
+}
+
+static void *__alloc(struct bpf_mem_cache *c, int node)
+{
+	/* Allocate, but don't deplete atomic reserves that typical
+	 * GFP_ATOMIC would do. irq_work runs on this cpu and kmalloc
+	 * will allocate from the current numa node which is what we
+	 * want here.
+	 */
+	gfp_t flags = GFP_NOWAIT | __GFP_NOWARN | __GFP_ACCOUNT;
+
+	if (c->percpu_size) {
+		void **obj = kmalloc_node(c->percpu_size, flags, node);
+		void *pptr = __alloc_percpu_gfp(c->unit_size, 8, flags);
+
+		if (!obj || !pptr) {
+			free_percpu(pptr);
+			kfree(obj);
+			return NULL;
+		}
+		obj[1] = pptr;
+		return obj;
+	}
+
+	return kmalloc_node(c->unit_size, flags, node);
+}
+
+static struct mem_cgroup *get_memcg(const struct bpf_mem_cache *c)
+{
+#ifdef CONFIG_MEMCG_KMEM
+	if (c->objcg)
+		return get_mem_cgroup_from_objcg(c->objcg);
+#endif
+
+#ifdef CONFIG_MEMCG
+	return root_mem_cgroup;
+#else
+	return NULL;
+#endif
+}
+
+/* Mostly runs from irq_work except __init phase. */
+static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
+{
+	struct mem_cgroup *memcg = NULL, *old_memcg;
+	unsigned long flags;
+	void *obj;
+	int i;
+
+	memcg = get_memcg(c);
+	old_memcg = set_active_memcg(memcg);
+	for (i = 0; i < cnt; i++) {
+		obj = __alloc(c, node);
+		if (!obj)
+			break;
+		if (IS_ENABLED(CONFIG_PREEMPT_RT))
+			/* In RT irq_work runs in per-cpu kthread, so disable
+			 * interrupts to avoid preemption and interrupts and
+			 * reduce the chance of bpf prog executing on this cpu
+			 * when active counter is busy.
+			 */
+			local_irq_save(flags);
+		/* alloc_bulk runs from irq_work which will not preempt a bpf
+		 * program that does unit_alloc/unit_free since IRQs are
+		 * disabled there. There is no race to increment 'active'
+		 * counter. It protects free_llist from corruption in case NMI
+		 * bpf prog preempted this loop.
+		 */
+		WARN_ON_ONCE(local_inc_return(&c->active) != 1);
+		__llist_add(obj, &c->free_llist);
+		c->free_cnt++;
+		local_dec(&c->active);
+		if (IS_ENABLED(CONFIG_PREEMPT_RT))
+			local_irq_restore(flags);
+	}
+	set_active_memcg(old_memcg);
+	mem_cgroup_put(memcg);
+}
+
+static void free_one(struct bpf_mem_cache *c, void *obj)
+{
+	if (c->percpu_size) {
+		free_percpu(((void **)obj)[1]);
+		kfree(obj);
+		return;
+	}
+
+	kfree(obj);
+}
+
+static void __free_rcu(struct rcu_head *head)
+{
+	struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu);
+	struct llist_node *llnode = llist_del_all(&c->waiting_for_gp);
+	struct llist_node *pos, *t;
+
+	llist_for_each_safe(pos, t, llnode)
+		free_one(c, pos);
+	atomic_set(&c->call_rcu_in_progress, 0);
+}
+
+static void __free_rcu_tasks_trace(struct rcu_head *head)
+{
+	struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu);
+
+	call_rcu(&c->rcu, __free_rcu);
+}
+
+static void enque_to_free(struct bpf_mem_cache *c, void *obj)
+{
+	struct llist_node *llnode = obj;
+
+	/* bpf_mem_cache is a per-cpu object. Freeing happens in irq_work.
+	 * Nothing races to add to free_by_rcu list.
+	 */
+	__llist_add(llnode, &c->free_by_rcu);
+}
+
+static void do_call_rcu(struct bpf_mem_cache *c)
+{
+	struct llist_node *llnode, *t;
+
+	if (atomic_xchg(&c->call_rcu_in_progress, 1))
+		return;
+
+	WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp));
+	llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu))
+		/* There is no concurrent __llist_add(waiting_for_gp) access.
+		 * It doesn't race with llist_del_all either.
+		 * But there could be two concurrent llist_del_all(waiting_for_gp):
+		 * from __free_rcu() and from drain_mem_cache().
+		 */
+		__llist_add(llnode, &c->waiting_for_gp);
+	/* Use call_rcu_tasks_trace() to wait for sleepable progs to finish.
+	 * Then use call_rcu() to wait for normal progs to finish
+	 * and finally do free_one() on each element.
+	 */
+	call_rcu_tasks_trace(&c->rcu, __free_rcu_tasks_trace);
+}
+
+static void free_bulk(struct bpf_mem_cache *c)
+{
+	struct llist_node *llnode, *t;
+	unsigned long flags;
+	int cnt;
+
+	do {
+		if (IS_ENABLED(CONFIG_PREEMPT_RT))
+			local_irq_save(flags);
+		WARN_ON_ONCE(local_inc_return(&c->active) != 1);
+		llnode = __llist_del_first(&c->free_llist);
+		if (llnode)
+			cnt = --c->free_cnt;
+		else
+			cnt = 0;
+		local_dec(&c->active);
+		if (IS_ENABLED(CONFIG_PREEMPT_RT))
+			local_irq_restore(flags);
+		enque_to_free(c, llnode);
+	} while (cnt > (c->high_watermark + c->low_watermark) / 2);
+
+	/* and drain free_llist_extra */
+	llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra))
+		enque_to_free(c, llnode);
+	do_call_rcu(c);
+}
+
+static void bpf_mem_refill(struct irq_work *work)
+{
+	struct bpf_mem_cache *c = container_of(work, struct bpf_mem_cache, refill_work);
+	int cnt;
+
+	/* Racy access to free_cnt. It doesn't need to be 100% accurate */
+	cnt = c->free_cnt;
+	if (cnt < c->low_watermark)
+		/* irq_work runs on this cpu and kmalloc will allocate
+		 * from the current numa node which is what we want here.
+		 */
+		alloc_bulk(c, c->batch, NUMA_NO_NODE);
+	else if (cnt > c->high_watermark)
+		free_bulk(c);
+}
+
+static void notrace irq_work_raise(struct bpf_mem_cache *c)
+{
+	irq_work_queue(&c->refill_work);
+}
+
+/* For typical bpf map case that uses bpf_mem_cache_alloc and single bucket
+ * the freelist cache will be elem_size * 64 (or less) on each cpu.
+ *
+ * For bpf programs that don't have statically known allocation sizes and
+ * assuming (low_mark + high_mark) / 2 as an average number of elements per
+ * bucket and all buckets are used the total amount of memory in freelists
+ * on each cpu will be:
+ * 64*16 + 64*32 + 64*64 + 64*96 + 64*128 + 64*196 + 64*256 + 32*512 + 16*1024 + 8*2048 + 4*4096
+ * == ~ 116 Kbyte using below heuristic.
+ * Initialized, but unused bpf allocator (not bpf map specific one) will
+ * consume ~ 11 Kbyte per cpu.
+ * Typical case will be between 11K and 116K closer to 11K.
+ * bpf progs can and should share bpf_mem_cache when possible.
+ */
+
+static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
+{
+	init_irq_work(&c->refill_work, bpf_mem_refill);
+	if (c->unit_size <= 256) {
+		c->low_watermark = 32;
+		c->high_watermark = 96;
+	} else {
+		/* When page_size == 4k, order-0 cache will have low_mark == 2
+		 * and high_mark == 6 with batch alloc of 3 individual pages at
+		 * a time.
+		 * 8k allocs and above low == 1, high == 3, batch == 1.
+		 */
+		c->low_watermark = max(32 * 256 / c->unit_size, 1);
+		c->high_watermark = max(96 * 256 / c->unit_size, 3);
+	}
+	c->batch = max((c->high_watermark - c->low_watermark) / 4 * 3, 1);
+
+	/* To avoid consuming memory assume that 1st run of bpf
+	 * prog won't be doing more than 4 map_update_elem from
+	 * irq disabled region
+	 */
+	alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu));
+}
+
+/* When size != 0 bpf_mem_cache for each cpu.
+ * This is typical bpf hash map use case when all elements have equal size.
+ *
+ * When size == 0 allocate 11 bpf_mem_cache-s for each cpu, then rely on
+ * kmalloc/kfree. Max allocation size is 4096 in this case.
+ * This is bpf_dynptr and bpf_kptr use case.
+ */
+int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
+{
+	static u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096};
+	struct bpf_mem_caches *cc, __percpu *pcc;
+	struct bpf_mem_cache *c, __percpu *pc;
+	struct obj_cgroup *objcg = NULL;
+	int cpu, i, unit_size, percpu_size = 0;
+
+	if (size) {
+		pc = __alloc_percpu_gfp(sizeof(*pc), 8, GFP_KERNEL);
+		if (!pc)
+			return -ENOMEM;
+
+		if (percpu)
+			/* room for llist_node and per-cpu pointer */
+			percpu_size = LLIST_NODE_SZ + sizeof(void *);
+		else
+			size += LLIST_NODE_SZ; /* room for llist_node */
+		unit_size = size;
+
+#ifdef CONFIG_MEMCG_KMEM
+		objcg = get_obj_cgroup_from_current();
+#endif
+		for_each_possible_cpu(cpu) {
+			c = per_cpu_ptr(pc, cpu);
+			c->unit_size = unit_size;
+			c->objcg = objcg;
+			c->percpu_size = percpu_size;
+			prefill_mem_cache(c, cpu);
+		}
+		ma->cache = pc;
+		return 0;
+	}
+
+	/* size == 0 && percpu is an invalid combination */
+	if (WARN_ON_ONCE(percpu))
+		return -EINVAL;
+
+	pcc = __alloc_percpu_gfp(sizeof(*cc), 8, GFP_KERNEL);
+	if (!pcc)
+		return -ENOMEM;
+#ifdef CONFIG_MEMCG_KMEM
+	objcg = get_obj_cgroup_from_current();
+#endif
+	for_each_possible_cpu(cpu) {
+		cc = per_cpu_ptr(pcc, cpu);
+		for (i = 0; i < NUM_CACHES; i++) {
+			c = &cc->cache[i];
+			c->unit_size = sizes[i];
+			c->objcg = objcg;
+			prefill_mem_cache(c, cpu);
+		}
+	}
+	ma->caches = pcc;
+	return 0;
+}
+
+static void drain_mem_cache(struct bpf_mem_cache *c)
+{
+	struct llist_node *llnode, *t;
+
+	/* No progs are using this bpf_mem_cache, but htab_map_free() called
+	 * bpf_mem_cache_free() for all remaining elements and they can be in
+	 * free_by_rcu or in waiting_for_gp lists, so drain those lists now.
+	 */
+	llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu))
+		free_one(c, llnode);
+	llist_for_each_safe(llnode, t, llist_del_all(&c->waiting_for_gp))
+		free_one(c, llnode);
+	llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist))
+		free_one(c, llnode);
+	llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra))
+		free_one(c, llnode);
+}
+
+static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma)
+{
+	free_percpu(ma->cache);
+	free_percpu(ma->caches);
+	ma->cache = NULL;
+	ma->caches = NULL;
+}
+
+static void free_mem_alloc(struct bpf_mem_alloc *ma)
+{
+	/* waiting_for_gp lists was drained, but __free_rcu might
+	 * still execute. Wait for it now before we freeing percpu caches.
+	 */
+	rcu_barrier_tasks_trace();
+	rcu_barrier();
+	free_mem_alloc_no_barrier(ma);
+}
+
+static void free_mem_alloc_deferred(struct work_struct *work)
+{
+	struct bpf_mem_alloc *ma = container_of(work, struct bpf_mem_alloc, work);
+
+	free_mem_alloc(ma);
+	kfree(ma);
+}
+
+static void destroy_mem_alloc(struct bpf_mem_alloc *ma, int rcu_in_progress)
+{
+	struct bpf_mem_alloc *copy;
+
+	if (!rcu_in_progress) {
+		/* Fast path. No callbacks are pending, hence no need to do
+		 * rcu_barrier-s.
+		 */
+		free_mem_alloc_no_barrier(ma);
+		return;
+	}
+
+	copy = kmalloc(sizeof(*ma), GFP_KERNEL);
+	if (!copy) {
+		/* Slow path with inline barrier-s */
+		free_mem_alloc(ma);
+		return;
+	}
+
+	/* Defer barriers into worker to let the rest of map memory to be freed */
+	copy->cache = ma->cache;
+	ma->cache = NULL;
+	copy->caches = ma->caches;
+	ma->caches = NULL;
+	INIT_WORK(&copy->work, free_mem_alloc_deferred);
+	queue_work(system_unbound_wq, &copy->work);
+}
+
+void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
+{
+	struct bpf_mem_caches *cc;
+	struct bpf_mem_cache *c;
+	int cpu, i, rcu_in_progress;
+
+	if (ma->cache) {
+		rcu_in_progress = 0;
+		for_each_possible_cpu(cpu) {
+			c = per_cpu_ptr(ma->cache, cpu);
+			drain_mem_cache(c);
+			rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
+		}
+		/* objcg is the same across cpus */
+		if (c->objcg)
+			obj_cgroup_put(c->objcg);
+		destroy_mem_alloc(ma, rcu_in_progress);
+	}
+	if (ma->caches) {
+		rcu_in_progress = 0;
+		for_each_possible_cpu(cpu) {
+			cc = per_cpu_ptr(ma->caches, cpu);
+			for (i = 0; i < NUM_CACHES; i++) {
+				c = &cc->cache[i];
+				drain_mem_cache(c);
+				rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
+			}
+		}
+		if (c->objcg)
+			obj_cgroup_put(c->objcg);
+		destroy_mem_alloc(ma, rcu_in_progress);
+	}
+}
+
+/* notrace is necessary here and in other functions to make sure
+ * bpf programs cannot attach to them and cause llist corruptions.
+ */
+static void notrace *unit_alloc(struct bpf_mem_cache *c)
+{
+	struct llist_node *llnode = NULL;
+	unsigned long flags;
+	int cnt = 0;
+
+	/* Disable irqs to prevent the following race for majority of prog types:
+	 * prog_A
+	 *   bpf_mem_alloc
+	 *      preemption or irq -> prog_B
+	 *        bpf_mem_alloc
+	 *
+	 * but prog_B could be a perf_event NMI prog.
+	 * Use per-cpu 'active' counter to order free_list access between
+	 * unit_alloc/unit_free/bpf_mem_refill.
+	 */
+	local_irq_save(flags);
+	if (local_inc_return(&c->active) == 1) {
+		llnode = __llist_del_first(&c->free_llist);
+		if (llnode)
+			cnt = --c->free_cnt;
+	}
+	local_dec(&c->active);
+	local_irq_restore(flags);
+
+	WARN_ON(cnt < 0);
+
+	if (cnt < c->low_watermark)
+		irq_work_raise(c);
+	return llnode;
+}
+
+/* Though 'ptr' object could have been allocated on a different cpu
+ * add it to the free_llist of the current cpu.
+ * Let kfree() logic deal with it when it's later called from irq_work.
+ */
+static void notrace unit_free(struct bpf_mem_cache *c, void *ptr)
+{
+	struct llist_node *llnode = ptr - LLIST_NODE_SZ;
+	unsigned long flags;
+	int cnt = 0;
+
+	BUILD_BUG_ON(LLIST_NODE_SZ > 8);
+
+	local_irq_save(flags);
+	if (local_inc_return(&c->active) == 1) {
+		__llist_add(llnode, &c->free_llist);
+		cnt = ++c->free_cnt;
+	} else {
+		/* unit_free() cannot fail. Therefore add an object to atomic
+		 * llist. free_bulk() will drain it. Though free_llist_extra is
+		 * a per-cpu list we have to use atomic llist_add here, since
+		 * it also can be interrupted by bpf nmi prog that does another
+		 * unit_free() into the same free_llist_extra.
+		 */
+		llist_add(llnode, &c->free_llist_extra);
+	}
+	local_dec(&c->active);
+	local_irq_restore(flags);
+
+	if (cnt > c->high_watermark)
+		/* free few objects from current cpu into global kmalloc pool */
+		irq_work_raise(c);
+}
+
+/* Called from BPF program or from sys_bpf syscall.
+ * In both cases migration is disabled.
+ */
+void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size)
+{
+	int idx;
+	void *ret;
+
+	if (!size)
+		return ZERO_SIZE_PTR;
+
+	idx = bpf_mem_cache_idx(size + LLIST_NODE_SZ);
+	if (idx < 0)
+		return NULL;
+
+	ret = unit_alloc(this_cpu_ptr(ma->caches)->cache + idx);
+	return !ret ? NULL : ret + LLIST_NODE_SZ;
+}
+
+void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr)
+{
+	int idx;
+
+	if (!ptr)
+		return;
+
+	idx = bpf_mem_cache_idx(__ksize(ptr - LLIST_NODE_SZ));
+	if (idx < 0)
+		return;
+
+	unit_free(this_cpu_ptr(ma->caches)->cache + idx, ptr);
+}
+
+void notrace *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma)
+{
+	void *ret;
+
+	ret = unit_alloc(this_cpu_ptr(ma->cache));
+	return !ret ? NULL : ret + LLIST_NODE_SZ;
+}
+
+void notrace bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr)
+{
+	if (!ptr)
+		return;
+
+	unit_free(this_cpu_ptr(ma->cache), ptr);
+}

kernel/bpf/syscall.c

@@ -638,7 +638,10 @@ static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock)
 		bpf_map_free_id(map, do_idr_lock);
 		btf_put(map->btf);
 		INIT_WORK(&map->work, bpf_map_free_deferred);
-		schedule_work(&map->work);
+		/* Avoid spawning kworkers, since they all might contend
+		 * for the same mutex like slab_mutex.
+		 */
+		queue_work(system_unbound_wq, &map->work);
 	}
 }
 
@@ -1437,9 +1440,9 @@ err_put:
 
 #define BPF_MAP_DELETE_ELEM_LAST_FIELD key
 
-static int map_delete_elem(union bpf_attr *attr)
+static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr)
 {
-	void __user *ukey = u64_to_user_ptr(attr->key);
+	bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel);
 	int ufd = attr->map_fd;
 	struct bpf_map *map;
 	struct fd f;
@@ -1459,7 +1462,7 @@ static int map_delete_elem(union bpf_attr *attr)
 		goto err_put;
 	}
 
-	key = __bpf_copy_key(ukey, map->key_size);
+	key = ___bpf_copy_key(ukey, map->key_size);
 	if (IS_ERR(key)) {
 		err = PTR_ERR(key);
 		goto err_put;
@@ -4941,7 +4944,7 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size)
 		err = map_update_elem(&attr, uattr);
 		break;
 	case BPF_MAP_DELETE_ELEM:
-		err = map_delete_elem(&attr);
+		err = map_delete_elem(&attr, uattr);
 		break;
 	case BPF_MAP_GET_NEXT_KEY:
 		err = map_get_next_key(&attr);
@@ -5073,8 +5076,10 @@ BPF_CALL_3(bpf_sys_bpf, int, cmd, union bpf_attr *, attr, u32, attr_size)
 {
 	switch (cmd) {
 	case BPF_MAP_CREATE:
+	case BPF_MAP_DELETE_ELEM:
 	case BPF_MAP_UPDATE_ELEM:
 	case BPF_MAP_FREEZE:
+	case BPF_MAP_GET_FD_BY_ID:
 	case BPF_PROG_LOAD:
 	case BPF_BTF_LOAD:
 	case BPF_LINK_CREATE:

kernel/bpf/trampoline.c

@@ -895,7 +895,7 @@ u64 notrace __bpf_prog_enter(struct bpf_prog *prog, struct bpf_tramp_run_ctx *ru
 
 	run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
 
-	if (unlikely(__this_cpu_inc_return(*(prog->active)) != 1)) {
+	if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
 		inc_misses_counter(prog);
 		return 0;
 	}
@@ -930,7 +930,7 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_
 	bpf_reset_run_ctx(run_ctx->saved_run_ctx);
 
 	update_prog_stats(prog, start);
-	__this_cpu_dec(*(prog->active));
+	this_cpu_dec(*(prog->active));
 	migrate_enable();
 	rcu_read_unlock();
 }
@@ -966,7 +966,7 @@ u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_r
 	migrate_disable();
 	might_fault();
 
-	if (unlikely(__this_cpu_inc_return(*(prog->active)) != 1)) {
+	if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
 		inc_misses_counter(prog);
 		return 0;
 	}
@@ -982,7 +982,7 @@ void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start,
 	bpf_reset_run_ctx(run_ctx->saved_run_ctx);
 
 	update_prog_stats(prog, start);
-	__this_cpu_dec(*(prog->active));
+	this_cpu_dec(*(prog->active));
 	migrate_enable();
 	rcu_read_unlock_trace();
 }

kernel/bpf/verifier.c

@@ -1092,6 +1092,7 @@ static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx)
 	id = ++env->id_gen;
 	state->refs[new_ofs].id = id;
 	state->refs[new_ofs].insn_idx = insn_idx;
+	state->refs[new_ofs].callback_ref = state->in_callback_fn ? state->frameno : 0;
 
 	return id;
 }
@@ -1104,6 +1105,9 @@ static int release_reference_state(struct bpf_func_state *state, int ptr_id)
 	last_idx = state->acquired_refs - 1;
 	for (i = 0; i < state->acquired_refs; i++) {
 		if (state->refs[i].id == ptr_id) {
+			/* Cannot release caller references in callbacks */
+			if (state->in_callback_fn && state->refs[i].callback_ref != state->frameno)
+				return -EINVAL;
 			if (last_idx && i != last_idx)
 				memcpy(&state->refs[i], &state->refs[last_idx],
 				       sizeof(*state->refs));
@@ -6918,10 +6922,17 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 		caller->regs[BPF_REG_0] = *r0;
 	}
 
-	/* Transfer references to the caller */
-	err = copy_reference_state(caller, callee);
-	if (err)
-		return err;
+	/* callback_fn frame should have released its own additions to parent's
+	 * reference state at this point, or check_reference_leak would
+	 * complain, hence it must be the same as the caller. There is no need
+	 * to copy it back.
+	 */
+	if (!callee->in_callback_fn) {
+		/* Transfer references to the caller */
+		err = copy_reference_state(caller, callee);
+		if (err)
+			return err;
+	}
 
 	*insn_idx = callee->callsite + 1;
 	if (env->log.level & BPF_LOG_LEVEL) {
@@ -7043,13 +7054,20 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 static int check_reference_leak(struct bpf_verifier_env *env)
 {
 	struct bpf_func_state *state = cur_func(env);
+	bool refs_lingering = false;
 	int i;
 
+	if (state->frameno && !state->in_callback_fn)
+		return 0;
+
 	for (i = 0; i < state->acquired_refs; i++) {
+		if (state->in_callback_fn && state->refs[i].callback_ref != state->frameno)
+			continue;
 		verbose(env, "Unreleased reference id=%d alloc_insn=%d\n",
 			state->refs[i].id, state->refs[i].insn_idx);
+		refs_lingering = true;
 	}
-	return state->acquired_refs ? -EINVAL : 0;
+	return refs_lingering ? -EINVAL : 0;
 }
 
 static int check_bpf_snprintf_call(struct bpf_verifier_env *env,
@@ -12338,6 +12356,16 @@ static int do_check(struct bpf_verifier_env *env)
 					return -EINVAL;
 				}
 
+				/* We must do check_reference_leak here before
+				 * prepare_func_exit to handle the case when
+				 * state->curframe > 0, it may be a callback
+				 * function, for which reference_state must
+				 * match caller reference state when it exits.
+				 */
+				err = check_reference_leak(env);
+				if (err)
+					return err;
+
 				if (state->curframe) {
 					/* exit from nested function */
 					err = prepare_func_exit(env, &env->insn_idx);
@@ -12347,10 +12375,6 @@ static int do_check(struct bpf_verifier_env *env)
 					continue;
 				}
 
-				err = check_reference_leak(env);
-				if (err)
-					return err;
-
 				err = check_return_code(env);
 				if (err)
 					return err;
@@ -12563,14 +12587,6 @@ err_put:
 	return err;
 }
 
-static int check_map_prealloc(struct bpf_map *map)
-{
-	return (map->map_type != BPF_MAP_TYPE_HASH &&
-		map->map_type != BPF_MAP_TYPE_PERCPU_HASH &&
-		map->map_type != BPF_MAP_TYPE_HASH_OF_MAPS) ||
-		!(map->map_flags & BPF_F_NO_PREALLOC);
-}
-
 static bool is_tracing_prog_type(enum bpf_prog_type type)
 {
 	switch (type) {
@@ -12585,50 +12601,12 @@ static bool is_tracing_prog_type(enum bpf_prog_type type)
 	}
 }
 
-static bool is_preallocated_map(struct bpf_map *map)
-{
-	if (!check_map_prealloc(map))
-		return false;
-	if (map->inner_map_meta && !check_map_prealloc(map->inner_map_meta))
-		return false;
-	return true;
-}
-
 static int check_map_prog_compatibility(struct bpf_verifier_env *env,
 					struct bpf_map *map,
 					struct bpf_prog *prog)
 
 {
 	enum bpf_prog_type prog_type = resolve_prog_type(prog);
-	/*
-	 * Validate that trace type programs use preallocated hash maps.
-	 *
-	 * For programs attached to PERF events this is mandatory as the
-	 * perf NMI can hit any arbitrary code sequence.
-	 *
-	 * All other trace types using preallocated hash maps are unsafe as
-	 * well because tracepoint or kprobes can be inside locked regions
-	 * of the memory allocator or at a place where a recursion into the
-	 * memory allocator would see inconsistent state.
-	 *
-	 * On RT enabled kernels run-time allocation of all trace type
-	 * programs is strictly prohibited due to lock type constraints. On
-	 * !RT kernels it is allowed for backwards compatibility reasons for
-	 * now, but warnings are emitted so developers are made aware of
-	 * the unsafety and can fix their programs before this is enforced.
-	 */
-	if (is_tracing_prog_type(prog_type) && !is_preallocated_map(map)) {
-		if (prog_type == BPF_PROG_TYPE_PERF_EVENT) {
-			verbose(env, "perf_event programs can only use preallocated hash map\n");
-			return -EINVAL;
-		}
-		if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
-			verbose(env, "trace type programs can only use preallocated hash map\n");
-			return -EINVAL;
-		}
-		WARN_ONCE(1, "trace type BPF program uses run-time allocation\n");
-		verbose(env, "trace type programs with run-time allocated hash maps are unsafe. Switch to preallocated hash maps.\n");
-	}
 
 	if (map_value_has_spin_lock(map)) {
 		if (prog_type == BPF_PROG_TYPE_SOCKET_FILTER) {
@@ -12675,12 +12653,6 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
 		case BPF_MAP_TYPE_LRU_PERCPU_HASH:
 		case BPF_MAP_TYPE_ARRAY_OF_MAPS:
 		case BPF_MAP_TYPE_HASH_OF_MAPS:
-			if (!is_preallocated_map(map)) {
-				verbose(env,
-					"Sleepable programs can only use preallocated maps\n");
-				return -EINVAL;
-			}
-			break;
 		case BPF_MAP_TYPE_RINGBUF:
 		case BPF_MAP_TYPE_INODE_STORAGE:
 		case BPF_MAP_TYPE_SK_STORAGE:

kernel/cgroup/rstat.c

@@ -3,6 +3,10 @@
 
 #include <linux/sched/cputime.h>
 
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/btf_ids.h>
+
 static DEFINE_SPINLOCK(cgroup_rstat_lock);
 static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock);
 
@@ -141,6 +145,31 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
 	return pos;
 }
 
+/*
+ * A hook for bpf stat collectors to attach to and flush their stats.
+ * Together with providing bpf kfuncs for cgroup_rstat_updated() and
+ * cgroup_rstat_flush(), this enables a complete workflow where bpf progs that
+ * collect cgroup stats can integrate with rstat for efficient flushing.
+ *
+ * A static noinline declaration here could cause the compiler to optimize away
+ * the function. A global noinline declaration will keep the definition, but may
+ * optimize away the callsite. Therefore, __weak is needed to ensure that the
+ * call is still emitted, by telling the compiler that we don't know what the
+ * function might eventually be.
+ *
+ * __diag_* below are needed to dismiss the missing prototype warning.
+ */
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+		  "kfuncs which will be used in BPF programs");
+
+__weak noinline void bpf_rstat_flush(struct cgroup *cgrp,
+				     struct cgroup *parent, int cpu)
+{
+}
+
+__diag_pop();
+
 /* see cgroup_rstat_flush() */
 static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep)
 	__releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock)
@@ -168,6 +197,7 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep)
 			struct cgroup_subsys_state *css;
 
 			cgroup_base_stat_flush(pos, cpu);
+			bpf_rstat_flush(pos, cgroup_parent(pos), cpu);
 
 			rcu_read_lock();
 			list_for_each_entry_rcu(css, &pos->rstat_css_list,
@@ -501,3 +531,21 @@ void cgroup_base_stat_cputime_show(struct seq_file *seq)
 	seq_printf(seq, "core_sched.force_idle_usec %llu\n", forceidle_time);
 #endif
 }
+
+/* Add bpf kfuncs for cgroup_rstat_updated() and cgroup_rstat_flush() */
+BTF_SET8_START(bpf_rstat_kfunc_ids)
+BTF_ID_FLAGS(func, cgroup_rstat_updated)
+BTF_ID_FLAGS(func, cgroup_rstat_flush, KF_SLEEPABLE)
+BTF_SET8_END(bpf_rstat_kfunc_ids)
+
+static const struct btf_kfunc_id_set bpf_rstat_kfunc_set = {
+	.owner          = THIS_MODULE,
+	.set            = &bpf_rstat_kfunc_ids,
+};
+
+static int __init bpf_rstat_kfunc_init(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING,
+					 &bpf_rstat_kfunc_set);
+}
+late_initcall(bpf_rstat_kfunc_init);

net/core/filter.c

@@ -3010,7 +3010,7 @@ BPF_CALL_0(bpf_get_cgroup_classid_curr)
 	return __task_get_classid(current);
 }
 
-static const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto = {
+const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto = {
 	.func		= bpf_get_cgroup_classid_curr,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
@@ -4489,7 +4489,8 @@ BPF_CALL_4(bpf_skb_get_tunnel_key, struct sk_buff *, skb, struct bpf_tunnel_key
 	void *to_orig = to;
 	int err;
 
-	if (unlikely(!info || (flags & ~(BPF_F_TUNINFO_IPV6)))) {
+	if (unlikely(!info || (flags & ~(BPF_F_TUNINFO_IPV6 |
+					 BPF_F_TUNINFO_FLAGS)))) {
 		err = -EINVAL;
 		goto err_clear;
 	}
@@ -4521,7 +4522,10 @@ set_compat:
 	to->tunnel_id = be64_to_cpu(info->key.tun_id);
 	to->tunnel_tos = info->key.tos;
 	to->tunnel_ttl = info->key.ttl;
-	to->tunnel_ext = 0;
+	if (flags & BPF_F_TUNINFO_FLAGS)
+		to->tunnel_flags = info->key.tun_flags;
+	else
+		to->tunnel_ext = 0;
 
 	if (flags & BPF_F_TUNINFO_IPV6) {
 		memcpy(to->remote_ipv6, &info->key.u.ipv6.src,
@@ -5014,251 +5018,222 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
 
+static int sol_socket_sockopt(struct sock *sk, int optname,
+			      char *optval, int *optlen,
+			      bool getopt)
+{
+	switch (optname) {
+	case SO_REUSEADDR:
+	case SO_SNDBUF:
+	case SO_RCVBUF:
+	case SO_KEEPALIVE:
+	case SO_PRIORITY:
+	case SO_REUSEPORT:
+	case SO_RCVLOWAT:
+	case SO_MARK:
+	case SO_MAX_PACING_RATE:
+	case SO_BINDTOIFINDEX:
+	case SO_TXREHASH:
+		if (*optlen != sizeof(int))
+			return -EINVAL;
+		break;
+	case SO_BINDTODEVICE:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (getopt) {
+		if (optname == SO_BINDTODEVICE)
+			return -EINVAL;
+		return sk_getsockopt(sk, SOL_SOCKET, optname,
+				     KERNEL_SOCKPTR(optval),
+				     KERNEL_SOCKPTR(optlen));
+	}
+
+	return sk_setsockopt(sk, SOL_SOCKET, optname,
+			     KERNEL_SOCKPTR(optval), *optlen);
+}
+
+static int bpf_sol_tcp_setsockopt(struct sock *sk, int optname,
+				  char *optval, int optlen)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	unsigned long timeout;
+	int val;
+
+	if (optlen != sizeof(int))
+		return -EINVAL;
+
+	val = *(int *)optval;
+
+	/* Only some options are supported */
+	switch (optname) {
+	case TCP_BPF_IW:
+		if (val <= 0 || tp->data_segs_out > tp->syn_data)
+			return -EINVAL;
+		tcp_snd_cwnd_set(tp, val);
+		break;
+	case TCP_BPF_SNDCWND_CLAMP:
+		if (val <= 0)
+			return -EINVAL;
+		tp->snd_cwnd_clamp = val;
+		tp->snd_ssthresh = val;
+		break;
+	case TCP_BPF_DELACK_MAX:
+		timeout = usecs_to_jiffies(val);
+		if (timeout > TCP_DELACK_MAX ||
+		    timeout < TCP_TIMEOUT_MIN)
+			return -EINVAL;
+		inet_csk(sk)->icsk_delack_max = timeout;
+		break;
+	case TCP_BPF_RTO_MIN:
+		timeout = usecs_to_jiffies(val);
+		if (timeout > TCP_RTO_MIN ||
+		    timeout < TCP_TIMEOUT_MIN)
+			return -EINVAL;
+		inet_csk(sk)->icsk_rto_min = timeout;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int sol_tcp_sockopt(struct sock *sk, int optname,
+			   char *optval, int *optlen,
+			   bool getopt)
+{
+	if (sk->sk_prot->setsockopt != tcp_setsockopt)
+		return -EINVAL;
+
+	switch (optname) {
+	case TCP_NODELAY:
+	case TCP_MAXSEG:
+	case TCP_KEEPIDLE:
+	case TCP_KEEPINTVL:
+	case TCP_KEEPCNT:
+	case TCP_SYNCNT:
+	case TCP_WINDOW_CLAMP:
+	case TCP_THIN_LINEAR_TIMEOUTS:
+	case TCP_USER_TIMEOUT:
+	case TCP_NOTSENT_LOWAT:
+	case TCP_SAVE_SYN:
+		if (*optlen != sizeof(int))
+			return -EINVAL;
+		break;
+	case TCP_CONGESTION:
+		if (*optlen < 2)
+			return -EINVAL;
+		break;
+	case TCP_SAVED_SYN:
+		if (*optlen < 1)
+			return -EINVAL;
+		break;
+	default:
+		if (getopt)
+			return -EINVAL;
+		return bpf_sol_tcp_setsockopt(sk, optname, optval, *optlen);
+	}
+
+	if (getopt) {
+		if (optname == TCP_SAVED_SYN) {
+			struct tcp_sock *tp = tcp_sk(sk);
+
+			if (!tp->saved_syn ||
+			    *optlen > tcp_saved_syn_len(tp->saved_syn))
+				return -EINVAL;
+			memcpy(optval, tp->saved_syn->data, *optlen);
+			/* It cannot free tp->saved_syn here because it
+			 * does not know if the user space still needs it.
+			 */
+			return 0;
+		}
+
+		if (optname == TCP_CONGESTION) {
+			if (!inet_csk(sk)->icsk_ca_ops)
+				return -EINVAL;
+			/* BPF expects NULL-terminated tcp-cc string */
+			optval[--(*optlen)] = '\0';
+		}
+
+		return do_tcp_getsockopt(sk, SOL_TCP, optname,
+					 KERNEL_SOCKPTR(optval),
+					 KERNEL_SOCKPTR(optlen));
+	}
+
+	return do_tcp_setsockopt(sk, SOL_TCP, optname,
+				 KERNEL_SOCKPTR(optval), *optlen);
+}
+
+static int sol_ip_sockopt(struct sock *sk, int optname,
+			  char *optval, int *optlen,
+			  bool getopt)
+{
+	if (sk->sk_family != AF_INET)
+		return -EINVAL;
+
+	switch (optname) {
+	case IP_TOS:
+		if (*optlen != sizeof(int))
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (getopt)
+		return do_ip_getsockopt(sk, SOL_IP, optname,
+					KERNEL_SOCKPTR(optval),
+					KERNEL_SOCKPTR(optlen));
+
+	return do_ip_setsockopt(sk, SOL_IP, optname,
+				KERNEL_SOCKPTR(optval), *optlen);
+}
+
+static int sol_ipv6_sockopt(struct sock *sk, int optname,
+			    char *optval, int *optlen,
+			    bool getopt)
+{
+	if (sk->sk_family != AF_INET6)
+		return -EINVAL;
+
+	switch (optname) {
+	case IPV6_TCLASS:
+	case IPV6_AUTOFLOWLABEL:
+		if (*optlen != sizeof(int))
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (getopt)
+		return ipv6_bpf_stub->ipv6_getsockopt(sk, SOL_IPV6, optname,
+						      KERNEL_SOCKPTR(optval),
+						      KERNEL_SOCKPTR(optlen));
+
+	return ipv6_bpf_stub->ipv6_setsockopt(sk, SOL_IPV6, optname,
+					      KERNEL_SOCKPTR(optval), *optlen);
+}
+
 static int __bpf_setsockopt(struct sock *sk, int level, int optname,
 			    char *optval, int optlen)
 {
-	char devname[IFNAMSIZ];
-	int val, valbool;
-	struct net *net;
-	int ifindex;
-	int ret = 0;
-
 	if (!sk_fullsock(sk))
 		return -EINVAL;
 
-	if (level == SOL_SOCKET) {
-		if (optlen != sizeof(int) && optname != SO_BINDTODEVICE)
-			return -EINVAL;
-		val = *((int *)optval);
-		valbool = val ? 1 : 0;
+	if (level == SOL_SOCKET)
+		return sol_socket_sockopt(sk, optname, optval, &optlen, false);
+	else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP)
+		return sol_ip_sockopt(sk, optname, optval, &optlen, false);
+	else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6)
+		return sol_ipv6_sockopt(sk, optname, optval, &optlen, false);
+	else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP)
+		return sol_tcp_sockopt(sk, optname, optval, &optlen, false);
 
-		/* Only some socketops are supported */
-		switch (optname) {
-		case SO_RCVBUF:
-			val = min_t(u32, val, READ_ONCE(sysctl_rmem_max));
-			val = min_t(int, val, INT_MAX / 2);
-			sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
-			WRITE_ONCE(sk->sk_rcvbuf,
-				   max_t(int, val * 2, SOCK_MIN_RCVBUF));
-			break;
-		case SO_SNDBUF:
-			val = min_t(u32, val, READ_ONCE(sysctl_wmem_max));
-			val = min_t(int, val, INT_MAX / 2);
-			sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
-			WRITE_ONCE(sk->sk_sndbuf,
-				   max_t(int, val * 2, SOCK_MIN_SNDBUF));
-			break;
-		case SO_MAX_PACING_RATE: /* 32bit version */
-			if (val != ~0U)
-				cmpxchg(&sk->sk_pacing_status,
-					SK_PACING_NONE,
-					SK_PACING_NEEDED);
-			sk->sk_max_pacing_rate = (val == ~0U) ?
-						 ~0UL : (unsigned int)val;
-			sk->sk_pacing_rate = min(sk->sk_pacing_rate,
-						 sk->sk_max_pacing_rate);
-			break;
-		case SO_PRIORITY:
-			sk->sk_priority = val;
-			break;
-		case SO_RCVLOWAT:
-			if (val < 0)
-				val = INT_MAX;
-			if (sk->sk_socket && sk->sk_socket->ops->set_rcvlowat)
-				ret = sk->sk_socket->ops->set_rcvlowat(sk, val);
-			else
-				WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
-			break;
-		case SO_MARK:
-			if (sk->sk_mark != val) {
-				sk->sk_mark = val;
-				sk_dst_reset(sk);
-			}
-			break;
-		case SO_BINDTODEVICE:
-			optlen = min_t(long, optlen, IFNAMSIZ - 1);
-			strncpy(devname, optval, optlen);
-			devname[optlen] = 0;
-
-			ifindex = 0;
-			if (devname[0] != '\0') {
-				struct net_device *dev;
-
-				ret = -ENODEV;
-
-				net = sock_net(sk);
-				dev = dev_get_by_name(net, devname);
-				if (!dev)
-					break;
-				ifindex = dev->ifindex;
-				dev_put(dev);
-			}
-			fallthrough;
-		case SO_BINDTOIFINDEX:
-			if (optname == SO_BINDTOIFINDEX)
-				ifindex = val;
-			ret = sock_bindtoindex(sk, ifindex, false);
-			break;
-		case SO_KEEPALIVE:
-			if (sk->sk_prot->keepalive)
-				sk->sk_prot->keepalive(sk, valbool);
-			sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool);
-			break;
-		case SO_REUSEPORT:
-			sk->sk_reuseport = valbool;
-			break;
-		case SO_TXREHASH:
-			if (val < -1 || val > 1) {
-				ret = -EINVAL;
-				break;
-			}
-			sk->sk_txrehash = (u8)val;
-			break;
-		default:
-			ret = -EINVAL;
-		}
-#ifdef CONFIG_INET
-	} else if (level == SOL_IP) {
-		if (optlen != sizeof(int) || sk->sk_family != AF_INET)
-			return -EINVAL;
-
-		val = *((int *)optval);
-		/* Only some options are supported */
-		switch (optname) {
-		case IP_TOS:
-			if (val < -1 || val > 0xff) {
-				ret = -EINVAL;
-			} else {
-				struct inet_sock *inet = inet_sk(sk);
-
-				if (val == -1)
-					val = 0;
-				inet->tos = val;
-			}
-			break;
-		default:
-			ret = -EINVAL;
-		}
-#if IS_ENABLED(CONFIG_IPV6)
-	} else if (level == SOL_IPV6) {
-		if (optlen != sizeof(int) || sk->sk_family != AF_INET6)
-			return -EINVAL;
-
-		val = *((int *)optval);
-		/* Only some options are supported */
-		switch (optname) {
-		case IPV6_TCLASS:
-			if (val < -1 || val > 0xff) {
-				ret = -EINVAL;
-			} else {
-				struct ipv6_pinfo *np = inet6_sk(sk);
-
-				if (val == -1)
-					val = 0;
-				np->tclass = val;
-			}
-			break;
-		default:
-			ret = -EINVAL;
-		}
-#endif
-	} else if (level == SOL_TCP &&
-		   sk->sk_prot->setsockopt == tcp_setsockopt) {
-		if (optname == TCP_CONGESTION) {
-			char name[TCP_CA_NAME_MAX];
-
-			strncpy(name, optval, min_t(long, optlen,
-						    TCP_CA_NAME_MAX-1));
-			name[TCP_CA_NAME_MAX-1] = 0;
-			ret = tcp_set_congestion_control(sk, name, false, true);
-		} else {
-			struct inet_connection_sock *icsk = inet_csk(sk);
-			struct tcp_sock *tp = tcp_sk(sk);
-			unsigned long timeout;
-
-			if (optlen != sizeof(int))
-				return -EINVAL;
-
-			val = *((int *)optval);
-			/* Only some options are supported */
-			switch (optname) {
-			case TCP_BPF_IW:
-				if (val <= 0 || tp->data_segs_out > tp->syn_data)
-					ret = -EINVAL;
-				else
-					tcp_snd_cwnd_set(tp, val);
-				break;
-			case TCP_BPF_SNDCWND_CLAMP:
-				if (val <= 0) {
-					ret = -EINVAL;
-				} else {
-					tp->snd_cwnd_clamp = val;
-					tp->snd_ssthresh = val;
-				}
-				break;
-			case TCP_BPF_DELACK_MAX:
-				timeout = usecs_to_jiffies(val);
-				if (timeout > TCP_DELACK_MAX ||
-				    timeout < TCP_TIMEOUT_MIN)
-					return -EINVAL;
-				inet_csk(sk)->icsk_delack_max = timeout;
-				break;
-			case TCP_BPF_RTO_MIN:
-				timeout = usecs_to_jiffies(val);
-				if (timeout > TCP_RTO_MIN ||
-				    timeout < TCP_TIMEOUT_MIN)
-					return -EINVAL;
-				inet_csk(sk)->icsk_rto_min = timeout;
-				break;
-			case TCP_SAVE_SYN:
-				if (val < 0 || val > 1)
-					ret = -EINVAL;
-				else
-					tp->save_syn = val;
-				break;
-			case TCP_KEEPIDLE:
-				ret = tcp_sock_set_keepidle_locked(sk, val);
-				break;
-			case TCP_KEEPINTVL:
-				if (val < 1 || val > MAX_TCP_KEEPINTVL)
-					ret = -EINVAL;
-				else
-					tp->keepalive_intvl = val * HZ;
-				break;
-			case TCP_KEEPCNT:
-				if (val < 1 || val > MAX_TCP_KEEPCNT)
-					ret = -EINVAL;
-				else
-					tp->keepalive_probes = val;
-				break;
-			case TCP_SYNCNT:
-				if (val < 1 || val > MAX_TCP_SYNCNT)
-					ret = -EINVAL;
-				else
-					icsk->icsk_syn_retries = val;
-				break;
-			case TCP_USER_TIMEOUT:
-				if (val < 0)
-					ret = -EINVAL;
-				else
-					icsk->icsk_user_timeout = val;
-				break;
-			case TCP_NOTSENT_LOWAT:
-				tp->notsent_lowat = val;
-				sk->sk_write_space(sk);
-				break;
-			case TCP_WINDOW_CLAMP:
-				ret = tcp_set_window_clamp(sk, val);
-				break;
-			default:
-				ret = -EINVAL;
-			}
-		}
-#endif
-	} else {
-		ret = -EINVAL;
-	}
-	return ret;
+	return -EINVAL;
 }
 
 static int _bpf_setsockopt(struct sock *sk, int level, int optname,
@@ -5272,101 +5247,30 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 static int __bpf_getsockopt(struct sock *sk, int level, int optname,
 			    char *optval, int optlen)
 {
-	if (!sk_fullsock(sk))
-		goto err_clear;
+	int err, saved_optlen = optlen;
 
-	if (level == SOL_SOCKET) {
-		if (optlen != sizeof(int))
-			goto err_clear;
-
-		switch (optname) {
-		case SO_RCVBUF:
-			*((int *)optval) = sk->sk_rcvbuf;
-			break;
-		case SO_SNDBUF:
-			*((int *)optval) = sk->sk_sndbuf;
-			break;
-		case SO_MARK:
-			*((int *)optval) = sk->sk_mark;
-			break;
-		case SO_PRIORITY:
-			*((int *)optval) = sk->sk_priority;
-			break;
-		case SO_BINDTOIFINDEX:
-			*((int *)optval) = sk->sk_bound_dev_if;
-			break;
-		case SO_REUSEPORT:
-			*((int *)optval) = sk->sk_reuseport;
-			break;
-		case SO_TXREHASH:
-			*((int *)optval) = sk->sk_txrehash;
-			break;
-		default:
-			goto err_clear;
-		}
-#ifdef CONFIG_INET
-	} else if (level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) {
-		struct inet_connection_sock *icsk;
-		struct tcp_sock *tp;
-
-		switch (optname) {
-		case TCP_CONGESTION:
-			icsk = inet_csk(sk);
-
-			if (!icsk->icsk_ca_ops || optlen <= 1)
-				goto err_clear;
-			strncpy(optval, icsk->icsk_ca_ops->name, optlen);
-			optval[optlen - 1] = 0;
-			break;
-		case TCP_SAVED_SYN:
-			tp = tcp_sk(sk);
-
-			if (optlen <= 0 || !tp->saved_syn ||
-			    optlen > tcp_saved_syn_len(tp->saved_syn))
-				goto err_clear;
-			memcpy(optval, tp->saved_syn->data, optlen);
-			break;
-		default:
-			goto err_clear;
-		}
-	} else if (level == SOL_IP) {
-		struct inet_sock *inet = inet_sk(sk);
-
-		if (optlen != sizeof(int) || sk->sk_family != AF_INET)
-			goto err_clear;
-
-		/* Only some options are supported */
-		switch (optname) {
-		case IP_TOS:
-			*((int *)optval) = (int)inet->tos;
-			break;
-		default:
-			goto err_clear;
-		}
-#if IS_ENABLED(CONFIG_IPV6)
-	} else if (level == SOL_IPV6) {
-		struct ipv6_pinfo *np = inet6_sk(sk);
-
-		if (optlen != sizeof(int) || sk->sk_family != AF_INET6)
-			goto err_clear;
-
-		/* Only some options are supported */
-		switch (optname) {
-		case IPV6_TCLASS:
-			*((int *)optval) = (int)np->tclass;
-			break;
-		default:
-			goto err_clear;
-		}
-#endif
-#endif
-	} else {
-		goto err_clear;
+	if (!sk_fullsock(sk)) {
+		err = -EINVAL;
+		goto done;
 	}
-	return 0;
-err_clear:
-	memset(optval, 0, optlen);
-	return -EINVAL;
+
+	if (level == SOL_SOCKET)
+		err = sol_socket_sockopt(sk, optname, optval, &optlen, true);
+	else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP)
+		err = sol_tcp_sockopt(sk, optname, optval, &optlen, true);
+	else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP)
+		err = sol_ip_sockopt(sk, optname, optval, &optlen, true);
+	else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6)
+		err = sol_ipv6_sockopt(sk, optname, optval, &optlen, true);
+	else
+		err = -EINVAL;
+
+done:
+	if (err)
+		optlen = 0;
+	if (optlen < saved_optlen)
+		memset(optval + optlen, 0, saved_optlen - optlen);
+	return err;
 }
 
 static int _bpf_getsockopt(struct sock *sk, int level, int optname,
@@ -7667,34 +7571,23 @@ const struct bpf_func_proto bpf_sk_storage_get_cg_sock_proto __weak;
 static const struct bpf_func_proto *
 sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
+	const struct bpf_func_proto *func_proto;
+
+	func_proto = cgroup_common_func_proto(func_id, prog);
+	if (func_proto)
+		return func_proto;
+
+	func_proto = cgroup_current_func_proto(func_id, prog);
+	if (func_proto)
+		return func_proto;
+
 	switch (func_id) {
-	/* inet and inet6 sockets are created in a process
-	 * context so there is always a valid uid/gid
-	 */
-	case BPF_FUNC_get_current_uid_gid:
-		return &bpf_get_current_uid_gid_proto;
-	case BPF_FUNC_get_local_storage:
-		return &bpf_get_local_storage_proto;
 	case BPF_FUNC_get_socket_cookie:
 		return &bpf_get_socket_cookie_sock_proto;
 	case BPF_FUNC_get_netns_cookie:
 		return &bpf_get_netns_cookie_sock_proto;
 	case BPF_FUNC_perf_event_output:
 		return &bpf_event_output_data_proto;
-	case BPF_FUNC_get_current_pid_tgid:
-		return &bpf_get_current_pid_tgid_proto;
-	case BPF_FUNC_get_current_comm:
-		return &bpf_get_current_comm_proto;
-#ifdef CONFIG_CGROUPS
-	case BPF_FUNC_get_current_cgroup_id:
-		return &bpf_get_current_cgroup_id_proto;
-	case BPF_FUNC_get_current_ancestor_cgroup_id:
-		return &bpf_get_current_ancestor_cgroup_id_proto;
-#endif
-#ifdef CONFIG_CGROUP_NET_CLASSID
-	case BPF_FUNC_get_cgroup_classid:
-		return &bpf_get_cgroup_classid_curr_proto;
-#endif
 	case BPF_FUNC_sk_storage_get:
 		return &bpf_sk_storage_get_cg_sock_proto;
 	case BPF_FUNC_ktime_get_coarse_ns:
@@ -7707,12 +7600,17 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 static const struct bpf_func_proto *
 sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
+	const struct bpf_func_proto *func_proto;
+
+	func_proto = cgroup_common_func_proto(func_id, prog);
+	if (func_proto)
+		return func_proto;
+
+	func_proto = cgroup_current_func_proto(func_id, prog);
+	if (func_proto)
+		return func_proto;
+
 	switch (func_id) {
-	/* inet and inet6 sockets are created in a process
-	 * context so there is always a valid uid/gid
-	 */
-	case BPF_FUNC_get_current_uid_gid:
-		return &bpf_get_current_uid_gid_proto;
 	case BPF_FUNC_bind:
 		switch (prog->expected_attach_type) {
 		case BPF_CGROUP_INET4_CONNECT:
@@ -7725,24 +7623,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_socket_cookie_sock_addr_proto;
 	case BPF_FUNC_get_netns_cookie:
 		return &bpf_get_netns_cookie_sock_addr_proto;
-	case BPF_FUNC_get_local_storage:
-		return &bpf_get_local_storage_proto;
 	case BPF_FUNC_perf_event_output:
 		return &bpf_event_output_data_proto;
-	case BPF_FUNC_get_current_pid_tgid:
-		return &bpf_get_current_pid_tgid_proto;
-	case BPF_FUNC_get_current_comm:
-		return &bpf_get_current_comm_proto;
-#ifdef CONFIG_CGROUPS
-	case BPF_FUNC_get_current_cgroup_id:
-		return &bpf_get_current_cgroup_id_proto;
-	case BPF_FUNC_get_current_ancestor_cgroup_id:
-		return &bpf_get_current_ancestor_cgroup_id_proto;
-#endif
-#ifdef CONFIG_CGROUP_NET_CLASSID
-	case BPF_FUNC_get_cgroup_classid:
-		return &bpf_get_cgroup_classid_curr_proto;
-#endif
 #ifdef CONFIG_INET
 	case BPF_FUNC_sk_lookup_tcp:
 		return &bpf_sock_addr_sk_lookup_tcp_proto;
@@ -7823,9 +7705,13 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto __weak;
 static const struct bpf_func_proto *
 cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
+	const struct bpf_func_proto *func_proto;
+
+	func_proto = cgroup_common_func_proto(func_id, prog);
+	if (func_proto)
+		return func_proto;
+
 	switch (func_id) {
-	case BPF_FUNC_get_local_storage:
-		return &bpf_get_local_storage_proto;
 	case BPF_FUNC_sk_fullsock:
 		return &bpf_sk_fullsock_proto;
 	case BPF_FUNC_sk_storage_get:
@@ -8065,6 +7951,12 @@ const struct bpf_func_proto bpf_sock_hash_update_proto __weak;
 static const struct bpf_func_proto *
 sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
+	const struct bpf_func_proto *func_proto;
+
+	func_proto = cgroup_common_func_proto(func_id, prog);
+	if (func_proto)
+		return func_proto;
+
 	switch (func_id) {
 	case BPF_FUNC_setsockopt:
 		return &bpf_sock_ops_setsockopt_proto;
@@ -8078,8 +7970,6 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sock_hash_update_proto;
 	case BPF_FUNC_get_socket_cookie:
 		return &bpf_get_socket_cookie_sock_ops_proto;
-	case BPF_FUNC_get_local_storage:
-		return &bpf_get_local_storage_proto;
 	case BPF_FUNC_perf_event_output:
 		return &bpf_event_output_data_proto;
 	case BPF_FUNC_sk_storage_get:
@@ -10812,14 +10702,13 @@ int sk_detach_filter(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(sk_detach_filter);
 
-int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf,
-		  unsigned int len)
+int sk_get_filter(struct sock *sk, sockptr_t optval, unsigned int len)
 {
 	struct sock_fprog_kern *fprog;
 	struct sk_filter *filter;
 	int ret = 0;
 
-	lock_sock(sk);
+	sockopt_lock_sock(sk);
 	filter = rcu_dereference_protected(sk->sk_filter,
 					   lockdep_sock_is_held(sk));
 	if (!filter)
@@ -10844,7 +10733,7 @@ int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf,
 		goto out;
 
 	ret = -EFAULT;
-	if (copy_to_user(ubuf, fprog->filter, bpf_classic_proglen(fprog)))
+	if (copy_to_sockptr(optval, fprog->filter, bpf_classic_proglen(fprog)))
 		goto out;
 
 	/* Instead of bytes, the API requests to return the number
@@ -10852,7 +10741,7 @@ int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf,
 	 */
 	ret = fprog->len;
 out:
-	release_sock(sk);
+	sockopt_release_sock(sk);
 	return ret;
 }
 

net/core/flow_dissector.c

@@ -866,8 +866,8 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys,
 	}
 }
 
-bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
-		      __be16 proto, int nhoff, int hlen, unsigned int flags)
+u32 bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
+		     __be16 proto, int nhoff, int hlen, unsigned int flags)
 {
 	struct bpf_flow_keys *flow_keys = ctx->flow_keys;
 	u32 result;
@@ -892,7 +892,7 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
 	flow_keys->thoff = clamp_t(u16, flow_keys->thoff,
 				   flow_keys->nhoff, hlen);
 
-	return result == BPF_OK;
+	return result;
 }
 
 static bool is_pppoe_ses_hdr_valid(const struct pppoe_hdr *hdr)
@@ -1008,6 +1008,7 @@ bool __skb_flow_dissect(const struct net *net,
 			};
 			__be16 n_proto = proto;
 			struct bpf_prog *prog;
+			u32 result;
 
 			if (skb) {
 				ctx.skb = skb;
@@ -1019,13 +1020,16 @@ bool __skb_flow_dissect(const struct net *net,
 			}
 
 			prog = READ_ONCE(run_array->items[0].prog);
-			ret = bpf_flow_dissect(prog, &ctx, n_proto, nhoff,
-					       hlen, flags);
+			result = bpf_flow_dissect(prog, &ctx, n_proto, nhoff,
+						  hlen, flags);
+			if (result == BPF_FLOW_DISSECTOR_CONTINUE)
+				goto dissect_continue;
 			__skb_flow_bpf_to_target(&flow_keys, flow_dissector,
 						 target_container);
 			rcu_read_unlock();
-			return ret;
+			return result == BPF_OK;
 		}
+dissect_continue:
 		rcu_read_unlock();
 	}
 

net/core/sock.c

@@ -703,15 +703,17 @@ static int sock_setbindtodevice(struct sock *sk, sockptr_t optval, int optlen)
 			goto out;
 	}
 
-	return sock_bindtoindex(sk, index, true);
+	sockopt_lock_sock(sk);
+	ret = sock_bindtoindex_locked(sk, index);
+	sockopt_release_sock(sk);
 out:
 #endif
 
 	return ret;
 }
 
-static int sock_getbindtodevice(struct sock *sk, char __user *optval,
-				int __user *optlen, int len)
+static int sock_getbindtodevice(struct sock *sk, sockptr_t optval,
+				sockptr_t optlen, int len)
 {
 	int ret = -ENOPROTOOPT;
 #ifdef CONFIG_NETDEVICES
@@ -735,12 +737,12 @@ static int sock_getbindtodevice(struct sock *sk, char __user *optval,
 	len = strlen(devname) + 1;
 
 	ret = -EFAULT;
-	if (copy_to_user(optval, devname, len))
+	if (copy_to_sockptr(optval, devname, len))
 		goto out;
 
 zero:
 	ret = -EFAULT;
-	if (put_user(len, optlen))
+	if (copy_to_sockptr(optlen, &len, sizeof(int)))
 		goto out;
 
 	ret = 0;
@@ -1036,17 +1038,51 @@ static int sock_reserve_memory(struct sock *sk, int bytes)
 	return 0;
 }
 
+void sockopt_lock_sock(struct sock *sk)
+{
+	/* When current->bpf_ctx is set, the setsockopt is called from
+	 * a bpf prog.  bpf has ensured the sk lock has been
+	 * acquired before calling setsockopt().
+	 */
+	if (has_current_bpf_ctx())
+		return;
+
+	lock_sock(sk);
+}
+EXPORT_SYMBOL(sockopt_lock_sock);
+
+void sockopt_release_sock(struct sock *sk)
+{
+	if (has_current_bpf_ctx())
+		return;
+
+	release_sock(sk);
+}
+EXPORT_SYMBOL(sockopt_release_sock);
+
+bool sockopt_ns_capable(struct user_namespace *ns, int cap)
+{
+	return has_current_bpf_ctx() || ns_capable(ns, cap);
+}
+EXPORT_SYMBOL(sockopt_ns_capable);
+
+bool sockopt_capable(int cap)
+{
+	return has_current_bpf_ctx() || capable(cap);
+}
+EXPORT_SYMBOL(sockopt_capable);
+
 /*
  *	This is meant for all protocols to use and covers goings on
  *	at the socket level. Everything here is generic.
  */
 
-int sock_setsockopt(struct socket *sock, int level, int optname,
-		    sockptr_t optval, unsigned int optlen)
+int sk_setsockopt(struct sock *sk, int level, int optname,
+		  sockptr_t optval, unsigned int optlen)
 {
 	struct so_timestamping timestamping;
+	struct socket *sock = sk->sk_socket;
 	struct sock_txtime sk_txtime;
-	struct sock *sk = sock->sk;
 	int val;
 	int valbool;
 	struct linger ling;
@@ -1067,11 +1103,11 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 
 	valbool = val ? 1 : 0;
 
-	lock_sock(sk);
+	sockopt_lock_sock(sk);
 
 	switch (optname) {
 	case SO_DEBUG:
-		if (val && !capable(CAP_NET_ADMIN))
+		if (val && !sockopt_capable(CAP_NET_ADMIN))
 			ret = -EACCES;
 		else
 			sock_valbool_flag(sk, SOCK_DBG, valbool);
@@ -1115,7 +1151,7 @@ set_sndbuf:
 		break;
 
 	case SO_SNDBUFFORCE:
-		if (!capable(CAP_NET_ADMIN)) {
+		if (!sockopt_capable(CAP_NET_ADMIN)) {
 			ret = -EPERM;
 			break;
 		}
@@ -1137,7 +1173,7 @@ set_sndbuf:
 		break;
 
 	case SO_RCVBUFFORCE:
-		if (!capable(CAP_NET_ADMIN)) {
+		if (!sockopt_capable(CAP_NET_ADMIN)) {
 			ret = -EPERM;
 			break;
 		}
@@ -1164,8 +1200,8 @@ set_sndbuf:
 
 	case SO_PRIORITY:
 		if ((val >= 0 && val <= 6) ||
-		    ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) ||
-		    ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+		    sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) ||
+		    sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 			sk->sk_priority = val;
 		else
 			ret = -EPERM;
@@ -1228,7 +1264,7 @@ set_sndbuf:
 	case SO_RCVLOWAT:
 		if (val < 0)
 			val = INT_MAX;
-		if (sock->ops->set_rcvlowat)
+		if (sock && sock->ops->set_rcvlowat)
 			ret = sock->ops->set_rcvlowat(sk, val);
 		else
 			WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
@@ -1310,8 +1346,8 @@ set_sndbuf:
 			clear_bit(SOCK_PASSSEC, &sock->flags);
 		break;
 	case SO_MARK:
-		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
-		    !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+		if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
+		    !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
 			ret = -EPERM;
 			break;
 		}
@@ -1319,8 +1355,8 @@ set_sndbuf:
 		__sock_set_mark(sk, val);
 		break;
 	case SO_RCVMARK:
-		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
-		    !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+		if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
+		    !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
 			ret = -EPERM;
 			break;
 		}
@@ -1354,7 +1390,7 @@ set_sndbuf:
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	case SO_BUSY_POLL:
 		/* allow unprivileged users to decrease the value */
-		if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN))
+		if ((val > sk->sk_ll_usec) && !sockopt_capable(CAP_NET_ADMIN))
 			ret = -EPERM;
 		else {
 			if (val < 0)
@@ -1364,13 +1400,13 @@ set_sndbuf:
 		}
 		break;
 	case SO_PREFER_BUSY_POLL:
-		if (valbool && !capable(CAP_NET_ADMIN))
+		if (valbool && !sockopt_capable(CAP_NET_ADMIN))
 			ret = -EPERM;
 		else
 			WRITE_ONCE(sk->sk_prefer_busy_poll, valbool);
 		break;
 	case SO_BUSY_POLL_BUDGET:
-		if (val > READ_ONCE(sk->sk_busy_poll_budget) && !capable(CAP_NET_ADMIN)) {
+		if (val > READ_ONCE(sk->sk_busy_poll_budget) && !sockopt_capable(CAP_NET_ADMIN)) {
 			ret = -EPERM;
 		} else {
 			if (val < 0 || val > U16_MAX)
@@ -1441,7 +1477,7 @@ set_sndbuf:
 		 * scheduler has enough safe guards.
 		 */
 		if (sk_txtime.clockid != CLOCK_MONOTONIC &&
-		    !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+		    !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
 			ret = -EPERM;
 			break;
 		}
@@ -1496,9 +1532,16 @@ set_sndbuf:
 		ret = -ENOPROTOOPT;
 		break;
 	}
-	release_sock(sk);
+	sockopt_release_sock(sk);
 	return ret;
 }
+
+int sock_setsockopt(struct socket *sock, int level, int optname,
+		    sockptr_t optval, unsigned int optlen)
+{
+	return sk_setsockopt(sock->sk, level, optname,
+			     optval, optlen);
+}
 EXPORT_SYMBOL(sock_setsockopt);
 
 static const struct cred *sk_get_peer_cred(struct sock *sk)
@@ -1525,22 +1568,25 @@ static void cred_to_ucred(struct pid *pid, const struct cred *cred,
 	}
 }
 
-static int groups_to_user(gid_t __user *dst, const struct group_info *src)
+static int groups_to_user(sockptr_t dst, const struct group_info *src)
 {
 	struct user_namespace *user_ns = current_user_ns();
 	int i;
 
-	for (i = 0; i < src->ngroups; i++)
-		if (put_user(from_kgid_munged(user_ns, src->gid[i]), dst + i))
+	for (i = 0; i < src->ngroups; i++) {
+		gid_t gid = from_kgid_munged(user_ns, src->gid[i]);
+
+		if (copy_to_sockptr_offset(dst, i * sizeof(gid), &gid, sizeof(gid)))
 			return -EFAULT;
+	}
 
 	return 0;
 }
 
-int sock_getsockopt(struct socket *sock, int level, int optname,
-		    char __user *optval, int __user *optlen)
+int sk_getsockopt(struct sock *sk, int level, int optname,
+		  sockptr_t optval, sockptr_t optlen)
 {
-	struct sock *sk = sock->sk;
+	struct socket *sock = sk->sk_socket;
 
 	union {
 		int val;
@@ -1557,7 +1603,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 	int lv = sizeof(int);
 	int len;
 
-	if (get_user(len, optlen))
+	if (copy_from_sockptr(&len, optlen, sizeof(int)))
 		return -EFAULT;
 	if (len < 0)
 		return -EINVAL;
@@ -1692,7 +1738,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred);
 		spin_unlock(&sk->sk_peer_lock);
 
-		if (copy_to_user(optval, &peercred, len))
+		if (copy_to_sockptr(optval, &peercred, len))
 			return -EFAULT;
 		goto lenout;
 	}
@@ -1710,11 +1756,11 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		if (len < n * sizeof(gid_t)) {
 			len = n * sizeof(gid_t);
 			put_cred(cred);
-			return put_user(len, optlen) ? -EFAULT : -ERANGE;
+			return copy_to_sockptr(optlen, &len, sizeof(int)) ? -EFAULT : -ERANGE;
 		}
 		len = n * sizeof(gid_t);
 
-		ret = groups_to_user((gid_t __user *)optval, cred->group_info);
+		ret = groups_to_user(optval, cred->group_info);
 		put_cred(cred);
 		if (ret)
 			return ret;
@@ -1730,7 +1776,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 			return -ENOTCONN;
 		if (lv < len)
 			return -EINVAL;
-		if (copy_to_user(optval, address, len))
+		if (copy_to_sockptr(optval, address, len))
 			return -EFAULT;
 		goto lenout;
 	}
@@ -1747,7 +1793,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case SO_PEERSEC:
-		return security_socket_getpeersec_stream(sock, optval, optlen, len);
+		return security_socket_getpeersec_stream(sock, optval.user, optlen.user, len);
 
 	case SO_MARK:
 		v.val = sk->sk_mark;
@@ -1779,7 +1825,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		return sock_getbindtodevice(sk, optval, optlen, len);
 
 	case SO_GET_FILTER:
-		len = sk_get_filter(sk, (struct sock_filter __user *)optval, len);
+		len = sk_get_filter(sk, optval, len);
 		if (len < 0)
 			return len;
 
@@ -1827,7 +1873,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		sk_get_meminfo(sk, meminfo);
 
 		len = min_t(unsigned int, len, sizeof(meminfo));
-		if (copy_to_user(optval, &meminfo, len))
+		if (copy_to_sockptr(optval, &meminfo, len))
 			return -EFAULT;
 
 		goto lenout;
@@ -1896,14 +1942,22 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 
 	if (len > lv)
 		len = lv;
-	if (copy_to_user(optval, &v, len))
+	if (copy_to_sockptr(optval, &v, len))
 		return -EFAULT;
 lenout:
-	if (put_user(len, optlen))
+	if (copy_to_sockptr(optlen, &len, sizeof(int)))
 		return -EFAULT;
 	return 0;
 }
 
+int sock_getsockopt(struct socket *sock, int level, int optname,
+		    char __user *optval, int __user *optlen)
+{
+	return sk_getsockopt(sock->sk, level, optname,
+			     USER_SOCKPTR(optval),
+			     USER_SOCKPTR(optlen));
+}
+
 /*
  * Initialize an sk_lock.
  *

net/ipv4/igmp.c

@@ -2529,11 +2529,10 @@ done:
 		err = ip_mc_leave_group(sk, &imr);
 	return err;
 }
-
 int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf,
-	struct ip_msfilter __user *optval, int __user *optlen)
+		 sockptr_t optval, sockptr_t optlen)
 {
-	int err, len, count, copycount;
+	int err, len, count, copycount, msf_size;
 	struct ip_mreqn	imr;
 	__be32 addr = msf->imsf_multiaddr;
 	struct ip_mc_socklist *pmc;
@@ -2575,12 +2574,15 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf,
 	copycount = count < msf->imsf_numsrc ? count : msf->imsf_numsrc;
 	len = flex_array_size(psl, sl_addr, copycount);
 	msf->imsf_numsrc = count;
-	if (put_user(IP_MSFILTER_SIZE(copycount), optlen) ||
-	    copy_to_user(optval, msf, IP_MSFILTER_SIZE(0))) {
+	msf_size = IP_MSFILTER_SIZE(copycount);
+	if (copy_to_sockptr(optlen, &msf_size, sizeof(int)) ||
+	    copy_to_sockptr(optval, msf, IP_MSFILTER_SIZE(0))) {
 		return -EFAULT;
 	}
 	if (len &&
-	    copy_to_user(&optval->imsf_slist_flex[0], psl->sl_addr, len))
+	    copy_to_sockptr_offset(optval,
+				   offsetof(struct ip_msfilter, imsf_slist_flex),
+				   psl->sl_addr, len))
 		return -EFAULT;
 	return 0;
 done:
@@ -2588,7 +2590,7 @@ done:
 }
 
 int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf,
-	struct sockaddr_storage __user *p)
+		 sockptr_t optval, size_t ss_offset)
 {
 	int i, count, copycount;
 	struct sockaddr_in *psin;
@@ -2618,15 +2620,17 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf,
 	count = psl ? psl->sl_count : 0;
 	copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc;
 	gsf->gf_numsrc = count;
-	for (i = 0; i < copycount; i++, p++) {
+	for (i = 0; i < copycount; i++) {
 		struct sockaddr_storage ss;
 
 		psin = (struct sockaddr_in *)&ss;
 		memset(&ss, 0, sizeof(ss));
 		psin->sin_family = AF_INET;
 		psin->sin_addr.s_addr = psl->sl_addr[i];
-		if (copy_to_user(p, &ss, sizeof(ss)))
+		if (copy_to_sockptr_offset(optval, ss_offset,
+					   &ss, sizeof(ss)))
 			return -EFAULT;
+		ss_offset += sizeof(ss);
 	}
 	return 0;
 }

net/ipv4/ip_sockglue.c

@@ -888,8 +888,8 @@ static int compat_ip_mcast_join_leave(struct sock *sk, int optname,
 
 DEFINE_STATIC_KEY_FALSE(ip4_min_ttl);
 
-static int do_ip_setsockopt(struct sock *sk, int level, int optname,
-		sockptr_t optval, unsigned int optlen)
+int do_ip_setsockopt(struct sock *sk, int level, int optname,
+		     sockptr_t optval, unsigned int optlen)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct net *net = sock_net(sk);
@@ -944,7 +944,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname,
 	err = 0;
 	if (needs_rtnl)
 		rtnl_lock();
-	lock_sock(sk);
+	sockopt_lock_sock(sk);
 
 	switch (optname) {
 	case IP_OPTIONS:
@@ -1333,14 +1333,14 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname,
 	case IP_IPSEC_POLICY:
 	case IP_XFRM_POLICY:
 		err = -EPERM;
-		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+		if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 			break;
 		err = xfrm_user_policy(sk, optname, optval, optlen);
 		break;
 
 	case IP_TRANSPARENT:
-		if (!!val && !ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
-		    !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+		if (!!val && !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
+		    !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
 			err = -EPERM;
 			break;
 		}
@@ -1368,13 +1368,13 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname,
 		err = -ENOPROTOOPT;
 		break;
 	}
-	release_sock(sk);
+	sockopt_release_sock(sk);
 	if (needs_rtnl)
 		rtnl_unlock();
 	return err;
 
 e_inval:
-	release_sock(sk);
+	sockopt_release_sock(sk);
 	if (needs_rtnl)
 		rtnl_unlock();
 	return -EINVAL;
@@ -1462,37 +1462,37 @@ static bool getsockopt_needs_rtnl(int optname)
 	return false;
 }
 
-static int ip_get_mcast_msfilter(struct sock *sk, void __user *optval,
-		int __user *optlen, int len)
+static int ip_get_mcast_msfilter(struct sock *sk, sockptr_t optval,
+				 sockptr_t optlen, int len)
 {
 	const int size0 = offsetof(struct group_filter, gf_slist_flex);
-	struct group_filter __user *p = optval;
 	struct group_filter gsf;
-	int num;
+	int num, gsf_size;
 	int err;
 
 	if (len < size0)
 		return -EINVAL;
-	if (copy_from_user(&gsf, p, size0))
+	if (copy_from_sockptr(&gsf, optval, size0))
 		return -EFAULT;
 
 	num = gsf.gf_numsrc;
-	err = ip_mc_gsfget(sk, &gsf, p->gf_slist_flex);
+	err = ip_mc_gsfget(sk, &gsf, optval,
+			   offsetof(struct group_filter, gf_slist_flex));
 	if (err)
 		return err;
 	if (gsf.gf_numsrc < num)
 		num = gsf.gf_numsrc;
-	if (put_user(GROUP_FILTER_SIZE(num), optlen) ||
-	    copy_to_user(p, &gsf, size0))
+	gsf_size = GROUP_FILTER_SIZE(num);
+	if (copy_to_sockptr(optlen, &gsf_size, sizeof(int)) ||
+	    copy_to_sockptr(optval, &gsf, size0))
 		return -EFAULT;
 	return 0;
 }
 
-static int compat_ip_get_mcast_msfilter(struct sock *sk, void __user *optval,
-		int __user *optlen, int len)
+static int compat_ip_get_mcast_msfilter(struct sock *sk, sockptr_t optval,
+					sockptr_t optlen, int len)
 {
 	const int size0 = offsetof(struct compat_group_filter, gf_slist_flex);
-	struct compat_group_filter __user *p = optval;
 	struct compat_group_filter gf32;
 	struct group_filter gf;
 	int num;
@@ -1500,7 +1500,7 @@ static int compat_ip_get_mcast_msfilter(struct sock *sk, void __user *optval,
 
 	if (len < size0)
 		return -EINVAL;
-	if (copy_from_user(&gf32, p, size0))
+	if (copy_from_sockptr(&gf32, optval, size0))
 		return -EFAULT;
 
 	gf.gf_interface = gf32.gf_interface;
@@ -1508,21 +1508,24 @@ static int compat_ip_get_mcast_msfilter(struct sock *sk, void __user *optval,
 	num = gf.gf_numsrc = gf32.gf_numsrc;
 	gf.gf_group = gf32.gf_group;
 
-	err = ip_mc_gsfget(sk, &gf, p->gf_slist_flex);
+	err = ip_mc_gsfget(sk, &gf, optval,
+			   offsetof(struct compat_group_filter, gf_slist_flex));
 	if (err)
 		return err;
 	if (gf.gf_numsrc < num)
 		num = gf.gf_numsrc;
 	len = GROUP_FILTER_SIZE(num) - (sizeof(gf) - sizeof(gf32));
-	if (put_user(len, optlen) ||
-	    put_user(gf.gf_fmode, &p->gf_fmode) ||
-	    put_user(gf.gf_numsrc, &p->gf_numsrc))
+	if (copy_to_sockptr(optlen, &len, sizeof(int)) ||
+	    copy_to_sockptr_offset(optval, offsetof(struct compat_group_filter, gf_fmode),
+				   &gf.gf_fmode, sizeof(gf.gf_fmode)) ||
+	    copy_to_sockptr_offset(optval, offsetof(struct compat_group_filter, gf_numsrc),
+				   &gf.gf_numsrc, sizeof(gf.gf_numsrc)))
 		return -EFAULT;
 	return 0;
 }
 
-static int do_ip_getsockopt(struct sock *sk, int level, int optname,
-			    char __user *optval, int __user *optlen)
+int do_ip_getsockopt(struct sock *sk, int level, int optname,
+		     sockptr_t optval, sockptr_t optlen)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	bool needs_rtnl = getsockopt_needs_rtnl(optname);
@@ -1535,14 +1538,14 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	if (ip_mroute_opt(optname))
 		return ip_mroute_getsockopt(sk, optname, optval, optlen);
 
-	if (get_user(len, optlen))
+	if (copy_from_sockptr(&len, optlen, sizeof(int)))
 		return -EFAULT;
 	if (len < 0)
 		return -EINVAL;
 
 	if (needs_rtnl)
 		rtnl_lock();
-	lock_sock(sk);
+	sockopt_lock_sock(sk);
 
 	switch (optname) {
 	case IP_OPTIONS:
@@ -1558,17 +1561,19 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
 			memcpy(optbuf, &inet_opt->opt,
 			       sizeof(struct ip_options) +
 			       inet_opt->opt.optlen);
-		release_sock(sk);
+		sockopt_release_sock(sk);
 
-		if (opt->optlen == 0)
-			return put_user(0, optlen);
+		if (opt->optlen == 0) {
+			len = 0;
+			return copy_to_sockptr(optlen, &len, sizeof(int));
+		}
 
 		ip_options_undo(opt);
 
 		len = min_t(unsigned int, len, opt->optlen);
-		if (put_user(len, optlen))
+		if (copy_to_sockptr(optlen, &len, sizeof(int)))
 			return -EFAULT;
-		if (copy_to_user(optval, opt->__data, len))
+		if (copy_to_sockptr(optval, opt->__data, len))
 			return -EFAULT;
 		return 0;
 	}
@@ -1632,7 +1637,7 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
 			dst_release(dst);
 		}
 		if (!val) {
-			release_sock(sk);
+			sockopt_release_sock(sk);
 			return -ENOTCONN;
 		}
 		break;
@@ -1657,11 +1662,11 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
 		struct in_addr addr;
 		len = min_t(unsigned int, len, sizeof(struct in_addr));
 		addr.s_addr = inet->mc_addr;
-		release_sock(sk);
+		sockopt_release_sock(sk);
 
-		if (put_user(len, optlen))
+		if (copy_to_sockptr(optlen, &len, sizeof(int)))
 			return -EFAULT;
-		if (copy_to_user(optval, &addr, len))
+		if (copy_to_sockptr(optval, &addr, len))
 			return -EFAULT;
 		return 0;
 	}
@@ -1673,12 +1678,11 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
 			err = -EINVAL;
 			goto out;
 		}
-		if (copy_from_user(&msf, optval, IP_MSFILTER_SIZE(0))) {
+		if (copy_from_sockptr(&msf, optval, IP_MSFILTER_SIZE(0))) {
 			err = -EFAULT;
 			goto out;
 		}
-		err = ip_mc_msfget(sk, &msf,
-				   (struct ip_msfilter __user *)optval, optlen);
+		err = ip_mc_msfget(sk, &msf, optval, optlen);
 		goto out;
 	}
 	case MCAST_MSFILTER:
@@ -1695,13 +1699,18 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	{
 		struct msghdr msg;
 
-		release_sock(sk);
+		sockopt_release_sock(sk);
 
 		if (sk->sk_type != SOCK_STREAM)
 			return -ENOPROTOOPT;
 
-		msg.msg_control_is_user = true;
-		msg.msg_control_user = optval;
+		if (optval.is_kernel) {
+			msg.msg_control_is_user = false;
+			msg.msg_control = optval.kernel;
+		} else {
+			msg.msg_control_is_user = true;
+			msg.msg_control_user = optval.user;
+		}
 		msg.msg_controllen = len;
 		msg.msg_flags = in_compat_syscall() ? MSG_CMSG_COMPAT : 0;
 
@@ -1722,7 +1731,7 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
 			put_cmsg(&msg, SOL_IP, IP_TOS, sizeof(tos), &tos);
 		}
 		len -= msg.msg_controllen;
-		return put_user(len, optlen);
+		return copy_to_sockptr(optlen, &len, sizeof(int));
 	}
 	case IP_FREEBIND:
 		val = inet->freebind;
@@ -1734,29 +1743,29 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
 		val = inet->min_ttl;
 		break;
 	default:
-		release_sock(sk);
+		sockopt_release_sock(sk);
 		return -ENOPROTOOPT;
 	}
-	release_sock(sk);
+	sockopt_release_sock(sk);
 
 	if (len < sizeof(int) && len > 0 && val >= 0 && val <= 255) {
 		unsigned char ucval = (unsigned char)val;
 		len = 1;
-		if (put_user(len, optlen))
+		if (copy_to_sockptr(optlen, &len, sizeof(int)))
 			return -EFAULT;
-		if (copy_to_user(optval, &ucval, 1))
+		if (copy_to_sockptr(optval, &ucval, 1))
 			return -EFAULT;
 	} else {
 		len = min_t(unsigned int, sizeof(int), len);
-		if (put_user(len, optlen))
+		if (copy_to_sockptr(optlen, &len, sizeof(int)))
 			return -EFAULT;
-		if (copy_to_user(optval, &val, len))
+		if (copy_to_sockptr(optval, &val, len))
 			return -EFAULT;
 	}
 	return 0;
 
 out:
-	release_sock(sk);
+	sockopt_release_sock(sk);
 	if (needs_rtnl)
 		rtnl_unlock();
 	return err;
@@ -1767,7 +1776,8 @@ int ip_getsockopt(struct sock *sk, int level,
 {
 	int err;
 
-	err = do_ip_getsockopt(sk, level, optname, optval, optlen);
+	err = do_ip_getsockopt(sk, level, optname,
+			       USER_SOCKPTR(optval), USER_SOCKPTR(optlen));
 
 #if IS_ENABLED(CONFIG_BPFILTER_UMH)
 	if (optname >= BPFILTER_IPT_SO_GET_INFO &&

net/ipv4/ipmr.c

@@ -1546,7 +1546,8 @@ out:
 }
 
 /* Getsock opt support for the multicast routing system. */
-int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int __user *optlen)
+int ip_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval,
+			 sockptr_t optlen)
 {
 	int olr;
 	int val;
@@ -1577,14 +1578,14 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int
 		return -ENOPROTOOPT;
 	}
 
-	if (get_user(olr, optlen))
+	if (copy_from_sockptr(&olr, optlen, sizeof(int)))
 		return -EFAULT;
 	olr = min_t(unsigned int, olr, sizeof(int));
 	if (olr < 0)
 		return -EINVAL;
-	if (put_user(olr, optlen))
+	if (copy_to_sockptr(optlen, &olr, sizeof(int)))
 		return -EFAULT;
-	if (copy_to_user(optval, &val, olr))
+	if (copy_to_sockptr(optval, &val, olr))
 		return -EFAULT;
 	return 0;
 }

net/ipv4/tcp.c

@@ -3199,7 +3199,7 @@ EXPORT_SYMBOL(tcp_disconnect);
 
 static inline bool tcp_can_repair_sock(const struct sock *sk)
 {
-	return ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) &&
+	return sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) &&
 		(sk->sk_state != TCP_LISTEN);
 }
 
@@ -3476,8 +3476,8 @@ int tcp_set_window_clamp(struct sock *sk, int val)
 /*
  *	Socket option code for TCP.
  */
-static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
-		sockptr_t optval, unsigned int optlen)
+int do_tcp_setsockopt(struct sock *sk, int level, int optname,
+		      sockptr_t optval, unsigned int optlen)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
@@ -3499,11 +3499,11 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 			return -EFAULT;
 		name[val] = 0;
 
-		lock_sock(sk);
-		err = tcp_set_congestion_control(sk, name, true,
-						 ns_capable(sock_net(sk)->user_ns,
-							    CAP_NET_ADMIN));
-		release_sock(sk);
+		sockopt_lock_sock(sk);
+		err = tcp_set_congestion_control(sk, name, !has_current_bpf_ctx(),
+						 sockopt_ns_capable(sock_net(sk)->user_ns,
+								    CAP_NET_ADMIN));
+		sockopt_release_sock(sk);
 		return err;
 	}
 	case TCP_ULP: {
@@ -3519,9 +3519,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 			return -EFAULT;
 		name[val] = 0;
 
-		lock_sock(sk);
+		sockopt_lock_sock(sk);
 		err = tcp_set_ulp(sk, name);
-		release_sock(sk);
+		sockopt_release_sock(sk);
 		return err;
 	}
 	case TCP_FASTOPEN_KEY: {
@@ -3554,7 +3554,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 	if (copy_from_sockptr(&val, optval, sizeof(val)))
 		return -EFAULT;
 
-	lock_sock(sk);
+	sockopt_lock_sock(sk);
 
 	switch (optname) {
 	case TCP_MAXSEG:
@@ -3776,7 +3776,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		break;
 	}
 
-	release_sock(sk);
+	sockopt_release_sock(sk);
 	return err;
 }
 
@@ -4040,15 +4040,15 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk,
 	return stats;
 }
 
-static int do_tcp_getsockopt(struct sock *sk, int level,
-		int optname, char __user *optval, int __user *optlen)
+int do_tcp_getsockopt(struct sock *sk, int level,
+		      int optname, sockptr_t optval, sockptr_t optlen)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
 	int val, len;
 
-	if (get_user(len, optlen))
+	if (copy_from_sockptr(&len, optlen, sizeof(int)))
 		return -EFAULT;
 
 	len = min_t(unsigned int, len, sizeof(int));
@@ -4098,15 +4098,15 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 	case TCP_INFO: {
 		struct tcp_info info;
 
-		if (get_user(len, optlen))
+		if (copy_from_sockptr(&len, optlen, sizeof(int)))
 			return -EFAULT;
 
 		tcp_get_info(sk, &info);
 
 		len = min_t(unsigned int, len, sizeof(info));
-		if (put_user(len, optlen))
+		if (copy_to_sockptr(optlen, &len, sizeof(int)))
 			return -EFAULT;
-		if (copy_to_user(optval, &info, len))
+		if (copy_to_sockptr(optval, &info, len))
 			return -EFAULT;
 		return 0;
 	}
@@ -4116,7 +4116,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		size_t sz = 0;
 		int attr;
 
-		if (get_user(len, optlen))
+		if (copy_from_sockptr(&len, optlen, sizeof(int)))
 			return -EFAULT;
 
 		ca_ops = icsk->icsk_ca_ops;
@@ -4124,9 +4124,9 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 			sz = ca_ops->get_info(sk, ~0U, &attr, &info);
 
 		len = min_t(unsigned int, len, sz);
-		if (put_user(len, optlen))
+		if (copy_to_sockptr(optlen, &len, sizeof(int)))
 			return -EFAULT;
-		if (copy_to_user(optval, &info, len))
+		if (copy_to_sockptr(optval, &info, len))
 			return -EFAULT;
 		return 0;
 	}
@@ -4135,27 +4135,28 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		break;
 
 	case TCP_CONGESTION:
-		if (get_user(len, optlen))
+		if (copy_from_sockptr(&len, optlen, sizeof(int)))
 			return -EFAULT;
 		len = min_t(unsigned int, len, TCP_CA_NAME_MAX);
-		if (put_user(len, optlen))
+		if (copy_to_sockptr(optlen, &len, sizeof(int)))
 			return -EFAULT;
-		if (copy_to_user(optval, icsk->icsk_ca_ops->name, len))
+		if (copy_to_sockptr(optval, icsk->icsk_ca_ops->name, len))
 			return -EFAULT;
 		return 0;
 
 	case TCP_ULP:
-		if (get_user(len, optlen))
+		if (copy_from_sockptr(&len, optlen, sizeof(int)))
 			return -EFAULT;
 		len = min_t(unsigned int, len, TCP_ULP_NAME_MAX);
 		if (!icsk->icsk_ulp_ops) {
-			if (put_user(0, optlen))
+			len = 0;
+			if (copy_to_sockptr(optlen, &len, sizeof(int)))
 				return -EFAULT;
 			return 0;
 		}
-		if (put_user(len, optlen))
+		if (copy_to_sockptr(optlen, &len, sizeof(int)))
 			return -EFAULT;
-		if (copy_to_user(optval, icsk->icsk_ulp_ops->name, len))
+		if (copy_to_sockptr(optval, icsk->icsk_ulp_ops->name, len))
 			return -EFAULT;
 		return 0;
 
@@ -4163,15 +4164,15 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		u64 key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(u64)];
 		unsigned int key_len;
 
-		if (get_user(len, optlen))
+		if (copy_from_sockptr(&len, optlen, sizeof(int)))
 			return -EFAULT;
 
 		key_len = tcp_fastopen_get_cipher(net, icsk, key) *
 				TCP_FASTOPEN_KEY_LENGTH;
 		len = min_t(unsigned int, len, key_len);
-		if (put_user(len, optlen))
+		if (copy_to_sockptr(optlen, &len, sizeof(int)))
 			return -EFAULT;
-		if (copy_to_user(optval, key, len))
+		if (copy_to_sockptr(optval, key, len))
 			return -EFAULT;
 		return 0;
 	}
@@ -4197,7 +4198,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 	case TCP_REPAIR_WINDOW: {
 		struct tcp_repair_window opt;
 
-		if (get_user(len, optlen))
+		if (copy_from_sockptr(&len, optlen, sizeof(int)))
 			return -EFAULT;
 
 		if (len != sizeof(opt))
@@ -4212,7 +4213,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		opt.rcv_wnd	= tp->rcv_wnd;
 		opt.rcv_wup	= tp->rcv_wup;
 
-		if (copy_to_user(optval, &opt, len))
+		if (copy_to_sockptr(optval, &opt, len))
 			return -EFAULT;
 		return 0;
 	}
@@ -4258,35 +4259,35 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		val = tp->save_syn;
 		break;
 	case TCP_SAVED_SYN: {
-		if (get_user(len, optlen))
+		if (copy_from_sockptr(&len, optlen, sizeof(int)))
 			return -EFAULT;
 
-		lock_sock(sk);
+		sockopt_lock_sock(sk);
 		if (tp->saved_syn) {
 			if (len < tcp_saved_syn_len(tp->saved_syn)) {
-				if (put_user(tcp_saved_syn_len(tp->saved_syn),
-					     optlen)) {
-					release_sock(sk);
+				len = tcp_saved_syn_len(tp->saved_syn);
+				if (copy_to_sockptr(optlen, &len, sizeof(int))) {
+					sockopt_release_sock(sk);
 					return -EFAULT;
 				}
-				release_sock(sk);
+				sockopt_release_sock(sk);
 				return -EINVAL;
 			}
 			len = tcp_saved_syn_len(tp->saved_syn);
-			if (put_user(len, optlen)) {
-				release_sock(sk);
+			if (copy_to_sockptr(optlen, &len, sizeof(int))) {
+				sockopt_release_sock(sk);
 				return -EFAULT;
 			}
-			if (copy_to_user(optval, tp->saved_syn->data, len)) {
-				release_sock(sk);
+			if (copy_to_sockptr(optval, tp->saved_syn->data, len)) {
+				sockopt_release_sock(sk);
 				return -EFAULT;
 			}
 			tcp_saved_syn_free(tp);
-			release_sock(sk);
+			sockopt_release_sock(sk);
 		} else {
-			release_sock(sk);
+			sockopt_release_sock(sk);
 			len = 0;
-			if (put_user(len, optlen))
+			if (copy_to_sockptr(optlen, &len, sizeof(int)))
 				return -EFAULT;
 		}
 		return 0;
@@ -4297,31 +4298,31 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		struct tcp_zerocopy_receive zc = {};
 		int err;
 
-		if (get_user(len, optlen))
+		if (copy_from_sockptr(&len, optlen, sizeof(int)))
 			return -EFAULT;
 		if (len < 0 ||
 		    len < offsetofend(struct tcp_zerocopy_receive, length))
 			return -EINVAL;
 		if (unlikely(len > sizeof(zc))) {
-			err = check_zeroed_user(optval + sizeof(zc),
-						len - sizeof(zc));
+			err = check_zeroed_sockptr(optval, sizeof(zc),
+						   len - sizeof(zc));
 			if (err < 1)
 				return err == 0 ? -EINVAL : err;
 			len = sizeof(zc);
-			if (put_user(len, optlen))
+			if (copy_to_sockptr(optlen, &len, sizeof(int)))
 				return -EFAULT;
 		}
-		if (copy_from_user(&zc, optval, len))
+		if (copy_from_sockptr(&zc, optval, len))
 			return -EFAULT;
 		if (zc.reserved)
 			return -EINVAL;
 		if (zc.msg_flags &  ~(TCP_VALID_ZC_MSG_FLAGS))
 			return -EINVAL;
-		lock_sock(sk);
+		sockopt_lock_sock(sk);
 		err = tcp_zerocopy_receive(sk, &zc, &tss);
 		err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname,
 							  &zc, &len, err);
-		release_sock(sk);
+		sockopt_release_sock(sk);
 		if (len >= offsetofend(struct tcp_zerocopy_receive, msg_flags))
 			goto zerocopy_rcv_cmsg;
 		switch (len) {
@@ -4351,7 +4352,7 @@ zerocopy_rcv_sk_err:
 zerocopy_rcv_inq:
 		zc.inq = tcp_inq_hint(sk);
 zerocopy_rcv_out:
-		if (!err && copy_to_user(optval, &zc, len))
+		if (!err && copy_to_sockptr(optval, &zc, len))
 			err = -EFAULT;
 		return err;
 	}
@@ -4360,9 +4361,9 @@ zerocopy_rcv_out:
 		return -ENOPROTOOPT;
 	}
 
-	if (put_user(len, optlen))
+	if (copy_to_sockptr(optlen, &len, sizeof(int)))
 		return -EFAULT;
-	if (copy_to_user(optval, &val, len))
+	if (copy_to_sockptr(optval, &val, len))
 		return -EFAULT;
 	return 0;
 }
@@ -4387,7 +4388,8 @@ int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
 	if (level != SOL_TCP)
 		return icsk->icsk_af_ops->getsockopt(sk, level, optname,
 						     optval, optlen);
-	return do_tcp_getsockopt(sk, level, optname, optval, optlen);
+	return do_tcp_getsockopt(sk, level, optname, USER_SOCKPTR(optval),
+				 USER_SOCKPTR(optlen));
 }
 EXPORT_SYMBOL(tcp_getsockopt);
 

net/ipv6/af_inet6.c

@@ -1057,6 +1057,8 @@ static const struct ipv6_stub ipv6_stub_impl = {
 static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = {
 	.inet6_bind = __inet6_bind,
 	.udp6_lib_lookup = __udp6_lib_lookup,
+	.ipv6_setsockopt = do_ipv6_setsockopt,
+	.ipv6_getsockopt = do_ipv6_getsockopt,
 };
 
 static int __init inet6_init(void)

net/ipv6/ip6mr.c

@@ -1827,8 +1827,8 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval,
  *	Getsock opt support for the multicast routing system.
  */
 
-int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval,
-			  int __user *optlen)
+int ip6_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval,
+			  sockptr_t optlen)
 {
 	int olr;
 	int val;
@@ -1859,16 +1859,16 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval,
 		return -ENOPROTOOPT;
 	}
 
-	if (get_user(olr, optlen))
+	if (copy_from_sockptr(&olr, optlen, sizeof(int)))
 		return -EFAULT;
 
 	olr = min_t(int, olr, sizeof(int));
 	if (olr < 0)
 		return -EINVAL;
 
-	if (put_user(olr, optlen))
+	if (copy_to_sockptr(optlen, &olr, sizeof(int)))
 		return -EFAULT;
-	if (copy_to_user(optval, &val, olr))
+	if (copy_to_sockptr(optval, &val, olr))
 		return -EFAULT;
 	return 0;
 }

net/ipv6/ipv6_sockglue.c

@@ -327,7 +327,7 @@ static int ipv6_set_opt_hdr(struct sock *sk, int optname, sockptr_t optval,
 	int err;
 
 	/* hop-by-hop / destination options are privileged option */
-	if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
+	if (optname != IPV6_RTHDR && !sockopt_ns_capable(net->user_ns, CAP_NET_RAW))
 		return -EPERM;
 
 	/* remove any sticky options header with a zero option
@@ -391,8 +391,8 @@ sticky_done:
 	return err;
 }
 
-static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
-		   sockptr_t optval, unsigned int optlen)
+int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
+		       sockptr_t optval, unsigned int optlen)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct net *net = sock_net(sk);
@@ -417,7 +417,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 
 	if (needs_rtnl)
 		rtnl_lock();
-	lock_sock(sk);
+	sockopt_lock_sock(sk);
 
 	switch (optname) {
 
@@ -634,8 +634,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case IPV6_TRANSPARENT:
-		if (valbool && !ns_capable(net->user_ns, CAP_NET_RAW) &&
-		    !ns_capable(net->user_ns, CAP_NET_ADMIN)) {
+		if (valbool && !sockopt_ns_capable(net->user_ns, CAP_NET_RAW) &&
+		    !sockopt_ns_capable(net->user_ns, CAP_NET_ADMIN)) {
 			retv = -EPERM;
 			break;
 		}
@@ -946,7 +946,7 @@ done:
 	case IPV6_IPSEC_POLICY:
 	case IPV6_XFRM_POLICY:
 		retv = -EPERM;
-		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+		if (!sockopt_ns_capable(net->user_ns, CAP_NET_ADMIN))
 			break;
 		retv = xfrm_user_policy(sk, optname, optval, optlen);
 		break;
@@ -994,14 +994,14 @@ done:
 		break;
 	}
 
-	release_sock(sk);
+	sockopt_release_sock(sk);
 	if (needs_rtnl)
 		rtnl_unlock();
 
 	return retv;
 
 e_inval:
-	release_sock(sk);
+	sockopt_release_sock(sk);
 	if (needs_rtnl)
 		rtnl_unlock();
 	return -EINVAL;
@@ -1030,7 +1030,7 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 EXPORT_SYMBOL(ipv6_setsockopt);
 
 static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt,
-				  int optname, char __user *optval, int len)
+				  int optname, sockptr_t optval, int len)
 {
 	struct ipv6_opt_hdr *hdr;
 
@@ -1058,56 +1058,53 @@ static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt,
 		return 0;
 
 	len = min_t(unsigned int, len, ipv6_optlen(hdr));
-	if (copy_to_user(optval, hdr, len))
+	if (copy_to_sockptr(optval, hdr, len))
 		return -EFAULT;
 	return len;
 }
 
-static int ipv6_get_msfilter(struct sock *sk, void __user *optval,
-		int __user *optlen, int len)
+static int ipv6_get_msfilter(struct sock *sk, sockptr_t optval,
+			     sockptr_t optlen, int len)
 {
 	const int size0 = offsetof(struct group_filter, gf_slist_flex);
-	struct group_filter __user *p = optval;
 	struct group_filter gsf;
 	int num;
 	int err;
 
 	if (len < size0)
 		return -EINVAL;
-	if (copy_from_user(&gsf, p, size0))
+	if (copy_from_sockptr(&gsf, optval, size0))
 		return -EFAULT;
 	if (gsf.gf_group.ss_family != AF_INET6)
 		return -EADDRNOTAVAIL;
 	num = gsf.gf_numsrc;
-	lock_sock(sk);
-	err = ip6_mc_msfget(sk, &gsf, p->gf_slist_flex);
+	sockopt_lock_sock(sk);
+	err = ip6_mc_msfget(sk, &gsf, optval, size0);
 	if (!err) {
 		if (num > gsf.gf_numsrc)
 			num = gsf.gf_numsrc;
-		if (put_user(GROUP_FILTER_SIZE(num), optlen) ||
-		    copy_to_user(p, &gsf, size0))
+		len = GROUP_FILTER_SIZE(num);
+		if (copy_to_sockptr(optlen, &len, sizeof(int)) ||
+		    copy_to_sockptr(optval, &gsf, size0))
 			err = -EFAULT;
 	}
-	release_sock(sk);
+	sockopt_release_sock(sk);
 	return err;
 }
 
-static int compat_ipv6_get_msfilter(struct sock *sk, void __user *optval,
-		int __user *optlen)
+static int compat_ipv6_get_msfilter(struct sock *sk, sockptr_t optval,
+				    sockptr_t optlen, int len)
 {
 	const int size0 = offsetof(struct compat_group_filter, gf_slist_flex);
-	struct compat_group_filter __user *p = optval;
 	struct compat_group_filter gf32;
 	struct group_filter gf;
-	int len, err;
+	int err;
 	int num;
 
-	if (get_user(len, optlen))
-		return -EFAULT;
 	if (len < size0)
 		return -EINVAL;
 
-	if (copy_from_user(&gf32, p, size0))
+	if (copy_from_sockptr(&gf32, optval, size0))
 		return -EFAULT;
 	gf.gf_interface = gf32.gf_interface;
 	gf.gf_fmode = gf32.gf_fmode;
@@ -1117,23 +1114,25 @@ static int compat_ipv6_get_msfilter(struct sock *sk, void __user *optval,
 	if (gf.gf_group.ss_family != AF_INET6)
 		return -EADDRNOTAVAIL;
 
-	lock_sock(sk);
-	err = ip6_mc_msfget(sk, &gf, p->gf_slist_flex);
-	release_sock(sk);
+	sockopt_lock_sock(sk);
+	err = ip6_mc_msfget(sk, &gf, optval, size0);
+	sockopt_release_sock(sk);
 	if (err)
 		return err;
 	if (num > gf.gf_numsrc)
 		num = gf.gf_numsrc;
 	len = GROUP_FILTER_SIZE(num) - (sizeof(gf)-sizeof(gf32));
-	if (put_user(len, optlen) ||
-	    put_user(gf.gf_fmode, &p->gf_fmode) ||
-	    put_user(gf.gf_numsrc, &p->gf_numsrc))
+	if (copy_to_sockptr(optlen, &len, sizeof(int)) ||
+	    copy_to_sockptr_offset(optval, offsetof(struct compat_group_filter, gf_fmode),
+				   &gf.gf_fmode, sizeof(gf32.gf_fmode)) ||
+	    copy_to_sockptr_offset(optval, offsetof(struct compat_group_filter, gf_numsrc),
+				   &gf.gf_numsrc, sizeof(gf32.gf_numsrc)))
 		return -EFAULT;
 	return 0;
 }
 
-static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
-		    char __user *optval, int __user *optlen, unsigned int flags)
+int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
+		       sockptr_t optval, sockptr_t optlen)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	int len;
@@ -1142,7 +1141,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 	if (ip6_mroute_opt(optname))
 		return ip6_mroute_getsockopt(sk, optname, optval, optlen);
 
-	if (get_user(len, optlen))
+	if (copy_from_sockptr(&len, optlen, sizeof(int)))
 		return -EFAULT;
 	switch (optname) {
 	case IPV6_ADDRFORM:
@@ -1156,7 +1155,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		break;
 	case MCAST_MSFILTER:
 		if (in_compat_syscall())
-			return compat_ipv6_get_msfilter(sk, optval, optlen);
+			return compat_ipv6_get_msfilter(sk, optval, optlen, len);
 		return ipv6_get_msfilter(sk, optval, optlen, len);
 	case IPV6_2292PKTOPTIONS:
 	{
@@ -1166,16 +1165,21 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		if (sk->sk_type != SOCK_STREAM)
 			return -ENOPROTOOPT;
 
-		msg.msg_control_user = optval;
+		if (optval.is_kernel) {
+			msg.msg_control_is_user = false;
+			msg.msg_control = optval.kernel;
+		} else {
+			msg.msg_control_is_user = true;
+			msg.msg_control_user = optval.user;
+		}
 		msg.msg_controllen = len;
-		msg.msg_flags = flags;
-		msg.msg_control_is_user = true;
+		msg.msg_flags = 0;
 
-		lock_sock(sk);
+		sockopt_lock_sock(sk);
 		skb = np->pktoptions;
 		if (skb)
 			ip6_datagram_recv_ctl(sk, &msg, skb);
-		release_sock(sk);
+		sockopt_release_sock(sk);
 		if (!skb) {
 			if (np->rxopt.bits.rxinfo) {
 				struct in6_pktinfo src_info;
@@ -1212,7 +1216,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 			}
 		}
 		len -= msg.msg_controllen;
-		return put_user(len, optlen);
+		return copy_to_sockptr(optlen, &len, sizeof(int));
 	}
 	case IPV6_MTU:
 	{
@@ -1264,15 +1268,15 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 	{
 		struct ipv6_txoptions *opt;
 
-		lock_sock(sk);
+		sockopt_lock_sock(sk);
 		opt = rcu_dereference_protected(np->opt,
 						lockdep_sock_is_held(sk));
 		len = ipv6_getsockopt_sticky(sk, opt, optname, optval, len);
-		release_sock(sk);
+		sockopt_release_sock(sk);
 		/* check if ipv6_getsockopt_sticky() returns err code */
 		if (len < 0)
 			return len;
-		return put_user(len, optlen);
+		return copy_to_sockptr(optlen, &len, sizeof(int));
 	}
 
 	case IPV6_RECVHOPOPTS:
@@ -1326,9 +1330,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		if (!mtuinfo.ip6m_mtu)
 			return -ENOTCONN;
 
-		if (put_user(len, optlen))
+		if (copy_to_sockptr(optlen, &len, sizeof(int)))
 			return -EFAULT;
-		if (copy_to_user(optval, &mtuinfo, len))
+		if (copy_to_sockptr(optval, &mtuinfo, len))
 			return -EFAULT;
 
 		return 0;
@@ -1405,7 +1409,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		if (len < sizeof(freq))
 			return -EINVAL;
 
-		if (copy_from_user(&freq, optval, sizeof(freq)))
+		if (copy_from_sockptr(&freq, optval, sizeof(freq)))
 			return -EFAULT;
 
 		if (freq.flr_action != IPV6_FL_A_GET)
@@ -1420,9 +1424,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		if (val < 0)
 			return val;
 
-		if (put_user(len, optlen))
+		if (copy_to_sockptr(optlen, &len, sizeof(int)))
 			return -EFAULT;
-		if (copy_to_user(optval, &freq, len))
+		if (copy_to_sockptr(optval, &freq, len))
 			return -EFAULT;
 
 		return 0;
@@ -1474,9 +1478,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		return -ENOPROTOOPT;
 	}
 	len = min_t(unsigned int, sizeof(int), len);
-	if (put_user(len, optlen))
+	if (copy_to_sockptr(optlen, &len, sizeof(int)))
 		return -EFAULT;
-	if (copy_to_user(optval, &val, len))
+	if (copy_to_sockptr(optval, &val, len))
 		return -EFAULT;
 	return 0;
 }
@@ -1492,7 +1496,8 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname,
 	if (level != SOL_IPV6)
 		return -ENOPROTOOPT;
 
-	err = do_ipv6_getsockopt(sk, level, optname, optval, optlen, 0);
+	err = do_ipv6_getsockopt(sk, level, optname,
+				 USER_SOCKPTR(optval), USER_SOCKPTR(optlen));
 #ifdef CONFIG_NETFILTER
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
 	if (err == -ENOPROTOOPT && optname != IPV6_2292PKTOPTIONS) {

net/ipv6/mcast.c

@@ -580,7 +580,7 @@ done:
 }
 
 int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
-		  struct sockaddr_storage __user *p)
+		  sockptr_t optval, size_t ss_offset)
 {
 	struct ipv6_pinfo *inet6 = inet6_sk(sk);
 	const struct in6_addr *group;
@@ -612,8 +612,7 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
 
 	copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc;
 	gsf->gf_numsrc = count;
-
-	for (i = 0; i < copycount; i++, p++) {
+	for (i = 0; i < copycount; i++) {
 		struct sockaddr_in6 *psin6;
 		struct sockaddr_storage ss;
 
@@ -621,8 +620,9 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
 		memset(&ss, 0, sizeof(ss));
 		psin6->sin6_family = AF_INET6;
 		psin6->sin6_addr = psl->sl_addr[i];
-		if (copy_to_user(p, &ss, sizeof(ss)))
+		if (copy_to_sockptr_offset(optval, ss_offset, &ss, sizeof(ss)))
 			return -EFAULT;
+		ss_offset += sizeof(ss);
 	}
 	return 0;
 }

samples/bpf/map_perf_test_kern.c

@@ -108,11 +108,14 @@ int stress_hmap(struct pt_regs *ctx)
 	u32 key = bpf_get_current_pid_tgid();
 	long init_val = 1;
 	long *value;
+	int i;
 
-	bpf_map_update_elem(&hash_map, &key, &init_val, BPF_ANY);
-	value = bpf_map_lookup_elem(&hash_map, &key);
-	if (value)
-		bpf_map_delete_elem(&hash_map, &key);
+	for (i = 0; i < 10; i++) {
+		bpf_map_update_elem(&hash_map, &key, &init_val, BPF_ANY);
+		value = bpf_map_lookup_elem(&hash_map, &key);
+		if (value)
+			bpf_map_delete_elem(&hash_map, &key);
+	}
 
 	return 0;
 }
@@ -123,11 +126,14 @@ int stress_percpu_hmap(struct pt_regs *ctx)
 	u32 key = bpf_get_current_pid_tgid();
 	long init_val = 1;
 	long *value;
+	int i;
 
-	bpf_map_update_elem(&percpu_hash_map, &key, &init_val, BPF_ANY);
-	value = bpf_map_lookup_elem(&percpu_hash_map, &key);
-	if (value)
-		bpf_map_delete_elem(&percpu_hash_map, &key);
+	for (i = 0; i < 10; i++) {
+		bpf_map_update_elem(&percpu_hash_map, &key, &init_val, BPF_ANY);
+		value = bpf_map_lookup_elem(&percpu_hash_map, &key);
+		if (value)
+			bpf_map_delete_elem(&percpu_hash_map, &key);
+	}
 	return 0;
 }
 
@@ -137,11 +143,14 @@ int stress_hmap_alloc(struct pt_regs *ctx)
 	u32 key = bpf_get_current_pid_tgid();
 	long init_val = 1;
 	long *value;
+	int i;
 
-	bpf_map_update_elem(&hash_map_alloc, &key, &init_val, BPF_ANY);
-	value = bpf_map_lookup_elem(&hash_map_alloc, &key);
-	if (value)
-		bpf_map_delete_elem(&hash_map_alloc, &key);
+	for (i = 0; i < 10; i++) {
+		bpf_map_update_elem(&hash_map_alloc, &key, &init_val, BPF_ANY);
+		value = bpf_map_lookup_elem(&hash_map_alloc, &key);
+		if (value)
+			bpf_map_delete_elem(&hash_map_alloc, &key);
+	}
 	return 0;
 }
 
@@ -151,11 +160,14 @@ int stress_percpu_hmap_alloc(struct pt_regs *ctx)
 	u32 key = bpf_get_current_pid_tgid();
 	long init_val = 1;
 	long *value;
+	int i;
 
-	bpf_map_update_elem(&percpu_hash_map_alloc, &key, &init_val, BPF_ANY);
-	value = bpf_map_lookup_elem(&percpu_hash_map_alloc, &key);
-	if (value)
-		bpf_map_delete_elem(&percpu_hash_map_alloc, &key);
+	for (i = 0; i < 10; i++) {
+		bpf_map_update_elem(&percpu_hash_map_alloc, &key, &init_val, BPF_ANY);
+		value = bpf_map_lookup_elem(&percpu_hash_map_alloc, &key);
+		if (value)
+			bpf_map_delete_elem(&percpu_hash_map_alloc, &key);
+	}
 	return 0;
 }
 

samples/bpf/map_perf_test_user.c

@@ -72,7 +72,7 @@ static int test_flags = ~0;
 static uint32_t num_map_entries;
 static uint32_t inner_lru_hash_size;
 static int lru_hash_lookup_test_entries = 32;
-static uint32_t max_cnt = 1000000;
+static uint32_t max_cnt = 10000;
 
 static int check_test_flags(enum test_type t)
 {

scripts/bpf_doc.py

@@ -10,6 +10,9 @@ from __future__ import print_function
 import argparse
 import re
 import sys, os
+import subprocess
+
+helpersDocStart = 'Start of BPF helper function descriptions:'
 
 class NoHelperFound(BaseException):
     pass
@@ -47,6 +50,10 @@ class Helper(APIElement):
     @desc: textual description of the helper function
     @ret: description of the return value of the helper function
     """
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.enum_val = None
+
     def proto_break_down(self):
         """
         Break down helper function protocol into smaller chunks: return type,
@@ -89,6 +96,7 @@ class HeaderParser(object):
         self.commands = []
         self.desc_unique_helpers = set()
         self.define_unique_helpers = []
+        self.helper_enum_vals = {}
         self.desc_syscalls = []
         self.enum_syscalls = []
 
@@ -233,7 +241,7 @@ class HeaderParser(object):
         self.enum_syscalls = re.findall('(BPF\w+)+', bpf_cmd_str)
 
     def parse_desc_helpers(self):
-        self.seek_to('* Start of BPF helper function descriptions:',
+        self.seek_to(helpersDocStart,
                      'Could not find start of eBPF helper descriptions list')
         while True:
             try:
@@ -245,30 +253,54 @@ class HeaderParser(object):
                 break
 
     def parse_define_helpers(self):
-        # Parse the number of FN(...) in #define __BPF_FUNC_MAPPER to compare
-        # later with the number of unique function names present in description.
+        # Parse FN(...) in #define __BPF_FUNC_MAPPER to compare later with the
+        # number of unique function names present in description and use the
+        # correct enumeration value.
         # Note: seek_to(..) discards the first line below the target search text,
         # resulting in FN(unspec) being skipped and not added to self.define_unique_helpers.
         self.seek_to('#define __BPF_FUNC_MAPPER(FN)',
                      'Could not find start of eBPF helper definition list')
-        # Searches for either one or more FN(\w+) defines or a backslash for newline
-        p = re.compile('\s*(FN\(\w+\))+|\\\\')
+        # Searches for one FN(\w+) define or a backslash for newline
+        p = re.compile('\s*FN\((\w+)\)|\\\\')
         fn_defines_str = ''
+        i = 1  # 'unspec' is skipped as mentioned above
         while True:
             capture = p.match(self.line)
             if capture:
                 fn_defines_str += self.line
+                self.helper_enum_vals[capture.expand(r'bpf_\1')] = i
+                i += 1
             else:
                 break
             self.line = self.reader.readline()
         # Find the number of occurences of FN(\w+)
         self.define_unique_helpers = re.findall('FN\(\w+\)', fn_defines_str)
 
+    def assign_helper_values(self):
+        seen_helpers = set()
+        for helper in self.helpers:
+            proto = helper.proto_break_down()
+            name = proto['name']
+            try:
+                enum_val = self.helper_enum_vals[name]
+            except KeyError:
+                raise Exception("Helper %s is missing from enum bpf_func_id" % name)
+
+            # Enforce current practice of having the descriptions ordered
+            # by enum value.
+            seen_helpers.add(name)
+            desc_val = len(seen_helpers)
+            if desc_val != enum_val:
+                raise Exception("Helper %s comment order (#%d) must be aligned with its position (#%d) in enum bpf_func_id" % (name, desc_val, enum_val))
+
+            helper.enum_val = enum_val
+
     def run(self):
         self.parse_desc_syscall()
         self.parse_enum_syscall()
         self.parse_desc_helpers()
         self.parse_define_helpers()
+        self.assign_helper_values()
         self.reader.close()
 
 ###############################################################################
@@ -357,6 +389,31 @@ class PrinterRST(Printer):
 
         print('')
 
+    def get_kernel_version(self):
+        try:
+            version = subprocess.run(['git', 'describe'], cwd=linuxRoot,
+                                     capture_output=True, check=True)
+            version = version.stdout.decode().rstrip()
+        except:
+            try:
+                version = subprocess.run(['make', 'kernelversion'], cwd=linuxRoot,
+                                         capture_output=True, check=True)
+                version = version.stdout.decode().rstrip()
+            except:
+                return 'Linux'
+        return 'Linux {version}'.format(version=version)
+
+    def get_last_doc_update(self, delimiter):
+        try:
+            cmd = ['git', 'log', '-1', '--pretty=format:%cs', '--no-patch',
+                   '-L',
+                   '/{}/,/\*\//:include/uapi/linux/bpf.h'.format(delimiter)]
+            date = subprocess.run(cmd, cwd=linuxRoot,
+                                  capture_output=True, check=True)
+            return date.stdout.decode().rstrip()
+        except:
+            return ''
+
 class PrinterHelpersRST(PrinterRST):
     """
     A printer for dumping collected information about helpers as a ReStructured
@@ -378,6 +435,8 @@ list of eBPF helper functions
 -------------------------------------------------------------------------------
 
 :Manual section: 7
+:Version: {version}
+{date_field}{date}
 
 DESCRIPTION
 ===========
@@ -410,8 +469,13 @@ kernel at the top).
 HELPERS
 =======
 '''
+        kernelVersion = self.get_kernel_version()
+        lastUpdate = self.get_last_doc_update(helpersDocStart)
+
         PrinterRST.print_license(self)
-        print(header)
+        print(header.format(version=kernelVersion,
+                            date_field = ':Date: ' if lastUpdate else '',
+                            date=lastUpdate))
 
     def print_footer(self):
         footer = '''
@@ -761,7 +825,7 @@ class PrinterHelpers(Printer):
             comma = ', '
             print(one_arg, end='')
 
-        print(') = (void *) %d;' % len(self.seen_helpers))
+        print(') = (void *) %d;' % helper.enum_val)
         print('')
 
 ###############################################################################

tools/bpf/bpftool/btf_dumper.c

@@ -452,7 +452,7 @@ static int btf_dumper_int(const struct btf_type *t, __u8 bit_offset,
 					     *(char *)data);
 		break;
 	case BTF_INT_BOOL:
-		jsonw_bool(jw, *(int *)data);
+		jsonw_bool(jw, *(bool *)data);
 		break;
 	default:
 		/* shouldn't happen */

tools/bpf/bpftool/link.c

@@ -83,6 +83,29 @@ static bool is_iter_map_target(const char *target_name)
 	       strcmp(target_name, "bpf_sk_storage_map") == 0;
 }
 
+static bool is_iter_cgroup_target(const char *target_name)
+{
+	return strcmp(target_name, "cgroup") == 0;
+}
+
+static const char *cgroup_order_string(__u32 order)
+{
+	switch (order) {
+	case BPF_CGROUP_ITER_ORDER_UNSPEC:
+		return "order_unspec";
+	case BPF_CGROUP_ITER_SELF_ONLY:
+		return "self_only";
+	case BPF_CGROUP_ITER_DESCENDANTS_PRE:
+		return "descendants_pre";
+	case BPF_CGROUP_ITER_DESCENDANTS_POST:
+		return "descendants_post";
+	case BPF_CGROUP_ITER_ANCESTORS_UP:
+		return "ancestors_up";
+	default: /* won't happen */
+		return "unknown";
+	}
+}
+
 static void show_iter_json(struct bpf_link_info *info, json_writer_t *wtr)
 {
 	const char *target_name = u64_to_ptr(info->iter.target_name);
@@ -91,6 +114,12 @@ static void show_iter_json(struct bpf_link_info *info, json_writer_t *wtr)
 
 	if (is_iter_map_target(target_name))
 		jsonw_uint_field(wtr, "map_id", info->iter.map.map_id);
+
+	if (is_iter_cgroup_target(target_name)) {
+		jsonw_lluint_field(wtr, "cgroup_id", info->iter.cgroup.cgroup_id);
+		jsonw_string_field(wtr, "order",
+				   cgroup_order_string(info->iter.cgroup.order));
+	}
 }
 
 static int get_prog_info(int prog_id, struct bpf_prog_info *info)
@@ -208,6 +237,12 @@ static void show_iter_plain(struct bpf_link_info *info)
 
 	if (is_iter_map_target(target_name))
 		printf("map_id %u  ", info->iter.map.map_id);
+
+	if (is_iter_cgroup_target(target_name)) {
+		printf("cgroup_id %llu  ", info->iter.cgroup.cgroup_id);
+		printf("order %s  ",
+		       cgroup_order_string(info->iter.cgroup.order));
+	}
 }
 
 static int show_link_close_plain(int fd, struct bpf_link_info *info)

tools/include/uapi/linux/bpf.h

@@ -87,10 +87,29 @@ struct bpf_cgroup_storage_key {
 	__u32	attach_type;		/* program attach type (enum bpf_attach_type) */
 };
 
+enum bpf_cgroup_iter_order {
+	BPF_CGROUP_ITER_ORDER_UNSPEC = 0,
+	BPF_CGROUP_ITER_SELF_ONLY,		/* process only a single object. */
+	BPF_CGROUP_ITER_DESCENDANTS_PRE,	/* walk descendants in pre-order. */
+	BPF_CGROUP_ITER_DESCENDANTS_POST,	/* walk descendants in post-order. */
+	BPF_CGROUP_ITER_ANCESTORS_UP,		/* walk ancestors upward. */
+};
+
 union bpf_iter_link_info {
 	struct {
 		__u32	map_fd;
 	} map;
+	struct {
+		enum bpf_cgroup_iter_order order;
+
+		/* At most one of cgroup_fd and cgroup_id can be non-zero. If
+		 * both are zero, the walk starts from the default cgroup v2
+		 * root. For walking v1 hierarchy, one should always explicitly
+		 * specify cgroup_fd.
+		 */
+		__u32	cgroup_fd;
+		__u64	cgroup_id;
+	} cgroup;
 };
 
 /* BPF syscall commands, see bpf(2) man-page for more details. */
@@ -4437,7 +4456,7 @@ union bpf_attr {
  *
  *		**-EEXIST** if the option already exists.
  *
- *		**-EFAULT** on failrue to parse the existing header options.
+ *		**-EFAULT** on failure to parse the existing header options.
  *
  *		**-EPERM** if the helper cannot be used under the current
  *		*skops*\ **->op**.
@@ -4646,7 +4665,7 @@ union bpf_attr {
  *		a *map* with *task* as the **key**.  From this
  *		perspective,  the usage is not much different from
  *		**bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this
- *		helper enforces the key must be an task_struct and the map must also
+ *		helper enforces the key must be a task_struct and the map must also
  *		be a **BPF_MAP_TYPE_TASK_STORAGE**.
  *
  *		Underneath, the value is stored locally at *task* instead of
@@ -4704,7 +4723,7 @@ union bpf_attr {
  *
  * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size)
  *	Description
- *		Returns the stored IMA hash of the *inode* (if it's avaialable).
+ *		Returns the stored IMA hash of the *inode* (if it's available).
  *		If the hash is larger than *size*, then only *size*
  *		bytes will be copied to *dst*
  *	Return
@@ -4728,12 +4747,12 @@ union bpf_attr {
  *
  *		The argument *len_diff* can be used for querying with a planned
  *		size change. This allows to check MTU prior to changing packet
- *		ctx. Providing an *len_diff* adjustment that is larger than the
+ *		ctx. Providing a *len_diff* adjustment that is larger than the
  *		actual packet size (resulting in negative packet size) will in
- *		principle not exceed the MTU, why it is not considered a
- *		failure.  Other BPF-helpers are needed for performing the
- *		planned size change, why the responsability for catch a negative
- *		packet size belong in those helpers.
+ *		principle not exceed the MTU, which is why it is not considered
+ *		a failure.  Other BPF helpers are needed for performing the
+ *		planned size change; therefore the responsibility for catching
+ *		a negative packet size belongs in those helpers.
  *
  *		Specifying *ifindex* zero means the MTU check is performed
  *		against the current net device.  This is practical if this isn't
@@ -5085,17 +5104,29 @@ union bpf_attr {
  *
  * int bpf_get_retval(void)
  *	Description
- *		Get the syscall's return value that will be returned to userspace.
+ *		Get the BPF program's return value that will be returned to the upper layers.
  *
- *		This helper is currently supported by cgroup programs only.
+ *		This helper is currently supported by cgroup programs and only by the hooks
+ *		where BPF program's return value is returned to the userspace via errno.
  *	Return
- *		The syscall's return value.
+ *		The BPF program's return value.
  *
  * int bpf_set_retval(int retval)
  *	Description
- *		Set the syscall's return value that will be returned to userspace.
+ *		Set the BPF program's return value that will be returned to the upper layers.
+ *
+ *		This helper is currently supported by cgroup programs and only by the hooks
+ *		where BPF program's return value is returned to the userspace via errno.
+ *
+ *		Note that there is the following corner case where the program exports an error
+ *		via bpf_set_retval but signals success via 'return 1':
+ *
+ *			bpf_set_retval(-EPERM);
+ *			return 1;
+ *
+ *		In this case, the BPF program's return value will use helper's -EPERM. This
+ *		still holds true for cgroup/bind{4,6} which supports extra 'return 3' success case.
  *
- *		This helper is currently supported by cgroup programs only.
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
@@ -5628,6 +5659,11 @@ enum {
 	BPF_F_SEQ_NUMBER		= (1ULL << 3),
 };
 
+/* BPF_FUNC_skb_get_tunnel_key flags. */
+enum {
+	BPF_F_TUNINFO_FLAGS		= (1ULL << 4),
+};
+
 /* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
  * BPF_FUNC_perf_event_read_value flags.
  */
@@ -5817,7 +5853,10 @@ struct bpf_tunnel_key {
 	};
 	__u8 tunnel_tos;
 	__u8 tunnel_ttl;
-	__u16 tunnel_ext;	/* Padding, future use. */
+	union {
+		__u16 tunnel_ext;	/* compat */
+		__be16 tunnel_flags;
+	};
 	__u32 tunnel_label;
 	union {
 		__u32 local_ipv4;
@@ -5861,6 +5900,11 @@ enum bpf_ret_code {
 	 *    represented by BPF_REDIRECT above).
 	 */
 	BPF_LWT_REROUTE = 128,
+	/* BPF_FLOW_DISSECTOR_CONTINUE: used by BPF_PROG_TYPE_FLOW_DISSECTOR
+	 *   to indicate that no custom dissection was performed, and
+	 *   fallback to standard dissector is requested.
+	 */
+	BPF_FLOW_DISSECTOR_CONTINUE = 129,
 };
 
 struct bpf_sock {
@@ -6159,11 +6203,22 @@ struct bpf_link_info {
 		struct {
 			__aligned_u64 target_name; /* in/out: target_name buffer ptr */
 			__u32 target_name_len;	   /* in/out: target_name buffer len */
+
+			/* If the iter specific field is 32 bits, it can be put
+			 * in the first or second union. Otherwise it should be
+			 * put in the second union.
+			 */
 			union {
 				struct {
 					__u32 map_id;
 				} map;
 			};
+			union {
+				struct {
+					__u64 cgroup_id;
+					__u32 order;
+				} cgroup;
+			};
 		} iter;
 		struct  {
 			__u32 netns_ino;

tools/lib/bpf/bpf_helpers.h

@@ -131,7 +131,7 @@
 /*
  * Helper function to perform a tail call with a constant/immediate map slot.
  */
-#if __clang_major__ >= 8 && defined(__bpf__)
+#if (!defined(__clang__) || __clang_major__ >= 8) && defined(__bpf__)
 static __always_inline void
 bpf_tail_call_static(void *ctx, const void *map, const __u32 slot)
 {
@@ -139,8 +139,8 @@ bpf_tail_call_static(void *ctx, const void *map, const __u32 slot)
 		__bpf_unreachable();
 
 	/*
-	 * Provide a hard guarantee that LLVM won't optimize setting r2 (map
-	 * pointer) and r3 (constant map index) from _different paths_ ending
+	 * Provide a hard guarantee that the compiler won't optimize setting r2
+	 * (map pointer) and r3 (constant map index) from _different paths_ ending
 	 * up at the _same_ call insn as otherwise we won't be able to use the
 	 * jmpq/nopl retpoline-free patching by the x86-64 JIT in the kernel
 	 * given they mismatch. See also d2e4c1e6c294 ("bpf: Constant map key
@@ -148,12 +148,19 @@ bpf_tail_call_static(void *ctx, const void *map, const __u32 slot)
 	 *
 	 * Note on clobber list: we need to stay in-line with BPF calling
 	 * convention, so even if we don't end up using r0, r4, r5, we need
-	 * to mark them as clobber so that LLVM doesn't end up using them
-	 * before / after the call.
+	 * to mark them as clobber so that the compiler doesn't end up using
+	 * them before / after the call.
 	 */
-	asm volatile("r1 = %[ctx]\n\t"
+	asm volatile(
+#ifdef __clang__
+		     "r1 = %[ctx]\n\t"
 		     "r2 = %[map]\n\t"
 		     "r3 = %[slot]\n\t"
+#else
+		     "mov %%r1,%[ctx]\n\t"
+		     "mov %%r2,%[map]\n\t"
+		     "mov %%r3,%[slot]\n\t"
+#endif
 		     "call 12"
 		     :: [ctx]"r"(ctx), [map]"r"(map), [slot]"i"(slot)
 		     : "r0", "r1", "r2", "r3", "r4", "r5");

tools/lib/bpf/skel_internal.h

@@ -251,6 +251,29 @@ static inline int skel_map_update_elem(int fd, const void *key,
 	return skel_sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, attr_sz);
 }
 
+static inline int skel_map_delete_elem(int fd, const void *key)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_sz);
+	attr.map_fd = fd;
+	attr.key = (long)key;
+
+	return skel_sys_bpf(BPF_MAP_DELETE_ELEM, &attr, attr_sz);
+}
+
+static inline int skel_map_get_fd_by_id(__u32 id)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_sz);
+	attr.map_id = id;
+
+	return skel_sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, attr_sz);
+}
+
 static inline int skel_raw_tracepoint_open(const char *name, int prog_fd)
 {
 	const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint.prog_fd);

tools/testing/selftests/bpf/DENYLIST.s390x

@@ -66,3 +66,7 @@ select_reuseport                         # intermittently fails on new s390x set
 xdp_synproxy                             # JIT does not support calling kernel function                                (kfunc)
 unpriv_bpf_disabled                      # fentry
 lru_bug                                  # prog 'printk': failed to auto-attach: -524
+setget_sockopt                           # attach unexpected error: -524                                               (trampoline)
+cb_refs                                  # expected error message unexpected error: -524                               (trampoline)
+cgroup_hierarchical_stats                # JIT does not support calling kernel function                                (kfunc)
+htab_update                              # failed to attach: ERROR: strerror_r(-524)=22                                (trampoline)

tools/testing/selftests/bpf/Makefile

@@ -45,7 +45,7 @@ ifneq ($(BPF_GCC),)
 TEST_GEN_PROGS += test_progs-bpf_gcc
 endif
 
-TEST_GEN_FILES = test_lwt_ip_encap.o test_tc_edt.o
+TEST_GEN_FILES = test_lwt_ip_encap.bpf.o test_tc_edt.bpf.o
 TEST_FILES = xsk_prereqs.sh $(wildcard progs/btf_dump_test_case_*.c)
 
 # Order correspond to 'make run_tests' order
@@ -323,6 +323,7 @@ $(OUTPUT)/test_l4lb_noinline.o: BPF_CFLAGS += -fno-inline
 $(OUTPUT)/test_xdp_noinline.o: BPF_CFLAGS += -fno-inline
 
 $(OUTPUT)/flow_dissector_load.o: flow_dissector_load.h
+$(OUTPUT)/cgroup_getset_retval_hooks.o: cgroup_getset_retval_hooks.h
 
 # Build BPF object using Clang
 # $1 - input .c file
@@ -357,17 +358,17 @@ LSKELS := kfunc_call_test.c fentry_test.c fexit_test.c fexit_sleep.c \
 LSKELS_EXTRA := test_ksyms_module.c test_ksyms_weak.c kfunc_call_test_subprog.c
 SKEL_BLACKLIST += $$(LSKELS)
 
-test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o
-linked_funcs.skel.h-deps := linked_funcs1.o linked_funcs2.o
-linked_vars.skel.h-deps := linked_vars1.o linked_vars2.o
-linked_maps.skel.h-deps := linked_maps1.o linked_maps2.o
+test_static_linked.skel.h-deps := test_static_linked1.bpf.o test_static_linked2.bpf.o
+linked_funcs.skel.h-deps := linked_funcs1.bpf.o linked_funcs2.bpf.o
+linked_vars.skel.h-deps := linked_vars1.bpf.o linked_vars2.bpf.o
+linked_maps.skel.h-deps := linked_maps1.bpf.o linked_maps2.bpf.o
 # In the subskeleton case, we want the test_subskeleton_lib.subskel.h file
 # but that's created as a side-effect of the skel.h generation.
-test_subskeleton.skel.h-deps := test_subskeleton_lib2.o test_subskeleton_lib.o test_subskeleton.o
-test_subskeleton_lib.skel.h-deps := test_subskeleton_lib2.o test_subskeleton_lib.o
-test_usdt.skel.h-deps := test_usdt.o test_usdt_multispec.o
+test_subskeleton.skel.h-deps := test_subskeleton_lib2.bpf.o test_subskeleton_lib.bpf.o test_subskeleton.bpf.o
+test_subskeleton_lib.skel.h-deps := test_subskeleton_lib2.bpf.o test_subskeleton_lib.bpf.o
+test_usdt.skel.h-deps := test_usdt.bpf.o test_usdt_multispec.bpf.o
 
-LINKED_BPF_SRCS := $(patsubst %.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
+LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
 
 # Set up extra TRUNNER_XXX "temporary" variables in the environment (relies on
 # $eval()) and pass control to DEFINE_TEST_RUNNER_RULES.
@@ -385,7 +386,7 @@ TRUNNER_EXTRA_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o,		\
 TRUNNER_EXTRA_HDRS := $$(filter %.h,$(TRUNNER_EXTRA_SOURCES))
 TRUNNER_TESTS_HDR := $(TRUNNER_TESTS_DIR)/tests.h
 TRUNNER_BPF_SRCS := $$(notdir $$(wildcard $(TRUNNER_BPF_PROGS_DIR)/*.c))
-TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, $$(TRUNNER_BPF_SRCS))
+TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.bpf.o, $$(TRUNNER_BPF_SRCS))
 TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h,	\
 				 $$(filter-out $(SKEL_BLACKLIST) $(LINKED_BPF_SRCS),\
 					       $$(TRUNNER_BPF_SRCS)))
@@ -415,7 +416,7 @@ endif
 # input/output directory combination
 ifeq ($($(TRUNNER_BPF_PROGS_DIR)$(if $2,-)$2-bpfobjs),)
 $(TRUNNER_BPF_PROGS_DIR)$(if $2,-)$2-bpfobjs := y
-$(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
+$(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.bpf.o:				\
 		     $(TRUNNER_BPF_PROGS_DIR)/%.c			\
 		     $(TRUNNER_BPF_PROGS_DIR)/*.h			\
 		     $$(INCLUDE_DIR)/vmlinux.h				\
@@ -425,25 +426,25 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
 	$$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@,			\
 					  $(TRUNNER_BPF_CFLAGS))
 
-$(TRUNNER_BPF_SKELS): %.skel.h: %.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
+$(TRUNNER_BPF_SKELS): %.skel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
 	$(Q)$$(BPFTOOL) gen object $$(<:.o=.linked1.o) $$<
 	$(Q)$$(BPFTOOL) gen object $$(<:.o=.linked2.o) $$(<:.o=.linked1.o)
 	$(Q)$$(BPFTOOL) gen object $$(<:.o=.linked3.o) $$(<:.o=.linked2.o)
 	$(Q)diff $$(<:.o=.linked2.o) $$(<:.o=.linked3.o)
-	$(Q)$$(BPFTOOL) gen skeleton $$(<:.o=.linked3.o) name $$(notdir $$(<:.o=)) > $$@
-	$(Q)$$(BPFTOOL) gen subskeleton $$(<:.o=.linked3.o) name $$(notdir $$(<:.o=)) > $$(@:.skel.h=.subskel.h)
+	$(Q)$$(BPFTOOL) gen skeleton $$(<:.o=.linked3.o) name $$(notdir $$(<:.bpf.o=)) > $$@
+	$(Q)$$(BPFTOOL) gen subskeleton $$(<:.o=.linked3.o) name $$(notdir $$(<:.bpf.o=)) > $$(@:.skel.h=.subskel.h)
 
-$(TRUNNER_BPF_LSKELS): %.lskel.h: %.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
+$(TRUNNER_BPF_LSKELS): %.lskel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
 	$(Q)$$(BPFTOOL) gen object $$(<:.o=.llinked1.o) $$<
 	$(Q)$$(BPFTOOL) gen object $$(<:.o=.llinked2.o) $$(<:.o=.llinked1.o)
 	$(Q)$$(BPFTOOL) gen object $$(<:.o=.llinked3.o) $$(<:.o=.llinked2.o)
 	$(Q)diff $$(<:.o=.llinked2.o) $$(<:.o=.llinked3.o)
-	$(Q)$$(BPFTOOL) gen skeleton -L $$(<:.o=.llinked3.o) name $$(notdir $$(<:.o=_lskel)) > $$@
+	$(Q)$$(BPFTOOL) gen skeleton -L $$(<:.o=.llinked3.o) name $$(notdir $$(<:.bpf.o=_lskel)) > $$@
 
 $(TRUNNER_BPF_SKELS_LINKED): $(TRUNNER_BPF_OBJS) $(BPFTOOL) | $(TRUNNER_OUTPUT)
-	$$(call msg,LINK-BPF,$(TRUNNER_BINARY),$$(@:.skel.h=.o))
+	$$(call msg,LINK-BPF,$(TRUNNER_BINARY),$$(@:.skel.h=.bpf.o))
 	$(Q)$$(BPFTOOL) gen object $$(@:.skel.h=.linked1.o) $$(addprefix $(TRUNNER_OUTPUT)/,$$($$(@F)-deps))
 	$(Q)$$(BPFTOOL) gen object $$(@:.skel.h=.linked2.o) $$(@:.skel.h=.linked1.o)
 	$(Q)$$(BPFTOOL) gen object $$(@:.skel.h=.linked3.o) $$(@:.skel.h=.linked2.o)
@@ -499,7 +500,7 @@ $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS)			\
 			     | $(TRUNNER_BINARY)-extras
 	$$(call msg,BINARY,,$$@)
 	$(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@
-	$(Q)$(RESOLVE_BTFIDS) --btf $(TRUNNER_OUTPUT)/btf_data.o $$@
+	$(Q)$(RESOLVE_BTFIDS) --btf $(TRUNNER_OUTPUT)/btf_data.bpf.o $$@
 	$(Q)ln -sf $(if $2,..,.)/tools/build/bpftool/bootstrap/bpftool $(if $2,$2/)bpftool
 
 endef

tools/testing/selftests/bpf/README.rst

@@ -126,11 +126,11 @@ available in 10.0.1. The patch is available in llvm 11.0.0 trunk.
 
 __  https://reviews.llvm.org/D78466
 
-bpf_verif_scale/loop6.o test failure with Clang 12
-==================================================
+bpf_verif_scale/loop6.bpf.o test failure with Clang 12
+======================================================
 
 With Clang 12, the following bpf_verif_scale test failed:
-  * ``bpf_verif_scale/loop6.o``
+  * ``bpf_verif_scale/loop6.bpf.o``
 
 The verifier output looks like
 
@@ -245,7 +245,7 @@ See `kernel llvm reloc`_ for more explanation and some examples.
 Using clang 13 to compile old libbpf which has static linker support,
 there will be a compilation failure::
 
-  libbpf: ELF relo #0 in section #6 has unexpected type 2 in .../bpf_tcp_nogpl.o
+  libbpf: ELF relo #0 in section #6 has unexpected type 2 in .../bpf_tcp_nogpl.bpf.o
 
 Here, ``type 2`` refers to new relocation type ``R_BPF_64_ABS64``.
 To fix this issue, user newer libbpf.

tools/testing/selftests/bpf/cgroup_getset_retval_hooks.h

@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+BPF_RETVAL_HOOK(ingress, "cgroup_skb/ingress", __sk_buff, -EINVAL)
+BPF_RETVAL_HOOK(egress, "cgroup_skb/egress", __sk_buff, -EINVAL)
+BPF_RETVAL_HOOK(sock_create, "cgroup/sock_create", bpf_sock, 0)
+BPF_RETVAL_HOOK(sock_ops, "sockops", bpf_sock_ops, -EINVAL)
+BPF_RETVAL_HOOK(dev, "cgroup/dev", bpf_cgroup_dev_ctx, 0)
+BPF_RETVAL_HOOK(bind4, "cgroup/bind4", bpf_sock_addr, 0)
+BPF_RETVAL_HOOK(bind6, "cgroup/bind6", bpf_sock_addr, 0)
+BPF_RETVAL_HOOK(connect4, "cgroup/connect4", bpf_sock_addr, 0)
+BPF_RETVAL_HOOK(connect6, "cgroup/connect6", bpf_sock_addr, 0)
+BPF_RETVAL_HOOK(post_bind4, "cgroup/post_bind4", bpf_sock_addr, 0)
+BPF_RETVAL_HOOK(post_bind6, "cgroup/post_bind6", bpf_sock_addr, 0)
+BPF_RETVAL_HOOK(sendmsg4, "cgroup/sendmsg4", bpf_sock_addr, 0)
+BPF_RETVAL_HOOK(sendmsg6, "cgroup/sendmsg6", bpf_sock_addr, 0)
+BPF_RETVAL_HOOK(sysctl, "cgroup/sysctl", bpf_sysctl, 0)
+BPF_RETVAL_HOOK(recvmsg4, "cgroup/recvmsg4", bpf_sock_addr, -EINVAL)
+BPF_RETVAL_HOOK(recvmsg6, "cgroup/recvmsg6", bpf_sock_addr, -EINVAL)
+BPF_RETVAL_HOOK(getsockopt, "cgroup/getsockopt", bpf_sockopt, 0)
+BPF_RETVAL_HOOK(setsockopt, "cgroup/setsockopt", bpf_sockopt, 0)
+BPF_RETVAL_HOOK(getpeername4, "cgroup/getpeername4", bpf_sock_addr, -EINVAL)
+BPF_RETVAL_HOOK(getpeername6, "cgroup/getpeername6", bpf_sock_addr, -EINVAL)
+BPF_RETVAL_HOOK(getsockname4, "cgroup/getsockname4", bpf_sock_addr, -EINVAL)
+BPF_RETVAL_HOOK(getsockname6, "cgroup/getsockname6", bpf_sock_addr, -EINVAL)
+BPF_RETVAL_HOOK(sock_release, "cgroup/sock_release", bpf_sock, 0)

tools/testing/selftests/bpf/cgroup_helpers.c

@@ -33,49 +33,52 @@
 #define CGROUP_MOUNT_DFLT		"/sys/fs/cgroup"
 #define NETCLS_MOUNT_PATH		CGROUP_MOUNT_DFLT "/net_cls"
 #define CGROUP_WORK_DIR			"/cgroup-test-work-dir"
-#define format_cgroup_path(buf, path) \
+
+#define format_cgroup_path_pid(buf, path, pid) \
 	snprintf(buf, sizeof(buf), "%s%s%d%s", CGROUP_MOUNT_PATH, \
-	CGROUP_WORK_DIR, getpid(), path)
+	CGROUP_WORK_DIR, pid, path)
+
+#define format_cgroup_path(buf, path) \
+	format_cgroup_path_pid(buf, path, getpid())
+
+#define format_parent_cgroup_path(buf, path) \
+	format_cgroup_path_pid(buf, path, getppid())
 
 #define format_classid_path(buf)				\
 	snprintf(buf, sizeof(buf), "%s%s", NETCLS_MOUNT_PATH,	\
 		 CGROUP_WORK_DIR)
 
-/**
- * enable_all_controllers() - Enable all available cgroup v2 controllers
- *
- * Enable all available cgroup v2 controllers in order to increase
- * the code coverage.
- *
- * If successful, 0 is returned.
- */
-static int enable_all_controllers(char *cgroup_path)
+static int __enable_controllers(const char *cgroup_path, const char *controllers)
 {
 	char path[PATH_MAX + 1];
-	char buf[PATH_MAX];
+	char enable[PATH_MAX + 1];
 	char *c, *c2;
 	int fd, cfd;
 	ssize_t len;
 
-	snprintf(path, sizeof(path), "%s/cgroup.controllers", cgroup_path);
-	fd = open(path, O_RDONLY);
-	if (fd < 0) {
-		log_err("Opening cgroup.controllers: %s", path);
-		return 1;
-	}
-
-	len = read(fd, buf, sizeof(buf) - 1);
-	if (len < 0) {
+	/* If not controllers are passed, enable all available controllers */
+	if (!controllers) {
+		snprintf(path, sizeof(path), "%s/cgroup.controllers",
+			 cgroup_path);
+		fd = open(path, O_RDONLY);
+		if (fd < 0) {
+			log_err("Opening cgroup.controllers: %s", path);
+			return 1;
+		}
+		len = read(fd, enable, sizeof(enable) - 1);
+		if (len < 0) {
+			close(fd);
+			log_err("Reading cgroup.controllers: %s", path);
+			return 1;
+		} else if (len == 0) { /* No controllers to enable */
+			close(fd);
+			return 0;
+		}
+		enable[len] = 0;
 		close(fd);
-		log_err("Reading cgroup.controllers: %s", path);
-		return 1;
+	} else {
+		strncpy(enable, controllers, sizeof(enable));
 	}
-	buf[len] = 0;
-	close(fd);
-
-	/* No controllers available? We're probably on cgroup v1. */
-	if (len == 0)
-		return 0;
 
 	snprintf(path, sizeof(path), "%s/cgroup.subtree_control", cgroup_path);
 	cfd = open(path, O_RDWR);
@@ -84,7 +87,7 @@ static int enable_all_controllers(char *cgroup_path)
 		return 1;
 	}
 
-	for (c = strtok_r(buf, " ", &c2); c; c = strtok_r(NULL, " ", &c2)) {
+	for (c = strtok_r(enable, " ", &c2); c; c = strtok_r(NULL, " ", &c2)) {
 		if (dprintf(cfd, "+%s\n", c) <= 0) {
 			log_err("Enabling controller %s: %s", c, path);
 			close(cfd);
@@ -95,6 +98,87 @@ static int enable_all_controllers(char *cgroup_path)
 	return 0;
 }
 
+/**
+ * enable_controllers() - Enable cgroup v2 controllers
+ * @relative_path: The cgroup path, relative to the workdir
+ * @controllers: List of controllers to enable in cgroup.controllers format
+ *
+ *
+ * Enable given cgroup v2 controllers, if @controllers is NULL, enable all
+ * available controllers.
+ *
+ * If successful, 0 is returned.
+ */
+int enable_controllers(const char *relative_path, const char *controllers)
+{
+	char cgroup_path[PATH_MAX + 1];
+
+	format_cgroup_path(cgroup_path, relative_path);
+	return __enable_controllers(cgroup_path, controllers);
+}
+
+static int __write_cgroup_file(const char *cgroup_path, const char *file,
+			       const char *buf)
+{
+	char file_path[PATH_MAX + 1];
+	int fd;
+
+	snprintf(file_path, sizeof(file_path), "%s/%s", cgroup_path, file);
+	fd = open(file_path, O_RDWR);
+	if (fd < 0) {
+		log_err("Opening %s", file_path);
+		return 1;
+	}
+
+	if (dprintf(fd, "%s", buf) <= 0) {
+		log_err("Writing to %s", file_path);
+		close(fd);
+		return 1;
+	}
+	close(fd);
+	return 0;
+}
+
+/**
+ * write_cgroup_file() - Write to a cgroup file
+ * @relative_path: The cgroup path, relative to the workdir
+ * @file: The name of the file in cgroupfs to write to
+ * @buf: Buffer to write to the file
+ *
+ * Write to a file in the given cgroup's directory.
+ *
+ * If successful, 0 is returned.
+ */
+int write_cgroup_file(const char *relative_path, const char *file,
+		      const char *buf)
+{
+	char cgroup_path[PATH_MAX - 24];
+
+	format_cgroup_path(cgroup_path, relative_path);
+	return __write_cgroup_file(cgroup_path, file, buf);
+}
+
+/**
+ * write_cgroup_file_parent() - Write to a cgroup file in the parent process
+ *                              workdir
+ * @relative_path: The cgroup path, relative to the parent process workdir
+ * @file: The name of the file in cgroupfs to write to
+ * @buf: Buffer to write to the file
+ *
+ * Write to a file in the given cgroup's directory under the parent process
+ * workdir.
+ *
+ * If successful, 0 is returned.
+ */
+int write_cgroup_file_parent(const char *relative_path, const char *file,
+			     const char *buf)
+{
+	char cgroup_path[PATH_MAX - 24];
+
+	format_parent_cgroup_path(cgroup_path, relative_path);
+	return __write_cgroup_file(cgroup_path, file, buf);
+}
+
 /**
  * setup_cgroup_environment() - Setup the cgroup environment
  *
@@ -133,7 +217,9 @@ int setup_cgroup_environment(void)
 		return 1;
 	}
 
-	if (enable_all_controllers(cgroup_workdir))
+	/* Enable all available controllers to increase test coverage */
+	if (__enable_controllers(CGROUP_MOUNT_PATH, NULL) ||
+	    __enable_controllers(cgroup_workdir, NULL))
 		return 1;
 
 	return 0;
@@ -173,7 +259,7 @@ static int join_cgroup_from_top(const char *cgroup_path)
 
 /**
  * join_cgroup() - Join a cgroup
- * @path: The cgroup path, relative to the workdir, to join
+ * @relative_path: The cgroup path, relative to the workdir, to join
  *
  * This function expects a cgroup to already be created, relative to the cgroup
  * work dir, and it joins it. For example, passing "/my-cgroup" as the path
@@ -182,11 +268,27 @@ static int join_cgroup_from_top(const char *cgroup_path)
  *
  * On success, it returns 0, otherwise on failure it returns 1.
  */
-int join_cgroup(const char *path)
+int join_cgroup(const char *relative_path)
 {
 	char cgroup_path[PATH_MAX + 1];
 
-	format_cgroup_path(cgroup_path, path);
+	format_cgroup_path(cgroup_path, relative_path);
+	return join_cgroup_from_top(cgroup_path);
+}
+
+/**
+ * join_parent_cgroup() - Join a cgroup in the parent process workdir
+ * @relative_path: The cgroup path, relative to parent process workdir, to join
+ *
+ * See join_cgroup().
+ *
+ * On success, it returns 0, otherwise on failure it returns 1.
+ */
+int join_parent_cgroup(const char *relative_path)
+{
+	char cgroup_path[PATH_MAX + 1];
+
+	format_parent_cgroup_path(cgroup_path, relative_path);
 	return join_cgroup_from_top(cgroup_path);
 }
 
@@ -212,9 +314,27 @@ void cleanup_cgroup_environment(void)
 	nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT);
 }
 
+/**
+ * get_root_cgroup() - Get the FD of the root cgroup
+ *
+ * On success, it returns the file descriptor. On failure, it returns -1.
+ * If there is a failure, it prints the error to stderr.
+ */
+int get_root_cgroup(void)
+{
+	int fd;
+
+	fd = open(CGROUP_MOUNT_PATH, O_RDONLY);
+	if (fd < 0) {
+		log_err("Opening root cgroup");
+		return -1;
+	}
+	return fd;
+}
+
 /**
  * create_and_get_cgroup() - Create a cgroup, relative to workdir, and get the FD
- * @path: The cgroup path, relative to the workdir, to join
+ * @relative_path: The cgroup path, relative to the workdir, to join
  *
  * This function creates a cgroup under the top level workdir and returns the
  * file descriptor. It is idempotent.
@@ -222,14 +342,14 @@ void cleanup_cgroup_environment(void)
  * On success, it returns the file descriptor. On failure it returns -1.
  * If there is a failure, it prints the error to stderr.
  */
-int create_and_get_cgroup(const char *path)
+int create_and_get_cgroup(const char *relative_path)
 {
 	char cgroup_path[PATH_MAX + 1];
 	int fd;
 
-	format_cgroup_path(cgroup_path, path);
+	format_cgroup_path(cgroup_path, relative_path);
 	if (mkdir(cgroup_path, 0777) && errno != EEXIST) {
-		log_err("mkdiring cgroup %s .. %s", path, cgroup_path);
+		log_err("mkdiring cgroup %s .. %s", relative_path, cgroup_path);
 		return -1;
 	}
 
@@ -244,13 +364,13 @@ int create_and_get_cgroup(const char *path)
 
 /**
  * get_cgroup_id() - Get cgroup id for a particular cgroup path
- * @path: The cgroup path, relative to the workdir, to join
+ * @relative_path: The cgroup path, relative to the workdir, to join
  *
  * On success, it returns the cgroup id. On failure it returns 0,
  * which is an invalid cgroup id.
  * If there is a failure, it prints the error to stderr.
  */
-unsigned long long get_cgroup_id(const char *path)
+unsigned long long get_cgroup_id(const char *relative_path)
 {
 	int dirfd, err, flags, mount_id, fhsize;
 	union {
@@ -261,7 +381,7 @@ unsigned long long get_cgroup_id(const char *path)
 	struct file_handle *fhp, *fhp2;
 	unsigned long long ret = 0;
 
-	format_cgroup_path(cgroup_workdir, path);
+	format_cgroup_path(cgroup_workdir, relative_path);
 
 	dirfd = AT_FDCWD;
 	flags = 0;

tools/testing/selftests/bpf/cgroup_helpers.h

@@ -10,11 +10,18 @@
 	__FILE__, __LINE__, clean_errno(), ##__VA_ARGS__)
 
 /* cgroupv2 related */
-int cgroup_setup_and_join(const char *path);
-int create_and_get_cgroup(const char *path);
-unsigned long long get_cgroup_id(const char *path);
+int enable_controllers(const char *relative_path, const char *controllers);
+int write_cgroup_file(const char *relative_path, const char *file,
+		      const char *buf);
+int write_cgroup_file_parent(const char *relative_path, const char *file,
+			     const char *buf);
+int cgroup_setup_and_join(const char *relative_path);
+int get_root_cgroup(void);
+int create_and_get_cgroup(const char *relative_path);
+unsigned long long get_cgroup_id(const char *relative_path);
 
-int join_cgroup(const char *path);
+int join_cgroup(const char *relative_path);
+int join_parent_cgroup(const char *relative_path);
 
 int setup_cgroup_environment(void);
 void cleanup_cgroup_environment(void);
@@ -26,4 +33,4 @@ int join_classid(void);
 int setup_classid_environment(void);
 void cleanup_classid_environment(void);
 
-#endif /* __CGROUP_HELPERS_H */
+#endif /* __CGROUP_HELPERS_H */

tools/testing/selftests/bpf/get_cgroup_id_user.c

@@ -48,7 +48,7 @@ static int bpf_find_map(const char *test, struct bpf_object *obj,
 int main(int argc, char **argv)
 {
 	const char *probe_name = "syscalls/sys_enter_nanosleep";
-	const char *file = "get_cgroup_id_kern.o";
+	const char *file = "get_cgroup_id_kern.bpf.o";
 	int err, bytes, efd, prog_fd, pmu_fd;
 	int cgroup_fd, cgidmap_fd, pidmap_fd;
 	struct perf_event_attr attr = {};

tools/testing/selftests/bpf/map_tests/task_storage_map.c

@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2022. Huawei Technologies Co., Ltd */
+#define _GNU_SOURCE
+#include <sched.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <errno.h>
+#include <string.h>
+#include <pthread.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "test_maps.h"
+#include "task_local_storage_helpers.h"
+#include "read_bpf_task_storage_busy.skel.h"
+
+struct lookup_ctx {
+	bool start;
+	bool stop;
+	int pid_fd;
+	int map_fd;
+	int loop;
+};
+
+static void *lookup_fn(void *arg)
+{
+	struct lookup_ctx *ctx = arg;
+	long value;
+	int i = 0;
+
+	while (!ctx->start)
+		usleep(1);
+
+	while (!ctx->stop && i++ < ctx->loop)
+		bpf_map_lookup_elem(ctx->map_fd, &ctx->pid_fd, &value);
+	return NULL;
+}
+
+static void abort_lookup(struct lookup_ctx *ctx, pthread_t *tids, unsigned int nr)
+{
+	unsigned int i;
+
+	ctx->stop = true;
+	ctx->start = true;
+	for (i = 0; i < nr; i++)
+		pthread_join(tids[i], NULL);
+}
+
+void test_task_storage_map_stress_lookup(void)
+{
+#define MAX_NR_THREAD 4096
+	unsigned int i, nr = 256, loop = 8192, cpu = 0;
+	struct read_bpf_task_storage_busy *skel;
+	pthread_t tids[MAX_NR_THREAD];
+	struct lookup_ctx ctx;
+	cpu_set_t old, new;
+	const char *cfg;
+	int err;
+
+	cfg = getenv("TASK_STORAGE_MAP_NR_THREAD");
+	if (cfg) {
+		nr = atoi(cfg);
+		if (nr > MAX_NR_THREAD)
+			nr = MAX_NR_THREAD;
+	}
+	cfg = getenv("TASK_STORAGE_MAP_NR_LOOP");
+	if (cfg)
+		loop = atoi(cfg);
+	cfg = getenv("TASK_STORAGE_MAP_PIN_CPU");
+	if (cfg)
+		cpu = atoi(cfg);
+
+	skel = read_bpf_task_storage_busy__open_and_load();
+	err = libbpf_get_error(skel);
+	CHECK(err, "open_and_load", "error %d\n", err);
+
+	/* Only for a fully preemptible kernel */
+	if (!skel->kconfig->CONFIG_PREEMPT)
+		return;
+
+	/* Save the old affinity setting */
+	sched_getaffinity(getpid(), sizeof(old), &old);
+
+	/* Pinned on a specific CPU */
+	CPU_ZERO(&new);
+	CPU_SET(cpu, &new);
+	sched_setaffinity(getpid(), sizeof(new), &new);
+
+	ctx.start = false;
+	ctx.stop = false;
+	ctx.pid_fd = sys_pidfd_open(getpid(), 0);
+	ctx.map_fd = bpf_map__fd(skel->maps.task);
+	ctx.loop = loop;
+	for (i = 0; i < nr; i++) {
+		err = pthread_create(&tids[i], NULL, lookup_fn, &ctx);
+		if (err) {
+			abort_lookup(&ctx, tids, i);
+			CHECK(err, "pthread_create", "error %d\n", err);
+			goto out;
+		}
+	}
+
+	ctx.start = true;
+	for (i = 0; i < nr; i++)
+		pthread_join(tids[i], NULL);
+
+	skel->bss->pid = getpid();
+	err = read_bpf_task_storage_busy__attach(skel);
+	CHECK(err, "attach", "error %d\n", err);
+
+	/* Trigger program */
+	syscall(SYS_gettid);
+	skel->bss->pid = 0;
+
+	CHECK(skel->bss->busy != 0, "bad bpf_task_storage_busy", "got %d\n", skel->bss->busy);
+out:
+	read_bpf_task_storage_busy__destroy(skel);
+	/* Restore affinity setting */
+	sched_setaffinity(getpid(), sizeof(old), &old);
+}

tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c

@@ -7,7 +7,7 @@ void serial_test_bpf_obj_id(void)
 {
 	const __u64 array_magic_value = 0xfaceb00c;
 	const __u32 array_key = 0;
-	const char *file = "./test_obj_id.o";
+	const char *file = "./test_obj_id.bpf.o";
 	const char *expected_prog_name = "test_obj_id";
 	const char *expected_map_name = "test_map_id";
 	const __u64 nsec_per_sec = 1000000000;

tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c

@@ -75,45 +75,45 @@ static void scale_test(const char *file,
 
 void test_verif_scale1()
 {
-	scale_test("test_verif_scale1.o", BPF_PROG_TYPE_SCHED_CLS, false);
+	scale_test("test_verif_scale1.bpf.o", BPF_PROG_TYPE_SCHED_CLS, false);
 }
 
 void test_verif_scale2()
 {
-	scale_test("test_verif_scale2.o", BPF_PROG_TYPE_SCHED_CLS, false);
+	scale_test("test_verif_scale2.bpf.o", BPF_PROG_TYPE_SCHED_CLS, false);
 }
 
 void test_verif_scale3()
 {
-	scale_test("test_verif_scale3.o", BPF_PROG_TYPE_SCHED_CLS, false);
+	scale_test("test_verif_scale3.bpf.o", BPF_PROG_TYPE_SCHED_CLS, false);
 }
 
 void test_verif_scale_pyperf_global()
 {
-	scale_test("pyperf_global.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+	scale_test("pyperf_global.bpf.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
 }
 
 void test_verif_scale_pyperf_subprogs()
 {
-	scale_test("pyperf_subprogs.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+	scale_test("pyperf_subprogs.bpf.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
 }
 
 void test_verif_scale_pyperf50()
 {
 	/* full unroll by llvm */
-	scale_test("pyperf50.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+	scale_test("pyperf50.bpf.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
 }
 
 void test_verif_scale_pyperf100()
 {
 	/* full unroll by llvm */
-	scale_test("pyperf100.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+	scale_test("pyperf100.bpf.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
 }
 
 void test_verif_scale_pyperf180()
 {
 	/* full unroll by llvm */
-	scale_test("pyperf180.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+	scale_test("pyperf180.bpf.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
 }
 
 void test_verif_scale_pyperf600()
@@ -124,13 +124,13 @@ void test_verif_scale_pyperf600()
 	 * 16k insns in loop body.
 	 * Total of 5 such loops. Total program size ~82k insns.
 	 */
-	scale_test("pyperf600.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+	scale_test("pyperf600.bpf.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
 }
 
 void test_verif_scale_pyperf600_bpf_loop(void)
 {
 	/* use the bpf_loop helper*/
-	scale_test("pyperf600_bpf_loop.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+	scale_test("pyperf600_bpf_loop.bpf.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
 }
 
 void test_verif_scale_pyperf600_nounroll()
@@ -141,37 +141,37 @@ void test_verif_scale_pyperf600_nounroll()
 	 * ~110 insns in loop body.
 	 * Total of 5 such loops. Total program size ~1500 insns.
 	 */
-	scale_test("pyperf600_nounroll.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+	scale_test("pyperf600_nounroll.bpf.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
 }
 
 void test_verif_scale_loop1()
 {
-	scale_test("loop1.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+	scale_test("loop1.bpf.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
 }
 
 void test_verif_scale_loop2()
 {
-	scale_test("loop2.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+	scale_test("loop2.bpf.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
 }
 
 void test_verif_scale_loop3_fail()
 {
-	scale_test("loop3.o", BPF_PROG_TYPE_RAW_TRACEPOINT, true /* fails */);
+	scale_test("loop3.bpf.o", BPF_PROG_TYPE_RAW_TRACEPOINT, true /* fails */);
 }
 
 void test_verif_scale_loop4()
 {
-	scale_test("loop4.o", BPF_PROG_TYPE_SCHED_CLS, false);
+	scale_test("loop4.bpf.o", BPF_PROG_TYPE_SCHED_CLS, false);
 }
 
 void test_verif_scale_loop5()
 {
-	scale_test("loop5.o", BPF_PROG_TYPE_SCHED_CLS, false);
+	scale_test("loop5.bpf.o", BPF_PROG_TYPE_SCHED_CLS, false);
 }
 
 void test_verif_scale_loop6()
 {
-	scale_test("loop6.o", BPF_PROG_TYPE_KPROBE, false);
+	scale_test("loop6.bpf.o", BPF_PROG_TYPE_KPROBE, false);
 }
 
 void test_verif_scale_strobemeta()
@@ -180,54 +180,54 @@ void test_verif_scale_strobemeta()
 	 * Total program size 20.8k insn.
 	 * ~350k processed_insns
 	 */
-	scale_test("strobemeta.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+	scale_test("strobemeta.bpf.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
 }
 
 void test_verif_scale_strobemeta_bpf_loop(void)
 {
 	/* use the bpf_loop helper*/
-	scale_test("strobemeta_bpf_loop.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+	scale_test("strobemeta_bpf_loop.bpf.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
 }
 
 void test_verif_scale_strobemeta_nounroll1()
 {
 	/* no unroll, tiny loops */
-	scale_test("strobemeta_nounroll1.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+	scale_test("strobemeta_nounroll1.bpf.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
 }
 
 void test_verif_scale_strobemeta_nounroll2()
 {
 	/* no unroll, tiny loops */
-	scale_test("strobemeta_nounroll2.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+	scale_test("strobemeta_nounroll2.bpf.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
 }
 
 void test_verif_scale_strobemeta_subprogs()
 {
 	/* non-inlined subprogs */
-	scale_test("strobemeta_subprogs.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+	scale_test("strobemeta_subprogs.bpf.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
 }
 
 void test_verif_scale_sysctl_loop1()
 {
-	scale_test("test_sysctl_loop1.o", BPF_PROG_TYPE_CGROUP_SYSCTL, false);
+	scale_test("test_sysctl_loop1.bpf.o", BPF_PROG_TYPE_CGROUP_SYSCTL, false);
 }
 
 void test_verif_scale_sysctl_loop2()
 {
-	scale_test("test_sysctl_loop2.o", BPF_PROG_TYPE_CGROUP_SYSCTL, false);
+	scale_test("test_sysctl_loop2.bpf.o", BPF_PROG_TYPE_CGROUP_SYSCTL, false);
 }
 
 void test_verif_scale_xdp_loop()
 {
-	scale_test("test_xdp_loop.o", BPF_PROG_TYPE_XDP, false);
+	scale_test("test_xdp_loop.bpf.o", BPF_PROG_TYPE_XDP, false);
 }
 
 void test_verif_scale_seg6_loop()
 {
-	scale_test("test_seg6_loop.o", BPF_PROG_TYPE_LWT_SEG6LOCAL, false);
+	scale_test("test_seg6_loop.bpf.o", BPF_PROG_TYPE_LWT_SEG6LOCAL, false);
 }
 
 void test_verif_twfw()
 {
-	scale_test("twfw.o", BPF_PROG_TYPE_CGROUP_SKB, false);
+	scale_test("twfw.bpf.o", BPF_PROG_TYPE_CGROUP_SKB, false);
 }

tools/testing/selftests/bpf/prog_tests/btf.c

@@ -4651,8 +4651,8 @@ struct btf_file_test {
 };
 
 static struct btf_file_test file_tests[] = {
-	{ .file = "test_btf_newkv.o", },
-	{ .file = "test_btf_nokv.o", .btf_kv_notfound = true, },
+	{ .file = "test_btf_newkv.bpf.o", },
+	{ .file = "test_btf_nokv.bpf.o", .btf_kv_notfound = true, },
 };
 
 static void do_test_file(unsigned int test_num)

tools/testing/selftests/bpf/prog_tests/btf_dump.c

@@ -52,7 +52,7 @@ static int test_btf_dump_case(int n, struct btf_dump_test_case *t)
 	int err = 0, fd = -1;
 	FILE *f = NULL;
 
-	snprintf(test_file, sizeof(test_file), "%s.o", t->file);
+	snprintf(test_file, sizeof(test_file), "%s.bpf.o", t->file);
 
 	btf = btf__parse_elf(test_file, NULL);
 	if (!ASSERT_OK_PTR(btf, "btf_parse_elf")) {
@@ -764,8 +764,8 @@ static void test_btf_dump_struct_data(struct btf *btf, struct btf_dump *d,
 
 	/* union with nested struct */
 	TEST_BTF_DUMP_DATA(btf, d, "union", str, union bpf_iter_link_info, BTF_F_COMPACT,
-			   "(union bpf_iter_link_info){.map = (struct){.map_fd = (__u32)1,},}",
-			   { .map = { .map_fd = 1 }});
+			   "(union bpf_iter_link_info){.map = (struct){.map_fd = (__u32)1,},.cgroup = (struct){.order = (enum bpf_cgroup_iter_order)BPF_CGROUP_ITER_SELF_ONLY,.cgroup_fd = (__u32)1,},}",
+			   { .cgroup = { .order = 1, .cgroup_fd = 1, }});
 
 	/* struct skb with nested structs/unions; because type output is so
 	 * complex, we don't do a string comparison, just verify we return
@@ -841,8 +841,8 @@ static void test_btf_dump_datasec_data(char *str)
 	char license[4] = "GPL";
 	struct btf_dump *d;
 
-	btf = btf__parse("xdping_kern.o", NULL);
-	if (!ASSERT_OK_PTR(btf, "xdping_kern.o BTF not found"))
+	btf = btf__parse("xdping_kern.bpf.o", NULL);
+	if (!ASSERT_OK_PTR(btf, "xdping_kern.bpf.o BTF not found"))
 		return;
 
 	d = btf_dump__new(btf, btf_dump_snprintf, str, NULL);

tools/testing/selftests/bpf/prog_tests/btf_endian.c

@@ -23,7 +23,7 @@ void test_btf_endian() {
 	int var_id;
 
 	/* Load BTF in native endianness */
-	btf = btf__parse_elf("btf_dump_test_case_syntax.o", NULL);
+	btf = btf__parse_elf("btf_dump_test_case_syntax.bpf.o", NULL);
 	if (!ASSERT_OK_PTR(btf, "parse_native_btf"))
 		goto err_out;
 

tools/testing/selftests/bpf/prog_tests/cb_refs.c

@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "bpf/libbpf.h"
+#include <test_progs.h>
+#include <network_helpers.h>
+
+#include "cb_refs.skel.h"
+
+static char log_buf[1024 * 1024];
+
+struct {
+	const char *prog_name;
+	const char *err_msg;
+} cb_refs_tests[] = {
+	{ "underflow_prog", "reference has not been acquired before" },
+	{ "leak_prog", "Unreleased reference" },
+	{ "nested_cb", "Unreleased reference id=4 alloc_insn=2" }, /* alloc_insn=2{4,5} */
+	{ "non_cb_transfer_ref", "Unreleased reference id=4 alloc_insn=1" }, /* alloc_insn=1{1,2} */
+};
+
+void test_cb_refs(void)
+{
+	LIBBPF_OPTS(bpf_object_open_opts, opts, .kernel_log_buf = log_buf,
+						.kernel_log_size = sizeof(log_buf),
+						.kernel_log_level = 1);
+	struct bpf_program *prog;
+	struct cb_refs *skel;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(cb_refs_tests); i++) {
+		LIBBPF_OPTS(bpf_test_run_opts, run_opts,
+			.data_in = &pkt_v4,
+			.data_size_in = sizeof(pkt_v4),
+			.repeat = 1,
+		);
+		skel = cb_refs__open_opts(&opts);
+		if (!ASSERT_OK_PTR(skel, "cb_refs__open_and_load"))
+			return;
+		prog = bpf_object__find_program_by_name(skel->obj, cb_refs_tests[i].prog_name);
+		bpf_program__set_autoload(prog, true);
+		if (!ASSERT_ERR(cb_refs__load(skel), "cb_refs__load"))
+			bpf_prog_test_run_opts(bpf_program__fd(prog), &run_opts);
+		if (!ASSERT_OK_PTR(strstr(log_buf, cb_refs_tests[i].err_msg), "expected error message")) {
+			fprintf(stderr, "Expected: %s\n", cb_refs_tests[i].err_msg);
+			fprintf(stderr, "Verifier: %s\n", log_buf);
+		}
+		cb_refs__destroy(skel);
+	}
+}

tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c

@@ -10,6 +10,7 @@
 
 #include "cgroup_getset_retval_setsockopt.skel.h"
 #include "cgroup_getset_retval_getsockopt.skel.h"
+#include "cgroup_getset_retval_hooks.skel.h"
 
 #define SOL_CUSTOM	0xdeadbeef
 
@@ -433,6 +434,50 @@ close_bpf_object:
 	cgroup_getset_retval_getsockopt__destroy(obj);
 }
 
+struct exposed_hook {
+	const char *name;
+	int expected_err;
+} exposed_hooks[] = {
+
+#define BPF_RETVAL_HOOK(NAME, SECTION, CTX, EXPECTED_ERR) \
+	{ \
+		.name = #NAME, \
+		.expected_err = EXPECTED_ERR, \
+	},
+
+#include "cgroup_getset_retval_hooks.h"
+
+#undef BPF_RETVAL_HOOK
+};
+
+static void test_exposed_hooks(int cgroup_fd, int sock_fd)
+{
+	struct cgroup_getset_retval_hooks *skel;
+	struct bpf_program *prog;
+	int err;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(exposed_hooks); i++) {
+		skel = cgroup_getset_retval_hooks__open();
+		if (!ASSERT_OK_PTR(skel, "cgroup_getset_retval_hooks__open"))
+			continue;
+
+		prog = bpf_object__find_program_by_name(skel->obj, exposed_hooks[i].name);
+		if (!ASSERT_NEQ(prog, NULL, "bpf_object__find_program_by_name"))
+			goto close_skel;
+
+		err = bpf_program__set_autoload(prog, true);
+		if (!ASSERT_OK(err, "bpf_program__set_autoload"))
+			goto close_skel;
+
+		err = cgroup_getset_retval_hooks__load(skel);
+		ASSERT_EQ(err, exposed_hooks[i].expected_err, "expected_err");
+
+close_skel:
+		cgroup_getset_retval_hooks__destroy(skel);
+	}
+}
+
 void test_cgroup_getset_retval(void)
 {
 	int cgroup_fd = -1;
@@ -476,6 +521,9 @@ void test_cgroup_getset_retval(void)
 	if (test__start_subtest("getsockopt-retval_sync"))
 		test_getsockopt_retval_sync(cgroup_fd, sock_fd);
 
+	if (test__start_subtest("exposed_hooks"))
+		test_exposed_hooks(cgroup_fd, sock_fd);
+
 close_fd:
 	close(cgroup_fd);
 }

tools/testing/selftests/bpf/prog_tests/cgroup_hierarchical_stats.c

@@ -0,0 +1,357 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Functions to manage eBPF programs attached to cgroup subsystems
+ *
+ * Copyright 2022 Google LLC.
+ */
+#include <asm-generic/errno.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#include <test_progs.h>
+#include <bpf/libbpf.h>
+#include <bpf/bpf.h>
+
+#include "cgroup_helpers.h"
+#include "cgroup_hierarchical_stats.skel.h"
+
+#define PAGE_SIZE 4096
+#define MB(x) (x << 20)
+
+#define BPFFS_ROOT "/sys/fs/bpf/"
+#define BPFFS_VMSCAN BPFFS_ROOT"vmscan/"
+
+#define CG_ROOT_NAME "root"
+#define CG_ROOT_ID 1
+
+#define CGROUP_PATH(p, n) {.path = p"/"n, .name = n}
+
+static struct {
+	const char *path, *name;
+	unsigned long long id;
+	int fd;
+} cgroups[] = {
+	CGROUP_PATH("/", "test"),
+	CGROUP_PATH("/test", "child1"),
+	CGROUP_PATH("/test", "child2"),
+	CGROUP_PATH("/test/child1", "child1_1"),
+	CGROUP_PATH("/test/child1", "child1_2"),
+	CGROUP_PATH("/test/child2", "child2_1"),
+	CGROUP_PATH("/test/child2", "child2_2"),
+};
+
+#define N_CGROUPS ARRAY_SIZE(cgroups)
+#define N_NON_LEAF_CGROUPS 3
+
+static int root_cgroup_fd;
+static bool mounted_bpffs;
+
+/* reads file at 'path' to 'buf', returns 0 on success. */
+static int read_from_file(const char *path, char *buf, size_t size)
+{
+	int fd, len;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return fd;
+
+	len = read(fd, buf, size);
+	close(fd);
+	if (len < 0)
+		return len;
+
+	buf[len] = 0;
+	return 0;
+}
+
+/* mounts bpffs and mkdir for reading stats, returns 0 on success. */
+static int setup_bpffs(void)
+{
+	int err;
+
+	/* Mount bpffs */
+	err = mount("bpf", BPFFS_ROOT, "bpf", 0, NULL);
+	mounted_bpffs = !err;
+	if (ASSERT_FALSE(err && errno != EBUSY, "mount"))
+		return err;
+
+	/* Create a directory to contain stat files in bpffs */
+	err = mkdir(BPFFS_VMSCAN, 0755);
+	if (!ASSERT_OK(err, "mkdir"))
+		return err;
+
+	return 0;
+}
+
+static void cleanup_bpffs(void)
+{
+	/* Remove created directory in bpffs */
+	ASSERT_OK(rmdir(BPFFS_VMSCAN), "rmdir "BPFFS_VMSCAN);
+
+	/* Unmount bpffs, if it wasn't already mounted when we started */
+	if (mounted_bpffs)
+		return;
+
+	ASSERT_OK(umount(BPFFS_ROOT), "unmount bpffs");
+}
+
+/* sets up cgroups, returns 0 on success. */
+static int setup_cgroups(void)
+{
+	int i, fd, err;
+
+	err = setup_cgroup_environment();
+	if (!ASSERT_OK(err, "setup_cgroup_environment"))
+		return err;
+
+	root_cgroup_fd = get_root_cgroup();
+	if (!ASSERT_GE(root_cgroup_fd, 0, "get_root_cgroup"))
+		return root_cgroup_fd;
+
+	for (i = 0; i < N_CGROUPS; i++) {
+		fd = create_and_get_cgroup(cgroups[i].path);
+		if (!ASSERT_GE(fd, 0, "create_and_get_cgroup"))
+			return fd;
+
+		cgroups[i].fd = fd;
+		cgroups[i].id = get_cgroup_id(cgroups[i].path);
+
+		/*
+		 * Enable memcg controller for the entire hierarchy.
+		 * Note that stats are collected for all cgroups in a hierarchy
+		 * with memcg enabled anyway, but are only exposed for cgroups
+		 * that have memcg enabled.
+		 */
+		if (i < N_NON_LEAF_CGROUPS) {
+			err = enable_controllers(cgroups[i].path, "memory");
+			if (!ASSERT_OK(err, "enable_controllers"))
+				return err;
+		}
+	}
+	return 0;
+}
+
+static void cleanup_cgroups(void)
+{
+	close(root_cgroup_fd);
+	for (int i = 0; i < N_CGROUPS; i++)
+		close(cgroups[i].fd);
+	cleanup_cgroup_environment();
+}
+
+/* Sets up cgroup hiearchary, returns 0 on success. */
+static int setup_hierarchy(void)
+{
+	return setup_bpffs() || setup_cgroups();
+}
+
+static void destroy_hierarchy(void)
+{
+	cleanup_cgroups();
+	cleanup_bpffs();
+}
+
+static int reclaimer(const char *cgroup_path, size_t size)
+{
+	static char size_buf[128];
+	char *buf, *ptr;
+	int err;
+
+	/* Join cgroup in the parent process workdir */
+	if (join_parent_cgroup(cgroup_path))
+		return EACCES;
+
+	/* Allocate memory */
+	buf = malloc(size);
+	if (!buf)
+		return ENOMEM;
+
+	/* Write to memory to make sure it's actually allocated */
+	for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
+		*ptr = 1;
+
+	/* Try to reclaim memory */
+	snprintf(size_buf, 128, "%lu", size);
+	err = write_cgroup_file_parent(cgroup_path, "memory.reclaim", size_buf);
+
+	free(buf);
+	/* memory.reclaim returns EAGAIN if the amount is not fully reclaimed */
+	if (err && errno != EAGAIN)
+		return errno;
+
+	return 0;
+}
+
+static int induce_vmscan(void)
+{
+	int i, status;
+
+	/*
+	 * In every leaf cgroup, run a child process that allocates some memory
+	 * and attempts to reclaim some of it.
+	 */
+	for (i = N_NON_LEAF_CGROUPS; i < N_CGROUPS; i++) {
+		pid_t pid;
+
+		/* Create reclaimer child */
+		pid = fork();
+		if (pid == 0) {
+			status = reclaimer(cgroups[i].path, MB(5));
+			exit(status);
+		}
+
+		/* Cleanup reclaimer child */
+		waitpid(pid, &status, 0);
+		ASSERT_TRUE(WIFEXITED(status), "reclaimer exited");
+		ASSERT_EQ(WEXITSTATUS(status), 0, "reclaim exit code");
+	}
+	return 0;
+}
+
+static unsigned long long
+get_cgroup_vmscan_delay(unsigned long long cgroup_id, const char *file_name)
+{
+	unsigned long long vmscan = 0, id = 0;
+	static char buf[128], path[128];
+
+	/* For every cgroup, read the file generated by cgroup_iter */
+	snprintf(path, 128, "%s%s", BPFFS_VMSCAN, file_name);
+	if (!ASSERT_OK(read_from_file(path, buf, 128), "read cgroup_iter"))
+		return 0;
+
+	/* Check the output file formatting */
+	ASSERT_EQ(sscanf(buf, "cg_id: %llu, total_vmscan_delay: %llu\n",
+			 &id, &vmscan), 2, "output format");
+
+	/* Check that the cgroup_id is displayed correctly */
+	ASSERT_EQ(id, cgroup_id, "cgroup_id");
+	/* Check that the vmscan reading is non-zero */
+	ASSERT_GT(vmscan, 0, "vmscan_reading");
+	return vmscan;
+}
+
+static void check_vmscan_stats(void)
+{
+	unsigned long long vmscan_readings[N_CGROUPS], vmscan_root;
+	int i;
+
+	for (i = 0; i < N_CGROUPS; i++) {
+		vmscan_readings[i] = get_cgroup_vmscan_delay(cgroups[i].id,
+							     cgroups[i].name);
+	}
+
+	/* Read stats for root too */
+	vmscan_root = get_cgroup_vmscan_delay(CG_ROOT_ID, CG_ROOT_NAME);
+
+	/* Check that child1 == child1_1 + child1_2 */
+	ASSERT_EQ(vmscan_readings[1], vmscan_readings[3] + vmscan_readings[4],
+		  "child1_vmscan");
+	/* Check that child2 == child2_1 + child2_2 */
+	ASSERT_EQ(vmscan_readings[2], vmscan_readings[5] + vmscan_readings[6],
+		  "child2_vmscan");
+	/* Check that test == child1 + child2 */
+	ASSERT_EQ(vmscan_readings[0], vmscan_readings[1] + vmscan_readings[2],
+		  "test_vmscan");
+	/* Check that root >= test */
+	ASSERT_GE(vmscan_root, vmscan_readings[1], "root_vmscan");
+}
+
+/* Creates iter link and pins in bpffs, returns 0 on success, -errno on failure.
+ */
+static int setup_cgroup_iter(struct cgroup_hierarchical_stats *obj,
+			     int cgroup_fd, const char *file_name)
+{
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	union bpf_iter_link_info linfo = {};
+	struct bpf_link *link;
+	static char path[128];
+	int err;
+
+	/*
+	 * Create an iter link, parameterized by cgroup_fd. We only want to
+	 * traverse one cgroup, so set the traversal order to "self".
+	 */
+	linfo.cgroup.cgroup_fd = cgroup_fd;
+	linfo.cgroup.order = BPF_CGROUP_ITER_SELF_ONLY;
+	opts.link_info = &linfo;
+	opts.link_info_len = sizeof(linfo);
+	link = bpf_program__attach_iter(obj->progs.dump_vmscan, &opts);
+	if (!ASSERT_OK_PTR(link, "attach_iter"))
+		return -EFAULT;
+
+	/* Pin the link to a bpffs file */
+	snprintf(path, 128, "%s%s", BPFFS_VMSCAN, file_name);
+	err = bpf_link__pin(link, path);
+	ASSERT_OK(err, "pin cgroup_iter");
+
+	/* Remove the link, leaving only the ref held by the pinned file */
+	bpf_link__destroy(link);
+	return err;
+}
+
+/* Sets up programs for collecting stats, returns 0 on success. */
+static int setup_progs(struct cgroup_hierarchical_stats **skel)
+{
+	int i, err;
+
+	*skel = cgroup_hierarchical_stats__open_and_load();
+	if (!ASSERT_OK_PTR(*skel, "open_and_load"))
+		return 1;
+
+	/* Attach cgroup_iter program that will dump the stats to cgroups */
+	for (i = 0; i < N_CGROUPS; i++) {
+		err = setup_cgroup_iter(*skel, cgroups[i].fd, cgroups[i].name);
+		if (!ASSERT_OK(err, "setup_cgroup_iter"))
+			return err;
+	}
+
+	/* Also dump stats for root */
+	err = setup_cgroup_iter(*skel, root_cgroup_fd, CG_ROOT_NAME);
+	if (!ASSERT_OK(err, "setup_cgroup_iter"))
+		return err;
+
+	bpf_program__set_autoattach((*skel)->progs.dump_vmscan, false);
+	err = cgroup_hierarchical_stats__attach(*skel);
+	if (!ASSERT_OK(err, "attach"))
+		return err;
+
+	return 0;
+}
+
+static void destroy_progs(struct cgroup_hierarchical_stats *skel)
+{
+	static char path[128];
+	int i;
+
+	for (i = 0; i < N_CGROUPS; i++) {
+		/* Delete files in bpffs that cgroup_iters are pinned in */
+		snprintf(path, 128, "%s%s", BPFFS_VMSCAN,
+			 cgroups[i].name);
+		ASSERT_OK(remove(path), "remove cgroup_iter pin");
+	}
+
+	/* Delete root file in bpffs */
+	snprintf(path, 128, "%s%s", BPFFS_VMSCAN, CG_ROOT_NAME);
+	ASSERT_OK(remove(path), "remove cgroup_iter root pin");
+	cgroup_hierarchical_stats__destroy(skel);
+}
+
+void test_cgroup_hierarchical_stats(void)
+{
+	struct cgroup_hierarchical_stats *skel = NULL;
+
+	if (setup_hierarchy())
+		goto hierarchy_cleanup;
+	if (setup_progs(&skel))
+		goto cleanup;
+	if (induce_vmscan())
+		goto cleanup;
+	check_vmscan_stats();
+cleanup:
+	destroy_progs(skel);
+hierarchy_cleanup:
+	destroy_hierarchy();
+}

tools/testing/selftests/bpf/prog_tests/cgroup_iter.c

@@ -0,0 +1,224 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Google */
+
+#include <test_progs.h>
+#include <bpf/libbpf.h>
+#include <bpf/btf.h>
+#include "cgroup_iter.skel.h"
+#include "cgroup_helpers.h"
+
+#define ROOT           0
+#define PARENT         1
+#define CHILD1         2
+#define CHILD2         3
+#define NUM_CGROUPS    4
+
+#define PROLOGUE       "prologue\n"
+#define EPILOGUE       "epilogue\n"
+
+static const char *cg_path[] = {
+	"/", "/parent", "/parent/child1", "/parent/child2"
+};
+
+static int cg_fd[] = {-1, -1, -1, -1};
+static unsigned long long cg_id[] = {0, 0, 0, 0};
+static char expected_output[64];
+
+static int setup_cgroups(void)
+{
+	int fd, i = 0;
+
+	for (i = 0; i < NUM_CGROUPS; i++) {
+		fd = create_and_get_cgroup(cg_path[i]);
+		if (fd < 0)
+			return fd;
+
+		cg_fd[i] = fd;
+		cg_id[i] = get_cgroup_id(cg_path[i]);
+	}
+	return 0;
+}
+
+static void cleanup_cgroups(void)
+{
+	int i;
+
+	for (i = 0; i < NUM_CGROUPS; i++)
+		close(cg_fd[i]);
+}
+
+static void read_from_cgroup_iter(struct bpf_program *prog, int cgroup_fd,
+				  int order, const char *testname)
+{
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	union bpf_iter_link_info linfo;
+	struct bpf_link *link;
+	int len, iter_fd;
+	static char buf[128];
+	size_t left;
+	char *p;
+
+	memset(&linfo, 0, sizeof(linfo));
+	linfo.cgroup.cgroup_fd = cgroup_fd;
+	linfo.cgroup.order = order;
+	opts.link_info = &linfo;
+	opts.link_info_len = sizeof(linfo);
+
+	link = bpf_program__attach_iter(prog, &opts);
+	if (!ASSERT_OK_PTR(link, "attach_iter"))
+		return;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (iter_fd < 0)
+		goto free_link;
+
+	memset(buf, 0, sizeof(buf));
+	left = ARRAY_SIZE(buf);
+	p = buf;
+	while ((len = read(iter_fd, p, left)) > 0) {
+		p += len;
+		left -= len;
+	}
+
+	ASSERT_STREQ(buf, expected_output, testname);
+
+	/* read() after iter finishes should be ok. */
+	if (len == 0)
+		ASSERT_OK(read(iter_fd, buf, sizeof(buf)), "second_read");
+
+	close(iter_fd);
+free_link:
+	bpf_link__destroy(link);
+}
+
+/* Invalid cgroup. */
+static void test_invalid_cgroup(struct cgroup_iter *skel)
+{
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	union bpf_iter_link_info linfo;
+	struct bpf_link *link;
+
+	memset(&linfo, 0, sizeof(linfo));
+	linfo.cgroup.cgroup_fd = (__u32)-1;
+	opts.link_info = &linfo;
+	opts.link_info_len = sizeof(linfo);
+
+	link = bpf_program__attach_iter(skel->progs.cgroup_id_printer, &opts);
+	ASSERT_ERR_PTR(link, "attach_iter");
+	bpf_link__destroy(link);
+}
+
+/* Specifying both cgroup_fd and cgroup_id is invalid. */
+static void test_invalid_cgroup_spec(struct cgroup_iter *skel)
+{
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	union bpf_iter_link_info linfo;
+	struct bpf_link *link;
+
+	memset(&linfo, 0, sizeof(linfo));
+	linfo.cgroup.cgroup_fd = (__u32)cg_fd[PARENT];
+	linfo.cgroup.cgroup_id = (__u64)cg_id[PARENT];
+	opts.link_info = &linfo;
+	opts.link_info_len = sizeof(linfo);
+
+	link = bpf_program__attach_iter(skel->progs.cgroup_id_printer, &opts);
+	ASSERT_ERR_PTR(link, "attach_iter");
+	bpf_link__destroy(link);
+}
+
+/* Preorder walk prints parent and child in order. */
+static void test_walk_preorder(struct cgroup_iter *skel)
+{
+	snprintf(expected_output, sizeof(expected_output),
+		 PROLOGUE "%8llu\n%8llu\n%8llu\n" EPILOGUE,
+		 cg_id[PARENT], cg_id[CHILD1], cg_id[CHILD2]);
+
+	read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[PARENT],
+			      BPF_CGROUP_ITER_DESCENDANTS_PRE, "preorder");
+}
+
+/* Postorder walk prints child and parent in order. */
+static void test_walk_postorder(struct cgroup_iter *skel)
+{
+	snprintf(expected_output, sizeof(expected_output),
+		 PROLOGUE "%8llu\n%8llu\n%8llu\n" EPILOGUE,
+		 cg_id[CHILD1], cg_id[CHILD2], cg_id[PARENT]);
+
+	read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[PARENT],
+			      BPF_CGROUP_ITER_DESCENDANTS_POST, "postorder");
+}
+
+/* Walking parents prints parent and then root. */
+static void test_walk_ancestors_up(struct cgroup_iter *skel)
+{
+	/* terminate the walk when ROOT is met. */
+	skel->bss->terminal_cgroup = cg_id[ROOT];
+
+	snprintf(expected_output, sizeof(expected_output),
+		 PROLOGUE "%8llu\n%8llu\n" EPILOGUE,
+		 cg_id[PARENT], cg_id[ROOT]);
+
+	read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[PARENT],
+			      BPF_CGROUP_ITER_ANCESTORS_UP, "ancestors_up");
+
+	skel->bss->terminal_cgroup = 0;
+}
+
+/* Early termination prints parent only. */
+static void test_early_termination(struct cgroup_iter *skel)
+{
+	/* terminate the walk after the first element is processed. */
+	skel->bss->terminate_early = 1;
+
+	snprintf(expected_output, sizeof(expected_output),
+		 PROLOGUE "%8llu\n" EPILOGUE, cg_id[PARENT]);
+
+	read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[PARENT],
+			      BPF_CGROUP_ITER_DESCENDANTS_PRE, "early_termination");
+
+	skel->bss->terminate_early = 0;
+}
+
+/* Waling self prints self only. */
+static void test_walk_self_only(struct cgroup_iter *skel)
+{
+	snprintf(expected_output, sizeof(expected_output),
+		 PROLOGUE "%8llu\n" EPILOGUE, cg_id[PARENT]);
+
+	read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[PARENT],
+			      BPF_CGROUP_ITER_SELF_ONLY, "self_only");
+}
+
+void test_cgroup_iter(void)
+{
+	struct cgroup_iter *skel = NULL;
+
+	if (setup_cgroup_environment())
+		return;
+
+	if (setup_cgroups())
+		goto out;
+
+	skel = cgroup_iter__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "cgroup_iter__open_and_load"))
+		goto out;
+
+	if (test__start_subtest("cgroup_iter__invalid_cgroup"))
+		test_invalid_cgroup(skel);
+	if (test__start_subtest("cgroup_iter__invalid_cgroup_spec"))
+		test_invalid_cgroup_spec(skel);
+	if (test__start_subtest("cgroup_iter__preorder"))
+		test_walk_preorder(skel);
+	if (test__start_subtest("cgroup_iter__postorder"))
+		test_walk_postorder(skel);
+	if (test__start_subtest("cgroup_iter__ancestors_up_walk"))
+		test_walk_ancestors_up(skel);
+	if (test__start_subtest("cgroup_iter__early_termination"))
+		test_early_termination(skel);
+	if (test__start_subtest("cgroup_iter__self_only"))
+		test_walk_self_only(skel);
+out:
+	cgroup_iter__destroy(skel);
+	cleanup_cgroups();
+	cleanup_cgroup_environment();
+}

tools/testing/selftests/bpf/prog_tests/connect_force_port.c

@@ -53,7 +53,7 @@ static int run_test(int cgroup_fd, int server_fd, int family, int type)
 	__u16 expected_peer_port = 60000;
 	struct bpf_program *prog;
 	struct bpf_object *obj;
-	const char *obj_file = v4 ? "connect_force_port4.o" : "connect_force_port6.o";
+	const char *obj_file = v4 ? "connect_force_port4.bpf.o" : "connect_force_port6.bpf.o";
 	int fd, err;
 	__u32 duration = 0;
 

tools/testing/selftests/bpf/prog_tests/core_reloc.c

@@ -13,7 +13,7 @@ static int duration = 0;
 
 #define MODULES_CASE(name, pg_name, tp_name) {				\
 	.case_name = name,						\
-	.bpf_obj_file = "test_core_reloc_module.o",			\
+	.bpf_obj_file = "test_core_reloc_module.bpf.o",			\
 	.btf_src_file = NULL, /* find in kernel module BTFs */		\
 	.input = "",							\
 	.input_len = 0,							\
@@ -43,8 +43,8 @@ static int duration = 0;
 
 #define FLAVORS_CASE_COMMON(name)					\
 	.case_name = #name,						\
-	.bpf_obj_file = "test_core_reloc_flavors.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.bpf_obj_file = "test_core_reloc_flavors.bpf.o",		\
+	.btf_src_file = "btf__core_reloc_" #name ".bpf.o",		\
 	.raw_tp_name = "sys_enter",					\
 	.prog_name = "test_core_flavors"				\
 
@@ -68,8 +68,8 @@ static int duration = 0;
 
 #define NESTING_CASE_COMMON(name)					\
 	.case_name = #name,						\
-	.bpf_obj_file = "test_core_reloc_nesting.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.bpf_obj_file = "test_core_reloc_nesting.bpf.o",		\
+	.btf_src_file = "btf__core_reloc_" #name ".bpf.o",		\
 	.raw_tp_name = "sys_enter",					\
 	.prog_name = "test_core_nesting"				\
 
@@ -96,8 +96,8 @@ static int duration = 0;
 
 #define ARRAYS_CASE_COMMON(name)					\
 	.case_name = #name,						\
-	.bpf_obj_file = "test_core_reloc_arrays.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.bpf_obj_file = "test_core_reloc_arrays.bpf.o",			\
+	.btf_src_file = "btf__core_reloc_" #name ".bpf.o",		\
 	.raw_tp_name = "sys_enter",					\
 	.prog_name = "test_core_arrays"					\
 
@@ -130,8 +130,8 @@ static int duration = 0;
 
 #define PRIMITIVES_CASE_COMMON(name)					\
 	.case_name = #name,						\
-	.bpf_obj_file = "test_core_reloc_primitives.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.bpf_obj_file = "test_core_reloc_primitives.bpf.o",		\
+	.btf_src_file = "btf__core_reloc_" #name ".bpf.o",		\
 	.raw_tp_name = "sys_enter",					\
 	.prog_name = "test_core_primitives"				\
 
@@ -150,8 +150,8 @@ static int duration = 0;
 
 #define MODS_CASE(name) {						\
 	.case_name = #name,						\
-	.bpf_obj_file = "test_core_reloc_mods.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.bpf_obj_file = "test_core_reloc_mods.bpf.o",			\
+	.btf_src_file = "btf__core_reloc_" #name ".bpf.o",		\
 	.input = STRUCT_TO_CHAR_PTR(core_reloc_##name) {		\
 		.a = 1,							\
 		.b = 2,							\
@@ -174,8 +174,8 @@ static int duration = 0;
 
 #define PTR_AS_ARR_CASE(name) {						\
 	.case_name = #name,						\
-	.bpf_obj_file = "test_core_reloc_ptr_as_arr.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.bpf_obj_file = "test_core_reloc_ptr_as_arr.bpf.o",		\
+	.btf_src_file = "btf__core_reloc_" #name ".bpf.o",		\
 	.input = (const char *)&(struct core_reloc_##name []){		\
 		{ .a = 1 },						\
 		{ .a = 2 },						\
@@ -203,8 +203,8 @@ static int duration = 0;
 
 #define INTS_CASE_COMMON(name)						\
 	.case_name = #name,						\
-	.bpf_obj_file = "test_core_reloc_ints.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.bpf_obj_file = "test_core_reloc_ints.bpf.o",			\
+	.btf_src_file = "btf__core_reloc_" #name ".bpf.o",		\
 	.raw_tp_name = "sys_enter",					\
 	.prog_name = "test_core_ints"
 
@@ -223,18 +223,18 @@ static int duration = 0;
 
 #define FIELD_EXISTS_CASE_COMMON(name)					\
 	.case_name = #name,						\
-	.bpf_obj_file = "test_core_reloc_existence.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.bpf_obj_file = "test_core_reloc_existence.bpf.o",		\
+	.btf_src_file = "btf__core_reloc_" #name ".bpf.o",		\
 	.raw_tp_name = "sys_enter",					\
 	.prog_name = "test_core_existence"
 
 #define BITFIELDS_CASE_COMMON(objfile, test_name_prefix,  name)		\
 	.case_name = test_name_prefix#name,				\
 	.bpf_obj_file = objfile,					\
-	.btf_src_file = "btf__core_reloc_" #name ".o"
+	.btf_src_file = "btf__core_reloc_" #name ".bpf.o"
 
 #define BITFIELDS_CASE(name, ...) {					\
-	BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_probed.o",	\
+	BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_probed.bpf.o",	\
 			      "probed:", name),				\
 	.input = STRUCT_TO_CHAR_PTR(core_reloc_##name) __VA_ARGS__,	\
 	.input_len = sizeof(struct core_reloc_##name),			\
@@ -244,7 +244,7 @@ static int duration = 0;
 	.raw_tp_name = "sys_enter",					\
 	.prog_name = "test_core_bitfields",				\
 }, {									\
-	BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_direct.o",	\
+	BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_direct.bpf.o",	\
 			      "direct:", name),				\
 	.input = STRUCT_TO_CHAR_PTR(core_reloc_##name) __VA_ARGS__,	\
 	.input_len = sizeof(struct core_reloc_##name),			\
@@ -256,14 +256,14 @@ static int duration = 0;
 
 
 #define BITFIELDS_ERR_CASE(name) {					\
-	BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_probed.o",	\
+	BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_probed.bpf.o",	\
 			      "probed:", name),				\
 	.fails = true,							\
-	.run_btfgen_fails = true,							\
+	.run_btfgen_fails = true,					\
 	.raw_tp_name = "sys_enter",					\
 	.prog_name = "test_core_bitfields",				\
 }, {									\
-	BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_direct.o",	\
+	BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_direct.bpf.o",	\
 			      "direct:", name),				\
 	.fails = true,							\
 	.run_btfgen_fails = true,							\
@@ -272,8 +272,8 @@ static int duration = 0;
 
 #define SIZE_CASE_COMMON(name)						\
 	.case_name = #name,						\
-	.bpf_obj_file = "test_core_reloc_size.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.bpf_obj_file = "test_core_reloc_size.bpf.o",			\
+	.btf_src_file = "btf__core_reloc_" #name ".bpf.o",		\
 	.raw_tp_name = "sys_enter",					\
 	.prog_name = "test_core_size"
 
@@ -307,13 +307,13 @@ static int duration = 0;
 #define SIZE_ERR_CASE(name) {						\
 	SIZE_CASE_COMMON(name),						\
 	.fails = true,							\
-	.run_btfgen_fails = true,							\
+	.run_btfgen_fails = true,					\
 }
 
 #define TYPE_BASED_CASE_COMMON(name)					\
 	.case_name = #name,						\
-	.bpf_obj_file = "test_core_reloc_type_based.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.bpf_obj_file = "test_core_reloc_type_based.bpf.o",		\
+	.btf_src_file = "btf__core_reloc_" #name ".bpf.o",		\
 	.raw_tp_name = "sys_enter",					\
 	.prog_name = "test_core_type_based"
 
@@ -331,8 +331,8 @@ static int duration = 0;
 
 #define TYPE_ID_CASE_COMMON(name)					\
 	.case_name = #name,						\
-	.bpf_obj_file = "test_core_reloc_type_id.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.bpf_obj_file = "test_core_reloc_type_id.bpf.o",		\
+	.btf_src_file = "btf__core_reloc_" #name ".bpf.o",		\
 	.raw_tp_name = "sys_enter",					\
 	.prog_name = "test_core_type_id"
 
@@ -350,8 +350,8 @@ static int duration = 0;
 
 #define ENUMVAL_CASE_COMMON(name)					\
 	.case_name = #name,						\
-	.bpf_obj_file = "test_core_reloc_enumval.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.bpf_obj_file = "test_core_reloc_enumval.bpf.o",		\
+	.btf_src_file = "btf__core_reloc_" #name ".bpf.o",		\
 	.raw_tp_name = "sys_enter",					\
 	.prog_name = "test_core_enumval"
 
@@ -369,8 +369,8 @@ static int duration = 0;
 
 #define ENUM64VAL_CASE_COMMON(name)					\
 	.case_name = #name,						\
-	.bpf_obj_file = "test_core_reloc_enum64val.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.bpf_obj_file = "test_core_reloc_enum64val.bpf.o",		\
+	.btf_src_file = "btf__core_reloc_" #name ".bpf.o",		\
 	.raw_tp_name = "sys_enter",					\
 	.prog_name = "test_core_enum64val"
 
@@ -547,7 +547,7 @@ static const struct core_reloc_test_case test_cases[] = {
 	/* validate we can find kernel image and use its BTF for relocs */
 	{
 		.case_name = "kernel",
-		.bpf_obj_file = "test_core_reloc_kernel.o",
+		.bpf_obj_file = "test_core_reloc_kernel.bpf.o",
 		.btf_src_file = NULL, /* load from /lib/modules/$(uname -r) */
 		.input = "",
 		.input_len = 0,
@@ -629,8 +629,8 @@ static const struct core_reloc_test_case test_cases[] = {
 	/* validate edge cases of capturing relocations */
 	{
 		.case_name = "misc",
-		.bpf_obj_file = "test_core_reloc_misc.o",
-		.btf_src_file = "btf__core_reloc_misc.o",
+		.bpf_obj_file = "test_core_reloc_misc.bpf.o",
+		.btf_src_file = "btf__core_reloc_misc.bpf.o",
 		.input = (const char *)&(struct core_reloc_misc_extensible[]){
 			{ .a = 1 },
 			{ .a = 2 }, /* not read */

tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c

@@ -174,8 +174,8 @@ static void test_target_no_callees(void)
 	const char *prog_name[] = {
 		"fexit/test_pkt_md_access",
 	};
-	test_fexit_bpf2bpf_common("./fexit_bpf2bpf_simple.o",
-				  "./test_pkt_md_access.o",
+	test_fexit_bpf2bpf_common("./fexit_bpf2bpf_simple.bpf.o",
+				  "./test_pkt_md_access.bpf.o",
 				  ARRAY_SIZE(prog_name),
 				  prog_name, true, NULL);
 }
@@ -188,8 +188,8 @@ static void test_target_yes_callees(void)
 		"fexit/test_pkt_access_subprog2",
 		"fexit/test_pkt_access_subprog3",
 	};
-	test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o",
-				  "./test_pkt_access.o",
+	test_fexit_bpf2bpf_common("./fexit_bpf2bpf.bpf.o",
+				  "./test_pkt_access.bpf.o",
 				  ARRAY_SIZE(prog_name),
 				  prog_name, true, NULL);
 }
@@ -206,8 +206,8 @@ static void test_func_replace(void)
 		"freplace/get_constant",
 		"freplace/test_pkt_write_access_subprog",
 	};
-	test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o",
-				  "./test_pkt_access.o",
+	test_fexit_bpf2bpf_common("./fexit_bpf2bpf.bpf.o",
+				  "./test_pkt_access.bpf.o",
 				  ARRAY_SIZE(prog_name),
 				  prog_name, true, NULL);
 }
@@ -217,8 +217,8 @@ static void test_func_replace_verify(void)
 	const char *prog_name[] = {
 		"freplace/do_bind",
 	};
-	test_fexit_bpf2bpf_common("./freplace_connect4.o",
-				  "./connect4_prog.o",
+	test_fexit_bpf2bpf_common("./freplace_connect4.bpf.o",
+				  "./connect4_prog.bpf.o",
 				  ARRAY_SIZE(prog_name),
 				  prog_name, false, NULL);
 }
@@ -227,7 +227,7 @@ static int test_second_attach(struct bpf_object *obj)
 {
 	const char *prog_name = "security_new_get_constant";
 	const char *tgt_name = "get_constant";
-	const char *tgt_obj_file = "./test_pkt_access.o";
+	const char *tgt_obj_file = "./test_pkt_access.bpf.o";
 	struct bpf_program *prog = NULL;
 	struct bpf_object *tgt_obj;
 	struct bpf_link *link;
@@ -272,8 +272,8 @@ static void test_func_replace_multi(void)
 	const char *prog_name[] = {
 		"freplace/get_constant",
 	};
-	test_fexit_bpf2bpf_common("./freplace_get_constant.o",
-				  "./test_pkt_access.o",
+	test_fexit_bpf2bpf_common("./freplace_get_constant.bpf.o",
+				  "./test_pkt_access.bpf.o",
 				  ARRAY_SIZE(prog_name),
 				  prog_name, true, test_second_attach);
 }
@@ -281,10 +281,10 @@ static void test_func_replace_multi(void)
 static void test_fmod_ret_freplace(void)
 {
 	struct bpf_object *freplace_obj = NULL, *pkt_obj, *fmod_obj = NULL;
-	const char *freplace_name = "./freplace_get_constant.o";
-	const char *fmod_ret_name = "./fmod_ret_freplace.o";
+	const char *freplace_name = "./freplace_get_constant.bpf.o";
+	const char *fmod_ret_name = "./fmod_ret_freplace.bpf.o";
 	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts);
-	const char *tgt_name = "./test_pkt_access.o";
+	const char *tgt_name = "./test_pkt_access.bpf.o";
 	struct bpf_link *freplace_link = NULL;
 	struct bpf_program *prog;
 	__u32 duration = 0;
@@ -339,8 +339,8 @@ static void test_func_sockmap_update(void)
 	const char *prog_name[] = {
 		"freplace/cls_redirect",
 	};
-	test_fexit_bpf2bpf_common("./freplace_cls_redirect.o",
-				  "./test_cls_redirect.o",
+	test_fexit_bpf2bpf_common("./freplace_cls_redirect.bpf.o",
+				  "./test_cls_redirect.bpf.o",
 				  ARRAY_SIZE(prog_name),
 				  prog_name, false, NULL);
 }
@@ -385,15 +385,15 @@ close_prog:
 static void test_func_replace_return_code(void)
 {
 	/* test invalid return code in the replaced program */
-	test_obj_load_failure_common("./freplace_connect_v4_prog.o",
-				     "./connect4_prog.o");
+	test_obj_load_failure_common("./freplace_connect_v4_prog.bpf.o",
+				     "./connect4_prog.bpf.o");
 }
 
 static void test_func_map_prog_compatibility(void)
 {
 	/* test with spin lock map value in the replaced program */
-	test_obj_load_failure_common("./freplace_attach_probe.o",
-				     "./test_attach_probe.o");
+	test_obj_load_failure_common("./freplace_attach_probe.bpf.o",
+				     "./test_attach_probe.bpf.o");
 }
 
 static void test_func_replace_global_func(void)
@@ -402,8 +402,8 @@ static void test_func_replace_global_func(void)
 		"freplace/test_pkt_access",
 	};
 
-	test_fexit_bpf2bpf_common("./freplace_global_func.o",
-				  "./test_pkt_access.o",
+	test_fexit_bpf2bpf_common("./freplace_global_func.bpf.o",
+				  "./test_pkt_access.bpf.o",
 				  ARRAY_SIZE(prog_name),
 				  prog_name, false, NULL);
 }

tools/testing/selftests/bpf/prog_tests/flow_dissector.c

@@ -8,6 +8,8 @@
 
 #include "bpf_flow.skel.h"
 
+#define FLOW_CONTINUE_SADDR 0x7f00007f /* 127.0.0.127 */
+
 #ifndef IP_MF
 #define IP_MF 0x2000
 #endif
@@ -100,6 +102,7 @@ struct test {
 	} pkt;
 	struct bpf_flow_keys keys;
 	__u32 flags;
+	__u32 retval;
 };
 
 #define VLAN_HLEN	4
@@ -126,6 +129,7 @@ struct test tests[] = {
 			.sport = 80,
 			.dport = 8080,
 		},
+		.retval = BPF_OK,
 	},
 	{
 		.name = "ipv6",
@@ -146,6 +150,7 @@ struct test tests[] = {
 			.sport = 80,
 			.dport = 8080,
 		},
+		.retval = BPF_OK,
 	},
 	{
 		.name = "802.1q-ipv4",
@@ -168,6 +173,7 @@ struct test tests[] = {
 			.sport = 80,
 			.dport = 8080,
 		},
+		.retval = BPF_OK,
 	},
 	{
 		.name = "802.1ad-ipv6",
@@ -191,6 +197,7 @@ struct test tests[] = {
 			.sport = 80,
 			.dport = 8080,
 		},
+		.retval = BPF_OK,
 	},
 	{
 		.name = "ipv4-frag",
@@ -217,6 +224,7 @@ struct test tests[] = {
 			.dport = 8080,
 		},
 		.flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG,
+		.retval = BPF_OK,
 	},
 	{
 		.name = "ipv4-no-frag",
@@ -239,6 +247,7 @@ struct test tests[] = {
 			.is_frag = true,
 			.is_first_frag = true,
 		},
+		.retval = BPF_OK,
 	},
 	{
 		.name = "ipv6-frag",
@@ -265,6 +274,7 @@ struct test tests[] = {
 			.dport = 8080,
 		},
 		.flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG,
+		.retval = BPF_OK,
 	},
 	{
 		.name = "ipv6-no-frag",
@@ -287,6 +297,7 @@ struct test tests[] = {
 			.is_frag = true,
 			.is_first_frag = true,
 		},
+		.retval = BPF_OK,
 	},
 	{
 		.name = "ipv6-flow-label",
@@ -309,6 +320,7 @@ struct test tests[] = {
 			.dport = 8080,
 			.flow_label = __bpf_constant_htonl(0xbeeef),
 		},
+		.retval = BPF_OK,
 	},
 	{
 		.name = "ipv6-no-flow-label",
@@ -331,6 +343,7 @@ struct test tests[] = {
 			.flow_label = __bpf_constant_htonl(0xbeeef),
 		},
 		.flags = BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL,
+		.retval = BPF_OK,
 	},
 	{
 		.name = "ipip-encap",
@@ -359,6 +372,7 @@ struct test tests[] = {
 			.sport = 80,
 			.dport = 8080,
 		},
+		.retval = BPF_OK,
 	},
 	{
 		.name = "ipip-no-encap",
@@ -386,6 +400,26 @@ struct test tests[] = {
 			.is_encap = true,
 		},
 		.flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP,
+		.retval = BPF_OK,
+	},
+	{
+		.name = "ipip-encap-dissector-continue",
+		.pkt.ipip = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
+			.iph.ihl = 5,
+			.iph.protocol = IPPROTO_IPIP,
+			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+			.iph.saddr = __bpf_constant_htonl(FLOW_CONTINUE_SADDR),
+			.iph_inner.ihl = 5,
+			.iph_inner.protocol = IPPROTO_TCP,
+			.iph_inner.tot_len =
+				__bpf_constant_htons(MAGIC_BYTES) -
+				sizeof(struct iphdr),
+			.tcp.doff = 5,
+			.tcp.source = 99,
+			.tcp.dest = 9090,
+		},
+		.retval = BPF_FLOW_DISSECTOR_CONTINUE,
 	},
 };
 
@@ -503,6 +537,10 @@ static void run_tests_skb_less(int tap_fd, struct bpf_map *keys)
 		err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt));
 		CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno);
 
+		/* check the stored flow_keys only if BPF_OK expected */
+		if (tests[i].retval != BPF_OK)
+			continue;
+
 		err = bpf_map_lookup_elem(keys_fd, &key, &flow_keys);
 		ASSERT_OK(err, "bpf_map_lookup_elem");
 
@@ -588,7 +626,11 @@ void test_flow_dissector(void)
 
 		err = bpf_prog_test_run_opts(prog_fd, &topts);
 		ASSERT_OK(err, "test_run");
-		ASSERT_EQ(topts.retval, 1, "test_run retval");
+		ASSERT_EQ(topts.retval, tests[i].retval, "test_run retval");
+
+		/* check the resulting flow_keys only if BPF_OK returned */
+		if (topts.retval != BPF_OK)
+			continue;
 		ASSERT_EQ(topts.data_size_out, sizeof(flow_keys),
 			  "test_run data_size_out");
 		CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys);

tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c

@@ -44,7 +44,7 @@ void serial_test_flow_dissector_load_bytes(void)
 	ASSERT_OK(err, "test_run");
 	ASSERT_EQ(topts.data_size_out, sizeof(flow_keys),
 		  "test_run data_size_out");
-	ASSERT_EQ(topts.retval, 1, "test_run retval");
+	ASSERT_EQ(topts.retval, BPF_OK, "test_run retval");
 
 	if (fd >= -1)
 		close(fd);

tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c

@@ -84,8 +84,8 @@ static void get_stack_print_output(void *ctx, int cpu, void *data, __u32 size)
 
 void test_get_stack_raw_tp(void)
 {
-	const char *file = "./test_get_stack_rawtp.o";
-	const char *file_err = "./test_get_stack_rawtp_err.o";
+	const char *file = "./test_get_stack_rawtp.bpf.o";
+	const char *file_err = "./test_get_stack_rawtp_err.bpf.o";
 	const char *prog_name = "bpf_prog1";
 	int i, err, prog_fd, exp_cnt = MAX_CNT_RAWTP;
 	struct perf_buffer *pb = NULL;

tools/testing/selftests/bpf/prog_tests/global_data.c

@@ -131,7 +131,7 @@ static void test_global_data_rdonly(struct bpf_object *obj, __u32 duration)
 
 void test_global_data(void)
 {
-	const char *file = "./test_global_data.o";
+	const char *file = "./test_global_data.bpf.o";
 	struct bpf_object *obj;
 	int err, prog_fd;
 	LIBBPF_OPTS(bpf_test_run_opts, topts,

tools/testing/selftests/bpf/prog_tests/global_data_init.c

@@ -3,7 +3,7 @@
 
 void test_global_data_init(void)
 {
-	const char *file = "./test_global_data.o";
+	const char *file = "./test_global_data.bpf.o";
 	int err = -ENOMEM, map_fd, zero = 0;
 	__u8 *buff = NULL, *newval = NULL;
 	struct bpf_object *obj;

tools/testing/selftests/bpf/prog_tests/global_func_args.c

@@ -39,7 +39,7 @@ static void test_global_func_args0(struct bpf_object *obj)
 
 void test_global_func_args(void)
 {
-	const char *file = "./test_global_func_args.o";
+	const char *file = "./test_global_func_args.bpf.o";
 	struct bpf_object *obj;
 	int err, prog_fd;
 	LIBBPF_OPTS(bpf_test_run_opts, topts,

tools/testing/selftests/bpf/prog_tests/htab_update.c

@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2022. Huawei Technologies Co., Ltd */
+#define _GNU_SOURCE
+#include <sched.h>
+#include <stdbool.h>
+#include <test_progs.h>
+#include "htab_update.skel.h"
+
+struct htab_update_ctx {
+	int fd;
+	int loop;
+	bool stop;
+};
+
+static void test_reenter_update(void)
+{
+	struct htab_update *skel;
+	unsigned int key, value;
+	int err;
+
+	skel = htab_update__open();
+	if (!ASSERT_OK_PTR(skel, "htab_update__open"))
+		return;
+
+	/* lookup_elem_raw() may be inlined and find_kernel_btf_id() will return -ESRCH */
+	bpf_program__set_autoload(skel->progs.lookup_elem_raw, true);
+	err = htab_update__load(skel);
+	if (!ASSERT_TRUE(!err || err == -ESRCH, "htab_update__load") || err)
+		goto out;
+
+	skel->bss->pid = getpid();
+	err = htab_update__attach(skel);
+	if (!ASSERT_OK(err, "htab_update__attach"))
+		goto out;
+
+	/* Will trigger the reentrancy of bpf_map_update_elem() */
+	key = 0;
+	value = 0;
+	err = bpf_map_update_elem(bpf_map__fd(skel->maps.htab), &key, &value, 0);
+	if (!ASSERT_OK(err, "add element"))
+		goto out;
+
+	ASSERT_EQ(skel->bss->update_err, -EBUSY, "no reentrancy");
+out:
+	htab_update__destroy(skel);
+}
+
+static void *htab_update_thread(void *arg)
+{
+	struct htab_update_ctx *ctx = arg;
+	cpu_set_t cpus;
+	int i;
+
+	/* Pinned on CPU 0 */
+	CPU_ZERO(&cpus);
+	CPU_SET(0, &cpus);
+	pthread_setaffinity_np(pthread_self(), sizeof(cpus), &cpus);
+
+	i = 0;
+	while (i++ < ctx->loop && !ctx->stop) {
+		unsigned int key = 0, value = 0;
+		int err;
+
+		err = bpf_map_update_elem(ctx->fd, &key, &value, 0);
+		if (err) {
+			ctx->stop = true;
+			return (void *)(long)err;
+		}
+	}
+
+	return NULL;
+}
+
+static void test_concurrent_update(void)
+{
+	struct htab_update_ctx ctx;
+	struct htab_update *skel;
+	unsigned int i, nr;
+	pthread_t *tids;
+	int err;
+
+	skel = htab_update__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "htab_update__open_and_load"))
+		return;
+
+	ctx.fd = bpf_map__fd(skel->maps.htab);
+	ctx.loop = 1000;
+	ctx.stop = false;
+
+	nr = 4;
+	tids = calloc(nr, sizeof(*tids));
+	if (!ASSERT_NEQ(tids, NULL, "no mem"))
+		goto out;
+
+	for (i = 0; i < nr; i++) {
+		err = pthread_create(&tids[i], NULL, htab_update_thread, &ctx);
+		if (!ASSERT_OK(err, "pthread_create")) {
+			unsigned int j;
+
+			ctx.stop = true;
+			for (j = 0; j < i; j++)
+				pthread_join(tids[j], NULL);
+			goto out;
+		}
+	}
+
+	for (i = 0; i < nr; i++) {
+		void *thread_err = NULL;
+
+		pthread_join(tids[i], &thread_err);
+		ASSERT_EQ(thread_err, NULL, "update error");
+	}
+
+out:
+	if (tids)
+		free(tids);
+	htab_update__destroy(skel);
+}
+
+void test_htab_update(void)
+{
+	if (test__start_subtest("reenter_update"))
+		test_reenter_update();
+	if (test__start_subtest("concurrent_update"))
+		test_concurrent_update();
+}

tools/testing/selftests/bpf/prog_tests/kfree_skb.c

@@ -69,7 +69,7 @@ void serial_test_kfree_skb(void)
 	const int zero = 0;
 	bool test_ok[2];
 
-	err = bpf_prog_test_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS,
+	err = bpf_prog_test_load("./test_pkt_access.bpf.o", BPF_PROG_TYPE_SCHED_CLS,
 				 &obj, &prog_fd);
 	if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno))
 		return;

tools/testing/selftests/bpf/prog_tests/kfunc_call.c

@@ -109,7 +109,7 @@ static void test_destructive(void)
 {
 	__u64 save_caps = 0;
 
-	ASSERT_OK(test_destructive_open_and_load(), "succesful_load");
+	ASSERT_OK(test_destructive_open_and_load(), "successful_load");
 
 	if (!ASSERT_OK(cap_disable_effective(1ULL << CAP_SYS_BOOT, &save_caps), "drop_caps"))
 		return;

tools/testing/selftests/bpf/prog_tests/l4lb_all.c

@@ -90,7 +90,7 @@ out:
 void test_l4lb_all(void)
 {
 	if (test__start_subtest("l4lb_inline"))
-		test_l4lb("test_l4lb.o");
+		test_l4lb("test_l4lb.bpf.o");
 	if (test__start_subtest("l4lb_noinline"))
-		test_l4lb("test_l4lb_noinline.o");
+		test_l4lb("test_l4lb_noinline.bpf.o");
 }

tools/testing/selftests/bpf/prog_tests/load_bytes_relative.c

@@ -27,8 +27,8 @@ void test_load_bytes_relative(void)
 	if (CHECK_FAIL(server_fd < 0))
 		goto close_cgroup_fd;
 
-	err = bpf_prog_test_load("./load_bytes_relative.o", BPF_PROG_TYPE_CGROUP_SKB,
-			    &obj, &prog_fd);
+	err = bpf_prog_test_load("./load_bytes_relative.bpf.o", BPF_PROG_TYPE_CGROUP_SKB,
+				 &obj, &prog_fd);
 	if (CHECK_FAIL(err))
 		goto close_server_fd;
 

tools/testing/selftests/bpf/prog_tests/map_lock.c

@@ -49,7 +49,7 @@ out:
 
 void test_map_lock(void)
 {
-	const char *file = "./test_map_lock.o";
+	const char *file = "./test_map_lock.bpf.o";
 	int prog_fd, map_fd[2], vars[17] = {};
 	pthread_t thread_id[6];
 	struct bpf_object *obj = NULL;

tools/testing/selftests/bpf/prog_tests/pinning.c

@@ -26,13 +26,13 @@ __u32 get_map_id(struct bpf_object *obj, const char *name)
 
 void test_pinning(void)
 {
-	const char *file_invalid = "./test_pinning_invalid.o";
+	const char *file_invalid = "./test_pinning_invalid.bpf.o";
 	const char *custpinpath = "/sys/fs/bpf/custom/pinmap";
 	const char *nopinpath = "/sys/fs/bpf/nopinmap";
 	const char *nopinpath2 = "/sys/fs/bpf/nopinmap2";
 	const char *custpath = "/sys/fs/bpf/custom";
 	const char *pinpath = "/sys/fs/bpf/pinmap";
-	const char *file = "./test_pinning.o";
+	const char *file = "./test_pinning.bpf.o";
 	__u32 map_id, map_id2, duration = 0;
 	struct stat statbuf = {};
 	struct bpf_object *obj;

tools/testing/selftests/bpf/prog_tests/pkt_access.c

@@ -4,7 +4,7 @@
 
 void test_pkt_access(void)
 {
-	const char *file = "./test_pkt_access.o";
+	const char *file = "./test_pkt_access.bpf.o";
 	struct bpf_object *obj;
 	int err, prog_fd;
 	LIBBPF_OPTS(bpf_test_run_opts, topts,

tools/testing/selftests/bpf/prog_tests/pkt_md_access.c

@@ -4,7 +4,7 @@
 
 void test_pkt_md_access(void)
 {
-	const char *file = "./test_pkt_md_access.o";
+	const char *file = "./test_pkt_md_access.bpf.o";
 	struct bpf_object *obj;
 	int err, prog_fd;
 	LIBBPF_OPTS(bpf_test_run_opts, topts,

tools/testing/selftests/bpf/prog_tests/probe_user.c

@@ -11,7 +11,7 @@ void serial_test_probe_user(void)
 #endif
 	};
 	enum { prog_count = ARRAY_SIZE(prog_names) };
-	const char *obj_file = "./test_probe_user.o";
+	const char *obj_file = "./test_probe_user.bpf.o";
 	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, );
 	int err, results_map_fd, sock_fd, duration = 0;
 	struct sockaddr curr, orig, tmp;

tools/testing/selftests/bpf/prog_tests/queue_stack_map.c

@@ -28,9 +28,9 @@ static void test_queue_stack_map_by_type(int type)
 		vals[i] = rand();
 
 	if (type == QUEUE)
-		strncpy(file, "./test_queue_map.o", sizeof(file));
+		strncpy(file, "./test_queue_map.bpf.o", sizeof(file));
 	else if (type == STACK)
-		strncpy(file, "./test_stack_map.o", sizeof(file));
+		strncpy(file, "./test_stack_map.bpf.o", sizeof(file));
 	else
 		return;
 

tools/testing/selftests/bpf/prog_tests/rdonly_maps.c

@@ -16,7 +16,7 @@ struct rdonly_map_subtest {
 
 void test_rdonly_maps(void)
 {
-	const char *file = "test_rdonly_maps.o";
+	const char *file = "test_rdonly_maps.bpf.o";
 	struct rdonly_map_subtest subtests[] = {
 		{ "skip loop", "skip_loop", 0, 0 },
 		{ "part loop", "part_loop", 3, 2 + 3 + 4 },

tools/testing/selftests/bpf/prog_tests/reference_tracking.c

@@ -3,7 +3,7 @@
 
 void test_reference_tracking(void)
 {
-	const char *file = "test_sk_lookup_kern.o";
+	const char *file = "test_sk_lookup_kern.bpf.o";
 	const char *obj_name = "ref_track";
 	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts,
 		.object_name = obj_name,

tools/testing/selftests/bpf/prog_tests/resolve_btfids.c

@@ -101,7 +101,7 @@ static int resolve_symbols(void)
 	int type_id;
 	__u32 nr;
 
-	btf = btf__parse_elf("btf_data.o", NULL);
+	btf = btf__parse_elf("btf_data.bpf.o", NULL);
 	if (CHECK(libbpf_get_error(btf), "resolve",
 		  "Failed to load BTF from btf_data.o\n"))
 		return -1;

tools/testing/selftests/bpf/prog_tests/select_reuseport.c

@@ -91,9 +91,9 @@ static int prepare_bpf_obj(void)
 	struct bpf_map *map;
 	int err;
 
-	obj = bpf_object__open("test_select_reuseport_kern.o");
+	obj = bpf_object__open("test_select_reuseport_kern.bpf.o");
 	err = libbpf_get_error(obj);
-	RET_ERR(err, "open test_select_reuseport_kern.o",
+	RET_ERR(err, "open test_select_reuseport_kern.bpf.o",
 		"obj:%p PTR_ERR(obj):%d\n", obj, err);
 
 	map = bpf_object__find_map_by_name(obj, "outer_map");

tools/testing/selftests/bpf/prog_tests/setget_sockopt.c

@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#define _GNU_SOURCE
+#include <sched.h>
+#include <linux/socket.h>
+#include <net/if.h>
+
+#include "test_progs.h"
+#include "cgroup_helpers.h"
+#include "network_helpers.h"
+
+#include "setget_sockopt.skel.h"
+
+#define CG_NAME "/setget-sockopt-test"
+
+static const char addr4_str[] = "127.0.0.1";
+static const char addr6_str[] = "::1";
+static struct setget_sockopt *skel;
+static int cg_fd;
+
+static int create_netns(void)
+{
+	if (!ASSERT_OK(unshare(CLONE_NEWNET), "create netns"))
+		return -1;
+
+	if (!ASSERT_OK(system("ip link set dev lo up"), "set lo up"))
+		return -1;
+
+	if (!ASSERT_OK(system("ip link add dev binddevtest1 type veth peer name binddevtest2"),
+		       "add veth"))
+		return -1;
+
+	if (!ASSERT_OK(system("ip link set dev binddevtest1 up"),
+		       "bring veth up"))
+		return -1;
+
+	return 0;
+}
+
+static void test_tcp(int family)
+{
+	struct setget_sockopt__bss *bss = skel->bss;
+	int sfd, cfd;
+
+	memset(bss, 0, sizeof(*bss));
+
+	sfd = start_server(family, SOCK_STREAM,
+			   family == AF_INET6 ? addr6_str : addr4_str, 0, 0);
+	if (!ASSERT_GE(sfd, 0, "start_server"))
+		return;
+
+	cfd = connect_to_fd(sfd, 0);
+	if (!ASSERT_GE(cfd, 0, "connect_to_fd_server")) {
+		close(sfd);
+		return;
+	}
+	close(sfd);
+	close(cfd);
+
+	ASSERT_EQ(bss->nr_listen, 1, "nr_listen");
+	ASSERT_EQ(bss->nr_connect, 1, "nr_connect");
+	ASSERT_EQ(bss->nr_active, 1, "nr_active");
+	ASSERT_EQ(bss->nr_passive, 1, "nr_passive");
+	ASSERT_EQ(bss->nr_socket_post_create, 2, "nr_socket_post_create");
+	ASSERT_EQ(bss->nr_binddev, 2, "nr_bind");
+}
+
+static void test_udp(int family)
+{
+	struct setget_sockopt__bss *bss = skel->bss;
+	int sfd;
+
+	memset(bss, 0, sizeof(*bss));
+
+	sfd = start_server(family, SOCK_DGRAM,
+			   family == AF_INET6 ? addr6_str : addr4_str, 0, 0);
+	if (!ASSERT_GE(sfd, 0, "start_server"))
+		return;
+	close(sfd);
+
+	ASSERT_GE(bss->nr_socket_post_create, 1, "nr_socket_post_create");
+	ASSERT_EQ(bss->nr_binddev, 1, "nr_bind");
+}
+
+void test_setget_sockopt(void)
+{
+	cg_fd = test__join_cgroup(CG_NAME);
+	if (cg_fd < 0)
+		return;
+
+	if (create_netns())
+		goto done;
+
+	skel = setget_sockopt__open();
+	if (!ASSERT_OK_PTR(skel, "open skel"))
+		goto done;
+
+	strcpy(skel->rodata->veth, "binddevtest1");
+	skel->rodata->veth_ifindex = if_nametoindex("binddevtest1");
+	if (!ASSERT_GT(skel->rodata->veth_ifindex, 0, "if_nametoindex"))
+		goto done;
+
+	if (!ASSERT_OK(setget_sockopt__load(skel), "load skel"))
+		goto done;
+
+	skel->links.skops_sockopt =
+		bpf_program__attach_cgroup(skel->progs.skops_sockopt, cg_fd);
+	if (!ASSERT_OK_PTR(skel->links.skops_sockopt, "attach cgroup"))
+		goto done;
+
+	skel->links.socket_post_create =
+		bpf_program__attach_cgroup(skel->progs.socket_post_create, cg_fd);
+	if (!ASSERT_OK_PTR(skel->links.socket_post_create, "attach_cgroup"))
+		goto done;
+
+	test_tcp(AF_INET6);
+	test_tcp(AF_INET);
+	test_udp(AF_INET6);
+	test_udp(AF_INET);
+
+done:
+	setget_sockopt__destroy(skel);
+	close(cg_fd);
+}

tools/testing/selftests/bpf/prog_tests/sk_assign.c

@@ -47,7 +47,7 @@ configure_stack(void)
 	if (CHECK_FAIL(system("tc qdisc add dev lo clsact")))
 		return false;
 	sprintf(tc_cmd, "%s %s %s %s", "tc filter add dev lo ingress bpf",
-		       "direct-action object-file ./test_sk_assign.o",
+		       "direct-action object-file ./test_sk_assign.bpf.o",
 		       "section tc",
 		       (env.verbosity < VERBOSE_VERY) ? " 2>/dev/null" : "verbose");
 	if (CHECK(system(tc_cmd), "BPF load failed;",

tools/testing/selftests/bpf/prog_tests/skb_ctx.c

@@ -31,7 +31,7 @@ void test_skb_ctx(void)
 	struct bpf_object *obj;
 	int err, prog_fd, i;
 
-	err = bpf_prog_test_load("./test_skb_ctx.o", BPF_PROG_TYPE_SCHED_CLS,
+	err = bpf_prog_test_load("./test_skb_ctx.bpf.o", BPF_PROG_TYPE_SCHED_CLS,
 				 &obj, &prog_fd);
 	if (!ASSERT_OK(err, "load"))
 		return;

tools/testing/selftests/bpf/prog_tests/skb_helpers.c

@@ -20,7 +20,7 @@ void test_skb_helpers(void)
 	struct bpf_object *obj;
 	int err, prog_fd;
 
-	err = bpf_prog_test_load("./test_skb_helpers.o",
+	err = bpf_prog_test_load("./test_skb_helpers.bpf.o",
 				 BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd);
 	if (!ASSERT_OK(err, "load"))
 		return;

tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c

@@ -174,7 +174,7 @@ static void run_test(int cgroup_fd)
 	pthread_t tid;
 	int err;
 
-	obj = bpf_object__open_file("sockopt_inherit.o", NULL);
+	obj = bpf_object__open_file("sockopt_inherit.bpf.o", NULL);
 	if (!ASSERT_OK_PTR(obj, "obj_open"))
 		return;
 

tools/testing/selftests/bpf/prog_tests/sockopt_multi.c

@@ -310,7 +310,7 @@ void test_sockopt_multi(void)
 	if (CHECK_FAIL(cg_child < 0))
 		goto out;
 
-	obj = bpf_object__open_file("sockopt_multi.o", NULL);
+	obj = bpf_object__open_file("sockopt_multi.bpf.o", NULL);
 	if (!ASSERT_OK_PTR(obj, "obj_load"))
 		goto out;
 

tools/testing/selftests/bpf/prog_tests/spinlock.c

@@ -19,7 +19,7 @@ static void *spin_lock_thread(void *arg)
 
 void test_spinlock(void)
 {
-	const char *file = "./test_spin_lock.o";
+	const char *file = "./test_spin_lock.bpf.o";
 	pthread_t thread_id[4];
 	struct bpf_object *obj = NULL;
 	int prog_fd;