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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2020-05-01 (v2)

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

We've added 61 non-merge commits during the last 6 day(s) which contain
a total of 153 files changed, 6739 insertions(+), 3367 deletions(-).

The main changes are:

1) pulled work.sysctl from vfs tree with sysctl bpf changes.

2) bpf_link observability, from Andrii.

3) BTF-defined map in map, from Andrii.

4) asan fixes for selftests, from Andrii.

5) Allow bpf_map_lookup_elem for SOCKMAP and SOCKHASH, from Jakub.

6) production cloudflare classifier as a selftes, from Lorenz.

7) bpf_ktime_get_*_ns() helper improvements, from Maciej.

8) unprivileged bpftool feature probe, from Quentin.

9) BPF_ENABLE_STATS command, from Song.

10) enable bpf_[gs]etsockopt() helpers for sock_ops progs, from Stanislav.

11) enable a bunch of common helpers for cg-device, sysctl, sockopt progs,
 from Stanislav.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

25 files changed, 226 insertions, 169 deletions

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index c11b413d5b1a..272626cc3fc9 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -57,8 +57,6 @@ struct bpf_cgroup_link {
 	enum bpf_attach_type type;
 };
 
-extern const struct bpf_link_ops bpf_cgroup_link_lops;
-
 struct bpf_prog_list {
 	struct list_head node;
 	struct bpf_prog *prog;
@@ -100,8 +98,6 @@ int __cgroup_bpf_attach(struct cgroup *cgrp,
 int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 			struct bpf_cgroup_link *link,
 			enum bpf_attach_type type);
-int __cgroup_bpf_replace(struct cgroup *cgrp, struct bpf_cgroup_link *link,
-			 struct bpf_prog *new_prog);
 int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 		       union bpf_attr __user *uattr);
 
@@ -112,8 +108,6 @@ int cgroup_bpf_attach(struct cgroup *cgrp,
 		      u32 flags);
 int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 		      enum bpf_attach_type type);
-int cgroup_bpf_replace(struct bpf_link *link, struct bpf_prog *old_prog,
-		       struct bpf_prog *new_prog);
 int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 		     union bpf_attr __user *uattr);
 
@@ -138,8 +132,7 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 
 int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 				   struct ctl_table *table, int write,
-				   void __user *buf, size_t *pcount,
-				   loff_t *ppos, void **new_buf,
+				   void **buf, size_t *pcount, loff_t *ppos,
 				   enum bpf_attach_type type);
 
 int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level,
@@ -302,12 +295,12 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 })
 
 
-#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, pos, nbuf)  \
+#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, pos)  \
 ({									       \
 	int __ret = 0;							       \
 	if (cgroup_bpf_enabled)						       \
 		__ret = __cgroup_bpf_run_filter_sysctl(head, table, write,     \
-						       buf, count, pos, nbuf,  \
+						       buf, count, pos,        \
 						       BPF_CGROUP_SYSCTL);     \
 	__ret;								       \
 })
@@ -354,7 +347,6 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr,
 #else
 
 struct bpf_prog;
-struct bpf_link;
 struct cgroup_bpf {};
 static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
 static inline void cgroup_bpf_offline(struct cgroup *cgrp) {}
@@ -378,13 +370,6 @@ static inline int cgroup_bpf_link_attach(const union bpf_attr *attr,
 	return -EINVAL;
 }
 
-static inline int cgroup_bpf_replace(struct bpf_link *link,
-				     struct bpf_prog *old_prog,
-				     struct bpf_prog *new_prog)
-{
-	return -EINVAL;
-}
-
 static inline int cgroup_bpf_prog_query(const union bpf_attr *attr,
 					union bpf_attr __user *uattr)
 {
@@ -429,7 +414,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos,nbuf) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; })
 #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \
 				       optlen, max_optlen, retval) ({ retval; })
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index fd2b2322412d..1262ec460ab3 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -987,6 +987,7 @@ _out:							\
 
 #ifdef CONFIG_BPF_SYSCALL
 DECLARE_PER_CPU(int, bpf_prog_active);
+extern struct mutex bpf_stats_enabled_mutex;
 
 /*
  * Block execution of BPF programs attached to instrumentation (perf,
@@ -1026,9 +1027,11 @@ extern const struct file_operations bpf_prog_fops;
 	extern const struct bpf_verifier_ops _name ## _verifier_ops;
 #define BPF_MAP_TYPE(_id, _ops) \
 	extern const struct bpf_map_ops _ops;
+#define BPF_LINK_TYPE(_id, _name)
 #include <linux/bpf_types.h>
 #undef BPF_PROG_TYPE
 #undef BPF_MAP_TYPE
+#undef BPF_LINK_TYPE
 
 extern const struct bpf_prog_ops bpf_offload_prog_ops;
 extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops;
@@ -1085,21 +1088,35 @@ int bpf_prog_new_fd(struct bpf_prog *prog);
 
 struct bpf_link {
 	atomic64_t refcnt;
+	u32 id;
+	enum bpf_link_type type;
 	const struct bpf_link_ops *ops;
 	struct bpf_prog *prog;
 	struct work_struct work;
 };
 
+struct bpf_link_primer {
+	struct bpf_link *link;
+	struct file *file;
+	int fd;
+	u32 id;
+};
+
 struct bpf_link_ops {
 	void (*release)(struct bpf_link *link);
 	void (*dealloc)(struct bpf_link *link);
-
+	int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog,
+			   struct bpf_prog *old_prog);
+	void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq);
+	int (*fill_link_info)(const struct bpf_link *link,
+			      struct bpf_link_info *info);
 };
 
-void bpf_link_init(struct bpf_link *link, const struct bpf_link_ops *ops,
-		   struct bpf_prog *prog);
-void bpf_link_cleanup(struct bpf_link *link, struct file *link_file,
-		      int link_fd);
+void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
+		   const struct bpf_link_ops *ops, struct bpf_prog *prog);
+int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer);
+int bpf_link_settle(struct bpf_link_primer *primer);
+void bpf_link_cleanup(struct bpf_link_primer *primer);
 void bpf_link_inc(struct bpf_link *link);
 void bpf_link_put(struct bpf_link *link);
 int bpf_link_new_fd(struct bpf_link *link);
@@ -1215,6 +1232,7 @@ int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog,
 
 struct bpf_prog *bpf_prog_by_id(u32 id);
 
+const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id);
 #else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 {
@@ -1365,6 +1383,12 @@ static inline struct bpf_prog *bpf_prog_by_id(u32 id)
 {
 	return ERR_PTR(-ENOTSUPP);
 }
+
+static inline const struct bpf_func_proto *
+bpf_base_func_proto(enum bpf_func_id func_id)
+{
+	return NULL;
+}
 #endif /* CONFIG_BPF_SYSCALL */
 
 static inline struct bpf_prog *bpf_prog_get_type(u32 ufd,
@@ -1502,6 +1526,7 @@ extern const struct bpf_func_proto bpf_get_smp_processor_id_proto;
 extern const struct bpf_func_proto bpf_get_numa_node_id_proto;
 extern const struct bpf_func_proto bpf_tail_call_proto;
 extern const struct bpf_func_proto bpf_ktime_get_ns_proto;
+extern const struct bpf_func_proto bpf_ktime_get_boot_ns_proto;
 extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto;
 extern const struct bpf_func_proto bpf_get_current_uid_gid_proto;
 extern const struct bpf_func_proto bpf_get_current_comm_proto;
@@ -1523,6 +1548,7 @@ extern const struct bpf_func_proto bpf_strtoul_proto;
 extern const struct bpf_func_proto bpf_tcp_sock_proto;
 extern const struct bpf_func_proto bpf_jiffies64_proto;
 extern const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto;
+extern const struct bpf_func_proto bpf_event_output_data_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);
@@ -1530,6 +1556,7 @@ const struct bpf_func_proto *bpf_tracing_func_proto(
 /* Shared helpers among cBPF and eBPF. */
 void bpf_user_rnd_init_once(void);
 u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
+u64 bpf_get_raw_cpu_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 
 #if defined(CONFIG_NET)
 bool bpf_sock_common_is_valid_access(int off, int size,
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index ba0c2d56f8a3..8345cdf553b8 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -118,3 +118,9 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops)
 #if defined(CONFIG_BPF_JIT)
 BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops)
 #endif
+
+BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint)
+BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing)
+#ifdef CONFIG_CGROUP_BPF
+BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup)
+#endif
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 4b898cdbdf05..a0eabfbeb0e1 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -86,7 +86,7 @@ static inline unsigned long compact_gap(unsigned int order)
 #ifdef CONFIG_COMPACTION
 extern int sysctl_compact_memory;
 extern int sysctl_compaction_handler(struct ctl_table *table, int write,
-			void __user *buffer, size_t *length, loff_t *ppos);
+			void *buffer, size_t *length, loff_t *ppos);
 extern int sysctl_extfrag_threshold;
 extern int sysctl_compact_unevictable_allowed;
 
diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index abf4b4e65dbb..7a899e83835d 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -22,4 +22,8 @@ extern void do_coredump(const kernel_siginfo_t *siginfo);
 static inline void do_coredump(const kernel_siginfo_t *siginfo) {}
 #endif
 
+extern int core_uses_pid;
+extern char core_pattern[];
+extern unsigned int core_pipe_limit;
+
 #endif /* _LINUX_COREDUMP_H */
diff --git a/include/linux/file.h b/include/linux/file.h
index 142d102f285e..122f80084a3e 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -94,4 +94,6 @@ extern void fd_install(unsigned int fd, struct file *file);
 extern void flush_delayed_fput(void);
 extern void __fput_sync(struct file *);
 
+extern unsigned int sysctl_nr_open_min, sysctl_nr_open_max;
+
 #endif /* __LINUX_FILE_H */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 9b5aa5c483cc..af37318bb1c5 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -863,8 +863,6 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog);
 int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
 			      bpf_aux_classic_check_t trans, bool save_orig);
 void bpf_prog_destroy(struct bpf_prog *fp);
-const struct bpf_func_proto *
-bpf_base_func_proto(enum bpf_func_id func_id);
 
 int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
 int sk_attach_bpf(u32 ufd, struct sock *sk);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4f6f59b4f22a..9b028d260649 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3536,11 +3536,11 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf,
 
 struct ctl_table;
 int proc_nr_files(struct ctl_table *table, int write,
-		  void __user *buffer, size_t *lenp, loff_t *ppos);
+		  void *buffer, size_t *lenp, loff_t *ppos);
 int proc_nr_dentry(struct ctl_table *table, int write,
-		  void __user *buffer, size_t *lenp, loff_t *ppos);
+		  void *buffer, size_t *lenp, loff_t *ppos);
 int proc_nr_inodes(struct ctl_table *table, int write,
-		   void __user *buffer, size_t *lenp, loff_t *ppos);
+		   void *buffer, size_t *lenp, loff_t *ppos);
 int __init get_filesystem_list(char *buf);
 
 #define __FMODE_EXEC		((__force int) FMODE_EXEC)
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index db95244a62d4..ddfc377de0d2 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -1005,8 +1005,7 @@ extern void disable_trace_on_warning(void);
 extern int __disable_trace_on_warning;
 
 int tracepoint_printk_sysctl(struct ctl_table *table, int write,
-			     void __user *buffer, size_t *lenp,
-			     loff_t *ppos);
+			     void *buffer, size_t *lenp, loff_t *ppos);
 
 #else /* CONFIG_TRACING */
 static inline void  disable_trace_on_warning(void) { }
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 43a1cef8f0f1..92c21c5ccc58 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -105,14 +105,13 @@ struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages,
 void hugepage_put_subpool(struct hugepage_subpool *spool);
 
 void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
-int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
-int hugetlb_overcommit_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
-int hugetlb_treat_movable_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
-
-#ifdef CONFIG_NUMA
-int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int,
-					void __user *, size_t *, loff_t *);
-#endif
+int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *);
+int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *,
+		loff_t *);
+int hugetlb_treat_movable_handler(struct ctl_table *, int, void *, size_t *,
+		loff_t *);
+int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, void *, size_t *,
+		loff_t *);
 
 int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *);
 long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 04bdaf01112c..594265bfd390 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -312,7 +312,7 @@ DEFINE_INSN_CACHE_OPS(optinsn);
 #ifdef CONFIG_SYSCTL
 extern int sysctl_kprobes_optimization;
 extern int proc_kprobes_optimization_handler(struct ctl_table *table,
-					     int write, void __user *buffer,
+					     int write, void *buffer,
 					     size_t *length, loff_t *ppos);
 #endif
 extern void wait_for_kprobe_optimizer(void);
diff --git a/include/linux/latencytop.h b/include/linux/latencytop.h
index 9022f0c2e2e4..abe3d95f795b 100644
--- a/include/linux/latencytop.h
+++ b/include/linux/latencytop.h
@@ -38,8 +38,8 @@ account_scheduler_latency(struct task_struct *task, int usecs, int inter)
 
 void clear_tsk_latency_tracing(struct task_struct *p);
 
-extern int sysctl_latencytop(struct ctl_table *table, int write,
-			void __user *buffer, size_t *lenp, loff_t *ppos);
+int sysctl_latencytop(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos);
 
 #else
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5a323422d783..a7b1ef8ed970 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -201,10 +201,10 @@ extern int sysctl_overcommit_memory;
 extern int sysctl_overcommit_ratio;
 extern unsigned long sysctl_overcommit_kbytes;
 
-extern int overcommit_ratio_handler(struct ctl_table *, int, void __user *,
-				    size_t *, loff_t *);
-extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *,
-				    size_t *, loff_t *);
+int overcommit_ratio_handler(struct ctl_table *, int, void *, size_t *,
+		loff_t *);
+int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *,
+		loff_t *);
 
 #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
 
@@ -2957,8 +2957,8 @@ extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm);
 
 #ifdef CONFIG_SYSCTL
 extern int sysctl_drop_caches;
-int drop_caches_sysctl_handler(struct ctl_table *, int,
-					void __user *, size_t *, loff_t *);
+int drop_caches_sysctl_handler(struct ctl_table *, int, void *, size_t *,
+		loff_t *);
 #endif
 
 void drop_slab(void);
@@ -3140,5 +3140,7 @@ unsigned long wp_shared_mapping_range(struct address_space *mapping,
 				      pgoff_t first_index, pgoff_t nr);
 #endif
 
+extern int sysctl_nr_trim_pages;
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 1b9de7d220fb..93cf20f41e26 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -909,24 +909,23 @@ static inline int is_highmem(struct zone *zone)
 
 /* These two functions are used to setup the per zone pages min values */
 struct ctl_table;
-int min_free_kbytes_sysctl_handler(struct ctl_table *, int,
-					void __user *, size_t *, loff_t *);
-int watermark_boost_factor_sysctl_handler(struct ctl_table *, int,
-					void __user *, size_t *, loff_t *);
-int watermark_scale_factor_sysctl_handler(struct ctl_table *, int,
-					void __user *, size_t *, loff_t *);
+
+int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void *, size_t *,
+		loff_t *);
+int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, void *,
+		size_t *, loff_t *);
 extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES];
-int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int,
-					void __user *, size_t *, loff_t *);
+int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void *,
+		size_t *, loff_t *);
 int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int,
-					void __user *, size_t *, loff_t *);
+		void *, size_t *, loff_t *);
 int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int,
-			void __user *, size_t *, loff_t *);
+		void *, size_t *, loff_t *);
 int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int,
-			void __user *, size_t *, loff_t *);
-
-extern int numa_zonelist_order_handler(struct ctl_table *, int,
-			void __user *, size_t *, loff_t *);
+		void *, size_t *, loff_t *);
+int numa_zonelist_order_handler(struct ctl_table *, int,
+		void *, size_t *, loff_t *);
+extern int percpu_pagelist_fraction;
 extern char numa_zonelist_order[];
 #define NUMA_ZONELIST_ORDER_LEN	16
 
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 9003e29cde46..750c7f395ca9 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -202,16 +202,11 @@ static inline void watchdog_update_hrtimer_threshold(u64 period) { }
 #endif
 
 struct ctl_table;
-extern int proc_watchdog(struct ctl_table *, int ,
-			 void __user *, size_t *, loff_t *);
-extern int proc_nmi_watchdog(struct ctl_table *, int ,
-			     void __user *, size_t *, loff_t *);
-extern int proc_soft_watchdog(struct ctl_table *, int ,
-			      void __user *, size_t *, loff_t *);
-extern int proc_watchdog_thresh(struct ctl_table *, int ,
-				void __user *, size_t *, loff_t *);
-extern int proc_watchdog_cpumask(struct ctl_table *, int,
-				 void __user *, size_t *, loff_t *);
+int proc_watchdog(struct ctl_table *, int, void *, size_t *, loff_t *);
+int proc_nmi_watchdog(struct ctl_table *, int , void *, size_t *, loff_t *);
+int proc_soft_watchdog(struct ctl_table *, int , void *, size_t *, loff_t *);
+int proc_watchdog_thresh(struct ctl_table *, int , void *, size_t *, loff_t *);
+int proc_watchdog_cpumask(struct ctl_table *, int, void *, size_t *, loff_t *);
 
 #ifdef CONFIG_HAVE_ACPI_APEI_NMI
 #include <asm/nmi.h>
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 9c3e7619c929..347ea379622a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1280,15 +1280,12 @@ extern int sysctl_perf_cpu_time_max_percent;
 
 extern void perf_sample_event_took(u64 sample_len_ns);
 
-extern int perf_proc_update_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos);
-extern int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos);
-
+int perf_proc_update_handler(struct ctl_table *table, int write,
+		void *buffer, size_t *lenp, loff_t *ppos);
+int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
+		void *buffer, size_t *lenp, loff_t *ppos);
 int perf_event_max_stack_handler(struct ctl_table *table, int write,
-				 void __user *buffer, size_t *lenp, loff_t *ppos);
+		void *buffer, size_t *lenp, loff_t *ppos);
 
 /* Access to perf_event_open(2) syscall. */
 #define PERF_SECURITY_OPEN		0
diff --git a/include/linux/pid.h b/include/linux/pid.h
index cc896f0fc4e3..93543cbc0e6b 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -108,6 +108,9 @@ extern void transfer_pid(struct task_struct *old, struct task_struct *new,
 struct pid_namespace;
 extern struct pid_namespace init_pid_ns;
 
+extern int pid_max;
+extern int pid_max_min, pid_max_max;
+
 /*
  * look up a PID in the hash table. Must be called with the tasklist_lock
  * or rcu_read_lock() held.
diff --git a/include/linux/printk.h b/include/linux/printk.h
index e061635e0409..fcde0772ec98 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -189,7 +189,7 @@ extern int printk_delay_msec;
 extern int dmesg_restrict;
 
 extern int
-devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void __user *buf,
+devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void *buf,
 			  size_t *lenp, loff_t *ppos);
 
 extern void wake_up_klogd(void);
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index d4f6215ee03f..7b4d3a49b6c5 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -12,9 +12,8 @@ extern unsigned int  sysctl_hung_task_panic;
 extern unsigned long sysctl_hung_task_timeout_secs;
 extern unsigned long sysctl_hung_task_check_interval_secs;
 extern int sysctl_hung_task_warnings;
-extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
-					 void __user *buffer,
-					 size_t *lenp, loff_t *ppos);
+int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
+		void *buffer, size_t *lenp, loff_t *ppos);
 #else
 /* Avoid need for ifdefs elsewhere in the code */
 enum { sysctl_hung_task_timeout_secs = 0 };
@@ -43,8 +42,7 @@ extern __read_mostly unsigned int sysctl_sched_migration_cost;
 extern __read_mostly unsigned int sysctl_sched_nr_migrate;
 
 int sched_proc_update_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *length,
-		loff_t *ppos);
+		void *buffer, size_t *length, loff_t *ppos);
 #endif
 
 /*
@@ -72,33 +70,21 @@ extern unsigned int sysctl_sched_autogroup_enabled;
 extern int sysctl_sched_rr_timeslice;
 extern int sched_rr_timeslice;
 
-extern int sched_rr_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos);
-
-extern int sched_rt_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos);
-
-#ifdef CONFIG_UCLAMP_TASK
-extern int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
-				       void __user *buffer, size_t *lenp,
-				       loff_t *ppos);
-#endif
-
-extern int sysctl_numa_balancing(struct ctl_table *table, int write,
-				 void __user *buffer, size_t *lenp,
-				 loff_t *ppos);
-
-extern int sysctl_schedstats(struct ctl_table *table, int write,
-				 void __user *buffer, size_t *lenp,
-				 loff_t *ppos);
+int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos);
+int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos);
+int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
+		void *buffer, size_t *lenp, loff_t *ppos);
+int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos);
+int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos);
 
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
 extern unsigned int sysctl_sched_energy_aware;
-extern int sched_energy_aware_handler(struct ctl_table *table, int write,
-				 void __user *buffer, size_t *lenp,
-				 loff_t *ppos);
+int sched_energy_aware_handler(struct ctl_table *table, int write,
+		void *buffer, size_t *lenp, loff_t *ppos);
 #endif
 
 #endif /* _LINUX_SCHED_SYSCTL_H */
diff --git a/include/linux/security.h b/include/linux/security.h
index a8d9310472df..6aa229b252ce 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -211,7 +211,7 @@ struct request_sock;
 
 #ifdef CONFIG_MMU
 extern int mmap_min_addr_handler(struct ctl_table *table, int write,
-				 void __user *buffer, size_t *lenp, loff_t *ppos);
+				 void *buffer, size_t *lenp, loff_t *ppos);
 #endif
 
 /* security_inode_init_security callback function to write xattrs */
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 02fa84493f23..f2401e45a3c2 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -44,35 +44,26 @@ struct ctl_dir;
 
 extern const int sysctl_vals[];
 
-typedef int proc_handler (struct ctl_table *ctl, int write,
-			  void __user *buffer, size_t *lenp, loff_t *ppos);
-
-extern int proc_dostring(struct ctl_table *, int,
-			 void __user *, size_t *, loff_t *);
-extern int proc_dointvec(struct ctl_table *, int,
-			 void __user *, size_t *, loff_t *);
-extern int proc_douintvec(struct ctl_table *, int,
-			 void __user *, size_t *, loff_t *);
-extern int proc_dointvec_minmax(struct ctl_table *, int,
-				void __user *, size_t *, loff_t *);
-extern int proc_douintvec_minmax(struct ctl_table *table, int write,
-				 void __user *buffer, size_t *lenp,
-				 loff_t *ppos);
-extern int proc_dointvec_jiffies(struct ctl_table *, int,
-				 void __user *, size_t *, loff_t *);
-extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int,
-					void __user *, size_t *, loff_t *);
-extern int proc_dointvec_ms_jiffies(struct ctl_table *, int,
-				    void __user *, size_t *, loff_t *);
-extern int proc_doulongvec_minmax(struct ctl_table *, int,
-				  void __user *, size_t *, loff_t *);
-extern int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int,
-				      void __user *, size_t *, loff_t *);
-extern int proc_do_large_bitmap(struct ctl_table *, int,
-				void __user *, size_t *, loff_t *);
-extern int proc_do_static_key(struct ctl_table *table, int write,
-			      void __user *buffer, size_t *lenp,
-			      loff_t *ppos);
+typedef int proc_handler(struct ctl_table *ctl, int write, void *buffer,
+		size_t *lenp, loff_t *ppos);
+
+int proc_dostring(struct ctl_table *, int, void *, size_t *, loff_t *);
+int proc_dointvec(struct ctl_table *, int, void *, size_t *, loff_t *);
+int proc_douintvec(struct ctl_table *, int, void *, size_t *, loff_t *);
+int proc_dointvec_minmax(struct ctl_table *, int, void *, size_t *, loff_t *);
+int proc_douintvec_minmax(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos);
+int proc_dointvec_jiffies(struct ctl_table *, int, void *, size_t *, loff_t *);
+int proc_dointvec_userhz_jiffies(struct ctl_table *, int, void *, size_t *,
+		loff_t *);
+int proc_dointvec_ms_jiffies(struct ctl_table *, int, void *, size_t *,
+		loff_t *);
+int proc_doulongvec_minmax(struct ctl_table *, int, void *, size_t *, loff_t *);
+int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int, void *,
+		size_t *, loff_t *);
+int proc_do_large_bitmap(struct ctl_table *, int, void *, size_t *, loff_t *);
+int proc_do_static_key(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos);
 
 /*
  * Register a set of sysctl names by calling register_sysctl_table
@@ -207,7 +198,15 @@ void unregister_sysctl_table(struct ctl_table_header * table);
 
 extern int sysctl_init(void);
 
+extern int pwrsw_enabled;
+extern int unaligned_enabled;
+extern int unaligned_dump_stack;
+extern int no_unaligned_warning;
+
 extern struct ctl_table sysctl_mount_point[];
+extern struct ctl_table random_table[];
+extern struct ctl_table firmware_config_table[];
+extern struct ctl_table epoll_table[];
 
 #else /* CONFIG_SYSCTL */
 static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * table)
@@ -238,7 +237,7 @@ static inline void setup_sysctl_set(struct ctl_table_set *p,
 
 #endif /* CONFIG_SYSCTL */
 
-int sysctl_max_threads(struct ctl_table *table, int write,
-		       void __user *buffer, size_t *lenp, loff_t *ppos);
+int sysctl_max_threads(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos);
 
 #endif /* _LINUX_SYSCTL_H */
diff --git a/include/linux/timer.h b/include/linux/timer.h
index 0dc19a8c39c9..07910ae5ddd9 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -201,8 +201,7 @@ struct ctl_table;
 
 extern unsigned int sysctl_timer_migration;
 int timer_migration_handler(struct ctl_table *table, int write,
-			    void __user *buffer, size_t *lenp,
-			    loff_t *ppos);
+			    void *buffer, size_t *lenp, loff_t *ppos);
 #endif
 
 unsigned long __round_jiffies(unsigned long j, int cpu);
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 292485f3d24d..cb507151710f 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -16,8 +16,8 @@ extern int sysctl_stat_interval;
 #define DISABLE_NUMA_STAT   0
 extern int sysctl_vm_numa_stat;
 DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key);
-extern int sysctl_vm_numa_stat_handler(struct ctl_table *table,
-		int write, void __user *buffer, size_t *length, loff_t *ppos);
+int sysctl_vm_numa_stat_handler(struct ctl_table *table, int write,
+		void *buffer, size_t *length, loff_t *ppos);
 #endif
 
 struct reclaim_stat {
@@ -274,8 +274,8 @@ void cpu_vm_stats_fold(int cpu);
 void refresh_zone_stat_thresholds(void);
 
 struct ctl_table;
-int vmstat_refresh(struct ctl_table *, int write,
-		   void __user *buffer, size_t *lenp, loff_t *ppos);
+int vmstat_refresh(struct ctl_table *, int write, void *buffer, size_t *lenp,
+		loff_t *ppos);
 
 void drain_zonestat(struct zone *zone, struct per_cpu_pageset *);
 
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index a19d845dd7eb..f8a7e1a850fb 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -362,24 +362,18 @@ extern int vm_highmem_is_dirtyable;
 extern int block_dump;
 extern int laptop_mode;
 
-extern int dirty_background_ratio_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos);
-extern int dirty_background_bytes_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos);
-extern int dirty_ratio_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos);
-extern int dirty_bytes_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos);
+int dirty_background_ratio_handler(struct ctl_table *table, int write,
+		void *buffer, size_t *lenp, loff_t *ppos);
+int dirty_background_bytes_handler(struct ctl_table *table, int write,
+		void *buffer, size_t *lenp, loff_t *ppos);
+int dirty_ratio_handler(struct ctl_table *table, int write,
+		void *buffer, size_t *lenp, loff_t *ppos);
+int dirty_bytes_handler(struct ctl_table *table, int write,
+		void *buffer, size_t *lenp, loff_t *ppos);
 int dirtytime_interval_handler(struct ctl_table *table, int write,
-			       void __user *buffer, size_t *lenp, loff_t *ppos);
-
-struct ctl_table;
-int dirty_writeback_centisecs_handler(struct ctl_table *, int,
-				      void __user *, size_t *, loff_t *);
+		void *buffer, size_t *lenp, loff_t *ppos);
+int dirty_writeback_centisecs_handler(struct ctl_table *table, int write,
+		void *buffer, size_t *lenp, loff_t *ppos);
 
 void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty);
 unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 7bbf1b65be10..b3643e27e264 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -113,6 +113,9 @@ enum bpf_cmd {
 	BPF_MAP_DELETE_BATCH,
 	BPF_LINK_CREATE,
 	BPF_LINK_UPDATE,
+	BPF_LINK_GET_FD_BY_ID,
+	BPF_LINK_GET_NEXT_ID,
+	BPF_ENABLE_STATS,
 };
 
 enum bpf_map_type {
@@ -220,6 +223,15 @@ enum bpf_attach_type {
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
+enum bpf_link_type {
+	BPF_LINK_TYPE_UNSPEC = 0,
+	BPF_LINK_TYPE_RAW_TRACEPOINT = 1,
+	BPF_LINK_TYPE_TRACING = 2,
+	BPF_LINK_TYPE_CGROUP = 3,
+
+	MAX_BPF_LINK_TYPE,
+};
+
 /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
  *
  * NONE(default): No further bpf programs allowed in the subtree.
@@ -379,6 +391,12 @@ enum {
  */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 
+/* type for BPF_ENABLE_STATS */
+enum bpf_stats_type {
+	/* enabled run_time_ns and run_cnt */
+	BPF_STATS_RUN_TIME = 0,
+};
+
 enum bpf_stack_build_id_status {
 	/* user space need an empty entry to identify end of a trace */
 	BPF_STACK_BUILD_ID_EMPTY = 0,
@@ -523,6 +541,7 @@ union bpf_attr {
 			__u32		prog_id;
 			__u32		map_id;
 			__u32		btf_id;
+			__u32		link_id;
 		};
 		__u32		next_id;
 		__u32		open_flags;
@@ -589,6 +608,10 @@ union bpf_attr {
 		__u32		old_prog_fd;
 	} link_update;
 
+	struct { /* struct used by BPF_ENABLE_STATS command */
+		__u32		type;
+	} enable_stats;
+
 } __attribute__((aligned(8)));
 
 /* The description below is an attempt at providing documentation to eBPF
@@ -652,6 +675,8 @@ union bpf_attr {
  * u64 bpf_ktime_get_ns(void)
  * 	Description
  * 		Return the time elapsed since system boot, in nanoseconds.
+ * 		Does not include time the system was suspended.
+ * 		See: clock_gettime(CLOCK_MONOTONIC)
  * 	Return
  * 		Current *ktime*.
  *
@@ -1562,7 +1587,7 @@ union bpf_attr {
  * 	Return
  * 		0
  *
- * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen)
+ * int bpf_setsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen)
  * 	Description
  * 		Emulate a call to **setsockopt()** on the socket associated to
  * 		*bpf_socket*, which must be a full socket. The *level* at
@@ -1570,6 +1595,11 @@ union bpf_attr {
  * 		must be specified, see **setsockopt(2)** for more information.
  * 		The option value of length *optlen* is pointed by *optval*.
  *
+ * 		*bpf_socket* should be one of the following:
+ * 		* **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
+ * 		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
+ * 		  and **BPF_CGROUP_INET6_CONNECT**.
+ *
  * 		This helper actually implements a subset of **setsockopt()**.
  * 		It supports the following *level*\ s:
  *
@@ -1764,7 +1794,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen)
+ * int bpf_getsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen)
  * 	Description
  * 		Emulate a call to **getsockopt()** on the socket associated to
  * 		*bpf_socket*, which must be a full socket. The *level* at
@@ -1773,6 +1803,11 @@ union bpf_attr {
  * 		The retrieved value is stored in the structure pointed by
  * 		*opval* and of length *optlen*.
  *
+ * 		*bpf_socket* should be one of the following:
+ * 		* **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
+ * 		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
+ * 		  and **BPF_CGROUP_INET6_CONNECT**.
+ *
  * 		This helper actually implements a subset of **getsockopt()**.
  * 		It supports the following *level*\ s:
  *
@@ -3025,6 +3060,14 @@ union bpf_attr {
  *		* **-EOPNOTSUPP**	Unsupported operation, for example a
  *					call from outside of TC ingress.
  *		* **-ESOCKTNOSUPPORT**	Socket type not supported (reuseport).
+ *
+ * u64 bpf_ktime_get_boot_ns(void)
+ * 	Description
+ * 		Return the time elapsed since system boot, in nanoseconds.
+ * 		Does include the time the system was suspended.
+ * 		See: clock_gettime(CLOCK_BOOTTIME)
+ * 	Return
+ * 		Current *ktime*.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3151,7 +3194,8 @@ union bpf_attr {
 	FN(xdp_output),			\
 	FN(get_netns_cookie),		\
 	FN(get_current_ancestor_cgroup_id),	\
-	FN(sk_assign),
+	FN(sk_assign),			\
+	FN(ktime_get_boot_ns),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -3598,6 +3642,25 @@ struct bpf_btf_info {
 	__u32 id;
 } __attribute__((aligned(8)));
 
+struct bpf_link_info {
+	__u32 type;
+	__u32 id;
+	__u32 prog_id;
+	union {
+		struct {
+			__aligned_u64 tp_name; /* in/out: tp_name buffer ptr */
+			__u32 tp_name_len;     /* in/out: tp_name buffer len */
+		} raw_tracepoint;
+		struct {
+			__u32 attach_type;
+		} tracing;
+		struct {
+			__u64 cgroup_id;
+			__u32 attach_type;
+		} cgroup;
+	};
+} __attribute__((aligned(8)));
+
 /* User bpf_sock_addr struct to access socket fields and sockaddr struct passed
  * by user and intended to be used by socket (e.g. to bind to, depends on
  * attach attach type).