5 files changed, 132 insertions, 38 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 2b914a56a2c5..0edd7d2c0064 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -5,6 +5,7 @@
 #define _LINUX_BPF_H 1
 
 #include <uapi/linux/bpf.h>
+#include <uapi/linux/filter.h>
 
 #include <linux/workqueue.h>
 #include <linux/file.h>
@@ -22,8 +23,10 @@
 #include <linux/sched/mm.h>
 #include <linux/slab.h>
 #include <linux/percpu-refcount.h>
+#include <linux/stddef.h>
 #include <linux/bpfptr.h>
 #include <linux/btf.h>
+#include <linux/rcupdate_trace.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -398,6 +401,9 @@ enum bpf_type_flag {
 	/* DYNPTR points to a ringbuf record. */
 	DYNPTR_TYPE_RINGBUF	= BIT(9 + BPF_BASE_TYPE_BITS),
 
+	/* Size is known at compile time. */
+	MEM_FIXED_SIZE		= BIT(10 + BPF_BASE_TYPE_BITS),
+
 	__BPF_TYPE_FLAG_MAX,
 	__BPF_TYPE_LAST_FLAG	= __BPF_TYPE_FLAG_MAX - 1,
 };
@@ -461,6 +467,8 @@ enum bpf_arg_type {
 	 * all bytes or clear them in error case.
 	 */
 	ARG_PTR_TO_UNINIT_MEM		= MEM_UNINIT | ARG_PTR_TO_MEM,
+	/* Pointer to valid memory of size known at compile time. */
+	ARG_PTR_TO_FIXED_SIZE_MEM	= MEM_FIXED_SIZE | ARG_PTR_TO_MEM,
 
 	/* This must be the last entry. Its purpose is to ensure the enum is
 	 * wide enough to hold the higher bits reserved for bpf_type_flag.
@@ -526,6 +534,14 @@ struct bpf_func_proto {
 			u32 *arg5_btf_id;
 		};
 		u32 *arg_btf_id[5];
+		struct {
+			size_t arg1_size;
+			size_t arg2_size;
+			size_t arg3_size;
+			size_t arg4_size;
+			size_t arg5_size;
+		};
+		size_t arg_size[5];
 	};
 	int *ret_btf_id; /* return value btf_id */
 	bool (*allowed)(const struct bpf_prog *prog);
@@ -1084,6 +1100,40 @@ struct bpf_prog_aux {
 	};
 };
 
+struct bpf_prog {
+	u16			pages;		/* Number of allocated pages */
+	u16			jited:1,	/* Is our filter JIT'ed? */
+				jit_requested:1,/* archs need to JIT the prog */
+				gpl_compatible:1, /* Is filter GPL compatible? */
+				cb_access:1,	/* Is control block accessed? */
+				dst_needed:1,	/* Do we need dst entry? */
+				blinding_requested:1, /* needs constant blinding */
+				blinded:1,	/* Was blinded */
+				is_func:1,	/* program is a bpf function */
+				kprobe_override:1, /* Do we override a kprobe? */
+				has_callchain_buf:1, /* callchain buffer allocated? */
+				enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */
+				call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */
+				call_get_func_ip:1, /* Do we call get_func_ip() */
+				tstamp_type_access:1; /* Accessed __sk_buff->tstamp_type */
+	enum bpf_prog_type	type;		/* Type of BPF program */
+	enum bpf_attach_type	expected_attach_type; /* For some prog types */
+	u32			len;		/* Number of filter blocks */
+	u32			jited_len;	/* Size of jited insns in bytes */
+	u8			tag[BPF_TAG_SIZE];
+	struct bpf_prog_stats __percpu *stats;
+	int __percpu		*active;
+	unsigned int		(*bpf_func)(const void *ctx,
+					    const struct bpf_insn *insn);
+	struct bpf_prog_aux	*aux;		/* Auxiliary fields */
+	struct sock_fprog_kern	*orig_prog;	/* Original BPF program */
+	/* Instructions for interpreter */
+	union {
+		DECLARE_FLEX_ARRAY(struct sock_filter, insns);
+		DECLARE_FLEX_ARRAY(struct bpf_insn, insnsi);
+	};
+};
+
 struct bpf_array_aux {
 	/* Programs with direct jumps into programs part of this array. */
 	struct list_head poke_progs;
@@ -1336,6 +1386,8 @@ extern struct bpf_empty_prog_array bpf_empty_prog_array;
 
 struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
 void bpf_prog_array_free(struct bpf_prog_array *progs);
+/* Use when traversal over the bpf_prog_array uses tasks_trace rcu */
+void bpf_prog_array_free_sleepable(struct bpf_prog_array *progs);
 int bpf_prog_array_length(struct bpf_prog_array *progs);
 bool bpf_prog_array_is_empty(struct bpf_prog_array *array);
 int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs,
@@ -1427,6 +1479,55 @@ bpf_prog_run_array(const struct bpf_prog_array *array,
 	return ret;
 }
 
+/* Notes on RCU design for bpf_prog_arrays containing sleepable programs:
+ *
+ * We use the tasks_trace rcu flavor read section to protect the bpf_prog_array
+ * overall. As a result, we must use the bpf_prog_array_free_sleepable
+ * in order to use the tasks_trace rcu grace period.
+ *
+ * When a non-sleepable program is inside the array, we take the rcu read
+ * section and disable preemption for that program alone, so it can access
+ * rcu-protected dynamically sized maps.
+ */
+static __always_inline u32
+bpf_prog_run_array_sleepable(const struct bpf_prog_array __rcu *array_rcu,
+			     const void *ctx, bpf_prog_run_fn run_prog)
+{
+	const struct bpf_prog_array_item *item;
+	const struct bpf_prog *prog;
+	const struct bpf_prog_array *array;
+	struct bpf_run_ctx *old_run_ctx;
+	struct bpf_trace_run_ctx run_ctx;
+	u32 ret = 1;
+
+	might_fault();
+
+	rcu_read_lock_trace();
+	migrate_disable();
+
+	array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held());
+	if (unlikely(!array))
+		goto out;
+	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
+	item = &array->items[0];
+	while ((prog = READ_ONCE(item->prog))) {
+		if (!prog->aux->sleepable)
+			rcu_read_lock();
+
+		run_ctx.bpf_cookie = item->bpf_cookie;
+		ret &= run_prog(prog, ctx);
+		item++;
+
+		if (!prog->aux->sleepable)
+			rcu_read_unlock();
+	}
+	bpf_reset_run_ctx(old_run_ctx);
+out:
+	migrate_enable();
+	rcu_read_unlock_trace();
+	return ret;
+}
+
 #ifdef CONFIG_BPF_SYSCALL
 DECLARE_PER_CPU(int, bpf_prog_active);
 extern struct mutex bpf_stats_enabled_mutex;
@@ -2104,6 +2205,7 @@ int sock_map_bpf_prog_query(const union bpf_attr *attr,
 			    union bpf_attr __user *uattr);
 
 void sock_map_unhash(struct sock *sk);
+void sock_map_destroy(struct sock *sk);
 void sock_map_close(struct sock *sk, long timeout);
 #else
 static inline int bpf_prog_offload_init(struct bpf_prog *prog,
@@ -2261,12 +2363,9 @@ extern const struct bpf_func_proto bpf_for_each_map_elem_proto;
 extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto;
 extern const struct bpf_func_proto bpf_sk_setsockopt_proto;
 extern const struct bpf_func_proto bpf_sk_getsockopt_proto;
-extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto;
 extern const struct bpf_func_proto bpf_find_vma_proto;
 extern const struct bpf_func_proto bpf_loop_proto;
-extern const struct bpf_func_proto bpf_strncmp_proto;
 extern const struct bpf_func_proto bpf_copy_from_user_task_proto;
-extern const struct bpf_func_proto bpf_kptr_xchg_proto;
 
 const struct bpf_func_proto *tracing_prog_func_proto(
   enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index e8439f6cbe57..3930c963fa67 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -299,7 +299,7 @@ struct bpf_verifier_state {
 	 * If is_state_visited() sees a state with branches > 0 it means
 	 * there is a loop. If such state is exactly equal to the current state
 	 * it's an infinite loop. Note states_equal() checks for states
-	 * equvalency, so two states being 'states_equal' does not mean
+	 * equivalency, so two states being 'states_equal' does not mean
 	 * infinite loop. The exact comparison is provided by
 	 * states_maybe_looping() function. It's a stronger pre-check and
 	 * much faster than states_equal().
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 2611cea2c2b6..1bfed7fa0428 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -177,6 +177,19 @@ static inline bool btf_type_is_enum(const struct btf_type *t)
 	return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM;
 }
 
+static inline bool btf_is_any_enum(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM ||
+	       BTF_INFO_KIND(t->info) == BTF_KIND_ENUM64;
+}
+
+static inline bool btf_kind_core_compat(const struct btf_type *t1,
+					const struct btf_type *t2)
+{
+	return BTF_INFO_KIND(t1->info) == BTF_INFO_KIND(t2->info) ||
+	       (btf_is_any_enum(t1) && btf_is_any_enum(t2));
+}
+
 static inline bool str_is_empty(const char *s)
 {
 	return !s || !s[0];
@@ -192,6 +205,16 @@ static inline bool btf_is_enum(const struct btf_type *t)
 	return btf_kind(t) == BTF_KIND_ENUM;
 }
 
+static inline bool btf_is_enum64(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_ENUM64;
+}
+
+static inline u64 btf_enum64_value(const struct btf_enum64 *e)
+{
+	return ((u64)e->val_hi32 << 32) | e->val_lo32;
+}
+
 static inline bool btf_is_composite(const struct btf_type *t)
 {
 	u16 kind = btf_kind(t);
@@ -332,6 +355,11 @@ static inline struct btf_enum *btf_enum(const struct btf_type *t)
 	return (struct btf_enum *)(t + 1);
 }
 
+static inline struct btf_enum64 *btf_enum64(const struct btf_type *t)
+{
+	return (struct btf_enum64 *)(t + 1);
+}
+
 static inline const struct btf_var_secinfo *btf_type_var_secinfo(
 		const struct btf_type *t)
 {
diff --git a/include/linux/filter.h b/include/linux/filter.h
index ed0c0ff42ad5..d0cbb31b1b4d 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -559,40 +559,6 @@ struct bpf_prog_stats {
 	struct u64_stats_sync syncp;
 } __aligned(2 * sizeof(u64));
 
-struct bpf_prog {
-	u16			pages;		/* Number of allocated pages */
-	u16			jited:1,	/* Is our filter JIT'ed? */
-				jit_requested:1,/* archs need to JIT the prog */
-				gpl_compatible:1, /* Is filter GPL compatible? */
-				cb_access:1,	/* Is control block accessed? */
-				dst_needed:1,	/* Do we need dst entry? */
-				blinding_requested:1, /* needs constant blinding */
-				blinded:1,	/* Was blinded */
-				is_func:1,	/* program is a bpf function */
-				kprobe_override:1, /* Do we override a kprobe? */
-				has_callchain_buf:1, /* callchain buffer allocated? */
-				enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */
-				call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */
-				call_get_func_ip:1, /* Do we call get_func_ip() */
-				tstamp_type_access:1; /* Accessed __sk_buff->tstamp_type */
-	enum bpf_prog_type	type;		/* Type of BPF program */
-	enum bpf_attach_type	expected_attach_type; /* For some prog types */
-	u32			len;		/* Number of filter blocks */
-	u32			jited_len;	/* Size of jited insns in bytes */
-	u8			tag[BPF_TAG_SIZE];
-	struct bpf_prog_stats __percpu *stats;
-	int __percpu		*active;
-	unsigned int		(*bpf_func)(const void *ctx,
-					    const struct bpf_insn *insn);
-	struct bpf_prog_aux	*aux;		/* Auxiliary fields */
-	struct sock_fprog_kern	*orig_prog;	/* Original BPF program */
-	/* Instructions for interpreter */
-	union {
-		DECLARE_FLEX_ARRAY(struct sock_filter, insns);
-		DECLARE_FLEX_ARRAY(struct bpf_insn, insnsi);
-	};
-};
-
 struct sk_filter {
 	refcount_t	refcnt;
 	struct rcu_head	rcu;
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index c5a2d6f50f25..153b6dec9b6a 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -95,6 +95,7 @@ struct sk_psock {
 	spinlock_t			link_lock;
 	refcount_t			refcnt;
 	void (*saved_unhash)(struct sock *sk);
+	void (*saved_destroy)(struct sock *sk);
 	void (*saved_close)(struct sock *sk, long timeout);
 	void (*saved_write_space)(struct sock *sk);
 	void (*saved_data_ready)(struct sock *sk);