bpf: Introduce bpf_obj_new

Introduce type safe memory allocator bpf_obj_new for BPF programs. The
kernel side kfunc is named bpf_obj_new_impl, as passing hidden arguments
to kfuncs still requires having them in prototype, unlike BPF helpers
which always take 5 arguments and have them checked using bpf_func_proto
in verifier, ignoring unset argument types.

Introduce __ign suffix to ignore a specific kfunc argument during type
checks, then use this to introduce support for passing type metadata to
the bpf_obj_new_impl kfunc.

The user passes BTF ID of the type it wants to allocates in program BTF,
the verifier then rewrites the first argument as the size of this type,
after performing some sanity checks (to ensure it exists and it is a
struct type).

The second argument is also fixed up and passed by the verifier. This is
the btf_struct_meta for the type being allocated. It would be needed
mostly for the offset array which is required for zero initializing
special fields while leaving the rest of storage in unitialized state.

It would also be needed in the next patch to perform proper destruction
of the object's special fields.

Under the hood, bpf_obj_new will call bpf_mem_alloc and bpf_mem_free,
using the any context BPF memory allocator introduced recently. To this
end, a global instance of the BPF memory allocator is initialized on
boot to be used for this purpose. This 'bpf_global_ma' serves all
allocations for bpf_obj_new. In the future, bpf_obj_new variants will
allow specifying a custom allocator.

Note that now that bpf_obj_new can be used to allocate objects that can
be linked to BPF linked list (when future linked list helpers are
available), we need to also free the elements using bpf_mem_free.
However, since the draining of elements is done outside the
bpf_spin_lock, we need to do migrate_disable around the call since
bpf_list_head_free can be called from map free path where migration is
enabled. Otherwise, when called from BPF programs migration is already
disabled.

A convenience macro is included in the bpf_experimental.h header to hide
over the ugly details of the implementation, leading to user code
looking similar to a language level extension which allocates and
constructs fields of a user type.

struct bar {
	struct bpf_list_node node;
};

struct foo {
	struct bpf_spin_lock lock;
	struct bpf_list_head head __contains(bar, node);
};

void prog(void) {
	struct foo *f;

	f = bpf_obj_new(typeof(*f));
	if (!f)
		return;
	...
}

A key piece of this story is still missing, i.e. the free function,
which will come in the next patch.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20221118015614.2013203-14-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

3 files changed, 150 insertions, 15 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 9c16338bcbe8..2e57fc839a5c 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -34,6 +34,7 @@
 #include <linux/log2.h>
 #include <linux/bpf_verifier.h>
 #include <linux/nodemask.h>
+#include <linux/bpf_mem_alloc.h>
 
 #include <asm/barrier.h>
 #include <asm/unaligned.h>
@@ -60,6 +61,9 @@
 #define CTX	regs[BPF_REG_CTX]
 #define IMM	insn->imm
 
+struct bpf_mem_alloc bpf_global_ma;
+bool bpf_global_ma_set;
+
 /* No hurry in this branch
  *
  * Exported for the bpf jit load helper.
@@ -2746,6 +2750,18 @@ int __weak bpf_arch_text_invalidate(void *dst, size_t len)
 	return -ENOTSUPP;
 }
 
+#ifdef CONFIG_BPF_SYSCALL
+static int __init bpf_global_ma_init(void)
+{
+	int ret;
+
+	ret = bpf_mem_alloc_init(&bpf_global_ma, 0, false);
+	bpf_global_ma_set = !ret;
+	return ret;
+}
+late_initcall(bpf_global_ma_init);
+#endif
+
 DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
 EXPORT_SYMBOL(bpf_stats_enabled_key);
 
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 5bc0b9f0f306..c4f1c22cc44c 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -19,6 +19,7 @@
 #include <linux/proc_ns.h>
 #include <linux/security.h>
 #include <linux/btf_ids.h>
+#include <linux/bpf_mem_alloc.h>
 
 #include "../../lib/kstrtox.h"
 
@@ -1735,25 +1736,57 @@ unlock:
 
 		obj -= field->list_head.node_offset;
 		head = head->next;
-		/* TODO: Rework later */
-		kfree(obj);
+		/* The contained type can also have resources, including a
+		 * bpf_list_head which needs to be freed.
+		 */
+		bpf_obj_free_fields(field->list_head.value_rec, obj);
+		/* bpf_mem_free requires migrate_disable(), since we can be
+		 * called from map free path as well apart from BPF program (as
+		 * part of map ops doing bpf_obj_free_fields).
+		 */
+		migrate_disable();
+		bpf_mem_free(&bpf_global_ma, obj);
+		migrate_enable();
 	}
 }
 
-BTF_SET8_START(tracing_btf_ids)
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+		  "Global functions as their definitions will be in vmlinux BTF");
+
+void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign)
+{
+	struct btf_struct_meta *meta = meta__ign;
+	u64 size = local_type_id__k;
+	void *p;
+
+	if (unlikely(!bpf_global_ma_set))
+		return NULL;
+	p = bpf_mem_alloc(&bpf_global_ma, size);
+	if (!p)
+		return NULL;
+	if (meta)
+		bpf_obj_init(meta->field_offs, p);
+	return p;
+}
+
+__diag_pop();
+
+BTF_SET8_START(generic_btf_ids)
 #ifdef CONFIG_KEXEC_CORE
 BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE)
 #endif
-BTF_SET8_END(tracing_btf_ids)
+BTF_ID_FLAGS(func, bpf_obj_new_impl, KF_ACQUIRE | KF_RET_NULL)
+BTF_SET8_END(generic_btf_ids)
 
-static const struct btf_kfunc_id_set tracing_kfunc_set = {
+static const struct btf_kfunc_id_set generic_kfunc_set = {
 	.owner = THIS_MODULE,
-	.set   = &tracing_btf_ids,
+	.set   = &generic_btf_ids,
 };
 
 static int __init kfunc_init(void)
 {
-	return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &tracing_kfunc_set);
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &generic_kfunc_set);
 }
 
 late_initcall(kfunc_init);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c8fcc2808d99..804f3bca6c08 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -7952,6 +7952,11 @@ static bool is_kfunc_arg_constant(const struct btf *btf, const struct btf_param
 	return __kfunc_param_match_suffix(btf, arg, "__k");
 }
 
+static bool is_kfunc_arg_ignore(const struct btf *btf, const struct btf_param *arg)
+{
+	return __kfunc_param_match_suffix(btf, arg, "__ign");
+}
+
 static bool is_kfunc_arg_scalar_with_name(const struct btf *btf,
 					  const struct btf_param *arg,
 					  const char *name)
@@ -8214,6 +8219,10 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 		int kf_arg_type;
 
 		t = btf_type_skip_modifiers(btf, args[i].type, NULL);
+
+		if (is_kfunc_arg_ignore(btf, &args[i]))
+			continue;
+
 		if (btf_type_is_scalar(t)) {
 			if (reg->type != SCALAR_VALUE) {
 				verbose(env, "R%d is not a scalar\n", regno);
@@ -8391,6 +8400,17 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 	return 0;
 }
 
+enum special_kfunc_type {
+	KF_bpf_obj_new_impl,
+};
+
+BTF_SET_START(special_kfunc_set)
+BTF_ID(func, bpf_obj_new_impl)
+BTF_SET_END(special_kfunc_set)
+
+BTF_ID_LIST(special_kfunc_list)
+BTF_ID(func, bpf_obj_new_impl)
+
 static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			    int *insn_idx_p)
 {
@@ -8465,17 +8485,59 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 	t = btf_type_skip_modifiers(desc_btf, func_proto->type, NULL);
 
 	if (is_kfunc_acquire(&meta) && !btf_type_is_struct_ptr(meta.btf, t)) {
-		verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n");
-		return -EINVAL;
+		/* Only exception is bpf_obj_new_impl */
+		if (meta.btf != btf_vmlinux || meta.func_id != special_kfunc_list[KF_bpf_obj_new_impl]) {
+			verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n");
+			return -EINVAL;
+		}
 	}
 
 	if (btf_type_is_scalar(t)) {
 		mark_reg_unknown(env, regs, BPF_REG_0);
 		mark_btf_func_reg_size(env, BPF_REG_0, t->size);
 	} else if (btf_type_is_ptr(t)) {
-		ptr_type = btf_type_skip_modifiers(desc_btf, t->type,
-						   &ptr_type_id);
-		if (!btf_type_is_struct(ptr_type)) {
+		ptr_type = btf_type_skip_modifiers(desc_btf, t->type, &ptr_type_id);
+
+		if (meta.btf == btf_vmlinux && btf_id_set_contains(&special_kfunc_set, meta.func_id)) {
+			if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl]) {
+				const struct btf_type *ret_t;
+				struct btf *ret_btf;
+				u32 ret_btf_id;
+
+				if (((u64)(u32)meta.arg_constant.value) != meta.arg_constant.value) {
+					verbose(env, "local type ID argument must be in range [0, U32_MAX]\n");
+					return -EINVAL;
+				}
+
+				ret_btf = env->prog->aux->btf;
+				ret_btf_id = meta.arg_constant.value;
+
+				/* This may be NULL due to user not supplying a BTF */
+				if (!ret_btf) {
+					verbose(env, "bpf_obj_new requires prog BTF\n");
+					return -EINVAL;
+				}
+
+				ret_t = btf_type_by_id(ret_btf, ret_btf_id);
+				if (!ret_t || !__btf_type_is_struct(ret_t)) {
+					verbose(env, "bpf_obj_new type ID argument must be of a struct\n");
+					return -EINVAL;
+				}
+
+				mark_reg_known_zero(env, regs, BPF_REG_0);
+				regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC;
+				regs[BPF_REG_0].btf = ret_btf;
+				regs[BPF_REG_0].btf_id = ret_btf_id;
+
+				env->insn_aux_data[insn_idx].obj_new_size = ret_t->size;
+				env->insn_aux_data[insn_idx].kptr_struct_meta =
+					btf_find_struct_meta(ret_btf, ret_btf_id);
+			} else {
+				verbose(env, "kernel function %s unhandled dynamic return type\n",
+					meta.func_name);
+				return -EFAULT;
+			}
+		} else if (!__btf_type_is_struct(ptr_type)) {
 			if (!meta.r0_size) {
 				ptr_type_name = btf_name_by_offset(desc_btf,
 								   ptr_type->name_off);
@@ -8503,6 +8565,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			regs[BPF_REG_0].type = PTR_TO_BTF_ID;
 			regs[BPF_REG_0].btf_id = ptr_type_id;
 		}
+
 		if (is_kfunc_ret_null(&meta)) {
 			regs[BPF_REG_0].type |= PTR_MAYBE_NULL;
 			/* For mark_ptr_or_null_reg, see 93c230e3f5bd6 */
@@ -14671,8 +14734,8 @@ static int fixup_call_args(struct bpf_verifier_env *env)
 	return err;
 }
 
-static int fixup_kfunc_call(struct bpf_verifier_env *env,
-			    struct bpf_insn *insn)
+static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
+			    struct bpf_insn *insn_buf, int insn_idx, int *cnt)
 {
 	const struct bpf_kfunc_desc *desc;
 
@@ -14691,8 +14754,21 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env,
 		return -EFAULT;
 	}
 
+	*cnt = 0;
 	insn->imm = desc->imm;
+	if (insn->off)
+		return 0;
+	if (desc->func_id == special_kfunc_list[KF_bpf_obj_new_impl]) {
+		struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta;
+		struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) };
+		u64 obj_new_size = env->insn_aux_data[insn_idx].obj_new_size;
 
+		insn_buf[0] = BPF_MOV64_IMM(BPF_REG_1, obj_new_size);
+		insn_buf[1] = addr[0];
+		insn_buf[2] = addr[1];
+		insn_buf[3] = *insn;
+		*cnt = 4;
+	}
 	return 0;
 }
 
@@ -14834,9 +14910,19 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 		if (insn->src_reg == BPF_PSEUDO_CALL)
 			continue;
 		if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) {
-			ret = fixup_kfunc_call(env, insn);
+			ret = fixup_kfunc_call(env, insn, insn_buf, i + delta, &cnt);
 			if (ret)
 				return ret;
+			if (cnt == 0)
+				continue;
+
+			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+			if (!new_prog)
+				return -ENOMEM;
+
+			delta	 += cnt - 1;
+			env->prog = prog = new_prog;
+			insn	  = new_prog->insnsi + i + delta;
 			continue;
 		}