bpf, x86: Generate trampolines from bpf_tramp_links

Replace struct bpf_tramp_progs with struct bpf_tramp_links to collect
struct bpf_tramp_link(s) for a trampoline.  struct bpf_tramp_link
extends bpf_link to act as a linked list node.

arch_prepare_bpf_trampoline() accepts a struct bpf_tramp_links to
collects all bpf_tramp_link(s) that a trampoline should call.

Change BPF trampoline and bpf_struct_ops to pass bpf_tramp_links
instead of bpf_tramp_progs.

Signed-off-by: Kui-Feng Lee <kuifeng@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220510205923.3206889-2-kuifeng@fb.com

3 files changed, 98 insertions, 69 deletions

diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 3a0103ad97bc..d9a3c9207240 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -33,15 +33,15 @@ struct bpf_struct_ops_map {
 	const struct bpf_struct_ops *st_ops;
 	/* protect map_update */
 	struct mutex lock;
-	/* progs has all the bpf_prog that is populated
+	/* link has all the bpf_links that is populated
 	 * to the func ptr of the kernel's struct
 	 * (in kvalue.data).
 	 */
-	struct bpf_prog **progs;
+	struct bpf_link **links;
 	/* image is a page that has all the trampolines
 	 * that stores the func args before calling the bpf_prog.
 	 * A PAGE_SIZE "image" is enough to store all trampoline for
-	 * "progs[]".
+	 * "links[]".
 	 */
 	void *image;
 	/* uvalue->data stores the kernel struct
@@ -283,9 +283,9 @@ static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map)
 	u32 i;
 
 	for (i = 0; i < btf_type_vlen(t); i++) {
-		if (st_map->progs[i]) {
-			bpf_prog_put(st_map->progs[i]);
-			st_map->progs[i] = NULL;
+		if (st_map->links[i]) {
+			bpf_link_put(st_map->links[i]);
+			st_map->links[i] = NULL;
 		}
 	}
 }
@@ -316,18 +316,34 @@ static int check_zero_holes(const struct btf_type *t, void *data)
 	return 0;
 }
 
-int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_progs *tprogs,
-				      struct bpf_prog *prog,
+static void bpf_struct_ops_link_release(struct bpf_link *link)
+{
+}
+
+static void bpf_struct_ops_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_tramp_link *tlink = container_of(link, struct bpf_tramp_link, link);
+
+	kfree(tlink);
+}
+
+const struct bpf_link_ops bpf_struct_ops_link_lops = {
+	.release = bpf_struct_ops_link_release,
+	.dealloc = bpf_struct_ops_link_dealloc,
+};
+
+int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
+				      struct bpf_tramp_link *link,
 				      const struct btf_func_model *model,
 				      void *image, void *image_end)
 {
 	u32 flags;
 
-	tprogs[BPF_TRAMP_FENTRY].progs[0] = prog;
-	tprogs[BPF_TRAMP_FENTRY].nr_progs = 1;
+	tlinks[BPF_TRAMP_FENTRY].links[0] = link;
+	tlinks[BPF_TRAMP_FENTRY].nr_links = 1;
 	flags = model->ret_size > 0 ? BPF_TRAMP_F_RET_FENTRY_RET : 0;
 	return arch_prepare_bpf_trampoline(NULL, image, image_end,
-					   model, flags, tprogs, NULL);
+					   model, flags, tlinks, NULL);
 }
 
 static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
@@ -338,7 +354,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	struct bpf_struct_ops_value *uvalue, *kvalue;
 	const struct btf_member *member;
 	const struct btf_type *t = st_ops->type;
-	struct bpf_tramp_progs *tprogs = NULL;
+	struct bpf_tramp_links *tlinks = NULL;
 	void *udata, *kdata;
 	int prog_fd, err = 0;
 	void *image, *image_end;
@@ -362,8 +378,8 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	if (uvalue->state || refcount_read(&uvalue->refcnt))
 		return -EINVAL;
 
-	tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL);
-	if (!tprogs)
+	tlinks = kcalloc(BPF_TRAMP_MAX, sizeof(*tlinks), GFP_KERNEL);
+	if (!tlinks)
 		return -ENOMEM;
 
 	uvalue = (struct bpf_struct_ops_value *)st_map->uvalue;
@@ -386,6 +402,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	for_each_member(i, t, member) {
 		const struct btf_type *mtype, *ptype;
 		struct bpf_prog *prog;
+		struct bpf_tramp_link *link;
 		u32 moff;
 
 		moff = __btf_member_bit_offset(t, member) / 8;
@@ -439,16 +456,26 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 			err = PTR_ERR(prog);
 			goto reset_unlock;
 		}
-		st_map->progs[i] = prog;
 
 		if (prog->type != BPF_PROG_TYPE_STRUCT_OPS ||
 		    prog->aux->attach_btf_id != st_ops->type_id ||
 		    prog->expected_attach_type != i) {
+			bpf_prog_put(prog);
 			err = -EINVAL;
 			goto reset_unlock;
 		}
 
-		err = bpf_struct_ops_prepare_trampoline(tprogs, prog,
+		link = kzalloc(sizeof(*link), GFP_USER);
+		if (!link) {
+			bpf_prog_put(prog);
+			err = -ENOMEM;
+			goto reset_unlock;
+		}
+		bpf_link_init(&link->link, BPF_LINK_TYPE_STRUCT_OPS,
+			      &bpf_struct_ops_link_lops, prog);
+		st_map->links[i] = &link->link;
+
+		err = bpf_struct_ops_prepare_trampoline(tlinks, link,
 							&st_ops->func_models[i],
 							image, image_end);
 		if (err < 0)
@@ -491,7 +518,7 @@ reset_unlock:
 	memset(uvalue, 0, map->value_size);
 	memset(kvalue, 0, map->value_size);
 unlock:
-	kfree(tprogs);
+	kfree(tlinks);
 	mutex_unlock(&st_map->lock);
 	return err;
 }
@@ -546,9 +573,9 @@ static void bpf_struct_ops_map_free(struct bpf_map *map)
 {
 	struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map;
 
-	if (st_map->progs)
+	if (st_map->links)
 		bpf_struct_ops_map_put_progs(st_map);
-	bpf_map_area_free(st_map->progs);
+	bpf_map_area_free(st_map->links);
 	bpf_jit_free_exec(st_map->image);
 	bpf_map_area_free(st_map->uvalue);
 	bpf_map_area_free(st_map);
@@ -597,11 +624,11 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 	map = &st_map->map;
 
 	st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE);
-	st_map->progs =
-		bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_prog *),
+	st_map->links =
+		bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_links *),
 				   NUMA_NO_NODE);
 	st_map->image = bpf_jit_alloc_exec(PAGE_SIZE);
-	if (!st_map->uvalue || !st_map->progs || !st_map->image) {
+	if (!st_map->uvalue || !st_map->links || !st_map->image) {
 		bpf_struct_ops_map_free(map);
 		return ERR_PTR(-ENOMEM);
 	}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 50164d324eaf..2dc582773344 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2864,19 +2864,12 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd)
 }
 EXPORT_SYMBOL(bpf_link_get_from_fd);
 
-struct bpf_tracing_link {
-	struct bpf_link link;
-	enum bpf_attach_type attach_type;
-	struct bpf_trampoline *trampoline;
-	struct bpf_prog *tgt_prog;
-};
-
 static void bpf_tracing_link_release(struct bpf_link *link)
 {
 	struct bpf_tracing_link *tr_link =
-		container_of(link, struct bpf_tracing_link, link);
+		container_of(link, struct bpf_tracing_link, link.link);
 
-	WARN_ON_ONCE(bpf_trampoline_unlink_prog(link->prog,
+	WARN_ON_ONCE(bpf_trampoline_unlink_prog(&tr_link->link,
 						tr_link->trampoline));
 
 	bpf_trampoline_put(tr_link->trampoline);
@@ -2889,7 +2882,7 @@ static void bpf_tracing_link_release(struct bpf_link *link)
 static void bpf_tracing_link_dealloc(struct bpf_link *link)
 {
 	struct bpf_tracing_link *tr_link =
-		container_of(link, struct bpf_tracing_link, link);
+		container_of(link, struct bpf_tracing_link, link.link);
 
 	kfree(tr_link);
 }
@@ -2898,7 +2891,7 @@ static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link,
 					 struct seq_file *seq)
 {
 	struct bpf_tracing_link *tr_link =
-		container_of(link, struct bpf_tracing_link, link);
+		container_of(link, struct bpf_tracing_link, link.link);
 
 	seq_printf(seq,
 		   "attach_type:\t%d\n",
@@ -2909,7 +2902,7 @@ static int bpf_tracing_link_fill_link_info(const struct bpf_link *link,
 					   struct bpf_link_info *info)
 {
 	struct bpf_tracing_link *tr_link =
-		container_of(link, struct bpf_tracing_link, link);
+		container_of(link, struct bpf_tracing_link, link.link);
 
 	info->tracing.attach_type = tr_link->attach_type;
 	bpf_trampoline_unpack_key(tr_link->trampoline->key,
@@ -2990,7 +2983,7 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 		err = -ENOMEM;
 		goto out_put_prog;
 	}
-	bpf_link_init(&link->link, BPF_LINK_TYPE_TRACING,
+	bpf_link_init(&link->link.link, BPF_LINK_TYPE_TRACING,
 		      &bpf_tracing_link_lops, prog);
 	link->attach_type = prog->expected_attach_type;
 
@@ -3060,11 +3053,11 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 		tgt_prog = prog->aux->dst_prog;
 	}
 
-	err = bpf_link_prime(&link->link, &link_primer);
+	err = bpf_link_prime(&link->link.link, &link_primer);
 	if (err)
 		goto out_unlock;
 
-	err = bpf_trampoline_link_prog(prog, tr);
+	err = bpf_trampoline_link_prog(&link->link, tr);
 	if (err) {
 		bpf_link_cleanup(&link_primer);
 		link = NULL;
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index ada97751ae1b..d5e6bc5517cb 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -168,30 +168,30 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
 	return ret;
 }
 
-static struct bpf_tramp_progs *
+static struct bpf_tramp_links *
 bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_arg)
 {
-	const struct bpf_prog_aux *aux;
-	struct bpf_tramp_progs *tprogs;
-	struct bpf_prog **progs;
+	struct bpf_tramp_link *link;
+	struct bpf_tramp_links *tlinks;
+	struct bpf_tramp_link **links;
 	int kind;
 
 	*total = 0;
-	tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL);
-	if (!tprogs)
+	tlinks = kcalloc(BPF_TRAMP_MAX, sizeof(*tlinks), GFP_KERNEL);
+	if (!tlinks)
 		return ERR_PTR(-ENOMEM);
 
 	for (kind = 0; kind < BPF_TRAMP_MAX; kind++) {
-		tprogs[kind].nr_progs = tr->progs_cnt[kind];
+		tlinks[kind].nr_links = tr->progs_cnt[kind];
 		*total += tr->progs_cnt[kind];
-		progs = tprogs[kind].progs;
+		links = tlinks[kind].links;
 
-		hlist_for_each_entry(aux, &tr->progs_hlist[kind], tramp_hlist) {
-			*ip_arg |= aux->prog->call_get_func_ip;
-			*progs++ = aux->prog;
+		hlist_for_each_entry(link, &tr->progs_hlist[kind], tramp_hlist) {
+			*ip_arg |= link->link.prog->call_get_func_ip;
+			*links++ = link;
 		}
 	}
-	return tprogs;
+	return tlinks;
 }
 
 static void __bpf_tramp_image_put_deferred(struct work_struct *work)
@@ -330,14 +330,14 @@ out:
 static int bpf_trampoline_update(struct bpf_trampoline *tr)
 {
 	struct bpf_tramp_image *im;
-	struct bpf_tramp_progs *tprogs;
+	struct bpf_tramp_links *tlinks;
 	u32 flags = BPF_TRAMP_F_RESTORE_REGS;
 	bool ip_arg = false;
 	int err, total;
 
-	tprogs = bpf_trampoline_get_progs(tr, &total, &ip_arg);
-	if (IS_ERR(tprogs))
-		return PTR_ERR(tprogs);
+	tlinks = bpf_trampoline_get_progs(tr, &total, &ip_arg);
+	if (IS_ERR(tlinks))
+		return PTR_ERR(tlinks);
 
 	if (total == 0) {
 		err = unregister_fentry(tr, tr->cur_image->image);
@@ -353,15 +353,15 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr)
 		goto out;
 	}
 
-	if (tprogs[BPF_TRAMP_FEXIT].nr_progs ||
-	    tprogs[BPF_TRAMP_MODIFY_RETURN].nr_progs)
+	if (tlinks[BPF_TRAMP_FEXIT].nr_links ||
+	    tlinks[BPF_TRAMP_MODIFY_RETURN].nr_links)
 		flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME;
 
 	if (ip_arg)
 		flags |= BPF_TRAMP_F_IP_ARG;
 
 	err = arch_prepare_bpf_trampoline(im, im->image, im->image + PAGE_SIZE,
-					  &tr->func.model, flags, tprogs,
+					  &tr->func.model, flags, tlinks,
 					  tr->func.addr);
 	if (err < 0)
 		goto out;
@@ -381,7 +381,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr)
 	tr->cur_image = im;
 	tr->selector++;
 out:
-	kfree(tprogs);
+	kfree(tlinks);
 	return err;
 }
 
@@ -407,13 +407,14 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog)
 	}
 }
 
-int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
+int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr)
 {
 	enum bpf_tramp_prog_type kind;
+	struct bpf_tramp_link *link_exiting;
 	int err = 0;
 	int cnt;
 
-	kind = bpf_attach_type_to_tramp(prog);
+	kind = bpf_attach_type_to_tramp(link->link.prog);
 	mutex_lock(&tr->mutex);
 	if (tr->extension_prog) {
 		/* cannot attach fentry/fexit if extension prog is attached.
@@ -429,25 +430,33 @@ int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
 			err = -EBUSY;
 			goto out;
 		}
-		tr->extension_prog = prog;
+		tr->extension_prog = link->link.prog;
 		err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP, NULL,
-					 prog->bpf_func);
+					 link->link.prog->bpf_func);
 		goto out;
 	}
-	if (cnt >= BPF_MAX_TRAMP_PROGS) {
+	if (cnt >= BPF_MAX_TRAMP_LINKS) {
 		err = -E2BIG;
 		goto out;
 	}
-	if (!hlist_unhashed(&prog->aux->tramp_hlist)) {
+	if (!hlist_unhashed(&link->tramp_hlist)) {
 		/* prog already linked */
 		err = -EBUSY;
 		goto out;
 	}
-	hlist_add_head(&prog->aux->tramp_hlist, &tr->progs_hlist[kind]);
+	hlist_for_each_entry(link_exiting, &tr->progs_hlist[kind], tramp_hlist) {
+		if (link_exiting->link.prog != link->link.prog)
+			continue;
+		/* prog already linked */
+		err = -EBUSY;
+		goto out;
+	}
+
+	hlist_add_head(&link->tramp_hlist, &tr->progs_hlist[kind]);
 	tr->progs_cnt[kind]++;
 	err = bpf_trampoline_update(tr);
 	if (err) {
-		hlist_del_init(&prog->aux->tramp_hlist);
+		hlist_del_init(&link->tramp_hlist);
 		tr->progs_cnt[kind]--;
 	}
 out:
@@ -456,12 +465,12 @@ out:
 }
 
 /* bpf_trampoline_unlink_prog() should never fail. */
-int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
+int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr)
 {
 	enum bpf_tramp_prog_type kind;
 	int err;
 
-	kind = bpf_attach_type_to_tramp(prog);
+	kind = bpf_attach_type_to_tramp(link->link.prog);
 	mutex_lock(&tr->mutex);
 	if (kind == BPF_TRAMP_REPLACE) {
 		WARN_ON_ONCE(!tr->extension_prog);
@@ -470,7 +479,7 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
 		tr->extension_prog = NULL;
 		goto out;
 	}
-	hlist_del_init(&prog->aux->tramp_hlist);
+	hlist_del_init(&link->tramp_hlist);
 	tr->progs_cnt[kind]--;
 	err = bpf_trampoline_update(tr);
 out:
@@ -635,7 +644,7 @@ void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr)
 int __weak
 arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end,
 			    const struct btf_func_model *m, u32 flags,
-			    struct bpf_tramp_progs *tprogs,
+			    struct bpf_tramp_links *tlinks,
 			    void *orig_call)
 {
 	return -ENOTSUPP;