Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2024-06-06

We've added 54 non-merge commits during the last 10 day(s) which contain
a total of 50 files changed, 1887 insertions(+), 527 deletions(-).

The main changes are:

1) Add a user space notification mechanism via epoll when a struct_ops
   object is getting detached/unregistered, from Kui-Feng Lee.

2) Big batch of BPF selftest refactoring for sockmap and BPF congctl
   tests, from Geliang Tang.

3) Add BTF field (type and string fields, right now) iterator support
   to libbpf instead of using existing callback-based approaches,
   from Andrii Nakryiko.

4) Extend BPF selftests for the latter with a new btf_field_iter
   selftest, from Alan Maguire.

5) Add new kfuncs for a generic, open-coded bits iterator,
   from Yafang Shao.

6) Fix BPF selftests' kallsyms_find() helper under kernels configured
   with CONFIG_LTO_CLANG_THIN, from Yonghong Song.

7) Remove a bunch of unused structs in BPF selftests,
   from David Alan Gilbert.

8) Convert test_sockmap section names into names understood by libbpf
   so it can deduce program type and attach type, from Jakub Sitnicki.

9) Extend libbpf with the ability to configure log verbosity
   via LIBBPF_LOG_LEVEL environment variable, from Mykyta Yatsenko.

10) Fix BPF selftests with regards to bpf_cookie and find_vma flakiness
    in nested VMs, from Song Liu.

11) Extend riscv32/64 JITs to introduce shift/add helpers to generate Zba
    optimization, from Xiao Wang.

12) Enable BPF programs to declare arrays and struct fields with kptr,
    bpf_rb_root, and bpf_list_head, from Kui-Feng Lee.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (54 commits)
  selftests/bpf: Drop useless arguments of do_test in bpf_tcp_ca
  selftests/bpf: Use start_test in test_dctcp in bpf_tcp_ca
  selftests/bpf: Use start_test in test_dctcp_fallback in bpf_tcp_ca
  selftests/bpf: Add start_test helper in bpf_tcp_ca
  selftests/bpf: Use connect_to_fd_opts in do_test in bpf_tcp_ca
  libbpf: Auto-attach struct_ops BPF maps in BPF skeleton
  selftests/bpf: Add btf_field_iter selftests
  selftests/bpf: Fix send_signal test with nested CONFIG_PARAVIRT
  libbpf: Remove callback-based type/string BTF field visitor helpers
  bpftool: Use BTF field iterator in btfgen
  libbpf: Make use of BTF field iterator in BTF handling code
  libbpf: Make use of BTF field iterator in BPF linker code
  libbpf: Add BTF field iterator
  selftests/bpf: Ignore .llvm.<hash> suffix in kallsyms_find()
  selftests/bpf: Fix bpf_cookie and find_vma in nested VM
  selftests/bpf: Test global bpf_list_head arrays.
  selftests/bpf: Test global bpf_rb_root arrays and fields in nested struct types.
  selftests/bpf: Test kptr arrays and kptrs in nested struct fields.
  bpf: limit the number of levels of a nested struct type.
  bpf: look into the types of the fields of a struct type recursively.
  ...
====================

Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: kuba-moo

Documentation/bpf/libbpf/libbpf_overview.rst

@@ -219,6 +219,14 @@ compilation and skeleton generation. Using Libbpf-rs will make building user
 space part of the BPF application easier. Note that the BPF program themselves
 must still be written in plain C.
 
+libbpf logging
+==============
+
+By default, libbpf logs informational and warning messages to stderr. The
+verbosity of these messages can be controlled by setting the environment
+variable LIBBPF_LOG_LEVEL to either warn, info, or debug. A custom log
+callback can be set using ``libbpf_set_print()``.
+
 Additional Documentation
 ========================
 

arch/riscv/net/bpf_jit.h

@@ -742,6 +742,17 @@ static inline u16 rvc_swsp(u32 imm8, u8 rs2)
 	return rv_css_insn(0x6, imm, rs2, 0x2);
 }
 
+/* RVZBA instructions. */
+static inline u32 rvzba_sh2add(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(0x10, rs2, rs1, 0x4, rd, 0x33);
+}
+
+static inline u32 rvzba_sh3add(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(0x10, rs2, rs1, 0x6, rd, 0x33);
+}
+
 /* RVZBB instructions. */
 static inline u32 rvzbb_sextb(u8 rd, u8 rs1)
 {
@@ -1095,6 +1106,28 @@ static inline void emit_sw(u8 rs1, s32 off, u8 rs2, struct rv_jit_context *ctx)
 		emit(rv_sw(rs1, off, rs2), ctx);
 }
 
+static inline void emit_sh2add(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvzba_enabled()) {
+		emit(rvzba_sh2add(rd, rs1, rs2), ctx);
+		return;
+	}
+
+	emit_slli(rd, rs1, 2, ctx);
+	emit_add(rd, rd, rs2, ctx);
+}
+
+static inline void emit_sh3add(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvzba_enabled()) {
+		emit(rvzba_sh3add(rd, rs1, rs2), ctx);
+		return;
+	}
+
+	emit_slli(rd, rs1, 3, ctx);
+	emit_add(rd, rd, rs2, ctx);
+}
+
 /* RV64-only helper functions. */
 #if __riscv_xlen == 64
 

arch/riscv/net/bpf_jit_comp32.c

@@ -811,8 +811,7 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx)
 	 * if (!prog)
 	 *   goto out;
 	 */
-	emit(rv_slli(RV_REG_T0, lo(idx_reg), 2), ctx);
-	emit(rv_add(RV_REG_T0, RV_REG_T0, lo(arr_reg)), ctx);
+	emit_sh2add(RV_REG_T0, lo(idx_reg), lo(arr_reg), ctx);
 	off = offsetof(struct bpf_array, ptrs);
 	if (is_12b_check(off, insn))
 		return -1;

arch/riscv/net/bpf_jit_comp64.c

@@ -380,8 +380,7 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx)
 	 * if (!prog)
 	 *     goto out;
 	 */
-	emit_slli(RV_REG_T2, RV_REG_A2, 3, ctx);
-	emit_add(RV_REG_T2, RV_REG_T2, RV_REG_A1, ctx);
+	emit_sh3add(RV_REG_T2, RV_REG_A2, RV_REG_A1, ctx);
 	off = offsetof(struct bpf_array, ptrs);
 	if (is_12b_check(off, insn))
 		return -1;
@@ -1099,12 +1098,10 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			/* Load current CPU number in T1 */
 			emit_ld(RV_REG_T1, offsetof(struct thread_info, cpu),
 				RV_REG_TP, ctx);
-			/* << 3 because offsets are 8 bytes */
-			emit_slli(RV_REG_T1, RV_REG_T1, 3, ctx);
 			/* Load address of __per_cpu_offset array in T2 */
 			emit_addr(RV_REG_T2, (u64)&__per_cpu_offset, extra_pass, ctx);
-			/* Add offset of current CPU to  __per_cpu_offset */
-			emit_add(RV_REG_T1, RV_REG_T2, RV_REG_T1, ctx);
+			/* Get address of __per_cpu_offset[cpu] in T1 */
+			emit_sh3add(RV_REG_T1, RV_REG_T1, RV_REG_T2, ctx);
 			/* Load __per_cpu_offset[cpu] in T1 */
 			emit_ld(RV_REG_T1, 0, RV_REG_T1, ctx);
 			/* Add the offset to Rd */

include/linux/bpf.h

@@ -1612,6 +1612,7 @@ struct bpf_link_ops {
 			      struct bpf_link_info *info);
 	int (*update_map)(struct bpf_link *link, struct bpf_map *new_map,
 			  struct bpf_map *old_map);
+	__poll_t (*poll)(struct file *file, struct poll_table_struct *pts);
 };
 
 struct bpf_tramp_link {
@@ -1730,9 +1731,9 @@ struct bpf_struct_ops {
 	int (*init_member)(const struct btf_type *t,
 			   const struct btf_member *member,
 			   void *kdata, const void *udata);
-	int (*reg)(void *kdata);
-	void (*unreg)(void *kdata);
-	int (*update)(void *kdata, void *old_kdata);
+	int (*reg)(void *kdata, struct bpf_link *link);
+	void (*unreg)(void *kdata, struct bpf_link *link);
+	int (*update)(void *kdata, void *old_kdata, struct bpf_link *link);
 	int (*validate)(void *kdata);
 	void *cfi_stubs;
 	struct module *owner;
@@ -2333,6 +2334,7 @@ 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);
+struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link);
 void bpf_link_put(struct bpf_link *link);
 int bpf_link_new_fd(struct bpf_link *link);
 struct bpf_link *bpf_link_get_from_fd(u32 ufd);
@@ -2704,6 +2706,11 @@ static inline void bpf_link_inc(struct bpf_link *link)
 {
 }
 
+static inline struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link)
+{
+	return NULL;
+}
+
 static inline void bpf_link_put(struct bpf_link *link)
 {
 }

kernel/bpf/bpf_struct_ops.c

@@ -12,6 +12,7 @@
 #include <linux/mutex.h>
 #include <linux/btf_ids.h>
 #include <linux/rcupdate_wait.h>
+#include <linux/poll.h>
 
 struct bpf_struct_ops_value {
 	struct bpf_struct_ops_common_value common;
@@ -56,6 +57,7 @@ struct bpf_struct_ops_map {
 struct bpf_struct_ops_link {
 	struct bpf_link link;
 	struct bpf_map __rcu *map;
+	wait_queue_head_t wait_hup;
 };
 
 static DEFINE_MUTEX(update_mutex);
@@ -757,7 +759,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 		goto unlock;
 	}
 
-	err = st_ops->reg(kdata);
+	err = st_ops->reg(kdata, NULL);
 	if (likely(!err)) {
 		/* This refcnt increment on the map here after
 		 * 'st_ops->reg()' is secure since the state of the
@@ -805,7 +807,7 @@ static long bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key)
 			     BPF_STRUCT_OPS_STATE_TOBEFREE);
 	switch (prev_state) {
 	case BPF_STRUCT_OPS_STATE_INUSE:
-		st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data);
+		st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data, NULL);
 		bpf_map_put(map);
 		return 0;
 	case BPF_STRUCT_OPS_STATE_TOBEFREE:
@@ -1057,10 +1059,7 @@ static void bpf_struct_ops_map_link_dealloc(struct bpf_link *link)
 	st_map = (struct bpf_struct_ops_map *)
 		rcu_dereference_protected(st_link->map, true);
 	if (st_map) {
-		/* st_link->map can be NULL if
-		 * bpf_struct_ops_link_create() fails to register.
-		 */
-		st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data);
+		st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data, link);
 		bpf_map_put(&st_map->map);
 	}
 	kfree(st_link);
@@ -1075,7 +1074,8 @@ static void bpf_struct_ops_map_link_show_fdinfo(const struct bpf_link *link,
 	st_link = container_of(link, struct bpf_struct_ops_link, link);
 	rcu_read_lock();
 	map = rcu_dereference(st_link->map);
-	seq_printf(seq, "map_id:\t%d\n", map->id);
+	if (map)
+		seq_printf(seq, "map_id:\t%d\n", map->id);
 	rcu_read_unlock();
 }
 
@@ -1088,7 +1088,8 @@ static int bpf_struct_ops_map_link_fill_link_info(const struct bpf_link *link,
 	st_link = container_of(link, struct bpf_struct_ops_link, link);
 	rcu_read_lock();
 	map = rcu_dereference(st_link->map);
-	info->struct_ops.map_id = map->id;
+	if (map)
+		info->struct_ops.map_id = map->id;
 	rcu_read_unlock();
 	return 0;
 }
@@ -1113,6 +1114,10 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map
 	mutex_lock(&update_mutex);
 
 	old_map = rcu_dereference_protected(st_link->map, lockdep_is_held(&update_mutex));
+	if (!old_map) {
+		err = -ENOLINK;
+		goto err_out;
+	}
 	if (expected_old_map && old_map != expected_old_map) {
 		err = -EPERM;
 		goto err_out;
@@ -1125,7 +1130,7 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map
 		goto err_out;
 	}
 
-	err = st_map->st_ops_desc->st_ops->update(st_map->kvalue.data, old_st_map->kvalue.data);
+	err = st_map->st_ops_desc->st_ops->update(st_map->kvalue.data, old_st_map->kvalue.data, link);
 	if (err)
 		goto err_out;
 
@@ -1139,11 +1144,53 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map
 	return err;
 }
 
+static int bpf_struct_ops_map_link_detach(struct bpf_link *link)
+{
+	struct bpf_struct_ops_link *st_link = container_of(link, struct bpf_struct_ops_link, link);
+	struct bpf_struct_ops_map *st_map;
+	struct bpf_map *map;
+
+	mutex_lock(&update_mutex);
+
+	map = rcu_dereference_protected(st_link->map, lockdep_is_held(&update_mutex));
+	if (!map) {
+		mutex_unlock(&update_mutex);
+		return 0;
+	}
+	st_map = container_of(map, struct bpf_struct_ops_map, map);
+
+	st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data, link);
+
+	RCU_INIT_POINTER(st_link->map, NULL);
+	/* Pair with bpf_map_get() in bpf_struct_ops_link_create() or
+	 * bpf_map_inc() in bpf_struct_ops_map_link_update().
+	 */
+	bpf_map_put(&st_map->map);
+
+	mutex_unlock(&update_mutex);
+
+	wake_up_interruptible_poll(&st_link->wait_hup, EPOLLHUP);
+
+	return 0;
+}
+
+static __poll_t bpf_struct_ops_map_link_poll(struct file *file,
+					     struct poll_table_struct *pts)
+{
+	struct bpf_struct_ops_link *st_link = file->private_data;
+
+	poll_wait(file, &st_link->wait_hup, pts);
+
+	return rcu_access_pointer(st_link->map) ? 0 : EPOLLHUP;
+}
+
 static const struct bpf_link_ops bpf_struct_ops_map_lops = {
 	.dealloc = bpf_struct_ops_map_link_dealloc,
+	.detach = bpf_struct_ops_map_link_detach,
 	.show_fdinfo = bpf_struct_ops_map_link_show_fdinfo,
 	.fill_link_info = bpf_struct_ops_map_link_fill_link_info,
 	.update_map = bpf_struct_ops_map_link_update,
+	.poll = bpf_struct_ops_map_link_poll,
 };
 
 int bpf_struct_ops_link_create(union bpf_attr *attr)
@@ -1176,13 +1223,21 @@ int bpf_struct_ops_link_create(union bpf_attr *attr)
 	if (err)
 		goto err_out;
 
-	err = st_map->st_ops_desc->st_ops->reg(st_map->kvalue.data);
+	init_waitqueue_head(&link->wait_hup);
+
+	/* Hold the update_mutex such that the subsystem cannot
+	 * do link->ops->detach() before the link is fully initialized.
+	 */
+	mutex_lock(&update_mutex);
+	err = st_map->st_ops_desc->st_ops->reg(st_map->kvalue.data, &link->link);
 	if (err) {
+		mutex_unlock(&update_mutex);
 		bpf_link_cleanup(&link_primer);
 		link = NULL;
 		goto err_out;
 	}
 	RCU_INIT_POINTER(link->map, map);
+	mutex_unlock(&update_mutex);
 
 	return bpf_link_settle(&link_primer);