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

Daniel Borkmann says:

====================
pull-request: bpf 2023-11-08

We've added 16 non-merge commits during the last 6 day(s) which contain
a total of 30 files changed, 341 insertions(+), 130 deletions(-).

The main changes are:

1) Fix a BPF verifier issue in precision tracking for BPF_ALU | BPF_TO_BE |
   BPF_END where the source register was incorrectly marked as precise,
   from Shung-Hsi Yu.

2) Fix a concurrency issue in bpf_timer where the former could still have
   been alive after an application releases or unpins the map, from Hou Tao.

3) Fix a BPF verifier issue where immediates are incorrectly cast to u32
   before being spilled and therefore losing sign information, from Hao Sun.

4) Fix a misplaced BPF_TRACE_ITER in check_css_task_iter_allowlist which
   incorrectly compared bpf_prog_type with bpf_attach_type, from Chuyi Zhou.

5) Add __bpf_hook_{start,end} as well as __bpf_kfunc_{start,end}_defs macros,
   migrate all BPF-related __diag callsites over to it, and add a new
   __diag_ignore_all for -Wmissing-declarations to the macros to address
   recent build warnings, from Dave Marchevsky.

6) Fix broken BPF selftest build of xdp_hw_metadata test on architectures
   where char is not signed, from Björn Töpel.

7) Fix test_maps selftest to properly use LIBBPF_OPTS() macro to initialize
   the bpf_map_create_opts, from Andrii Nakryiko.

8) Fix bpffs selftest to avoid unmounting /sys/kernel/debug as it may have
   been mounted and used by other applications already, from Manu Bretelle.

9) Fix a build issue without CONFIG_CGROUPS wrt css_task open-coded
   iterators, from Matthieu Baerts.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  selftests/bpf: get trusted cgrp from bpf_iter__cgroup directly
  bpf: Let verifier consider {task,cgroup} is trusted in bpf_iter_reg
  selftests/bpf: Fix broken build where char is unsigned
  selftests/bpf: precision tracking test for BPF_NEG and BPF_END
  bpf: Fix precision tracking for BPF_ALU | BPF_TO_BE | BPF_END
  selftests/bpf: Add test for using css_task iter in sleepable progs
  selftests/bpf: Add tests for css_task iter combining with cgroup iter
  bpf: Relax allowlist for css_task iter
  selftests/bpf: fix test_maps' use of bpf_map_create_opts
  bpf: Check map->usercnt after timer->timer is assigned
  bpf: Add __bpf_hook_{start,end} macros
  bpf: Add __bpf_kfunc_{start,end}_defs macros
  selftests/bpf: fix test_bpffs
  selftests/bpf: Add test for immediate spilled to stack
  bpf: Fix check_stack_write_fixed_off() to correctly spill imm
  bpf: fix compilation error without CGROUPS
====================

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

Author: kuba-moo

Documentation/bpf/kfuncs.rst

@@ -37,16 +37,14 @@ prototype in a header for the wrapper kfunc.
 An example is given below::
 
         /* Disables missing prototype warnings */
-        __diag_push();
-        __diag_ignore_all("-Wmissing-prototypes",
-                          "Global kfuncs as their definitions will be in BTF");
+        __bpf_kfunc_start_defs();
 
         __bpf_kfunc struct task_struct *bpf_find_get_task_by_vpid(pid_t nr)
         {
                 return find_get_task_by_vpid(nr);
         }
 
-        __diag_pop();
+        __bpf_kfunc_end_defs();
 
 A wrapper kfunc is often needed when we need to annotate parameters of the
 kfunc. Otherwise one may directly make the kfunc visible to the BPF program by

include/linux/btf.h

@@ -84,6 +84,17 @@
  */
 #define __bpf_kfunc __used noinline
 
+#define __bpf_kfunc_start_defs()					       \
+	__diag_push();							       \
+	__diag_ignore_all("-Wmissing-declarations",			       \
+			  "Global kfuncs as their definitions will be in BTF");\
+	__diag_ignore_all("-Wmissing-prototypes",			       \
+			  "Global kfuncs as their definitions will be in BTF")
+
+#define __bpf_kfunc_end_defs() __diag_pop()
+#define __bpf_hook_start() __bpf_kfunc_start_defs()
+#define __bpf_hook_end() __bpf_kfunc_end_defs()
+
 /*
  * Return the name of the passed struct, if exists, or halt the build if for
  * example the structure gets renamed. In this way, developers have to revisit

kernel/bpf/bpf_iter.c

@@ -782,9 +782,7 @@ struct bpf_iter_num_kern {
 	int end; /* final value, exclusive */
 } __aligned(8);
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc int bpf_iter_num_new(struct bpf_iter_num *it, int start, int end)
 {
@@ -843,4 +841,4 @@ __bpf_kfunc void bpf_iter_num_destroy(struct bpf_iter_num *it)
 	s->cur = s->end = 0;
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();

kernel/bpf/cgroup_iter.c

@@ -282,7 +282,7 @@ static struct bpf_iter_reg bpf_cgroup_reg_info = {
 	.ctx_arg_info_size	= 1,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__cgroup, cgroup),
-		  PTR_TO_BTF_ID_OR_NULL },
+		  PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
 	},
 	.seq_info		= &cgroup_iter_seq_info,
 };
@@ -305,9 +305,7 @@ struct bpf_iter_css_kern {
 	unsigned int flags;
 } __attribute__((aligned(8)));
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		"Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc int bpf_iter_css_new(struct bpf_iter_css *it,
 		struct cgroup_subsys_state *start, unsigned int flags)
@@ -358,4 +356,4 @@ __bpf_kfunc void bpf_iter_css_destroy(struct bpf_iter_css *it)
 {
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();

kernel/bpf/cpumask.c

@@ -34,9 +34,7 @@ static bool cpu_valid(u32 cpu)
 	return cpu < nr_cpu_ids;
 }
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global kfuncs as their definitions will be in BTF");
+__bpf_kfunc_start_defs();
 
 /**
  * bpf_cpumask_create() - Create a mutable BPF cpumask.
@@ -407,7 +405,7 @@ __bpf_kfunc u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1,
 	return cpumask_any_and_distribute(src1, src2);
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(cpumask_kfunc_btf_ids)
 BTF_ID_FLAGS(func, bpf_cpumask_create, KF_ACQUIRE | KF_RET_NULL)

kernel/bpf/helpers.c

@@ -1177,13 +1177,6 @@ BPF_CALL_3(bpf_timer_init, struct bpf_timer_kern *, timer, struct bpf_map *, map
 		ret = -EBUSY;
 		goto out;
 	}
-	if (!atomic64_read(&map->usercnt)) {
-		/* maps with timers must be either held by user space
-		 * or pinned in bpffs.
-		 */
-		ret = -EPERM;
-		goto out;
-	}
 	/* allocate hrtimer via map_kmalloc to use memcg accounting */
 	t = bpf_map_kmalloc_node(map, sizeof(*t), GFP_ATOMIC, map->numa_node);
 	if (!t) {
@@ -1196,7 +1189,21 @@ BPF_CALL_3(bpf_timer_init, struct bpf_timer_kern *, timer, struct bpf_map *, map
 	rcu_assign_pointer(t->callback_fn, NULL);
 	hrtimer_init(&t->timer, clockid, HRTIMER_MODE_REL_SOFT);
 	t->timer.function = bpf_timer_cb;
-	timer->timer = t;
+	WRITE_ONCE(timer->timer, t);
+	/* Guarantee the order between timer->timer and map->usercnt. So
+	 * when there are concurrent uref release and bpf timer init, either
+	 * bpf_timer_cancel_and_free() called by uref release reads a no-NULL
+	 * timer or atomic64_read() below returns a zero usercnt.
+	 */
+	smp_mb();
+	if (!atomic64_read(&map->usercnt)) {
+		/* maps with timers must be either held by user space
+		 * or pinned in bpffs.
+		 */
+		WRITE_ONCE(timer->timer, NULL);
+		kfree(t);
+		ret = -EPERM;
+	}
 out:
 	__bpf_spin_unlock_irqrestore(&timer->lock);
 	return ret;
@@ -1374,7 +1381,7 @@ void bpf_timer_cancel_and_free(void *val)
 	/* The subsequent bpf_timer_start/cancel() helpers won't be able to use
 	 * this timer, since it won't be initialized.
 	 */
-	timer->timer = NULL;
+	WRITE_ONCE(timer->timer, NULL);
 out:
 	__bpf_spin_unlock_irqrestore(&timer->lock);
 	if (!t)
@@ -1886,9 +1893,7 @@ void bpf_rb_root_free(const struct btf_field *field, void *rb_root,
 	}
 }
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign)
 {
@@ -2505,7 +2510,7 @@ __bpf_kfunc void bpf_throw(u64 cookie)
 	WARN(1, "A call to BPF exception callback should never return\n");
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(generic_btf_ids)
 #ifdef CONFIG_KEXEC_CORE
@@ -2564,15 +2569,17 @@ BTF_ID_FLAGS(func, bpf_iter_num_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_iter_task_vma_new, KF_ITER_NEW | KF_RCU)
 BTF_ID_FLAGS(func, bpf_iter_task_vma_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_task_vma_destroy, KF_ITER_DESTROY)
+#ifdef CONFIG_CGROUPS
 BTF_ID_FLAGS(func, bpf_iter_css_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS)
 BTF_ID_FLAGS(func, bpf_iter_css_task_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY)
-BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED)
-BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL)
-BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_iter_css_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED)
 BTF_ID_FLAGS(func, bpf_iter_css_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_css_destroy, KF_ITER_DESTROY)
+#endif
+BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED)
+BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_dynptr_adjust)
 BTF_ID_FLAGS(func, bpf_dynptr_is_null)
 BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly)

kernel/bpf/map_iter.c

@@ -193,9 +193,7 @@ static int __init bpf_map_iter_init(void)
 
 late_initcall(bpf_map_iter_init);
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc s64 bpf_map_sum_elem_count(const struct bpf_map *map)
 {
@@ -213,7 +211,7 @@ __bpf_kfunc s64 bpf_map_sum_elem_count(const struct bpf_map *map)
 	return ret;
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(bpf_map_iter_kfunc_ids)
 BTF_ID_FLAGS(func, bpf_map_sum_elem_count, KF_TRUSTED_ARGS)

kernel/bpf/task_iter.c

@@ -704,7 +704,7 @@ static struct bpf_iter_reg task_reg_info = {
 	.ctx_arg_info_size	= 1,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__task, task),
-		  PTR_TO_BTF_ID_OR_NULL },
+		  PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
 	},
 	.seq_info		= &task_seq_info,
 	.fill_link_info		= bpf_iter_fill_link_info,
@@ -822,9 +822,7 @@ struct bpf_iter_task_vma_kern {
 	struct bpf_iter_task_vma_kern_data *data;
 } __attribute__((aligned(8)));
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it,
 				      struct task_struct *task, u64 addr)
@@ -890,7 +888,9 @@ __bpf_kfunc void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it)
 	}
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
+
+#ifdef CONFIG_CGROUPS
 
 struct bpf_iter_css_task {
 	__u64 __opaque[1];
@@ -900,9 +900,7 @@ struct bpf_iter_css_task_kern {
 	struct css_task_iter *css_it;
 } __attribute__((aligned(8)));
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc int bpf_iter_css_task_new(struct bpf_iter_css_task *it,
 		struct cgroup_subsys_state *css, unsigned int flags)
@@ -948,7 +946,9 @@ __bpf_kfunc void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it)
 	bpf_mem_free(&bpf_global_ma, kit->css_it);
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
+
+#endif /* CONFIG_CGROUPS */
 
 struct bpf_iter_task {
 	__u64 __opaque[3];
@@ -969,9 +969,7 @@ enum {
 	BPF_TASK_ITER_PROC_THREADS
 };
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it,
 		struct task_struct *task__nullable, unsigned int flags)
@@ -1041,7 +1039,7 @@ __bpf_kfunc void bpf_iter_task_destroy(struct bpf_iter_task *it)
 {
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work);
 

kernel/bpf/verifier.c

@@ -3742,7 +3742,12 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 	if (class == BPF_ALU || class == BPF_ALU64) {
 		if (!bt_is_reg_set(bt, dreg))
 			return 0;
-		if (opcode == BPF_MOV) {
+		if (opcode == BPF_END || opcode == BPF_NEG) {
+			/* sreg is reserved and unused
+			 * dreg still need precision before this insn
+			 */
+			return 0;
+		} else if (opcode == BPF_MOV) {
 			if (BPF_SRC(insn->code) == BPF_X) {
 				/* dreg = sreg or dreg = (s8, s16, s32)sreg
 				 * dreg needs precision after this insn
@@ -4674,7 +4679,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 		   insn->imm != 0 && env->bpf_capable) {
 		struct bpf_reg_state fake_reg = {};
 
-		__mark_reg_known(&fake_reg, (u32)insn->imm);
+		__mark_reg_known(&fake_reg, insn->imm);
 		fake_reg.type = SCALAR_VALUE;
 		save_register_state(state, spi, &fake_reg, size);
 	} else if (reg && is_spillable_regtype(reg->type)) {
@@ -5388,7 +5393,9 @@ static bool in_rcu_cs(struct bpf_verifier_env *env)
 /* Once GCC supports btf_type_tag the following mechanism will be replaced with tag check */
 BTF_SET_START(rcu_protected_types)
 BTF_ID(struct, prog_test_ref_kfunc)
+#ifdef CONFIG_CGROUPS
 BTF_ID(struct, cgroup)
+#endif
 BTF_ID(struct, bpf_cpumask)
 BTF_ID(struct, task_struct)
 BTF_SET_END(rcu_protected_types)
@@ -10835,7 +10842,9 @@ BTF_ID(func, bpf_dynptr_clone)
 BTF_ID(func, bpf_percpu_obj_new_impl)
 BTF_ID(func, bpf_percpu_obj_drop_impl)
 BTF_ID(func, bpf_throw)
+#ifdef CONFIG_CGROUPS
 BTF_ID(func, bpf_iter_css_task_new)
+#endif
 BTF_SET_END(special_kfunc_set)
 
 BTF_ID_LIST(special_kfunc_list)
@@ -10861,7 +10870,11 @@ BTF_ID(func, bpf_dynptr_clone)
 BTF_ID(func, bpf_percpu_obj_new_impl)
 BTF_ID(func, bpf_percpu_obj_drop_impl)
 BTF_ID(func, bpf_throw)
+#ifdef CONFIG_CGROUPS
 BTF_ID(func, bpf_iter_css_task_new)
+#else
+BTF_ID_UNUSED
+#endif
 
 static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta)
 {
@@ -11394,17 +11407,25 @@ static int process_kf_arg_ptr_to_rbtree_node(struct bpf_verifier_env *env,
 						  &meta->arg_rbtree_root.field);
 }
 
+/*
+ * css_task iter allowlist is needed to avoid dead locking on css_set_lock.
+ * LSM hooks and iters (both sleepable and non-sleepable) are safe.
+ * Any sleepable progs are also safe since bpf_check_attach_target() enforce
+ * them can only be attached to some specific hook points.
+ */
 static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env)
 {
 	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
 
 	switch (prog_type) {
 	case BPF_PROG_TYPE_LSM:
 		return true;
-	case BPF_TRACE_ITER:
-		return env->prog->aux->sleepable;
+	case BPF_PROG_TYPE_TRACING:
+		if (env->prog->expected_attach_type == BPF_TRACE_ITER)
+			return true;
+		fallthrough;
 	default:
-		return false;
+		return env->prog->aux->sleepable;
 	}
 }
 
@@ -11663,7 +11684,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 		case KF_ARG_PTR_TO_ITER:
 			if (meta->func_id == special_kfunc_list[KF_bpf_iter_css_task_new]) {
 				if (!check_css_task_iter_allowlist(env)) {
-					verbose(env, "css_task_iter is only allowed in bpf_lsm and bpf iter-s\n");
+					verbose(env, "css_task_iter is only allowed in bpf_lsm, bpf_iter and sleepable progs\n");
 					return -EINVAL;
 				}
 			}

kernel/cgroup/rstat.c

@@ -156,19 +156,16 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
  * optimize away the callsite. Therefore, __weak is needed to ensure that the
  * call is still emitted, by telling the compiler that we don't know what the
  * function might eventually be.
- *
- * __diag_* below are needed to dismiss the missing prototype warning.
  */
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "kfuncs which will be used in BPF programs");
+
+__bpf_hook_start();
 
 __weak noinline void bpf_rstat_flush(struct cgroup *cgrp,
 				     struct cgroup *parent, int cpu)
 {
 }
 
-__diag_pop();
+__bpf_hook_end();
 
 /* see cgroup_rstat_flush() */
 static void cgroup_rstat_flush_locked(struct cgroup *cgrp)