Merge tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Pull bpf fixes from Alexei Starovoitov:

 - Fix interaction between livepatch and BPF fexit programs (Song Liu)
   With Steven and Masami acks.

 - Fix stack ORC unwind from BPF kprobe_multi (Jiri Olsa)
   With Steven and Masami acks.

 - Fix out of bounds access in widen_imprecise_scalars() in the verifier
   (Eduard Zingerman)

 - Fix conflicts between MPTCP and BPF sockmap (Jiayuan Chen)

 - Fix net_sched storage collision with BPF data_meta/data_end (Eric
   Dumazet)

 - Add _impl suffix to BPF kfuncs with implicit args to avoid breaking
   them in bpf-next when KF_IMPLICIT_ARGS is added (Mykyta Yatsenko)

* tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  selftests/bpf: Test widen_imprecise_scalars() with different stack depth
  bpf: account for current allocated stack depth in widen_imprecise_scalars()
  bpf: Add bpf_prog_run_data_pointers()
  selftests/bpf: Add mptcp test with sockmap
  mptcp: Fix proto fallback detection with BPF
  mptcp: Disallow MPTCP subflows from sockmap
  selftests/bpf: Add stacktrace ips test for raw_tp
  selftests/bpf: Add stacktrace ips test for kprobe_multi/kretprobe_multi
  x86/fgraph,bpf: Fix stack ORC unwind from kprobe_multi return probe
  Revert "perf/x86: Always store regs->ip in perf_callchain_kernel()"
  bpf: add _impl suffix for bpf_stream_vprintk() kfunc
  bpf:add _impl suffix for bpf_task_work_schedule* kfuncs
  selftests/bpf: Add tests for livepatch + bpf trampoline
  ftrace: bpf: Fix IPMODIFY + DIRECT in modify_ftrace_direct()
  ftrace: Fix BPF fexit with livepatch

5 files changed, 72 insertions, 40 deletions

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index eb25e70e0bdc..e4007fea4909 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -4169,7 +4169,8 @@ release_prog:
 }
 
 /**
- * bpf_task_work_schedule_signal - Schedule BPF callback using task_work_add with TWA_SIGNAL mode
+ * bpf_task_work_schedule_signal_impl - Schedule BPF callback using task_work_add with TWA_SIGNAL
+ * mode
  * @task: Task struct for which callback should be scheduled
  * @tw: Pointer to struct bpf_task_work in BPF map value for internal bookkeeping
  * @map__map: bpf_map that embeds struct bpf_task_work in the values
@@ -4178,15 +4179,17 @@ release_prog:
  *
  * Return: 0 if task work has been scheduled successfully, negative error code otherwise
  */
-__bpf_kfunc int bpf_task_work_schedule_signal(struct task_struct *task, struct bpf_task_work *tw,
-					      void *map__map, bpf_task_work_callback_t callback,
-					      void *aux__prog)
+__bpf_kfunc int bpf_task_work_schedule_signal_impl(struct task_struct *task,
+						   struct bpf_task_work *tw, void *map__map,
+						   bpf_task_work_callback_t callback,
+						   void *aux__prog)
 {
 	return bpf_task_work_schedule(task, tw, map__map, callback, aux__prog, TWA_SIGNAL);
 }
 
 /**
- * bpf_task_work_schedule_resume - Schedule BPF callback using task_work_add with TWA_RESUME mode
+ * bpf_task_work_schedule_resume_impl - Schedule BPF callback using task_work_add with TWA_RESUME
+ * mode
  * @task: Task struct for which callback should be scheduled
  * @tw: Pointer to struct bpf_task_work in BPF map value for internal bookkeeping
  * @map__map: bpf_map that embeds struct bpf_task_work in the values
@@ -4195,9 +4198,10 @@ __bpf_kfunc int bpf_task_work_schedule_signal(struct task_struct *task, struct b
  *
  * Return: 0 if task work has been scheduled successfully, negative error code otherwise
  */
-__bpf_kfunc int bpf_task_work_schedule_resume(struct task_struct *task, struct bpf_task_work *tw,
-					      void *map__map, bpf_task_work_callback_t callback,
-					      void *aux__prog)
+__bpf_kfunc int bpf_task_work_schedule_resume_impl(struct task_struct *task,
+						   struct bpf_task_work *tw, void *map__map,
+						   bpf_task_work_callback_t callback,
+						   void *aux__prog)
 {
 	return bpf_task_work_schedule(task, tw, map__map, callback, aux__prog, TWA_RESUME);
 }
@@ -4376,9 +4380,9 @@ BTF_ID_FLAGS(func, bpf_strnstr);
 #if defined(CONFIG_BPF_LSM) && defined(CONFIG_CGROUPS)
 BTF_ID_FLAGS(func, bpf_cgroup_read_xattr, KF_RCU)
 #endif
-BTF_ID_FLAGS(func, bpf_stream_vprintk, KF_TRUSTED_ARGS)
-BTF_ID_FLAGS(func, bpf_task_work_schedule_signal, KF_TRUSTED_ARGS)
-BTF_ID_FLAGS(func, bpf_task_work_schedule_resume, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_stream_vprintk_impl, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_task_work_schedule_signal_impl, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_task_work_schedule_resume_impl, KF_TRUSTED_ARGS)
 BTF_KFUNCS_END(common_btf_ids)
 
 static const struct btf_kfunc_id_set common_kfunc_set = {
diff --git a/kernel/bpf/stream.c b/kernel/bpf/stream.c
index eb6c5a21c2ef..ff16c631951b 100644
--- a/kernel/bpf/stream.c
+++ b/kernel/bpf/stream.c
@@ -355,7 +355,8 @@ __bpf_kfunc_start_defs();
  * Avoid using enum bpf_stream_id so that kfunc users don't have to pull in the
  * enum in headers.
  */
-__bpf_kfunc int bpf_stream_vprintk(int stream_id, const char *fmt__str, const void *args, u32 len__sz, void *aux__prog)
+__bpf_kfunc int bpf_stream_vprintk_impl(int stream_id, const char *fmt__str, const void *args,
+					u32 len__sz, void *aux__prog)
 {
 	struct bpf_bprintf_data data = {
 		.get_bin_args	= true,
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 5949095e51c3..f2cb0b097093 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -479,11 +479,6 @@ again:
 		 * BPF_TRAMP_F_SHARE_IPMODIFY is set, we can generate the
 		 * trampoline again, and retry register.
 		 */
-		/* reset fops->func and fops->trampoline for re-register */
-		tr->fops->func = NULL;
-		tr->fops->trampoline = 0;
-
-		/* free im memory and reallocate later */
 		bpf_tramp_image_free(im);
 		goto again;
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index ff40e5e65c43..fbe4bb91c564 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -8866,7 +8866,7 @@ static int widen_imprecise_scalars(struct bpf_verifier_env *env,
 				   struct bpf_verifier_state *cur)
 {
 	struct bpf_func_state *fold, *fcur;
-	int i, fr;
+	int i, fr, num_slots;
 
 	reset_idmap_scratch(env);
 	for (fr = old->curframe; fr >= 0; fr--) {
@@ -8879,7 +8879,9 @@ static int widen_imprecise_scalars(struct bpf_verifier_env *env,
 					&fcur->regs[i],
 					&env->idmap_scratch);
 
-		for (i = 0; i < fold->allocated_stack / BPF_REG_SIZE; i++) {
+		num_slots = min(fold->allocated_stack / BPF_REG_SIZE,
+				fcur->allocated_stack / BPF_REG_SIZE);
+		for (i = 0; i < num_slots; i++) {
 			if (!is_spilled_reg(&fold->stack[i]) ||
 			    !is_spilled_reg(&fcur->stack[i]))
 				continue;
@@ -12259,8 +12261,8 @@ enum special_kfunc_type {
 	KF_bpf_res_spin_lock_irqsave,
 	KF_bpf_res_spin_unlock_irqrestore,
 	KF___bpf_trap,
-	KF_bpf_task_work_schedule_signal,
-	KF_bpf_task_work_schedule_resume,
+	KF_bpf_task_work_schedule_signal_impl,
+	KF_bpf_task_work_schedule_resume_impl,
 };
 
 BTF_ID_LIST(special_kfunc_list)
@@ -12331,13 +12333,13 @@ BTF_ID(func, bpf_res_spin_unlock)
 BTF_ID(func, bpf_res_spin_lock_irqsave)
 BTF_ID(func, bpf_res_spin_unlock_irqrestore)
 BTF_ID(func, __bpf_trap)
-BTF_ID(func, bpf_task_work_schedule_signal)
-BTF_ID(func, bpf_task_work_schedule_resume)
+BTF_ID(func, bpf_task_work_schedule_signal_impl)
+BTF_ID(func, bpf_task_work_schedule_resume_impl)
 
 static bool is_task_work_add_kfunc(u32 func_id)
 {
-	return func_id == special_kfunc_list[KF_bpf_task_work_schedule_signal] ||
-	       func_id == special_kfunc_list[KF_bpf_task_work_schedule_resume];
+	return func_id == special_kfunc_list[KF_bpf_task_work_schedule_signal_impl] ||
+	       func_id == special_kfunc_list[KF_bpf_task_work_schedule_resume_impl];
 }
 
 static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 42bd2ba68a82..59cfacb8a5bb 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1971,7 +1971,8 @@ static void ftrace_hash_rec_enable_modify(struct ftrace_ops *ops)
  */
 static int __ftrace_hash_update_ipmodify(struct ftrace_ops *ops,
 					 struct ftrace_hash *old_hash,
-					 struct ftrace_hash *new_hash)
+					 struct ftrace_hash *new_hash,
+					 bool update_target)
 {
 	struct ftrace_page *pg;
 	struct dyn_ftrace *rec, *end = NULL;
@@ -2006,10 +2007,13 @@ static int __ftrace_hash_update_ipmodify(struct ftrace_ops *ops,
 		if (rec->flags & FTRACE_FL_DISABLED)
 			continue;
 
-		/* We need to update only differences of filter_hash */
+		/*
+		 * Unless we are updating the target of a direct function,
+		 * we only need to update differences of filter_hash
+		 */
 		in_old = !!ftrace_lookup_ip(old_hash, rec->ip);
 		in_new = !!ftrace_lookup_ip(new_hash, rec->ip);
-		if (in_old == in_new)
+		if (!update_target && (in_old == in_new))
 			continue;
 
 		if (in_new) {
@@ -2020,7 +2024,16 @@ static int __ftrace_hash_update_ipmodify(struct ftrace_ops *ops,
 				if (is_ipmodify)
 					goto rollback;
 
-				FTRACE_WARN_ON(rec->flags & FTRACE_FL_DIRECT);
+				/*
+				 * If this is called by __modify_ftrace_direct()
+				 * then it is only changing where the direct
+				 * pointer is jumping to, and the record already
+				 * points to a direct trampoline. If it isn't,
+				 * then it is a bug to update ipmodify on a direct
+				 * caller.
+				 */
+				FTRACE_WARN_ON(!update_target &&
+					       (rec->flags & FTRACE_FL_DIRECT));
 
 				/*
 				 * Another ops with IPMODIFY is already
@@ -2076,7 +2089,7 @@ static int ftrace_hash_ipmodify_enable(struct ftrace_ops *ops)
 	if (ftrace_hash_empty(hash))
 		hash = NULL;
 
-	return __ftrace_hash_update_ipmodify(ops, EMPTY_HASH, hash);
+	return __ftrace_hash_update_ipmodify(ops, EMPTY_HASH, hash, false);
 }
 
 /* Disabling always succeeds */
@@ -2087,7 +2100,7 @@ static void ftrace_hash_ipmodify_disable(struct ftrace_ops *ops)
 	if (ftrace_hash_empty(hash))
 		hash = NULL;
 
-	__ftrace_hash_update_ipmodify(ops, hash, EMPTY_HASH);
+	__ftrace_hash_update_ipmodify(ops, hash, EMPTY_HASH, false);
 }
 
 static int ftrace_hash_ipmodify_update(struct ftrace_ops *ops,
@@ -2101,7 +2114,7 @@ static int ftrace_hash_ipmodify_update(struct ftrace_ops *ops,
 	if (ftrace_hash_empty(new_hash))
 		new_hash = NULL;
 
-	return __ftrace_hash_update_ipmodify(ops, old_hash, new_hash);
+	return __ftrace_hash_update_ipmodify(ops, old_hash, new_hash, false);
 }
 
 static void print_ip_ins(const char *fmt, const unsigned char *p)
@@ -5953,6 +5966,17 @@ static void register_ftrace_direct_cb(struct rcu_head *rhp)
 	free_ftrace_hash(fhp);
 }
 
+static void reset_direct(struct ftrace_ops *ops, unsigned long addr)
+{
+	struct ftrace_hash *hash = ops->func_hash->filter_hash;
+
+	remove_direct_functions_hash(hash, addr);
+
+	/* cleanup for possible another register call */
+	ops->func = NULL;
+	ops->trampoline = 0;
+}
+
 /**
  * register_ftrace_direct - Call a custom trampoline directly
  * for multiple functions registered in @ops
@@ -6048,6 +6072,8 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 	ops->direct_call = addr;
 
 	err = register_ftrace_function_nolock(ops);
+	if (err)
+		reset_direct(ops, addr);
 
  out_unlock:
 	mutex_unlock(&direct_mutex);
@@ -6080,7 +6106,6 @@ EXPORT_SYMBOL_GPL(register_ftrace_direct);
 int unregister_ftrace_direct(struct ftrace_ops *ops, unsigned long addr,
 			     bool free_filters)
 {
-	struct ftrace_hash *hash = ops->func_hash->filter_hash;
 	int err;
 
 	if (check_direct_multi(ops))
@@ -6090,13 +6115,9 @@ int unregister_ftrace_direct(struct ftrace_ops *ops, unsigned long addr,
 
 	mutex_lock(&direct_mutex);
 	err = unregister_ftrace_function(ops);
-	remove_direct_functions_hash(hash, addr);
+	reset_direct(ops, addr);
 	mutex_unlock(&direct_mutex);
 
-	/* cleanup for possible another register call */
-	ops->func = NULL;
-	ops->trampoline = 0;
-
 	if (free_filters)
 		ftrace_free_filter(ops);
 	return err;
@@ -6106,7 +6127,7 @@ EXPORT_SYMBOL_GPL(unregister_ftrace_direct);
 static int
 __modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 {
-	struct ftrace_hash *hash;
+	struct ftrace_hash *hash = ops->func_hash->filter_hash;
 	struct ftrace_func_entry *entry, *iter;
 	static struct ftrace_ops tmp_ops = {
 		.func		= ftrace_stub,
@@ -6127,12 +6148,20 @@ __modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 		return err;
 
 	/*
+	 * Call __ftrace_hash_update_ipmodify() here, so that we can call
+	 * ops->ops_func for the ops. This is needed because the above
+	 * register_ftrace_function_nolock() worked on tmp_ops.
+	 */
+	err = __ftrace_hash_update_ipmodify(ops, hash, hash, true);
+	if (err)
+		goto out;
+
+	/*
 	 * Now the ftrace_ops_list_func() is called to do the direct callers.
 	 * We can safely change the direct functions attached to each entry.
 	 */
 	mutex_lock(&ftrace_lock);
 
-	hash = ops->func_hash->filter_hash;
 	size = 1 << hash->size_bits;
 	for (i = 0; i < size; i++) {
 		hlist_for_each_entry(iter, &hash->buckets[i], hlist) {
@@ -6147,6 +6176,7 @@ __modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 
 	mutex_unlock(&ftrace_lock);
 
+out:
 	/* Removing the tmp_ops will add the updated direct callers to the functions */
 	unregister_ftrace_function(&tmp_ops);