Merge tag 'v5.12-rc5' into locking/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/bpf/bpf_inode_storage.c

@@ -109,7 +109,7 @@ static void *bpf_fd_inode_storage_lookup_elem(struct bpf_map *map, void *key)
 	fd = *(int *)key;
 	f = fget_raw(fd);
 	if (!f)
-		return NULL;
+		return ERR_PTR(-EBADF);
 
 	sdata = inode_storage_lookup(f->f_inode, map, true);
 	fput(f);

kernel/bpf/bpf_struct_ops.c

@@ -430,7 +430,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 
 		tprogs[BPF_TRAMP_FENTRY].progs[0] = prog;
 		tprogs[BPF_TRAMP_FENTRY].nr_progs = 1;
-		err = arch_prepare_bpf_trampoline(image,
+		err = arch_prepare_bpf_trampoline(NULL, image,
 						  st_map->image + PAGE_SIZE,
 						  &st_ops->func_models[i], 0,
 						  tprogs, NULL);

kernel/bpf/core.c

@@ -827,7 +827,7 @@ static int __init bpf_jit_charge_init(void)
 }
 pure_initcall(bpf_jit_charge_init);
 
-static int bpf_jit_charge_modmem(u32 pages)
+int bpf_jit_charge_modmem(u32 pages)
 {
 	if (atomic_long_add_return(pages, &bpf_jit_current) >
 	    (bpf_jit_limit >> PAGE_SHIFT)) {
@@ -840,7 +840,7 @@ static int bpf_jit_charge_modmem(u32 pages)
 	return 0;
 }
 
-static void bpf_jit_uncharge_modmem(u32 pages)
+void bpf_jit_uncharge_modmem(u32 pages)
 {
 	atomic_long_sub(pages, &bpf_jit_current);
 }

kernel/bpf/preload/bpf_preload_kern.c

@@ -60,9 +60,12 @@ static int finish(void)
 			 &magic, sizeof(magic), &pos);
 	if (n != sizeof(magic))
 		return -EPIPE;
+
 	tgid = umd_ops.info.tgid;
-	wait_event(tgid->wait_pidfd, thread_group_exited(tgid));
-	umd_ops.info.tgid = NULL;
+	if (tgid) {
+		wait_event(tgid->wait_pidfd, thread_group_exited(tgid));
+		umd_cleanup_helper(&umd_ops.info);
+	}
 	return 0;
 }
 
@@ -80,10 +83,18 @@ static int __init load_umd(void)
 
 static void __exit fini_umd(void)
 {
+	struct pid *tgid;
+
 	bpf_preload_ops = NULL;
+
 	/* kill UMD in case it's still there due to earlier error */
-	kill_pid(umd_ops.info.tgid, SIGKILL, 1);
-	umd_ops.info.tgid = NULL;
+	tgid = umd_ops.info.tgid;
+	if (tgid) {
+		kill_pid(tgid, SIGKILL, 1);
+
+		wait_event(tgid->wait_pidfd, thread_group_exited(tgid));
+		umd_cleanup_helper(&umd_ops.info);
+	}
 	umd_unload_blob(&umd_ops.info);
 }
 late_initcall(load_umd);

kernel/bpf/syscall.c

@@ -854,6 +854,11 @@ static int map_create(union bpf_attr *attr)
 			err = PTR_ERR(btf);
 			goto free_map;
 		}
+		if (btf_is_kernel(btf)) {
+			btf_put(btf);
+			err = -EACCES;
+			goto free_map;
+		}
 		map->btf = btf;
 
 		if (attr->btf_value_type_id) {

kernel/bpf/trampoline.c

@@ -57,19 +57,10 @@ void bpf_image_ksym_del(struct bpf_ksym *ksym)
 			   PAGE_SIZE, true, ksym->name);
 }
 
-static void bpf_trampoline_ksym_add(struct bpf_trampoline *tr)
-{
-	struct bpf_ksym *ksym = &tr->ksym;
-
-	snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu", tr->key);
-	bpf_image_ksym_add(tr->image, ksym);
-}
-
 static struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
 {
 	struct bpf_trampoline *tr;
 	struct hlist_head *head;
-	void *image;
 	int i;
 
 	mutex_lock(&trampoline_mutex);
@@ -84,14 +75,6 @@ static struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
 	if (!tr)
 		goto out;
 
-	/* is_root was checked earlier. No need for bpf_jit_charge_modmem() */
-	image = bpf_jit_alloc_exec_page();
-	if (!image) {
-		kfree(tr);
-		tr = NULL;
-		goto out;
-	}
-
 	tr->key = key;
 	INIT_HLIST_NODE(&tr->hlist);
 	hlist_add_head(&tr->hlist, head);
@@ -99,9 +82,6 @@ static struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
 	mutex_init(&tr->mutex);
 	for (i = 0; i < BPF_TRAMP_MAX; i++)
 		INIT_HLIST_HEAD(&tr->progs_hlist[i]);
-	tr->image = image;
-	INIT_LIST_HEAD_RCU(&tr->ksym.lnode);
-	bpf_trampoline_ksym_add(tr);
 out:
 	mutex_unlock(&trampoline_mutex);
 	return tr;
@@ -185,10 +165,142 @@ bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total)
 	return tprogs;
 }
 
+static void __bpf_tramp_image_put_deferred(struct work_struct *work)
+{
+	struct bpf_tramp_image *im;
+
+	im = container_of(work, struct bpf_tramp_image, work);
+	bpf_image_ksym_del(&im->ksym);
+	bpf_jit_free_exec(im->image);
+	bpf_jit_uncharge_modmem(1);
+	percpu_ref_exit(&im->pcref);
+	kfree_rcu(im, rcu);
+}
+
+/* callback, fexit step 3 or fentry step 2 */
+static void __bpf_tramp_image_put_rcu(struct rcu_head *rcu)
+{
+	struct bpf_tramp_image *im;
+
+	im = container_of(rcu, struct bpf_tramp_image, rcu);
+	INIT_WORK(&im->work, __bpf_tramp_image_put_deferred);
+	schedule_work(&im->work);
+}
+
+/* callback, fexit step 2. Called after percpu_ref_kill confirms. */
+static void __bpf_tramp_image_release(struct percpu_ref *pcref)
+{
+	struct bpf_tramp_image *im;
+
+	im = container_of(pcref, struct bpf_tramp_image, pcref);
+	call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu);
+}
+
+/* callback, fexit or fentry step 1 */
+static void __bpf_tramp_image_put_rcu_tasks(struct rcu_head *rcu)
+{
+	struct bpf_tramp_image *im;
+
+	im = container_of(rcu, struct bpf_tramp_image, rcu);
+	if (im->ip_after_call)
+		/* the case of fmod_ret/fexit trampoline and CONFIG_PREEMPTION=y */
+		percpu_ref_kill(&im->pcref);
+	else
+		/* the case of fentry trampoline */
+		call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu);
+}
+
+static void bpf_tramp_image_put(struct bpf_tramp_image *im)
+{
+	/* The trampoline image that calls original function is using:
+	 * rcu_read_lock_trace to protect sleepable bpf progs
+	 * rcu_read_lock to protect normal bpf progs
+	 * percpu_ref to protect trampoline itself
+	 * rcu tasks to protect trampoline asm not covered by percpu_ref
+	 * (which are few asm insns before __bpf_tramp_enter and
+	 *  after __bpf_tramp_exit)
+	 *
+	 * The trampoline is unreachable before bpf_tramp_image_put().
+	 *
+	 * First, patch the trampoline to avoid calling into fexit progs.
+	 * The progs will be freed even if the original function is still
+	 * executing or sleeping.
+	 * In case of CONFIG_PREEMPT=y use call_rcu_tasks() to wait on
+	 * first few asm instructions to execute and call into
+	 * __bpf_tramp_enter->percpu_ref_get.
+	 * Then use percpu_ref_kill to wait for the trampoline and the original
+	 * function to finish.
+	 * Then use call_rcu_tasks() to make sure few asm insns in
+	 * the trampoline epilogue are done as well.
+	 *
+	 * In !PREEMPT case the task that got interrupted in the first asm
+	 * insns won't go through an RCU quiescent state which the
+	 * percpu_ref_kill will be waiting for. Hence the first
+	 * call_rcu_tasks() is not necessary.
+	 */
+	if (im->ip_after_call) {
+		int err = bpf_arch_text_poke(im->ip_after_call, BPF_MOD_JUMP,
+					     NULL, im->ip_epilogue);
+		WARN_ON(err);
+		if (IS_ENABLED(CONFIG_PREEMPTION))
+			call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu_tasks);
+		else
+			percpu_ref_kill(&im->pcref);
+		return;
+	}
+
+	/* The trampoline without fexit and fmod_ret progs doesn't call original
+	 * function and doesn't use percpu_ref.
+	 * Use call_rcu_tasks_trace() to wait for sleepable progs to finish.
+	 * Then use call_rcu_tasks() to wait for the rest of trampoline asm
+	 * and normal progs.
+	 */
+	call_rcu_tasks_trace(&im->rcu, __bpf_tramp_image_put_rcu_tasks);
+}
+
+static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, u32 idx)
+{
+	struct bpf_tramp_image *im;
+	struct bpf_ksym *ksym;
+	void *image;
+	int err = -ENOMEM;
+
+	im = kzalloc(sizeof(*im), GFP_KERNEL);
+	if (!im)
+		goto out;
+
+	err = bpf_jit_charge_modmem(1);
+	if (err)
+		goto out_free_im;
+
+	err = -ENOMEM;
+	im->image = image = bpf_jit_alloc_exec_page();
+	if (!image)
+		goto out_uncharge;
+
+	err = percpu_ref_init(&im->pcref, __bpf_tramp_image_release, 0, GFP_KERNEL);
+	if (err)
+		goto out_free_image;
+
+	ksym = &im->ksym;
+	INIT_LIST_HEAD_RCU(&ksym->lnode);
+	snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu_%u", key, idx);
+	bpf_image_ksym_add(image, ksym);
+	return im;
+
+out_free_image:
+	bpf_jit_free_exec(im->image);
+out_uncharge:
+	bpf_jit_uncharge_modmem(1);
+out_free_im:
+	kfree(im);
+out:
+	return ERR_PTR(err);
+}
+
 static int bpf_trampoline_update(struct bpf_trampoline *tr)
 {
-	void *old_image = tr->image + ((tr->selector + 1) & 1) * PAGE_SIZE/2;
-	void *new_image = tr->image + (tr->selector & 1) * PAGE_SIZE/2;
+	struct bpf_tramp_image *im;
 	struct bpf_tramp_progs *tprogs;
 	u32 flags = BPF_TRAMP_F_RESTORE_REGS;
 	int err, total;
@@ -198,41 +310,42 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr)
 		return PTR_ERR(tprogs);
 
 	if (total == 0) {
-		err = unregister_fentry(tr, old_image);
+		err = unregister_fentry(tr, tr->cur_image->image);
+		bpf_tramp_image_put(tr->cur_image);
+		tr->cur_image = NULL;
 		tr->selector = 0;
 		goto out;
 	}
 
+	im = bpf_tramp_image_alloc(tr->key, tr->selector);
+	if (IS_ERR(im)) {
+		err = PTR_ERR(im);
+		goto out;
+	}
+
 	if (tprogs[BPF_TRAMP_FEXIT].nr_progs ||
 	    tprogs[BPF_TRAMP_MODIFY_RETURN].nr_progs)
 		flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME;
 
-	/* Though the second half of trampoline page is unused a task could be
-	 * preempted in the middle of the first half of trampoline and two
-	 * updates to trampoline would change the code from underneath the
-	 * preempted task. Hence wait for tasks to voluntarily schedule or go
-	 * to userspace.
-	 * The same trampoline can hold both sleepable and non-sleepable progs.
-	 * synchronize_rcu_tasks_trace() is needed to make sure all sleepable
-	 * programs finish executing.
-	 * Wait for these two grace periods together.
-	 */
-	synchronize_rcu_mult(call_rcu_tasks, call_rcu_tasks_trace);
-
-	err = arch_prepare_bpf_trampoline(new_image, new_image + PAGE_SIZE / 2,
+	err = arch_prepare_bpf_trampoline(im, im->image, im->image + PAGE_SIZE,
 					  &tr->func.model, flags, tprogs,
 					  tr->func.addr);
 	if (err < 0)
 		goto out;
 
-	if (tr->selector)
+	WARN_ON(tr->cur_image && tr->selector == 0);
+	WARN_ON(!tr->cur_image && tr->selector);
+	if (tr->cur_image)
 		/* progs already running at this address */
-		err = modify_fentry(tr, old_image, new_image);
+		err = modify_fentry(tr, tr->cur_image->image, im->image);
 	else
 		/* first time registering */
-		err = register_fentry(tr, new_image);
+		err = register_fentry(tr, im->image);
 	if (err)
 		goto out;
+	if (tr->cur_image)
+		bpf_tramp_image_put(tr->cur_image);
+	tr->cur_image = im;
 	tr->selector++;
 out:
 	kfree(tprogs);
@@ -364,17 +477,12 @@ void bpf_trampoline_put(struct bpf_trampoline *tr)
 		goto out;
 	if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT])))
 		goto out;
-	bpf_image_ksym_del(&tr->ksym);
-	/* This code will be executed when all bpf progs (both sleepable and
-	 * non-sleepable) went through
-	 * bpf_prog_put()->call_rcu[_tasks_trace]()->bpf_prog_free_deferred().
-	 * Hence no need for another synchronize_rcu_tasks_trace() here,
-	 * but synchronize_rcu_tasks() is still needed, since trampoline
-	 * may not have had any sleepable programs and we need to wait
-	 * for tasks to get out of trampoline code before freeing it.
+	/* This code will be executed even when the last bpf_tramp_image
+	 * is alive. All progs are detached from the trampoline and the
+	 * trampoline image is patched with jmp into epilogue to skip
+	 * fexit progs. The fentry-only trampoline will be freed via
+	 * multiple rcu callbacks.
 	 */
-	synchronize_rcu_tasks();
-	bpf_jit_free_exec(tr->image);
 	hlist_del(&tr->hlist);
 	kfree(tr);
 out:
@@ -478,8 +586,18 @@ void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start)
 	rcu_read_unlock_trace();
 }
 
+void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr)
+{
+	percpu_ref_get(&tr->pcref);
+}
+
+void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr)
+{
+	percpu_ref_put(&tr->pcref);
+}
+
 int __weak
-arch_prepare_bpf_trampoline(void *image, void *image_end,
+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,
 			    void *orig_call)

kernel/bpf/verifier.c

@@ -5861,10 +5861,14 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
 {
 	bool mask_to_left = (opcode == BPF_ADD &&  off_is_neg) ||
 			    (opcode == BPF_SUB && !off_is_neg);
-	u32 off;
+	u32 off, max;
 
 	switch (ptr_reg->type) {
 	case PTR_TO_STACK:
+		/* Offset 0 is out-of-bounds, but acceptable start for the
+		 * left direction, see BPF_REG_FP.
+		 */
+		max = MAX_BPF_STACK + mask_to_left;
 		/* Indirect variable offset stack access is prohibited in
 		 * unprivileged mode so it's not handled here.
 		 */
@@ -5872,16 +5876,17 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
 		if (mask_to_left)
 			*ptr_limit = MAX_BPF_STACK + off;
 		else
-			*ptr_limit = -off;
-		return 0;
+			*ptr_limit = -off - 1;
+		return *ptr_limit >= max ? -ERANGE : 0;
 	case PTR_TO_MAP_VALUE:
+		max = ptr_reg->map_ptr->value_size;
 		if (mask_to_left) {
 			*ptr_limit = ptr_reg->umax_value + ptr_reg->off;
 		} else {
 			off = ptr_reg->smin_value + ptr_reg->off;
-			*ptr_limit = ptr_reg->map_ptr->value_size - off;
+			*ptr_limit = ptr_reg->map_ptr->value_size - off - 1;
 		}
-		return 0;
+		return *ptr_limit >= max ? -ERANGE : 0;
 	default:
 		return -EINVAL;
 	}
@@ -5934,6 +5939,7 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env,
 	u32 alu_state, alu_limit;
 	struct bpf_reg_state tmp;
 	bool ret;
+	int err;
 
 	if (can_skip_alu_sanitation(env, insn))
 		return 0;
@@ -5949,10 +5955,13 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env,
 	alu_state |= ptr_is_dst_reg ?
 		     BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
 
-	if (retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg))
-		return 0;
-	if (update_alu_sanitation_state(aux, alu_state, alu_limit))
-		return -EACCES;
+	err = retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg);
+	if (err < 0)
+		return err;
+
+	err = update_alu_sanitation_state(aux, alu_state, alu_limit);
+	if (err < 0)
+		return err;
 do_sim:
 	/* Simulate and find potential out-of-bounds access under
 	 * speculative execution from truncation as a result of
@@ -6103,7 +6112,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	case BPF_ADD:
 		ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
 		if (ret < 0) {
-			verbose(env, "R%d tried to add from different maps or paths\n", dst);
+			verbose(env, "R%d tried to add from different maps, paths, or prohibited types\n", dst);
 			return ret;
 		}
 		/* We can take a fixed offset as long as it doesn't overflow
@@ -6158,7 +6167,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	case BPF_SUB:
 		ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
 		if (ret < 0) {
-			verbose(env, "R%d tried to sub from different maps or paths\n", dst);
+			verbose(env, "R%d tried to sub from different maps, paths, or prohibited types\n", dst);
 			return ret;
 		}
 		if (dst_reg == off_reg) {
@@ -9056,6 +9065,10 @@ static int check_btf_info(struct bpf_verifier_env *env,
 	btf = btf_get_by_fd(attr->prog_btf_fd);
 	if (IS_ERR(btf))
 		return PTR_ERR(btf);
+	if (btf_is_kernel(btf)) {
+		btf_put(btf);
+		return -EACCES;
+	}
 	env->prog->aux->btf = btf;
 
 	err = check_btf_func(env, attr, uattr);
@@ -11660,7 +11673,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			off_reg = issrc ? insn->src_reg : insn->dst_reg;
 			if (isneg)
 				*patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1);
-			*patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit - 1);
+			*patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit);
 			*patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg);
 			*patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg);
 			*patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0);

kernel/fork.c

@@ -1948,8 +1948,14 @@ static __latent_entropy struct task_struct *copy_process(
 	p = dup_task_struct(current, node);
 	if (!p)
 		goto fork_out;
-	if (args->io_thread)
+	if (args->io_thread) {
+		/*
+		 * Mark us an IO worker, and block any signal that isn't
+		 * fatal or STOP
+		 */
 		p->flags |= PF_IO_WORKER;
+		siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP));
+	}
 
 	/*
 	 * This _must_ happen before we call free_task(), i.e. before we jump
@@ -2438,15 +2444,8 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node)
 		.stack_size	= (unsigned long)arg,
 		.io_thread	= 1,
 	};
-	struct task_struct *tsk;
 
-	tsk = copy_process(NULL, 0, node, &args);
-	if (!IS_ERR(tsk)) {
-		sigfillset(&tsk->blocked);
-		sigdelsetmask(&tsk->blocked, sigmask(SIGKILL));
-		tsk->flags |= PF_NOFREEZE;
-	}
-	return tsk;
+	return copy_process(NULL, 0, node, &args);
 }
 
 /*

kernel/futex.c

@@ -2728,14 +2728,13 @@ retry:
 		goto out;
 
 	restart = &current->restart_block;
-	restart->fn = futex_wait_restart;
 	restart->futex.uaddr = uaddr;
 	restart->futex.val = val;
 	restart->futex.time = *abs_time;
 	restart->futex.bitset = bitset;
 	restart->futex.flags = flags | FLAGS_HAS_TIMEOUT;
 
-	ret = -ERESTART_RESTARTBLOCK;
+	ret = set_restart_fn(restart, futex_wait_restart);
 
 out:
 	if (to) {

kernel/gcov/clang.c

@@ -75,7 +75,9 @@ struct gcov_fn_info {
 
 	u32 num_counters;
 	u64 *counters;
+#if CONFIG_CLANG_VERSION < 110000
 	const char *function_name;
+#endif
 };
 
 static struct gcov_info *current_info;
@@ -105,6 +107,7 @@ void llvm_gcov_init(llvm_gcov_callback writeout, llvm_gcov_callback flush)
 }
 EXPORT_SYMBOL(llvm_gcov_init);
 
+#if CONFIG_CLANG_VERSION < 110000
 void llvm_gcda_start_file(const char *orig_filename, const char version[4],
 		u32 checksum)
 {
@@ -113,7 +116,17 @@ void llvm_gcda_start_file(const char *orig_filename, const char version[4],
 	current_info->checksum = checksum;
 }
 EXPORT_SYMBOL(llvm_gcda_start_file);
+#else
+void llvm_gcda_start_file(const char *orig_filename, u32 version, u32 checksum)
+{
+	current_info->filename = orig_filename;
+	current_info->version = version;
+	current_info->checksum = checksum;
+}
+EXPORT_SYMBOL(llvm_gcda_start_file);
+#endif
 
+#if CONFIG_CLANG_VERSION < 110000
 void llvm_gcda_emit_function(u32 ident, const char *function_name,
 		u32 func_checksum, u8 use_extra_checksum, u32 cfg_checksum)
 {
@@ -133,6 +146,24 @@ void llvm_gcda_emit_function(u32 ident, const char *function_name,
 	list_add_tail(&info->head, &current_info->functions);
 }
 EXPORT_SYMBOL(llvm_gcda_emit_function);
+#else
+void llvm_gcda_emit_function(u32 ident, u32 func_checksum,
+		u8 use_extra_checksum, u32 cfg_checksum)
+{
+	struct gcov_fn_info *info = kzalloc(sizeof(*info), GFP_KERNEL);
+
+	if (!info)
+		return;
+
+	INIT_LIST_HEAD(&info->head);
+	info->ident = ident;
+	info->checksum = func_checksum;
+	info->use_extra_checksum = use_extra_checksum;
+	info->cfg_checksum = cfg_checksum;
+	list_add_tail(&info->head, &current_info->functions);
+}
+EXPORT_SYMBOL(llvm_gcda_emit_function);
+#endif
 
 void llvm_gcda_emit_arcs(u32 num_counters, u64 *counters)
 {
@@ -295,6 +326,7 @@ void gcov_info_add(struct gcov_info *dst, struct gcov_info *src)
 	}
 }
 
+#if CONFIG_CLANG_VERSION < 110000
 static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn)
 {
 	size_t cv_size; /* counter values size */
@@ -322,6 +354,28 @@ err_name:
 	kfree(fn_dup);
 	return NULL;
 }
+#else
+static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn)
+{
+	size_t cv_size; /* counter values size */
+	struct gcov_fn_info *fn_dup = kmemdup(fn, sizeof(*fn),
+			GFP_KERNEL);
+	if (!fn_dup)
+		return NULL;
+	INIT_LIST_HEAD(&fn_dup->head);
+
+	cv_size = fn->num_counters * sizeof(fn->counters[0]);
+	fn_dup->counters = vmalloc(cv_size);
+	if (!fn_dup->counters) {
+		kfree(fn_dup);
+		return NULL;
+	}
+
+	memcpy(fn_dup->counters, fn->counters, cv_size);
+
+	return fn_dup;
+}
+#endif
 
 /**
  * gcov_info_dup - duplicate profiling data set
@@ -362,6 +416,7 @@ err:
  * gcov_info_free - release memory for profiling data set duplicate
  * @info: profiling data set duplicate to free
  */
+#if CONFIG_CLANG_VERSION < 110000
 void gcov_info_free(struct gcov_info *info)
 {
 	struct gcov_fn_info *fn, *tmp;
@@ -375,6 +430,20 @@ void gcov_info_free(struct gcov_info *info)
 	kfree(info->filename);
 	kfree(info);
 }
+#else
+void gcov_info_free(struct gcov_info *info)
+{
+	struct gcov_fn_info *fn, *tmp;
+
+	list_for_each_entry_safe(fn, tmp, &info->functions, head) {
+		vfree(fn->counters);
+		list_del(&fn->head);
+		kfree(fn);
+	}
+	kfree(info->filename);
+	kfree(info);
+}
+#endif
 
 #define ITER_STRIDE	PAGE_SIZE
 

kernel/irq/irq_sim.c

@@ -159,7 +159,7 @@ static const struct irq_domain_ops irq_sim_domain_ops = {
  * irq_domain_create_sim - Create a new interrupt simulator irq_domain and
  *                         allocate a range of dummy interrupts.
  *
- * @fnode:      struct fwnode_handle to be associated with this domain.
+ * @fwnode:     struct fwnode_handle to be associated with this domain.
  * @num_irqs:   Number of interrupts to allocate.
  *
  * On success: return a new irq_domain object.
@@ -228,7 +228,7 @@ static void devm_irq_domain_release_sim(struct device *dev, void *res)
  *                              a managed device.
  *
  * @dev:        Device to initialize the simulator object for.
- * @fnode:      struct fwnode_handle to be associated with this domain.
+ * @fwnode:     struct fwnode_handle to be associated with this domain.
  * @num_irqs:   Number of interrupts to allocate
  *
  * On success: return a new irq_domain object.

kernel/irq/manage.c

@@ -1142,11 +1142,15 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
 	irqreturn_t ret;
 
 	local_bh_disable();
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_irq_disable();
 	ret = action->thread_fn(action->irq, action->dev_id);
 	if (ret == IRQ_HANDLED)
 		atomic_inc(&desc->threads_handled);
 
 	irq_finalize_oneshot(desc, action);
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_irq_enable();
 	local_bh_enable();
 	return ret;
 }

kernel/jump_label.c

@@ -407,6 +407,14 @@ static bool jump_label_can_update(struct jump_entry *entry, bool init)
 		return false;
 
 	if (!kernel_text_address(jump_entry_code(entry))) {
+		/*
+		 * This skips patching built-in __exit, which
+		 * is part of init_section_contains() but is
+		 * not part of kernel_text_address().
+		 *
+		 * Skipping built-in __exit is fine since it
+		 * will never be executed.
+		 */
 		WARN_ONCE(!jump_entry_is_init(entry),
 			  "can't patch jump_label at %pS",
 			  (void *)jump_entry_code(entry));

kernel/power/energy_model.c

@@ -98,7 +98,7 @@ static int __init em_debug_init(void)
 
 	return 0;
 }
-core_initcall(em_debug_init);
+fs_initcall(em_debug_init);
 #else /* CONFIG_DEBUG_FS */
 static void em_debug_create_pd(struct device *dev) {}
 static void em_debug_remove_pd(struct device *dev) {}

kernel/ptrace.c

@@ -375,7 +375,7 @@ static int ptrace_attach(struct task_struct *task, long request,
 	audit_ptrace(task);
 
 	retval = -EPERM;
-	if (unlikely(task->flags & (PF_KTHREAD | PF_IO_WORKER)))
+	if (unlikely(task->flags & PF_KTHREAD))
 		goto out;
 	if (same_thread_group(task, current))
 		goto out;

kernel/reboot.c

@@ -244,8 +244,6 @@ void migrate_to_reboot_cpu(void)
 void kernel_restart(char *cmd)
 {
 	kernel_restart_prepare(cmd);
-	if (pm_power_off_prepare)
-		pm_power_off_prepare();
 	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	if (!cmd)

kernel/signal.c

@@ -91,7 +91,7 @@ static bool sig_task_ignored(struct task_struct *t, int sig, bool force)
 		return true;
 
 	/* Only allow kernel generated signals to this kthread */
-	if (unlikely((t->flags & (PF_KTHREAD | PF_IO_WORKER)) &&
+	if (unlikely((t->flags & PF_KTHREAD) &&
 		     (handler == SIG_KTHREAD_KERNEL) && !force))
 		return true;
 
@@ -1096,7 +1096,7 @@ static int __send_signal(int sig, struct kernel_siginfo *info, struct task_struc
 	/*
 	 * Skip useless siginfo allocation for SIGKILL and kernel threads.
 	 */
-	if ((sig == SIGKILL) || (t->flags & (PF_KTHREAD | PF_IO_WORKER)))
+	if ((sig == SIGKILL) || (t->flags & PF_KTHREAD))
 		goto out_set;
 
 	/*
@@ -2767,6 +2767,14 @@ relock:
 			do_coredump(&ksig->info);
 		}
 
+		/*
+		 * PF_IO_WORKER threads will catch and exit on fatal signals
+		 * themselves. They have cleanup that must be performed, so
+		 * we cannot call do_exit() on their behalf.
+		 */
+		if (current->flags & PF_IO_WORKER)
+			goto out;
+
 		/*
 		 * Death signals, no core dump.
 		 */
@@ -2774,7 +2782,7 @@ relock:
 		/* NOTREACHED */
 	}
 	spin_unlock_irq(&sighand->siglock);
-
+out:
 	ksig->sig = signr;
 
 	if (!(ksig->ka.sa.sa_flags & SA_EXPOSE_TAGBITS))

kernel/static_call.c

@@ -35,27 +35,30 @@ static inline void *static_call_addr(struct static_call_site *site)
 	return (void *)((long)site->addr + (long)&site->addr);
 }
 
+static inline unsigned long __static_call_key(const struct static_call_site *site)
+{
+	return (long)site->key + (long)&site->key;
+}
 
 static inline struct static_call_key *static_call_key(const struct static_call_site *site)
 {
-	return (struct static_call_key *)
-		(((long)site->key + (long)&site->key) & ~STATIC_CALL_SITE_FLAGS);
+	return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS);
 }
 
 /* These assume the key is word-aligned. */
 static inline bool static_call_is_init(struct static_call_site *site)
 {
-	return ((long)site->key + (long)&site->key) & STATIC_CALL_SITE_INIT;
+	return __static_call_key(site) & STATIC_CALL_SITE_INIT;
 }
 
 static inline bool static_call_is_tail(struct static_call_site *site)
 {
-	return ((long)site->key + (long)&site->key) & STATIC_CALL_SITE_TAIL;
+	return __static_call_key(site) & STATIC_CALL_SITE_TAIL;
 }
 
 static inline void static_call_set_init(struct static_call_site *site)
 {
-	site->key = ((long)static_call_key(site) | STATIC_CALL_SITE_INIT) -
+	site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) -
 		    (long)&site->key;
 }
 
@@ -146,6 +149,7 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 	};
 
 	for (site_mod = &first; site_mod; site_mod = site_mod->next) {
+		bool init = system_state < SYSTEM_RUNNING;
 		struct module *mod = site_mod->mod;
 
 		if (!site_mod->sites) {
@@ -165,6 +169,7 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 		if (mod) {
 			stop = mod->static_call_sites +
 			       mod->num_static_call_sites;
+			init = mod->state == MODULE_STATE_COMING;
 		}
 #endif
 
@@ -172,25 +177,26 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 		     site < stop && static_call_key(site) == key; site++) {
 			void *site_addr = static_call_addr(site);
 
-			if (static_call_is_init(site)) {
-				/*
-				 * Don't write to call sites which were in
-				 * initmem and have since been freed.
-				 */
-				if (!mod && system_state >= SYSTEM_RUNNING)
-					continue;
-				if (mod && !within_module_init((unsigned long)site_addr, mod))
-					continue;
-			}
+			if (!init && static_call_is_init(site))
+				continue;
 
 			if (!kernel_text_address((unsigned long)site_addr)) {
-				WARN_ONCE(1, "can't patch static call site at %pS",
+				/*
+				 * This skips patching built-in __exit, which
+				 * is part of init_section_contains() but is
+				 * not part of kernel_text_address().
+				 *
+				 * Skipping built-in __exit is fine since it
+				 * will never be executed.
+				 */
+				WARN_ONCE(!static_call_is_init(site),
+					  "can't patch static call site at %pS",
 					  site_addr);
 				continue;
 			}
 
 			arch_static_call_transform(site_addr, NULL, func,
-				static_call_is_tail(site));
+						   static_call_is_tail(site));
 		}
 	}
 
@@ -349,7 +355,7 @@ static int static_call_add_module(struct module *mod)
 	struct static_call_site *site;
 
 	for (site = start; site != stop; site++) {
-		unsigned long s_key = (long)site->key + (long)&site->key;
+		unsigned long s_key = __static_call_key(site);
 		unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS;
 		unsigned long key;
 

kernel/time/alarmtimer.c

@@ -854,9 +854,9 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
 	if (flags == TIMER_ABSTIME)
 		return -ERESTARTNOHAND;
 
-	restart->fn = alarm_timer_nsleep_restart;
 	restart->nanosleep.clockid = type;
 	restart->nanosleep.expires = exp;
+	set_restart_fn(restart, alarm_timer_nsleep_restart);
 	return ret;
 }
 

kernel/time/hrtimer.c

@@ -1957,9 +1957,9 @@ long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode,
 	}
 
 	restart = &current->restart_block;
-	restart->fn = hrtimer_nanosleep_restart;
 	restart->nanosleep.clockid = t.timer.base->clockid;
 	restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer);
+	set_restart_fn(restart, hrtimer_nanosleep_restart);
 out:
 	destroy_hrtimer_on_stack(&t.timer);
 	return ret;

kernel/time/posix-cpu-timers.c

@@ -1480,8 +1480,8 @@ static int posix_cpu_nsleep(const clockid_t which_clock, int flags,
 		if (flags & TIMER_ABSTIME)
 			return -ERESTARTNOHAND;
 
-		restart_block->fn = posix_cpu_nsleep_restart;
 		restart_block->nanosleep.clockid = which_clock;
+		set_restart_fn(restart_block, posix_cpu_nsleep_restart);
 	}
 	return error;
 }

kernel/trace/ftrace.c

@@ -5045,6 +5045,20 @@ struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr)
 	return NULL;
 }
 
+static struct ftrace_direct_func *ftrace_alloc_direct_func(unsigned long addr)
+{
+	struct ftrace_direct_func *direct;
+
+	direct = kmalloc(sizeof(*direct), GFP_KERNEL);
+	if (!direct)
+		return NULL;
+	direct->addr = addr;
+	direct->count = 0;
+	list_add_rcu(&direct->next, &ftrace_direct_funcs);
+	ftrace_direct_func_count++;
+	return direct;
+}
+
 /**
  * register_ftrace_direct - Call a custom trampoline directly
  * @ip: The address of the nop at the beginning of a function
@@ -5120,15 +5134,11 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr)
 
 	direct = ftrace_find_direct_func(addr);
 	if (!direct) {
-		direct = kmalloc(sizeof(*direct), GFP_KERNEL);
+		direct = ftrace_alloc_direct_func(addr);
 		if (!direct) {
 			kfree(entry);
 			goto out_unlock;
 		}
-		direct->addr = addr;
-		direct->count = 0;
-		list_add_rcu(&direct->next, &ftrace_direct_funcs);
-		ftrace_direct_func_count++;
 	}
 
 	entry->ip = ip;
@@ -5329,6 +5339,7 @@ int __weak ftrace_modify_direct_caller(struct ftrace_func_entry *entry,
 int modify_ftrace_direct(unsigned long ip,
 			 unsigned long old_addr, unsigned long new_addr)
 {
+	struct ftrace_direct_func *direct, *new_direct = NULL;
 	struct ftrace_func_entry *entry;
 	struct dyn_ftrace *rec;
 	int ret = -ENODEV;
@@ -5344,6 +5355,20 @@ int modify_ftrace_direct(unsigned long ip,
 	if (entry->direct != old_addr)
 		goto out_unlock;
 
+	direct = ftrace_find_direct_func(old_addr);
+	if (WARN_ON(!direct))
+		goto out_unlock;
+	if (direct->count > 1) {
+		ret = -ENOMEM;
+		new_direct = ftrace_alloc_direct_func(new_addr);
+		if (!new_direct)
+			goto out_unlock;
+		direct->count--;
+		new_direct->count++;
+	} else {
+		direct->addr = new_addr;
+	}
+
 	/*
 	 * If there's no other ftrace callback on the rec->ip location,
 	 * then it can be changed directly by the architecture.
@@ -5357,6 +5382,14 @@ int modify_ftrace_direct(unsigned long ip,
 		ret = 0;
 	}
 
+	if (unlikely(ret && new_direct)) {
+		direct->count++;
+		list_del_rcu(&new_direct->next);
+		synchronize_rcu_tasks();
+		kfree(new_direct);
+		ftrace_direct_func_count--;
+	}
+
  out_unlock:
 	mutex_unlock(&ftrace_lock);
 	mutex_unlock(&direct_mutex);

kernel/usermode_driver.c

@@ -139,14 +139,23 @@ static void umd_cleanup(struct subprocess_info *info)
 	struct umd_info *umd_info = info->data;
 
 	/* cleanup if umh_setup() was successful but exec failed */
-	if (info->retval) {
-		fput(umd_info->pipe_to_umh);
-		fput(umd_info->pipe_from_umh);
-		put_pid(umd_info->tgid);
-		umd_info->tgid = NULL;
-	}
+	if (info->retval)
+		umd_cleanup_helper(umd_info);
 }
 
+/**
+ * umd_cleanup_helper - release the resources which were allocated in umd_setup
+ * @info: information about usermode driver
+ */
+void umd_cleanup_helper(struct umd_info *info)
+{
+	fput(info->pipe_to_umh);
+	fput(info->pipe_from_umh);
+	put_pid(info->tgid);
+	info->tgid = NULL;
+}
+EXPORT_SYMBOL_GPL(umd_cleanup_helper);
+
 /**
  * fork_usermode_driver - fork a usermode driver
  * @info: information about usermode driver (shouldn't be NULL)