[patch v2 01/11] futex: Move futex task related data into a struct

[Thomas Gleixner <tglx@kernel.org>]

Having all these members in task_struct along with the required #ifdeffery
is annoying, does not allow efficient initializing of the data with
memset() and makes extending it tedious.

Move it into a data structure and fix up all usage sites.

Signed-off-by: Thomas Gleixner <tglx@kernel.org>
---
V2: Rename the struct and add the missing kernel doc - Andre
---
 Documentation/locking/robust-futexes.rst |    8 ++--
 include/linux/futex.h                    |   12 ++----
 include/linux/futex_types.h              |   36 ++++++++++++++++++++
 include/linux/sched.h                    |   16 ++-------
 kernel/exit.c                            |    4 +-
 kernel/futex/core.c                      |   55 +++++++++++++++----------------
 kernel/futex/pi.c                        |   26 +++++++-------
 kernel/futex/syscalls.c                  |   23 ++++--------
 8 files changed, 99 insertions(+), 81 deletions(-)

--- a/Documentation/locking/robust-futexes.rst
+++ b/Documentation/locking/robust-futexes.rst
@@ -94,7 +94,7 @@ time, the kernel checks this user-space
 locks to be cleaned up?
 
 In the common case, at do_exit() time, there is no list registered, so
-the cost of robust futexes is just a simple current->robust_list != NULL
+the cost of robust futexes is just a current->futex.robust_list != NULL
 comparison. If the thread has registered a list, then normally the list
 is empty. If the thread/process crashed or terminated in some incorrect
 way then the list might be non-empty: in this case the kernel carefully
@@ -178,9 +178,9 @@ The patch adds two new syscalls: one to
                      size_t __user *len_ptr);
 
 List registration is very fast: the pointer is simply stored in
-current->robust_list. [Note that in the future, if robust futexes become
-widespread, we could extend sys_clone() to register a robust-list head
-for new threads, without the need of another syscall.]
+current->futex.robust_list. [Note that in the future, if robust futexes
+become widespread, we could extend sys_clone() to register a robust-list
+head for new threads, without the need of another syscall.]
 
 So there is virtually zero overhead for tasks not using robust futexes,
 and even for robust futex users, there is only one extra syscall per
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -64,14 +64,10 @@ enum {
 
 static inline void futex_init_task(struct task_struct *tsk)
 {
-	tsk->robust_list = NULL;
-#ifdef CONFIG_COMPAT
-	tsk->compat_robust_list = NULL;
-#endif
-	INIT_LIST_HEAD(&tsk->pi_state_list);
-	tsk->pi_state_cache = NULL;
-	tsk->futex_state = FUTEX_STATE_OK;
-	mutex_init(&tsk->futex_exit_mutex);
+	memset(&tsk->futex, 0, sizeof(tsk->futex));
+	INIT_LIST_HEAD(&tsk->futex.pi_state_list);
+	tsk->futex.state = FUTEX_STATE_OK;
+	mutex_init(&tsk->futex.exit_mutex);
 }
 
 void futex_exit_recursive(struct task_struct *tsk);
--- /dev/null
+++ b/include/linux/futex_types.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_FUTEX_TYPES_H
+#define _LINUX_FUTEX_TYPES_H
+
+#ifdef CONFIG_FUTEX
+#include <linux/mutex_types.h>
+#include <linux/types.h>
+
+struct compat_robust_list_head;
+struct futex_pi_state;
+struct robust_list_head;
+
+/**
+ * struct futex_sched_data - Futex related per task data
+ * @robust_list:	User space registered robust list pointer
+ * @compat_robust_list:	User space registered robust list pointer for compat tasks
+ * @pi_state_list:	List head for Priority Inheritance (PI) state management
+ * @pi_state_cache:	Pointer to cache one PI state object per task
+ * @exit_mutex:		Mutex for serializing exit
+ * @state:		Futex handling state to handle exit races correctly
+ */
+struct futex_sched_data {
+	struct robust_list_head __user		*robust_list;
+#ifdef CONFIG_COMPAT
+	struct compat_robust_list_head __user	*compat_robust_list;
+#endif
+	struct list_head			pi_state_list;
+	struct futex_pi_state			*pi_state_cache;
+	struct mutex				exit_mutex;
+	unsigned int				state;
+};
+#else
+struct futex_sched_data { };
+#endif /* !CONFIG_FUTEX */
+
+#endif /* _LINUX_FUTEX_TYPES_H */
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -16,6 +16,7 @@
 #include <linux/cpumask_types.h>
 
 #include <linux/cache.h>
+#include <linux/futex_types.h>
 #include <linux/irqflags_types.h>
 #include <linux/smp_types.h>
 #include <linux/pid_types.h>
@@ -64,7 +65,6 @@ struct bpf_net_context;
 struct capture_control;
 struct cfs_rq;
 struct fs_struct;
-struct futex_pi_state;
 struct io_context;
 struct io_uring_task;
 struct mempolicy;
@@ -76,7 +76,6 @@ struct pid_namespace;
 struct pipe_inode_info;
 struct rcu_node;
 struct reclaim_state;
-struct robust_list_head;
 struct root_domain;
 struct rq;
 struct sched_attr;
@@ -1329,16 +1328,9 @@ struct task_struct {
 	u32				closid;
 	u32				rmid;
 #endif
-#ifdef CONFIG_FUTEX
-	struct robust_list_head __user	*robust_list;
-#ifdef CONFIG_COMPAT
-	struct compat_robust_list_head __user *compat_robust_list;
-#endif
-	struct list_head		pi_state_list;
-	struct futex_pi_state		*pi_state_cache;
-	struct mutex			futex_exit_mutex;
-	unsigned int			futex_state;
-#endif
+
+	struct futex_sched_data		futex;
+
 #ifdef CONFIG_PERF_EVENTS
 	u8				perf_recursion[PERF_NR_CONTEXTS];
 	struct perf_event_context	*perf_event_ctxp;
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -989,8 +989,8 @@ void __noreturn do_exit(long code)
 	proc_exit_connector(tsk);
 	mpol_put_task_policy(tsk);
 #ifdef CONFIG_FUTEX
-	if (unlikely(current->pi_state_cache))
-		kfree(current->pi_state_cache);
+	if (unlikely(current->futex.pi_state_cache))
+		kfree(current->futex.pi_state_cache);
 #endif
 	/*
 	 * Make sure we are holding no locks:
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -32,18 +32,19 @@
  *  "But they come in a choice of three flavours!"
  */
 #include <linux/compat.h>
-#include <linux/jhash.h>
-#include <linux/pagemap.h>
 #include <linux/debugfs.h>
-#include <linux/plist.h>
+#include <linux/fault-inject.h>
 #include <linux/gfp.h>
-#include <linux/vmalloc.h>
+#include <linux/jhash.h>
 #include <linux/memblock.h>
-#include <linux/fault-inject.h>
-#include <linux/slab.h>
-#include <linux/prctl.h>
 #include <linux/mempolicy.h>
 #include <linux/mmap_lock.h>
+#include <linux/pagemap.h>
+#include <linux/plist.h>
+#include <linux/prctl.h>
+#include <linux/rseq.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
 
 #include "futex.h"
 #include "../locking/rtmutex_common.h"
@@ -829,7 +830,7 @@ void wait_for_owner_exiting(int ret, str
 	if (WARN_ON_ONCE(ret == -EBUSY && !exiting))
 		return;
 
-	mutex_lock(&exiting->futex_exit_mutex);
+	mutex_lock(&exiting->futex.exit_mutex);
 	/*
 	 * No point in doing state checking here. If the waiter got here
 	 * while the task was in exec()->exec_futex_release() then it can
@@ -838,7 +839,7 @@ void wait_for_owner_exiting(int ret, str
 	 * already. Highly unlikely and not a problem. Just one more round
 	 * through the futex maze.
 	 */
-	mutex_unlock(&exiting->futex_exit_mutex);
+	mutex_unlock(&exiting->futex.exit_mutex);
 
 	put_task_struct(exiting);
 }
@@ -1048,7 +1049,7 @@ static int handle_futex_death(u32 __user
 	 *
 	 * In both cases the following conditions are met:
 	 *
-	 *	1) task->robust_list->list_op_pending != NULL
+	 *	1) task->futex.robust_list->list_op_pending != NULL
 	 *	   @pending_op == true
 	 *	2) The owner part of user space futex value == 0
 	 *	3) Regular futex: @pi == false
@@ -1153,7 +1154,7 @@ static inline int fetch_robust_entry(str
  */
 static void exit_robust_list(struct task_struct *curr)
 {
-	struct robust_list_head __user *head = curr->robust_list;
+	struct robust_list_head __user *head = curr->futex.robust_list;
 	struct robust_list __user *entry, *next_entry, *pending;
 	unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
 	unsigned int next_pi;
@@ -1247,7 +1248,7 @@ compat_fetch_robust_entry(compat_uptr_t
  */
 static void compat_exit_robust_list(struct task_struct *curr)
 {
-	struct compat_robust_list_head __user *head = curr->compat_robust_list;
+	struct compat_robust_list_head __user *head = curr->futex.compat_robust_list;
 	struct robust_list __user *entry, *next_entry, *pending;
 	unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
 	unsigned int next_pi;
@@ -1323,7 +1324,7 @@ static void compat_exit_robust_list(stru
  */
 static void exit_pi_state_list(struct task_struct *curr)
 {
-	struct list_head *next, *head = &curr->pi_state_list;
+	struct list_head *next, *head = &curr->futex.pi_state_list;
 	struct futex_pi_state *pi_state;
 	union futex_key key = FUTEX_KEY_INIT;
 
@@ -1407,19 +1408,19 @@ static inline void exit_pi_state_list(st
 
 static void futex_cleanup(struct task_struct *tsk)
 {
-	if (unlikely(tsk->robust_list)) {
+	if (unlikely(tsk->futex.robust_list)) {
 		exit_robust_list(tsk);
-		tsk->robust_list = NULL;
+		tsk->futex.robust_list = NULL;
 	}
 
 #ifdef CONFIG_COMPAT
-	if (unlikely(tsk->compat_robust_list)) {
+	if (unlikely(tsk->futex.compat_robust_list)) {
 		compat_exit_robust_list(tsk);
-		tsk->compat_robust_list = NULL;
+		tsk->futex.compat_robust_list = NULL;
 	}
 #endif
 
-	if (unlikely(!list_empty(&tsk->pi_state_list)))
+	if (unlikely(!list_empty(&tsk->futex.pi_state_list)))
 		exit_pi_state_list(tsk);
 }
 
@@ -1442,10 +1443,10 @@ static void futex_cleanup(struct task_st
  */
 void futex_exit_recursive(struct task_struct *tsk)
 {
-	/* If the state is FUTEX_STATE_EXITING then futex_exit_mutex is held */
-	if (tsk->futex_state == FUTEX_STATE_EXITING)
-		mutex_unlock(&tsk->futex_exit_mutex);
-	tsk->futex_state = FUTEX_STATE_DEAD;
+	/* If the state is FUTEX_STATE_EXITING then futex.exit_mutex is held */
+	if (tsk->futex.state == FUTEX_STATE_EXITING)
+		mutex_unlock(&tsk->futex.exit_mutex);
+	tsk->futex.state = FUTEX_STATE_DEAD;
 }
 
 static void futex_cleanup_begin(struct task_struct *tsk)
@@ -1453,10 +1454,10 @@ static void futex_cleanup_begin(struct t
 	/*
 	 * Prevent various race issues against a concurrent incoming waiter
 	 * including live locks by forcing the waiter to block on
-	 * tsk->futex_exit_mutex when it observes FUTEX_STATE_EXITING in
+	 * tsk->futex.exit_mutex when it observes FUTEX_STATE_EXITING in
 	 * attach_to_pi_owner().
 	 */
-	mutex_lock(&tsk->futex_exit_mutex);
+	mutex_lock(&tsk->futex.exit_mutex);
 
 	/*
 	 * Switch the state to FUTEX_STATE_EXITING under tsk->pi_lock.
@@ -1470,7 +1471,7 @@ static void futex_cleanup_begin(struct t
 	 * be observed in exit_pi_state_list().
 	 */
 	raw_spin_lock_irq(&tsk->pi_lock);
-	tsk->futex_state = FUTEX_STATE_EXITING;
+	tsk->futex.state = FUTEX_STATE_EXITING;
 	raw_spin_unlock_irq(&tsk->pi_lock);
 }
 
@@ -1480,12 +1481,12 @@ static void futex_cleanup_end(struct tas
 	 * Lockless store. The only side effect is that an observer might
 	 * take another loop until it becomes visible.
 	 */
-	tsk->futex_state = state;
+	tsk->futex.state = state;
 	/*
 	 * Drop the exit protection. This unblocks waiters which observed
 	 * FUTEX_STATE_EXITING to reevaluate the state.
 	 */
-	mutex_unlock(&tsk->futex_exit_mutex);
+	mutex_unlock(&tsk->futex.exit_mutex);
 }
 
 void futex_exec_release(struct task_struct *tsk)
--- a/kernel/futex/pi.c
+++ b/kernel/futex/pi.c
@@ -14,7 +14,7 @@ int refill_pi_state_cache(void)
 {
 	struct futex_pi_state *pi_state;
 
-	if (likely(current->pi_state_cache))
+	if (likely(current->futex.pi_state_cache))
 		return 0;
 
 	pi_state = kzalloc_obj(*pi_state);
@@ -28,17 +28,17 @@ int refill_pi_state_cache(void)
 	refcount_set(&pi_state->refcount, 1);
 	pi_state->key = FUTEX_KEY_INIT;
 
-	current->pi_state_cache = pi_state;
+	current->futex.pi_state_cache = pi_state;
 
 	return 0;
 }
 
 static struct futex_pi_state *alloc_pi_state(void)
 {
-	struct futex_pi_state *pi_state = current->pi_state_cache;
+	struct futex_pi_state *pi_state = current->futex.pi_state_cache;
 
 	WARN_ON(!pi_state);
-	current->pi_state_cache = NULL;
+	current->futex.pi_state_cache = NULL;
 
 	return pi_state;
 }
@@ -60,7 +60,7 @@ static void pi_state_update_owner(struct
 	if (new_owner) {
 		raw_spin_lock(&new_owner->pi_lock);
 		WARN_ON(!list_empty(&pi_state->list));
-		list_add(&pi_state->list, &new_owner->pi_state_list);
+		list_add(&pi_state->list, &new_owner->futex.pi_state_list);
 		pi_state->owner = new_owner;
 		raw_spin_unlock(&new_owner->pi_lock);
 	}
@@ -96,7 +96,7 @@ void put_pi_state(struct futex_pi_state
 		raw_spin_unlock_irqrestore(&pi_state->pi_mutex.wait_lock, flags);
 	}
 
-	if (current->pi_state_cache) {
+	if (current->futex.pi_state_cache) {
 		kfree(pi_state);
 	} else {
 		/*
@@ -106,7 +106,7 @@ void put_pi_state(struct futex_pi_state
 		 */
 		pi_state->owner = NULL;
 		refcount_set(&pi_state->refcount, 1);
-		current->pi_state_cache = pi_state;
+		current->futex.pi_state_cache = pi_state;
 	}
 }
 
@@ -179,7 +179,7 @@ void put_pi_state(struct futex_pi_state
  *
  * p->pi_lock:
  *
- *	p->pi_state_list -> pi_state->list, relation
+ *	p->futex.pi_state_list -> pi_state->list, relation
  *	pi_mutex->owner -> pi_state->owner, relation
  *
  * pi_state->refcount:
@@ -327,7 +327,7 @@ static int handle_exit_race(u32 __user *
 	 * If the futex exit state is not yet FUTEX_STATE_DEAD, tell the
 	 * caller that the alleged owner is busy.
 	 */
-	if (tsk && tsk->futex_state != FUTEX_STATE_DEAD)
+	if (tsk && tsk->futex.state != FUTEX_STATE_DEAD)
 		return -EBUSY;
 
 	/*
@@ -346,8 +346,8 @@ static int handle_exit_race(u32 __user *
 	 *    *uaddr = 0xC0000000;	     tsk = get_task(PID);
 	 *   }				     if (!tsk->flags & PF_EXITING) {
 	 *  ...				       attach();
-	 *  tsk->futex_state =               } else {
-	 *	FUTEX_STATE_DEAD;              if (tsk->futex_state !=
+	 *  tsk->futex.state =               } else {
+	 *	FUTEX_STATE_DEAD;              if (tsk->futex.state !=
 	 *					  FUTEX_STATE_DEAD)
 	 *				         return -EAGAIN;
 	 *				       return -ESRCH; <--- FAIL
@@ -395,7 +395,7 @@ static void __attach_to_pi_owner(struct
 	pi_state->key = *key;
 
 	WARN_ON(!list_empty(&pi_state->list));
-	list_add(&pi_state->list, &p->pi_state_list);
+	list_add(&pi_state->list, &p->futex.pi_state_list);
 	/*
 	 * Assignment without holding pi_state->pi_mutex.wait_lock is safe
 	 * because there is no concurrency as the object is not published yet.
@@ -439,7 +439,7 @@ static int attach_to_pi_owner(u32 __user
 	 * in futex_exit_release(), we do this protected by p->pi_lock:
 	 */
 	raw_spin_lock_irq(&p->pi_lock);
-	if (unlikely(p->futex_state != FUTEX_STATE_OK)) {
+	if (unlikely(p->futex.state != FUTEX_STATE_OK)) {
 		/*
 		 * The task is on the way out. When the futex state is
 		 * FUTEX_STATE_DEAD, we know that the task has finished
--- a/kernel/futex/syscalls.c
+++ b/kernel/futex/syscalls.c
@@ -25,17 +25,13 @@
  * @head:	pointer to the list-head
  * @len:	length of the list-head, as userspace expects
  */
-SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head,
-		size_t, len)
+SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head, size_t, len)
 {
-	/*
-	 * The kernel knows only one size for now:
-	 */
+	/* The kernel knows only one size for now. */
 	if (unlikely(len != sizeof(*head)))
 		return -EINVAL;
 
-	current->robust_list = head;
-
+	current->futex.robust_list = head;
 	return 0;
 }
 
@@ -43,9 +39,9 @@ static inline void __user *futex_task_ro
 {
 #ifdef CONFIG_COMPAT
 	if (compat)
-		return p->compat_robust_list;
+		return p->futex.compat_robust_list;
 #endif
-	return p->robust_list;
+	return p->futex.robust_list;
 }
 
 static void __user *futex_get_robust_list_common(int pid, bool compat)
@@ -467,15 +463,13 @@ SYSCALL_DEFINE4(futex_requeue,
 }
 
 #ifdef CONFIG_COMPAT
-COMPAT_SYSCALL_DEFINE2(set_robust_list,
-		struct compat_robust_list_head __user *, head,
-		compat_size_t, len)
+COMPAT_SYSCALL_DEFINE2(set_robust_list, struct compat_robust_list_head __user *, head,
+		       compat_size_t, len)
 {
 	if (unlikely(len != sizeof(*head)))
 		return -EINVAL;
 
-	current->compat_robust_list = head;
-
+	current->futex.compat_robust_list = head;
 	return 0;
 }
 
@@ -515,4 +509,3 @@ SYSCALL_DEFINE6(futex_time32, u32 __user
 	return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3);
 }
 #endif /* CONFIG_COMPAT_32BIT_TIME */
-