From dfb36e4a8db0cd56f92d4cb445f54e85a9b40897 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Mon, 11 Aug 2025 10:11:47 -0400 Subject: futex: Use user_write_access_begin/_end() in futex_put_value() Commit cec199c5e39b ("futex: Implement FUTEX2_NUMA") introduced the futex_put_value() helper to write a value to the given user address. However, it uses user_read_access_begin() before the write. For architectures that differentiate between read and write accesses, like PowerPC, futex_put_value() fails with -EFAULT. Fix that by using the user_write_access_begin/user_write_access_end() pair instead. Fixes: cec199c5e39b ("futex: Implement FUTEX2_NUMA") Signed-off-by: Waiman Long Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/20250811141147.322261-1-longman@redhat.com --- kernel/futex/futex.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/futex') diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h index c74eac572acd..2cd57096c38e 100644 --- a/kernel/futex/futex.h +++ b/kernel/futex/futex.h @@ -319,13 +319,13 @@ static __always_inline int futex_put_value(u32 val, u32 __user *to) { if (can_do_masked_user_access()) to = masked_user_access_begin(to); - else if (!user_read_access_begin(to, sizeof(*to))) + else if (!user_write_access_begin(to, sizeof(*to))) return -EFAULT; unsafe_put_user(val, to, Efault); - user_read_access_end(); + user_write_access_end(); return 0; Efault: - user_read_access_end(); + user_write_access_end(); return -EFAULT; } -- cgit v1.2.3 From d9b05321e21e4b218de4ce8a590bf375f58b6346 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 22 Aug 2025 16:12:38 +0200 Subject: futex: Move futex_hash_free() back to __mmput() To avoid a memory leak via mm_alloc() + mmdrop() the futex cleanup code has been moved to __mmdrop(). This resulted in a warnings if the futex hash table has been allocated via vmalloc() the mmdrop() was invoked from atomic context. The free path must stay in __mmput() to ensure it is invoked from preemptible context. In order to avoid the memory leak, delay the allocation of mm_struct::mm->futex_ref to futex_hash_allocate(). This works because neither the per-CPU counter nor the private hash has been allocated and therefore - futex_private_hash() callers (such as exit_pi_state_list()) don't acquire reference if there is no private hash yet. There is also no reference put. - Regular callers (futex_hash()) fallback to global hash. No reference counting here. The futex_ref member can be allocated in futex_hash_allocate() before the private hash itself is allocated. This happens either while the first thread is created or on request. In both cases the process has just a single thread so there can be either futex operation in progress or the request to create a private hash. Move futex_hash_free() back to __mmput(); Move the allocation of mm_struct::futex_ref to futex_hash_allocate(). [ bp: Fold a follow-up fix to prevent a use-after-free: https://lore.kernel.org/r/20250830213806.sEKuuGSm@linutronix.de ] Fixes: e703b7e247503 ("futex: Move futex cleanup to __mmdrop()") Closes: https://lore.kernel.org/all/20250821102721.6deae493@kernel.org/ Reported-by: Jakub Kicinski Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov (AMD) Link: https://lkml.kernel.org/r/20250822141238.PfnkTjFb@linutronix.de --- kernel/fork.c | 2 +- kernel/futex/core.c | 16 ++++++++++++---- 2 files changed, 13 insertions(+), 5 deletions(-) (limited to 'kernel/futex') diff --git a/kernel/fork.c b/kernel/fork.c index af673856499d..c4ada32598bd 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -689,7 +689,6 @@ void __mmdrop(struct mm_struct *mm) mm_pasid_drop(mm); mm_destroy_cid(mm); percpu_counter_destroy_many(mm->rss_stat, NR_MM_COUNTERS); - futex_hash_free(mm); free_mm(mm); } @@ -1138,6 +1137,7 @@ static inline void __mmput(struct mm_struct *mm) if (mm->binfmt) module_put(mm->binfmt->module); lru_gen_del_mm(mm); + futex_hash_free(mm); mmdrop(mm); } diff --git a/kernel/futex/core.c b/kernel/futex/core.c index d9bb5567af0c..125804fbb5cb 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -1722,12 +1722,9 @@ int futex_mm_init(struct mm_struct *mm) RCU_INIT_POINTER(mm->futex_phash, NULL); mm->futex_phash_new = NULL; /* futex-ref */ + mm->futex_ref = NULL; atomic_long_set(&mm->futex_atomic, 0); mm->futex_batches = get_state_synchronize_rcu(); - mm->futex_ref = alloc_percpu(unsigned int); - if (!mm->futex_ref) - return -ENOMEM; - this_cpu_inc(*mm->futex_ref); /* 0 -> 1 */ return 0; } @@ -1801,6 +1798,17 @@ static int futex_hash_allocate(unsigned int hash_slots, unsigned int flags) } } + if (!mm->futex_ref) { + /* + * This will always be allocated by the first thread and + * therefore requires no locking. + */ + mm->futex_ref = alloc_percpu(unsigned int); + if (!mm->futex_ref) + return -ENOMEM; + this_cpu_inc(*mm->futex_ref); /* 0 -> 1 */ + } + fph = kvzalloc(struct_size(fph, queues, hash_slots), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!fph) -- cgit v1.2.3 From b549113738e8c751b613118032a724b772aa83f2 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 10 Sep 2025 12:42:43 +0200 Subject: futex: Prevent use-after-free during requeue-PI syzbot managed to trigger the following race: T1 T2 futex_wait_requeue_pi() futex_do_wait() schedule() futex_requeue() futex_proxy_trylock_atomic() futex_requeue_pi_prepare() requeue_pi_wake_futex() futex_requeue_pi_complete() /* preempt */ * timeout/ signal wakes T1 * futex_requeue_pi_wakeup_sync() // Q_REQUEUE_PI_LOCKED futex_hash_put() // back to userland, on stack futex_q is garbage /* back */ wake_up_state(q->task, TASK_NORMAL); In this scenario futex_wait_requeue_pi() is able to leave without using futex_q::lock_ptr for synchronization. This can be prevented by reading futex_q::task before updating the futex_q::requeue_state. A reference on the task_struct is not needed because requeue_pi_wake_futex() is invoked with a spinlock_t held which implies a RCU read section. Even if T1 terminates immediately after, the task_struct will remain valid during T2's wake_up_state(). A READ_ONCE on futex_q::task before futex_requeue_pi_complete() is enough because it ensures that the variable is read before the state is updated. Read futex_q::task before updating the requeue state, use it for the following wakeup. Fixes: 07d91ef510fb1 ("futex: Prevent requeue_pi() lock nesting issue on RT") Reported-by: syzbot+034246a838a10d181e78@syzkaller.appspotmail.com Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Closes: https://lore.kernel.org/all/68b75989.050a0220.3db4df.01dd.GAE@google.com/ --- kernel/futex/requeue.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel/futex') diff --git a/kernel/futex/requeue.c b/kernel/futex/requeue.c index c716a66f8692..d818b4d47f1b 100644 --- a/kernel/futex/requeue.c +++ b/kernel/futex/requeue.c @@ -230,8 +230,9 @@ static inline void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key, struct futex_hash_bucket *hb) { - q->key = *key; + struct task_struct *task; + q->key = *key; __futex_unqueue(q); WARN_ON(!q->rt_waiter); @@ -243,10 +244,11 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key, futex_hash_get(hb); q->drop_hb_ref = true; q->lock_ptr = &hb->lock; + task = READ_ONCE(q->task); /* Signal locked state to the waiter */ futex_requeue_pi_complete(q, 1); - wake_up_state(q->task, TASK_NORMAL); + wake_up_state(task, TASK_NORMAL); } /** -- cgit v1.2.3 From 6b54082c3ed4dc9821cdf0edb17302355cc5bb45 Mon Sep 17 00:00:00 2001 From: Pranav Tyagi Date: Mon, 15 Sep 2025 23:51:54 +0530 Subject: futex: Don't leak robust_list pointer on exec race sys_get_robust_list() and compat_get_robust_list() use ptrace_may_access() to check if the calling task is allowed to access another task's robust_list pointer. This check is racy against a concurrent exec() in the target process. During exec(), a task may transition from a non-privileged binary to a privileged one (e.g., setuid binary) and its credentials/memory mappings may change. If get_robust_list() performs ptrace_may_access() before this transition, it may erroneously allow access to sensitive information after the target becomes privileged. A racy access allows an attacker to exploit a window during which ptrace_may_access() passes before a target process transitions to a privileged state via exec(). For example, consider a non-privileged task T that is about to execute a setuid-root binary. An attacker task A calls get_robust_list(T) while T is still unprivileged. Since ptrace_may_access() checks permissions based on current credentials, it succeeds. However, if T begins exec immediately afterwards, it becomes privileged and may change its memory mappings. Because get_robust_list() proceeds to access T->robust_list without synchronizing with exec() it may read user-space pointers from a now-privileged process. This violates the intended post-exec access restrictions and could expose sensitive memory addresses or be used as a primitive in a larger exploit chain. Consequently, the race can lead to unauthorized disclosure of information across privilege boundaries and poses a potential security risk. Take a read lock on signal->exec_update_lock prior to invoking ptrace_may_access() and accessing the robust_list/compat_robust_list. This ensures that the target task's exec state remains stable during the check, allowing for consistent and synchronized validation of credentials. Suggested-by: Jann Horn Signed-off-by: Pranav Tyagi Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/linux-fsdevel/1477863998-3298-5-git-send-email-jann@thejh.net/ Link: https://github.com/KSPP/linux/issues/119 --- kernel/futex/syscalls.c | 106 +++++++++++++++++++++++++----------------------- 1 file changed, 56 insertions(+), 50 deletions(-) (limited to 'kernel/futex') diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c index 4b6da9116aa6..880c9bf2f315 100644 --- a/kernel/futex/syscalls.c +++ b/kernel/futex/syscalls.c @@ -39,6 +39,56 @@ SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head, return 0; } +static inline void __user *futex_task_robust_list(struct task_struct *p, bool compat) +{ +#ifdef CONFIG_COMPAT + if (compat) + return p->compat_robust_list; +#endif + return p->robust_list; +} + +static void __user *futex_get_robust_list_common(int pid, bool compat) +{ + struct task_struct *p = current; + void __user *head; + int ret; + + scoped_guard(rcu) { + if (pid) { + p = find_task_by_vpid(pid); + if (!p) + return (void __user *)ERR_PTR(-ESRCH); + } + get_task_struct(p); + } + + /* + * Hold exec_update_lock to serialize with concurrent exec() + * so ptrace_may_access() is checked against stable credentials + */ + ret = down_read_killable(&p->signal->exec_update_lock); + if (ret) + goto err_put; + + ret = -EPERM; + if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) + goto err_unlock; + + head = futex_task_robust_list(p, compat); + + up_read(&p->signal->exec_update_lock); + put_task_struct(p); + + return head; + +err_unlock: + up_read(&p->signal->exec_update_lock); +err_put: + put_task_struct(p); + return (void __user *)ERR_PTR(ret); +} + /** * sys_get_robust_list() - Get the robust-futex list head of a task * @pid: pid of the process [zero for current task] @@ -49,36 +99,14 @@ SYSCALL_DEFINE3(get_robust_list, int, pid, struct robust_list_head __user * __user *, head_ptr, size_t __user *, len_ptr) { - struct robust_list_head __user *head; - unsigned long ret; - struct task_struct *p; - - rcu_read_lock(); - - ret = -ESRCH; - if (!pid) - p = current; - else { - p = find_task_by_vpid(pid); - if (!p) - goto err_unlock; - } - - ret = -EPERM; - if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) - goto err_unlock; + struct robust_list_head __user *head = futex_get_robust_list_common(pid, false); - head = p->robust_list; - rcu_read_unlock(); + if (IS_ERR(head)) + return PTR_ERR(head); if (put_user(sizeof(*head), len_ptr)) return -EFAULT; return put_user(head, head_ptr); - -err_unlock: - rcu_read_unlock(); - - return ret; } long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, @@ -455,36 +483,14 @@ COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid, compat_uptr_t __user *, head_ptr, compat_size_t __user *, len_ptr) { - struct compat_robust_list_head __user *head; - unsigned long ret; - struct task_struct *p; - - rcu_read_lock(); - - ret = -ESRCH; - if (!pid) - p = current; - else { - p = find_task_by_vpid(pid); - if (!p) - goto err_unlock; - } - - ret = -EPERM; - if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) - goto err_unlock; + struct compat_robust_list_head __user *head = futex_get_robust_list_common(pid, true); - head = p->compat_robust_list; - rcu_read_unlock(); + if (IS_ERR(head)) + return PTR_ERR(head); if (put_user(sizeof(*head), len_ptr)) return -EFAULT; return put_user(ptr_to_compat(head), head_ptr); - -err_unlock: - rcu_read_unlock(); - - return ret; } #endif /* CONFIG_COMPAT */ -- cgit v1.2.3 From 4cb5ac2626b5704ed712ac1d46b9d89fdfc12c5d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Jul 2025 16:29:46 +0200 Subject: futex: Optimize per-cpu reference counting Shrikanth noted that the per-cpu reference counter was still some 10% slower than the old immutable option (which removes the reference counting entirely). Further optimize the per-cpu reference counter by: - switching from RCU to preempt; - using __this_cpu_*() since we now have preempt disabled; - switching from smp_load_acquire() to READ_ONCE(). This is all safe because disabling preemption inhibits the RCU grace period exactly like rcu_read_lock(). Having preemption disabled allows using __this_cpu_*() provided the only access to the variable is in task context -- which is the case here. Furthermore, since we know changing fph->state to FR_ATOMIC demands a full RCU grace period we can rely on the implied smp_mb() from that to replace the acquire barrier(). This is very similar to the percpu_down_read_internal() fast-path. The reason this is significant for PowerPC is that it uses the generic this_cpu_*() implementation which relies on local_irq_disable() (the x86 implementation relies on it being a single memop instruction to be IRQ-safe). Switching to preempt_disable() and __this_cpu*() avoids this IRQ state swizzling. Also, PowerPC needs LWSYNC for the ACQUIRE barrier, not having to use explicit barriers safes a bunch. Combined this reduces the performance gap by half, down to some 5%. Fixes: 760e6f7befba ("futex: Remove support for IMMUTABLE") Reported-by: Shrikanth Hegde Tested-by: Shrikanth Hegde Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Sebastian Andrzej Siewior Link: https://patch.msgid.link/20251106092929.GR4067720@noisy.programming.kicks-ass.net --- kernel/futex/core.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'kernel/futex') diff --git a/kernel/futex/core.c b/kernel/futex/core.c index 125804fbb5cb..2e77a6e5c865 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -1680,10 +1680,10 @@ static bool futex_ref_get(struct futex_private_hash *fph) { struct mm_struct *mm = fph->mm; - guard(rcu)(); + guard(preempt)(); - if (smp_load_acquire(&fph->state) == FR_PERCPU) { - this_cpu_inc(*mm->futex_ref); + if (READ_ONCE(fph->state) == FR_PERCPU) { + __this_cpu_inc(*mm->futex_ref); return true; } @@ -1694,10 +1694,10 @@ static bool futex_ref_put(struct futex_private_hash *fph) { struct mm_struct *mm = fph->mm; - guard(rcu)(); + guard(preempt)(); - if (smp_load_acquire(&fph->state) == FR_PERCPU) { - this_cpu_dec(*mm->futex_ref); + if (READ_ONCE(fph->state) == FR_PERCPU) { + __this_cpu_dec(*mm->futex_ref); return false; } -- cgit v1.2.3