diff options
Diffstat (limited to 'kernel/futex')
| -rw-r--r-- | kernel/futex/core.c | 1165 | ||||
| -rw-r--r-- | kernel/futex/futex.h | 190 | ||||
| -rw-r--r-- | kernel/futex/pi.c | 347 | ||||
| -rw-r--r-- | kernel/futex/requeue.c | 486 | ||||
| -rw-r--r-- | kernel/futex/syscalls.c | 341 | ||||
| -rw-r--r-- | kernel/futex/waitwake.c | 336 |
6 files changed, 2072 insertions, 793 deletions
diff --git a/kernel/futex/core.c b/kernel/futex/core.c index 514e4582b863..cf7e610eac42 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -34,9 +34,16 @@ #include <linux/compat.h> #include <linux/jhash.h> #include <linux/pagemap.h> +#include <linux/debugfs.h> +#include <linux/plist.h> +#include <linux/gfp.h> +#include <linux/vmalloc.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 "futex.h" #include "../locking/rtmutex_common.h" @@ -47,12 +54,23 @@ * reside in the same cacheline. */ static struct { - struct futex_hash_bucket *queues; - unsigned long hashsize; + unsigned long hashmask; + unsigned int hashshift; + struct futex_hash_bucket *queues[MAX_NUMNODES]; } __futex_data __read_mostly __aligned(2*sizeof(long)); -#define futex_queues (__futex_data.queues) -#define futex_hashsize (__futex_data.hashsize) +#define futex_hashmask (__futex_data.hashmask) +#define futex_hashshift (__futex_data.hashshift) +#define futex_queues (__futex_data.queues) + +struct futex_private_hash { + int state; + unsigned int hash_mask; + struct rcu_head rcu; + void *mm; + bool custom; + struct futex_hash_bucket queues[]; +}; /* * Fault injections for futexes. @@ -105,21 +123,331 @@ late_initcall(fail_futex_debugfs); #endif /* CONFIG_FAIL_FUTEX */ +static struct futex_hash_bucket * +__futex_hash(union futex_key *key, struct futex_private_hash *fph); + +#ifdef CONFIG_FUTEX_PRIVATE_HASH +static bool futex_ref_get(struct futex_private_hash *fph); +static bool futex_ref_put(struct futex_private_hash *fph); +static bool futex_ref_is_dead(struct futex_private_hash *fph); + +enum { FR_PERCPU = 0, FR_ATOMIC }; + +static inline bool futex_key_is_private(union futex_key *key) +{ + /* + * Relies on get_futex_key() to set either bit for shared + * futexes -- see comment with union futex_key. + */ + return !(key->both.offset & (FUT_OFF_INODE | FUT_OFF_MMSHARED)); +} + +static bool futex_private_hash_get(struct futex_private_hash *fph) +{ + return futex_ref_get(fph); +} + +void futex_private_hash_put(struct futex_private_hash *fph) +{ + if (futex_ref_put(fph)) + wake_up_var(fph->mm); +} + /** - * futex_hash - Return the hash bucket in the global hash - * @key: Pointer to the futex key for which the hash is calculated + * futex_hash_get - Get an additional reference for the local hash. + * @hb: ptr to the private local hash. * - * We hash on the keys returned from get_futex_key (see below) and return the - * corresponding hash bucket in the global hash. + * Obtain an additional reference for the already obtained hash bucket. The + * caller must already own an reference. */ +void futex_hash_get(struct futex_hash_bucket *hb) +{ + struct futex_private_hash *fph = hb->priv; + + if (!fph) + return; + WARN_ON_ONCE(!futex_private_hash_get(fph)); +} + +void futex_hash_put(struct futex_hash_bucket *hb) +{ + struct futex_private_hash *fph = hb->priv; + + if (!fph) + return; + futex_private_hash_put(fph); +} + +static struct futex_hash_bucket * +__futex_hash_private(union futex_key *key, struct futex_private_hash *fph) +{ + u32 hash; + + if (!futex_key_is_private(key)) + return NULL; + + if (!fph) + fph = rcu_dereference(key->private.mm->futex_phash); + if (!fph || !fph->hash_mask) + return NULL; + + hash = jhash2((void *)&key->private.address, + sizeof(key->private.address) / 4, + key->both.offset); + return &fph->queues[hash & fph->hash_mask]; +} + +static void futex_rehash_private(struct futex_private_hash *old, + struct futex_private_hash *new) +{ + struct futex_hash_bucket *hb_old, *hb_new; + unsigned int slots = old->hash_mask + 1; + unsigned int i; + + for (i = 0; i < slots; i++) { + struct futex_q *this, *tmp; + + hb_old = &old->queues[i]; + + spin_lock(&hb_old->lock); + plist_for_each_entry_safe(this, tmp, &hb_old->chain, list) { + + plist_del(&this->list, &hb_old->chain); + futex_hb_waiters_dec(hb_old); + + WARN_ON_ONCE(this->lock_ptr != &hb_old->lock); + + hb_new = __futex_hash(&this->key, new); + futex_hb_waiters_inc(hb_new); + /* + * The new pointer isn't published yet but an already + * moved user can be unqueued due to timeout or signal. + */ + spin_lock_nested(&hb_new->lock, SINGLE_DEPTH_NESTING); + plist_add(&this->list, &hb_new->chain); + this->lock_ptr = &hb_new->lock; + spin_unlock(&hb_new->lock); + } + spin_unlock(&hb_old->lock); + } +} + +static bool __futex_pivot_hash(struct mm_struct *mm, + struct futex_private_hash *new) +{ + struct futex_private_hash *fph; + + WARN_ON_ONCE(mm->futex_phash_new); + + fph = rcu_dereference_protected(mm->futex_phash, + lockdep_is_held(&mm->futex_hash_lock)); + if (fph) { + if (!futex_ref_is_dead(fph)) { + mm->futex_phash_new = new; + return false; + } + + futex_rehash_private(fph, new); + } + new->state = FR_PERCPU; + scoped_guard(rcu) { + mm->futex_batches = get_state_synchronize_rcu(); + rcu_assign_pointer(mm->futex_phash, new); + } + kvfree_rcu(fph, rcu); + return true; +} + +static void futex_pivot_hash(struct mm_struct *mm) +{ + scoped_guard(mutex, &mm->futex_hash_lock) { + struct futex_private_hash *fph; + + fph = mm->futex_phash_new; + if (fph) { + mm->futex_phash_new = NULL; + __futex_pivot_hash(mm, fph); + } + } +} + +struct futex_private_hash *futex_private_hash(void) +{ + struct mm_struct *mm = current->mm; + /* + * Ideally we don't loop. If there is a replacement in progress + * then a new private hash is already prepared and a reference can't be + * obtained once the last user dropped it's. + * In that case we block on mm_struct::futex_hash_lock and either have + * to perform the replacement or wait while someone else is doing the + * job. Eitherway, on the second iteration we acquire a reference on the + * new private hash or loop again because a new replacement has been + * requested. + */ +again: + scoped_guard(rcu) { + struct futex_private_hash *fph; + + fph = rcu_dereference(mm->futex_phash); + if (!fph) + return NULL; + + if (futex_private_hash_get(fph)) + return fph; + } + futex_pivot_hash(mm); + goto again; +} + +struct futex_hash_bucket *futex_hash(union futex_key *key) +{ + struct futex_private_hash *fph; + struct futex_hash_bucket *hb; + +again: + scoped_guard(rcu) { + hb = __futex_hash(key, NULL); + fph = hb->priv; + + if (!fph || futex_private_hash_get(fph)) + return hb; + } + futex_pivot_hash(key->private.mm); + goto again; +} + +#else /* !CONFIG_FUTEX_PRIVATE_HASH */ + +static struct futex_hash_bucket * +__futex_hash_private(union futex_key *key, struct futex_private_hash *fph) +{ + return NULL; +} + struct futex_hash_bucket *futex_hash(union futex_key *key) { - u32 hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / 4, - key->both.offset); + return __futex_hash(key, NULL); +} + +#endif /* CONFIG_FUTEX_PRIVATE_HASH */ + +#ifdef CONFIG_FUTEX_MPOL + +static int __futex_key_to_node(struct mm_struct *mm, unsigned long addr) +{ + struct vm_area_struct *vma = vma_lookup(mm, addr); + struct mempolicy *mpol; + int node = FUTEX_NO_NODE; + + if (!vma) + return FUTEX_NO_NODE; + + mpol = vma_policy(vma); + if (!mpol) + return FUTEX_NO_NODE; + + switch (mpol->mode) { + case MPOL_PREFERRED: + node = first_node(mpol->nodes); + break; + case MPOL_PREFERRED_MANY: + case MPOL_BIND: + if (mpol->home_node != NUMA_NO_NODE) + node = mpol->home_node; + break; + default: + break; + } - return &futex_queues[hash & (futex_hashsize - 1)]; + return node; } +static int futex_key_to_node_opt(struct mm_struct *mm, unsigned long addr) +{ + int seq, node; + + guard(rcu)(); + + if (!mmap_lock_speculate_try_begin(mm, &seq)) + return -EBUSY; + + node = __futex_key_to_node(mm, addr); + + if (mmap_lock_speculate_retry(mm, seq)) + return -EAGAIN; + + return node; +} + +static int futex_mpol(struct mm_struct *mm, unsigned long addr) +{ + int node; + + node = futex_key_to_node_opt(mm, addr); + if (node >= FUTEX_NO_NODE) + return node; + + guard(mmap_read_lock)(mm); + return __futex_key_to_node(mm, addr); +} + +#else /* !CONFIG_FUTEX_MPOL */ + +static int futex_mpol(struct mm_struct *mm, unsigned long addr) +{ + return FUTEX_NO_NODE; +} + +#endif /* CONFIG_FUTEX_MPOL */ + +/** + * __futex_hash - Return the hash bucket + * @key: Pointer to the futex key for which the hash is calculated + * @fph: Pointer to private hash if known + * + * We hash on the keys returned from get_futex_key (see below) and return the + * corresponding hash bucket. + * If the FUTEX is PROCESS_PRIVATE then a per-process hash bucket (from the + * private hash) is returned if existing. Otherwise a hash bucket from the + * global hash is returned. + */ +static struct futex_hash_bucket * +__futex_hash(union futex_key *key, struct futex_private_hash *fph) +{ + int node = key->both.node; + u32 hash; + + if (node == FUTEX_NO_NODE) { + struct futex_hash_bucket *hb; + + hb = __futex_hash_private(key, fph); + if (hb) + return hb; + } + + hash = jhash2((u32 *)key, + offsetof(typeof(*key), both.offset) / sizeof(u32), + key->both.offset); + + if (node == FUTEX_NO_NODE) { + /* + * In case of !FLAGS_NUMA, use some unused hash bits to pick a + * node -- this ensures regular futexes are interleaved across + * the nodes and avoids having to allocate multiple + * hash-tables. + * + * NOTE: this isn't perfectly uniform, but it is fast and + * handles sparse node masks. + */ + node = (hash >> futex_hashshift) % nr_node_ids; + if (!node_possible(node)) { + node = find_next_bit_wrap(node_possible_map.bits, + nr_node_ids, node); + } + } + + return &futex_queues[node][hash & futex_hashmask]; +} /** * futex_setup_timer - set up the sleeping hrtimer. @@ -138,9 +466,9 @@ futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, if (!time) return NULL; - hrtimer_init_sleeper_on_stack(timeout, (flags & FLAGS_CLOCKRT) ? - CLOCK_REALTIME : CLOCK_MONOTONIC, - HRTIMER_MODE_ABS); + hrtimer_setup_sleeper_on_stack(timeout, + (flags & FLAGS_CLOCKRT) ? CLOCK_REALTIME : CLOCK_MONOTONIC, + HRTIMER_MODE_ABS); /* * If range_ns is 0, calling hrtimer_set_expires_range_ns() is * effectively the same as calling hrtimer_set_expires(). @@ -179,12 +507,12 @@ static u64 get_inode_sequence_number(struct inode *inode) return old; for (;;) { - u64 new = atomic64_add_return(1, &i_seq); + u64 new = atomic64_inc_return(&i_seq); if (WARN_ON_ONCE(!new)) continue; - old = atomic64_cmpxchg_relaxed(&inode->i_sequence, 0, new); - if (old) + old = 0; + if (!atomic64_try_cmpxchg_relaxed(&inode->i_sequence, &old, new)) return old; return new; } @@ -193,7 +521,7 @@ static u64 get_inode_sequence_number(struct inode *inode) /** * get_futex_key() - Get parameters which are the keys for a futex * @uaddr: virtual address of the futex - * @fshared: false for a PROCESS_PRIVATE futex, true for PROCESS_SHARED + * @flags: FLAGS_* * @key: address where result is stored. * @rw: mapping needs to be read/write (values: FUTEX_READ, * FUTEX_WRITE) @@ -204,7 +532,7 @@ static u64 get_inode_sequence_number(struct inode *inode) * * For shared mappings (when @fshared), the key is: * - * ( inode->i_sequence, page->index, offset_within_page ) + * ( inode->i_sequence, page offset within mapping, offset_within_page ) * * [ also see get_inode_sequence_number() ] * @@ -217,29 +545,68 @@ static u64 get_inode_sequence_number(struct inode *inode) * * lock_page() might sleep, the caller should not hold a spinlock. */ -int get_futex_key(u32 __user *uaddr, bool fshared, union futex_key *key, +int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key, enum futex_access rw) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; - struct page *page, *tail; + struct page *page; + struct folio *folio; struct address_space *mapping; - int err, ro = 0; + int node, err, size, ro = 0; + bool node_updated = false; + bool fshared; + + fshared = flags & FLAGS_SHARED; + size = futex_size(flags); + if (flags & FLAGS_NUMA) + size *= 2; /* * The futex address must be "naturally" aligned. */ key->both.offset = address % PAGE_SIZE; - if (unlikely((address % sizeof(u32)) != 0)) + if (unlikely((address % size) != 0)) return -EINVAL; address -= key->both.offset; - if (unlikely(!access_ok(uaddr, sizeof(u32)))) + if (unlikely(!access_ok(uaddr, size))) return -EFAULT; if (unlikely(should_fail_futex(fshared))) return -EFAULT; + node = FUTEX_NO_NODE; + + if (flags & FLAGS_NUMA) { + u32 __user *naddr = (void *)uaddr + size / 2; + + if (get_user_inline(node, naddr)) + return -EFAULT; + + if ((node != FUTEX_NO_NODE) && + ((unsigned int)node >= MAX_NUMNODES || !node_possible(node))) + return -EINVAL; + } + + if (node == FUTEX_NO_NODE && (flags & FLAGS_MPOL)) { + node = futex_mpol(mm, address); + node_updated = true; + } + + if (flags & FLAGS_NUMA) { + u32 __user *naddr = (void *)uaddr + size / 2; + + if (node == FUTEX_NO_NODE) { + node = numa_node_id(); + node_updated = true; + } + if (node_updated && put_user_inline(node, naddr)) + return -EFAULT; + } + + key->both.node = node; + /* * PROCESS_PRIVATE futexes are fast. * As the mm cannot disappear under us and the 'key' only needs @@ -248,7 +615,17 @@ int get_futex_key(u32 __user *uaddr, bool fshared, union futex_key *key, * but access_ok() should be faster than find_vma() */ if (!fshared) { - key->private.mm = mm; + /* + * On no-MMU, shared futexes are treated as private, therefore + * we must not include the current process in the key. Since + * there is only one address space, the address is a unique key + * on its own. + */ + if (IS_ENABLED(CONFIG_MMU)) + key->private.mm = mm; + else + key->private.mm = NULL; + key->private.address = address; return 0; } @@ -273,54 +650,52 @@ again: err = 0; /* - * The treatment of mapping from this point on is critical. The page - * lock protects many things but in this context the page lock + * The treatment of mapping from this point on is critical. The folio + * lock protects many things but in this context the folio lock * stabilizes mapping, prevents inode freeing in the shared * file-backed region case and guards against movement to swap cache. * - * Strictly speaking the page lock is not needed in all cases being - * considered here and page lock forces unnecessarily serialization + * Strictly speaking the folio lock is not needed in all cases being + * considered here and folio lock forces unnecessarily serialization. * From this point on, mapping will be re-verified if necessary and - * page lock will be acquired only if it is unavoidable + * folio lock will be acquired only if it is unavoidable * - * Mapping checks require the head page for any compound page so the - * head page and mapping is looked up now. For anonymous pages, it - * does not matter if the page splits in the future as the key is - * based on the address. For filesystem-backed pages, the tail is - * required as the index of the page determines the key. For - * base pages, there is no tail page and tail == page. + * Mapping checks require the folio so it is looked up now. For + * anonymous pages, it does not matter if the folio is split + * in the future as the key is based on the address. For + * filesystem-backed pages, the precise page is required as the + * index of the page determines the key. */ - tail = page; - page = compound_head(page); - mapping = READ_ONCE(page->mapping); + folio = page_folio(page); + mapping = READ_ONCE(folio->mapping); /* - * If page->mapping is NULL, then it cannot be a PageAnon + * If folio->mapping is NULL, then it cannot be an anonymous * page; but it might be the ZERO_PAGE or in the gate area or * in a special mapping (all cases which we are happy to fail); * or it may have been a good file page when get_user_pages_fast * found it, but truncated or holepunched or subjected to - * invalidate_complete_page2 before we got the page lock (also + * invalidate_complete_page2 before we got the folio lock (also * cases which we are happy to fail). And we hold a reference, * so refcount care in invalidate_inode_page's remove_mapping * prevents drop_caches from setting mapping to NULL beneath us. * * The case we do have to guard against is when memory pressure made * shmem_writepage move it from filecache to swapcache beneath us: - * an unlikely race, but we do need to retry for page->mapping. + * an unlikely race, but we do need to retry for folio->mapping. */ if (unlikely(!mapping)) { int shmem_swizzled; /* - * Page lock is required to identify which special case above - * applies. If this is really a shmem page then the page lock + * Folio lock is required to identify which special case above + * applies. If this is really a shmem page then the folio lock * will prevent unexpected transitions. */ - lock_page(page); - shmem_swizzled = PageSwapCache(page) || page->mapping; - unlock_page(page); - put_page(page); + folio_lock(folio); + shmem_swizzled = folio_test_swapcache(folio) || folio->mapping; + folio_unlock(folio); + folio_put(folio); if (shmem_swizzled) goto again; @@ -331,14 +706,14 @@ again: /* * Private mappings are handled in a simple way. * - * If the futex key is stored on an anonymous page, then the associated + * If the futex key is stored in anonymous memory, then the associated * object is the mm which is implicitly pinned by the calling process. * * NOTE: When userspace waits on a MAP_SHARED mapping, even if * it's a read-only handle, it's expected that futexes attach to * the object not the particular process. */ - if (PageAnon(page)) { + if (folio_test_anon(folio)) { /* * A RO anonymous page will never change and thus doesn't make * sense for futex operations. @@ -357,10 +732,10 @@ again: /* * The associated futex object in this case is the inode and - * the page->mapping must be traversed. Ordinarily this should - * be stabilised under page lock but it's not strictly + * the folio->mapping must be traversed. Ordinarily this should + * be stabilised under folio lock but it's not strictly * necessary in this case as we just want to pin the inode, not - * update the radix tree or anything like that. + * update i_pages or anything like that. * * The RCU read lock is taken as the inode is finally freed * under RCU. If the mapping still matches expectations then the @@ -368,9 +743,9 @@ again: */ rcu_read_lock(); - if (READ_ONCE(page->mapping) != mapping) { + if (READ_ONCE(folio->mapping) != mapping) { rcu_read_unlock(); - put_page(page); + folio_put(folio); goto again; } @@ -378,19 +753,19 @@ again: inode = READ_ONCE(mapping->host); if (!inode) { rcu_read_unlock(); - put_page(page); + folio_put(folio); goto again; } key->both.offset |= FUT_OFF_INODE; /* inode-based key */ key->shared.i_seq = get_inode_sequence_number(inode); - key->shared.pgoff = page_to_pgoff(tail); + key->shared.pgoff = page_pgoff(folio, page); rcu_read_unlock(); } out: - put_page(page); + folio_put(folio); return err; } @@ -437,28 +812,6 @@ struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, union futex_key * return NULL; } -int futex_cmpxchg_value_locked(u32 *curval, u32 __user *uaddr, u32 uval, u32 newval) -{ - int ret; - - pagefault_disable(); - ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval); - pagefault_enable(); - - return ret; -} - -int futex_get_value_locked(u32 *dest, u32 __user *from) -{ - int ret; - - pagefault_disable(); - ret = __get_user(*dest, from); - pagefault_enable(); - - return ret ? -EFAULT : 0; -} - /** * wait_for_owner_exiting - Block until the owner has exited * @ret: owner's current futex lock status @@ -510,13 +863,9 @@ void __futex_unqueue(struct futex_q *q) } /* The key must be already stored in q->key. */ -struct futex_hash_bucket *futex_q_lock(struct futex_q *q) +void futex_q_lock(struct futex_q *q, struct futex_hash_bucket *hb) __acquires(&hb->lock) { - struct futex_hash_bucket *hb; - - hb = futex_hash(&q->key); - /* * Increment the counter before taking the lock so that * a potential waker won't miss a to-be-slept task that is @@ -530,17 +879,17 @@ struct futex_hash_bucket *futex_q_lock(struct futex_q *q) q->lock_ptr = &hb->lock; spin_lock(&hb->lock); - return hb; } void futex_q_unlock(struct futex_hash_bucket *hb) __releases(&hb->lock) { - spin_unlock(&hb->lock); futex_hb_waiters_dec(hb); + spin_unlock(&hb->lock); } -void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb) +void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb, + struct task_struct *task) { int prio; @@ -556,7 +905,7 @@ void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb) plist_node_init(&q->list, prio); plist_add(&q->list, &hb->chain); - q->task = current; + q->task = task; } /** @@ -575,6 +924,8 @@ int futex_unqueue(struct futex_q *q) spinlock_t *lock_ptr; int ret = 0; + /* RCU so lock_ptr is not going away during locking. */ + guard(rcu)(); /* In the common case we don't take the spinlock, which is nice. */ retry: /* @@ -613,13 +964,40 @@ retry: return ret; } +void futex_q_lockptr_lock(struct futex_q *q) +{ + spinlock_t *lock_ptr; + + /* + * See futex_unqueue() why lock_ptr can change. + */ + guard(rcu)(); +retry: + lock_ptr = READ_ONCE(q->lock_ptr); + spin_lock(lock_ptr); + + if (unlikely(lock_ptr != q->lock_ptr)) { + spin_unlock(lock_ptr); + goto retry; + } +} + /* - * PI futexes can not be requeued and must remove themselves from the - * hash bucket. The hash bucket lock (i.e. lock_ptr) is held. + * PI futexes can not be requeued and must remove themselves from the hash + * bucket. The hash bucket lock (i.e. lock_ptr) is held. */ void futex_unqueue_pi(struct futex_q *q) { - __futex_unqueue(q); + /* + * If the lock was not acquired (due to timeout or signal) then the + * rt_waiter is removed before futex_q is. If this is observed by + * an unlocker after dropping the rtmutex wait lock and before + * acquiring the hash bucket lock, then the unlocker dequeues the + * futex_q from the hash bucket list to guarantee consistent state + * vs. userspace. Therefore the dequeue here must be conditional. + */ + if (!plist_node_empty(&q->list)) + __futex_unqueue(q); BUG_ON(!q->pi_state); put_pi_state(q->pi_state); @@ -688,7 +1066,8 @@ retry: owner = uval & FUTEX_TID_MASK; if (pending_op && !pi && !owner) { - futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY); + futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, + FUTEX_BITSET_MATCH_ANY); return 0; } @@ -740,8 +1119,10 @@ retry: * Wake robust non-PI futexes here. The wakeup of * PI futexes happens in exit_pi_state(): */ - if (!pi && (uval & FUTEX_WAITERS)) - futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY); + if (!pi && (uval & FUTEX_WAITERS)) { + futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, + FUTEX_BITSET_MATCH_ANY); + } return 0; } @@ -944,10 +1325,20 @@ static void exit_pi_state_list(struct task_struct *curr) { struct list_head *next, *head = &curr->pi_state_list; struct futex_pi_state *pi_state; - struct futex_hash_bucket *hb; union futex_key key = FUTEX_KEY_INIT; /* + * The mutex mm_struct::futex_hash_lock might be acquired. + */ + might_sleep(); + /* + * Ensure the hash remains stable (no resize) during the while loop + * below. The hb pointer is acquired under the pi_lock so we can't block + * on the mutex. + */ + WARN_ON(curr != current); + guard(private_hash)(); + /* * We are a ZOMBIE and nobody can enqueue itself on * pi_state_list anymore, but we have to be careful * versus waiters unqueueing themselves: @@ -957,50 +1348,52 @@ static void exit_pi_state_list(struct task_struct *curr) next = head->next; pi_state = list_entry(next, struct futex_pi_state, list); key = pi_state->key; - hb = futex_hash(&key); - - /* - * We can race against put_pi_state() removing itself from the - * list (a waiter going away). put_pi_state() will first - * decrement the reference count and then modify the list, so - * its possible to see the list entry but fail this reference - * acquire. - * - * In that case; drop the locks to let put_pi_state() make - * progress and retry the loop. - */ - if (!refcount_inc_not_zero(&pi_state->refcount)) { + if (1) { + CLASS(hb, hb)(&key); + + /* + * We can race against put_pi_state() removing itself from the + * list (a waiter going away). put_pi_state() will first + * decrement the reference count and then modify the list, so + * its possible to see the list entry but fail this reference + * acquire. + * + * In that case; drop the locks to let put_pi_state() make + * progress and retry the loop. + */ + if (!refcount_inc_not_zero(&pi_state->refcount)) { + raw_spin_unlock_irq(&curr->pi_lock); + cpu_relax(); + raw_spin_lock_irq(&curr->pi_lock); + continue; + } raw_spin_unlock_irq(&curr->pi_lock); - cpu_relax(); - raw_spin_lock_irq(&curr->pi_lock); - continue; - } - raw_spin_unlock_irq(&curr->pi_lock); - spin_lock(&hb->lock); - raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); - raw_spin_lock(&curr->pi_lock); - /* - * We dropped the pi-lock, so re-check whether this - * task still owns the PI-state: - */ - if (head->next != next) { - /* retain curr->pi_lock for the loop invariant */ - raw_spin_unlock(&pi_state->pi_mutex.wait_lock); + spin_lock(&hb->lock); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + raw_spin_lock(&curr->pi_lock); + /* + * We dropped the pi-lock, so re-check whether this + * task still owns the PI-state: + */ + if (head->next != next) { + /* retain curr->pi_lock for the loop invariant */ + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); + spin_unlock(&hb->lock); + put_pi_state(pi_state); + continue; + } + + WARN_ON(pi_state->owner != curr); + WARN_ON(list_empty(&pi_state->list)); + list_del_init(&pi_state->list); + pi_state->owner = NULL; + + raw_spin_unlock(&curr->pi_lock); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); - put_pi_state(pi_state); - continue; } - WARN_ON(pi_state->owner != curr); - WARN_ON(list_empty(&pi_state->list)); - list_del_init(&pi_state->list); - pi_state->owner = NULL; - - raw_spin_unlock(&curr->pi_lock); - raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); - spin_unlock(&hb->lock); - rt_mutex_futex_unlock(&pi_state->pi_mutex); put_pi_state(pi_state); @@ -1120,30 +1513,500 @@ void futex_exit_release(struct task_struct *tsk) futex_cleanup_end(tsk, FUTEX_STATE_DEAD); } +static void futex_hash_bucket_init(struct futex_hash_bucket *fhb, + struct futex_private_hash *fph) +{ +#ifdef CONFIG_FUTEX_PRIVATE_HASH + fhb->priv = fph; +#endif + atomic_set(&fhb->waiters, 0); + plist_head_init(&fhb->chain); + spin_lock_init(&fhb->lock); +} + +#define FH_CUSTOM 0x01 + +#ifdef CONFIG_FUTEX_PRIVATE_HASH + +/* + * futex-ref + * + * Heavily inspired by percpu-rwsem/percpu-refcount; not reusing any of that + * code because it just doesn't fit right. + * + * Dual counter, per-cpu / atomic approach like percpu-refcount, except it + * re-initializes the state automatically, such that the fph swizzle is also a + * transition back to per-cpu. + */ + +static void futex_ref_rcu(struct rcu_head *head); + +static void __futex_ref_atomic_begin(struct futex_private_hash *fph) +{ + struct mm_struct *mm = fph->mm; + + /* + * The counter we're about to switch to must have fully switched; + * otherwise it would be impossible for it to have reported success + * from futex_ref_is_dead(). + */ + WARN_ON_ONCE(atomic_long_read(&mm->futex_atomic) != 0); + + /* + * Set the atomic to the bias value such that futex_ref_{get,put}() + * will never observe 0. Will be fixed up in __futex_ref_atomic_end() + * when folding in the percpu count. + */ + atomic_long_set(&mm->futex_atomic, LONG_MAX); + smp_store_release(&fph->state, FR_ATOMIC); + + call_rcu_hurry(&mm->futex_rcu, futex_ref_rcu); +} + +static void __futex_ref_atomic_end(struct futex_private_hash *fph) +{ + struct mm_struct *mm = fph->mm; + unsigned int count = 0; + long ret; + int cpu; + + /* + * Per __futex_ref_atomic_begin() the state of the fph must be ATOMIC + * and per this RCU callback, everybody must now observe this state and + * use the atomic variable. + */ + WARN_ON_ONCE(fph->state != FR_ATOMIC); + + /* + * Therefore the per-cpu counter is now stable, sum and reset. + */ + for_each_possible_cpu(cpu) { + unsigned int *ptr = per_cpu_ptr(mm->futex_ref, cpu); + count += *ptr; + *ptr = 0; + } + + /* + * Re-init for the next cycle. + */ + this_cpu_inc(*mm->futex_ref); /* 0 -> 1 */ + + /* + * Add actual count, subtract bias and initial refcount. + * + * The moment this atomic operation happens, futex_ref_is_dead() can + * become true. + */ + ret = atomic_long_add_return(count - LONG_MAX - 1, &mm->futex_atomic); + if (!ret) + wake_up_var(mm); + + WARN_ON_ONCE(ret < 0); + mmput_async(mm); +} + +static void futex_ref_rcu(struct rcu_head *head) +{ + struct mm_struct *mm = container_of(head, struct mm_struct, futex_rcu); + struct futex_private_hash *fph = rcu_dereference_raw(mm->futex_phash); + + if (fph->state == FR_PERCPU) { + /* + * Per this extra grace-period, everybody must now observe + * fph as the current fph and no previously observed fph's + * are in-flight. + * + * Notably, nobody will now rely on the atomic + * futex_ref_is_dead() state anymore so we can begin the + * migration of the per-cpu counter into the atomic. + */ + __futex_ref_atomic_begin(fph); + return; + } + + __futex_ref_atomic_end(fph); +} + +/* + * Drop the initial refcount and transition to atomics. + */ +static void futex_ref_drop(struct futex_private_hash *fph) +{ + struct mm_struct *mm = fph->mm; + + /* + * Can only transition the current fph; + */ + WARN_ON_ONCE(rcu_dereference_raw(mm->futex_phash) != fph); + /* + * We enqueue at least one RCU callback. Ensure mm stays if the task + * exits before the transition is completed. + */ + mmget(mm); + + /* + * In order to avoid the following scenario: + * + * futex_hash() __futex_pivot_hash() + * guard(rcu); guard(mm->futex_hash_lock); + * fph = mm->futex_phash; + * rcu_assign_pointer(&mm->futex_phash, new); + * futex_hash_allocate() + * futex_ref_drop() + * fph->state = FR_ATOMIC; + * atomic_set(, BIAS); + * + * futex_private_hash_get(fph); // OOPS + * + * Where an old fph (which is FR_ATOMIC) and should fail on + * inc_not_zero, will succeed because a new transition is started and + * the atomic is bias'ed away from 0. + * + * There must be at least one full grace-period between publishing a + * new fph and trying to replace it. + */ + if (poll_state_synchronize_rcu(mm->futex_batches)) { + /* + * There was a grace-period, we can begin now. + */ + __futex_ref_atomic_begin(fph); + return; + } + + call_rcu_hurry(&mm->futex_rcu, futex_ref_rcu); +} + +static bool futex_ref_get(struct futex_private_hash *fph) +{ + struct mm_struct *mm = fph->mm; + + guard(preempt)(); + + if (READ_ONCE(fph->state) == FR_PERCPU) { + __this_cpu_inc(*mm->futex_ref); + return true; + } + + return atomic_long_inc_not_zero(&mm->futex_atomic); +} + +static bool futex_ref_put(struct futex_private_hash *fph) +{ + struct mm_struct *mm = fph->mm; + + guard(preempt)(); + + if (READ_ONCE(fph->state) == FR_PERCPU) { + __this_cpu_dec(*mm->futex_ref); + return false; + } + + return atomic_long_dec_and_test(&mm->futex_atomic); +} + +static bool futex_ref_is_dead(struct futex_private_hash *fph) +{ + struct mm_struct *mm = fph->mm; + + guard(rcu)(); + + if (smp_load_acquire(&fph->state) == FR_PERCPU) + return false; + + return atomic_long_read(&mm->futex_atomic) == 0; +} + +int futex_mm_init(struct mm_struct *mm) +{ + mutex_init(&mm->futex_hash_lock); + 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(); + return 0; +} + +void futex_hash_free(struct mm_struct *mm) +{ + struct futex_private_hash *fph; + + free_percpu(mm->futex_ref); + kvfree(mm->futex_phash_new); + fph = rcu_dereference_raw(mm->futex_phash); + if (fph) + kvfree(fph); +} + +static bool futex_pivot_pending(struct mm_struct *mm) +{ + struct futex_private_hash *fph; + + guard(rcu)(); + + if (!mm->futex_phash_new) + return true; + + fph = rcu_dereference(mm->futex_phash); + return futex_ref_is_dead(fph); +} + +static bool futex_hash_less(struct futex_private_hash *a, + struct futex_private_hash *b) +{ + /* user provided always wins */ + if (!a->custom && b->custom) + return true; + if (a->custom && !b->custom) + return false; + + /* zero-sized hash wins */ + if (!b->hash_mask) + return true; + if (!a->hash_mask) + return false; + + /* keep the biggest */ + if (a->hash_mask < b->hash_mask) + return true; + if (a->hash_mask > b->hash_mask) + return false; + + return false; /* equal */ +} + +static int futex_hash_allocate(unsigned int hash_slots, unsigned int flags) +{ + struct mm_struct *mm = current->mm; + struct futex_private_hash *fph; + bool custom = flags & FH_CUSTOM; + int i; + + if (hash_slots && (hash_slots == 1 || !is_power_of_2(hash_slots))) + return -EINVAL; + + /* + * Once we've disabled the global hash there is no way back. + */ + scoped_guard(rcu) { + fph = rcu_dereference(mm->futex_phash); + if (fph && !fph->hash_mask) { + if (custom) + return -EBUSY; + return 0; + } + } + + 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) + return -ENOMEM; + + fph->hash_mask = hash_slots ? hash_slots - 1 : 0; + fph->custom = custom; + fph->mm = mm; + + for (i = 0; i < hash_slots; i++) + futex_hash_bucket_init(&fph->queues[i], fph); + + if (custom) { + /* + * Only let prctl() wait / retry; don't unduly delay clone(). + */ +again: + wait_var_event(mm, futex_pivot_pending(mm)); + } + + scoped_guard(mutex, &mm->futex_hash_lock) { + struct futex_private_hash *free __free(kvfree) = NULL; + struct futex_private_hash *cur, *new; + + cur = rcu_dereference_protected(mm->futex_phash, + lockdep_is_held(&mm->futex_hash_lock)); + new = mm->futex_phash_new; + mm->futex_phash_new = NULL; + + if (fph) { + if (cur && !cur->hash_mask) { + /* + * If two threads simultaneously request the global + * hash then the first one performs the switch, + * the second one returns here. + */ + free = fph; + mm->futex_phash_new = new; + return -EBUSY; + } + if (cur && !new) { + /* + * If we have an existing hash, but do not yet have + * allocated a replacement hash, drop the initial + * reference on the existing hash. + */ + futex_ref_drop(cur); + } + + if (new) { + /* + * Two updates raced; throw out the lesser one. + */ + if (futex_hash_less(new, fph)) { + free = new; + new = fph; + } else { + free = fph; + } + } else { + new = fph; + } + fph = NULL; + } + + if (new) { + /* + * Will set mm->futex_phash_new on failure; + * futex_private_hash_get() will try again. + */ + if (!__futex_pivot_hash(mm, new) && custom) + goto again; + } + } + return 0; +} + +int futex_hash_allocate_default(void) +{ + unsigned int threads, buckets, current_buckets = 0; + struct futex_private_hash *fph; + + if (!current->mm) + return 0; + + scoped_guard(rcu) { + threads = min_t(unsigned int, + get_nr_threads(current), + num_online_cpus()); + + fph = rcu_dereference(current->mm->futex_phash); + if (fph) { + if (fph->custom) + return 0; + + current_buckets = fph->hash_mask + 1; + } + } + + /* + * The default allocation will remain within + * 16 <= threads * 4 <= global hash size + */ + buckets = roundup_pow_of_two(4 * threads); + buckets = clamp(buckets, 16, futex_hashmask + 1); + + if (current_buckets >= buckets) + return 0; + + return futex_hash_allocate(buckets, 0); +} + +static int futex_hash_get_slots(void) +{ + struct futex_private_hash *fph; + + guard(rcu)(); + fph = rcu_dereference(current->mm->futex_phash); + if (fph && fph->hash_mask) + return fph->hash_mask + 1; + return 0; +} + +#else + +static int futex_hash_allocate(unsigned int hash_slots, unsigned int flags) +{ + return -EINVAL; +} + +static int futex_hash_get_slots(void) +{ + return 0; +} + +#endif + +int futex_hash_prctl(unsigned long arg2, unsigned long arg3, unsigned long arg4) +{ + unsigned int flags = FH_CUSTOM; + int ret; + + switch (arg2) { + case PR_FUTEX_HASH_SET_SLOTS: + if (arg4) + return -EINVAL; + ret = futex_hash_allocate(arg3, flags); + break; + + case PR_FUTEX_HASH_GET_SLOTS: + ret = futex_hash_get_slots(); + break; + + default: + ret = -EINVAL; + break; + } + return ret; +} + static int __init futex_init(void) { - unsigned int futex_shift; - unsigned long i; + unsigned long hashsize, i; + unsigned int order, n; + unsigned long size; -#if CONFIG_BASE_SMALL - futex_hashsize = 16; +#ifdef CONFIG_BASE_SMALL + hashsize = 16; #else - futex_hashsize = roundup_pow_of_two(256 * num_possible_cpus()); + hashsize = 256 * num_possible_cpus(); + hashsize /= num_possible_nodes(); + hashsize = max(4, hashsize); + hashsize = roundup_pow_of_two(hashsize); #endif + futex_hashshift = ilog2(hashsize); + size = sizeof(struct futex_hash_bucket) * hashsize; + order = get_order(size); + + for_each_node(n) { + struct futex_hash_bucket *table; + + if (order > MAX_PAGE_ORDER) + table = vmalloc_huge_node(size, GFP_KERNEL, n); + else + table = alloc_pages_exact_nid(n, size, GFP_KERNEL); + + BUG_ON(!table); + + for (i = 0; i < hashsize; i++) + futex_hash_bucket_init(&table[i], NULL); - futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues), - futex_hashsize, 0, - futex_hashsize < 256 ? HASH_SMALL : 0, - &futex_shift, NULL, - futex_hashsize, futex_hashsize); - futex_hashsize = 1UL << futex_shift; - - for (i = 0; i < futex_hashsize; i++) { - atomic_set(&futex_queues[i].waiters, 0); - plist_head_init(&futex_queues[i].chain); - spin_lock_init(&futex_queues[i].lock); + futex_queues[n] = table; } + futex_hashmask = hashsize - 1; + pr_info("futex hash table entries: %lu (%lu bytes on %d NUMA nodes, total %lu KiB, %s).\n", + hashsize, size, num_possible_nodes(), size * num_possible_nodes() / 1024, + order > MAX_PAGE_ORDER ? "vmalloc" : "linear"); return 0; } core_initcall(futex_init); diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h index b5379c0e6d6d..30c2afa03889 100644 --- a/kernel/futex/futex.h +++ b/kernel/futex/futex.h @@ -5,6 +5,9 @@ #include <linux/futex.h> #include <linux/rtmutex.h> #include <linux/sched/wake_q.h> +#include <linux/compat.h> +#include <linux/uaccess.h> +#include <linux/cleanup.h> #ifdef CONFIG_PREEMPT_RT #include <linux/rcuwait.h> @@ -16,17 +19,103 @@ * Futex flags used to encode options to functions and preserve them across * restarts. */ +#define FLAGS_SIZE_8 0x0000 +#define FLAGS_SIZE_16 0x0001 +#define FLAGS_SIZE_32 0x0002 +#define FLAGS_SIZE_64 0x0003 + +#define FLAGS_SIZE_MASK 0x0003 + #ifdef CONFIG_MMU -# define FLAGS_SHARED 0x01 +# define FLAGS_SHARED 0x0010 #else /* * NOMMU does not have per process address space. Let the compiler optimize * code away. */ -# define FLAGS_SHARED 0x00 +# define FLAGS_SHARED 0x0000 #endif -#define FLAGS_CLOCKRT 0x02 -#define FLAGS_HAS_TIMEOUT 0x04 +#define FLAGS_CLOCKRT 0x0020 +#define FLAGS_HAS_TIMEOUT 0x0040 +#define FLAGS_NUMA 0x0080 +#define FLAGS_STRICT 0x0100 +#define FLAGS_MPOL 0x0200 + +/* FUTEX_ to FLAGS_ */ +static inline unsigned int futex_to_flags(unsigned int op) +{ + unsigned int flags = FLAGS_SIZE_32; + + if (!(op & FUTEX_PRIVATE_FLAG)) + flags |= FLAGS_SHARED; + + if (op & FUTEX_CLOCK_REALTIME) + flags |= FLAGS_CLOCKRT; + + return flags; +} + +#define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_NUMA | FUTEX2_MPOL | FUTEX2_PRIVATE) + +/* FUTEX2_ to FLAGS_ */ +static inline unsigned int futex2_to_flags(unsigned int flags2) +{ + unsigned int flags = flags2 & FUTEX2_SIZE_MASK; + + if (!(flags2 & FUTEX2_PRIVATE)) + flags |= FLAGS_SHARED; + + if (flags2 & FUTEX2_NUMA) + flags |= FLAGS_NUMA; + + if (flags2 & FUTEX2_MPOL) + flags |= FLAGS_MPOL; + + return flags; +} + +static inline unsigned int futex_size(unsigned int flags) +{ + return 1 << (flags & FLAGS_SIZE_MASK); +} + +static inline bool futex_flags_valid(unsigned int flags) +{ + /* Only 64bit futexes for 64bit code */ + if (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall()) { + if ((flags & FLAGS_SIZE_MASK) == FLAGS_SIZE_64) + return false; + } + + /* Only 32bit futexes are implemented -- for now */ + if ((flags & FLAGS_SIZE_MASK) != FLAGS_SIZE_32) + return false; + + /* + * Must be able to represent both FUTEX_NO_NODE and every valid nodeid + * in a futex word. + */ + if (flags & FLAGS_NUMA) { + int bits = 8 * futex_size(flags); + u64 max = ~0ULL; + + max >>= 64 - bits; + if (nr_node_ids >= max) + return false; + } + + return true; +} + +static inline bool futex_validate_input(unsigned int flags, u64 val) +{ + int bits = 8 * futex_size(flags); + + if (bits < 64 && (val >> bits)) + return false; + + return true; +} #ifdef CONFIG_FAIL_FUTEX extern bool should_fail_futex(bool fshared); @@ -46,6 +135,7 @@ struct futex_hash_bucket { atomic_t waiters; spinlock_t lock; struct plist_head chain; + struct futex_private_hash *priv; } ____cacheline_aligned_in_smp; /* @@ -69,17 +159,23 @@ struct futex_pi_state { union futex_key key; } __randomize_layout; +struct futex_q; +typedef void (futex_wake_fn)(struct wake_q_head *wake_q, struct futex_q *q); + /** * struct futex_q - The hashed futex queue entry, one per waiting task * @list: priority-sorted list of tasks waiting on this futex * @task: the task waiting on the futex * @lock_ptr: the hash bucket lock + * @wake: the wake handler for this queue + * @wake_data: data associated with the wake handler * @key: the key the futex is hashed on * @pi_state: optional priority inheritance state * @rt_waiter: rt_waiter storage for use with requeue_pi * @requeue_pi_key: the requeue_pi target futex key * @bitset: bitset for the optional bitmasked wakeup * @requeue_state: State field for futex_requeue_pi() + * @drop_hb_ref: Waiter should drop the extra hash bucket reference if true * @requeue_wait: RCU wait for futex_requeue_pi() (RT only) * * We use this hashed waitqueue, instead of a normal wait_queue_entry_t, so @@ -98,12 +194,15 @@ struct futex_q { struct task_struct *task; spinlock_t *lock_ptr; + futex_wake_fn *wake; + void *wake_data; union futex_key key; struct futex_pi_state *pi_state; struct rt_mutex_waiter *rt_waiter; union futex_key *requeue_pi_key; u32 bitset; atomic_t requeue_state; + bool drop_hb_ref; #ifdef CONFIG_PREEMPT_RT struct rcuwait requeue_wait; #endif @@ -116,14 +215,35 @@ enum futex_access { FUTEX_WRITE }; -extern int get_futex_key(u32 __user *uaddr, bool fshared, union futex_key *key, +extern int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key, enum futex_access rw); - +extern void futex_q_lockptr_lock(struct futex_q *q); extern struct hrtimer_sleeper * futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, int flags, u64 range_ns); extern struct futex_hash_bucket *futex_hash(union futex_key *key); +#ifdef CONFIG_FUTEX_PRIVATE_HASH +extern void futex_hash_get(struct futex_hash_bucket *hb); +extern void futex_hash_put(struct futex_hash_bucket *hb); + +extern struct futex_private_hash *futex_private_hash(void); +extern void futex_private_hash_put(struct futex_private_hash *fph); + +#else /* !CONFIG_FUTEX_PRIVATE_HASH */ +static inline void futex_hash_get(struct futex_hash_bucket *hb) { } +static inline void futex_hash_put(struct futex_hash_bucket *hb) { } +static inline struct futex_private_hash *futex_private_hash(void) { return NULL; } +static inline void futex_private_hash_put(struct futex_private_hash *fph) { } +#endif + +DEFINE_CLASS(hb, struct futex_hash_bucket *, + if (_T) futex_hash_put(_T), + futex_hash(key), union futex_key *key); + +DEFINE_CLASS(private_hash, struct futex_private_hash *, + if (_T) futex_private_hash_put(_T), + futex_private_hash(), void); /** * futex_match - Check whether two futex keys are equal @@ -141,24 +261,43 @@ static inline int futex_match(union futex_key *key1, union futex_key *key2) } extern int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags, - struct futex_q *q, struct futex_hash_bucket **hb); -extern void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q, - struct hrtimer_sleeper *timeout); + struct futex_q *q, union futex_key *key2, + struct task_struct *task); +extern void futex_do_wait(struct futex_q *q, struct hrtimer_sleeper *timeout); +extern bool __futex_wake_mark(struct futex_q *q); extern void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q); extern int fault_in_user_writeable(u32 __user *uaddr); -extern int futex_cmpxchg_value_locked(u32 *curval, u32 __user *uaddr, u32 uval, u32 newval); -extern int futex_get_value_locked(u32 *dest, u32 __user *from); extern struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, union futex_key *key); +static inline int futex_cmpxchg_value_locked(u32 *curval, u32 __user *uaddr, u32 uval, u32 newval) +{ + int ret; + + pagefault_disable(); + ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval); + pagefault_enable(); + + return ret; +} + +/* Read from user memory with pagefaults disabled */ +static inline int futex_get_value_locked(u32 *dest, u32 __user *from) +{ + guard(pagefault)(); + return get_user_inline(*dest, from); +} + extern void __futex_unqueue(struct futex_q *q); -extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb); +extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb, + struct task_struct *task); extern int futex_unqueue(struct futex_q *q); /** * futex_queue() - Enqueue the futex_q on the futex_hash_bucket * @q: The futex_q to enqueue * @hb: The destination hash bucket + * @task: Task queueing this futex * * The hb->lock must be held by the caller, and is released here. A call to * futex_queue() is typically paired with exactly one call to futex_unqueue(). The @@ -166,11 +305,14 @@ extern int futex_unqueue(struct futex_q *q); * or nothing if the unqueue is done as part of the wake process and the unqueue * state is implicit in the state of woken task (see futex_wait_requeue_pi() for * an example). + * + * Note that @task may be NULL, for async usage of futexes. */ -static inline void futex_queue(struct futex_q *q, struct futex_hash_bucket *hb) +static inline void futex_queue(struct futex_q *q, struct futex_hash_bucket *hb, + struct task_struct *task) __releases(&hb->lock) { - __futex_queue(q, hb); + __futex_queue(q, hb, task); spin_unlock(&hb->lock); } @@ -216,7 +358,7 @@ static inline int futex_hb_waiters_pending(struct futex_hash_bucket *hb) #endif } -extern struct futex_hash_bucket *futex_q_lock(struct futex_q *q); +extern void futex_q_lock(struct futex_q *q, struct futex_hash_bucket *hb); extern void futex_q_unlock(struct futex_hash_bucket *hb); @@ -260,10 +402,14 @@ extern int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset, u32 __user *uaddr2); -extern int futex_requeue(u32 __user *uaddr1, unsigned int flags, - u32 __user *uaddr2, int nr_wake, int nr_requeue, +extern int futex_requeue(u32 __user *uaddr1, unsigned int flags1, + u32 __user *uaddr2, unsigned int flags2, + int nr_wake, int nr_requeue, u32 *cmpval, int requeue_pi); +extern int __futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, + struct hrtimer_sleeper *to, u32 bitset); + extern int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset); @@ -279,6 +425,16 @@ struct futex_vector { struct futex_q q; }; +extern int futex_parse_waitv(struct futex_vector *futexv, + struct futex_waitv __user *uwaitv, + unsigned int nr_futexes, futex_wake_fn *wake, + void *wake_data); + +extern int futex_wait_multiple_setup(struct futex_vector *vs, int count, + int *woken); + +extern int futex_unqueue_multiple(struct futex_vector *v, int count); + extern int futex_wait_multiple(struct futex_vector *vs, unsigned int count, struct hrtimer_sleeper *to); diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c index ce2889f12375..dacb2330f1fb 100644 --- a/kernel/futex/pi.c +++ b/kernel/futex/pi.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-or-later #include <linux/slab.h> +#include <linux/sched/rt.h> #include <linux/sched/task.h> #include "futex.h" @@ -610,29 +611,16 @@ int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb, /* * Caller must hold a reference on @pi_state. */ -static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_state) +static int wake_futex_pi(u32 __user *uaddr, u32 uval, + struct futex_pi_state *pi_state, + struct rt_mutex_waiter *top_waiter) { - struct rt_mutex_waiter *top_waiter; struct task_struct *new_owner; bool postunlock = false; DEFINE_RT_WAKE_Q(wqh); u32 curval, newval; int ret = 0; - top_waiter = rt_mutex_top_waiter(&pi_state->pi_mutex); - if (WARN_ON_ONCE(!top_waiter)) { - /* - * As per the comment in futex_unlock_pi() this should not happen. - * - * When this happens, give up our locks and try again, giving - * the futex_lock_pi() instance time to complete, either by - * waiting on the rtmutex or removing itself from the futex - * queue. - */ - ret = -EAGAIN; - goto out_unlock; - } - new_owner = top_waiter->task; /* @@ -818,7 +806,7 @@ handle_err: break; } - spin_lock(q->lock_ptr); + futex_q_lockptr_lock(q); raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); /* @@ -932,8 +920,8 @@ int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int tryl struct hrtimer_sleeper timeout, *to; struct task_struct *exiting = NULL; struct rt_mutex_waiter rt_waiter; - struct futex_hash_bucket *hb; struct futex_q q = futex_q_init; + DEFINE_WAKE_Q(wake_q); int res, ret; if (!IS_ENABLED(CONFIG_FUTEX_PI)) @@ -945,132 +933,188 @@ int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int tryl to = futex_setup_timer(time, &timeout, flags, 0); retry: - ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q.key, FUTEX_WRITE); + ret = get_futex_key(uaddr, flags, &q.key, FUTEX_WRITE); if (unlikely(ret != 0)) goto out; retry_private: - hb = futex_q_lock(&q); + if (1) { + CLASS(hb, hb)(&q.key); - ret = futex_lock_pi_atomic(uaddr, hb, &q.key, &q.pi_state, current, - &exiting, 0); - if (unlikely(ret)) { - /* - * Atomic work succeeded and we got the lock, - * or failed. Either way, we do _not_ block. - */ - switch (ret) { - case 1: - /* We got the lock. */ - ret = 0; - goto out_unlock_put_key; - case -EFAULT: - goto uaddr_faulted; - case -EBUSY: - case -EAGAIN: - /* - * Two reasons for this: - * - EBUSY: Task is exiting and we just wait for the - * exit to complete. - * - EAGAIN: The user space value changed. - */ - futex_q_unlock(hb); + futex_q_lock(&q, hb); + + ret = futex_lock_pi_atomic(uaddr, hb, &q.key, &q.pi_state, current, + &exiting, 0); + if (unlikely(ret)) { /* - * Handle the case where the owner is in the middle of - * exiting. Wait for the exit to complete otherwise - * this task might loop forever, aka. live lock. + * Atomic work succeeded and we got the lock, + * or failed. Either way, we do _not_ block. */ - wait_for_owner_exiting(ret, exiting); - cond_resched(); - goto retry; - default: - goto out_unlock_put_key; + switch (ret) { + case 1: + /* We got the lock. */ + ret = 0; + goto out_unlock_put_key; + case -EFAULT: + goto uaddr_faulted; + case -EBUSY: + case -EAGAIN: + /* + * Two reasons for this: + * - EBUSY: Task is exiting and we just wait for the + * exit to complete. + * - EAGAIN: The user space value changed. + */ + futex_q_unlock(hb); + /* + * Handle the case where the owner is in the middle of + * exiting. Wait for the exit to complete otherwise + * this task might loop forever, aka. live lock. + */ + wait_for_owner_exiting(ret, exiting); + cond_resched(); + goto retry; + default: + goto out_unlock_put_key; + } } - } - WARN_ON(!q.pi_state); + WARN_ON(!q.pi_state); - /* - * Only actually queue now that the atomic ops are done: - */ - __futex_queue(&q, hb); + /* + * Only actually queue now that the atomic ops are done: + */ + __futex_queue(&q, hb, current); - if (trylock) { - ret = rt_mutex_futex_trylock(&q.pi_state->pi_mutex); - /* Fixup the trylock return value: */ - ret = ret ? 0 : -EWOULDBLOCK; - goto no_block; - } + if (trylock) { + ret = rt_mutex_futex_trylock(&q.pi_state->pi_mutex); + /* Fixup the trylock return value: */ + ret = ret ? 0 : -EWOULDBLOCK; + goto no_block; + } - rt_mutex_init_waiter(&rt_waiter); + /* + * Caution; releasing @hb in-scope. The hb->lock is still locked + * while the reference is dropped. The reference can not be dropped + * after the unlock because if a user initiated resize is in progress + * then we might need to wake him. This can not be done after the + * rt_mutex_pre_schedule() invocation. The hb will remain valid because + * the thread, performing resize, will block on hb->lock during + * the requeue. + */ + futex_hash_put(no_free_ptr(hb)); + /* + * Must be done before we enqueue the waiter, here is unfortunately + * under the hb lock, but that *should* work because it does nothing. + */ + rt_mutex_pre_schedule(); - /* - * On PREEMPT_RT, when hb->lock becomes an rt_mutex, we must not - * hold it while doing rt_mutex_start_proxy(), because then it will - * include hb->lock in the blocking chain, even through we'll not in - * fact hold it while blocking. This will lead it to report -EDEADLK - * and BUG when futex_unlock_pi() interleaves with this. - * - * Therefore acquire wait_lock while holding hb->lock, but drop the - * latter before calling __rt_mutex_start_proxy_lock(). This - * interleaves with futex_unlock_pi() -- which does a similar lock - * handoff -- such that the latter can observe the futex_q::pi_state - * before __rt_mutex_start_proxy_lock() is done. - */ - raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock); - spin_unlock(q.lock_ptr); - /* - * __rt_mutex_start_proxy_lock() unconditionally enqueues the @rt_waiter - * such that futex_unlock_pi() is guaranteed to observe the waiter when - * it sees the futex_q::pi_state. - */ - ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current); - raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock); + rt_mutex_init_waiter(&rt_waiter); - if (ret) { - if (ret == 1) - ret = 0; - goto cleanup; - } + /* + * On PREEMPT_RT, when hb->lock becomes an rt_mutex, we must not + * hold it while doing rt_mutex_start_proxy(), because then it will + * include hb->lock in the blocking chain, even through we'll not in + * fact hold it while blocking. This will lead it to report -EDEADLK + * and BUG when futex_unlock_pi() interleaves with this. + * + * Therefore acquire wait_lock while holding hb->lock, but drop the + * latter before calling __rt_mutex_start_proxy_lock(). This + * interleaves with futex_unlock_pi() -- which does a similar lock + * handoff -- such that the latter can observe the futex_q::pi_state + * before __rt_mutex_start_proxy_lock() is done. + */ + raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock); + spin_unlock(q.lock_ptr); + /* + * __rt_mutex_start_proxy_lock() unconditionally enqueues the @rt_waiter + * such that futex_unlock_pi() is guaranteed to observe the waiter when + * it sees the futex_q::pi_state. + */ + ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current, &wake_q); + raw_spin_unlock_irq_wake(&q.pi_state->pi_mutex.wait_lock, &wake_q); - if (unlikely(to)) - hrtimer_sleeper_start_expires(to, HRTIMER_MODE_ABS); + if (ret) { + if (ret == 1) + ret = 0; + goto cleanup; + } + + if (unlikely(to)) + hrtimer_sleeper_start_expires(to, HRTIMER_MODE_ABS); - ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter); + ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter); cleanup: - spin_lock(q.lock_ptr); - /* - * If we failed to acquire the lock (deadlock/signal/timeout), we must - * first acquire the hb->lock before removing the lock from the - * rt_mutex waitqueue, such that we can keep the hb and rt_mutex wait - * lists consistent. - * - * In particular; it is important that futex_unlock_pi() can not - * observe this inconsistency. - */ - if (ret && !rt_mutex_cleanup_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter)) - ret = 0; + /* + * If we failed to acquire the lock (deadlock/signal/timeout), we must + * unwind the above, however we canont lock hb->lock because + * rt_mutex already has a waiter enqueued and hb->lock can itself try + * and enqueue an rt_waiter through rtlock. + * + * Doing the cleanup without holding hb->lock can cause inconsistent + * state between hb and pi_state, but only in the direction of not + * seeing a waiter that is leaving. + * + * See futex_unlock_pi(), it deals with this inconsistency. + * + * There be dragons here, since we must deal with the inconsistency on + * the way out (here), it is impossible to detect/warn about the race + * the other way around (missing an incoming waiter). + * + * What could possibly go wrong... + */ + if (ret && !rt_mutex_cleanup_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter)) + ret = 0; + /* + * Now that the rt_waiter has been dequeued, it is safe to use + * spinlock/rtlock (which might enqueue its own rt_waiter) and fix up + * the + */ + futex_q_lockptr_lock(&q); + /* + * Waiter is unqueued. + */ + rt_mutex_post_schedule(); no_block: - /* - * Fixup the pi_state owner and possibly acquire the lock if we - * haven't already. - */ - res = fixup_pi_owner(uaddr, &q, !ret); - /* - * If fixup_pi_owner() returned an error, propagate that. If it acquired - * the lock, clear our -ETIMEDOUT or -EINTR. - */ - if (res) - ret = (res < 0) ? res : 0; - - futex_unqueue_pi(&q); - spin_unlock(q.lock_ptr); - goto out; + /* + * Fixup the pi_state owner and possibly acquire the lock if we + * haven't already. + */ + res = fixup_pi_owner(uaddr, &q, !ret); + /* + * If fixup_pi_owner() returned an error, propagate that. If it acquired + * the lock, clear our -ETIMEDOUT or -EINTR. + */ + if (res) + ret = (res < 0) ? res : 0; + + futex_unqueue_pi(&q); + spin_unlock(q.lock_ptr); + if (q.drop_hb_ref) { + CLASS(hb, hb)(&q.key); + /* Additional reference from futex_unlock_pi() */ + futex_hash_put(hb); + } + goto out; out_unlock_put_key: - futex_q_unlock(hb); + futex_q_unlock(hb); + goto out; + +uaddr_faulted: + futex_q_unlock(hb); + + ret = fault_in_user_writeable(uaddr); + if (ret) + goto out; + + if (!(flags & FLAGS_SHARED)) + goto retry_private; + + goto retry; + } out: if (to) { @@ -1078,18 +1122,6 @@ out: destroy_hrtimer_on_stack(&to->timer); } return ret != -EINTR ? ret : -ERESTARTNOINTR; - -uaddr_faulted: - futex_q_unlock(hb); - - ret = fault_in_user_writeable(uaddr); - if (ret) - goto out; - - if (!(flags & FLAGS_SHARED)) - goto retry_private; - - goto retry; } /* @@ -1101,7 +1133,6 @@ int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) { u32 curval, uval, vpid = task_pid_vnr(current); union futex_key key = FUTEX_KEY_INIT; - struct futex_hash_bucket *hb; struct futex_q *top_waiter; int ret; @@ -1117,12 +1148,13 @@ retry: if ((uval & FUTEX_TID_MASK) != vpid) return -EPERM; - ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, FUTEX_WRITE); + ret = get_futex_key(uaddr, flags, &key, FUTEX_WRITE); if (ret) return ret; - hb = futex_hash(&key); + CLASS(hb, hb)(&key); spin_lock(&hb->lock); +retry_hb: /* * Check waiters first. We do not trust user space values at @@ -1132,6 +1164,7 @@ retry: top_waiter = futex_top_waiter(hb, &key); if (top_waiter) { struct futex_pi_state *pi_state = top_waiter->pi_state; + struct rt_mutex_waiter *rt_waiter; ret = -EINVAL; if (!pi_state) @@ -1144,22 +1177,50 @@ retry: if (pi_state->owner != current) goto out_unlock; - get_pi_state(pi_state); /* * By taking wait_lock while still holding hb->lock, we ensure - * there is no point where we hold neither; and therefore - * wake_futex_p() must observe a state consistent with what we - * observed. + * there is no point where we hold neither; and thereby + * wake_futex_pi() must observe any new waiters. + * + * Since the cleanup: case in futex_lock_pi() removes the + * rt_waiter without holding hb->lock, it is possible for + * wake_futex_pi() to not find a waiter while the above does, + * in this case the waiter is on the way out and it can be + * ignored. * * In particular; this forces __rt_mutex_start_proxy() to * complete such that we're guaranteed to observe the - * rt_waiter. Also see the WARN in wake_futex_pi(). + * rt_waiter. */ raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + + /* + * Futex vs rt_mutex waiter state -- if there are no rt_mutex + * waiters even though futex thinks there are, then the waiter + * is leaving. The entry needs to be removed from the list so a + * new futex_lock_pi() is not using this stale PI-state while + * the futex is available in user space again. + * There can be more than one task on its way out so it needs + * to retry. + */ + rt_waiter = rt_mutex_top_waiter(&pi_state->pi_mutex); + if (!rt_waiter) { + /* + * Acquire a reference for the leaving waiter to ensure + * valid futex_q::lock_ptr. + */ + futex_hash_get(hb); + top_waiter->drop_hb_ref = true; + __futex_unqueue(top_waiter); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); + goto retry_hb; + } + + get_pi_state(pi_state); spin_unlock(&hb->lock); /* drops pi_state->pi_mutex.wait_lock */ - ret = wake_futex_pi(uaddr, uval, pi_state); + ret = wake_futex_pi(uaddr, uval, pi_state, rt_waiter); put_pi_state(pi_state); diff --git a/kernel/futex/requeue.c b/kernel/futex/requeue.c index cba8b1a6a4cc..d818b4d47f1b 100644 --- a/kernel/futex/requeue.c +++ b/kernel/futex/requeue.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later +#include <linux/plist.h> #include <linux/sched/signal.h> #include "futex.h" @@ -58,6 +59,7 @@ enum { const struct futex_q futex_q_init = { /* list gets initialized in futex_queue()*/ + .wake = futex_wake_mark, .key = FUTEX_KEY_INIT, .bitset = FUTEX_BITSET_MATCH_ANY, .requeue_state = ATOMIC_INIT(Q_REQUEUE_PI_NONE), @@ -85,6 +87,11 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1, futex_hb_waiters_inc(hb2); plist_add(&q->list, &hb2->chain); q->lock_ptr = &hb2->lock; + /* + * hb1 and hb2 belong to the same futex_hash_bucket_private + * because if we managed get a reference on hb1 then it can't be + * replaced. Therefore we avoid put(hb1)+get(hb2) here. + */ } q->key = *key2; } @@ -223,18 +230,25 @@ 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); q->rt_waiter = NULL; - + /* + * Acquire a reference for the waiter to ensure valid + * futex_q::lock_ptr. + */ + 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); } /** @@ -269,7 +283,7 @@ futex_proxy_trylock_atomic(u32 __user *pifutex, struct futex_hash_bucket *hb1, union futex_key *key2, struct futex_pi_state **ps, struct task_struct **exiting, int set_waiters) { - struct futex_q *top_waiter = NULL; + struct futex_q *top_waiter; u32 curval; int ret; @@ -346,8 +360,9 @@ futex_proxy_trylock_atomic(u32 __user *pifutex, struct futex_hash_bucket *hb1, /** * futex_requeue() - Requeue waiters from uaddr1 to uaddr2 * @uaddr1: source futex user address - * @flags: futex flags (FLAGS_SHARED, etc.) + * @flags1: futex flags (FLAGS_SHARED, etc.) * @uaddr2: target futex user address + * @flags2: futex flags (FLAGS_SHARED, etc.) * @nr_wake: number of waiters to wake (must be 1 for requeue_pi) * @nr_requeue: number of waiters to requeue (0-INT_MAX) * @cmpval: @uaddr1 expected value (or %NULL) @@ -361,13 +376,13 @@ futex_proxy_trylock_atomic(u32 __user *pifutex, struct futex_hash_bucket *hb1, * - >=0 - on success, the number of tasks requeued or woken; * - <0 - on error */ -int futex_requeue(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, +int futex_requeue(u32 __user *uaddr1, unsigned int flags1, + u32 __user *uaddr2, unsigned int flags2, int nr_wake, int nr_requeue, u32 *cmpval, int requeue_pi) { union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT; int task_count = 0, ret; struct futex_pi_state *pi_state = NULL; - struct futex_hash_bucket *hb1, *hb2; struct futex_q *this, *next; DEFINE_WAKE_Q(wake_q); @@ -424,10 +439,10 @@ int futex_requeue(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, } retry: - ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, FUTEX_READ); + ret = get_futex_key(uaddr1, flags1, &key1, FUTEX_READ); if (unlikely(ret != 0)) return ret; - ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, + ret = get_futex_key(uaddr2, flags2, &key2, requeue_pi ? FUTEX_WRITE : FUTEX_READ); if (unlikely(ret != 0)) return ret; @@ -439,240 +454,242 @@ retry: if (requeue_pi && futex_match(&key1, &key2)) return -EINVAL; - hb1 = futex_hash(&key1); - hb2 = futex_hash(&key2); - retry_private: - futex_hb_waiters_inc(hb2); - double_lock_hb(hb1, hb2); + if (1) { + CLASS(hb, hb1)(&key1); + CLASS(hb, hb2)(&key2); - if (likely(cmpval != NULL)) { - u32 curval; + futex_hb_waiters_inc(hb2); + double_lock_hb(hb1, hb2); - ret = futex_get_value_locked(&curval, uaddr1); + if (likely(cmpval != NULL)) { + u32 curval; - if (unlikely(ret)) { - double_unlock_hb(hb1, hb2); - futex_hb_waiters_dec(hb2); + ret = futex_get_value_locked(&curval, uaddr1); - ret = get_user(curval, uaddr1); - if (ret) - return ret; + if (unlikely(ret)) { + futex_hb_waiters_dec(hb2); + double_unlock_hb(hb1, hb2); - if (!(flags & FLAGS_SHARED)) - goto retry_private; + ret = get_user(curval, uaddr1); + if (ret) + return ret; - goto retry; - } - if (curval != *cmpval) { - ret = -EAGAIN; - goto out_unlock; - } - } + if (!(flags1 & FLAGS_SHARED)) + goto retry_private; - if (requeue_pi) { - struct task_struct *exiting = NULL; + goto retry; + } + if (curval != *cmpval) { + ret = -EAGAIN; + goto out_unlock; + } + } - /* - * Attempt to acquire uaddr2 and wake the top waiter. If we - * intend to requeue waiters, force setting the FUTEX_WAITERS - * bit. We force this here where we are able to easily handle - * faults rather in the requeue loop below. - * - * Updates topwaiter::requeue_state if a top waiter exists. - */ - ret = futex_proxy_trylock_atomic(uaddr2, hb1, hb2, &key1, - &key2, &pi_state, - &exiting, nr_requeue); + if (requeue_pi) { + struct task_struct *exiting = NULL; - /* - * At this point the top_waiter has either taken uaddr2 or - * is waiting on it. In both cases pi_state has been - * established and an initial refcount on it. In case of an - * error there's nothing. - * - * The top waiter's requeue_state is up to date: - * - * - If the lock was acquired atomically (ret == 1), then - * the state is Q_REQUEUE_PI_LOCKED. - * - * The top waiter has been dequeued and woken up and can - * return to user space immediately. The kernel/user - * space state is consistent. In case that there must be - * more waiters requeued the WAITERS bit in the user - * space futex is set so the top waiter task has to go - * into the syscall slowpath to unlock the futex. This - * will block until this requeue operation has been - * completed and the hash bucket locks have been - * dropped. - * - * - If the trylock failed with an error (ret < 0) then - * the state is either Q_REQUEUE_PI_NONE, i.e. "nothing - * happened", or Q_REQUEUE_PI_IGNORE when there was an - * interleaved early wakeup. - * - * - If the trylock did not succeed (ret == 0) then the - * state is either Q_REQUEUE_PI_IN_PROGRESS or - * Q_REQUEUE_PI_WAIT if an early wakeup interleaved. - * This will be cleaned up in the loop below, which - * cannot fail because futex_proxy_trylock_atomic() did - * the same sanity checks for requeue_pi as the loop - * below does. - */ - switch (ret) { - case 0: - /* We hold a reference on the pi state. */ - break; - - case 1: /* - * futex_proxy_trylock_atomic() acquired the user space - * futex. Adjust task_count. + * Attempt to acquire uaddr2 and wake the top waiter. If we + * intend to requeue waiters, force setting the FUTEX_WAITERS + * bit. We force this here where we are able to easily handle + * faults rather in the requeue loop below. + * + * Updates topwaiter::requeue_state if a top waiter exists. */ - task_count++; - ret = 0; - break; + ret = futex_proxy_trylock_atomic(uaddr2, hb1, hb2, &key1, + &key2, &pi_state, + &exiting, nr_requeue); - /* - * If the above failed, then pi_state is NULL and - * waiter::requeue_state is correct. - */ - case -EFAULT: - double_unlock_hb(hb1, hb2); - futex_hb_waiters_dec(hb2); - ret = fault_in_user_writeable(uaddr2); - if (!ret) - goto retry; - return ret; - case -EBUSY: - case -EAGAIN: /* - * Two reasons for this: - * - EBUSY: Owner is exiting and we just wait for the - * exit to complete. - * - EAGAIN: The user space value changed. + * At this point the top_waiter has either taken uaddr2 or + * is waiting on it. In both cases pi_state has been + * established and an initial refcount on it. In case of an + * error there's nothing. + * + * The top waiter's requeue_state is up to date: + * + * - If the lock was acquired atomically (ret == 1), then + * the state is Q_REQUEUE_PI_LOCKED. + * + * The top waiter has been dequeued and woken up and can + * return to user space immediately. The kernel/user + * space state is consistent. In case that there must be + * more waiters requeued the WAITERS bit in the user + * space futex is set so the top waiter task has to go + * into the syscall slowpath to unlock the futex. This + * will block until this requeue operation has been + * completed and the hash bucket locks have been + * dropped. + * + * - If the trylock failed with an error (ret < 0) then + * the state is either Q_REQUEUE_PI_NONE, i.e. "nothing + * happened", or Q_REQUEUE_PI_IGNORE when there was an + * interleaved early wakeup. + * + * - If the trylock did not succeed (ret == 0) then the + * state is either Q_REQUEUE_PI_IN_PROGRESS or + * Q_REQUEUE_PI_WAIT if an early wakeup interleaved. + * This will be cleaned up in the loop below, which + * cannot fail because futex_proxy_trylock_atomic() did + * the same sanity checks for requeue_pi as the loop + * below does. */ - double_unlock_hb(hb1, hb2); - futex_hb_waiters_dec(hb2); - /* - * Handle the case where the owner is in the middle of - * exiting. Wait for the exit to complete otherwise - * this task might loop forever, aka. live lock. - */ - wait_for_owner_exiting(ret, exiting); - cond_resched(); - goto retry; - default: - goto out_unlock; - } - } - - plist_for_each_entry_safe(this, next, &hb1->chain, list) { - if (task_count - nr_wake >= nr_requeue) - break; - - if (!futex_match(&this->key, &key1)) - continue; - - /* - * FUTEX_WAIT_REQUEUE_PI and FUTEX_CMP_REQUEUE_PI should always - * be paired with each other and no other futex ops. - * - * We should never be requeueing a futex_q with a pi_state, - * which is awaiting a futex_unlock_pi(). - */ - if ((requeue_pi && !this->rt_waiter) || - (!requeue_pi && this->rt_waiter) || - this->pi_state) { - ret = -EINVAL; - break; - } - - /* Plain futexes just wake or requeue and are done */ - if (!requeue_pi) { - if (++task_count <= nr_wake) - futex_wake_mark(&wake_q, this); - else - requeue_futex(this, hb1, hb2, &key2); - continue; + switch (ret) { + case 0: + /* We hold a reference on the pi state. */ + break; + + case 1: + /* + * futex_proxy_trylock_atomic() acquired the user space + * futex. Adjust task_count. + */ + task_count++; + ret = 0; + break; + + /* + * If the above failed, then pi_state is NULL and + * waiter::requeue_state is correct. + */ + case -EFAULT: + futex_hb_waiters_dec(hb2); + double_unlock_hb(hb1, hb2); + ret = fault_in_user_writeable(uaddr2); + if (!ret) + goto retry; + return ret; + case -EBUSY: + case -EAGAIN: + /* + * Two reasons for this: + * - EBUSY: Owner is exiting and we just wait for the + * exit to complete. + * - EAGAIN: The user space value changed. + */ + futex_hb_waiters_dec(hb2); + double_unlock_hb(hb1, hb2); + /* + * Handle the case where the owner is in the middle of + * exiting. Wait for the exit to complete otherwise + * this task might loop forever, aka. live lock. + */ + wait_for_owner_exiting(ret, exiting); + cond_resched(); + goto retry; + default: + goto out_unlock; + } } - /* Ensure we requeue to the expected futex for requeue_pi. */ - if (!futex_match(this->requeue_pi_key, &key2)) { - ret = -EINVAL; - break; - } + plist_for_each_entry_safe(this, next, &hb1->chain, list) { + if (task_count - nr_wake >= nr_requeue) + break; - /* - * Requeue nr_requeue waiters and possibly one more in the case - * of requeue_pi if we couldn't acquire the lock atomically. - * - * Prepare the waiter to take the rt_mutex. Take a refcount - * on the pi_state and store the pointer in the futex_q - * object of the waiter. - */ - get_pi_state(pi_state); + if (!futex_match(&this->key, &key1)) + continue; - /* Don't requeue when the waiter is already on the way out. */ - if (!futex_requeue_pi_prepare(this, pi_state)) { /* - * Early woken waiter signaled that it is on the - * way out. Drop the pi_state reference and try the - * next waiter. @this->pi_state is still NULL. + * FUTEX_WAIT_REQUEUE_PI and FUTEX_CMP_REQUEUE_PI should always + * be paired with each other and no other futex ops. + * + * We should never be requeueing a futex_q with a pi_state, + * which is awaiting a futex_unlock_pi(). */ - put_pi_state(pi_state); - continue; - } + if ((requeue_pi && !this->rt_waiter) || + (!requeue_pi && this->rt_waiter) || + this->pi_state) { + ret = -EINVAL; + break; + } + + /* Plain futexes just wake or requeue and are done */ + if (!requeue_pi) { + if (++task_count <= nr_wake) + this->wake(&wake_q, this); + else + requeue_futex(this, hb1, hb2, &key2); + continue; + } + + /* Ensure we requeue to the expected futex for requeue_pi. */ + if (!futex_match(this->requeue_pi_key, &key2)) { + ret = -EINVAL; + break; + } - ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex, - this->rt_waiter, - this->task); - - if (ret == 1) { - /* - * We got the lock. We do neither drop the refcount - * on pi_state nor clear this->pi_state because the - * waiter needs the pi_state for cleaning up the - * user space value. It will drop the refcount - * after doing so. this::requeue_state is updated - * in the wakeup as well. - */ - requeue_pi_wake_futex(this, &key2, hb2); - task_count++; - } else if (!ret) { - /* Waiter is queued, move it to hb2 */ - requeue_futex(this, hb1, hb2, &key2); - futex_requeue_pi_complete(this, 0); - task_count++; - } else { - /* - * rt_mutex_start_proxy_lock() detected a potential - * deadlock when we tried to queue that waiter. - * Drop the pi_state reference which we took above - * and remove the pointer to the state from the - * waiters futex_q object. - */ - this->pi_state = NULL; - put_pi_state(pi_state); - futex_requeue_pi_complete(this, ret); /* - * We stop queueing more waiters and let user space - * deal with the mess. + * Requeue nr_requeue waiters and possibly one more in the case + * of requeue_pi if we couldn't acquire the lock atomically. + * + * Prepare the waiter to take the rt_mutex. Take a refcount + * on the pi_state and store the pointer in the futex_q + * object of the waiter. */ - break; + get_pi_state(pi_state); + + /* Don't requeue when the waiter is already on the way out. */ + if (!futex_requeue_pi_prepare(this, pi_state)) { + /* + * Early woken waiter signaled that it is on the + * way out. Drop the pi_state reference and try the + * next waiter. @this->pi_state is still NULL. + */ + put_pi_state(pi_state); + continue; + } + + ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex, + this->rt_waiter, + this->task); + + if (ret == 1) { + /* + * We got the lock. We do neither drop the refcount + * on pi_state nor clear this->pi_state because the + * waiter needs the pi_state for cleaning up the + * user space value. It will drop the refcount + * after doing so. this::requeue_state is updated + * in the wakeup as well. + */ + requeue_pi_wake_futex(this, &key2, hb2); + task_count++; + } else if (!ret) { + /* Waiter is queued, move it to hb2 */ + requeue_futex(this, hb1, hb2, &key2); + futex_requeue_pi_complete(this, 0); + task_count++; + } else { + /* + * rt_mutex_start_proxy_lock() detected a potential + * deadlock when we tried to queue that waiter. + * Drop the pi_state reference which we took above + * and remove the pointer to the state from the + * waiters futex_q object. + */ + this->pi_state = NULL; + put_pi_state(pi_state); + futex_requeue_pi_complete(this, ret); + /* + * We stop queueing more waiters and let user space + * deal with the mess. + */ + break; + } } - } - /* - * We took an extra initial reference to the pi_state in - * futex_proxy_trylock_atomic(). We need to drop it here again. - */ - put_pi_state(pi_state); + /* + * We took an extra initial reference to the pi_state in + * futex_proxy_trylock_atomic(). We need to drop it here again. + */ + put_pi_state(pi_state); out_unlock: - double_unlock_hb(hb1, hb2); + futex_hb_waiters_dec(hb2); + double_unlock_hb(hb1, hb2); + } wake_up_q(&wake_q); - futex_hb_waiters_dec(hb2); return ret ? ret : task_count; } @@ -765,7 +782,6 @@ int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, { struct hrtimer_sleeper timeout, *to; struct rt_mutex_waiter rt_waiter; - struct futex_hash_bucket *hb; union futex_key key2 = FUTEX_KEY_INIT; struct futex_q q = futex_q_init; struct rt_mutex_base *pi_mutex; @@ -789,7 +805,7 @@ int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, */ rt_mutex_init_waiter(&rt_waiter); - ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, FUTEX_WRITE); + ret = get_futex_key(uaddr2, flags, &key2, FUTEX_WRITE); if (unlikely(ret != 0)) goto out; @@ -801,35 +817,28 @@ int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, * Prepare to wait on uaddr. On success, it holds hb->lock and q * is initialized. */ - ret = futex_wait_setup(uaddr, val, flags, &q, &hb); + ret = futex_wait_setup(uaddr, val, flags, &q, &key2, current); if (ret) goto out; - /* - * The check above which compares uaddrs is not sufficient for - * shared futexes. We need to compare the keys: - */ - if (futex_match(&q.key, &key2)) { - futex_q_unlock(hb); - ret = -EINVAL; - goto out; - } - /* Queue the futex_q, drop the hb lock, wait for wakeup. */ - futex_wait_queue(hb, &q, to); + futex_do_wait(&q, to); switch (futex_requeue_pi_wakeup_sync(&q)) { case Q_REQUEUE_PI_IGNORE: - /* The waiter is still on uaddr1 */ - spin_lock(&hb->lock); - ret = handle_early_requeue_pi_wakeup(hb, &q, to); - spin_unlock(&hb->lock); + { + CLASS(hb, hb)(&q.key); + /* The waiter is still on uaddr1 */ + spin_lock(&hb->lock); + ret = handle_early_requeue_pi_wakeup(hb, &q, to); + spin_unlock(&hb->lock); + } break; case Q_REQUEUE_PI_LOCKED: /* The requeue acquired the lock */ if (q.pi_state && (q.pi_state->owner != current)) { - spin_lock(q.lock_ptr); + futex_q_lockptr_lock(&q); ret = fixup_pi_owner(uaddr2, &q, true); /* * Drop the reference to the pi state which the @@ -850,11 +859,13 @@ int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, pi_mutex = &q.pi_state->pi_mutex; ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter); - /* Current is not longer pi_blocked_on */ - spin_lock(q.lock_ptr); + /* + * See futex_unlock_pi()'s cleanup: comment. + */ if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter)) ret = 0; + futex_q_lockptr_lock(&q); debug_rt_mutex_free_waiter(&rt_waiter); /* * Fixup the pi_state owner and possibly acquire the lock if we @@ -886,6 +897,11 @@ int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, default: BUG(); } + if (q.drop_hb_ref) { + CLASS(hb, hb)(&q.key); + /* Additional reference from requeue_pi_wake_futex() */ + futex_hash_put(hb); + } out: if (to) { diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c index a8074079b09e..880c9bf2f315 100644 --- a/kernel/futex/syscalls.c +++ b/kernel/futex/syscalls.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later -#include <linux/compat.h> #include <linux/syscalls.h> #include <linux/time_namespace.h> @@ -40,6 +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] @@ -50,50 +99,25 @@ 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, u32 __user *uaddr2, u32 val2, u32 val3) { + unsigned int flags = futex_to_flags(op); int cmd = op & FUTEX_CMD_MASK; - unsigned int flags = 0; - - if (!(op & FUTEX_PRIVATE_FLAG)) - flags |= FLAGS_SHARED; - if (op & FUTEX_CLOCK_REALTIME) { - flags |= FLAGS_CLOCKRT; - if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI && + if (flags & FLAGS_CLOCKRT) { + if (cmd != FUTEX_WAIT_BITSET && + cmd != FUTEX_WAIT_REQUEUE_PI && cmd != FUTEX_LOCK_PI2) return -ENOSYS; } @@ -110,9 +134,9 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, case FUTEX_WAKE_BITSET: return futex_wake(uaddr, flags, val, val3); case FUTEX_REQUEUE: - return futex_requeue(uaddr, flags, uaddr2, val, val2, NULL, 0); + return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, NULL, 0); case FUTEX_CMP_REQUEUE: - return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 0); + return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, &val3, 0); case FUTEX_WAKE_OP: return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3); case FUTEX_LOCK_PI: @@ -129,7 +153,7 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3, uaddr2); case FUTEX_CMP_REQUEUE_PI: - return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 1); + return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, &val3, 1); } return -ENOSYS; } @@ -183,43 +207,91 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); } -/* Mask of available flags for each futex in futex_waitv list */ -#define FUTEXV_WAITER_MASK (FUTEX_32 | FUTEX_PRIVATE_FLAG) - /** * futex_parse_waitv - Parse a waitv array from userspace * @futexv: Kernel side list of waiters to be filled * @uwaitv: Userspace list to be parsed * @nr_futexes: Length of futexv + * @wake: Wake to call when futex is woken + * @wake_data: Data for the wake handler * * Return: Error code on failure, 0 on success */ -static int futex_parse_waitv(struct futex_vector *futexv, - struct futex_waitv __user *uwaitv, - unsigned int nr_futexes) +int futex_parse_waitv(struct futex_vector *futexv, + struct futex_waitv __user *uwaitv, + unsigned int nr_futexes, futex_wake_fn *wake, + void *wake_data) { struct futex_waitv aux; unsigned int i; for (i = 0; i < nr_futexes; i++) { + unsigned int flags; + if (copy_from_user(&aux, &uwaitv[i], sizeof(aux))) return -EFAULT; - if ((aux.flags & ~FUTEXV_WAITER_MASK) || aux.__reserved) + if ((aux.flags & ~FUTEX2_VALID_MASK) || aux.__reserved) + return -EINVAL; + + flags = futex2_to_flags(aux.flags); + if (!futex_flags_valid(flags)) return -EINVAL; - if (!(aux.flags & FUTEX_32)) + if (!futex_validate_input(flags, aux.val)) return -EINVAL; - futexv[i].w.flags = aux.flags; + futexv[i].w.flags = flags; futexv[i].w.val = aux.val; futexv[i].w.uaddr = aux.uaddr; futexv[i].q = futex_q_init; + futexv[i].q.wake = wake; + futexv[i].q.wake_data = wake_data; } return 0; } +static int futex2_setup_timeout(struct __kernel_timespec __user *timeout, + clockid_t clockid, struct hrtimer_sleeper *to) +{ + int flag_clkid = 0, flag_init = 0; + struct timespec64 ts; + ktime_t time; + int ret; + + if (!timeout) + return 0; + + if (clockid == CLOCK_REALTIME) { + flag_clkid = FLAGS_CLOCKRT; + flag_init = FUTEX_CLOCK_REALTIME; + } + + if (clockid != CLOCK_REALTIME && clockid != CLOCK_MONOTONIC) + return -EINVAL; + + if (get_timespec64(&ts, timeout)) + return -EFAULT; + + /* + * Since there's no opcode for futex_waitv, use + * FUTEX_WAIT_BITSET that uses absolute timeout as well + */ + ret = futex_init_timeout(FUTEX_WAIT_BITSET, flag_init, &ts, &time); + if (ret) + return ret; + + futex_setup_timer(&time, to, flag_clkid, 0); + return 0; +} + +static inline void futex2_destroy_timeout(struct hrtimer_sleeper *to) +{ + hrtimer_cancel(&to->timer); + destroy_hrtimer_on_stack(&to->timer); +} + /** * sys_futex_waitv - Wait on a list of futexes * @waiters: List of futexes to wait on @@ -249,8 +321,6 @@ SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters, { struct hrtimer_sleeper to; struct futex_vector *futexv; - struct timespec64 ts; - ktime_t time; int ret; /* This syscall supports no flags for now */ @@ -260,30 +330,8 @@ SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters, if (!nr_futexes || nr_futexes > FUTEX_WAITV_MAX || !waiters) return -EINVAL; - if (timeout) { - int flag_clkid = 0, flag_init = 0; - - if (clockid == CLOCK_REALTIME) { - flag_clkid = FLAGS_CLOCKRT; - flag_init = FUTEX_CLOCK_REALTIME; - } - - if (clockid != CLOCK_REALTIME && clockid != CLOCK_MONOTONIC) - return -EINVAL; - - if (get_timespec64(&ts, timeout)) - return -EFAULT; - - /* - * Since there's no opcode for futex_waitv, use - * FUTEX_WAIT_BITSET that uses absolute timeout as well - */ - ret = futex_init_timeout(FUTEX_WAIT_BITSET, flag_init, &ts, &time); - if (ret) - return ret; - - futex_setup_timer(&time, &to, flag_clkid, 0); - } + if (timeout && (ret = futex2_setup_timeout(timeout, clockid, &to))) + return ret; futexv = kcalloc(nr_futexes, sizeof(*futexv), GFP_KERNEL); if (!futexv) { @@ -291,20 +339,133 @@ SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters, goto destroy_timer; } - ret = futex_parse_waitv(futexv, waiters, nr_futexes); + ret = futex_parse_waitv(futexv, waiters, nr_futexes, futex_wake_mark, + NULL); if (!ret) ret = futex_wait_multiple(futexv, nr_futexes, timeout ? &to : NULL); kfree(futexv); destroy_timer: - if (timeout) { - hrtimer_cancel(&to.timer); - destroy_hrtimer_on_stack(&to.timer); - } + if (timeout) + futex2_destroy_timeout(&to); return ret; } +/* + * sys_futex_wake - Wake a number of futexes + * @uaddr: Address of the futex(es) to wake + * @mask: bitmask + * @nr: Number of the futexes to wake + * @flags: FUTEX2 flags + * + * Identical to the traditional FUTEX_WAKE_BITSET op, except it is part of the + * futex2 family of calls. + */ + +SYSCALL_DEFINE4(futex_wake, + void __user *, uaddr, + unsigned long, mask, + int, nr, + unsigned int, flags) +{ + if (flags & ~FUTEX2_VALID_MASK) + return -EINVAL; + + flags = futex2_to_flags(flags); + if (!futex_flags_valid(flags)) + return -EINVAL; + + if (!futex_validate_input(flags, mask)) + return -EINVAL; + + return futex_wake(uaddr, FLAGS_STRICT | flags, nr, mask); +} + +/* + * sys_futex_wait - Wait on a futex + * @uaddr: Address of the futex to wait on + * @val: Value of @uaddr + * @mask: bitmask + * @flags: FUTEX2 flags + * @timeout: Optional absolute timeout + * @clockid: Clock to be used for the timeout, realtime or monotonic + * + * Identical to the traditional FUTEX_WAIT_BITSET op, except it is part of the + * futex2 familiy of calls. + */ + +SYSCALL_DEFINE6(futex_wait, + void __user *, uaddr, + unsigned long, val, + unsigned long, mask, + unsigned int, flags, + struct __kernel_timespec __user *, timeout, + clockid_t, clockid) +{ + struct hrtimer_sleeper to; + int ret; + + if (flags & ~FUTEX2_VALID_MASK) + return -EINVAL; + + flags = futex2_to_flags(flags); + if (!futex_flags_valid(flags)) + return -EINVAL; + + if (!futex_validate_input(flags, val) || + !futex_validate_input(flags, mask)) + return -EINVAL; + + if (timeout && (ret = futex2_setup_timeout(timeout, clockid, &to))) + return ret; + + ret = __futex_wait(uaddr, flags, val, timeout ? &to : NULL, mask); + + if (timeout) + futex2_destroy_timeout(&to); + + return ret; +} + +/* + * sys_futex_requeue - Requeue a waiter from one futex to another + * @waiters: array describing the source and destination futex + * @flags: unused + * @nr_wake: number of futexes to wake + * @nr_requeue: number of futexes to requeue + * + * Identical to the traditional FUTEX_CMP_REQUEUE op, except it is part of the + * futex2 family of calls. + */ + +SYSCALL_DEFINE4(futex_requeue, + struct futex_waitv __user *, waiters, + unsigned int, flags, + int, nr_wake, + int, nr_requeue) +{ + struct futex_vector futexes[2]; + u32 cmpval; + int ret; + + if (flags) + return -EINVAL; + + if (!waiters) + return -EINVAL; + + ret = futex_parse_waitv(futexes, waiters, 2, futex_wake_mark, NULL); + if (ret) + return ret; + + cmpval = futexes[0].w.val; + + return futex_requeue(u64_to_user_ptr(futexes[0].w.uaddr), futexes[0].w.flags, + u64_to_user_ptr(futexes[1].w.uaddr), futexes[1].w.flags, + nr_wake, nr_requeue, &cmpval, 0); +} + #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(set_robust_list, struct compat_robust_list_head __user *, head, @@ -322,36 +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; - } + struct compat_robust_list_head __user *head = futex_get_robust_list_common(pid, true); - ret = -EPERM; - if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) - goto err_unlock; - - 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 */ diff --git a/kernel/futex/waitwake.c b/kernel/futex/waitwake.c index ba01b9408203..e2bbe5509ec2 100644 --- a/kernel/futex/waitwake.c +++ b/kernel/futex/waitwake.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later +#include <linux/plist.h> #include <linux/sched/task.h> #include <linux/sched/signal.h> #include <linux/freezer.h> @@ -106,20 +107,11 @@ * double_lock_hb() and double_unlock_hb(), respectively. */ -/* - * The hash bucket lock must be held when this is called. - * Afterwards, the futex_q must not be accessed. Callers - * must ensure to later call wake_up_q() for the actual - * wakeups to occur. - */ -void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q) +bool __futex_wake_mark(struct futex_q *q) { - struct task_struct *p = q->task; - if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n")) - return; + return false; - get_task_struct(p); __futex_unqueue(q); /* * The waiting task can free the futex_q as soon as q->lock_ptr = NULL @@ -130,6 +122,26 @@ void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q) */ smp_store_release(&q->lock_ptr, NULL); + return true; +} + +/* + * The hash bucket lock must be held when this is called. + * Afterwards, the futex_q must not be accessed. Callers + * must ensure to later call wake_up_q() for the actual + * wakeups to occur. + */ +void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q) +{ + struct task_struct *p = q->task; + + get_task_struct(p); + + if (!__futex_wake_mark(q)) { + put_task_struct(p); + return; + } + /* * Queue the task for later wakeup for after we've released * the hb->lock. @@ -142,20 +154,22 @@ void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q) */ int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) { - struct futex_hash_bucket *hb; struct futex_q *this, *next; union futex_key key = FUTEX_KEY_INIT; - int ret; DEFINE_WAKE_Q(wake_q); + int ret; if (!bitset) return -EINVAL; - ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, FUTEX_READ); + ret = get_futex_key(uaddr, flags, &key, FUTEX_READ); if (unlikely(ret != 0)) return ret; - hb = futex_hash(&key); + if ((flags & FLAGS_STRICT) && !nr_wake) + return 0; + + CLASS(hb, hb)(&key); /* Make sure we really have tasks to wakeup */ if (!futex_hb_waiters_pending(hb)) @@ -174,7 +188,7 @@ int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) if (!(this->bitset & bitset)) continue; - futex_wake_mark(&wake_q, this); + this->wake(&wake_q, this); if (++ret >= nr_wake) break; } @@ -195,13 +209,12 @@ static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr) if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) { if (oparg < 0 || oparg > 31) { - char comm[sizeof(current->comm)]; /* * kill this print and return -EINVAL when userspace * is sane again */ pr_info_ratelimited("futex_wake_op: %s tries to shift op by %d; fix this program\n", - get_task_comm(comm, current), oparg); + current->comm, oparg); oparg &= 31; } oparg = 1 << oparg; @@ -239,80 +252,81 @@ int futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, int nr_wake, int nr_wake2, int op) { union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT; - struct futex_hash_bucket *hb1, *hb2; struct futex_q *this, *next; int ret, op_ret; DEFINE_WAKE_Q(wake_q); retry: - ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, FUTEX_READ); + ret = get_futex_key(uaddr1, flags, &key1, FUTEX_READ); if (unlikely(ret != 0)) return ret; - ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, FUTEX_WRITE); + ret = get_futex_key(uaddr2, flags, &key2, FUTEX_WRITE); if (unlikely(ret != 0)) return ret; - hb1 = futex_hash(&key1); - hb2 = futex_hash(&key2); - retry_private: - double_lock_hb(hb1, hb2); - op_ret = futex_atomic_op_inuser(op, uaddr2); - if (unlikely(op_ret < 0)) { - double_unlock_hb(hb1, hb2); - - if (!IS_ENABLED(CONFIG_MMU) || - unlikely(op_ret != -EFAULT && op_ret != -EAGAIN)) { - /* - * we don't get EFAULT from MMU faults if we don't have - * an MMU, but we might get them from range checking - */ - ret = op_ret; - return ret; - } - - if (op_ret == -EFAULT) { - ret = fault_in_user_writeable(uaddr2); - if (ret) + if (1) { + CLASS(hb, hb1)(&key1); + CLASS(hb, hb2)(&key2); + + double_lock_hb(hb1, hb2); + op_ret = futex_atomic_op_inuser(op, uaddr2); + if (unlikely(op_ret < 0)) { + double_unlock_hb(hb1, hb2); + + if (!IS_ENABLED(CONFIG_MMU) || + unlikely(op_ret != -EFAULT && op_ret != -EAGAIN)) { + /* + * we don't get EFAULT from MMU faults if we don't have + * an MMU, but we might get them from range checking + */ + ret = op_ret; return ret; - } - - cond_resched(); - if (!(flags & FLAGS_SHARED)) - goto retry_private; - goto retry; - } + } - plist_for_each_entry_safe(this, next, &hb1->chain, list) { - if (futex_match (&this->key, &key1)) { - if (this->pi_state || this->rt_waiter) { - ret = -EINVAL; - goto out_unlock; + if (op_ret == -EFAULT) { + ret = fault_in_user_writeable(uaddr2); + if (ret) + return ret; } - futex_wake_mark(&wake_q, this); - if (++ret >= nr_wake) - break; + + cond_resched(); + if (!(flags & FLAGS_SHARED)) + goto retry_private; + goto retry; } - } - if (op_ret > 0) { - op_ret = 0; - plist_for_each_entry_safe(this, next, &hb2->chain, list) { - if (futex_match (&this->key, &key2)) { + plist_for_each_entry_safe(this, next, &hb1->chain, list) { + if (futex_match(&this->key, &key1)) { if (this->pi_state || this->rt_waiter) { ret = -EINVAL; goto out_unlock; } - futex_wake_mark(&wake_q, this); - if (++op_ret >= nr_wake2) + this->wake(&wake_q, this); + if (++ret >= nr_wake) break; } } - ret += op_ret; - } + + if (op_ret > 0) { + op_ret = 0; + plist_for_each_entry_safe(this, next, &hb2->chain, list) { + if (futex_match(&this->key, &key2)) { + if (this->pi_state || this->rt_waiter) { + ret = -EINVAL; + goto out_unlock; + } + this->wake(&wake_q, this); + if (++op_ret >= nr_wake2) + break; + } + } + ret += op_ret; + } out_unlock: - double_unlock_hb(hb1, hb2); + double_unlock_hb(hb1, hb2); + } wake_up_q(&wake_q); return ret; } @@ -320,23 +334,12 @@ out_unlock: static long futex_wait_restart(struct restart_block *restart); /** - * futex_wait_queue() - futex_queue() and wait for wakeup, timeout, or signal - * @hb: the futex hash bucket, must be locked by the caller + * futex_do_wait() - wait for wakeup, timeout, or signal * @q: the futex_q to queue up on * @timeout: the prepared hrtimer_sleeper, or null for no timeout */ -void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q, - struct hrtimer_sleeper *timeout) +void futex_do_wait(struct futex_q *q, struct hrtimer_sleeper *timeout) { - /* - * The task state is guaranteed to be set before another task can - * wake it. set_current_state() is implemented using smp_store_mb() and - * futex_queue() calls spin_unlock() upon completion, both serializing - * access to the hash list and forcing another memory barrier. - */ - set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); - futex_queue(q, hb); - /* Arm the timer */ if (timeout) hrtimer_sleeper_start_expires(timeout, HRTIMER_MODE_ABS); @@ -358,7 +361,7 @@ void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q, } /** - * unqueue_multiple - Remove various futexes from their hash bucket + * futex_unqueue_multiple - Remove various futexes from their hash bucket * @v: The list of futexes to unqueue * @count: Number of futexes in the list * @@ -368,7 +371,7 @@ void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q, * - >=0 - Index of the last futex that was awoken; * - -1 - No futex was awoken */ -static int unqueue_multiple(struct futex_vector *v, int count) +int futex_unqueue_multiple(struct futex_vector *v, int count) { int ret = -1, i; @@ -396,14 +399,19 @@ static int unqueue_multiple(struct futex_vector *v, int count) * - 0 - Success * - <0 - -EFAULT, -EWOULDBLOCK or -EINVAL */ -static int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken) +int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken) { - struct futex_hash_bucket *hb; bool retry = false; int ret, i; u32 uval; /* + * Make sure to have a reference on the private_hash such that we + * don't block on rehash after changing the task state below. + */ + guard(private_hash)(); + + /* * Enqueuing multiple futexes is tricky, because we need to enqueue * each futex on the list before dealing with the next one to avoid * deadlocking on the hash bucket. But, before enqueuing, we need to @@ -419,11 +427,11 @@ static int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *wo */ retry: for (i = 0; i < count; i++) { - if ((vs[i].w.flags & FUTEX_PRIVATE_FLAG) && retry) + if (!(vs[i].w.flags & FLAGS_SHARED) && retry) continue; ret = get_futex_key(u64_to_user_ptr(vs[i].w.uaddr), - !(vs[i].w.flags & FUTEX_PRIVATE_FLAG), + vs[i].w.flags, &vs[i].q.key, FUTEX_READ); if (unlikely(ret)) @@ -435,22 +443,26 @@ retry: for (i = 0; i < count; i++) { u32 __user *uaddr = (u32 __user *)(unsigned long)vs[i].w.uaddr; struct futex_q *q = &vs[i].q; - u32 val = (u32)vs[i].w.val; + u32 val = vs[i].w.val; - hb = futex_q_lock(q); - ret = futex_get_value_locked(&uval, uaddr); + if (1) { + CLASS(hb, hb)(&q->key); - if (!ret && uval == val) { - /* - * The bucket lock can't be held while dealing with the - * next futex. Queue each futex at this moment so hb can - * be unlocked. - */ - futex_queue(q, hb); - continue; - } + futex_q_lock(q, hb); + ret = futex_get_value_locked(&uval, uaddr); - futex_q_unlock(hb); + if (!ret && uval == val) { + /* + * The bucket lock can't be held while dealing with the + * next futex. Queue each futex at this moment so hb can + * be unlocked. + */ + futex_queue(q, hb, current); + continue; + } + + futex_q_unlock(hb); + } __set_current_state(TASK_RUNNING); /* @@ -458,7 +470,7 @@ retry: * was woken, we don't return error and return this index to * userspace */ - *woken = unqueue_multiple(vs, i); + *woken = futex_unqueue_multiple(vs, i); if (*woken >= 0) return 1; @@ -543,7 +555,7 @@ int futex_wait_multiple(struct futex_vector *vs, unsigned int count, __set_current_state(TASK_RUNNING); - ret = unqueue_multiple(vs, count); + ret = futex_unqueue_multiple(vs, count); if (ret >= 0) return ret; @@ -564,7 +576,8 @@ int futex_wait_multiple(struct futex_vector *vs, unsigned int count, * @val: the expected value * @flags: futex flags (FLAGS_SHARED, etc.) * @q: the associated futex_q - * @hb: storage for hash_bucket pointer to be returned to caller + * @key2: the second futex_key if used for requeue PI + * @task: Task queueing this futex * * Setup the futex_q and locate the hash_bucket. Get the futex value and * compare it with the expected value. Handle atomic faults internally. @@ -572,10 +585,12 @@ int futex_wait_multiple(struct futex_vector *vs, unsigned int count, * * Return: * - 0 - uaddr contains val and hb has been locked; - * - <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlocked + * - <0 - On error and the hb is unlocked. A possible reason: the uaddr can not + * be read, does not contain the expected value or is not properly aligned. */ int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags, - struct futex_q *q, struct futex_hash_bucket **hb) + struct futex_q *q, union futex_key *key2, + struct task_struct *task) { u32 uval; int ret; @@ -599,69 +614,84 @@ int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags, * while the syscall executes. */ retry: - ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key, FUTEX_READ); + ret = get_futex_key(uaddr, flags, &q->key, FUTEX_READ); if (unlikely(ret != 0)) return ret; retry_private: - *hb = futex_q_lock(q); + if (1) { + CLASS(hb, hb)(&q->key); - ret = futex_get_value_locked(&uval, uaddr); + futex_q_lock(q, hb); - if (ret) { - futex_q_unlock(*hb); + ret = futex_get_value_locked(&uval, uaddr); - ret = get_user(uval, uaddr); - if (ret) - return ret; + if (ret) { + futex_q_unlock(hb); + + ret = get_user(uval, uaddr); + if (ret) + return ret; - if (!(flags & FLAGS_SHARED)) - goto retry_private; + if (!(flags & FLAGS_SHARED)) + goto retry_private; - goto retry; - } + goto retry; + } - if (uval != val) { - futex_q_unlock(*hb); - ret = -EWOULDBLOCK; + if (uval != val) { + futex_q_unlock(hb); + return -EWOULDBLOCK; + } + + if (key2 && futex_match(&q->key, key2)) { + futex_q_unlock(hb); + return -EINVAL; + } + + /* + * The task state is guaranteed to be set before another task can + * wake it. set_current_state() is implemented using smp_store_mb() and + * futex_queue() calls spin_unlock() upon completion, both serializing + * access to the hash list and forcing another memory barrier. + */ + if (task == current) + set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); + futex_queue(q, hb, task); } return ret; } -int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset) +int __futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, + struct hrtimer_sleeper *to, u32 bitset) { - struct hrtimer_sleeper timeout, *to; - struct restart_block *restart; - struct futex_hash_bucket *hb; struct futex_q q = futex_q_init; int ret; if (!bitset) return -EINVAL; + q.bitset = bitset; - to = futex_setup_timer(abs_time, &timeout, flags, - current->timer_slack_ns); retry: /* * Prepare to wait on uaddr. On success, it holds hb->lock and q * is initialized. */ - ret = futex_wait_setup(uaddr, val, flags, &q, &hb); + ret = futex_wait_setup(uaddr, val, flags, &q, NULL, current); if (ret) - goto out; + return ret; /* futex_queue and wait for wakeup, timeout, or a signal. */ - futex_wait_queue(hb, &q, to); + futex_do_wait(&q, to); /* If we were woken (and unqueued), we succeeded, whatever. */ - ret = 0; if (!futex_unqueue(&q)) - goto out; - ret = -ETIMEDOUT; + return 0; + if (to && !to->task) - goto out; + return -ETIMEDOUT; /* * We expect signal_pending(current), but we might be the @@ -670,24 +700,38 @@ retry: if (!signal_pending(current)) goto retry; - ret = -ERESTARTSYS; - if (!abs_time) - goto out; + return -ERESTARTSYS; +} + +int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset) +{ + struct hrtimer_sleeper timeout, *to; + struct restart_block *restart; + int ret; - restart = ¤t->restart_block; - restart->futex.uaddr = uaddr; - restart->futex.val = val; - restart->futex.time = *abs_time; - restart->futex.bitset = bitset; - restart->futex.flags = flags | FLAGS_HAS_TIMEOUT; + to = futex_setup_timer(abs_time, &timeout, flags, + current->timer_slack_ns); - ret = set_restart_fn(restart, futex_wait_restart); + ret = __futex_wait(uaddr, flags, val, to, bitset); + + /* No timeout, nothing to clean up. */ + if (!to) + return ret; -out: - if (to) { - hrtimer_cancel(&to->timer); - destroy_hrtimer_on_stack(&to->timer); + hrtimer_cancel(&to->timer); + destroy_hrtimer_on_stack(&to->timer); + + if (ret == -ERESTARTSYS) { + restart = ¤t->restart_block; + restart->futex.uaddr = uaddr; + restart->futex.val = val; + restart->futex.time = *abs_time; + restart->futex.bitset = bitset; + restart->futex.flags = flags | FLAGS_HAS_TIMEOUT; + + return set_restart_fn(restart, futex_wait_restart); } + return ret; } |