diff options
64 files changed, 582 insertions, 264 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 5a7a83c411e9..e92c0056e4e0 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -6429,6 +6429,9 @@ rootflags= [KNL] Set root filesystem mount option string + initramfs_options= [KNL] + Specify mount options for for the initramfs mount. + rootfstype= [KNL] Set root filesystem type rootwait [KNL] Wait (indefinitely) for root device to show up. diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index 85f590254f07..b5db45c0094c 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -340,8 +340,8 @@ of those. Caller makes sure async writeback cannot be running for the inode whil ->drop_inode() returns int now; it's called on final iput() with inode->i_lock held and it returns true if filesystems wants the inode to be -dropped. As before, generic_drop_inode() is still the default and it's been -updated appropriately. generic_delete_inode() is also alive and it consists +dropped. As before, inode_generic_drop() is still the default and it's been +updated appropriately. inode_just_drop() is also alive and it consists simply of return 1. Note that all actual eviction work is done by caller after ->drop_inode() returns. diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 2971551b7235..b7e3147ba3d4 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -2362,6 +2362,7 @@ The following mount options are supported: hidepid= Set /proc/<pid>/ access mode. gid= Set the group authorized to learn processes information. subset= Show only the specified subset of procfs. + pidns= Specify a the namespace used by this procfs. ========= ======================================================== hidepid=off or hidepid=0 means classic mode - everybody may access all @@ -2394,6 +2395,13 @@ information about processes information, just add identd to this group. subset=pid hides all top level files and directories in the procfs that are not related to tasks. +pidns= specifies a pid namespace (either as a string path to something like +`/proc/$pid/ns/pid`, or a file descriptor when using `FSCONFIG_SET_FD`) that +will be used by the procfs instance when translating pids. By default, procfs +will use the calling process's active pid namespace. Note that the pid +namespace of an existing procfs instance cannot be modified (attempting to do +so will give an `-EBUSY` error). + Chapter 5: Filesystem behavior ============================== diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index 486a91633474..7a314eee6305 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -327,11 +327,11 @@ or bottom half). inode->i_lock spinlock held. This method should be either NULL (normal UNIX filesystem - semantics) or "generic_delete_inode" (for filesystems that do + semantics) or "inode_just_drop" (for filesystems that do not want to cache inodes - causing "delete_inode" to always be called regardless of the value of i_nlink) - The "generic_delete_inode()" behavior is equivalent to the old + The "inode_just_drop()" behavior is equivalent to the old practice of using "force_delete" in the put_inode() case, but does not have the races that the "force_delete()" approach had. diff --git a/block/bdev.c b/block/bdev.c index b77ddd12dc06..810707cca970 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -412,7 +412,7 @@ static const struct super_operations bdev_sops = { .statfs = simple_statfs, .alloc_inode = bdev_alloc_inode, .free_inode = bdev_free_inode, - .drop_inode = generic_delete_inode, + .drop_inode = inode_just_drop, .evict_inode = bdev_evict_inode, }; diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 54c480e874cb..d7714d8afb0f 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -388,7 +388,7 @@ static const struct super_operations dax_sops = { .alloc_inode = dax_alloc_inode, .destroy_inode = dax_destroy_inode, .free_inode = dax_free_inode, - .drop_inode = generic_delete_inode, + .drop_inode = inode_just_drop, }; static int dax_init_fs_context(struct fs_context *fc) diff --git a/drivers/misc/ibmasm/ibmasmfs.c b/drivers/misc/ibmasm/ibmasmfs.c index c44de892a61e..5372ed2a363e 100644 --- a/drivers/misc/ibmasm/ibmasmfs.c +++ b/drivers/misc/ibmasm/ibmasmfs.c @@ -94,7 +94,7 @@ static int ibmasmfs_init_fs_context(struct fs_context *fc) static const struct super_operations ibmasmfs_s_ops = { .statfs = simple_statfs, - .drop_inode = generic_delete_inode, + .drop_inode = inode_just_drop, }; static const struct file_operations *ibmasmfs_dir_ops = &simple_dir_operations; diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 08a251df20c4..5246fa6af3d6 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -1891,7 +1891,7 @@ static struct dentry *ffs_sb_create_file(struct super_block *sb, /* Super block */ static const struct super_operations ffs_sb_operations = { .statfs = simple_statfs, - .drop_inode = generic_delete_inode, + .drop_inode = inode_just_drop, }; struct ffs_sb_fill_data { diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index b51e132b0cd2..13c3da49348c 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -2011,7 +2011,7 @@ gadgetfs_create_file (struct super_block *sb, char const *name, static const struct super_operations gadget_fs_operations = { .statfs = simple_statfs, - .drop_inode = generic_delete_inode, + .drop_inode = inode_just_drop, }; static int diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index 795c6388744c..1581ebac5bb4 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -252,7 +252,7 @@ static int v9fs_drop_inode(struct inode *inode) v9ses = v9fs_inode2v9ses(inode); if (v9ses->cache & (CACHE_META|CACHE_LOOSE)) - return generic_drop_inode(inode); + return inode_generic_drop(inode); /* * in case of non cached mode always drop the * inode because we want the inode attribute diff --git a/fs/afs/inode.c b/fs/afs/inode.c index e9538e91f848..e1cb17b85791 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -723,9 +723,9 @@ int afs_drop_inode(struct inode *inode) _enter(""); if (test_bit(AFS_VNODE_PSEUDODIR, &AFS_FS_I(inode)->flags)) - return generic_delete_inode(inode); + return inode_just_drop(inode); else - return generic_drop_inode(inode); + return inode_generic_drop(inode); } /* diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 18db1053cdf0..3923be975e47 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7973,7 +7973,7 @@ int btrfs_drop_inode(struct inode *inode) if (btrfs_root_refs(&root->root_item) == 0) return 1; else - return generic_drop_inode(inode); + return inode_generic_drop(inode); } static void init_once(void *foo) diff --git a/fs/ceph/super.c b/fs/ceph/super.c index c3eb651862c5..70dc9467f6a0 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -1042,7 +1042,7 @@ static const struct super_operations ceph_super_ops = { .alloc_inode = ceph_alloc_inode, .free_inode = ceph_free_inode, .write_inode = ceph_write_inode, - .drop_inode = generic_delete_inode, + .drop_inode = inode_just_drop, .evict_inode = ceph_evict_inode, .sync_fs = ceph_sync_fs, .put_super = ceph_put_super, diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c index 740f18b60c9d..456c4a2efb53 100644 --- a/fs/configfs/mount.c +++ b/fs/configfs/mount.c @@ -36,7 +36,7 @@ static void configfs_free_inode(struct inode *inode) static const struct super_operations configfs_ops = { .statfs = simple_statfs, - .drop_inode = generic_delete_inode, + .drop_inode = inode_just_drop, .free_inode = configfs_free_inode, }; diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index b002e9b734f9..12daa85ed941 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -116,9 +116,18 @@ static struct inode *get_cramfs_inode(struct super_block *sb, inode_nohighmem(inode); inode->i_data.a_ops = &cramfs_aops; break; - default: + case S_IFCHR: + case S_IFBLK: + case S_IFIFO: + case S_IFSOCK: init_special_inode(inode, cramfs_inode->mode, old_decode_dev(cramfs_inode->size)); + break; + default: + printk(KERN_DEBUG "CRAMFS: Invalid file type 0%04o for inode %lu.\n", + inode->i_mode, inode->i_ino); + iget_failed(inode); + return ERR_PTR(-EIO); } inode->i_mode = cramfs_inode->mode; diff --git a/fs/dcache.c b/fs/dcache.c index 60046ae23d51..336bdb4c4b1f 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2509,8 +2509,8 @@ static inline unsigned start_dir_add(struct inode *dir) { preempt_disable_nested(); for (;;) { - unsigned n = dir->i_dir_seq; - if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n) + unsigned n = READ_ONCE(dir->i_dir_seq); + if (!(n & 1) && try_cmpxchg(&dir->i_dir_seq, &n, n + 1)) return n; cpu_relax(); } diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 4bb4002e3cdf..1f4d8ce56667 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -127,7 +127,7 @@ static int efivarfs_unfreeze_fs(struct super_block *sb); static const struct super_operations efivarfs_ops = { .statfs = efivarfs_statfs, - .drop_inode = generic_delete_inode, + .drop_inode = inode_just_drop, .alloc_inode = efivarfs_alloc_inode, .free_inode = efivarfs_free_inode, .show_options = efivarfs_show_options, diff --git a/fs/eventpoll.c b/fs/eventpoll.c index b22d6f819f78..ee7c4b683ec3 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -46,10 +46,10 @@ * * 1) epnested_mutex (mutex) * 2) ep->mtx (mutex) - * 3) ep->lock (rwlock) + * 3) ep->lock (spinlock) * * The acquire order is the one listed above, from 1 to 3. - * We need a rwlock (ep->lock) because we manipulate objects + * We need a spinlock (ep->lock) because we manipulate objects * from inside the poll callback, that might be triggered from * a wake_up() that in turn might be called from IRQ context. * So we can't sleep inside the poll callback and hence we need @@ -195,7 +195,7 @@ struct eventpoll { struct list_head rdllist; /* Lock which protects rdllist and ovflist */ - rwlock_t lock; + spinlock_t lock; /* RB tree root used to store monitored fd structs */ struct rb_root_cached rbr; @@ -741,10 +741,10 @@ static void ep_start_scan(struct eventpoll *ep, struct list_head *txlist) * in a lockless way. */ lockdep_assert_irqs_enabled(); - write_lock_irq(&ep->lock); + spin_lock_irq(&ep->lock); list_splice_init(&ep->rdllist, txlist); WRITE_ONCE(ep->ovflist, NULL); - write_unlock_irq(&ep->lock); + spin_unlock_irq(&ep->lock); } static void ep_done_scan(struct eventpoll *ep, @@ -752,7 +752,7 @@ static void ep_done_scan(struct eventpoll *ep, { struct epitem *epi, *nepi; - write_lock_irq(&ep->lock); + spin_lock_irq(&ep->lock); /* * During the time we spent inside the "sproc" callback, some * other events might have been queued by the poll callback. @@ -793,7 +793,7 @@ static void ep_done_scan(struct eventpoll *ep, wake_up(&ep->wq); } - write_unlock_irq(&ep->lock); + spin_unlock_irq(&ep->lock); } static void ep_get(struct eventpoll *ep) @@ -868,10 +868,10 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force) rb_erase_cached(&epi->rbn, &ep->rbr); - write_lock_irq(&ep->lock); + spin_lock_irq(&ep->lock); if (ep_is_linked(epi)) list_del_init(&epi->rdllink); - write_unlock_irq(&ep->lock); + spin_unlock_irq(&ep->lock); wakeup_source_unregister(ep_wakeup_source(epi)); /* @@ -1152,7 +1152,7 @@ static int ep_alloc(struct eventpoll **pep) return -ENOMEM; mutex_init(&ep->mtx); - rwlock_init(&ep->lock); + spin_lock_init(&ep->lock); init_waitqueue_head(&ep->wq); init_waitqueue_head(&ep->poll_wait); INIT_LIST_HEAD(&ep->rdllist); @@ -1240,99 +1240,9 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, #endif /* CONFIG_KCMP */ /* - * Adds a new entry to the tail of the list in a lockless way, i.e. - * multiple CPUs are allowed to call this function concurrently. - * - * Beware: it is necessary to prevent any other modifications of the - * existing list until all changes are completed, in other words - * concurrent list_add_tail_lockless() calls should be protected - * with a read lock, where write lock acts as a barrier which - * makes sure all list_add_tail_lockless() calls are fully - * completed. - * - * Also an element can be locklessly added to the list only in one - * direction i.e. either to the tail or to the head, otherwise - * concurrent access will corrupt the list. - * - * Return: %false if element has been already added to the list, %true - * otherwise. - */ -static inline bool list_add_tail_lockless(struct list_head *new, - struct list_head *head) -{ - struct list_head *prev; - - /* - * This is simple 'new->next = head' operation, but cmpxchg() - * is used in order to detect that same element has been just - * added to the list from another CPU: the winner observes - * new->next == new. - */ - if (!try_cmpxchg(&new->next, &new, head)) - return false; - - /* - * Initially ->next of a new element must be updated with the head - * (we are inserting to the tail) and only then pointers are atomically - * exchanged. XCHG guarantees memory ordering, thus ->next should be - * updated before pointers are actually swapped and pointers are - * swapped before prev->next is updated. - */ - - prev = xchg(&head->prev, new); - - /* - * It is safe to modify prev->next and new->prev, because a new element - * is added only to the tail and new->next is updated before XCHG. - */ - - prev->next = new; - new->prev = prev; - - return true; -} - -/* - * Chains a new epi entry to the tail of the ep->ovflist in a lockless way, - * i.e. multiple CPUs are allowed to call this function concurrently. - * - * Return: %false if epi element has been already chained, %true otherwise. - */ -static inline bool chain_epi_lockless(struct epitem *epi) -{ - struct eventpoll *ep = epi->ep; - - /* Fast preliminary check */ - if (epi->next != EP_UNACTIVE_PTR) - return false; - - /* Check that the same epi has not been just chained from another CPU */ - if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR) - return false; - - /* Atomically exchange tail */ - epi->next = xchg(&ep->ovflist, epi); - - return true; -} - -/* * This is the callback that is passed to the wait queue wakeup * mechanism. It is called by the stored file descriptors when they * have events to report. - * - * This callback takes a read lock in order not to contend with concurrent - * events from another file descriptor, thus all modifications to ->rdllist - * or ->ovflist are lockless. Read lock is paired with the write lock from - * ep_start/done_scan(), which stops all list modifications and guarantees - * that lists state is seen correctly. - * - * Another thing worth to mention is that ep_poll_callback() can be called - * concurrently for the same @epi from different CPUs if poll table was inited - * with several wait queues entries. Plural wakeup from different CPUs of a - * single wait queue is serialized by wq.lock, but the case when multiple wait - * queues are used should be detected accordingly. This is detected using - * cmpxchg() operation. */ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { @@ -1343,7 +1253,7 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v unsigned long flags; int ewake = 0; - read_lock_irqsave(&ep->lock, flags); + spin_lock_irqsave(&ep->lock, flags); ep_set_busy_poll_napi_id(epi); @@ -1372,12 +1282,15 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v * chained in ep->ovflist and requeued later on. */ if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) { - if (chain_epi_lockless(epi)) + if (epi->next == EP_UNACTIVE_PTR) { + epi->next = READ_ONCE(ep->ovflist); + WRITE_ONCE(ep->ovflist, epi); ep_pm_stay_awake_rcu(epi); + } } else if (!ep_is_linked(epi)) { /* In the usual case, add event to ready list. */ - if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) - ep_pm_stay_awake_rcu(epi); + list_add_tail(&epi->rdllink, &ep->rdllist); + ep_pm_stay_awake_rcu(epi); } /* @@ -1410,7 +1323,7 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v pwake++; out_unlock: - read_unlock_irqrestore(&ep->lock, flags); + spin_unlock_irqrestore(&ep->lock, flags); /* We have to call this outside the lock */ if (pwake) @@ -1745,7 +1658,7 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, } /* We have to drop the new item inside our item list to keep track of it */ - write_lock_irq(&ep->lock); + spin_lock_irq(&ep->lock); /* record NAPI ID of new item if present */ ep_set_busy_poll_napi_id(epi); @@ -1762,7 +1675,7 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, pwake++; } - write_unlock_irq(&ep->lock); + spin_unlock_irq(&ep->lock); /* We have to call this outside the lock */ if (pwake) @@ -1826,7 +1739,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, * list, push it inside. */ if (ep_item_poll(epi, &pt, 1)) { - write_lock_irq(&ep->lock); + spin_lock_irq(&ep->lock); if (!ep_is_linked(epi)) { list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); @@ -1837,7 +1750,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, if (waitqueue_active(&ep->poll_wait)) pwake++; } - write_unlock_irq(&ep->lock); + spin_unlock_irq(&ep->lock); } |