diff options
Diffstat (limited to 'include')
40 files changed, 868 insertions, 907 deletions
diff --git a/include/acpi/actbl3.h b/include/acpi/actbl3.h index 7b9571e00cc4..832c6464f063 100644 --- a/include/acpi/actbl3.h +++ b/include/acpi/actbl3.h @@ -443,6 +443,7 @@ struct acpi_tpm2_phy { #define ACPI_TPM2_RESERVED10 10 #define ACPI_TPM2_COMMAND_BUFFER_WITH_ARM_SMC 11 /* V1.2 Rev 8 */ #define ACPI_TPM2_RESERVED 12 +#define ACPI_TPM2_COMMAND_BUFFER_WITH_PLUTON 13 /* Optional trailer appears after any start_method subtables */ diff --git a/include/linux/audit.h b/include/linux/audit.h index 3608992848d3..31086a72e32a 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -14,6 +14,7 @@ #include <linux/audit_arch.h> #include <uapi/linux/audit.h> #include <uapi/linux/netfilter/nf_tables.h> +#include <uapi/linux/fanotify.h> #define AUDIT_INO_UNSET ((unsigned long)-1) #define AUDIT_DEV_UNSET ((dev_t)-1) @@ -416,7 +417,7 @@ extern void __audit_log_capset(const struct cred *new, const struct cred *old); extern void __audit_mmap_fd(int fd, int flags); extern void __audit_openat2_how(struct open_how *how); extern void __audit_log_kern_module(char *name); -extern void __audit_fanotify(unsigned int response); +extern void __audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar); extern void __audit_tk_injoffset(struct timespec64 offset); extern void __audit_ntp_log(const struct audit_ntp_data *ad); extern void __audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, @@ -523,10 +524,10 @@ static inline void audit_log_kern_module(char *name) __audit_log_kern_module(name); } -static inline void audit_fanotify(unsigned int response) +static inline void audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar) { if (!audit_dummy_context()) - __audit_fanotify(response); + __audit_fanotify(response, friar); } static inline void audit_tk_injoffset(struct timespec64 offset) @@ -679,7 +680,7 @@ static inline void audit_log_kern_module(char *name) { } -static inline void audit_fanotify(unsigned int response) +static inline void audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar) { } static inline void audit_tk_injoffset(struct timespec64 offset) diff --git a/include/linux/capability.h b/include/linux/capability.h index 65efb74c3585..03c2a613ad40 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -42,6 +42,7 @@ struct inode; struct dentry; struct task_struct; struct user_namespace; +struct mnt_idmap; extern const kernel_cap_t __cap_empty_set; extern const kernel_cap_t __cap_init_eff_set; @@ -248,9 +249,9 @@ static inline bool ns_capable_setid(struct user_namespace *ns, int cap) } #endif /* CONFIG_MULTIUSER */ bool privileged_wrt_inode_uidgid(struct user_namespace *ns, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, const struct inode *inode); -bool capable_wrt_inode_uidgid(struct user_namespace *mnt_userns, +bool capable_wrt_inode_uidgid(struct mnt_idmap *idmap, const struct inode *inode, int cap); extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap); extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns); @@ -271,11 +272,11 @@ static inline bool checkpoint_restore_ns_capable(struct user_namespace *ns) } /* audit system wants to get cap info from files as well */ -int get_vfs_caps_from_disk(struct user_namespace *mnt_userns, +int get_vfs_caps_from_disk(struct mnt_idmap *idmap, const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); -int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry, +int cap_convert_nscap(struct mnt_idmap *idmap, struct dentry *dentry, const void **ivalue, size_t size); #endif /* !_LINUX_CAPABILITY_H */ diff --git a/include/linux/evm.h b/include/linux/evm.h index 7a9ee2157f69..7dc1ee74169f 100644 --- a/include/linux/evm.h +++ b/include/linux/evm.h @@ -21,34 +21,34 @@ extern enum integrity_status evm_verifyxattr(struct dentry *dentry, void *xattr_value, size_t xattr_value_len, struct integrity_iint_cache *iint); -extern int evm_inode_setattr(struct user_namespace *mnt_userns, +extern int evm_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); extern void evm_inode_post_setattr(struct dentry *dentry, int ia_valid); -extern int evm_inode_setxattr(struct user_namespace *mnt_userns, +extern int evm_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size); extern void evm_inode_post_setxattr(struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len); -extern int evm_inode_removexattr(struct user_namespace *mnt_userns, +extern int evm_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name); extern void evm_inode_post_removexattr(struct dentry *dentry, const char *xattr_name); -static inline void evm_inode_post_remove_acl(struct user_namespace *mnt_userns, +static inline void evm_inode_post_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { evm_inode_post_removexattr(dentry, acl_name); } -extern int evm_inode_set_acl(struct user_namespace *mnt_userns, +extern int evm_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl); -static inline int evm_inode_remove_acl(struct user_namespace *mnt_userns, +static inline int evm_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { - return evm_inode_set_acl(mnt_userns, dentry, acl_name, NULL); + return evm_inode_set_acl(idmap, dentry, acl_name, NULL); } static inline void evm_inode_post_set_acl(struct dentry *dentry, const char *acl_name, @@ -90,7 +90,7 @@ static inline enum integrity_status evm_verifyxattr(struct dentry *dentry, } #endif -static inline int evm_inode_setattr(struct user_namespace *mnt_userns, +static inline int evm_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { return 0; @@ -101,7 +101,7 @@ static inline void evm_inode_post_setattr(struct dentry *dentry, int ia_valid) return; } -static inline int evm_inode_setxattr(struct user_namespace *mnt_userns, +static inline int evm_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size) { @@ -116,7 +116,7 @@ static inline void evm_inode_post_setxattr(struct dentry *dentry, return; } -static inline int evm_inode_removexattr(struct user_namespace *mnt_userns, +static inline int evm_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name) { @@ -129,21 +129,21 @@ static inline void evm_inode_post_removexattr(struct dentry *dentry, return; } -static inline void evm_inode_post_remove_acl(struct user_namespace *mnt_userns, +static inline void evm_inode_post_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return; } -static inline int evm_inode_set_acl(struct user_namespace *mnt_userns, +static inline int evm_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { return 0; } -static inline int evm_inode_remove_acl(struct user_namespace *mnt_userns, +static inline int evm_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index fe848901fcc3..9f4d4bcbf251 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -213,7 +213,6 @@ struct export_operations { bool write, u32 *device_generation); int (*commit_blocks)(struct inode *inode, struct iomap *iomaps, int nr_iomaps, struct iattr *iattr); - u64 (*fetch_iversion)(struct inode *); #define EXPORT_OP_NOWCC (0x1) /* don't collect v3 wcc data */ #define EXPORT_OP_NOSUBTREECHK (0x2) /* no subtree checking */ #define EXPORT_OP_CLOSE_BEFORE_UNLINK (0x4) /* close files before unlink */ diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 8ad743def6f3..4f1c4f603118 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -122,6 +122,11 @@ #define ALL_FANOTIFY_EVENT_BITS (FANOTIFY_OUTGOING_EVENTS | \ FANOTIFY_EVENT_FLAGS) +/* These masks check for invalid bits in permission responses. */ +#define FANOTIFY_RESPONSE_ACCESS (FAN_ALLOW | FAN_DENY) +#define FANOTIFY_RESPONSE_FLAGS (FAN_AUDIT | FAN_INFO) +#define FANOTIFY_RESPONSE_VALID_MASK (FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS) + /* Do not use these old uapi constants internally */ #undef FAN_ALL_CLASS_BITS #undef FAN_ALL_INIT_FLAGS diff --git a/include/linux/fb.h b/include/linux/fb.h index 96b96323e9cb..73eb1f85ea8e 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -662,6 +662,7 @@ extern int fb_deferred_io_init(struct fb_info *info); extern void fb_deferred_io_open(struct fb_info *info, struct inode *inode, struct file *file); +extern void fb_deferred_io_release(struct fb_info *info); extern void fb_deferred_io_cleanup(struct fb_info *info); extern int fb_deferred_io_fsync(struct file *file, loff_t start, loff_t end, int datasync); diff --git a/include/linux/fileattr.h b/include/linux/fileattr.h index 9e37e063ac69..47c05a9851d0 100644 --- a/include/linux/fileattr.h +++ b/include/linux/fileattr.h @@ -53,7 +53,7 @@ static inline bool fileattr_has_fsx(const struct fileattr *fa) } int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa); -int vfs_fileattr_set(struct user_namespace *mnt_userns, struct dentry *dentry, +int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); #endif /* _LINUX_FILEATTR_H */ diff --git a/include/linux/filelock.h b/include/linux/filelock.h new file mode 100644 index 000000000000..efcdd1631d9b --- /dev/null +++ b/include/linux/filelock.h @@ -0,0 +1,439 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_FILELOCK_H +#define _LINUX_FILELOCK_H + +#include <linux/fs.h> + +#define FL_POSIX 1 +#define FL_FLOCK 2 +#define FL_DELEG 4 /* NFSv4 delegation */ +#define FL_ACCESS 8 /* not trying to lock, just looking */ +#define FL_EXISTS 16 /* when unlocking, test for existence */ +#define FL_LEASE 32 /* lease held on this file */ +#define FL_CLOSE 64 /* unlock on close */ +#define FL_SLEEP 128 /* A blocking lock */ +#define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */ +#define FL_UNLOCK_PENDING 512 /* Lease is being broken */ +#define FL_OFDLCK 1024 /* lock is "owned" by struct file */ +#define FL_LAYOUT 2048 /* outstanding pNFS layout */ +#define FL_RECLAIM 4096 /* reclaiming from a reboot server */ + +#define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE) + +/* + * Special return value from posix_lock_file() and vfs_lock_file() for + * asynchronous locking. + */ +#define FILE_LOCK_DEFERRED 1 + +struct file_lock; + +struct file_lock_operations { + void (*fl_copy_lock)(struct file_lock *, struct file_lock *); + void (*fl_release_private)(struct file_lock *); +}; + +struct lock_manager_operations { + void *lm_mod_owner; + fl_owner_t (*lm_get_owner)(fl_owner_t); + void (*lm_put_owner)(fl_owner_t); + void (*lm_notify)(struct file_lock *); /* unblock callback */ + int (*lm_grant)(struct file_lock *, int); + bool (*lm_break)(struct file_lock *); + int (*lm_change)(struct file_lock *, int, struct list_head *); + void (*lm_setup)(struct file_lock *, void **); + bool (*lm_breaker_owns_lease)(struct file_lock *); + bool (*lm_lock_expirable)(struct file_lock *cfl); + void (*lm_expire_lock)(void); +}; + +struct lock_manager { + struct list_head list; + /* + * NFSv4 and up also want opens blocked during the grace period; + * NLM doesn't care: + */ + bool block_opens; +}; + +struct net; +void locks_start_grace(struct net *, struct lock_manager *); +void locks_end_grace(struct lock_manager *); +bool locks_in_grace(struct net *); +bool opens_in_grace(struct net *); + +/* + * struct file_lock has a union that some filesystems use to track + * their own private info. The NFS side of things is defined here: + */ +#include <linux/nfs_fs_i.h> + +/* + * struct file_lock represents a generic "file lock". It's used to represent + * POSIX byte range locks, BSD (flock) locks, and leases. It's important to + * note that the same struct is used to represent both a request for a lock and + * the lock itself, but the same object is never used for both. + * + * FIXME: should we create a separate "struct lock_request" to help distinguish + * these two uses? + * + * The varous i_flctx lists are ordered by: + * + * 1) lock owner + * 2) lock range start + * 3) lock range end + * + * Obviously, the last two criteria only matter for POSIX locks. + */ +struct file_lock { + struct file_lock *fl_blocker; /* The lock, that is blocking us */ + struct list_head fl_list; /* link into file_lock_context */ + struct hlist_node fl_link; /* node in global lists */ + struct list_head fl_blocked_requests; /* list of requests with + * ->fl_blocker pointing here + */ + struct list_head fl_blocked_member; /* node in + * ->fl_blocker->fl_blocked_requests + */ + fl_owner_t fl_owner; + unsigned int fl_flags; + unsigned char fl_type; + unsigned int fl_pid; + int fl_link_cpu; /* what cpu's list is this on? */ + wait_queue_head_t fl_wait; + struct file *fl_file; + loff_t fl_start; + loff_t fl_end; + + struct fasync_struct * fl_fasync; /* for lease break notifications */ + /* for lease breaks: */ + unsigned long fl_break_time; + unsigned long fl_downgrade_time; + + const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */ + const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ + union { + struct nfs_lock_info nfs_fl; + struct nfs4_lock_info nfs4_fl; + struct { + struct list_head link; /* link in AFS vnode's pending_locks list */ + int state; /* state of grant or error if -ve */ + unsigned int debug_id; + } afs; + struct { + struct inode *inode; + } ceph; + } fl_u; +} __randomize_layout; + +struct file_lock_context { + spinlock_t flc_lock; + struct list_head flc_flock; + struct list_head flc_posix; + struct list_head flc_lease; +}; + +#ifdef CONFIG_FILE_LOCKING +int fcntl_getlk(struct file *, unsigned int, struct flock *); +int fcntl_setlk(unsigned int, struct file *, unsigned int, + struct flock *); + +#if BITS_PER_LONG == 32 +int fcntl_getlk64(struct file *, unsigned int, struct flock64 *); +int fcntl_setlk64(unsigned int, struct file *, unsigned int, + struct flock64 *); +#endif + +int fcntl_setlease(unsigned int fd, struct file *filp, long arg); +int fcntl_getlease(struct file *filp); + +/* fs/locks.c */ +void locks_free_lock_context(struct inode *inode); +void locks_free_lock(struct file_lock *fl); +void locks_init_lock(struct file_lock *); +struct file_lock * locks_alloc_lock(void); +void locks_copy_lock(struct file_lock *, struct file_lock *); +void locks_copy_conflock(struct file_lock *, struct file_lock *); +void locks_remove_posix(struct file *, fl_owner_t); +void locks_remove_file(struct file *); +void locks_release_private(struct file_lock *); +void posix_test_lock(struct file *, struct file_lock *); +int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); +int locks_delete_block(struct file_lock *); +int vfs_test_lock(struct file *, struct file_lock *); +int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); +int vfs_cancel_lock(struct file *filp, struct file_lock *fl); +bool vfs_inode_has_locks(struct inode *inode); +int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); +int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); +void lease_get_mtime(struct inode *, struct timespec64 *time); +int generic_setlease(struct file *, long, struct file_lock **, void **priv); +int vfs_setlease(struct file *, long, struct file_lock **, void **); +int lease_modify(struct file_lock *, int, struct list_head *); + +struct notifier_block; +int lease_register_notifier(struct notifier_block *); +void lease_unregister_notifier(struct notifier_block *); + +struct files_struct; +void show_fd_locks(struct seq_file *f, + struct file *filp, struct files_struct *files); +bool locks_owner_has_blockers(struct file_lock_context *flctx, + fl_owner_t owner); + +static inline struct file_lock_context * +locks_inode_context(const struct inode *inode) +{ + return smp_load_acquire(&inode->i_flctx); +} + +#else /* !CONFIG_FILE_LOCKING */ +static inline int fcntl_getlk(struct file *file, unsigned int cmd, + struct flock __user *user) +{ + return -EINVAL; +} + +static inline int fcntl_setlk(unsigned int fd, struct file *file, + unsigned int cmd, struct flock __user *user) +{ + return -EACCES; +} + +#if BITS_PER_LONG == 32 +static inline int fcntl_getlk64(struct file *file, unsigned int cmd, + struct flock64 *user) +{ + return -EINVAL; +} + +static inline int fcntl_setlk64(unsigned int fd, struct file *file, + unsigned int cmd, struct flock64 *user) +{ + return -EACCES; +} +#endif +static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg) +{ + return -EINVAL; +} + +static inline int fcntl_getlease(struct file *filp) +{ + return F_UNLCK; +} + +static inline void +locks_free_lock_context(struct inode *inode) +{ +} + +static inline void locks_init_lock(struct file_lock *fl) +{ + return; +} + +static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) +{ + return; +} + +static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl) +{ + return; +} + +static inline void locks_remove_posix(struct file *filp, fl_owner_t owner) +{ + return; +} + +static inline void locks_remove_file(struct file *filp) +{ + return; +} + +static inline void posix_test_lock(struct file *filp, struct file_lock *fl) +{ + return; +} + +static inline int posix_lock_file(struct file *filp, struct file_lock *fl, + struct file_lock *conflock) +{ + return -ENOLCK; +} + +static inline int locks_delete_block(struct file_lock *waiter) +{ + return -ENOENT; +} + +static inline int vfs_test_lock(struct file *filp, struct file_lock *fl) +{ + return 0; +} + +static inline int vfs_lock_file(struct file *filp, unsigned int cmd, + struct file_lock *fl, struct file_lock *conf) +{ + return -ENOLCK; +} + +static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) +{ + return 0; +} + +static inline bool vfs_inode_has_locks(struct inode *inode) +{ + return false; +} + +static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) +{ + return -ENOLCK; +} + +static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) +{ + return 0; +} + +static inline void lease_get_mtime(struct inode *inode, + struct timespec64 *time) +{ + return; +} + +static inline int generic_setlease(struct file *filp, long arg, + struct file_lock **flp, void **priv) +{ + return -EINVAL; +} + +static inline int vfs_setlease(struct file *filp, long arg, + struct file_lock **lease, void **priv) +{ + return -EINVAL; +} + +static inline int lease_modify(struct file_lock *fl, int arg, + struct list_head *dispose) +{ + return -EINVAL; +} + +struct files_struct; +static inline void show_fd_locks(struct seq_file *f, + struct file *filp, struct files_struct *files) {} +static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, + fl_owner_t owner) +{ + return false; +} + +static inline struct file_lock_context * +locks_inode_context(const struct inode *inode) +{ + return NULL; +} + +#endif /* !CONFIG_FILE_LOCKING */ + +static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) +{ + return locks_lock_inode_wait(file_inode(filp), fl); +} + +#ifdef CONFIG_FILE_LOCKING +static inline int break_lease(struct inode *inode, unsigned int mode) +{ + /* + * Since this check is lockless, we must ensure that any refcounts + * taken are done before checking i_flctx->flc_lease. Otherwise, we + * could end up racing with tasks trying to set a new lease on this + * file. + */ + smp_mb(); + if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) + return __break_lease(inode, mode, FL_LEASE); + return 0; +} + +static inline int break_deleg(struct inode *inode, unsigned int mode) +{ + /* + * Since this check is lockless, we must ensure that any refcounts + * taken are done before checking i_flctx->flc_lease. Otherwise, we + * could end up racing with tasks trying to set a new lease on this + * file. + */ + smp_mb(); + if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) + return __break_lease(inode, mode, FL_DELEG); + return 0; +} + +static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) +{ + int ret; + + ret = break_deleg(inode, O_WRONLY|O_NONBLOCK); + if (ret == -EWOULDBLOCK && delegated_inode) { + *delegated_inode = inode; + ihold(inode); + } + return ret; +} + +static inline int break_deleg_wait(struct inode **delegated_inode) +{ + int ret; + + ret = break_deleg(*delegated_inode, O_WRONLY); + iput(*delegated_inode); + *delegated_inode = NULL; + return ret; +} + +static inline int break_layout(struct inode *inode, bool wait) +{ + smp_mb(); + if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) + return __break_lease(inode, + wait ? O_WRONLY : O_WRONLY | O_NONBLOCK, + FL_LAYOUT); + return 0; +} + +#else /* !CONFIG_FILE_LOCKING */ +static inline int break_lease(struct inode *inode, unsigned int mode) +{ + return 0; +} + +static inline int break_deleg(struct inode *inode, unsigned int mode) +{ + return 0; +} + +static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) +{ + return 0; +} + +static inline int break_deleg_wait(struct inode **delegated_inode) +{ + BUG(); + return 0; +} + +static inline int break_layout(struct inode *inode, bool wait) +{ + return 0; +} + +#endif /* CONFIG_FILE_LOCKING */ + +#endif /* _LINUX_FILELOCK_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index c1769a2c5d70..2acc46fb5f97 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1003,135 +1003,11 @@ static inline struct file *get_file(struct file *f) #define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX) #endif -#define FL_POSIX 1 -#define FL_FLOCK 2 -#define FL_DELEG 4 /* NFSv4 delegation */ -#define FL_ACCESS 8 /* not trying to lock, just looking */ -#define FL_EXISTS 16 /* when unlocking, test for existence */ -#define FL_LEASE 32 /* lease held on this file */ -#define FL_CLOSE 64 /* unlock on close */ -#define FL_SLEEP 128 /* A blocking lock */ -#define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */ -#define FL_UNLOCK_PENDING 512 /* Lease is being broken */ -#define FL_OFDLCK 1024 /* lock is "owned" by struct file */ -#define FL_LAYOUT 2048 /* outstanding pNFS layout */ -#define FL_RECLAIM 4096 /* reclaiming from a reboot server */ - -#define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE) - -/* - * Special return value from posix_lock_file() and vfs_lock_file() for - * asynchronous locking. - */ -#define FILE_LOCK_DEFERRED 1 - /* legacy typedef, should eventually be removed */ typedef void *fl_owner_t; struct file_lock; -struct file_lock_operations { - void (*fl_copy_lock)(struct file_lock *, struct file_lock *); - void (*fl_release_private)(struct file_lock *); -}; - -struct lock_manager_operations { - void *lm_mod_owner; - fl_owner_t (*lm_get_owner)(fl_owner_t); - void (*lm_put_owner)(fl_owner_t); - void (*lm_notify)(struct file_lock *); /* unblock callback */ - int (*lm_grant)(struct file_lock *, int); - bool (*lm_break)(struct file_lock *); - int (*lm_change)(struct file_lock *, int, struct list_head *); - void (*lm_setup)(struct file_lock *, void **); - bool (*lm_breaker_owns_lease)(struct file_lock *); - bool (*lm_lock_expirable)(struct file_lock *cfl); - void (*lm_expire_lock)(void); -}; - -struct lock_manager { - struct list_head list; - /* - * NFSv4 and up also want opens blocked during the grace period; - * NLM doesn't care: - */ - bool block_opens; -}; - -struct net; -void locks_start_grace(struct net *, struct lock_manager *); -void locks_end_grace(struct lock_manager *); -bool locks_in_grace(struct net *); -bool opens_in_grace(struct net *); - -/* that will die - we need it for nfs_lock_info */ -#include <linux/nfs_fs_i.h> - -/* - * struct file_lock represents a generic "file lock". It's used to represent - * POSIX byte range locks, BSD (flock) locks, and leases. It's important to - * note that the same struct is used to represent both a request for a lock and - * the lock itself, but the same object is never used for both. - * - * FIXME: should we create a separate "struct lock_request" to help distinguish - * these two uses? - * - * The varous i_flctx lists are ordered by: - * - * 1) lock owner - * 2) lock range start - * 3) lock range end - * - * Obviously, the last two criteria only matter for POSIX locks. - */ -struct file_lock { - struct file_lock *fl_blocker; /* The lock, that is blocking us */ - struct list_head fl_list; /* link into file_lock_context */ - struct hlist_node fl_link; /* node in global lists */ - struct list_head fl_blocked_requests; /* list of requests with - * ->fl_blocker pointing here - */ - struct list_head fl_blocked_member; /* node in - * ->fl_blocker->fl_blocked_requests - */ - fl_owner_t fl_owner; - unsigned int fl_flags; - unsigned char fl_type; - unsigned int fl_pid; - int fl_link_cpu; /* what cpu's list is this on? */ - wait_queue_head_t fl_wait; - struct file *fl_file; - loff_t fl_start; - loff_t fl_end; - - struct fasync_struct * fl_fasync; /* for lease break notifications */ - /* for lease breaks: */ - unsigned long fl_break_time; - unsigned long fl_downgrade_time; - - const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */ - const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ - union { - struct nfs_lock_info nfs_fl; - struct nfs4_lock_info nfs4_fl; - struct { - struct list_head link; /* link in AFS vnode's pending_locks list */ - int state; /* state of grant or error if -ve */ - unsigned int debug_id; - } afs; - struct { - struct inode *inode; - } ceph; - } fl_u; -} __randomize_layout; - -struct file_lock_context { - spinlock_t flc_lock; - struct list_head flc_flock; - struct list_head flc_posix; - struct list_head flc_lease; -}; - /* The following constant reflects the upper bound of the file/locking space */ #ifndef OFFSET_MAX #define OFFSET_MAX type_max(loff_t) @@ -1140,216 +1016,6 @@ struct file_lock_context { extern void send_sigio(struct fown_struct *fown, int fd, int band); -#define locks_inode(f) file_inode(f) - -#ifdef CONFIG_FILE_LOCKING -extern int fcntl_getlk(struct file *, unsigned int, struct flock *); -extern int fcntl_setlk(unsigned int, struct file *, unsigned int, - struct flock *); - -#if BITS_PER_LONG == 32 -extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 *); -extern int fcntl_setlk64(unsigned int, struct file *, unsigned int, - struct flock64 *); -#endif - -extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg); -extern int fcntl_getlease(struct file *filp); - -/* fs/locks.c */ -void locks_free_lock_context(struct inode *inode); -void locks_free_lock(struct file_lock *fl); -extern void locks_init_lock(struct file_lock *); -extern struct file_lock * locks_alloc_lock(void); -extern void locks_copy_lock(struct file_lock *, struct file_lock *); -extern void locks_copy_conflock(struct file_lock *, struct file_lock *); -extern void locks_remove_posix(struct file *, fl_owner_t); -extern void locks_remove_file(struct file *); -extern void locks_release_private(struct file_lock *); -extern void posix_test_lock(struct file *, struct file_lock *); -extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); -extern int locks_delete_block(struct file_lock *); -extern int vfs_test_lock(struct file *, struct file_lock *); -extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); -extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl); -bool vfs_inode_has_locks(struct inode *inode); -extern int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); -extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); -extern void lease_get_mtime(struct inode *, struct timespec64 *time); -extern int generic_setlease(struct file *, long, struct file_lock **, void **priv); -extern int vfs_setlease(struct file *, long, struct file_lock **, void **); -extern int lease_modify(struct file_lock *, int, struct list_head *); - -struct notifier_block; -extern int lease_register_notifier(struct notifier_block *); -extern void lease_unregister_notifier(struct notifier_block *); - -struct files_struct; -extern void show_fd_locks(struct seq_file *f, - struct file *filp, struct files_struct *files); -extern bool locks_owner_has_blockers(struct file_lock_context *flctx, - fl_owner_t owner); - -static inline struct file_lock_context * -locks_inode_context(const struct inode *inode) -{ - return smp_load_acquire(&inode->i_flctx); -} - -#else /* !CONFIG_FILE_LOCKING */ -static inline int fcntl_getlk(struct file *file, unsigned int cmd, - struct flock __user *user) -{ - return -EINVAL; -} - -static inline int fcntl_setlk(unsigned int fd, struct file *file, - unsigned int cmd, struct flock __user *user) -{ - return -EACCES; -} - -#if BITS_PER_LONG == 32 -static inline int fcntl_getlk64(struct file *file, unsigned int cmd, - struct flock64 *user) -{ - return -EINVAL; -} - -static inline int fcntl_setlk64(unsigned int fd, struct file *file, - unsigned int cmd, struct flock64 *user) -{ - return -EACCES; -} -#endif -static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg) -{ - return -EINVAL; -} - -static inline int fcntl_getlease(struct file *filp) -{ - return F_UNLCK; -} - -static inline void -locks_free_lock_context(struct inode *inode) -{ -} - -static inline void locks_init_lock(struct file_lock *fl) -{ - return; -} - -static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) -{ - return; -} - -static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl) -{ - return; -} - -static inline void locks_remove_posix(struct file *filp, fl_owner_t owner) -{ - return; -} - -static inline void locks_remove_file(struct file *filp) -{ - return; -} - -static inline void posix_test_lock(struct file *filp, struct file_lock *fl) -{ - return; -} - -static inline int posix_lock_file(struct file *filp, struct file_lock *fl, - struct file_lock *conflock) -{ - return -ENOLCK; -} - -static inline int locks_delete_block(struct file_lock *waiter) -{ - return -ENOENT; -} - -static inline int vfs_test_lock(struct file *filp, struct file_lock *fl) -{ - return 0; -} - -static inline int vfs_lock_file(struct file *filp, unsigned int cmd, - struct file_lock *fl, struct file_lock *conf) -{ - return -ENOLCK; -} - -static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) -{ - return 0; -} - -static inline bool vfs_inode_has_locks(struct inode *inode) -{ - return false; -} - -static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) -{ - return -ENOLCK; -} - -static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) -{ - return 0; -} - -static inline void lease_get_mtime(struct inode *inode, - struct timespec64 *time) -{ - return; -} - -static inline int generic_setlease(struct file *filp, long arg, - struct file_lock **flp, void **priv) -{ - return -EINVAL; -} - -static inline int vfs_setlease(struct file *filp, long arg, - struct file_lock **lease, void **priv) -{ - return -EINVAL; -} - -static inline int lease_modify(struct file_lock *fl, int arg, - struct list_head *dispose) -{ - return -EINVAL; -} - -struct files_struct; -static inline void show_fd_locks(struct seq_file *f, - struct file *filp, struct files_struct *files) {} -static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, - fl_owner_t owner) -{ - return false; -} - -static inline struct file_lock_context * -locks_inode_context(const struct inode *inode) -{ - return NULL; -} - -#endif /* !CONFIG_FILE_LOCKING */ - static inline struct inode *file_inode(const struct file *f) { return f->f_inode; @@ -1360,11 +1026,6 @@ static inline struct dentry *file_dentry(const struct file *file) return d_real(file->f_path.dentry, file_inode(file)); } -static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) -{ - return locks_lock_inode_wait(locks_inode(filp), fl); -} - struct fasync_struct { rwlock_t fa_lock; int magic; @@ -1635,22 +1296,22 @@ static inline void i_gid_write(struct inode *inode, gid_t gid) } /** - * i_uid_into_vfsuid - map an inode's i_uid down into a mnt_userns - * @mnt_userns: user namespace of the mount the inode was found from + * i_uid_into_vfsuid - map an inode's i_uid down according to an idmapping + * @idmap: idmap of the mount the inode was found from * @inode: inode to map * - * Return: whe inode's i_uid mapped down according to @mnt_userns. + * Return: whe inode's i_uid mapped down according to @idmap. * If the inode's i_uid has no mapping INVALID_VFSUID is returned. */ -static inline vfsuid_t i_uid_into_vfsuid(struct user_namespace *mnt_userns, +static inline vfsuid_t i_uid_into_vfsuid(struct mnt_idmap *idmap, const struct inode *inode) { - return make_vfsuid(mnt_userns, i_user_ns(inode), inode->i_uid); + return make_vfsuid(idmap, i_user_ns(inode), inode->i_uid); } /** * i_uid_needs_update - check whether inode's i_uid needs to be updated - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * @@ -1659,50 +1320,50 @@ static inline vfsuid_t i_uid_into_vfsuid(struct user_namespace *mnt_userns, * * Return: true if @inode's i_uid field needs to be updated, false if not. */ -static inline bool i_uid_needs_update(struct user_namespace *mnt_userns, +static inline bool i_uid_needs_update(struct mnt_idmap *idmap, const struct iattr *attr, const struct inode *inode) { return ((attr->ia_valid & ATTR_UID) && !vfsuid_eq(attr->ia_vfsuid, - i_uid_into_vfsuid(mnt_userns, inode))); + i_uid_into_vfsuid(idmap, inode))); } /** * i_uid_update - update @inode's i_uid field - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Safely update @inode's i_uid field translating the vfsuid of any idmapped * mount into the filesystem kuid. */ -static inline void i_uid_update(struct user_namespace *mnt_userns, +static inline void i_uid_update(struct mnt_idmap *idmap, const struct iattr *attr, struct inode *inode) { if (attr->ia_valid & ATTR_UID) - inode->i_uid = from_vfsuid(mnt_userns, i_user_ns(inode), + inode->i_uid = from_vfsuid(idmap, i_user_ns(inode), attr->ia_vfsuid); } /** - * i_gid_into_vfsgid - map an inode's i_gid down into a mnt_userns - * @mnt_userns: user namespace of the mount the inode was found from + * i_gid_into_vfsgid - map an inode's i_gid down according to an idmapping + * @idmap: idmap of the mount the inode was found from * @inode: inode to map * - * Return: the inode's i_gid mapped down according to @mnt_userns. + * Return: the inode's i_gid mapped down according to @idmap. * If the inode's i_gid has no mapping INVALID_VFSGID is returned. */ -static inline vfsgid_t i_gid_into_vfsgid(struct user_namespace *mnt_userns, +static inline vfsgid_t i_gid_into_vfsgid(struct mnt_idmap *idmap, const struct inode *inode) { - return make_vfsgid(mnt_userns, i_user_ns(inode), inode->i_gid); + return make_vfsgid(idmap, i_user_ns(inode), inode->i_gid); } /** * i_gid_needs_update - check whether inode's i_gid needs to be updated - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * @@ -1711,83 +1372,83 @@ static inline vfsgid_t i_gid_into_vfsgid(struct user_namespace *mnt_userns, * * Return: true if @inode's i_gid field needs to be updated, false if not. */ -static inline bool i_gid_needs_update(struct user_namespace *mnt_userns, +static inline bool i_gid_needs_update(struct mnt_idmap *idmap, const struct iattr *attr, const struct inode *inode) { return ((attr->ia_valid & ATTR_GID) && !vfsgid_eq(attr->ia_vfsgid, - i_gid_into_vfsgid(mnt_userns, inode))); + i_gid_into_vfsgid(idmap, inode))); } /** * i_gid_update - update @inode's i_gid field - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Safely update @inode's i_gid field translating the vfsgid of any idmapped * mount into the filesystem kgid. */ -static inline void i_gid_update(struct user_namespace *mnt_userns, +static inline void i_gid_update(struct mnt_idmap *idmap, const struct iattr *attr, struct inode *inode) { if (attr->ia_valid & ATTR_GID) - inode->i_gid = from_vfsgid(mnt_userns, i_user_ns(inode), + inode->i_gid = from_vfsgid(idmap, i_user_ns(inode), attr->ia_vfsgid); } /** * inode_fsuid_set - initialize inode's i_uid field with callers fsuid * @inode: inode to initialize - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * * Initialize the i_uid field of @inode. If the inode was found/created via - * an idmapped mount map the caller's fsuid according to @mnt_users. + * an idmapped mount map the caller's fsuid according to @idmap. */ static inline void inode_fsuid_set(struct inode *inode, - struct user_namespace *mnt_userns) + struct mnt_idmap *idmap) { - inode->i_uid = mapped_fsuid(mnt_userns, i_user_ns(inode)); + inode->i_uid = mapped_fsuid(idmap, i_user_ns(inode)); } /** * inode_fsgid_set - initialize inode's i_gid field with callers fsgid * @inode: inode to initialize - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * * Initialize the i_gid field of @inode. If the inode was found/created via - * an idmapped mount map the caller's fsgid according to @mnt_users. + * an idmapped mount map the caller's fsgid according to @idmap. */ static inline void inode_fsgid_set(struct inode *inode, - struct user_namespace *mnt_userns) + struct mnt_idmap *idmap) { - inode->i_gid = mapped_fsgid(mnt_userns, i_user_ns(inode)); + inode->i_gid = mapped_fsgid(idmap, i_user_ns(inode)); } /** * fsuidgid_has_mapping() - check whether caller's fsuid/fsgid is mapped * @sb: the superblock we want a mapping in - * @mnt_userns: user namespace of the relevant mount + * @idmap: idmap of the relevant mount * * Check whether the caller's fsuid and fsgid have a valid mapping in the * s_user_ns of the superblock @sb. If the caller is on an idmapped mount map - * the caller's fsuid and fsgid according to the @mnt_userns first. + * the caller's fsuid and fsgid according to the @idmap first. * * Return: true if fsuid and fsgid is mapped, false if not. */ static inline bool fsuidgid_has_mapping(struct super_block *sb, - struct user_namespace *mnt_userns) + struct mnt_idmap *idmap) { struct user_namespace *fs_userns = sb->s_user_ns; kuid_t kuid; kgid_t kgid; - kuid = mapped_fsuid(mnt_userns, fs_userns); + kuid = mapped_fsuid(idmap, fs_userns); if (!uid_valid(kuid)) return false; - kgid = mapped_fsgid(mnt_userns, fs_userns); + kgid = mapped_fsgid(idmap, fs_userns); if (!gid_valid(kgid)) return false; return kuid_has_mapping(fs_userns, kuid) && @@ -1941,42 +1602,42 @@ static inline bool sb_start_intwrite_trylock(struct super_block *sb) return __sb_start_write_trylock(sb, SB_FREEZE_FS); } -bool inode_owner_or_capable(struct user_namespace *mnt_userns, +bool inode_owner_or_capable(struct mnt_idmap *idmap, const struct inode *inode); /* * VFS helper functions.. */ -int vfs_create(struct user_namespace *, struct inode *, +int vfs_create(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool); -int vfs_mkdir(struct user_namespace *, struct inode *, +int vfs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, umode_t); -int vfs_mknod(struct user_namespace *, struct inode *, struct dentry *, +int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); -int vfs_symlink(struct user_namespace *, struct inode *, +int vfs_symlink(struct mnt_idmap *, struct inode *, struct dentry *, const char *); -int vfs_link(struct dentry *, struct user_namespace *, struct inode *, +int vfs_link(struct dentry *, struct mnt_idmap *, struct inode *, struct dentry *, struct inode **); -int vfs_rmdir(struct user_namespace *, struct inode *, struct dentry *); -int vfs_unlink(struct user_namespace *, struct inode *, struct dentry *, +int vfs_rmdir(struct mnt_idmap *, struct inode *, struct dentry *); +int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *, struct inode **); /** * struct renamedata - contains all information required for renaming - * @old_mnt_userns: old user namespace of the mount the inode was found from + * @old_mnt_idmap: idmap of the old mount the inode was found from * @old_dir: parent of source * @old_dentry: source - * @new_mnt_userns: new user namespace of the mount the inode was found from + * @new_mnt_idmap: idmap of the new mount the inode was found from * @new_dir: parent of destination * @new_dentry: destination * @delegated_inode: returns an inode needing a delegation break * @flags: rename flags */ struct renamedata { - struct user_namespace *old_mnt_userns; + struct mnt_idmap *old_mnt_idmap; struct inode *old_dir; struct dentry *old_dentry; - struct user_namespace *new_mnt_userns; + struct mnt_idmap *new_mnt_idmap; struct inode *new_dir; struct dentry *new_dentry; struct inode **delegated_inode; @@ -1985,14 +1646,14 @@ struct renamedata { int vfs_rename(struct renamedata *); -static inline int vfs_whiteout(struct user_namespace *mnt_userns, +static inline int vfs_whiteout(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry) { - return vfs_mknod(mnt_userns, dir, dentry, S_IFCHR | WHITEOUT_MODE, + return vfs_mknod(idmap, dir, dentry, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); } -struct file *vfs_tmpfile_open(struct user_namespace *mnt_userns, +struct file *vfs_tmpfile_open(struct mnt_idmap *idmap, const struct path *parentpath, umode_t mode, int open_flag, const struct cred *cred); @@ -2016,10 +1677,10 @@ extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, /* * VFS file helper functions. */ -void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode, +void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode, const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); -umode_t mode_strip_sgid(struct user_namespace *mnt_userns, +umode_t mode_strip_sgid(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode); /* @@ -2137,27 +1798,26 @@ struct file_operations { struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); - int (*permission) (struct user_namespace *, struct inode *, int); + int (*permission) (struct mnt_idmap *, struct inode *, int); struct posix_acl * (*get_inode_acl)(struct inode *, int, bool); int (*readlink) (struct dentry *, char __user *,int); - int (*create) (struct user_namespace *, struct inode *,struct dentry *, + int (*create) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); - int (*symlink) (struct user_namespace *, struct inode *,struct dentry *, + int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *, const char *); - int (*mkdir) (struct user_namespace *, struct inode *,struct dentry *, + int (*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t); int (*rmdir) (struct inode *,struct dentry *); - int (*mknod) (struct user_namespace *, struct inode *,struct dentry *, + int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t,dev_t); - int (*rename) (struct user_namespace *, struct inode *, struct dentry *, + int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); - int (*setattr) (struct user_namespace *, struct dentry *, - struct iattr *); - int (*getattr) (struct user_namespace *, const struct path *, + int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *); + int (*getattr) (struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, @@ -2166,13 +1826,13 @@ struct inode_operations { int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode); - int (*tmpfile) (struct user_namespace *, struct inode *, + int (*tmpfile) (struct mnt_idmap *, struct inode *, struct file *, umode_t); - struct posix_acl *(*get_acl)(struct user_namespace *, struct dentry *, + struct posix_acl *(*get_acl)(struct mnt_idmap *, struct dentry *, int); - int (*set_acl)(struct user_namespace *, struct dentry *, + int (*set_acl)(struct mnt_idmap *, struct dentry *, struct posix_acl *, int); - int (*fileattr_set)(struct user_namespace *mnt_userns, + int (*fileattr_set)(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa); } ____cacheline_aligned; @@ -2326,11 +1986,11 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) -static inline bool HAS_UNMAPPED_ID(struct user_namespace *mnt_userns, +static inline bool HAS_UNMAPPED_ID(struct mnt_idmap *idmap, struct inode *inode) { - return !vfsuid_valid(i_uid_into_vfsuid(mnt_userns, inode)) || - !vfsgid_valid(i_gid_into_vfsgid(mnt_userns, inode)); + return !vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) || + !vfsgid_valid(i_gid_into_vfsgid(idmap, inode)); } static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) @@ -2624,96 +2284,6 @@ extern struct kobject *fs_kobj; #define MAX_RW_COUNT (INT_MAX & PAGE_MASK) -#ifdef CONFIG_FILE_LOCKING -static inline int break_lease(struct inode *inode, unsigned int mode) -{ - /* - * Since this check is lockless, we must ensure that any refcounts - * taken are done before checking i_flctx->flc_lease. Otherwise, we - * could end up racing with tasks trying to set a new lease on this - * file. - */ - smp_mb(); - if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) - return __break_lease(inode, mode, FL_LEASE); - return 0; -} - -static inline int break_deleg(struct inode *inode, unsigned int mode) -{ - /* - * Since this check is lockless, we must ensure that any refcounts - * taken are done before checking i_flctx->flc_lease. Otherwise, we - * could end up racing with tasks trying to set a new lease on this - * file. - */ - smp_mb(); - if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) - return __break_lease(inode, mode, FL_DELEG); - return 0; -} - -static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) -{ - int ret; - - ret = break_deleg(inode, O_WRONLY|O_NONBLOCK); - if (ret == -EWOULDBLOCK && delegated_inode) { - *delegated_inode = inode; - ihold(inode); - } - return ret; -} - -static inline int break_deleg_wait(struct inode **delegated_inode) -{ - int ret; - - ret = break_deleg(*delegated_inode, O_WRONLY); - iput(*delegated_inode); - *delegated_inode = NULL; - return ret; -} - -static inline int break_layout(struct inode *inode, bool wait) -{ - smp_mb(); - if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) - return __break_lease(inode, - wait ? O_WRONLY : O_WRONLY | O_NONBLOCK, - FL_LAYOUT); - return 0; -} - -#else /* !CONFIG_FILE_LOCKING */ -static inline int break_lease(struct inode *inode, unsigned int mode) -{ - return 0; -} - -static inline int break_deleg(struct inode *inode, unsigned int mode) -{ - return 0; -} - -static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) -{ - return 0; -} - -static inline int break_deleg_wait(struct inode **delegated_inode) -{ - BUG(); - return 0; -} - -static inline int break_layout(struct inode *inode, bool wait) -{ - return 0; -} - -#endif /* CONFIG_FILE_LOCKING */ - /* fs/open.c */ struct audit_names; struct filename { @@ -2725,11 +2295,6 @@ struct filename { }; static_assert(offsetof(struct filename, iname) % sizeof(long) == 0); -static inline struct user_namespace *file_mnt_user_ns(struct file *file) -{ - return mnt_user_ns(file->f_path.mnt); -} - static inline struct mnt_idmap *file_mnt_idmap(struct file *file) { return mnt_idmap(file->f_path.mnt); @@ -2749,7 +2314,7 @@ static inline bool is_idmapped_mnt(const struct vfsmount *mnt) } extern long vfs_truncate(const struct path *, loff_t); -int do_truncate(struct user_namespace *, struct dentry *, loff_t start, +int do_truncate(struct mnt_idmap *, struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); @@ -2904,21 +2469,21 @@ static inline int bmap(struct inode *inode, sector_t *block) } #endif -int notify_change(struct user_namespace *, struct dentry *, +int notify_change(struct mnt_idmap *, struct dentry *, struct iattr *, struct inode **); -int inode_permission(struct user_namespace *, struct inode *, int); -int generic_permission(struct user_namespace *, struct inode *, int); +int inode_permission(struct mnt_idmap *, struct inode *, int); +int generic_permission(struct mnt_idmap *, struct inode *, int); static inline int file_permission(struct file *file, int mask) { - return inode_permission(file_mnt_user_ns(file), + return inode_permission(file_mnt_idmap(file), file_inode(file), mask); } static inline int path_permission(const struct path *path, int mask) { - return inode_permission(mnt_user_ns(path->mnt), + return inode_permission(mnt_idmap(path->mnt), d_inode(path->dentry), mask); } -int __check_sticky(struct user_namespace *mnt_userns, struct inode *dir, +int __check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode); static inline bool execute_ok(struct inode *inode) @@ -3106,7 +2671,7 @@ extern void __destroy_inode(struct inode *); extern struct inode *new_inode_pseudo(struct super_block *sb); extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); -extern int setattr_should_drop_suidgid(struct user_namespace *, struct inode *); +extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *); extern int file_remove_privs(struct file *); /* @@ -3265,7 +2830,7 @@ extern void page_put_link(void *); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); -void generic_fillattr(struct user_namespace *, struct inode *, struct kstat *); +void generic_fillattr(struct mnt_idmap *, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); @@ -3316,9 +2881,9 @@ extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, struct dir_context *); -extern int simple_setattr(struct user_namespace *, struct dentry *, +extern int simple_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); -extern int simple_getattr(struct user_namespace *, const struct path *, +extern int simple_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_open(struct inode *inode, struct file *file); @@ -3327,7 +2892,7 @@ extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); extern int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); -extern int simple_rename(struct user_namespace *, struct inode *, +extern int simple_rename(struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); extern void simple_recursive_removal(struct dentry *, @@ -3369,11 +2934,11 @@ extern int generic_check_addressable(unsigned, u64); extern void generic_set_encrypted_ci_d_ops(struct dentry *dentry); -int may_setattr(struct user_namespace *mnt_userns, struct inode *inode, +int may_setattr(struct mnt_idmap *idmap, struct inode *inode, unsigned int ia_valid); -int setattr_prepare(struct user_namespace *, struct dentry *, struct iattr *); +int setattr_prepare(struct mnt_idmap *, struct dentry *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); -void setattr_copy(struct user_namespace *, struct inode *inode, +void setattr_copy(struct mnt_idmap *, struct inode *inode, const struct iattr *attr); extern int file_update_time(struct file *file); @@ -3540,13 +3105,13 @@ static inline bool is_sxid(umode_t mode) return mode & (S_ISUID | S_ISGID); } -static inline int check_sticky(struct user_namespace *mnt_userns, +static inline int check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode) { if (!(dir->i_mode & S_ISVTX)) return 0; - return __check_sticky(mnt_userns, dir, inode); + return __check_sticky(idmap, dir, inode); } static inline void inode_has_no_xattr(struct inode *inode) diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 4f5f8a651213..e0a49c3125eb 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -257,8 +257,8 @@ int fscrypt_encrypt_block_inplace(const struct inode *inode, struct page *page, unsigned int len, unsigned int offs, u64 lblk_num, gfp_t gfp_flags); -int fscrypt_decrypt_pagecache_blocks(struct page *page, unsigned int len, - unsigned int offs); +int fscrypt_decrypt_pagecache_blocks(struct folio *folio, size_t len, + size_t offs); int fscrypt_decrypt_block_inplace(const struct inode *inode, struct page *page, unsigned int len, unsigned int offs, u64 lblk_num); @@ -309,8 +309,6 @@ fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) /* keyring.c */ void fscrypt_destroy_keyring(struct super_block *sb); int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); -int fscrypt_add_test_dummy_key(struct super_block *sb, - const struct fscrypt_dummy_policy *dummy_policy); int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg); int fscrypt_ioctl_remove_key_all_users(struct file *filp, void __user *arg); int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg); @@ -422,9 +420,8 @@ static inline int fscrypt_encrypt_block_inplace(const struct inode *inode, return -EOPNOTSUPP; } -static inline int fscrypt_decrypt_pagecache_blocks(struct page *page, - unsigned int len, - unsigned int offs) +static inline int fscrypt_decrypt_pagecache_blocks(struct folio *folio, + size_t len, size_t offs) { return -EOPNOTSUPP; } @@ -530,13 +527,6 @@ static inline int fscrypt_ioctl_add_key(struct file *filp, void __user *arg) return -EOPNOTSUPP; } -static inline int -fscrypt_add_test_dummy_key(struct super_block *sb, - const struct fscrypt_dummy_policy *dummy_policy) -{ - return 0; -} - static inline int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg) { return -EOPNOTSUPP; diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index 40f14e5fed9d..119a3266791f 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -12,6 +12,7 @@ #define _LINUX_FSVERITY_H #include <linux/fs.h> +#include <linux/mm.h> #include <crypto/hash_info.h> #include <crypto/sha2.h> #include <uapi/linux/fsverity.h> @@ -93,8 +94,7 @@ struct fsverity_operations { * isn't already cached. Implementations may ignore this * argument; it's only a performance optimization. * - * This can be called at any time on an open verity file, as well as - * between ->begin_enable_verity() and ->end_enable_verity(). It may be + * This can be called at any time on an open verity file. It may be * called by multiple processes concurrently, even with the same page. * * Note that this must retrieve a *page*, not necessarily a *block*. @@ -109,9 +109,9 @@ struct fsverity_operations { * Write a Merkle tree block to the given inode. * * @inode: the inode for which the Merkle tree is being built - * @buf: block to write - * @index: 0-based index of the block within the Merkle tree - * @log_blocksize: log base 2 of the Merkle tree block size + * @buf: the Merkle tree block to write + * @pos: the position of the block in the Merkle tree (in bytes) + * @size: the Merkle tree block size (in bytes) * * This is only called between ->begin_enable_verity() and * ->end_enable_verity(). @@ -119,7 +119,7 @@ struct fsverity_operations { * Return: 0 on success, -errno on failure */ int (*write_merkle_tree_block)(struct inode *inode, const void *buf, - u64 index, int log_blocksize); + u64 pos, unsigned int size); }; #ifdef CONFIG_FS_VERITY @@ -148,9 +148,21 @@ int fsverity_get_digest(struct inode *inode, /* open.c */ -int fsverity_file_open(struct inode *inode, struct file *filp); -int fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr); -void fsverity_cleanup_inode(struct inode *inode); +int __fsverity_file_open(struct inode *inode, struct file *filp); +int __fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr); +void __fsverity_cleanup_inode(struct inode *inode); + +/** + * fsverity_cleanup_inode() - free the inode's verity info, if present + * @inode: an inode being evicted + * + * Filesystems must call this on inode eviction to free ->i_verity_info. + */ +static inline void fsverity_cleanup_inode(struct inode *inode) +{ + if (inode->i_verity_info) + __fsverity_cleanup_inode(inode); +} /* read_metadata.c */ @@ -158,7 +170,7 @@ int fsverity_ioctl_read_metadata(struct file *filp, const void __user *uarg); /* verify.c */ -bool fsverity_verify_page(struct page *page); +bool fsverity_verify_blocks(struct folio *folio, size_t len, size_t offset); void fsverity_verify_bio(struct bio *bio); void fsverity_enqueue_verify_work(struct work_struct *work); @@ -193,15 +205,15 @@ static inline int fsverity_get_digest(struct inode *inode, /* open.c */ -static inline int fsverity_file_open(struct inode *inode, struct file *filp) +static inline int __fsverity_file_open(struct inode *inode, struct file *filp) { - return IS_VERITY(inode) ? -EOPNOTSUPP : 0; + return -EOPNOTSUPP; } -static inline int fsverity_prepare_setattr(struct dentry *dentry, - struct iattr *attr) +static inline int __fsverity_prepare_setattr(struct dentry *dentry, + struct iattr *attr) { - return IS_VERITY(d_inode(dentry)) ? -EOPNOTSUPP : 0; + return -EOPNOTSUPP; } static inline void fsverity_cleanup_inode(struct inode *inode) @@ -218,7 +230,8 @@ static inline int fsverity_ioctl_read_metadata(struct file *filp, /* verify.c */ -static inline bool fsverity_verify_page(struct page *page) +static inline bool fsverity_verify_blocks(struct folio *folio, size_t len, + size_t offset) { WARN_ON(1); return false; @@ -236,6 +249,16 @@ static inline void fsverity_enqueue_verify_work(struct work_struct *work) #endif /* !CONFIG_FS_VERITY */ +static inline bool fsverity_verify_folio(struct folio *folio) +{ + return fsverity_verify_blocks(folio, folio_size(folio), 0); +} + +static inline bool fsverity_verify_page(struct page *page) +{ + return fsverity_verify_blocks(page_folio(page), PAGE_SIZE, 0); +} + /** * fsverity_active() - do reads from the inode need to go through fs-verity? * @inode: inode to check @@ -254,4 +277,42 @@ static inline bool fsverity_active(const struct inode *inode) return fsverity_get_info(inode) != NULL; } +/** + * fsverity_file_open() - prepare to open a verity file + * @inode: the inode being opened + * @filp: the struct file being set up + * + * When opening a verity file, deny the open if it is for writing. Otherwise, + * set up the inode's ->i_verity_info if not already done. + * + * When combined with fscrypt, this must be called after fscrypt_file_open(). + * Otherwise, we won't have the key set up to decrypt the verity metadata. + * + * Return: 0 on success, -errno on failure + */ +static inline int fsverity_file_open(struct inode *inode, struct file *filp) +{ + if (IS_VERITY(inode)) + return __fsverity_file_open(inode, filp); + return 0; +} + +/** + * fsverity_prepare_setattr() - prepare to change a verity inode's attributes + * @dentry: dentry through which the inode is being changed + * @attr: attributes to change + * + * Verity files are immutable, so deny truncates. This isn't covered by the + * open-time check because sys_truncate() takes a path, not a file descriptor. + * + * Return: 0 on success, -errno on failure + */ +static inline int fsverity_prepare_setattr(struct dentry *dentry, + struct iattr *attr) +{ + if (IS_VERITY(d_inode(dentry))) + return __fsverity_prepare_setattr(dentry, attr); + return 0; +} + #endif /* _LINUX_FSVERITY_H */ diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index e098f38422af..a3028e400a9c 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -152,7 +152,10 @@ static inline void totalhigh_pages_add(long count) static inline bool is_kmap_addr(const void *x) { unsigned long addr = (unsigned long)x; - return addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP); + + return (addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP)) || + (addr >= __fix_to_virt(FIX_KMAP_END) && + addr < __fix_to_virt(FIX_KMAP_BEGIN)); } #else /* CONFIG_HIGHMEM */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index db194e2ba69f..9ab9d3105d5c 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -743,7 +743,10 @@ static inline struct hstate *hstate_sizelog(int page_size_log) if (!page_size_log) return &default_hstate; - return size_to_hstate(1UL << page_size_log); + if (page_size_log < BITS_PER_LONG) + return size_to_hstate(1UL << page_size_log); + + return NULL; } static inline struct hstate *hstate_vma(struct vm_area_struct *vma) diff --git a/include/linux/ima.h b/include/linux/ima.h index 5a0b2a285a18..172b113a9864 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -18,7 +18,7 @@ struct linux_binprm; extern enum hash_algo ima_get_current_hash_algo(void); extern int ima_bprm_check(struct linux_binprm *bprm); extern int ima_file_check(struct file *file, int mask); -extern void ima_post_create_tmpfile(struct user_namespace *mnt_userns, +extern void ima_post_create_tmpfile(struct mnt_idmap *idmap, struct inode *inode); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); @@ -30,7 +30,7 @@ extern int ima_read_file(struct file *file, enum kernel_read_file_id id, bool contents); extern int ima_post_read_file(struct file *file, void *buf, loff_t size, enum kernel_read_file_id id); -extern void ima_post_path_mknod(struct user_namespace *mnt_userns, +extern void ima_post_path_mknod(struct mnt_idmap *idmap, struct dentry *dentry); extern int ima_file_hash(struct file *file, char *buf, size_t buf_size); extern int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size); @@ -66,7 +66,7 @@ static inline int ima_file_check(struct file *file, int mask) return 0; } -static inline void ima_post_create_tmpfile(struct user_namespace *mnt_userns, +static inline void ima_post_create_tmpfile(struct mnt_idmap *idmap, struct inode *inode) { } @@ -111,7 +111,7 @@ static inline int ima_post_read_file(struct file *file, void *buf, loff_t size, return 0; } -static inline void ima_post_path_mknod(struct user_namespace *mnt_userns, +static inline void ima_post_path_mknod(struct mnt_idmap *idmap, struct dentry *dentry) { return; @@ -183,18 +183,18 @@ static inline void ima_post_key_create_or_update(struct key *keyring, #ifdef CONFIG_IMA_APPRAISE extern bool is_ima_appraise_enabled(void); -extern void ima_inode_post_setattr(struct user_namespace *mnt_userns, +extern void ima_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry); extern int ima_inode_setxattr(struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len); -extern int ima_inode_set_acl(struct user_namespace *mnt_userns, +extern int ima_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl); -static inline int ima_inode_remove_acl(struct user_namespace *mnt_userns, +static inline int ima_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { - return ima_inode_set_acl(mnt_userns, dentry, acl_name, NULL); + return ima_inode_set_acl(idmap, dentry, acl_name, NULL); } extern int ima_inode_removexattr(struct dentry *dentry, const char *xattr_name); #else @@ -203,7 +203,7 @@ static inline bool is_ima_appraise_enabled(void) return 0; } -static inline void ima_inode_post_setattr(struct user_namespace *mnt_userns, +static inline void ima_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry) { return; @@ -217,7 +217,7 @@ static inline int ima_inode_setxattr(struct dentry *dentry, return 0; } -static inline int ima_inode_set_acl(struct user_namespace *mnt_userns, +static inline int ima_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { @@ -231,7 +231,7 @@ static inline int ima_inode_removexattr(struct dentry *dentry, return 0; } -static inline int ima_inode_remove_acl(struct user_namespace *mnt_userns, +static inline int ima_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { diff --git a/include/linux/iversion.h b/include/linux/iversion.h index e27bd4f55d84..f174ff1b59ee 100644 --- a/include/linux/iversion.h +++ b/include/linux/iversion.h @@ -9,8 +9,26 @@ * --------------------------- * The change attribute (i_version) is mandated by NFSv4 and is mostly for * knfsd, but is also used for other purposes (e.g. IMA). The i_version must - * appear different to observers if there was a change to the inode's data or - * metadata since it was last queried. + * appear larger to observers if there was an explicit change to the inode's + * data or metadata since it was last queried. + * + * An explicit change is one that would ordinarily result in a change to the + * inode status change time (aka ctime). i_version must appear to change, even + * if the ctime does not (since the whole point is to avoid missing updates due + * to timestamp granularity). If POSIX or other relevant spec mandates that the + * ctime must change due to an operation, then the i_version counter must be + * incremented as well. + * + * Making the i_version update completely atomic with the operation itself would + * be prohibitively expensive. Traditionally the kernel has updated the times on + * directories after an operation that changes its contents. For regular files, + * the ctime is usually updated before the data is copied into the cache for a + * write. This means that there is a window of time when an observer can + * associate a new timestamp with old file contents. Since the purpose of the + * i_version is to allow for better cache coherency, the i_version must always + * be updated after the results of the operation are visible. Updating it before + * and after a change is also permitted. (Note that no filesystems currently do + * this. Fixing that is a work-in-progress). * * Observers see the i_version as a 64-bit number that never decreases. If it * remains the same since it was last checked, then nothing has changed in the @@ -234,42 +252,6 @@ inode_peek_iversion(const struct inode *inode) return inode_peek_iversion_raw(inode) >> I_VERSION_QUERIED_SHIFT; } -/** - * inode_query_iversion - read i_version for later use - * @inode: inode from which i_version should be read - * - * Read the inode i_version counter. This should be used by callers that wish - * to store the returned i_version for later comparison. This will guarantee - * that a later query of the i_version will result in a different value if - * anything has changed. - * - * In this implementation, we fetch the current value, set the QUERIED flag and - * then try to swap it into place with a cmpxchg, if it wasn't already set. If - * that fails, we try again with the newly fetched value from the cmpxchg. - */ -static inline u64 -inode_query_iversion(struct inode *inode) -{ - u64 cur, new; - - cur = inode_peek_iversion_raw(inode); - do { - /* If flag is already set, then no need to swap */ - if (cur & I_VERSION_QUERIED) { - /* - * This barrier (and the implicit barrier in the - * cmpxchg below) pairs with the barrier in - * inode_maybe_inc_iversion(). - */ - smp_mb(); - break; - } - - new = cur | I_VERSION_QUERIED; - } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); - return cur >> I_VERSION_QUERIED_SHIFT; -} - /* * For filesystems without any sort of change attribute, the best we can * do is fake one up from the ctime: @@ -283,6 +265,8 @@ static inline u64 time_to_chattr(struct timespec64 *t) return chattr; } +u64 inode_query_iversion(struct inode *inode); + /** * inode_eq_iversion_raw - check whether the raw i_version counter has changed * @inode: inode to check diff --git a/include/linux/key.h b/include/linux/key.h index d27477faf00d..8dc7f7c3088b 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -386,6 +386,14 @@ extern int wait_for_key_construction(struct key *key, bool intr); extern int key_validate(const struct key *key); +extern key_ref_t key_create(key_ref_t keyring, + const char *type, + const char *description, + const void *payload, + size_t plen, + key_perm_t perm, + unsigned long flags); + extern key_ref_t key_create_or_update(key_ref_t keyring, const char *type, const char *description, diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 70ce419e2709..2b7f067af3c4 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -312,7 +312,7 @@ static inline struct file *nlmsvc_file_file(struct nlm_file *file) static inline struct inode *nlmsvc_file_inode(struct nlm_file *file) { - return locks_inode(nlmsvc_file_file(file)); + return file_inode(nlmsvc_file_file(file)); } static inline int __nlm_privileged_request4(const struct sockaddr *sap) @@ -372,7 +372,7 @@ static inline int nlm_privileged_requester(const struct svc_rqst *rqstp) static inline int nlm_compare_locks(const struct file_lock *fl1, const struct file_lock *fl2) { - return locks_inode(fl1->fl_file) == locks_inode(fl2->fl_file) + return file_inode(fl1->fl_file) == file_inode(fl2->fl_file) && fl1->fl_pid == fl2->fl_pid && fl1->fl_owner == fl2->fl_owner && fl1->fl_start == fl2->fl_start diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index 67e4a2c5500b..b60fbcd8cdfa 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -11,6 +11,7 @@ #define LOCKD_XDR_H #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/nfs.h> #include <linux/sunrpc/xdr.h> diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index ed6cb2ac55fa..094b76dc7164 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -136,25 +136,25 @@ LSM_HOOK(int, 0, inode_follow_link, struct dentry *dentry, struct inode *inode, LSM_HOOK(int, 0, inode_permission, struct inode *inode, int mask) LSM_HOOK(int, 0, inode_setattr, struct dentry *dentry, struct iattr *attr) LSM_HOOK(int, 0, inode_getattr, const struct path *path) -LSM_HOOK(int, 0, inode_setxattr, struct user_namespace *mnt_userns, +LSM_HOOK(int, 0, inode_setxattr, struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) LSM_HOOK(void, LSM_RET_VOID, inode_post_setxattr, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) LSM_HOOK(int, 0, inode_getxattr, struct dentry *dentry, const char *name) LSM_HOOK(int, 0, inode_listxattr, struct dentry *dentry) -LSM_HOOK(int, 0, inode_removexattr, struct user_namespace *mnt_userns, +LSM_HOOK(int, 0, inode_removexattr, struct mnt_idmap *idmap, struct dentry *dentry, const char *name) -LSM_HOOK(int, 0, inode_set_acl, struct user_namespace *mnt_userns, +LSM_HOOK(int, 0, inode_set_acl, struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) -LSM_HOOK(int, 0, inode_get_acl, struct user_namespace *mnt_userns, +LSM_HOOK(int, 0, inode_get_acl, struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) -LSM_HOOK(int, 0, inode_remove_acl, struct user_namespace *mnt_userns, +LSM_HOOK(int, 0, inode_remove_acl, struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) LSM_HOOK(int, 0, inode_need_killpriv, struct dentry *dentry) -LSM_HOOK(int, 0, inode_killpriv, struct user_namespace *mnt_userns, +LSM_HOOK(int, 0, inode_killpriv, struct mnt_idmap *idmap, struct dentry *dentry) -LSM_HOOK(int, -EOPNOTSUPP, inode_getsecurity, struct user_namespace *mnt_userns, +LSM_HOOK(int, -EOPNOTSUPP, inode_getsecurity, struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) LSM_HOOK(int, -EOPNOTSUPP, inode_setsecurity, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 0a5ba81f7367..6e156d2acffc 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -475,7 +475,7 @@ * @inode_killpriv: * The setuid bit is being removed. Remove similar security labels. * Called with the dentry->d_inode->i_mutex held. - * @mnt_userns: user namespace of the mount. + * @idmap: idmap of the mount. * @dentry is the dentry being changed. * Return 0 on success. If error is returned, then the operation * causing setuid bit removal is failed. diff --git a/include/linux/mm.h b/include/linux/mm.h index 8f857163ac89..bd3197748562 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -137,7 +137,7 @@ extern int mmap_rnd_compat_bits __read_mostly; * define their own version of this macro in <asm/pgtable.h> */ #if BITS_PER_LONG == 64 -/* This function must be updated when the size of struct page grows above 80 +/* This function must be updated when the size of struct page grows above 96 * or reduces below 56. The idea that compiler optimizes out switch() * statement, and only leaves move/store instructions. Also the compiler can * combine write statements if they are both assignments and can be reordered, @@ -148,12 +148,18 @@ static inline void __mm_zero_struct_page(struct page *page) { unsigned long *_pp = (void *)page; - /* Check that struct page is either 56, 64, 72, or 80 bytes */ + /* Check that struct page is either 56, 64, 72, 80, 88 or 96 bytes */ BUILD_BUG_ON(sizeof(struct page) & 7); BUILD_BUG_ON(sizeof(struct page) < 56); - BUILD_BUG_ON(sizeof(struct page) > 80); + BUILD_BUG_ON(sizeof(struct page) > 96); switch (sizeof(struct page)) { + case 96: + _pp[11] = 0; + fallthrough; + case 88: + _pp[10] = 0; + fallthrough; case 80: _pp[9] = 0; fallthrough; @@ -2095,8 +2101,6 @@ int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, struct task_struct *task, bool bypass_rlim); struct kvec; -int get_kernel_pages(const struct kvec *iov, int nr_pages, int write, - struct page **pages); struct page *get_dump_page(unsigned long addr); bool folio_mark_dirty(struct folio *folio); diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h index 0ccca33a7a6d..057c89867aa2 100644 --- a/include/linux/mnt_idmapping.h +++ b/include/linux/mnt_idmapping.h @@ -113,167 +113,23 @@ static inline bool vfsgid_eq_kgid(vfsgid_t vfsgid, kgid_t kgid) #define AS_KUIDT(val) (kuid_t){ __vfsuid_val(val) } #define AS_KGIDT(val) (kgid_t){ __vfsgid_val(val) } -#ifdef CONFIG_MULTIUSER -/** - * vfsgid_in_group_p() - check whether a vfsuid matches the caller's groups - * @vfsgid: the mnt gid to match - * - * This function can be used to determine whether @vfsuid matches any of the - * caller's groups. - * - * Return: 1 if vfsuid matches caller's groups, 0 if not. - */ -static inline int vfsgid_in_group_p(vfsgid_t vfsgid) -{ - return in_group_p(AS_KGIDT(vfsgid)); -} -#else -static inline int vfsgid_in_group_p(vfsgid_t vfsgid) -{ - return 1; -} -#endif +int vfsgid_in_group_p(vfsgid_t vfsgid); -/** - * initial_idmapping - check whether this is the initial mapping - * @ns: idmapping to check - * - * Check whether this is the initial mapping, mapping 0 to 0, 1 to 1, - * [...], 1000 to 1000 [...]. - * - * Return: true if this is the initial mapping, false if not. - */ -static inline bool initial_idmapping(const struct user_namespace *ns) -{ - return ns == &init_user_ns; -} +vfsuid_t make_vfsuid(struct mnt_idmap *idmap, + struct user_namespace *fs_userns, kuid_t kuid); -/** - * no_idmapping - check whether we can skip remapping a kuid/gid - * @mnt_userns: the mount's idmapping - * @fs_userns: the filesystem's idmapping - * - * This function can be used to check whether a remapping between two - * idmappings is required. - * An idmapped mount is a mount that has an idmapping attached to it that - * is different from the filsystem's idmapping and the initial idmapping. - * If the initial mapping is used or the idmapping of the mount and the - * filesystem are identical no remapping is required. - * - * Return: true if remapping can be skipped, false if not. - */ -static inline bool no_idmapping(const struct user_namespace *mnt_userns, - const struct user_namespace *fs_userns) -{ - return initial_idmapping(mnt_userns) || mnt_userns == fs_userns; -} +vfsgid_t make_vfsgid(struct mnt_idmap *idmap, + struct user_namespace *fs_userns, kgid_t kgid); -/** - * make_vfsuid - map a filesystem kuid into a mnt_userns - * @mnt_userns: the mount's idmapping - * @fs_userns: the filesystem's idmapping - * @kuid : kuid to be mapped - * - * Take a @kuid and remap it from @fs_userns into @mnt_userns. Use this - * function when preparing a @kuid to be reported to userspace. - * - * If no_idmapping() determines that this is not an idmapped mount we can - * simply return @kuid unchanged. - * If initial_idmapping() tells us that the filesystem is not mounted with an - * idmapping we know the value of @kuid won't change when calling - * from_kuid() so we can simply retrieve the value via __kuid_val() - * directly. - * - * Return: @kuid mapped according to @mnt_userns. - * If @kuid has no mapping in either @mnt_userns or @fs_userns INVALID_UID is - * returned. - */ +kuid_t from_vfsuid(struct mnt_idmap *idmap, + struct user_namespace *fs_userns, vfsuid_t vfsuid); -static inline vfsuid_t make_vfsuid(struct user_namespace *mnt_userns, - struct user_namespace *fs_userns, - kuid_t kuid) -{ - uid_t uid; - - if (no_idmapping(mnt_userns, fs_userns)) - return VFSUIDT_INIT(kuid); - if (initial_idmapping(fs_userns)) - uid = __kuid_val(kuid); - else - uid = from_kuid(fs_userns, kuid); - if (uid == (uid_t)-1) - return INVALID_VFSUID; - return VFSUIDT_INIT(make_kuid(mnt_userns, uid)); -} - -/** - * make_vfsgid - map a filesystem kgid into a mnt_userns - * @mnt_userns: the mount's idmapping - * @fs_userns: the filesystem's idmapping - * @kgid : kgid to be mapped - * - * Take a @kgid and remap it from @fs_userns into @mnt_userns. Use this - * function when preparing a @kgid to be reported to userspace. - * - * If no_idmapping() determines that this is not an idmapped mount we can - * simply return @kgid unchanged. - * If initial_idmapping() tells us that the filesystem is not mounted with an - * idmapping we know the value of @kgid won't change when calling - * from_kgid() so we can simply retrieve the value via __kgid_val() - * directly. - * - * Return: @kgid mapped according to @mnt_userns. - * If @kgid has no mapping in either @mnt_userns or @fs_userns INVALID_GID is - * returned. - */ - -static inline vfsgid_t make_vfsgid(struct user_namespace *mnt_userns, - struct user_namespace *fs_userns, - kgid_t kgid) -{ - gid_t gid; - - if (no_idmapping(mnt_userns, fs_userns)) - return VFSGIDT_INIT(kgid); - if (initial_idmapping(fs_userns)) - gid = __kgid_val(kgid); - else - gid = from_kgid(fs_userns, kgid); - if (gid == (gid_t)-1) - return INVALID_VFSGID; - return VFSGIDT_INIT(make_kgid(mnt_userns, gid)); -} - -/** - * from_vfsuid - map a vfsuid into the filesystem idmapping - * @mnt_userns: the mount's idmapping - * @fs_userns: the filesystem's idmapping - * @vfsuid : vfsuid to be mapped - * - * Map @vfsuid into the filesystem idmapping. This function has to be used in - * order to e.g. write @vfsuid to inode->i_uid. - * - * Return: @vfsuid mapped into the filesystem idmapping - */ -static inline kuid_t from_vfsuid(struct user_namespace *mnt_userns, - struct user_namespace *fs_userns, - vfsuid_t vfsuid) -{ - uid_t uid; - - if (no_idmapping(mnt_userns, fs_userns)) - return AS_KUIDT(vfsuid); - uid = from_kuid(mnt_userns, AS_KUIDT(vfsuid)); - if (uid == (uid_t)-1) - return INVALID_UID; - if (initial_idmapping(fs_userns)) - return KUIDT_INIT(uid); - return make_kuid(fs_userns, uid); -} +kgid_t from_vfsgid(struct mnt_idmap *idmap, + struct user_namespace *fs_userns, vfsgid_t vfsgid); /** * vfsuid_has_fsmapping - check whether a vfsuid maps into the filesystem - * @mnt_userns: the mount's idmapping + * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @vfsuid: vfsuid to be mapped * @@ -283,11 +139,11 @@ static inline kuid_t from_vfsuid(struct user_namespace *mnt_userns, * * Return: true if @vfsuid has a mapping in the filesystem, false if not. */ -static inline bool vfsuid_has_fsmapping(struct user_namespace *mnt_userns, +static inline bool vfsuid_has_fsmapping(struct mnt_idmap *idmap, struct user_namespace *fs_userns, vfsuid_t vfsuid) { - return uid_valid(from_vfsuid(mnt_userns, fs_userns, vfsuid)); + return uid_valid(from_vfsuid(idmap, fs_userns, vfsuid)); } static inline bool vfsuid_has_mapping(struct user_namespace *userns, @@ -310,35 +166,8 @@ static inline kuid_t vfsuid_into_kuid(vfsuid_t vfsuid) } /** - * from_vfsgid - map a vfsgid into the filesystem idmapping - * @mnt_userns: the mount's idmapping - * @fs_userns: the filesystem's idmapping - * @vfsgid : vfsgid to be mapped - * - * Map @vfsgid into the filesystem idmapping. This function has to be used in - * order to e.g. write @vfsgid to inode->i_gid. - * - * Return: @vfsgid mapped into the filesystem idmapping - */ -static inline kgid_t from_vfsgid(struct user_namespace *mnt_userns, - struct user_namespace *fs_userns, - vfsgid_t vfsgid) -{ - gid_t gid; - - if (no_idmapping(mnt_userns, fs_userns)) - return AS_KGIDT(vfsgid); - gid = from_kgid(mnt_userns, AS_KGIDT(vfsgid)); - if (gid == (gid_t)-1) - return INVALID_GID; - if (initial_idmapping(fs_userns)) - return KGIDT_INIT(gid); - return make_kgid(fs_userns, gid); -} - -/** * vfsgid_has_fsmapping - check whether a vfsgid maps into the filesystem - * @mnt_userns: the mount's idmapping + * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @vfsgid: vfsgid to be mapped * @@ -348,11 +177,11 @@ static inline kgid_t from_vfsgid(struct user_namespace *mnt_userns, * * Return: true if @vfsgid has a mapping in the filesystem, false if not. */ -static inline bool vfsgid_has_fsmapping(struct user_namespace *mnt_userns, +static inline bool vfsgid_has_fsmapping(struct mnt_idmap *idmap, struct user_namespace *fs_userns, vfsgid_t vfsgid) { - return gid_valid(from_vfsgid(mnt_userns, fs_userns, vfsgid)); + return gid_valid(from_vfsgid(idmap, fs_userns, vfsgid)); } static inline bool vfsgid_has_mapping(struct user_namespace *userns, @@ -375,8 +204,8 @@ static inline kgid_t vfsgid_into_kgid(vfsgid_t vfsgid) } /** - * mapped_fsuid - return caller's fsuid mapped up into a mnt_userns - * @mnt_userns: the mount's idmapping + * mapped_fsuid - return caller's fsuid mapped according to an idmapping + * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * * Use this helper to initialize a new vfs or filesystem object based on @@ -385,18 +214,17 @@ static inline kgid_t vfsgid_into_kgid(vfsgid_t vfsgid) * O_CREAT. Other examples include the allocation of quotas for a specific * user. * - * Return: the caller's current fsuid mapped up according to @mnt_userns. + * Return: the caller's current fsuid mapped up according to @idmap. */ -static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns, +static inline kuid_t mapped_fsuid(struct mnt_idmap *idmap, struct user_namespace *fs_userns) { - return from_vfsuid(mnt_userns, fs_userns, - VFSUIDT_INIT(current_fsuid())); + return from_vfsuid(idmap, fs_userns, VFSUIDT_INIT(current_fsuid())); } /** - * mapped_fsgid - return caller's fsgid mapped up into a mnt_userns - * @mnt_userns: the mount's idmapping + * mapped_fsgid - return caller's fsgid mapped according to an idmapping + * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * * Use this helper to initialize a new vfs or filesystem object based on @@ -405,13 +233,15 @@ static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns, * O_CREAT. Other examples include the allocation of quotas for a specific * user. * - * Return: the caller's current fsgid mapped up according to @mnt_userns. + * Return: the caller's current fsgid mapped up according to @idmap. */ -static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns, +static inline kgid_t mapped_fsgid(struct mnt_idmap *idmap, struct user_namespace *fs_userns) { - return from_vfsgid(mnt_userns, fs_userns, - VFSGIDT_INIT(current_fsgid())); + return from_vfsgid(idmap, fs_userns, VFSGIDT_INIT(current_fsgid())); } +bool check_fsmapping(const struct mnt_idmap *idmap, + const struct super_block *sb); + #endif /* _LINUX_MNT_IDMAPPING_H */ diff --git a/include/linux/mount.h b/include/linux/mount.h index 62475996fac6..52f452b2259a 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -74,8 +74,6 @@ struct vfsmount { struct mnt_idmap *mnt_idmap; } __randomize_layout; -struct user_namespace *mnt_user_ns(const struct vfsmount *mnt); -struct user_namespace *mnt_idmap_owner(const struct mnt_idmap *idmap); static inline struct mnt_idmap *mnt_idmap(const struct vfsmount *mnt) { /* Pairs with smp_store_release() in do_idmap_mount(). */ diff --git a/include/linux/namei.h b/include/linux/namei.h index 00fee52df842..0d4531fd46e7 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -68,11 +68,11 @@ extern struct dentry *try_lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int); extern struct dentry *lookup_positive_unlocked(const char *, struct dentry *, int); -struct dentry *lookup_one(struct user_namespace *, const char *, struct dentry *, int); -struct dentry *lookup_one_unlocked(struct user_namespace *mnt_userns, +struct dentry *lookup_one(struct mnt_idmap *, const char *, struct dentry *, int); +struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len); -struct dentry *lookup_one_positive_unlocked(struct user_namespace *mnt_userns, +struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index aad12a179e54..e6e02184c25a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2839,8 +2839,6 @@ int unregister_netdevice_notifier(struct notifier_block *nb); int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb); int unregister_netdevice_notifier_net(struct net *net, struct notifier_block *nb); -void move_netdevice_notifier_net(struct net *src_net, struct net *dst_net, - struct notifier_block *nb); int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index d92fdfd2444c..d6c119e31d7a 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -392,11 +392,11 @@ extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr); -extern int nfs_getattr(struct user_namespace *, const struct path *, +extern int nfs_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *, const struct cred *); extern void nfs_access_set_mask(struct nfs_access_entry *, u32); -extern int nfs_permission(struct user_namespace *, struct inode *, int); +extern int nfs_permission(struct mnt_idmap *, struct inode *, int); extern int nfs_open(struct inode *, struct file *); extern int nfs_attribute_cache_expired(struct inode *inode); extern int nfs_revalidate_inode(struct inode *inode, unsigned long flags); @@ -405,7 +405,7 @@ extern int nfs_clear_invalid_mapping(struct address_space *mapping); extern bool nfs_mapping_need_revalidate_inode(struct inode *inode); extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); extern int nfs_revalidate_mapping_rcu(struct inode *inode); -extern int nfs_setattr(struct user_namespace *, struct dentry *, struct iattr *); +extern int nfs_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *); extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr); extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx); diff --git a/include/linux/pci.h b/include/linux/pci.h index adffd65e84b4..254c8a4126a8 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1621,6 +1621,18 @@ pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, flags, NULL); } +static inline struct msi_map pci_msix_alloc_irq_at(struct pci_dev *dev, unsigned int index, + const struct irq_affinity_desc *affdesc) +{ + struct msi_map map = { .index = -ENOSYS, }; + + return map; +} + +static inline void pci_msix_free_irq(struct pci_dev *pdev, struct msi_map map) +{ +} + static inline void pci_free_irq_vectors(struct pci_dev *dev) { } diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index ef914a600087..525b5d64e394 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -100,7 +100,6 @@ struct arm_pmu { void (*stop)(struct arm_pmu *); void (*reset)(void *); int (*map_event)(struct perf_event *event); - bool (*filter)(struct pmu *pmu, int cpu); int num_events; bool secure_access; /* 32-bit ARM only */ #define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40 diff --git a/include/linux/poison.h b/include/linux/poison.h index 2d3249eb0e62..0e8a1f2ceb2f 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -84,4 +84,7 @@ /********** kernel/bpf/ **********/ #define BPF_PTR_POISON ((void *)(0xeB9FUL + POISON_POINTER_DELTA)) +/********** VFS **********/ +#define VFS_PTR_POISON ((void *)(0xF5 + POISON_POINTER_DELTA)) + #endif diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index ee608d22ecb9..21cc29b8a9e8 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -69,20 +69,20 @@ extern int __posix_acl_create(struct posix_acl **, gfp_t, umode_t *); extern int __posix_acl_chmod(struct posix_acl **, gfp_t, umode_t); extern struct posix_acl *get_posix_acl(struct inode *, int); -int set_posix_acl(struct user_namespace *, struct dentry *, int, +int set_posix_acl(struct mnt_idmap *, struct dentry *, int, struct posix_acl *); struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type); struct posix_acl *posix_acl_clone(const struct posix_acl *acl, gfp_t flags); #ifdef CONFIG_FS_POSIX_ACL -int posix_acl_chmod(struct user_namespace *, struct dentry *, umode_t); +int posix_acl_chmod(struct mnt_idmap *, struct dentry *, umode_t); extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **, struct posix_acl **); -int posix_acl_update_mode(struct user_namespace *, struct inode *, umode_t *, +int posix_acl_update_mode(struct mnt_idmap *, struct inode *, umode_t *, struct posix_acl **); -int simple_set_acl(struct user_namespace *, struct dentry *, +int simple_set_acl(struct mnt_idmap *, struct dentry *, struct posix_acl *, int); extern int simple_acl_create(struct inode *, struct inode *); @@ -91,7 +91,7 @@ void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl); void forget_cached_acl(struct inode *inode, int type); void forget_all_cached_acls(struct inode *inode); int posix_acl_valid(struct user_namespace *, const struct posix_acl *); -int posix_acl_permission(struct user_namespace *, struct inode *, +int posix_acl_permission(struct mnt_idmap *, struct inode *, const struct posix_acl *, int); static inline void cache_no_acl(struct inode *inode) @@ -100,14 +100,14 @@ static inline void cache_no_acl(struct inode *inode) inode->i_default_acl = NULL; } -int vfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int vfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl); -struct posix_acl *vfs_get_acl(struct user_namespace *mnt_userns, +struct posix_acl *vfs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name); -int vfs_remove_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name); #else -static inline int posix_acl_chmod(struct user_namespace *mnt_userns, +static inline int posix_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode) { return 0; @@ -134,21 +134,21 @@ static inline void forget_all_cached_acls(struct inode *inode) { } -static inline int vfs_set_acl(struct user_namespace *mnt_userns, +static inline int vfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, struct posix_acl *acl) { return -EOPNOTSUPP; } -static inline struct posix_acl *vfs_get_acl(struct user_namespace *mnt_userns, +static inline struct posix_acl *vfs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return ERR_PTR(-EOPNOTSUPP); } -static inline int vfs_remove_acl(struct user_namespace *mnt_userns, +static inline int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return -EOPNOTSUPP; diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 0d8625d71733..11a4becff3a9 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -20,12 +20,12 @@ static inline struct quota_info *sb_dqopt(struct super_block *sb) } /* i_mutex must being held */ -static inline bool is_quota_modification(struct user_namespace *mnt_userns, +static inline bool is_quota_modification(struct mnt_idmap *idmap, struct inode *inode, struct iattr *ia) { return ((ia->ia_valid & ATTR_SIZE) || - i_uid_needs_update(mnt_userns, ia, inode) || - i_gid_needs_update(mnt_userns, ia, inode)); + i_uid_needs_update(idmap, ia, inode) || + i_gid_needs_update(idmap, ia, inode)); } #if defined(CONFIG_QUOTA) @@ -116,7 +116,7 @@ int dquot_set_dqblk(struct super_block *sb, struct kqid id, struct qc_dqblk *di); int __dquot_transfer(struct inode *inode, struct dquot **transfer_to); -int dquot_transfer(struct user_namespace *mnt_userns, struct inode *inode, +int dquot_transfer(struct mnt_idmap *idmap, struct inode *inode, struct iattr *iattr); static inline struct mem_dqinfo *sb_dqinfo(struct super_block *sb, int type) @@ -236,7 +236,7 @@ static inline void dquot_free_inode(struct inode *inode) { } -static inline int dquot_transfer(struct user_namespace *mnt_userns, +static inline int dquot_transfer(struct mnt_idmap *idmap, struct inode *inode, struct iattr *iattr) { return 0; diff --git a/include/linux/security.h b/include/linux/security.h index 5b67f208f7de..5984d0d550b4 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -153,12 +153,11 @@ extern int cap_capset(struct cred *new, const struct cred *old, extern int cap_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file); int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); -int cap_inode_removexattr(struct user_namespace *mnt_userns, +int cap_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name); int cap_inode_need_killpriv(struct dentry *dentry); -int cap_inode_killpriv(struct user_namespace *mnt_userns, - struct dentry *dentry); -int cap_inode_getsecurity(struct user_namespace *mnt_userns, +int cap_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry); +int cap_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc); extern int cap_mmap_addr(unsigned long addr); @@ -356,29 +355,28 @@ int security_inode_readlink(struct dentry *dentry); int security_inode_follow_link(struct dentry *dentry, struct inode *inode, bool rcu); int security_inode_permission(struct inode *inode, int mask); -int security_inode_setattr(struct user_namespace *mnt_userns, +int security_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); int security_inode_getattr(const struct path *path); -int security_inode_setxattr(struct user_namespace *mnt_userns, +int security_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags); -int security_inode_set_acl(struct user_namespace *mnt_userns, +int security_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl); -int security_inode_get_acl(struct user_namespace *mnt_userns, +int security_inode_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name); -int security_inode_remove_acl(struct user_namespace *mnt_userns, +int security_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name); void security_inode_post_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); int security_inode_getxattr(struct dentry *dentry, const char *name); int security_inode_listxattr(struct dentry *dentry); -int security_inode_removexattr(struct user_namespace *mnt_userns, +int security_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name); int security_inode_need_killpriv(struct dentry *dentry); -int security_inode_killpriv(struct user_namespace *mnt_userns, - struct dentry *dentry); -int security_inode_getsecurity(struct user_namespace *mnt_userns, +int security_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry); +int security_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc); int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags); @@ -862,7 +860,7 @@ static inline int security_inode_permission(struct inode *inode, int mask) return 0; } -static inline int security_inode_setattr(struct user_namespace *mnt_userns, +static inline int security_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { @@ -874,14 +872,14 @@ static inline int security_inode_getattr(const struct path *path) return 0; } -static inline int security_inode_setxattr(struct user_namespace *mnt_userns, +static inline int security_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { return cap_inode_setxattr(dentry, name, value, size, flags); } -static inline int security_inode_set_acl(struct user_namespace *mnt_userns, +static inline int security_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) @@ -889,14 +887,14 @@ static inline int security_inode_set_acl(struct user_namespace *mnt_userns, return 0; } -static inline int security_inode_get_acl(struct user_namespace *mnt_userns, +static inline int security_inode_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return 0; } -static inline int security_inode_remove_acl(struct user_namespace *mnt_userns, +static inline int security_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { @@ -918,11 +916,11 @@ static inline int security_inode_listxattr(struct dentry *dentry) return 0; } -static inline int security_inode_removexattr(struct user_namespace *mnt_userns, +static inline int security_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { - return cap_inode_removexattr(mnt_userns, dentry, name); + return cap_inode_removexattr(idmap, dentry, name); } static inline int security_inode_need_killpriv(struct dentry *dentry) @@ -930,18 +928,18 @@ static inline int security_inode_need_killpriv(struct dentry *dentry) return cap_inode_need_killpriv(dentry); } -static inline int security_inode_killpriv(struct user_namespace *mnt_userns, +static inline int security_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry) { - return cap_inode_killpriv(mnt_userns, dentry); + return cap_inode_killpriv(idmap, dentry); } -static inline int security_inode_getsecurity(struct user_namespace *mnt_userns, +static inline int security_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) { - return cap_inode_getsecurity(mnt_userns, inode, name, buffer, alloc); + return cap_inode_getsecurity(idmap, inode, name, buffer, alloc); } static inline int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 71310efe2fab..7bde8e1c228a 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -107,7 +107,7 @@ extern void synchronize_shrinkers(void); #ifdef CONFIG_SHRINKER_DEBUG extern int shrinker_debugfs_add(struct shrinker *shrinker); -extern void shrinker_debugfs_remove(struct shrinker *shrinker); +extern struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker); extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...); #else /* CONFIG_SHRINKER_DEBUG */ @@ -115,8 +115,9 @@ static inline int shrinker_debugfs_add(struct shrinker *shrinker) { return 0; } -static inline void shrinker_debugfs_remove(struct shrinker *shrinker) +static inline struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) { + return NULL; } static inline __printf(2, 3) int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) diff --git a/include/linux/stat.h b/include/linux/stat.h index ff277ced50e9..52150570d37a 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -52,6 +52,15 @@ struct kstat { u64 mnt_id; u32 dio_mem_align; u32 dio_offset_align; + u64 change_cookie; }; +/* These definitions are internal to the kernel for now. Mainly used by nfsd. */ + +/* mask values */ +#define STATX_CHANGE_COOKIE 0x40000000U /* Want/got stx_change_attr */ + +/* file attribute values */ +#define STATX_ATTR_CHANGE_MONOTONIC 0x8000000000000000ULL /* version monotonically increases */ + #endif diff --git a/include/linux/tpm.h b/include/linux/tpm.h index dfeb25a0362d..4dc97b9f65fb 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -265,6 +265,7 @@ enum tpm2_startup_types { enum tpm2_cc_attrs { TPM2_CC_ATTR_CHANDLES = 25, TPM2_CC_ATTR_RHANDLE = 28, + TPM2_CC_ATTR_VENDOR = 29, }; #define TPM_VID_INTEL 0x8086 diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 2e7dd44926e4..6af72461397d 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -42,7 +42,7 @@ struct xattr_handler { struct inode *inode, const char *name, void *buffer, size_t size); int (*set)(const struct xattr_handler *, - struct user_namespace *mnt_userns, struct dentry *dentry, + struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *buffer, size_t size, int flags); }; @@ -56,25 +56,25 @@ struct xattr { }; ssize_t __vfs_getxattr(struct dentry *, struct inode *, const char *, void *, size_t); -ssize_t vfs_getxattr(struct user_namespace *, struct dentry *, const char *, +ssize_t vfs_getxattr(struct mnt_idmap *, struct dentry *, const char *, void *, size_t); ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size); -int __vfs_setxattr(struct user_namespace *, struct dentry *, struct inode *, +int __vfs_setxattr(struct mnt_idmap *, struct dentry *, struct inode *, const char *, const void *, size_t, int); -int __vfs_setxattr_noperm(struct user_namespace *, struct dentry *, +int __vfs_setxattr_noperm(struct mnt_idmap *, struct dentry *, const char *, const void *, size_t, int); -int __vfs_setxattr_locked(struct user_namespace *, struct dentry *, +int __vfs_setxattr_locked(struct mnt_idmap *, struct dentry *, const char *, const void *, size_t, int, struct inode **); -int vfs_setxattr(struct user_namespace *, struct dentry *, const char *, +int vfs_setxattr(struct mnt_idmap *, struct dentry *, const char *, const void *, size_t, int); -int __vfs_removexattr(struct user_namespace *, struct dentry *, const char *); -int __vfs_removexattr_locked(struct user_namespace *, struct dentry *, +int __vfs_removexattr(struct mnt_idmap *, struct dentry *, const char *); +int __vfs_removexattr_locked(struct mnt_idmap *, struct dentry *, const char *, struct inode **); -int vfs_removexattr(struct user_namespace *, struct dentry *, const char *); +int vfs_removexattr(struct mnt_idmap *, struct dentry *, const char *); ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size); -int vfs_getxattr_alloc(struct user_namespace *mnt_userns, +int vfs_getxattr_alloc(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, char **xattr_value, size_t size, gfp_t flags); diff --git a/include/net/sock.h b/include/net/sock.h index dcd72e6285b2..556209727633 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2434,6 +2434,19 @@ static inline __must_check bool skb_set_owner_sk_safe(struct sk_buff *skb, struc return false; } +static inline struct sk_buff *skb_clone_and_charge_r(struct sk_buff *skb, struct sock *sk) +{ + skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC)); + if (skb) { + if (sk_rmem_schedule(sk, skb, skb->truesize)) { + skb_set_owner_r(skb, sk); + return skb; + } + __kfree_skb(skb); + } + return NULL; +} + static inline void skb_prepare_for_gro(struct sk_buff *skb) { if (skb->destructor != sock_wfree) { diff --git a/include/trace/events/erofs.h b/include/trace/events/erofs.h index 4f4c44ea3a65..cf4a0d28b178 100644 --- a/include/trace/events/erofs.h +++ b/include/trace/events/erofs.h @@ -19,12 +19,17 @@ struct erofs_map_blocks; { 1, "DIR" }) #define show_map_flags(flags) __print_flags(flags, "|", \ - { EROFS_GET_BLOCKS_RAW, "RAW" }) + { EROFS_GET_BLOCKS_FIEMAP, "FIEMAP" }, \ + { EROFS_GET_BLOCKS_READMORE, "READMORE" }, \ + { EROFS_GET_BLOCKS_FINDTAIL, "FINDTAIL" }) #define show_mflags(flags) __print_flags(flags, "", \ - { EROFS_MAP_MAPPED, "M" }, \ - { EROFS_MAP_META, "I" }, \ - { EROFS_MAP_ENCODED, "E" }) + { EROFS_MAP_MAPPED, "M" }, \ + { EROFS_MAP_META, "I" }, \ + { EROFS_MAP_ENCODED, "E" }, \ + { EROFS_MAP_FULL_MAPPED, "F" }, \ + { EROFS_MAP_FRAGMENT, "R" }, \ + { EROFS_MAP_PARTIAL_REF, "P" }) TRACE_EVENT(erofs_lookup, @@ -66,8 +71,8 @@ TRACE_EVENT(erofs_fill_inode, TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->nid = EROFS_I(inode)->nid; - __entry->blkaddr = erofs_blknr(iloc(EROFS_I_SB(inode), __entry->nid)); - __entry->ofs = erofs_blkoff(iloc(EROFS_I_SB(inode), __entry->nid)); + __entry->blkaddr = erofs_blknr(erofs_iloc(inode)); + __entry->ofs = erofs_blkoff(erofs_iloc(inode)); ), TP_printk("dev = (%d,%d), nid = %llu, blkaddr %u ofs %u", diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 436258214bb0..cd14c94e9a1e 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -188,15 +188,43 @@ struct fanotify_event_info_error { __u32 error_count; }; +/* + * User space may need to record additional information about its decision. + * The extra information type records what kind of information is included. + * The default is none. We also define an extra information buffer whose + * size is determined by the extra information type. + * + * If the information type is Audit Rule, then the information following + * is the rule number that triggered the user space decision that + * requires auditing. + */ + +#define FAN_RESPONSE_INFO_NONE 0 +#define FAN_RESPONSE_INFO_AUDIT_RULE 1 + struct fanotify_response { __s32 fd; __u32 response; }; +struct fanotify_response_info_header { + __u8 type; + __u8 pad; + __u16 len; +}; + +struct fanotify_response_info_audit_rule { + struct fanotify_response_info_header hdr; + __u32 rule_number; + __u32 subj_trust; + __u32 obj_trust; +}; + /* Legit userspace responses to a _PERM event */ #define FAN_ALLOW 0x01 #define FAN_DENY 0x02 -#define FAN_AUDIT 0x10 /* Bit mask to create audit record for result */ +#define FAN_AUDIT 0x10 /* Bitmask to create audit record for result */ +#define FAN_INFO 0x20 /* Bitmask to indicate additional information */ /* No fd set in event */ #define FAN_NOFD -1 |