locks: add a dedicated spinlock to protect i_flctx lists

[mirror_ubuntu-jammy-kernel.git] / include / linux / fs.h

diff --git a/include/linux/fs.h b/include/linux/fs.h
index bb29b02d9bb6646c5d96c8d4d5c084a83f7efefe..32eafa9b5c9f73f5b8efd0d75d53e61b8cd9ed80 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -18,6 +18,7 @@
 #include <linux/pid.h>
 #include <linux/bug.h>
 #include <linux/mutex.h>
+#include <linux/rwsem.h>
 #include <linux/capability.h>
 #include <linux/semaphore.h>
 #include <linux/fiemap.h>
@@ -134,7 +135,7 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define FMODE_CAN_WRITE         ((__force fmode_t)0x40000)
 
 /* File was opened by fanotify and shouldn't generate fanotify events */
-#define FMODE_NONOTIFY         ((__force fmode_t)0x1000000)
+#define FMODE_NONOTIFY         ((__force fmode_t)0x4000000)
 
 /*
  * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
@@ -401,7 +402,7 @@ struct address_space {
        atomic_t                i_mmap_writable;/* count VM_SHARED mappings */
        struct rb_root          i_mmap;         /* tree of private and shared mappings */
        struct list_head        i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
-       struct mutex            i_mmap_mutex;   /* protect tree, count, list */
+       struct rw_semaphore     i_mmap_rwsem;   /* protect tree, count, list */
        /* Protected by tree_lock together with the radix tree */
        unsigned long           nrpages;        /* number of total pages */
        unsigned long           nrshadows;      /* number of shadow entries */
@@ -467,6 +468,26 @@ struct block_device {
 
 int mapping_tagged(struct address_space *mapping, int tag);
 
+static inline void i_mmap_lock_write(struct address_space *mapping)
+{
+       down_write(&mapping->i_mmap_rwsem);
+}
+
+static inline void i_mmap_unlock_write(struct address_space *mapping)
+{
+       up_write(&mapping->i_mmap_rwsem);
+}
+
+static inline void i_mmap_lock_read(struct address_space *mapping)
+{
+       down_read(&mapping->i_mmap_rwsem);
+}
+
+static inline void i_mmap_unlock_read(struct address_space *mapping)
+{
+       up_read(&mapping->i_mmap_rwsem);
+}
+
 /*
  * Might pages of this file be mapped into userspace?
  */
@@ -604,7 +625,7 @@ struct inode {
        atomic_t                i_readcount; /* struct files open RO */
 #endif
        const struct file_operations    *i_fop; /* former ->i_op->default_file_ops */
-       struct file_lock        *i_flock;
+       struct file_lock_context        *i_flctx;
        struct address_space    i_data;
        struct list_head        i_devices;
        union {
@@ -864,6 +885,8 @@ static inline struct file *get_file(struct file *f)
 /* 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 *);
@@ -913,6 +936,7 @@ int locks_in_grace(struct net *);
  */
 struct file_lock {
        struct file_lock *fl_next;      /* singly linked list for this inode  */
+       struct list_head fl_list;       /* link into file_lock_context */
        struct hlist_node fl_link;      /* node in global lists */
        struct list_head fl_block;      /* circular list of blocked processes */
        fl_owner_t fl_owner;
@@ -943,6 +967,13 @@ struct file_lock {
        } fl_u;
 };
 
+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 INT_LIMIT(x)   (~((x)1 << (sizeof(x)*8 - 1)))
@@ -969,6 +1000,7 @@ 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 file_lock_context *ctx);
 void locks_free_lock(struct file_lock *fl);
 extern void locks_init_lock(struct file_lock *);
 extern struct file_lock * locks_alloc_lock(void);
@@ -1026,6 +1058,11 @@ static inline int fcntl_getlease(struct file *filp)
        return F_UNLCK;
 }
 
+static inline void
+locks_free_lock_context(struct file_lock_context *ctx)
+{
+}
+
 static inline void locks_init_lock(struct file_lock *fl)
 {
        return;
@@ -1497,6 +1534,7 @@ struct file_operations {
        long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
        long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
        int (*mmap) (struct file *, struct vm_area_struct *);
+       void (*mremap)(struct file *, struct vm_area_struct *);
        int (*open) (struct inode *, struct file *);
        int (*flush) (struct file *, fl_owner_t id);
        int (*release) (struct inode *, struct file *);
@@ -1560,6 +1598,7 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
                              struct iovec *fast_pointer,
                              struct iovec **ret_pointer);
 
+extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
@@ -1936,7 +1975,7 @@ static inline int locks_verify_truncate(struct inode *inode,
                                    struct file *filp,
                                    loff_t size)
 {
-       if (inode->i_flock && mandatory_lock(inode))
+       if (inode->i_flctx && mandatory_lock(inode))
                return locks_mandatory_area(
                        FLOCK_VERIFY_WRITE, inode, filp,
                        size < inode->i_size ? size : inode->i_size,
@@ -1954,7 +1993,7 @@ static inline int break_lease(struct inode *inode, unsigned int mode)
         * end up racing with tasks trying to set a new lease on this file.
         */
        smp_mb();
-       if (inode->i_flock)
+       if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
                return __break_lease(inode, mode, FL_LEASE);
        return 0;
 }
@@ -1967,7 +2006,7 @@ static inline int break_deleg(struct inode *inode, unsigned int mode)
         * end up racing with tasks trying to set a new lease on this file.
         */
        smp_mb();
-       if (inode->i_flock)
+       if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
                return __break_lease(inode, mode, FL_DELEG);
        return 0;
 }
@@ -2063,7 +2102,7 @@ struct filename {
 extern long vfs_truncate(struct path *, loff_t);
 extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
                       struct file *filp);
-extern int do_fallocate(struct file *file, int mode, loff_t offset,
+extern int vfs_fallocate(struct file *file, int mode, loff_t offset,
                        loff_t len);
 extern long do_sys_open(int dfd, const char __user *filename, int flags,
                        umode_t mode);
@@ -2075,6 +2114,7 @@ extern int vfs_open(const struct path *, struct file *, const struct cred *);
 extern struct file * dentry_open(const struct path *, int, const struct cred *);
 extern int filp_close(struct file *, fl_owner_t id);
 
+extern struct filename *getname_flags(const char __user *, int, int *);
 extern struct filename *getname(const char __user *);
 extern struct filename *getname_kernel(const char *);
 
@@ -2152,7 +2192,6 @@ static inline int sb_is_blkdev_sb(struct super_block *sb)
 extern int sync_filesystem(struct super_block *);
 extern const struct file_operations def_blk_fops;
 extern const struct file_operations def_chr_fops;
-extern const struct file_operations bad_sock_fops;
 #ifdef CONFIG_BLOCK
 extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
 extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);