Update kernel fs.h header file
From 3.0.31 kernel.
SHA for latest change of fs.h is:
547740231f76185aadbef34dfa83c3e7dba3b34b
Also need to include blk_types.h that fs.h includes,
the SHA for it's last change is:
155d109b5f52ffd749219b27702462dcd9cf4f8d
Change-Id: I0636b7c2f1df268aeeb0e32c90e7127e7a82815f
diff --git a/original/linux/blk_types.h b/original/linux/blk_types.h
new file mode 100644
index 0000000..6395692
--- /dev/null
+++ b/original/linux/blk_types.h
@@ -0,0 +1,195 @@
+/*
+ * Block data types and constants. Directly include this file only to
+ * break include dependency loop.
+ */
+#ifndef __LINUX_BLK_TYPES_H
+#define __LINUX_BLK_TYPES_H
+
+#ifdef CONFIG_BLOCK
+
+#include <linux/types.h>
+
+struct bio_set;
+struct bio;
+struct bio_integrity_payload;
+struct page;
+struct block_device;
+typedef void (bio_end_io_t) (struct bio *, int);
+typedef void (bio_destructor_t) (struct bio *);
+
+/*
+ * was unsigned short, but we might as well be ready for > 64kB I/O pages
+ */
+struct bio_vec {
+ struct page *bv_page;
+ unsigned int bv_len;
+ unsigned int bv_offset;
+};
+
+/*
+ * main unit of I/O for the block layer and lower layers (ie drivers and
+ * stacking drivers)
+ */
+struct bio {
+ sector_t bi_sector; /* device address in 512 byte
+ sectors */
+ struct bio *bi_next; /* request queue link */
+ struct block_device *bi_bdev;
+ unsigned long bi_flags; /* status, command, etc */
+ unsigned long bi_rw; /* bottom bits READ/WRITE,
+ * top bits priority
+ */
+
+ unsigned short bi_vcnt; /* how many bio_vec's */
+ unsigned short bi_idx; /* current index into bvl_vec */
+
+ /* Number of segments in this BIO after
+ * physical address coalescing is performed.
+ */
+ unsigned int bi_phys_segments;
+
+ unsigned int bi_size; /* residual I/O count */
+
+ /*
+ * To keep track of the max segment size, we account for the
+ * sizes of the first and last mergeable segments in this bio.
+ */
+ unsigned int bi_seg_front_size;
+ unsigned int bi_seg_back_size;
+
+ unsigned int bi_max_vecs; /* max bvl_vecs we can hold */
+
+ unsigned int bi_comp_cpu; /* completion CPU */
+
+ atomic_t bi_cnt; /* pin count */
+
+ struct bio_vec *bi_io_vec; /* the actual vec list */
+
+ bio_end_io_t *bi_end_io;
+
+ void *bi_private;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+ struct bio_integrity_payload *bi_integrity; /* data integrity */
+#endif
+
+ bio_destructor_t *bi_destructor; /* destructor */
+
+ /*
+ * We can inline a number of vecs at the end of the bio, to avoid
+ * double allocations for a small number of bio_vecs. This member
+ * MUST obviously be kept at the very end of the bio.
+ */
+ struct bio_vec bi_inline_vecs[0];
+};
+
+/*
+ * bio flags
+ */
+#define BIO_UPTODATE 0 /* ok after I/O completion */
+#define BIO_RW_BLOCK 1 /* RW_AHEAD set, and read/write would block */
+#define BIO_EOF 2 /* out-out-bounds error */
+#define BIO_SEG_VALID 3 /* bi_phys_segments valid */
+#define BIO_CLONED 4 /* doesn't own data */
+#define BIO_BOUNCED 5 /* bio is a bounce bio */
+#define BIO_USER_MAPPED 6 /* contains user pages */
+#define BIO_EOPNOTSUPP 7 /* not supported */
+#define BIO_CPU_AFFINE 8 /* complete bio on same CPU as submitted */
+#define BIO_NULL_MAPPED 9 /* contains invalid user pages */
+#define BIO_FS_INTEGRITY 10 /* fs owns integrity data, not block layer */
+#define BIO_QUIET 11 /* Make BIO Quiet */
+#define BIO_MAPPED_INTEGRITY 12/* integrity metadata has been remapped */
+#define bio_flagged(bio, flag) ((bio)->bi_flags & (1 << (flag)))
+
+/*
+ * top 4 bits of bio flags indicate the pool this bio came from
+ */
+#define BIO_POOL_BITS (4)
+#define BIO_POOL_NONE ((1UL << BIO_POOL_BITS) - 1)
+#define BIO_POOL_OFFSET (BITS_PER_LONG - BIO_POOL_BITS)
+#define BIO_POOL_MASK (1UL << BIO_POOL_OFFSET)
+#define BIO_POOL_IDX(bio) ((bio)->bi_flags >> BIO_POOL_OFFSET)
+
+#endif /* CONFIG_BLOCK */
+
+/*
+ * Request flags. For use in the cmd_flags field of struct request, and in
+ * bi_rw of struct bio. Note that some flags are only valid in either one.
+ */
+enum rq_flag_bits {
+ /* common flags */
+ __REQ_WRITE, /* not set, read. set, write */
+ __REQ_FAILFAST_DEV, /* no driver retries of device errors */
+ __REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */
+ __REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */
+
+ __REQ_SYNC, /* request is sync (sync write or read) */
+ __REQ_META, /* metadata io request */
+ __REQ_DISCARD, /* request to discard sectors */
+ __REQ_NOIDLE, /* don't anticipate more IO after this one */
+
+ /* bio only flags */
+ __REQ_RAHEAD, /* read ahead, can fail anytime */
+ __REQ_THROTTLED, /* This bio has already been subjected to
+ * throttling rules. Don't do it again. */
+
+ /* request only flags */
+ __REQ_SORTED, /* elevator knows about this request */
+ __REQ_SOFTBARRIER, /* may not be passed by ioscheduler */
+ __REQ_FUA, /* forced unit access */
+ __REQ_NOMERGE, /* don't touch this for merging */
+ __REQ_STARTED, /* drive already may have started this one */
+ __REQ_DONTPREP, /* don't call prep for this one */
+ __REQ_QUEUED, /* uses queueing */
+ __REQ_ELVPRIV, /* elevator private data attached */
+ __REQ_FAILED, /* set if the request failed */
+ __REQ_QUIET, /* don't worry about errors */
+ __REQ_PREEMPT, /* set for "ide_preempt" requests */
+ __REQ_ALLOCED, /* request came from our alloc pool */
+ __REQ_COPY_USER, /* contains copies of user pages */
+ __REQ_FLUSH, /* request for cache flush */
+ __REQ_FLUSH_SEQ, /* request for flush sequence */
+ __REQ_IO_STAT, /* account I/O stat */
+ __REQ_MIXED_MERGE, /* merge of different types, fail separately */
+ __REQ_SECURE, /* secure discard (used with __REQ_DISCARD) */
+ __REQ_NR_BITS, /* stops here */
+};
+
+#define REQ_WRITE (1 << __REQ_WRITE)
+#define REQ_FAILFAST_DEV (1 << __REQ_FAILFAST_DEV)
+#define REQ_FAILFAST_TRANSPORT (1 << __REQ_FAILFAST_TRANSPORT)
+#define REQ_FAILFAST_DRIVER (1 << __REQ_FAILFAST_DRIVER)
+#define REQ_SYNC (1 << __REQ_SYNC)
+#define REQ_META (1 << __REQ_META)
+#define REQ_DISCARD (1 << __REQ_DISCARD)
+#define REQ_NOIDLE (1 << __REQ_NOIDLE)
+
+#define REQ_FAILFAST_MASK \
+ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
+#define REQ_COMMON_MASK \
+ (REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_DISCARD | \
+ REQ_NOIDLE | REQ_FLUSH | REQ_FUA | REQ_SECURE)
+#define REQ_CLONE_MASK REQ_COMMON_MASK
+
+#define REQ_RAHEAD (1 << __REQ_RAHEAD)
+#define REQ_THROTTLED (1 << __REQ_THROTTLED)
+
+#define REQ_SORTED (1 << __REQ_SORTED)
+#define REQ_SOFTBARRIER (1 << __REQ_SOFTBARRIER)
+#define REQ_FUA (1 << __REQ_FUA)
+#define REQ_NOMERGE (1 << __REQ_NOMERGE)
+#define REQ_STARTED (1 << __REQ_STARTED)
+#define REQ_DONTPREP (1 << __REQ_DONTPREP)
+#define REQ_QUEUED (1 << __REQ_QUEUED)
+#define REQ_ELVPRIV (1 << __REQ_ELVPRIV)
+#define REQ_FAILED (1 << __REQ_FAILED)
+#define REQ_QUIET (1 << __REQ_QUIET)
+#define REQ_PREEMPT (1 << __REQ_PREEMPT)
+#define REQ_ALLOCED (1 << __REQ_ALLOCED)
+#define REQ_COPY_USER (1 << __REQ_COPY_USER)
+#define REQ_FLUSH (1 << __REQ_FLUSH)
+#define REQ_FLUSH_SEQ (1 << __REQ_FLUSH_SEQ)
+#define REQ_IO_STAT (1 << __REQ_IO_STAT)
+#define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE)
+#define REQ_SECURE (1 << __REQ_SECURE)
+
+#endif /* __LINUX_BLK_TYPES_H */
diff --git a/original/linux/fs.h b/original/linux/fs.h
index 555bc19..d8ecb01 100644
--- a/original/linux/fs.h
+++ b/original/linux/fs.h
@@ -8,6 +8,8 @@
#include <linux/limits.h>
#include <linux/ioctl.h>
+#include <linux/blk_types.h>
+#include <linux/types.h>
/*
* It's silly to have NR_OPEN bigger than NR_FILE, but you can change
@@ -21,8 +23,8 @@
/* Fixed constants first: */
#undef NR_OPEN
-#define NR_OPEN (1024*1024) /* Absolute upper limit on fd num */
-#define INR_OPEN 1024 /* Initial setting for nfile rlimits */
+#define INR_OPEN_CUR 1024 /* Initial setting for nfile rlimits */
+#define INR_OPEN_MAX 4096 /* Hard limit for nfile rlimits */
#define BLOCK_SIZE_BITS 10
#define BLOCK_SIZE (1<<BLOCK_SIZE_BITS)
@@ -30,28 +32,27 @@
#define SEEK_SET 0 /* seek relative to beginning of file */
#define SEEK_CUR 1 /* seek relative to current file position */
#define SEEK_END 2 /* seek relative to end of file */
+#define SEEK_MAX SEEK_END
+
+struct fstrim_range {
+ __u64 start;
+ __u64 len;
+ __u64 minlen;
+};
/* And dynamically-tunable limits and defaults: */
struct files_stat_struct {
- int nr_files; /* read only */
- int nr_free_files; /* read only */
- int max_files; /* tunable */
+ unsigned long nr_files; /* read only */
+ unsigned long nr_free_files; /* read only */
+ unsigned long max_files; /* tunable */
};
-extern struct files_stat_struct files_stat;
-extern int get_max_files(void);
struct inodes_stat_t {
int nr_inodes;
int nr_unused;
- int dummy[5];
+ int dummy[5]; /* padding for sysctl ABI compatibility */
};
-extern struct inodes_stat_t inodes_stat;
-extern int leases_enable, lease_break_time;
-
-#ifdef CONFIG_DNOTIFY
-extern int dir_notify_enable;
-#endif
#define NR_FILE 8192 /* this can well be larger on a larger system */
@@ -59,30 +60,112 @@
#define MAY_WRITE 2
#define MAY_READ 4
#define MAY_APPEND 8
+#define MAY_ACCESS 16
+#define MAY_OPEN 32
+#define MAY_CHDIR 64
-#define FMODE_READ 1
-#define FMODE_WRITE 2
+/*
+ * flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond
+ * to O_WRONLY and O_RDWR via the strange trick in __dentry_open()
+ */
-/* Internal kernel extensions */
-#define FMODE_LSEEK 4
-#define FMODE_PREAD 8
-#define FMODE_PWRITE FMODE_PREAD /* These go hand in hand */
+/* file is open for reading */
+#define FMODE_READ ((__force fmode_t)0x1)
+/* file is open for writing */
+#define FMODE_WRITE ((__force fmode_t)0x2)
+/* file is seekable */
+#define FMODE_LSEEK ((__force fmode_t)0x4)
+/* file can be accessed using pread */
+#define FMODE_PREAD ((__force fmode_t)0x8)
+/* file can be accessed using pwrite */
+#define FMODE_PWRITE ((__force fmode_t)0x10)
+/* File is opened for execution with sys_execve / sys_uselib */
+#define FMODE_EXEC ((__force fmode_t)0x20)
+/* File is opened with O_NDELAY (only set for block devices) */
+#define FMODE_NDELAY ((__force fmode_t)0x40)
+/* File is opened with O_EXCL (only set for block devices) */
+#define FMODE_EXCL ((__force fmode_t)0x80)
+/* File is opened using open(.., 3, ..) and is writeable only for ioctls
+ (specialy hack for floppy.c) */
+#define FMODE_WRITE_IOCTL ((__force fmode_t)0x100)
-/* File is being opened for execution. Primary users of this flag are
- distributed filesystems that can use it to achieve correct ETXTBUSY
- behavior for cross-node execution/opening_for_writing of files */
-#define FMODE_EXEC 16
+/*
+ * Don't update ctime and mtime.
+ *
+ * Currently a special hack for the XFS open_by_handle ioctl, but we'll
+ * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon.
+ */
+#define FMODE_NOCMTIME ((__force fmode_t)0x800)
-#define RW_MASK 1
-#define RWA_MASK 2
-#define READ 0
-#define WRITE 1
-#define READA 2 /* read-ahead - don't block if no resources */
-#define SWRITE 3 /* for ll_rw_block() - wait for buffer lock */
-#define SPECIAL 4 /* For non-blockdevice requests in request queue */
-#define READ_SYNC (READ | (1 << BIO_RW_SYNC))
-#define WRITE_SYNC (WRITE | (1 << BIO_RW_SYNC))
-#define WRITE_BARRIER ((1 << BIO_RW) | (1 << BIO_RW_BARRIER))
+/* Expect random access pattern */
+#define FMODE_RANDOM ((__force fmode_t)0x1000)
+
+/* File is huge (eg. /dev/kmem): treat loff_t as unsigned */
+#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000)
+
+/* File is opened with O_PATH; almost nothing can be done with it */
+#define FMODE_PATH ((__force fmode_t)0x4000)
+
+/* File was opened by fanotify and shouldn't generate fanotify events */
+#define FMODE_NONOTIFY ((__force fmode_t)0x1000000)
+
+/*
+ * The below are the various read and write types that we support. Some of
+ * them include behavioral modifiers that send information down to the
+ * block layer and IO scheduler. Terminology:
+ *
+ * The block layer uses device plugging to defer IO a little bit, in
+ * the hope that we will see more IO very shortly. This increases
+ * coalescing of adjacent IO and thus reduces the number of IOs we
+ * have to send to the device. It also allows for better queuing,
+ * if the IO isn't mergeable. If the caller is going to be waiting
+ * for the IO, then he must ensure that the device is unplugged so
+ * that the IO is dispatched to the driver.
+ *
+ * All IO is handled async in Linux. This is fine for background
+ * writes, but for reads or writes that someone waits for completion
+ * on, we want to notify the block layer and IO scheduler so that they
+ * know about it. That allows them to make better scheduling
+ * decisions. So when the below references 'sync' and 'async', it
+ * is referencing this priority hint.
+ *
+ * With that in mind, the available types are:
+ *
+ * READ A normal read operation. Device will be plugged.
+ * READ_SYNC A synchronous read. Device is not plugged, caller can
+ * immediately wait on this read without caring about
+ * unplugging.
+ * READA Used for read-ahead operations. Lower priority, and the
+ * block layer could (in theory) choose to ignore this
+ * request if it runs into resource problems.
+ * WRITE A normal async write. Device will be plugged.
+ * WRITE_SYNC Synchronous write. Identical to WRITE, but passes down
+ * the hint that someone will be waiting on this IO
+ * shortly. The write equivalent of READ_SYNC.
+ * WRITE_ODIRECT Special case write for O_DIRECT only.
+ * WRITE_FLUSH Like WRITE_SYNC but with preceding cache flush.
+ * WRITE_FUA Like WRITE_SYNC but data is guaranteed to be on
+ * non-volatile media on completion.
+ * WRITE_FLUSH_FUA Combination of WRITE_FLUSH and FUA. The IO is preceded
+ * by a cache flush and data is guaranteed to be on
+ * non-volatile media on completion.
+ *
+ */
+#define RW_MASK REQ_WRITE
+#define RWA_MASK REQ_RAHEAD
+
+#define READ 0
+#define WRITE RW_MASK
+#define READA RWA_MASK
+
+#define READ_SYNC (READ | REQ_SYNC)
+#define READ_META (READ | REQ_META)
+#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE)
+#define WRITE_ODIRECT (WRITE | REQ_SYNC)
+#define WRITE_META (WRITE | REQ_META)
+#define WRITE_FLUSH (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH)
+#define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA)
+#define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
#define SEL_IN 1
#define SEL_OUT 2
@@ -91,10 +174,12 @@
/* public flags for file_system_type */
#define FS_REQUIRES_DEV 1
#define FS_BINARY_MOUNTDATA 2
+#define FS_HAS_SUBTYPE 4
#define FS_REVAL_DOT 16384 /* Check the paths ".", ".." for staleness */
-#define FS_ODD_RENAME 32768 /* Temporary stuff; will go away as soon
- * as nfs_rename() will be cleaned up
- */
+#define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move()
+ * during rename() internally.
+ */
+
/*
* These are the fs-independent mount-flags: up to 32 flags are supported
*/
@@ -119,13 +204,19 @@
#define MS_PRIVATE (1<<18) /* change to private */
#define MS_SLAVE (1<<19) /* change to slave */
#define MS_SHARED (1<<20) /* change to shared */
+#define MS_RELATIME (1<<21) /* Update atime relative to mtime/ctime. */
+#define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */
+#define MS_I_VERSION (1<<23) /* Update inode I_version field */
+#define MS_STRICTATIME (1<<24) /* Always perform atime updates */
+#define MS_NOSEC (1<<28)
+#define MS_BORN (1<<29)
#define MS_ACTIVE (1<<30)
#define MS_NOUSER (1<<31)
/*
* Superblock flags that can be altered by MS_REMOUNT
*/
-#define MS_RMT_MASK (MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK)
+#define MS_RMT_MASK (MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION)
/*
* Old magic mount flag and mask
@@ -145,6 +236,9 @@
#define S_NOCMTIME 128 /* Do not update file c/mtime */
#define S_SWAPFILE 256 /* Do not truncate: swapon got its bmaps */
#define S_PRIVATE 512 /* Inode is fs-internal */
+#define S_IMA 1024 /* Inode has an associated IMA struct */
+#define S_AUTOMOUNT 2048 /* Automount/referral quasi-directory */
+#define S_NOSEC 4096 /* no suid or xattr security attributes */
/*
* Note that nosuid etc flags are inode-specific: setting some file-system
@@ -167,6 +261,8 @@
#define IS_DIRSYNC(inode) (__IS_FLG(inode, MS_SYNCHRONOUS|MS_DIRSYNC) || \
((inode)->i_flags & (S_SYNC|S_DIRSYNC)))
#define IS_MANDLOCK(inode) __IS_FLG(inode, MS_MANDLOCK)
+#define IS_NOATIME(inode) __IS_FLG(inode, MS_RDONLY|MS_NOATIME)
+#define IS_I_VERSION(inode) __IS_FLG(inode, MS_I_VERSION)
#define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA)
#define IS_APPEND(inode) ((inode)->i_flags & S_APPEND)
@@ -177,6 +273,9 @@
#define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME)
#define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE)
#define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE)
+#define IS_IMA(inode) ((inode)->i_flags & S_IMA)
+#define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT)
+#define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC)
/* the read-only stuff doesn't really belong here, but any other place is
probably as bad and I don't want to create yet another include file. */
@@ -211,10 +310,63 @@
#define BLKTRACESTART _IO(0x12,116)
#define BLKTRACESTOP _IO(0x12,117)
#define BLKTRACETEARDOWN _IO(0x12,118)
+#define BLKDISCARD _IO(0x12,119)
+#define BLKIOMIN _IO(0x12,120)
+#define BLKIOOPT _IO(0x12,121)
+#define BLKALIGNOFF _IO(0x12,122)
+#define BLKPBSZGET _IO(0x12,123)
+#define BLKDISCARDZEROES _IO(0x12,124)
+#define BLKSECDISCARD _IO(0x12,125)
#define BMAP_IOCTL 1 /* obsolete - kept for compatibility */
#define FIBMAP _IO(0x00,1) /* bmap access */
#define FIGETBSZ _IO(0x00,2) /* get the block size used for bmap */
+#define FIFREEZE _IOWR('X', 119, int) /* Freeze */
+#define FITHAW _IOWR('X', 120, int) /* Thaw */
+#define FITRIM _IOWR('X', 121, struct fstrim_range) /* Trim */
+
+#define FS_IOC_GETFLAGS _IOR('f', 1, long)
+#define FS_IOC_SETFLAGS _IOW('f', 2, long)
+#define FS_IOC_GETVERSION _IOR('v', 1, long)
+#define FS_IOC_SETVERSION _IOW('v', 2, long)
+#define FS_IOC_FIEMAP _IOWR('f', 11, struct fiemap)
+#define FS_IOC32_GETFLAGS _IOR('f', 1, int)
+#define FS_IOC32_SETFLAGS _IOW('f', 2, int)
+#define FS_IOC32_GETVERSION _IOR('v', 1, int)
+#define FS_IOC32_SETVERSION _IOW('v', 2, int)
+
+/*
+ * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
+ */
+#define FS_SECRM_FL 0x00000001 /* Secure deletion */
+#define FS_UNRM_FL 0x00000002 /* Undelete */
+#define FS_COMPR_FL 0x00000004 /* Compress file */
+#define FS_SYNC_FL 0x00000008 /* Synchronous updates */
+#define FS_IMMUTABLE_FL 0x00000010 /* Immutable file */
+#define FS_APPEND_FL 0x00000020 /* writes to file may only append */
+#define FS_NODUMP_FL 0x00000040 /* do not dump file */
+#define FS_NOATIME_FL 0x00000080 /* do not update atime */
+/* Reserved for compression usage... */
+#define FS_DIRTY_FL 0x00000100
+#define FS_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */
+#define FS_NOCOMP_FL 0x00000400 /* Don't compress */
+#define FS_ECOMPR_FL 0x00000800 /* Compression error */
+/* End compression flags --- maybe not all used */
+#define FS_BTREE_FL 0x00001000 /* btree format dir */
+#define FS_INDEX_FL 0x00001000 /* hash-indexed directory */
+#define FS_IMAGIC_FL 0x00002000 /* AFS directory */
+#define FS_JOURNAL_DATA_FL 0x00004000 /* Reserved for ext3 */
+#define FS_NOTAIL_FL 0x00008000 /* file tail should not be merged */
+#define FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */
+#define FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/
+#define FS_EXTENT_FL 0x00080000 /* Extents */
+#define FS_DIRECTIO_FL 0x00100000 /* Use direct i/o */
+#define FS_NOCOW_FL 0x00800000 /* Do not cow file */
+#define FS_RESERVED_FL 0x80000000 /* reserved for ext2 lib */
+
+#define FS_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */
+#define FS_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */
+
#define SYNC_FILE_RANGE_WAIT_BEFORE 1
#define SYNC_FILE_RANGE_WRITE 2
@@ -227,59 +379,74 @@
#include <linux/types.h>
#include <linux/kdev_t.h>
#include <linux/dcache.h>
+#include <linux/path.h>
#include <linux/stat.h>
#include <linux/cache.h>
-#include <linux/kobject.h>
#include <linux/list.h>
#include <linux/radix-tree.h>
#include <linux/prio_tree.h>
#include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/pid.h>
#include <linux/mutex.h>
+#include <linux/capability.h>
+#include <linux/semaphore.h>
+#include <linux/fiemap.h>
+#include <linux/rculist_bl.h>
#include <asm/atomic.h>
-#include <asm/semaphore.h>
#include <asm/byteorder.h>
+struct export_operations;
struct hd_geometry;
struct iovec;
struct nameidata;
struct kiocb;
+struct kobject;
struct pipe_inode_info;
struct poll_table_struct;
struct kstatfs;
struct vm_area_struct;
struct vfsmount;
+struct cred;
-extern void __init inode_init(unsigned long);
+extern void __init inode_init(void);
extern void __init inode_init_early(void);
-extern void __init mnt_init(unsigned long);
extern void __init files_init(unsigned long);
+extern struct files_stat_struct files_stat;
+extern unsigned long get_max_files(void);
+extern int sysctl_nr_open;
+extern struct inodes_stat_t inodes_stat;
+extern int leases_enable, lease_break_time;
+
struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
- ssize_t bytes, void *private);
+ ssize_t bytes, void *private, int ret,
+ bool is_async);
/*
* Attribute flags. These should be or-ed together to figure out what
* has been changed!
*/
-#define ATTR_MODE 1
-#define ATTR_UID 2
-#define ATTR_GID 4
-#define ATTR_SIZE 8
-#define ATTR_ATIME 16
-#define ATTR_MTIME 32
-#define ATTR_CTIME 64
-#define ATTR_ATIME_SET 128
-#define ATTR_MTIME_SET 256
-#define ATTR_FORCE 512 /* Not a change, but a change it */
-#define ATTR_ATTR_FLAG 1024
-#define ATTR_KILL_SUID 2048
-#define ATTR_KILL_SGID 4096
-#define ATTR_FILE 8192
+#define ATTR_MODE (1 << 0)
+#define ATTR_UID (1 << 1)
+#define ATTR_GID (1 << 2)
+#define ATTR_SIZE (1 << 3)
+#define ATTR_ATIME (1 << 4)
+#define ATTR_MTIME (1 << 5)
+#define ATTR_CTIME (1 << 6)
+#define ATTR_ATIME_SET (1 << 7)
+#define ATTR_MTIME_SET (1 << 8)
+#define ATTR_FORCE (1 << 9) /* Not a change, but a change it */
+#define ATTR_ATTR_FLAG (1 << 10)
+#define ATTR_KILL_SUID (1 << 11)
+#define ATTR_KILL_SGID (1 << 12)
+#define ATTR_FILE (1 << 13)
+#define ATTR_KILL_PRIV (1 << 14)
+#define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */
+#define ATTR_TIMES_SET (1 << 16)
/*
* This is the Inode Attributes structure, used for notify_change(). It
@@ -301,7 +468,7 @@
struct timespec ia_ctime;
/*
- * Not an attribute, but an auxilary info for filesystems wanting to
+ * Not an attribute, but an auxiliary info for filesystems wanting to
* implement an ftruncate() like method. NOTE: filesystem should
* check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL).
*/
@@ -331,7 +498,7 @@
* trying again. The aop will be taking reasonable
* precautions not to livelock. If the caller held a page
* reference, it should drop it before retrying. Returned
- * by readpage(), prepare_write(), and commit_write().
+ * by readpage().
*
* address_space_operation functions return these large constants to indicate
* special semantics to the caller. These are much larger than the bytes in a
@@ -344,6 +511,12 @@
AOP_TRUNCATED_PAGE = 0x80001,
};
+#define AOP_FLAG_UNINTERRUPTIBLE 0x0001 /* will not do a short write */
+#define AOP_FLAG_CONT_EXPAND 0x0002 /* called from cont_expand */
+#define AOP_FLAG_NOFS 0x0004 /* used by filesystem to direct
+ * helper code (eg buffer layer)
+ * to clear GFP_FS from alloc */
+
/*
* oh the beauties of C type declarations.
*/
@@ -351,10 +524,63 @@
struct address_space;
struct writeback_control;
+struct iov_iter {
+ const struct iovec *iov;
+ unsigned long nr_segs;
+ size_t iov_offset;
+ size_t count;
+};
+
+size_t iov_iter_copy_from_user_atomic(struct page *page,
+ struct iov_iter *i, unsigned long offset, size_t bytes);
+size_t iov_iter_copy_from_user(struct page *page,
+ struct iov_iter *i, unsigned long offset, size_t bytes);
+void iov_iter_advance(struct iov_iter *i, size_t bytes);
+int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
+size_t iov_iter_single_seg_count(struct iov_iter *i);
+
+static inline void iov_iter_init(struct iov_iter *i,
+ const struct iovec *iov, unsigned long nr_segs,
+ size_t count, size_t written)
+{
+ i->iov = iov;
+ i->nr_segs = nr_segs;
+ i->iov_offset = 0;
+ i->count = count + written;
+
+ iov_iter_advance(i, written);
+}
+
+static inline size_t iov_iter_count(struct iov_iter *i)
+{
+ return i->count;
+}
+
+/*
+ * "descriptor" for what we're up to with a read.
+ * This allows us to use the same read code yet
+ * have multiple different users of the data that
+ * we read from a file.
+ *
+ * The simplest case just copies the data to user
+ * mode.
+ */
+typedef struct {
+ size_t written;
+ size_t count;
+ union {
+ char __user *buf;
+ void *data;
+ } arg;
+ int error;
+} read_descriptor_t;
+
+typedef int (*read_actor_t)(read_descriptor_t *, struct page *,
+ unsigned long, unsigned long);
+
struct address_space_operations {
int (*writepage)(struct page *page, struct writeback_control *wbc);
int (*readpage)(struct file *, struct page *);
- void (*sync_page)(struct page *);
/* Write back some dirty pages from this mapping. */
int (*writepages)(struct address_space *, struct writeback_control *);
@@ -365,35 +591,55 @@
int (*readpages)(struct file *filp, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages);
- /*
- * ext3 requires that a successful prepare_write() call be followed
- * by a commit_write() call - they must be balanced
- */
- int (*prepare_write)(struct file *, struct page *, unsigned, unsigned);
- int (*commit_write)(struct file *, struct page *, unsigned, unsigned);
+ int (*write_begin)(struct file *, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned flags,
+ struct page **pagep, void **fsdata);
+ int (*write_end)(struct file *, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata);
+
/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
sector_t (*bmap)(struct address_space *, sector_t);
void (*invalidatepage) (struct page *, unsigned long);
int (*releasepage) (struct page *, gfp_t);
+ void (*freepage)(struct page *);
ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
loff_t offset, unsigned long nr_segs);
- struct page* (*get_xip_page)(struct address_space *, sector_t,
- int);
+ int (*get_xip_mem)(struct address_space *, pgoff_t, int,
+ void **, unsigned long *);
/* migrate the contents of a page to the specified target */
int (*migratepage) (struct address_space *,
struct page *, struct page *);
+ int (*launder_page) (struct page *);
+ int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
+ unsigned long);
+ int (*error_remove_page)(struct address_space *, struct page *);
};
+extern const struct address_space_operations empty_aops;
+
+/*
+ * pagecache_write_begin/pagecache_write_end must be used by general code
+ * to write into the pagecache.
+ */
+int pagecache_write_begin(struct file *, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned flags,
+ struct page **pagep, void **fsdata);
+
+int pagecache_write_end(struct file *, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata);
+
struct backing_dev_info;
struct address_space {
struct inode *host; /* owner: inode, block_device */
struct radix_tree_root page_tree; /* radix tree of all pages */
- rwlock_t tree_lock; /* and rwlock protecting it */
+ spinlock_t tree_lock; /* and lock protecting it */
unsigned int i_mmap_writable;/* count VM_SHARED mappings */
struct prio_tree_root i_mmap; /* tree of private and shared mappings */
struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
- spinlock_t i_mmap_lock; /* protect tree, count, list */
- unsigned int truncate_count; /* Cover race condition with truncate */
+ struct mutex i_mmap_mutex; /* protect tree, count, list */
+ /* Protected by tree_lock together with the radix tree */
unsigned long nrpages; /* number of total pages */
pgoff_t writeback_index;/* writeback starts here */
const struct address_space_operations *a_ops; /* methods */
@@ -405,21 +651,23 @@
} __attribute__((aligned(sizeof(long))));
/*
* On most architectures that alignment is already the case; but
- * must be enforced here for CRIS, to let the least signficant bit
+ * must be enforced here for CRIS, to let the least significant bit
* of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
*/
struct block_device {
dev_t bd_dev; /* not a kdev_t - it's a search key */
- struct inode * bd_inode; /* will die */
int bd_openers;
+ struct inode * bd_inode; /* will die */
+ struct super_block * bd_super;
struct mutex bd_mutex; /* open/close mutex */
- struct mutex bd_mount_mutex; /* mount mutex */
struct list_head bd_inodes;
+ void * bd_claiming;
void * bd_holder;
int bd_holders;
+ bool bd_write_holder;
#ifdef CONFIG_SYSFS
- struct list_head bd_holder_list;
+ struct list_head bd_holder_disks;
#endif
struct block_device * bd_contains;
unsigned bd_block_size;
@@ -429,7 +677,6 @@
int bd_invalidated;
struct gendisk * bd_disk;
struct list_head bd_list;
- struct backing_dev_info *bd_inode_backing_dev_info;
/*
* Private data. You must have bd_claim'ed the block_device
* to use this. NOTE: bd_claim allows an owner to claim
@@ -437,29 +684,20 @@
* care to not mess up bd_private for that case.
*/
unsigned long bd_private;
-};
-/*
- * bdev->bd_mutex nesting subclasses for the lock validator:
- *
- * 0: normal
- * 1: 'whole'
- * 2: 'partition'
- */
-enum bdev_bd_mutex_lock_class
-{
- BD_MUTEX_NORMAL,
- BD_MUTEX_WHOLE,
- BD_MUTEX_PARTITION
+ /* The counter of freeze processes */
+ int bd_fsfreeze_count;
+ /* Mutex for freeze */
+ struct mutex bd_fsfreeze_mutex;
};
-
/*
* Radix-tree tags, for tagging dirty and writeback pages within the pagecache
* radix trees
*/
#define PAGECACHE_TAG_DIRTY 0
#define PAGECACHE_TAG_WRITEBACK 1
+#define PAGECACHE_TAG_TOWRITE 2
int mapping_tagged(struct address_space *mapping, int tag);
@@ -494,73 +732,89 @@
#define i_size_ordered_init(inode) do { } while (0)
#endif
+struct posix_acl;
+#define ACL_NOT_CACHED ((void *)(-1))
+
struct inode {
- struct hlist_node i_hash;
- struct list_head i_list;
- struct list_head i_sb_list;
- struct list_head i_dentry;
- unsigned long i_ino;
- atomic_t i_count;
+ /* RCU path lookup touches following: */
umode_t i_mode;
- unsigned int i_nlink;
uid_t i_uid;
gid_t i_gid;
+ const struct inode_operations *i_op;
+ struct super_block *i_sb;
+
+ spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
+ unsigned int i_flags;
+ unsigned long i_state;
+#ifdef CONFIG_SECURITY
+ void *i_security;
+#endif
+ struct mutex i_mutex;
+
+
+ unsigned long dirtied_when; /* jiffies of first dirtying */
+
+ struct hlist_node i_hash;
+ struct list_head i_wb_list; /* backing dev IO list */
+ struct list_head i_lru; /* inode LRU list */
+ struct list_head i_sb_list;
+ union {
+ struct list_head i_dentry;
+ struct rcu_head i_rcu;
+ };
+ unsigned long i_ino;
+ atomic_t i_count;
+ unsigned int i_nlink;
dev_t i_rdev;
+ unsigned int i_blkbits;
+ u64 i_version;
loff_t i_size;
+#ifdef __NEED_I_SIZE_ORDERED
+ seqcount_t i_size_seqcount;
+#endif
struct timespec i_atime;
struct timespec i_mtime;
struct timespec i_ctime;
- unsigned int i_blkbits;
- unsigned long i_blksize;
- unsigned long i_version;
blkcnt_t i_blocks;
unsigned short i_bytes;
- spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
- struct mutex i_mutex;
struct rw_semaphore i_alloc_sem;
- struct inode_operations *i_op;
const struct file_operations *i_fop; /* former ->i_op->default_file_ops */
- struct super_block *i_sb;
struct file_lock *i_flock;
struct address_space *i_mapping;
struct address_space i_data;
#ifdef CONFIG_QUOTA
struct dquot *i_dquot[MAXQUOTAS];
#endif
- /* These three should probably be a union */
struct list_head i_devices;
- struct pipe_inode_info *i_pipe;
- struct block_device *i_bdev;
- struct cdev *i_cdev;
- int i_cindex;
+ union {
+ struct pipe_inode_info *i_pipe;
+ struct block_device *i_bdev;
+ struct cdev *i_cdev;
+ };
__u32 i_generation;
-#ifdef CONFIG_DNOTIFY
- unsigned long i_dnotify_mask; /* Directory notify events */
- struct dnotify_struct *i_dnotify; /* for directory notifications */
+#ifdef CONFIG_FSNOTIFY
+ __u32 i_fsnotify_mask; /* all events this inode cares about */
+ struct hlist_head i_fsnotify_marks;
#endif
-#ifdef CONFIG_INOTIFY
- struct list_head inotify_watches; /* watches on this inode */
- struct mutex inotify_mutex; /* protects the watches list */
+#ifdef CONFIG_IMA
+ atomic_t i_readcount; /* struct files open RO */
#endif
-
- unsigned long i_state;
- unsigned long dirtied_when; /* jiffies of first dirtying */
-
- unsigned int i_flags;
-
atomic_t i_writecount;
- void *i_security;
- union {
- void *generic_ip;
- } u;
-#ifdef __NEED_I_SIZE_ORDERED
- seqcount_t i_size_seqcount;
+#ifdef CONFIG_FS_POSIX_ACL
+ struct posix_acl *i_acl;
+ struct posix_acl *i_default_acl;
#endif
+ void *i_private; /* fs or device private pointer */
};
+static inline int inode_unhashed(struct inode *inode)
+{
+ return hlist_unhashed(&inode->i_hash);
+}
+
/*
* inode->i_mutex nesting subclasses for the lock validator:
*
@@ -591,7 +845,7 @@
* cmpxchg8b without the need of the lock prefix). For SMP compiles
* and 64bit archs it makes no difference if preempt is enabled or not.
*/
-static inline loff_t i_size_read(struct inode *inode)
+static inline loff_t i_size_read(const struct inode *inode)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
loff_t i_size;
@@ -614,7 +868,11 @@
#endif
}
-
+/*
+ * NOTE: unlike i_size_read(), i_size_write() does need locking around it
+ * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount
+ * can be lost, resulting in subsequent i_size_read() calls spinning forever.
+ */
static inline void i_size_write(struct inode *inode, loff_t i_size)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
@@ -630,12 +888,12 @@
#endif
}
-static inline unsigned iminor(struct inode *inode)
+static inline unsigned iminor(const struct inode *inode)
{
return MINOR(inode->i_rdev);
}
-static inline unsigned imajor(struct inode *inode)
+static inline unsigned imajor(const struct inode *inode)
{
return MAJOR(inode->i_rdev);
}
@@ -644,9 +902,9 @@
struct fown_struct {
rwlock_t lock; /* protects pid, uid, euid fields */
- int pid; /* pid or -pgrp where SIGIO should be sent */
+ struct pid *pid; /* pid or -pgrp where SIGIO should be sent */
+ enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */
uid_t uid, euid; /* uid/euid of process setting the owner */
- void *security;
int signum; /* posix.1b rt signal to be delivered on IO */
};
@@ -654,19 +912,27 @@
* Track a single file's readahead state
*/
struct file_ra_state {
- unsigned long start; /* Current window */
- unsigned long size;
- unsigned long flags; /* ra flags RA_FLAG_xxx*/
- unsigned long cache_hit; /* cache hit count*/
- unsigned long prev_page; /* Cache last read() position */
- unsigned long ahead_start; /* Ahead window */
- unsigned long ahead_size;
- unsigned long ra_pages; /* Maximum readahead window */
- unsigned long mmap_hit; /* Cache hit stat for mmap accesses */
- unsigned long mmap_miss; /* Cache miss stat for mmap accesses */
+ pgoff_t start; /* where readahead started */
+ unsigned int size; /* # of readahead pages */
+ unsigned int async_size; /* do asynchronous readahead when
+ there are only # of pages ahead */
+
+ unsigned int ra_pages; /* Maximum readahead window */
+ unsigned int mmap_miss; /* Cache miss stat for mmap accesses */
+ loff_t prev_pos; /* Cache last read() position */
};
-#define RA_FLAG_MISS 0x01 /* a cache miss occured against this file */
-#define RA_FLAG_INCACHE 0x02 /* file is already in cache */
+
+/*
+ * Check if @index falls in the readahead windows.
+ */
+static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
+{
+ return (index >= ra->start &&
+ index < ra->start + ra->size);
+}
+
+#define FILE_MNT_WRITE_TAKEN 1
+#define FILE_MNT_WRITE_RELEASED 2
struct file {
/*
@@ -677,36 +943,93 @@
struct list_head fu_list;
struct rcu_head fu_rcuhead;
} f_u;
- struct dentry *f_dentry;
- struct vfsmount *f_vfsmnt;
+ struct path f_path;
+#define f_dentry f_path.dentry
+#define f_vfsmnt f_path.mnt
const struct file_operations *f_op;
- atomic_t f_count;
+ spinlock_t f_lock; /* f_ep_links, f_flags, no IRQ */
+#ifdef CONFIG_SMP
+ int f_sb_list_cpu;
+#endif
+ atomic_long_t f_count;
unsigned int f_flags;
- mode_t f_mode;
+ fmode_t f_mode;
loff_t f_pos;
struct fown_struct f_owner;
- unsigned int f_uid, f_gid;
+ const struct cred *f_cred;
struct file_ra_state f_ra;
- unsigned long f_version;
+ u64 f_version;
+#ifdef CONFIG_SECURITY
void *f_security;
-
+#endif
/* needed for tty driver, and maybe others */
void *private_data;
#ifdef CONFIG_EPOLL
/* Used by fs/eventpoll.c to link all the hooks to this file */
struct list_head f_ep_links;
- spinlock_t f_ep_lock;
+ struct list_head f_tfile_llink;
#endif /* #ifdef CONFIG_EPOLL */
struct address_space *f_mapping;
+#ifdef CONFIG_DEBUG_WRITECOUNT
+ unsigned long f_mnt_write_state;
+#endif
};
-extern spinlock_t files_lock;
-#define file_list_lock() spin_lock(&files_lock);
-#define file_list_unlock() spin_unlock(&files_lock);
-#define get_file(x) atomic_inc(&(x)->f_count)
-#define file_count(x) atomic_read(&(x)->f_count)
+struct file_handle {
+ __u32 handle_bytes;
+ int handle_type;
+ /* file identifier */
+ unsigned char f_handle[0];
+};
+
+#define get_file(x) atomic_long_inc(&(x)->f_count)
+#define fput_atomic(x) atomic_long_add_unless(&(x)->f_count, -1, 1)
+#define file_count(x) atomic_long_read(&(x)->f_count)
+
+#ifdef CONFIG_DEBUG_WRITECOUNT
+static inline void file_take_write(struct file *f)
+{
+ WARN_ON(f->f_mnt_write_state != 0);
+ f->f_mnt_write_state = FILE_MNT_WRITE_TAKEN;
+}
+static inline void file_release_write(struct file *f)
+{
+ f->f_mnt_write_state |= FILE_MNT_WRITE_RELEASED;
+}
+static inline void file_reset_write(struct file *f)
+{
+ f->f_mnt_write_state = 0;
+}
+static inline void file_check_state(struct file *f)
+{
+ /*
+ * At this point, either both or neither of these bits
+ * should be set.
+ */
+ WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN);
+ WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_RELEASED);
+}
+static inline int file_check_writeable(struct file *f)
+{
+ if (f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN)
+ return 0;
+ printk(KERN_WARNING "writeable file with no "
+ "mnt_want_write()\n");
+ WARN_ON(1);
+ return -EINVAL;
+}
+#else /* !CONFIG_DEBUG_WRITECOUNT */
+static inline void file_take_write(struct file *filp) {}
+static inline void file_release_write(struct file *filp) {}
+static inline void file_reset_write(struct file *filp) {}
+static inline void file_check_state(struct file *filp) {}
+static inline int file_check_writeable(struct file *filp)
+{
+ return 0;
+}
+#endif /* CONFIG_DEBUG_WRITECOUNT */
#define MAX_NON_LFS ((1UL<<31) - 1)
@@ -727,6 +1050,12 @@
#define FL_SLEEP 128 /* A blocking lock */
/*
+ * Special return value from posix_lock_file() and vfs_lock_file() for
+ * asynchronous locking.
+ */
+#define FILE_LOCK_DEFERRED 1
+
+/*
* The POSIX file lock owner is determined by
* the "struct files_struct" in the thread group
* (or NULL for no owner - BSD locks).
@@ -736,8 +1065,6 @@
typedef struct files_struct *fl_owner_t;
struct file_lock_operations {
- void (*fl_insert)(struct file_lock *); /* lock insertion callback */
- void (*fl_remove)(struct file_lock *); /* lock removal callback */
void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
void (*fl_release_private)(struct file_lock *);
};
@@ -745,13 +1072,20 @@
struct lock_manager_operations {
int (*fl_compare_owner)(struct file_lock *, struct file_lock *);
void (*fl_notify)(struct file_lock *); /* unblock callback */
- void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
+ int (*fl_grant)(struct file_lock *, struct file_lock *, int);
void (*fl_release_private)(struct file_lock *);
void (*fl_break)(struct file_lock *);
- int (*fl_mylease)(struct file_lock *, struct file_lock *);
int (*fl_change)(struct file_lock **, int);
};
+struct lock_manager {
+ struct list_head list;
+};
+
+void locks_start_grace(struct lock_manager *);
+void locks_end_grace(struct lock_manager *);
+int locks_in_grace(void);
+
/* that will die - we need it for nfs_lock_info */
#include <linux/nfs_fs_i.h>
@@ -760,22 +1094,27 @@
struct list_head fl_link; /* doubly linked list of all locks */
struct list_head fl_block; /* circular list of blocked processes */
fl_owner_t fl_owner;
- unsigned int fl_pid;
- wait_queue_head_t fl_wait;
- struct file *fl_file;
unsigned char fl_flags;
unsigned char fl_type;
+ unsigned int fl_pid;
+ struct pid *fl_nspid;
+ 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 */
unsigned long fl_break_time; /* for nonblocking lease breaks */
- struct file_lock_operations *fl_ops; /* Callbacks for filesystems */
- struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */
+ 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 */
+ } afs;
} fl_u;
};
@@ -788,6 +1127,9 @@
#include <linux/fcntl.h>
+extern void send_sigio(struct fown_struct *fown, int fd, int band);
+
+#ifdef CONFIG_FILE_LOCKING
extern int fcntl_getlk(struct file *, struct flock __user *);
extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
struct flock __user *);
@@ -798,50 +1140,213 @@
struct flock64 __user *);
#endif
-extern void send_sigio(struct fown_struct *fown, int fd, int band);
extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg);
extern int fcntl_getlease(struct file *filp);
-/* fs/sync.c */
-extern int do_sync_file_range(struct file *file, loff_t offset, loff_t endbyte,
- unsigned int flags);
-
/* fs/locks.c */
+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_lock(struct file_lock *, const struct file_lock *);
extern void locks_remove_posix(struct file *, fl_owner_t);
extern void locks_remove_flock(struct file *);
-extern int posix_test_lock(struct file *, struct file_lock *, struct file_lock *);
-extern int posix_lock_file_conf(struct file *, struct file_lock *, struct file_lock *);
-extern int posix_lock_file(struct file *, struct file_lock *);
+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 posix_lock_file_wait(struct file *, struct file_lock *);
extern int posix_unblock_lock(struct file *, 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);
extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl);
extern int __break_lease(struct inode *inode, unsigned int flags);
extern void lease_get_mtime(struct inode *, struct timespec *time);
-extern int setlease(struct file *, long, struct file_lock **);
+extern int generic_setlease(struct file *, long, struct file_lock **);
+extern int vfs_setlease(struct file *, long, struct file_lock **);
extern int lease_modify(struct file_lock **, int);
extern int lock_may_read(struct inode *, loff_t start, unsigned long count);
extern int lock_may_write(struct inode *, loff_t start, unsigned long count);
+extern void lock_flocks(void);
+extern void unlock_flocks(void);
+#else /* !CONFIG_FILE_LOCKING */
+static inline int fcntl_getlk(struct file *file, 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, struct flock64 __user *user)
+{
+ return -EINVAL;
+}
+
+static inline int fcntl_setlk64(unsigned int fd, struct file *file,
+ unsigned int cmd, struct flock64 __user *user)
+{
+ return -EACCES;
+}
+#endif
+static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
+{
+ return 0;
+}
+
+static inline int fcntl_getlease(struct file *filp)
+{
+ return 0;
+}
+
+static inline void locks_init_lock(struct file_lock *fl)
+{
+ return;
+}
+
+static inline void __locks_copy_lock(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_flock(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 posix_lock_file_wait(struct file *filp, struct file_lock *fl)
+{
+ return -ENOLCK;
+}
+
+static inline int posix_unblock_lock(struct file *filp,
+ 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 int flock_lock_file_wait(struct file *filp,
+ struct file_lock *request)
+{
+ return -ENOLCK;
+}
+
+static inline int __break_lease(struct inode *inode, unsigned int mode)
+{
+ return 0;
+}
+
+static inline void lease_get_mtime(struct inode *inode, struct timespec *time)
+{
+ return;
+}
+
+static inline int generic_setlease(struct file *filp, long arg,
+ struct file_lock **flp)
+{
+ return -EINVAL;
+}
+
+static inline int vfs_setlease(struct file *filp, long arg,
+ struct file_lock **lease)
+{
+ return -EINVAL;
+}
+
+static inline int lease_modify(struct file_lock **before, int arg)
+{
+ return -EINVAL;
+}
+
+static inline int lock_may_read(struct inode *inode, loff_t start,
+ unsigned long len)
+{
+ return 1;
+}
+
+static inline int lock_may_write(struct inode *inode, loff_t start,
+ unsigned long len)
+{
+ return 1;
+}
+
+static inline void lock_flocks(void)
+{
+}
+
+static inline void unlock_flocks(void)
+{
+}
+
+#endif /* !CONFIG_FILE_LOCKING */
+
struct fasync_struct {
- int magic;
- int fa_fd;
- struct fasync_struct *fa_next; /* singly linked list */
- struct file *fa_file;
+ spinlock_t fa_lock;
+ int magic;
+ int fa_fd;
+ struct fasync_struct *fa_next; /* singly linked list */
+ struct file *fa_file;
+ struct rcu_head fa_rcu;
};
#define FASYNC_MAGIC 0x4601
/* SMP safe fasync helpers: */
extern int fasync_helper(int, struct file *, int, struct fasync_struct **);
+extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *);
+extern int fasync_remove_entry(struct file *, struct fasync_struct **);
+extern struct fasync_struct *fasync_alloc(void);
+extern void fasync_free(struct fasync_struct *);
+
/* can be called from interrupts */
extern void kill_fasync(struct fasync_struct **, int, int);
-/* only for net: no internal synchronization */
-extern void __kill_fasync(struct fasync_struct *, int, int);
+extern int __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
extern int f_setown(struct file *filp, unsigned long arg, int force);
extern void f_delown(struct file *filp);
+extern pid_t f_getown(struct file *filp);
extern int send_sigurg(struct fown_struct *fown);
/*
@@ -851,43 +1356,50 @@
#define MNT_FORCE 0x00000001 /* Attempt to forcibily umount */
#define MNT_DETACH 0x00000002 /* Just detach from the tree */
#define MNT_EXPIRE 0x00000004 /* Mark for expiry */
+#define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */
+#define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */
extern struct list_head super_blocks;
extern spinlock_t sb_lock;
-#define sb_entry(list) list_entry((list), struct super_block, s_list)
-#define S_BIAS (1<<30)
struct super_block {
struct list_head s_list; /* Keep this first */
dev_t s_dev; /* search index; _not_ kdev_t */
- unsigned long s_blocksize;
- unsigned char s_blocksize_bits;
unsigned char s_dirt;
- unsigned long long s_maxbytes; /* Max file size */
+ unsigned char s_blocksize_bits;
+ unsigned long s_blocksize;
+ loff_t s_maxbytes; /* Max file size */
struct file_system_type *s_type;
- struct super_operations *s_op;
- struct dquot_operations *dq_op;
- struct quotactl_ops *s_qcop;
- struct export_operations *s_export_op;
+ const struct super_operations *s_op;
+ const struct dquot_operations *dq_op;
+ const struct quotactl_ops *s_qcop;
+ const struct export_operations *s_export_op;
unsigned long s_flags;
unsigned long s_magic;
struct dentry *s_root;
struct rw_semaphore s_umount;
struct mutex s_lock;
int s_count;
- int s_syncing;
- int s_need_sync_fs;
atomic_t s_active;
+#ifdef CONFIG_SECURITY
void *s_security;
- struct xattr_handler **s_xattr;
+#endif
+ const struct xattr_handler **s_xattr;
struct list_head s_inodes; /* all inodes */
- struct list_head s_dirty; /* dirty inodes */
- struct list_head s_io; /* parked for writeback */
- struct hlist_head s_anon; /* anonymous dentries for (nfs) exporting */
+ struct hlist_bl_head s_anon; /* anonymous dentries for (nfs) exporting */
+#ifdef CONFIG_SMP
+ struct list_head __percpu *s_files;
+#else
struct list_head s_files;
+#endif
+ /* s_dentry_lru, s_nr_dentry_unused protected by dcache.c lru locks */
+ struct list_head s_dentry_lru; /* unused dentry lru */
+ int s_nr_dentry_unused; /* # of dentry on lru */
struct block_device *s_bdev;
+ struct backing_dev_info *s_bdi;
+ struct mtd_info *s_mtd;
struct list_head s_instances;
struct quota_info s_dquot; /* Diskquota specific options */
@@ -895,8 +1407,14 @@
wait_queue_head_t s_wait_unfrozen;
char s_id[32]; /* Informational name */
+ u8 s_uuid[16]; /* UUID */
void *s_fs_info; /* Filesystem private info */
+ fmode_t s_mode;
+
+ /* Granularity of c/m/atime in ns.
+ Cannot be worse than a second */
+ u32 s_time_gran;
/*
* The next field is for VFS *only*. No filesystems have any business
@@ -904,9 +1422,23 @@
*/
struct mutex s_vfs_rename_mutex; /* Kludge */
- /* Granularity of c/m/atime in ns.
- Cannot be worse than a second */
- u32 s_time_gran;
+ /*
+ * Filesystem subtype. If non-empty the filesystem type field
+ * in /proc/mounts will be "type.subtype"
+ */
+ char *s_subtype;
+
+ /*
+ * Saved mount options for lazy filesystems using
+ * generic_show_options()
+ */
+ char __rcu *s_options;
+ const struct dentry_operations *s_d_op; /* default d_op for dentries */
+
+ /*
+ * Saved pool identifier for cleancache (-1 means none)
+ */
+ int cleancache_poolid;
};
extern struct timespec current_fs_time(struct super_block *sb);
@@ -923,45 +1455,29 @@
#define vfs_check_frozen(sb, level) \
wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level)))
-static inline void get_fs_excl(void)
-{
- atomic_inc(¤t->fs_excl);
-}
-
-static inline void put_fs_excl(void)
-{
- atomic_dec(¤t->fs_excl);
-}
-
-static inline int has_fs_excl(void)
-{
- return atomic_read(¤t->fs_excl);
-}
-
+#define get_fs_excl() atomic_inc(¤t->fs_excl)
+#define put_fs_excl() atomic_dec(¤t->fs_excl)
+#define has_fs_excl() atomic_read(¤t->fs_excl)
/*
- * Superblock locking.
+ * until VFS tracks user namespaces for inodes, just make all files
+ * belong to init_user_ns
*/
-static inline void lock_super(struct super_block * sb)
-{
- get_fs_excl();
- mutex_lock(&sb->s_lock);
-}
+extern struct user_namespace init_user_ns;
+#define inode_userns(inode) (&init_user_ns)
+extern bool inode_owner_or_capable(const struct inode *inode);
-static inline void unlock_super(struct super_block * sb)
-{
- put_fs_excl();
- mutex_unlock(&sb->s_lock);
-}
+/* not quite ready to be deprecated, but... */
+extern void lock_super(struct super_block *);
+extern void unlock_super(struct super_block *);
/*
* VFS helper functions..
*/
-extern int vfs_permission(struct nameidata *, int);
extern int vfs_create(struct inode *, struct dentry *, int, struct nameidata *);
extern int vfs_mkdir(struct inode *, struct dentry *, int);
extern int vfs_mknod(struct inode *, struct dentry *, int, dev_t);
-extern int vfs_symlink(struct inode *, struct dentry *, const char *, int);
+extern int vfs_symlink(struct inode *, struct dentry *, const char *);
extern int vfs_link(struct dentry *, struct inode *, struct dentry *);
extern int vfs_rmdir(struct inode *, struct dentry *);
extern int vfs_unlink(struct inode *, struct dentry *);
@@ -976,6 +1492,21 @@
* VFS file helper functions.
*/
extern int file_permission(struct file *, int);
+extern void inode_init_owner(struct inode *inode, const struct inode *dir,
+ mode_t mode);
+/*
+ * VFS FS_IOC_FIEMAP helper definitions.
+ */
+struct fiemap_extent_info {
+ unsigned int fi_flags; /* Flags as passed from user */
+ unsigned int fi_extents_mapped; /* Number of mapped extents */
+ unsigned int fi_extents_max; /* Size of fiemap_extent array */
+ struct fiemap_extent __user *fi_extents_start; /* Start of
+ fiemap_extent array */
+};
+int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical,
+ u64 phys, u64 len, u32 flags);
+int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
/*
* File types
@@ -993,52 +1524,14 @@
#define DT_SOCK 12
#define DT_WHT 14
-#define OSYNC_METADATA (1<<0)
-#define OSYNC_DATA (1<<1)
-#define OSYNC_INODE (1<<2)
-int generic_osync_inode(struct inode *, struct address_space *, int);
-
/*
* This is the "filldir" function type, used by readdir() to let
* the kernel specify what kind of dirent layout it wants to have.
* This allows the kernel to read directories into kernel space or
* to have different dirent layouts depending on the binary type.
*/
-typedef int (*filldir_t)(void *, const char *, int, loff_t, ino_t, unsigned);
-
-struct block_device_operations {
- int (*open) (struct inode *, struct file *);
- int (*release) (struct inode *, struct file *);
- int (*ioctl) (struct inode *, struct file *, unsigned, unsigned long);
- long (*unlocked_ioctl) (struct file *, unsigned, unsigned long);
- long (*compat_ioctl) (struct file *, unsigned, unsigned long);
- int (*direct_access) (struct block_device *, sector_t, unsigned long *);
- int (*media_changed) (struct gendisk *);
- int (*revalidate_disk) (struct gendisk *);
- int (*getgeo)(struct block_device *, struct hd_geometry *);
- struct module *owner;
-};
-
-/*
- * "descriptor" for what we're up to with a read for sendfile().
- * This allows us to use the same read code yet
- * have multiple different users of the data that
- * we read from a file.
- *
- * The simplest case just copies the data to user
- * mode.
- */
-typedef struct {
- size_t written;
- size_t count;
- union {
- char __user * buf;
- void *data;
- } arg;
- int error;
-} read_descriptor_t;
-
-typedef int (*read_actor_t)(read_descriptor_t *, struct page *, unsigned long, unsigned long);
+typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
+struct block_device_operations;
/* These macros are for out of kernel modules to test that
* the kernel supports the unlocked_ioctl and compat_ioctl
@@ -1048,44 +1541,51 @@
/*
* NOTE:
- * read, write, poll, fsync, readv, writev, unlocked_ioctl and compat_ioctl
- * can be called without the big kernel lock held in all filesystems.
+ * all file operations except setlease can be called without
+ * the big kernel lock held in all filesystems.
*/
struct file_operations {
struct module *owner;
loff_t (*llseek) (struct file *, loff_t, int);
ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
- ssize_t (*aio_read) (struct kiocb *, char __user *, size_t, loff_t);
ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
- ssize_t (*aio_write) (struct kiocb *, const char __user *, size_t, loff_t);
+ ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
+ ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
int (*readdir) (struct file *, void *, filldir_t);
unsigned int (*poll) (struct file *, struct poll_table_struct *);
- int (*ioctl) (struct inode *, struct file *, unsigned int, unsigned long);
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 *);
int (*open) (struct inode *, struct file *);
int (*flush) (struct file *, fl_owner_t id);
int (*release) (struct inode *, struct file *);
- int (*fsync) (struct file *, struct dentry *, int datasync);
+ int (*fsync) (struct file *, int datasync);
int (*aio_fsync) (struct kiocb *, int datasync);
int (*fasync) (int, struct file *, int);
int (*lock) (struct file *, int, struct file_lock *);
- ssize_t (*readv) (struct file *, const struct iovec *, unsigned long, loff_t *);
- ssize_t (*writev) (struct file *, const struct iovec *, unsigned long, loff_t *);
- ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t, void *);
ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int);
unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
int (*check_flags)(int);
- int (*dir_notify)(struct file *filp, unsigned long arg);
int (*flock) (struct file *, int, struct file_lock *);
ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
+ int (*setlease)(struct file *, long, struct file_lock **);
+ long (*fallocate)(struct file *file, int mode, loff_t offset,
+ loff_t len);
};
+#define IPERM_FLAG_RCU 0x0001
+
struct inode_operations {
- int (*create) (struct inode *,struct dentry *,int, struct nameidata *);
struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *);
+ void * (*follow_link) (struct dentry *, struct nameidata *);
+ int (*permission) (struct inode *, int, unsigned int);
+ int (*check_acl)(struct inode *, int, unsigned int);
+
+ int (*readlink) (struct dentry *, char __user *,int);
+ void (*put_link) (struct dentry *, struct nameidata *, void *);
+
+ int (*create) (struct inode *,struct dentry *,int, struct nameidata *);
int (*link) (struct dentry *,struct inode *,struct dentry *);
int (*unlink) (struct inode *,struct dentry *);
int (*symlink) (struct inode *,struct dentry *,const char *);
@@ -1094,11 +1594,7 @@
int (*mknod) (struct inode *,struct dentry *,int,dev_t);
int (*rename) (struct inode *, struct dentry *,
struct inode *, struct dentry *);
- int (*readlink) (struct dentry *, char __user *,int);
- void * (*follow_link) (struct dentry *, struct nameidata *);
- void (*put_link) (struct dentry *, struct nameidata *, void *);
void (*truncate) (struct inode *);
- int (*permission) (struct inode *, int, struct nameidata *);
int (*setattr) (struct dentry *, struct iattr *);
int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
@@ -1106,10 +1602,17 @@
ssize_t (*listxattr) (struct dentry *, char *, size_t);
int (*removexattr) (struct dentry *, const char *);
void (*truncate_range)(struct inode *, loff_t, loff_t);
-};
+ int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
+ u64 len);
+} ____cacheline_aligned;
struct seq_file;
+ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
+ unsigned long nr_segs, unsigned long fast_segs,
+ 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_write(struct file *, const char __user *, size_t, loff_t *);
extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
@@ -1117,48 +1620,93 @@
extern ssize_t vfs_writev(struct file *, const struct iovec __user *,
unsigned long, loff_t *);
-/*
- * NOTE: write_inode, delete_inode, clear_inode, put_inode can be called
- * without the big kernel lock held in all filesystems.
- */
struct super_operations {
struct inode *(*alloc_inode)(struct super_block *sb);
void (*destroy_inode)(struct inode *);
- void (*read_inode) (struct inode *);
-
- void (*dirty_inode) (struct inode *);
- int (*write_inode) (struct inode *, int);
- void (*put_inode) (struct inode *);
- void (*drop_inode) (struct inode *);
- void (*delete_inode) (struct inode *);
+ void (*dirty_inode) (struct inode *, int flags);
+ int (*write_inode) (struct inode *, struct writeback_control *wbc);
+ int (*drop_inode) (struct inode *);
+ void (*evict_inode) (struct inode *);
void (*put_super) (struct super_block *);
void (*write_super) (struct super_block *);
int (*sync_fs)(struct super_block *sb, int wait);
- void (*write_super_lockfs) (struct super_block *);
- void (*unlockfs) (struct super_block *);
+ int (*freeze_fs) (struct super_block *);
+ int (*unfreeze_fs) (struct super_block *);
int (*statfs) (struct dentry *, struct kstatfs *);
int (*remount_fs) (struct super_block *, int *, char *);
- void (*clear_inode) (struct inode *);
- void (*umount_begin) (struct vfsmount *, int);
+ void (*umount_begin) (struct super_block *);
int (*show_options)(struct seq_file *, struct vfsmount *);
+ int (*show_devname)(struct seq_file *, struct vfsmount *);
+ int (*show_path)(struct seq_file *, struct vfsmount *);
int (*show_stats)(struct seq_file *, struct vfsmount *);
-
+#ifdef CONFIG_QUOTA
ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
+#endif
+ int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
};
-/* Inode state bits. Protected by inode_lock. */
-#define I_DIRTY_SYNC 1 /* Not dirty enough for O_DATASYNC */
-#define I_DIRTY_DATASYNC 2 /* Data-related inode changes pending */
-#define I_DIRTY_PAGES 4 /* Data-related inode changes pending */
-#define __I_LOCK 3
-#define I_LOCK (1 << __I_LOCK)
-#define I_FREEING 16
-#define I_CLEAR 32
-#define I_NEW 64
-#define I_WILL_FREE 128
+/*
+ * Inode state bits. Protected by inode->i_lock
+ *
+ * Three bits determine the dirty state of the inode, I_DIRTY_SYNC,
+ * I_DIRTY_DATASYNC and I_DIRTY_PAGES.
+ *
+ * Four bits define the lifetime of an inode. Initially, inodes are I_NEW,
+ * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at
+ * various stages of removing an inode.
+ *
+ * Two bits are used for locking and completion notification, I_NEW and I_SYNC.
+ *
+ * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on
+ * fdatasync(). i_atime is the usual cause.
+ * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of
+ * these changes separately from I_DIRTY_SYNC so that we
+ * don't have to write inode on fdatasync() when only
+ * mtime has changed in it.
+ * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean.
+ * I_NEW Serves as both a mutex and completion notification.
+ * New inodes set I_NEW. If two processes both create
+ * the same inode, one of them will release its inode and
+ * wait for I_NEW to be released before returning.
+ * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can
+ * also cause waiting on I_NEW, without I_NEW actually
+ * being set. find_inode() uses this to prevent returning
+ * nearly-dead inodes.
+ * I_WILL_FREE Must be set when calling write_inode_now() if i_count
+ * is zero. I_FREEING must be set when I_WILL_FREE is
+ * cleared.
+ * I_FREEING Set when inode is about to be freed but still has dirty
+ * pages or buffers attached or the inode itself is still
+ * dirty.
+ * I_CLEAR Added by end_writeback(). In this state the inode is clean
+ * and can be destroyed. Inode keeps I_FREEING.
+ *
+ * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are
+ * prohibited for many purposes. iget() must wait for
+ * the inode to be completely released, then create it
+ * anew. Other functions will just ignore such inodes,
+ * if appropriate. I_NEW is used for waiting.
+ *
+ * I_SYNC Synchonized write of dirty inode data. The bits is
+ * set during data writeback, and cleared with a wakeup
+ * on the bit address once it is done.
+ *
+ * Q: What is the difference between I_WILL_FREE and I_FREEING?
+ */
+#define I_DIRTY_SYNC (1 << 0)
+#define I_DIRTY_DATASYNC (1 << 1)
+#define I_DIRTY_PAGES (1 << 2)
+#define __I_NEW 3
+#define I_NEW (1 << __I_NEW)
+#define I_WILL_FREE (1 << 4)
+#define I_FREEING (1 << 5)
+#define I_CLEAR (1 << 6)
+#define __I_SYNC 7
+#define I_SYNC (1 << __I_SYNC)
+#define I_REFERENCED (1 << 8)
#define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
@@ -1173,182 +1721,144 @@
__mark_inode_dirty(inode, I_DIRTY_SYNC);
}
-static inline void inode_inc_link_count(struct inode *inode)
+/**
+ * inc_nlink - directly increment an inode's link count
+ * @inode: inode
+ *
+ * This is a low-level filesystem helper to replace any
+ * direct filesystem manipulation of i_nlink. Currently,
+ * it is only here for parity with dec_nlink().
+ */
+static inline void inc_nlink(struct inode *inode)
{
inode->i_nlink++;
+}
+
+static inline void inode_inc_link_count(struct inode *inode)
+{
+ inc_nlink(inode);
mark_inode_dirty(inode);
}
+/**
+ * drop_nlink - directly drop an inode's link count
+ * @inode: inode
+ *
+ * This is a low-level filesystem helper to replace any
+ * direct filesystem manipulation of i_nlink. In cases
+ * where we are attempting to track writes to the
+ * filesystem, a decrement to zero means an imminent
+ * write when the file is truncated and actually unlinked
+ * on the filesystem.
+ */
+static inline void drop_nlink(struct inode *inode)
+{
+ inode->i_nlink--;
+}
+
+/**
+ * clear_nlink - directly zero an inode's link count
+ * @inode: inode
+ *
+ * This is a low-level filesystem helper to replace any
+ * direct filesystem manipulation of i_nlink. See
+ * drop_nlink() for why we care about i_nlink hitting zero.
+ */
+static inline void clear_nlink(struct inode *inode)
+{
+ inode->i_nlink = 0;
+}
+
static inline void inode_dec_link_count(struct inode *inode)
{
- inode->i_nlink--;
+ drop_nlink(inode);
mark_inode_dirty(inode);
}
+/**
+ * inode_inc_iversion - increments i_version
+ * @inode: inode that need to be updated
+ *
+ * Every time the inode is modified, the i_version field will be incremented.
+ * The filesystem has to be mounted with i_version flag
+ */
+
+static inline void inode_inc_iversion(struct inode *inode)
+{
+ spin_lock(&inode->i_lock);
+ inode->i_version++;
+ spin_unlock(&inode->i_lock);
+}
+
extern void touch_atime(struct vfsmount *mnt, struct dentry *dentry);
static inline void file_accessed(struct file *file)
{
if (!(file->f_flags & O_NOATIME))
- touch_atime(file->f_vfsmnt, file->f_dentry);
+ touch_atime(file->f_path.mnt, file->f_path.dentry);
}
int sync_inode(struct inode *inode, struct writeback_control *wbc);
-
-/**
- * struct export_operations - for nfsd to communicate with file systems
- * @decode_fh: decode a file handle fragment and return a &struct dentry
- * @encode_fh: encode a file handle fragment from a dentry
- * @get_name: find the name for a given inode in a given directory
- * @get_parent: find the parent of a given directory
- * @get_dentry: find a dentry for the inode given a file handle sub-fragment
- * @find_exported_dentry:
- * set by the exporting module to a standard helper function.
- *
- * Description:
- * The export_operations structure provides a means for nfsd to communicate
- * with a particular exported file system - particularly enabling nfsd and
- * the filesystem to co-operate when dealing with file handles.
- *
- * export_operations contains two basic operation for dealing with file
- * handles, decode_fh() and encode_fh(), and allows for some other
- * operations to be defined which standard helper routines use to get
- * specific information from the filesystem.
- *
- * nfsd encodes information use to determine which filesystem a filehandle
- * applies to in the initial part of the file handle. The remainder, termed
- * a file handle fragment, is controlled completely by the filesystem. The
- * standard helper routines assume that this fragment will contain one or
- * two sub-fragments, one which identifies the file, and one which may be
- * used to identify the (a) directory containing the file.
- *
- * In some situations, nfsd needs to get a dentry which is connected into a
- * specific part of the file tree. To allow for this, it passes the
- * function acceptable() together with a @context which can be used to see
- * if the dentry is acceptable. As there can be multiple dentrys for a
- * given file, the filesystem should check each one for acceptability before
- * looking for the next. As soon as an acceptable one is found, it should
- * be returned.
- *
- * decode_fh:
- * @decode_fh is given a &struct super_block (@sb), a file handle fragment
- * (@fh, @fh_len) and an acceptability testing function (@acceptable,
- * @context). It should return a &struct dentry which refers to the same
- * file that the file handle fragment refers to, and which passes the
- * acceptability test. If it cannot, it should return a %NULL pointer if
- * the file was found but no acceptable &dentries were available, or a
- * %ERR_PTR error code indicating why it couldn't be found (e.g. %ENOENT or
- * %ENOMEM).
- *
- * encode_fh:
- * @encode_fh should store in the file handle fragment @fh (using at most
- * @max_len bytes) information that can be used by @decode_fh to recover the
- * file refered to by the &struct dentry @de. If the @connectable flag is
- * set, the encode_fh() should store sufficient information so that a good
- * attempt can be made to find not only the file but also it's place in the
- * filesystem. This typically means storing a reference to de->d_parent in
- * the filehandle fragment. encode_fh() should return the number of bytes
- * stored or a negative error code such as %-ENOSPC
- *
- * get_name:
- * @get_name should find a name for the given @child in the given @parent
- * directory. The name should be stored in the @name (with the
- * understanding that it is already pointing to a a %NAME_MAX+1 sized
- * buffer. get_name() should return %0 on success, a negative error code
- * or error. @get_name will be called without @parent->i_mutex held.
- *
- * get_parent:
- * @get_parent should find the parent directory for the given @child which
- * is also a directory. In the event that it cannot be found, or storage
- * space cannot be allocated, a %ERR_PTR should be returned.
- *
- * get_dentry:
- * Given a &super_block (@sb) and a pointer to a file-system specific inode
- * identifier, possibly an inode number, (@inump) get_dentry() should find
- * the identified inode and return a dentry for that inode. Any suitable
- * dentry can be returned including, if necessary, a new dentry created with
- * d_alloc_root. The caller can then find any other extant dentrys by
- * following the d_alias links. If a new dentry was created using
- * d_alloc_root, DCACHE_NFSD_DISCONNECTED should be set, and the dentry
- * should be d_rehash()ed.
- *
- * If the inode cannot be found, either a %NULL pointer or an %ERR_PTR code
- * can be returned. The @inump will be whatever was passed to
- * nfsd_find_fh_dentry() in either the @obj or @parent parameters.
- *
- * Locking rules:
- * get_parent is called with child->d_inode->i_mutex down
- * get_name is not (which is possibly inconsistent)
- */
-
-struct export_operations {
- struct dentry *(*decode_fh)(struct super_block *sb, __u32 *fh, int fh_len, int fh_type,
- int (*acceptable)(void *context, struct dentry *de),
- void *context);
- int (*encode_fh)(struct dentry *de, __u32 *fh, int *max_len,
- int connectable);
-
- /* the following are only called from the filesystem itself */
- int (*get_name)(struct dentry *parent, char *name,
- struct dentry *child);
- struct dentry * (*get_parent)(struct dentry *child);
- struct dentry * (*get_dentry)(struct super_block *sb, void *inump);
-
- /* This is set by the exporting module to a standard helper */
- struct dentry * (*find_exported_dentry)(
- struct super_block *sb, void *obj, void *parent,
- int (*acceptable)(void *context, struct dentry *de),
- void *context);
-
-
-};
-
-extern struct dentry *
-find_exported_dentry(struct super_block *sb, void *obj, void *parent,
- int (*acceptable)(void *context, struct dentry *de),
- void *context);
+int sync_inode_metadata(struct inode *inode, int wait);
struct file_system_type {
const char *name;
int fs_flags;
- int (*get_sb) (struct file_system_type *, int,
- const char *, void *, struct vfsmount *);
+ struct dentry *(*mount) (struct file_system_type *, int,
+ const char *, void *);
void (*kill_sb) (struct super_block *);
struct module *owner;
struct file_system_type * next;
struct list_head fs_supers;
+
struct lock_class_key s_lock_key;
struct lock_class_key s_umount_key;
+ struct lock_class_key s_vfs_rename_key;
+
+ struct lock_class_key i_lock_key;
+ struct lock_class_key i_mutex_key;
+ struct lock_class_key i_mutex_dir_key;
+ struct lock_class_key i_alloc_sem_key;
};
-extern int get_sb_bdev(struct file_system_type *fs_type,
+extern struct dentry *mount_ns(struct file_system_type *fs_type, int flags,
+ void *data, int (*fill_super)(struct super_block *, void *, int));
+extern struct dentry *mount_bdev(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data,
- int (*fill_super)(struct super_block *, void *, int),
- struct vfsmount *mnt);
-extern int get_sb_single(struct file_system_type *fs_type,
+ int (*fill_super)(struct super_block *, void *, int));
+extern struct dentry *mount_single(struct file_system_type *fs_type,
int flags, void *data,
- int (*fill_super)(struct super_block *, void *, int),
- struct vfsmount *mnt);
-extern int get_sb_nodev(struct file_system_type *fs_type,
+ int (*fill_super)(struct super_block *, void *, int));
+extern struct dentry *mount_nodev(struct file_system_type *fs_type,
int flags, void *data,
- int (*fill_super)(struct super_block *, void *, int),
- struct vfsmount *mnt);
+ int (*fill_super)(struct super_block *, void *, int));
void generic_shutdown_super(struct super_block *sb);
void kill_block_super(struct super_block *sb);
void kill_anon_super(struct super_block *sb);
void kill_litter_super(struct super_block *sb);
void deactivate_super(struct super_block *sb);
+void deactivate_locked_super(struct super_block *sb);
int set_anon_super(struct super_block *s, void *data);
struct super_block *sget(struct file_system_type *type,
int (*test)(struct super_block *,void *),
int (*set)(struct super_block *,void *),
void *data);
-extern int get_sb_pseudo(struct file_system_type *, char *,
- struct super_operations *ops, unsigned long,
- struct vfsmount *mnt);
-extern int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb);
-int __put_super(struct super_block *sb);
-int __put_super_and_need_restart(struct super_block *sb);
-void unnamed_dev_init(void);
+extern struct dentry *mount_pseudo(struct file_system_type *, char *,
+ const struct super_operations *ops,
+ const struct dentry_operations *dops,
+ unsigned long);
+
+static inline void sb_mark_dirty(struct super_block *sb)
+{
+ sb->s_dirt = 1;
+}
+static inline void sb_mark_clean(struct super_block *sb)
+{
+ sb->s_dirt = 0;
+}
+static inline int sb_is_dirty(struct super_block *sb)
+{
+ return sb->s_dirt;
+}
/* Alas, no aliases. Too much hassle with bringing module.h everywhere */
#define fops_get(fops) \
@@ -1358,24 +1868,35 @@
extern int register_filesystem(struct file_system_type *);
extern int unregister_filesystem(struct file_system_type *);
-extern struct vfsmount *kern_mount(struct file_system_type *);
+extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
+#define kern_mount(type) kern_mount_data(type, NULL)
extern int may_umount_tree(struct vfsmount *);
extern int may_umount(struct vfsmount *);
-extern void umount_tree(struct vfsmount *, int, struct list_head *);
-extern void release_mounts(struct list_head *);
extern long do_mount(char *, char *, char *, unsigned long, void *);
-extern struct vfsmount *copy_tree(struct vfsmount *, struct dentry *, int);
-extern void mnt_set_mountpoint(struct vfsmount *, struct dentry *,
- struct vfsmount *);
+extern struct vfsmount *collect_mounts(struct path *);
+extern void drop_collected_mounts(struct vfsmount *);
+extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
+ struct vfsmount *);
+extern int vfs_statfs(struct path *, struct kstatfs *);
+extern int user_statfs(const char __user *, struct kstatfs *);
+extern int fd_statfs(int, struct kstatfs *);
+extern int statfs_by_dentry(struct dentry *, struct kstatfs *);
+extern int freeze_super(struct super_block *super);
+extern int thaw_super(struct super_block *super);
+extern bool our_mnt(struct vfsmount *mnt);
-extern int vfs_statfs(struct dentry *, struct kstatfs *);
+extern int current_umask(void);
/* /sys/fs */
-extern struct subsystem fs_subsys;
+extern struct kobject *fs_kobj;
+
+#define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK)
+extern int rw_verify_area(int, struct file *, loff_t *, size_t);
#define FLOCK_VERIFY_READ 1
#define FLOCK_VERIFY_WRITE 2
+#ifdef CONFIG_FILE_LOCKING
extern int locks_mandatory_locked(struct inode *);
extern int locks_mandatory_area(int, struct inode *, struct file *, loff_t, size_t);
@@ -1383,23 +1904,34 @@
* Candidates for mandatory locking have the setgid bit set
* but no group execute bit - an otherwise meaningless combination.
*/
-#define MANDATORY_LOCK(inode) \
- (IS_MANDLOCK(inode) && ((inode)->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID)
+
+static inline int __mandatory_lock(struct inode *ino)
+{
+ return (ino->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID;
+}
+
+/*
+ * ... and these candidates should be on MS_MANDLOCK mounted fs,
+ * otherwise these will be advisory locks
+ */
+
+static inline int mandatory_lock(struct inode *ino)
+{
+ return IS_MANDLOCK(ino) && __mandatory_lock(ino);
+}
static inline int locks_verify_locked(struct inode *inode)
{
- if (MANDATORY_LOCK(inode))
+ if (mandatory_lock(inode))
return locks_mandatory_locked(inode);
return 0;
}
-extern int rw_verify_area(int, struct file *, loff_t *, size_t);
-
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_flock && mandatory_lock(inode))
return locks_mandatory_area(
FLOCK_VERIFY_WRITE, inode, filp,
size < inode->i_size ? size : inode->i_size,
@@ -1415,92 +1947,194 @@
return __break_lease(inode, mode);
return 0;
}
+#else /* !CONFIG_FILE_LOCKING */
+static inline int locks_mandatory_locked(struct inode *inode)
+{
+ return 0;
+}
+
+static inline int locks_mandatory_area(int rw, struct inode *inode,
+ struct file *filp, loff_t offset,
+ size_t count)
+{
+ return 0;
+}
+
+static inline int __mandatory_lock(struct inode *inode)
+{
+ return 0;
+}
+
+static inline int mandatory_lock(struct inode *inode)
+{
+ return 0;
+}
+
+static inline int locks_verify_locked(struct inode *inode)
+{
+ return 0;
+}
+
+static inline int locks_verify_truncate(struct inode *inode, struct file *filp,
+ size_t size)
+{
+ return 0;
+}
+
+static inline int break_lease(struct inode *inode, unsigned int mode)
+{
+ return 0;
+}
+
+#endif /* CONFIG_FILE_LOCKING */
/* fs/open.c */
extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
struct file *filp);
-extern long do_sys_open(int fdf, const char __user *filename, int flags,
+extern int do_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,
int mode);
extern struct file *filp_open(const char *, int, int);
-extern struct file * dentry_open(struct dentry *, struct vfsmount *, int);
+extern struct file *file_open_root(struct dentry *, struct vfsmount *,
+ const char *, int);
+extern struct file * dentry_open(struct dentry *, struct vfsmount *, int,
+ const struct cred *);
extern int filp_close(struct file *, fl_owner_t id);
extern char * getname(const char __user *);
+/* fs/ioctl.c */
+
+extern int ioctl_preallocate(struct file *filp, void __user *argp);
+
/* fs/dcache.c */
extern void __init vfs_caches_init_early(void);
extern void __init vfs_caches_init(unsigned long);
-#define __getname() kmem_cache_alloc(names_cachep, SLAB_KERNEL)
-#define __putname(name) kmem_cache_free(names_cachep, (void *)(name))
+extern struct kmem_cache *names_cachep;
+
+#define __getname_gfp(gfp) kmem_cache_alloc(names_cachep, (gfp))
+#define __getname() __getname_gfp(GFP_KERNEL)
+#define __putname(name) kmem_cache_free(names_cachep, (void *)(name))
#ifndef CONFIG_AUDITSYSCALL
#define putname(name) __putname(name)
#else
extern void putname(const char *name);
#endif
+#ifdef CONFIG_BLOCK
extern int register_blkdev(unsigned int, const char *);
-extern int unregister_blkdev(unsigned int, const char *);
+extern void unregister_blkdev(unsigned int, const char *);
extern struct block_device *bdget(dev_t);
+extern struct block_device *bdgrab(struct block_device *bdev);
extern void bd_set_size(struct block_device *, loff_t size);
extern void bd_forget(struct inode *inode);
extern void bdput(struct block_device *);
-extern struct block_device *open_by_devnum(dev_t, unsigned);
-extern struct block_device *open_partition_by_devnum(dev_t, unsigned);
+extern void invalidate_bdev(struct block_device *);
+extern int sync_blockdev(struct block_device *bdev);
+extern struct super_block *freeze_bdev(struct block_device *);
+extern void emergency_thaw_all(void);
+extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
+extern int fsync_bdev(struct block_device *);
+#else
+static inline void bd_forget(struct inode *inode) {}
+static inline int sync_blockdev(struct block_device *bdev) { return 0; }
+static inline void invalidate_bdev(struct block_device *bdev) {}
+
+static inline struct super_block *freeze_bdev(struct block_device *sb)
+{
+ return NULL;
+}
+
+static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb)
+{
+ return 0;
+}
+#endif
+extern int sync_filesystem(struct super_block *);
extern const struct file_operations def_blk_fops;
-extern const struct address_space_operations def_blk_aops;
extern const struct file_operations def_chr_fops;
extern const struct file_operations bad_sock_fops;
extern const struct file_operations def_fifo_fops;
+#ifdef CONFIG_BLOCK
extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
-extern int blkdev_ioctl(struct inode *, struct file *, unsigned, unsigned long);
+extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
-extern int blkdev_get(struct block_device *, mode_t, unsigned);
-extern int blkdev_put(struct block_device *);
-extern int blkdev_put_partition(struct block_device *);
-extern int bd_claim(struct block_device *, void *);
-extern void bd_release(struct block_device *);
+extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder);
+extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
+ void *holder);
+extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode,
+ void *holder);
+extern int blkdev_put(struct block_device *bdev, fmode_t mode);
#ifdef CONFIG_SYSFS
-extern int bd_claim_by_disk(struct block_device *, void *, struct gendisk *);
-extern void bd_release_from_disk(struct block_device *, struct gendisk *);
+extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
+extern void bd_unlink_disk_holder(struct block_device *bdev,
+ struct gendisk *disk);
#else
-#define bd_claim_by_disk(bdev, holder, disk) bd_claim(bdev, holder)
-#define bd_release_from_disk(bdev, disk) bd_release(bdev)
+static inline int bd_link_disk_holder(struct block_device *bdev,
+ struct gendisk *disk)
+{
+ return 0;
+}
+static inline void bd_unlink_disk_holder(struct block_device *bdev,
+ struct gendisk *disk)
+{
+}
+#endif
#endif
/* fs/char_dev.c */
#define CHRDEV_MAJOR_HASH_SIZE 255
extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *);
extern int register_chrdev_region(dev_t, unsigned, const char *);
-extern int register_chrdev(unsigned int, const char *,
- const struct file_operations *);
-extern int unregister_chrdev(unsigned int, const char *);
+extern int __register_chrdev(unsigned int major, unsigned int baseminor,
+ unsigned int count, const char *name,
+ const struct file_operations *fops);
+extern void __unregister_chrdev(unsigned int major, unsigned int baseminor,
+ unsigned int count, const char *name);
extern void unregister_chrdev_region(dev_t, unsigned);
-extern int chrdev_open(struct inode *, struct file *);
extern void chrdev_show(struct seq_file *,off_t);
+static inline int register_chrdev(unsigned int major, const char *name,
+ const struct file_operations *fops)
+{
+ return __register_chrdev(major, 0, 256, name, fops);
+}
+
+static inline void unregister_chrdev(unsigned int major, const char *name)
+{
+ __unregister_chrdev(major, 0, 256, name);
+}
+
/* fs/block_dev.c */
-#define BLKDEV_MAJOR_HASH_SIZE 255
#define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */
+#define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */
+
+#ifdef CONFIG_BLOCK
+#define BLKDEV_MAJOR_HASH_SIZE 255
extern const char *__bdevname(dev_t, char *buffer);
extern const char *bdevname(struct block_device *bdev, char *buffer);
extern struct block_device *lookup_bdev(const char *);
-extern struct block_device *open_bdev_excl(const char *, int, void *);
-extern void close_bdev_excl(struct block_device *);
extern void blkdev_show(struct seq_file *,off_t);
+#else
+#define BLKDEV_MAJOR_HASH_SIZE 0
+#endif
+
extern void init_special_inode(struct inode *, umode_t, dev_t);
/* Invalid inode operations -- fs/bad_inode.c */
extern void make_bad_inode(struct inode *);
extern int is_bad_inode(struct inode *);
-extern const struct file_operations read_fifo_fops;
-extern const struct file_operations write_fifo_fops;
-extern const struct file_operations rdwr_fifo_fops;
+extern const struct file_operations read_pipefifo_fops;
+extern const struct file_operations write_pipefifo_fops;
+extern const struct file_operations rdwr_pipefifo_fops;
extern int fs_may_remount_ro(struct super_block *);
+#ifdef CONFIG_BLOCK
/*
* return READ, READA, or WRITE
*/
@@ -1511,18 +2145,21 @@
*/
#define bio_data_dir(bio) ((bio)->bi_rw & 1)
+extern void check_disk_size_change(struct gendisk *disk,
+ struct block_device *bdev);
+extern int revalidate_disk(struct gendisk *);
extern int check_disk_change(struct block_device *);
-extern int invalidate_inodes(struct super_block *);
-extern int __invalidate_device(struct block_device *);
+extern int __invalidate_device(struct block_device *, bool);
extern int invalidate_partition(struct gendisk *, int);
+#endif
unsigned long invalidate_mapping_pages(struct address_space *mapping,
pgoff_t start, pgoff_t end);
-unsigned long invalidate_inode_pages(struct address_space *mapping);
+
static inline void invalidate_remote_inode(struct inode *inode)
{
if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode))
- invalidate_inode_pages(inode->i_mapping);
+ invalidate_mapping_pages(inode->i_mapping, 0, -1);
}
extern int invalidate_inode_pages2(struct address_space *mapping);
extern int invalidate_inode_pages2_range(struct address_space *mapping,
@@ -1531,26 +2168,35 @@
extern int filemap_fdatawrite(struct address_space *);
extern int filemap_flush(struct address_space *);
extern int filemap_fdatawait(struct address_space *);
+extern int filemap_fdatawait_range(struct address_space *, loff_t lstart,
+ loff_t lend);
extern int filemap_write_and_wait(struct address_space *mapping);
extern int filemap_write_and_wait_range(struct address_space *mapping,
loff_t lstart, loff_t lend);
-extern int wait_on_page_writeback_range(struct address_space *mapping,
- pgoff_t start, pgoff_t end);
extern int __filemap_fdatawrite_range(struct address_space *mapping,
loff_t start, loff_t end, int sync_mode);
+extern int filemap_fdatawrite_range(struct address_space *mapping,
+ loff_t start, loff_t end);
-extern long do_fsync(struct file *file, int datasync);
+extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end,
+ int datasync);
+extern int vfs_fsync(struct file *file, int datasync);
+extern int generic_write_sync(struct file *file, loff_t pos, loff_t count);
extern void sync_supers(void);
-extern void sync_filesystems(int wait);
extern void emergency_sync(void);
extern void emergency_remount(void);
-extern int do_remount_sb(struct super_block *sb, int flags,
- void *data, int force);
+#ifdef CONFIG_BLOCK
extern sector_t bmap(struct inode *, sector_t);
+#endif
extern int notify_change(struct dentry *, struct iattr *);
-extern int permission(struct inode *, int, struct nameidata *);
-extern int generic_permission(struct inode *, int,
- int (*check_acl)(struct inode *, int));
+extern int inode_permission(struct inode *, int);
+extern int generic_permission(struct inode *, int, unsigned int,
+ int (*check_acl)(struct inode *, int, unsigned int));
+
+static inline bool execute_ok(struct inode *inode)
+{
+ return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode);
+}
extern int get_write_access(struct inode *);
extern int deny_write_access(struct file *);
@@ -1561,18 +2207,39 @@
static inline void allow_write_access(struct file *file)
{
if (file)
- atomic_inc(&file->f_dentry->d_inode->i_writecount);
+ atomic_inc(&file->f_path.dentry->d_inode->i_writecount);
}
-extern int do_pipe(int *);
+#ifdef CONFIG_IMA
+static inline void i_readcount_dec(struct inode *inode)
+{
+ BUG_ON(!atomic_read(&inode->i_readcount));
+ atomic_dec(&inode->i_readcount);
+}
+static inline void i_readcount_inc(struct inode *inode)
+{
+ atomic_inc(&inode->i_readcount);
+}
+#else
+static inline void i_readcount_dec(struct inode *inode)
+{
+ return;
+}
+static inline void i_readcount_inc(struct inode *inode)
+{
+ return;
+}
+#endif
+extern int do_pipe_flags(int *, int);
+extern struct file *create_read_pipe(struct file *f, int flags);
+extern struct file *create_write_pipe(int flags);
+extern void free_write_pipe(struct file *);
-extern int open_namei(int dfd, const char *, int, int, struct nameidata *);
-extern int may_open(struct nameidata *, int, int);
-
-extern int kernel_read(struct file *, unsigned long, char *, unsigned long);
+extern int kernel_read(struct file *, loff_t, char *, unsigned long);
extern struct file * open_exec(const char *);
/* fs/dcache.c -- generic fs support functions */
extern int is_subdir(struct dentry *, struct dentry *);
+extern int path_is_under(struct path *, struct path *);
extern ino_t find_inode_number(struct dentry *, struct qstr *);
#include <linux/err.h>
@@ -1582,13 +2249,16 @@
extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin);
+extern int inode_init_always(struct super_block *, struct inode *);
extern void inode_init_once(struct inode *);
+extern void address_space_init_once(struct address_space *mapping);
+extern void ihold(struct inode * inode);
extern void iput(struct inode *);
extern struct inode * igrab(struct inode *);
extern ino_t iunique(struct super_block *, ino_t);
extern int inode_needs_sync(struct inode *inode);
-extern void generic_delete_inode(struct inode *inode);
-extern void generic_drop_inode(struct inode *inode);
+extern int generic_delete_inode(struct inode *inode);
+extern int generic_drop_inode(struct inode *inode);
extern struct inode *ilookup5_nowait(struct super_block *sb,
unsigned long hashval, int (*test)(struct inode *, void *),
@@ -1599,39 +2269,32 @@
extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *);
extern struct inode * iget_locked(struct super_block *, unsigned long);
+extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *);
+extern int insert_inode_locked(struct inode *);
extern void unlock_new_inode(struct inode *);
-
-static inline struct inode *iget(struct super_block *sb, unsigned long ino)
-{
- struct inode *inode = iget_locked(sb, ino);
-
- if (inode && (inode->i_state & I_NEW)) {
- sb->s_op->read_inode(inode);
- unlock_new_inode(inode);
- }
-
- return inode;
-}
+extern unsigned int get_next_ino(void);
extern void __iget(struct inode * inode);
-extern void clear_inode(struct inode *);
-extern void destroy_inode(struct inode *);
+extern void iget_failed(struct inode *);
+extern void end_writeback(struct inode *);
+extern void __destroy_inode(struct inode *);
extern struct inode *new_inode(struct super_block *);
-extern int remove_suid(struct dentry *);
-extern void remove_dquot_ref(struct super_block *, int, struct list_head *);
+extern void free_inode_nonrcu(struct inode *inode);
+extern int should_remove_suid(struct dentry *);
+extern int file_remove_suid(struct file *);
extern void __insert_inode_hash(struct inode *, unsigned long hashval);
extern void remove_inode_hash(struct inode *);
-static inline void insert_inode_hash(struct inode *inode) {
+static inline void insert_inode_hash(struct inode *inode)
+{
__insert_inode_hash(inode, inode->i_ino);
}
+extern void inode_sb_list_add(struct inode *inode);
-extern struct file * get_empty_filp(void);
-extern void file_move(struct file *f, struct list_head *list);
-extern void file_kill(struct file *f);
-struct bio;
+#ifdef CONFIG_BLOCK
extern void submit_bio(int, struct bio *);
extern int bdev_read_only(struct block_device *);
+#endif
extern int set_blocksize(struct block_device *, int);
extern int sb_set_blocksize(struct super_block *, int);
extern int sb_min_blocksize(struct super_block *, int);
@@ -1639,31 +2302,30 @@
extern int generic_file_mmap(struct file *, struct vm_area_struct *);
extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size);
-extern int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size);
-extern ssize_t generic_file_read(struct file *, char __user *, size_t, loff_t *);
int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
-extern ssize_t generic_file_write(struct file *, const char __user *, size_t, loff_t *);
-extern ssize_t generic_file_aio_read(struct kiocb *, char __user *, size_t, loff_t);
-extern ssize_t __generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t *);
-extern ssize_t generic_file_aio_write(struct kiocb *, const char __user *, size_t, loff_t);
-extern ssize_t generic_file_aio_write_nolock(struct kiocb *, const struct iovec *,
- unsigned long, loff_t *);
+extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
+extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long,
+ loff_t *);
+extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *,
unsigned long *, loff_t, loff_t *, size_t, size_t);
extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *,
unsigned long, loff_t, loff_t *, size_t, ssize_t);
extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
-ssize_t generic_file_write_nolock(struct file *file, const struct iovec *iov,
- unsigned long nr_segs, loff_t *ppos);
-extern ssize_t generic_file_sendfile(struct file *, loff_t *, size_t, read_actor_t, void *);
-extern void do_generic_mapping_read(struct address_space *mapping,
- struct file_ra_state *, struct file *,
- loff_t *, read_descriptor_t *, read_actor_t);
+extern int generic_segment_checks(const struct iovec *iov,
+ unsigned long *nr_segs, size_t *count, int access_flags);
+
+/* fs/block_dev.c */
+extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos);
+extern int blkdev_fsync(struct file *filp, int datasync);
/* fs/splice.c */
extern ssize_t generic_file_splice_read(struct file *, loff_t *,
struct pipe_inode_info *, size_t, unsigned int);
+extern ssize_t default_file_splice_read(struct file *, loff_t *,
+ struct pipe_inode_info *, size_t, unsigned int);
extern ssize_t generic_file_splice_write(struct pipe_inode_info *,
struct file *, loff_t *, size_t, unsigned int);
extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
@@ -1673,22 +2335,17 @@
extern void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
-extern ssize_t generic_file_readv(struct file *filp, const struct iovec *iov,
- unsigned long nr_segs, loff_t *ppos);
-ssize_t generic_file_writev(struct file *filp, const struct iovec *iov,
- unsigned long nr_segs, loff_t *ppos);
+extern loff_t noop_llseek(struct file *file, loff_t offset, int origin);
extern loff_t no_llseek(struct file *file, loff_t offset, int origin);
extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin);
-extern loff_t remote_llseek(struct file *file, loff_t offset, int origin);
+extern loff_t generic_file_llseek_unlocked(struct file *file, loff_t offset,
+ int origin);
extern int generic_file_open(struct inode * inode, struct file * filp);
extern int nonseekable_open(struct inode * inode, struct file * filp);
#ifdef CONFIG_FS_XIP
extern ssize_t xip_file_read(struct file *filp, char __user *buf, size_t len,
loff_t *ppos);
-extern ssize_t xip_file_sendfile(struct file *in_file, loff_t *ppos,
- size_t count, read_actor_t actor,
- void *target);
extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma);
extern ssize_t xip_file_write(struct file *filp, const char __user *buf,
size_t len, loff_t *ppos);
@@ -1700,28 +2357,24 @@
}
#endif
-static inline void do_generic_file_read(struct file * filp, loff_t *ppos,
- read_descriptor_t * desc,
- read_actor_t actor)
-{
- do_generic_mapping_read(filp->f_mapping,
- &filp->f_ra,
- filp,
- ppos,
- desc,
- actor);
-}
+#ifdef CONFIG_BLOCK
+typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode,
+ loff_t file_offset);
+
+enum {
+ /* need locking between buffered and direct access */
+ DIO_LOCKING = 0x01,
+
+ /* filesystem does not support filling holes */
+ DIO_SKIP_HOLES = 0x02,
+};
+
+void dio_end_io(struct bio *bio, int error);
ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
struct block_device *bdev, const struct iovec *iov, loff_t offset,
unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
- int lock_type);
-
-enum {
- DIO_LOCKING = 1, /* need locking between buffered and direct access */
- DIO_NO_LOCKING, /* bdev; no locking at all between buffered/direct */
- DIO_OWN_LOCKING, /* filesystem locks buffered and direct internally */
-};
+ dio_submit_t submit_io, int flags);
static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
struct inode *inode, struct block_device *bdev, const struct iovec *iov,
@@ -1729,26 +2382,10 @@
dio_iodone_t end_io)
{
return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
- nr_segs, get_block, end_io, DIO_LOCKING);
+ nr_segs, get_block, end_io, NULL,
+ DIO_LOCKING | DIO_SKIP_HOLES);
}
-
-static inline ssize_t blockdev_direct_IO_no_locking(int rw, struct kiocb *iocb,
- struct inode *inode, struct block_device *bdev, const struct iovec *iov,
- loff_t offset, unsigned long nr_segs, get_block_t get_block,
- dio_iodone_t end_io)
-{
- return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
- nr_segs, get_block, end_io, DIO_NO_LOCKING);
-}
-
-static inline ssize_t blockdev_direct_IO_own_locking(int rw, struct kiocb *iocb,
- struct inode *inode, struct block_device *bdev, const struct iovec *iov,
- loff_t offset, unsigned long nr_segs, get_block_t get_block,
- dio_iodone_t end_io)
-{
- return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
- nr_segs, get_block, end_io, DIO_OWN_LOCKING);
-}
+#endif
extern const struct file_operations generic_ro_fops;
@@ -1760,12 +2397,13 @@
extern void *page_follow_link_light(struct dentry *, struct nameidata *);
extern void page_put_link(struct dentry *, struct nameidata *, void *);
extern int __page_symlink(struct inode *inode, const char *symname, int len,
- gfp_t gfp_mask);
+ int nofs);
extern int page_symlink(struct inode *inode, const char *symname, int len);
-extern struct inode_operations page_symlink_inode_operations;
+extern const struct inode_operations page_symlink_inode_operations;
extern int generic_readlink(struct dentry *, char __user *, int);
extern void generic_fillattr(struct inode *, struct kstat *);
extern int vfs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+void __inode_add_bytes(struct inode *inode, loff_t bytes);
void inode_add_bytes(struct inode *inode, loff_t bytes);
void inode_sub_bytes(struct inode *inode, loff_t bytes);
loff_t inode_get_bytes(struct inode *inode);
@@ -1773,48 +2411,69 @@
extern int vfs_readdir(struct file *, filldir_t, void *);
-extern int vfs_stat(char __user *, struct kstat *);
-extern int vfs_lstat(char __user *, struct kstat *);
-extern int vfs_stat_fd(int dfd, char __user *, struct kstat *);
-extern int vfs_lstat_fd(int dfd, char __user *, struct kstat *);
+extern int vfs_stat(const char __user *, struct kstat *);
+extern int vfs_lstat(const char __user *, struct kstat *);
extern int vfs_fstat(unsigned int, struct kstat *);
+extern int vfs_fstatat(int , const char __user *, struct kstat *, int);
-extern int vfs_ioctl(struct file *, unsigned int, unsigned int, unsigned long);
+extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
+ unsigned long arg);
+extern int __generic_block_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo,
+ loff_t start, loff_t len,
+ get_block_t *get_block);
+extern int generic_block_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo, u64 start,
+ u64 len, get_block_t *get_block);
+extern void get_filesystem(struct file_system_type *fs);
+extern void put_filesystem(struct file_system_type *fs);
extern struct file_system_type *get_fs_type(const char *name);
extern struct super_block *get_super(struct block_device *);
+extern struct super_block *get_active_super(struct block_device *bdev);
extern struct super_block *user_get_super(dev_t);
extern void drop_super(struct super_block *sb);
+extern void iterate_supers(void (*)(struct super_block *, void *), void *);
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 *, void *, filldir_t);
+extern int simple_setattr(struct dentry *, struct iattr *);
extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *);
extern int simple_statfs(struct dentry *, struct kstatfs *);
extern int simple_link(struct dentry *, struct inode *, struct dentry *);
extern int simple_unlink(struct inode *, struct dentry *);
extern int simple_rmdir(struct inode *, struct dentry *);
extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
-extern int simple_sync_file(struct file *, struct dentry *, int);
+extern int noop_fsync(struct file *, int);
extern int simple_empty(struct dentry *);
extern int simple_readpage(struct file *file, struct page *page);
-extern int simple_prepare_write(struct file *file, struct page *page,
- unsigned offset, unsigned to);
-extern int simple_commit_write(struct file *file, struct page *page,
- unsigned offset, unsigned to);
+extern int simple_write_begin(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned flags,
+ struct page **pagep, void **fsdata);
+extern int simple_write_end(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata);
extern struct dentry *simple_lookup(struct inode *, struct dentry *, struct nameidata *);
extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
extern const struct file_operations simple_dir_operations;
-extern struct inode_operations simple_dir_inode_operations;
+extern const struct inode_operations simple_dir_inode_operations;
struct tree_descr { char *name; const struct file_operations *ops; int mode; };
struct dentry *d_alloc_name(struct dentry *, const char *);
-extern int simple_fill_super(struct super_block *, int, struct tree_descr *);
+extern int simple_fill_super(struct super_block *, unsigned long, struct tree_descr *);
extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count);
extern void simple_release_fs(struct vfsmount **mount, int *count);
-extern ssize_t simple_read_from_buffer(void __user *, size_t, loff_t *, const void *, size_t);
+extern ssize_t simple_read_from_buffer(void __user *to, size_t count,
+ loff_t *ppos, const void *from, size_t available);
+extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
+ const void __user *from, size_t count);
+
+extern int generic_file_fsync(struct file *, int);
+
+extern int generic_check_addressable(unsigned, u64);
#ifdef CONFIG_MIGRATION
extern int buffer_migrate_page(struct address_space *,
@@ -1823,24 +2482,30 @@
#define buffer_migrate_page NULL
#endif
-extern int inode_change_ok(struct inode *, struct iattr *);
-extern int __must_check inode_setattr(struct inode *, struct iattr *);
+extern int inode_change_ok(const struct inode *, struct iattr *);
+extern int inode_newsize_ok(const struct inode *, loff_t offset);
+extern void setattr_copy(struct inode *inode, const struct iattr *attr);
extern void file_update_time(struct file *file);
+extern int generic_show_options(struct seq_file *m, struct vfsmount *mnt);
+extern void save_mount_options(struct super_block *sb, char *options);
+extern void replace_mount_options(struct super_block *sb, char *options);
+
static inline ino_t parent_ino(struct dentry *dentry)
{
ino_t res;
+ /*
+ * Don't strictly need d_lock here? If the parent ino could change
+ * then surely we'd have a deeper race in the caller?
+ */
spin_lock(&dentry->d_lock);
res = dentry->d_parent->d_inode->i_ino;
spin_unlock(&dentry->d_lock);
return res;
}
-/* kernel/fork.c */
-extern int unshare_files(void);
-
/* Transaction based IO helpers */
/*
@@ -1860,19 +2525,7 @@
size_t size, loff_t *pos);
int simple_transaction_release(struct inode *inode, struct file *file);
-static inline void simple_transaction_set(struct file *file, size_t n)
-{
- struct simple_transaction_argresp *ar = file->private_data;
-
- BUG_ON(n > SIMPLE_TRANSACTION_LIMIT);
-
- /*
- * The barrier ensures that ar->size will really remain zero until
- * ar->data is ready for reading.
- */
- smp_mb();
- ar->size = n;
-}
+void simple_transaction_set(struct file *file, size_t n);
/*
* simple attribute files
@@ -1896,12 +2549,13 @@
__simple_attr_check_format(__fmt, 0ull); \
return simple_attr_open(inode, file, __get, __set, __fmt); \
} \
-static struct file_operations __fops = { \
+static const struct file_operations __fops = { \
.owner = THIS_MODULE, \
.open = __fops ## _open, \
- .release = simple_attr_close, \
+ .release = simple_attr_release, \
.read = simple_attr_read, \
.write = simple_attr_write, \
+ .llseek = generic_file_llseek, \
};
static inline void __attribute__((format(printf, 1, 2)))
@@ -1911,34 +2565,40 @@
}
int simple_attr_open(struct inode *inode, struct file *file,
- u64 (*get)(void *), void (*set)(void *, u64),
+ int (*get)(void *, u64 *), int (*set)(void *, u64),
const char *fmt);
-int simple_attr_close(struct inode *inode, struct file *file);
+int simple_attr_release(struct inode *inode, struct file *file);
ssize_t simple_attr_read(struct file *file, char __user *buf,
size_t len, loff_t *ppos);
ssize_t simple_attr_write(struct file *file, const char __user *buf,
size_t len, loff_t *ppos);
+struct ctl_table;
+int proc_nr_files(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos);
+int proc_nr_dentry(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos);
+int proc_nr_inodes(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos);
+int __init get_filesystem_list(char *buf);
-#ifdef CONFIG_SECURITY
-static inline char *alloc_secdata(void)
+#define __FMODE_EXEC ((__force int) FMODE_EXEC)
+#define __FMODE_NONOTIFY ((__force int) FMODE_NONOTIFY)
+
+#define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE])
+#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \
+ (flag & __FMODE_NONOTIFY)))
+
+static inline int is_sxid(mode_t mode)
{
- return (char *)get_zeroed_page(GFP_KERNEL);
+ return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP));
}
-static inline void free_secdata(void *secdata)
+static inline void inode_has_no_xattr(struct inode *inode)
{
- free_page((unsigned long)secdata);
+ if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & MS_NOSEC))
+ inode->i_flags |= S_NOSEC;
}
-#else
-static inline char *alloc_secdata(void)
-{
- return (char *)1;
-}
-
-static inline void free_secdata(void *secdata)
-{ }
-#endif /* CONFIG_SECURITY */
#endif /* __KERNEL__ */
#endif /* _LINUX_FS_H */
