linux/fs/xfs/xfs_linux.h

258 lines
6.6 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
* All Rights Reserved.
*/
#ifndef __XFS_LINUX__
#define __XFS_LINUX__
#include <linux/types.h>
#include <linux/uuid.h>
/*
* Kernel specific type declarations for XFS
*/
typedef __s64 xfs_off_t; /* <file offset> type */
typedef unsigned long long xfs_ino_t; /* <inode> type */
typedef __s64 xfs_daddr_t; /* <disk address> type */
typedef __u32 xfs_dev_t;
typedef __u32 xfs_nlink_t;
#include "xfs_types.h"
#include "kmem.h"
#include "mrlock.h"
#include <linux/semaphore.h>
#include <linux/mm.h>
#include <linux/sched/mm.h>
#include <linux/kernel.h>
#include <linux/blkdev.h>
#include <linux/slab.h>
#include <linux/crc32c.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/file.h>
#include <linux/swap.h>
#include <linux/errno.h>
#include <linux/sched/signal.h>
#include <linux/bitops.h>
#include <linux/major.h>
#include <linux/pagemap.h>
#include <linux/vfs.h>
#include <linux/seq_file.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/proc_fs.h>
#include <linux/sort.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/delay.h>
#include <linux/log2.h>
#include <linux/spinlock.h>
#include <linux/random.h>
#include <linux/ctype.h>
#include <linux/writeback.h>
#include <linux/capability.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/list_sort.h>
#include <linux/ratelimit.h>
#include <linux/rhashtable.h>
#include <linux/xattr.h>
#include <linux/mnt_idmapping.h>
#include <asm/page.h>
#include <asm/div64.h>
#include <asm/param.h>
#include <linux/uaccess.h>
#include <asm/byteorder.h>
#include <asm/unaligned.h>
#include "xfs_fs.h"
#include "xfs_stats.h"
#include "xfs_sysctl.h"
#include "xfs_iops.h"
#include "xfs_aops.h"
#include "xfs_super.h"
#include "xfs_cksum.h"
#include "xfs_buf.h"
#include "xfs_message.h"
#ifdef __BIG_ENDIAN
#define XFS_NATIVE_HOST 1
#else
#undef XFS_NATIVE_HOST
#endif
#define irix_sgid_inherit xfs_params.sgid_inherit.val
#define irix_symlink_mode xfs_params.symlink_mode.val
#define xfs_panic_mask xfs_params.panic_mask.val
#define xfs_error_level xfs_params.error_level.val
#define xfs_syncd_centisecs xfs_params.syncd_timer.val
#define xfs_stats_clear xfs_params.stats_clear.val
#define xfs_inherit_sync xfs_params.inherit_sync.val
#define xfs_inherit_nodump xfs_params.inherit_nodump.val
#define xfs_inherit_noatime xfs_params.inherit_noatim.val
#define xfs_inherit_nosymlinks xfs_params.inherit_nosym.val
#define xfs_rotorstep xfs_params.rotorstep.val
#define xfs_inherit_nodefrag xfs_params.inherit_nodfrg.val
[XFS] Concurrent Multi-File Data Streams In media spaces, video is often stored in a frame-per-file format. When dealing with uncompressed realtime HD video streams in this format, it is crucial that files do not get fragmented and that multiple files a placed contiguously on disk. When multiple streams are being ingested and played out at the same time, it is critical that the filesystem does not cross the streams and interleave them together as this creates seek and readahead cache miss latency and prevents both ingest and playout from meeting frame rate targets. This patch set creates a "stream of files" concept into the allocator to place all the data from a single stream contiguously on disk so that RAID array readahead can be used effectively. Each additional stream gets placed in different allocation groups within the filesystem, thereby ensuring that we don't cross any streams. When an AG fills up, we select a new AG for the stream that is not in use. The core of the functionality is the stream tracking - each inode that we create in a directory needs to be associated with the directories' stream. Hence every time we create a file, we look up the directories' stream object and associate the new file with that object. Once we have a stream object for a file, we use the AG that the stream object point to for allocations. If we can't allocate in that AG (e.g. it is full) we move the entire stream to another AG. Other inodes in the same stream are moved to the new AG on their next allocation (i.e. lazy update). Stream objects are kept in a cache and hold a reference on the inode. Hence the inode cannot be reclaimed while there is an outstanding stream reference. This means that on unlink we need to remove the stream association and we also need to flush all the associations on certain events that want to reclaim all unreferenced inodes (e.g. filesystem freeze). SGI-PV: 964469 SGI-Modid: xfs-linux-melb:xfs-kern:29096a Signed-off-by: David Chinner <dgc@sgi.com> Signed-off-by: Barry Naujok <bnaujok@sgi.com> Signed-off-by: Donald Douwsma <donaldd@sgi.com> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Tim Shimmin <tes@sgi.com> Signed-off-by: Vlad Apostolov <vapo@sgi.com>
2007-07-11 01:09:12 +00:00
#define xfs_fstrm_centisecs xfs_params.fstrm_timer.val
#define xfs_blockgc_secs xfs_params.blockgc_timer.val
#define current_cpu() (raw_smp_processor_id())
#define current_set_flags_nested(sp, f) \
(*(sp) = current->flags, current->flags |= (f))
#define current_restore_flags_nested(sp, f) \
(current->flags = ((current->flags & ~(f)) | (*(sp) & (f))))
#define NBBY 8 /* number of bits per byte */
/*
* Size of block device i/o is parameterized here.
* Currently the system supports page-sized i/o.
*/
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 12:29:47 +00:00
#define BLKDEV_IOSHIFT PAGE_SHIFT
#define BLKDEV_IOSIZE (1<<BLKDEV_IOSHIFT)
/* number of BB's per block device block */
#define BLKDEV_BB BTOBB(BLKDEV_IOSIZE)
#define ENOATTR ENODATA /* Attribute not found */
#define EWRONGFS EINVAL /* Mount with wrong filesystem type */
#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */
#define EFSBADCRC EBADMSG /* Bad CRC detected */
#define __return_address __builtin_return_address(0)
/*
* Return the address of a label. Use barrier() so that the optimizer
* won't reorder code to refactor the error jumpouts into a single
* return, which throws off the reported address.
*/
#define __this_address ({ __label__ __here; __here: barrier(); &&__here; })
#define XFS_PROJID_DEFAULT 0
#define howmany(x, y) (((x)+((y)-1))/(y))
static inline void delay(long ticks)
{
schedule_timeout_uninterruptible(ticks);
}
/*
* XFS wrapper structure for sysfs support. It depends on external data
* structures and is embedded in various internal data structures to implement
* the XFS sysfs object heirarchy. Define it here for broad access throughout
* the codebase.
*/
struct xfs_kobj {
struct kobject kobject;
struct completion complete;
};
struct xstats {
struct xfsstats __percpu *xs_stats;
struct xfs_kobj xs_kobj;
};
extern struct xstats xfsstats;
static inline dev_t xfs_to_linux_dev_t(xfs_dev_t dev)
{
return MKDEV(sysv_major(dev) & 0x1ff, sysv_minor(dev));
}
static inline xfs_dev_t linux_to_xfs_dev_t(dev_t dev)
{
return sysv_encode_dev(dev);
}
/*
* Various platform dependent calls that don't fit anywhere else
*/
#define xfs_sort(a,n,s,fn) sort(a,n,s,fn,NULL)
#define xfs_stack_trace() dump_stack()
static inline uint64_t rounddown_64(uint64_t x, uint32_t y)
{
do_div(x, y);
return x * y;
}
static inline uint64_t roundup_64(uint64_t x, uint32_t y)
{
x += y - 1;
do_div(x, y);
return x * y;
}
static inline uint64_t howmany_64(uint64_t x, uint32_t y)
{
x += y - 1;
do_div(x, y);
return x;
}
int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count,
char *data, enum req_op op);
#define ASSERT_ALWAYS(expr) \
(likely(expr) ? (void)0 : assfail(NULL, #expr, __FILE__, __LINE__))
#ifdef DEBUG
#define ASSERT(expr) \
(likely(expr) ? (void)0 : assfail(NULL, #expr, __FILE__, __LINE__))
#else /* !DEBUG */
#ifdef XFS_WARN
#define ASSERT(expr) \
(likely(expr) ? (void)0 : asswarn(NULL, #expr, __FILE__, __LINE__))
#else /* !DEBUG && !XFS_WARN */
#define ASSERT(expr) ((void)0)
#endif /* XFS_WARN */
#endif /* DEBUG */
#define XFS_IS_CORRUPT(mp, expr) \
(unlikely(expr) ? xfs_corruption_error(#expr, XFS_ERRLEVEL_LOW, (mp), \
NULL, 0, __FILE__, __LINE__, \
__this_address), \
true : false)
#define STATIC static noinline
#ifdef CONFIG_XFS_RT
xfs: XFS_IS_REALTIME_INODE() should be false if no rt device present If using a kernel with CONFIG_XFS_RT=y and we set the RHINHERIT flag on a directory in a filesystem that does not have a realtime device and create a new file in that directory, it gets marked as a real time file. When data is written and a fsync is issued, the filesystem attempts to flush a non-existent rt device during the fsync process. This results in a crash dereferencing a null buftarg pointer in xfs_blkdev_issue_flush(): BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 IP: xfs_blkdev_issue_flush+0xd/0x20 ..... Call Trace: xfs_file_fsync+0x188/0x1c0 vfs_fsync_range+0x3b/0xa0 do_fsync+0x3d/0x70 SyS_fsync+0x10/0x20 do_syscall_64+0x4d/0xb0 entry_SYSCALL64_slow_path+0x25/0x25 Setting RT inode flags does not require special privileges so any unprivileged user can cause this oops to occur. To reproduce, confirm kernel is compiled with CONFIG_XFS_RT=y and run: # mkfs.xfs -f /dev/pmem0 # mount /dev/pmem0 /mnt/test # mkdir /mnt/test/foo # xfs_io -c 'chattr +t' /mnt/test/foo # xfs_io -f -c 'pwrite 0 5m' -c fsync /mnt/test/foo/bar Or just run xfstests with MKFS_OPTIONS="-d rtinherit=1" and wait. Kernels built with CONFIG_XFS_RT=n are not exposed to this bug. Fixes: f538d4da8d52 ("[XFS] write barrier support") Cc: <stable@vger.kernel.org> Signed-off-by: Richard Wareing <rwareing@fb.com> Signed-off-by: Dave Chinner <david@fromorbit.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-12 23:09:35 +00:00
/*
* make sure we ignore the inode flag if the filesystem doesn't have a
* configured realtime device.
*/
#define XFS_IS_REALTIME_INODE(ip) \
(((ip)->i_diflags & XFS_DIFLAG_REALTIME) && \
xfs: XFS_IS_REALTIME_INODE() should be false if no rt device present If using a kernel with CONFIG_XFS_RT=y and we set the RHINHERIT flag on a directory in a filesystem that does not have a realtime device and create a new file in that directory, it gets marked as a real time file. When data is written and a fsync is issued, the filesystem attempts to flush a non-existent rt device during the fsync process. This results in a crash dereferencing a null buftarg pointer in xfs_blkdev_issue_flush(): BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 IP: xfs_blkdev_issue_flush+0xd/0x20 ..... Call Trace: xfs_file_fsync+0x188/0x1c0 vfs_fsync_range+0x3b/0xa0 do_fsync+0x3d/0x70 SyS_fsync+0x10/0x20 do_syscall_64+0x4d/0xb0 entry_SYSCALL64_slow_path+0x25/0x25 Setting RT inode flags does not require special privileges so any unprivileged user can cause this oops to occur. To reproduce, confirm kernel is compiled with CONFIG_XFS_RT=y and run: # mkfs.xfs -f /dev/pmem0 # mount /dev/pmem0 /mnt/test # mkdir /mnt/test/foo # xfs_io -c 'chattr +t' /mnt/test/foo # xfs_io -f -c 'pwrite 0 5m' -c fsync /mnt/test/foo/bar Or just run xfstests with MKFS_OPTIONS="-d rtinherit=1" and wait. Kernels built with CONFIG_XFS_RT=n are not exposed to this bug. Fixes: f538d4da8d52 ("[XFS] write barrier support") Cc: <stable@vger.kernel.org> Signed-off-by: Richard Wareing <rwareing@fb.com> Signed-off-by: Dave Chinner <david@fromorbit.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-12 23:09:35 +00:00
(ip)->i_mount->m_rtdev_targp)
#define XFS_IS_REALTIME_MOUNT(mp) ((mp)->m_rtdev_targp ? 1 : 0)
#else
#define XFS_IS_REALTIME_INODE(ip) (0)
#define XFS_IS_REALTIME_MOUNT(mp) (0)
#endif
/*
* Starting in Linux 4.15, the %p (raw pointer value) printk modifier
* prints a hashed version of the pointer to avoid leaking kernel
* pointers into dmesg. If we're trying to debug the kernel we want the
* raw values, so override this behavior as best we can.
*/
#ifdef DEBUG
# define PTR_FMT "%px"
#else
# define PTR_FMT "%p"
#endif
#endif /* __XFS_LINUX__ */