From e27f41e1b789e60e7d8cc9c81fd93ca49ef31f13 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Fri, 28 Sep 2012 23:24:52 -0400 Subject: ext4: give i_aiodio_unwritten a more appropriate name AIO/DIO prefix is wrong because it account unwritten extents which also may be scheduled from buffered write endio Reviewed-by: Jan Kara Signed-off-by: Dmitry Monakhov Signed-off-by: "Theodore Ts'o" --- fs/ext4/file.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'fs/ext4/file.c') diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 3b0e3bdaabf..39335bda404 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -55,11 +55,11 @@ static int ext4_release_file(struct inode *inode, struct file *filp) return 0; } -static void ext4_aiodio_wait(struct inode *inode) +static void ext4_unwritten_wait(struct inode *inode) { wait_queue_head_t *wq = ext4_ioend_wq(inode); - wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_aiodio_unwritten) == 0)); + wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_unwritten) == 0)); } /* @@ -116,7 +116,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov, "performance will be poor.", inode->i_ino, current->comm); mutex_lock(ext4_aio_mutex(inode)); - ext4_aiodio_wait(inode); + ext4_unwritten_wait(inode); } BUG_ON(iocb->ki_pos != pos); -- cgit v1.2.3-70-g09d2 From c278531d39f3158bfee93dc67da0b77e09776de2 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Fri, 5 Oct 2012 11:31:55 -0400 Subject: ext4: fix ext4_flush_completed_IO wait semantics BUG #1) All places where we call ext4_flush_completed_IO are broken because buffered io and DIO/AIO goes through three stages 1) submitted io, 2) completed io (in i_completed_io_list) conversion pended 3) finished io (conversion done) And by calling ext4_flush_completed_IO we will flush only requests which were in (2) stage, which is wrong because: 1) punch_hole and truncate _must_ wait for all outstanding unwritten io regardless to it's state. 2) fsync and nolock_dio_read should also wait because there is a time window between end_page_writeback() and ext4_add_complete_io() As result integrity fsync is broken in case of buffered write to fallocated region: fsync blkdev_completion ->filemap_write_and_wait_range ->ext4_end_bio ->end_page_writeback <-- filemap_write_and_wait_range return ->ext4_flush_completed_IO sees empty i_completed_io_list but pended conversion still exist ->ext4_add_complete_io BUG #2) Race window becomes wider due to the 'ext4: completed_io locking cleanup V4' patch series This patch make following changes: 1) ext4_flush_completed_io() now first try to flush completed io and when wait for any outstanding unwritten io via ext4_unwritten_wait() 2) Rename function to more appropriate name. 3) Assert that all callers of ext4_flush_unwritten_io should hold i_mutex to prevent endless wait Signed-off-by: Dmitry Monakhov Signed-off-by: "Theodore Ts'o" Reviewed-by: Jan Kara --- fs/ext4/ext4.h | 3 ++- fs/ext4/extents.c | 6 +++--- fs/ext4/file.c | 2 +- fs/ext4/fsync.c | 2 +- fs/ext4/indirect.c | 8 +++++--- fs/ext4/page-io.c | 11 +++++++---- 6 files changed, 19 insertions(+), 13 deletions(-) (limited to 'fs/ext4/file.c') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 1be2b4472a8..3ab2539b7b2 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1947,7 +1947,7 @@ extern void ext4_htree_free_dir_info(struct dir_private_info *p); /* fsync.c */ extern int ext4_sync_file(struct file *, loff_t, loff_t, int); -extern int ext4_flush_completed_IO(struct inode *); +extern int ext4_flush_unwritten_io(struct inode *); /* hash.c */ extern int ext4fs_dirhash(const char *name, int len, struct @@ -2371,6 +2371,7 @@ extern const struct file_operations ext4_dir_operations; extern const struct inode_operations ext4_file_inode_operations; extern const struct file_operations ext4_file_operations; extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin); +extern void ext4_unwritten_wait(struct inode *inode); /* namei.c */ extern const struct inode_operations ext4_dir_inode_operations; diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index c1fcf489e05..1c94cca35ed 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4268,7 +4268,7 @@ void ext4_ext_truncate(struct inode *inode) * finish any pending end_io work so we won't run the risk of * converting any truncated blocks to initialized later */ - ext4_flush_completed_IO(inode); + ext4_flush_unwritten_io(inode); /* * probably first extent we're gonna free will be last in block @@ -4847,10 +4847,10 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length) /* Wait all existing dio workers, newcomers will block on i_mutex */ ext4_inode_block_unlocked_dio(inode); - inode_dio_wait(inode); - err = ext4_flush_completed_IO(inode); + err = ext4_flush_unwritten_io(inode); if (err) goto out_dio; + inode_dio_wait(inode); credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, credits); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 39335bda404..ca6f07afe60 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -55,7 +55,7 @@ static int ext4_release_file(struct inode *inode, struct file *filp) return 0; } -static void ext4_unwritten_wait(struct inode *inode) +void ext4_unwritten_wait(struct inode *inode) { wait_queue_head_t *wq = ext4_ioend_wq(inode); diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 460000868b8..be1d89f385b 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -138,7 +138,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) if (inode->i_sb->s_flags & MS_RDONLY) goto out; - ret = ext4_flush_completed_IO(inode); + ret = ext4_flush_unwritten_io(inode); if (ret < 0) goto out; diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 8d849dae842..792e388e7b4 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -807,9 +807,11 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, retry: if (rw == READ && ext4_should_dioread_nolock(inode)) { - if (unlikely(!list_empty(&ei->i_completed_io_list))) - ext4_flush_completed_IO(inode); - + if (unlikely(atomic_read(&EXT4_I(inode)->i_unwritten))) { + mutex_lock(&inode->i_mutex); + ext4_flush_unwritten_io(inode); + mutex_unlock(&inode->i_mutex); + } /* * Nolock dioread optimization may be dynamically disabled * via ext4_inode_block_unlocked_dio(). Check inode's state diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 5b24c407701..68e896e12a6 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -189,8 +189,6 @@ static int ext4_do_flush_completed_IO(struct inode *inode, list_add_tail(&io->list, &complete); } - /* It is important to update all flags for all end_io in one shot w/o - * dropping the lock.*/ spin_lock_irqsave(&ei->i_completed_io_lock, flags); while (!list_empty(&complete)) { io = list_entry(complete.next, ext4_io_end_t, list); @@ -228,9 +226,14 @@ static void ext4_end_io_work(struct work_struct *work) ext4_do_flush_completed_IO(io->inode, io); } -int ext4_flush_completed_IO(struct inode *inode) +int ext4_flush_unwritten_io(struct inode *inode) { - return ext4_do_flush_completed_IO(inode, NULL); + int ret; + WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex) && + !(inode->i_state & I_FREEING)); + ret = ext4_do_flush_completed_IO(inode, NULL); + ext4_unwritten_wait(inode); + return ret; } ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags) -- cgit v1.2.3-70-g09d2 From 0b173bc4daa8f8ec03a85abf5e47b23502ff80af Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Mon, 8 Oct 2012 16:28:46 -0700 Subject: mm: kill vma flag VM_CAN_NONLINEAR Move actual pte filling for non-linear file mappings into the new special vma operation: ->remap_pages(). Filesystems must implement this method to get non-linear mapping support, if it uses filemap_fault() then generic_file_remap_pages() can be used. Now device drivers can implement this method and obtain nonlinear vma support. Signed-off-by: Konstantin Khlebnikov Cc: Alexander Viro Cc: Carsten Otte Cc: Chris Metcalf #arch/tile Cc: Cyrill Gorcunov Cc: Eric Paris Cc: H. Peter Anvin Cc: Hugh Dickins Cc: Ingo Molnar Cc: James Morris Cc: Jason Baron Cc: Kentaro Takeda Cc: Matt Helsley Cc: Nick Piggin Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Robert Richter Cc: Suresh Siddha Cc: Tetsuo Handa Cc: Venkatesh Pallipadi Acked-by: Linus Torvalds Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/staging/android/ashmem.c | 1 - fs/9p/vfs_file.c | 1 + fs/btrfs/file.c | 2 +- fs/ceph/addr.c | 2 +- fs/cifs/file.c | 1 + fs/ext4/file.c | 2 +- fs/fuse/file.c | 1 + fs/gfs2/file.c | 2 +- fs/nfs/file.c | 1 + fs/nilfs2/file.c | 2 +- fs/ocfs2/mmap.c | 2 +- fs/ubifs/file.c | 1 + fs/xfs/xfs_file.c | 2 +- include/linux/fs.h | 2 ++ include/linux/mm.h | 7 ++++--- mm/filemap.c | 2 +- mm/filemap_xip.c | 3 ++- mm/fremap.c | 14 ++++++++------ mm/mmap.c | 3 +-- mm/nommu.c | 8 ++++++++ mm/shmem.c | 3 +-- 21 files changed, 39 insertions(+), 23 deletions(-) (limited to 'fs/ext4/file.c') diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index 94a740d2883..634b9ae713e 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -332,7 +332,6 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma) if (vma->vm_file) fput(vma->vm_file); vma->vm_file = asma->file; - vma->vm_flags |= VM_CAN_NONLINEAR; out: mutex_unlock(&ashmem_mutex); diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index dd6f7ee1e31..c2483e97bee 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -738,6 +738,7 @@ v9fs_cached_file_write(struct file *filp, const char __user * data, static const struct vm_operations_struct v9fs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = v9fs_vm_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 5caf285c6e4..f6b40e86121 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1599,6 +1599,7 @@ out: static const struct vm_operations_struct btrfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = btrfs_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; static int btrfs_file_mmap(struct file *filp, struct vm_area_struct *vma) @@ -1610,7 +1611,6 @@ static int btrfs_file_mmap(struct file *filp, struct vm_area_struct *vma) file_accessed(filp); vma->vm_ops = &btrfs_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 22b6e4583fa..6690269f5dd 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1224,6 +1224,7 @@ out: static struct vm_operations_struct ceph_vmops = { .fault = filemap_fault, .page_mkwrite = ceph_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; int ceph_mmap(struct file *file, struct vm_area_struct *vma) @@ -1234,6 +1235,5 @@ int ceph_mmap(struct file *file, struct vm_area_struct *vma) return -ENOEXEC; file_accessed(file); vma->vm_ops = &ceph_vmops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 7d7bbdc4c8e..edb25b4bbb9 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3003,6 +3003,7 @@ cifs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) static struct vm_operations_struct cifs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = cifs_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/ext4/file.c b/fs/ext4/file.c index ca6f07afe60..bf3966bccd3 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -207,6 +207,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, static const struct vm_operations_struct ext4_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = ext4_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) @@ -217,7 +218,6 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) return -ENOEXEC; file_accessed(file); vma->vm_ops = &ext4_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index aba15f1b7ad..78d2837bc94 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1379,6 +1379,7 @@ static const struct vm_operations_struct fuse_file_vm_ops = { .close = fuse_vma_close, .fault = filemap_fault, .page_mkwrite = fuse_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 30e21997a1a..0def0504afc 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -492,6 +492,7 @@ out: static const struct vm_operations_struct gfs2_vm_ops = { .fault = filemap_fault, .page_mkwrite = gfs2_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; /** @@ -526,7 +527,6 @@ static int gfs2_mmap(struct file *file, struct vm_area_struct *vma) return error; } vma->vm_ops = &gfs2_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 6a7fcab7ecb..f692be97676 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -578,6 +578,7 @@ out: static const struct vm_operations_struct nfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = nfs_vm_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; static int nfs_need_sync_write(struct file *filp, struct inode *inode) diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 5b387a4c293..16f35f7423c 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -135,13 +135,13 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) static const struct vm_operations_struct nilfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = nilfs_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; static int nilfs_file_mmap(struct file *file, struct vm_area_struct *vma) { file_accessed(file); vma->vm_ops = &nilfs_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index d150372fd81..47a87dda54c 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -173,6 +173,7 @@ out: static const struct vm_operations_struct ocfs2_file_vm_ops = { .fault = ocfs2_fault, .page_mkwrite = ocfs2_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; int ocfs2_mmap(struct file *file, struct vm_area_struct *vma) @@ -188,7 +189,6 @@ int ocfs2_mmap(struct file *file, struct vm_area_struct *vma) ocfs2_inode_unlock(file->f_dentry->d_inode, lock_level); out: vma->vm_ops = &ocfs2_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index ff48c5a8530..5bc77817f38 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1536,6 +1536,7 @@ out_unlock: static const struct vm_operations_struct ubifs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = ubifs_vm_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; static int ubifs_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 1eaeb8be3aa..aa473fa640a 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -940,7 +940,6 @@ xfs_file_mmap( struct vm_area_struct *vma) { vma->vm_ops = &xfs_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; file_accessed(filp); return 0; @@ -1443,4 +1442,5 @@ const struct file_operations xfs_dir_file_operations = { static const struct vm_operations_struct xfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = xfs_vm_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; diff --git a/include/linux/fs.h b/include/linux/fs.h index ca6d8c806f4..5a8a273d5b2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2552,6 +2552,8 @@ extern int sb_min_blocksize(struct super_block *, int); 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 generic_file_remap_pages(struct vm_area_struct *, unsigned long addr, + unsigned long size, pgoff_t pgoff); extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size); int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); diff --git a/include/linux/mm.h b/include/linux/mm.h index fb0685b1791..44d3fc25f55 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -105,7 +105,6 @@ extern unsigned int kobjsize(const void *objp); #define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ #define VM_NODUMP 0x04000000 /* Do not include in the core dump */ -#define VM_CAN_NONLINEAR 0x08000000 /* Has ->fault & does nonlinear pages */ #define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */ #define VM_HUGEPAGE 0x20000000 /* MADV_HUGEPAGE marked this vma */ #define VM_NOHUGEPAGE 0x40000000 /* MADV_NOHUGEPAGE marked this vma */ @@ -171,8 +170,7 @@ extern pgprot_t protection_map[16]; * of VM_FAULT_xxx flags that give details about how the fault was handled. * * pgoff should be used in favour of virtual_address, if possible. If pgoff - * is used, one may set VM_CAN_NONLINEAR in the vma->vm_flags to get nonlinear - * mapping support. + * is used, one may implement ->remap_pages to get nonlinear mapping support. */ struct vm_fault { unsigned int flags; /* FAULT_FLAG_xxx flags */ @@ -230,6 +228,9 @@ struct vm_operations_struct { int (*migrate)(struct vm_area_struct *vma, const nodemask_t *from, const nodemask_t *to, unsigned long flags); #endif + /* called by sys_remap_file_pages() to populate non-linear mapping */ + int (*remap_pages)(struct vm_area_struct *vma, unsigned long addr, + unsigned long size, pgoff_t pgoff); }; struct mmu_gather; diff --git a/mm/filemap.c b/mm/filemap.c index 384344575c3..a9827b42556 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1737,6 +1737,7 @@ EXPORT_SYMBOL(filemap_page_mkwrite); const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = filemap_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; /* This is used for a general mmap of a disk file */ @@ -1749,7 +1750,6 @@ int generic_file_mmap(struct file * file, struct vm_area_struct * vma) return -ENOEXEC; file_accessed(file); vma->vm_ops = &generic_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 13e013b1270..91750227a19 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -305,6 +305,7 @@ out: static const struct vm_operations_struct xip_file_vm_ops = { .fault = xip_file_fault, .page_mkwrite = filemap_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; int xip_file_mmap(struct file * file, struct vm_area_struct * vma) @@ -313,7 +314,7 @@ int xip_file_mmap(struct file * file, struct vm_area_struct * vma) file_accessed(file); vma->vm_ops = &xip_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR | VM_MIXEDMAP; + vma->vm_flags |= VM_MIXEDMAP; return 0; } EXPORT_SYMBOL_GPL(xip_file_mmap); diff --git a/mm/fremap.c b/mm/fremap.c index 048659c0c03..3d731a49878 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -5,6 +5,7 @@ * * started by Ingo Molnar, Copyright (C) 2002, 2003 */ +#include #include #include #include @@ -80,9 +81,10 @@ out: return err; } -static int populate_range(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, unsigned long size, pgoff_t pgoff) +int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr, + unsigned long size, pgoff_t pgoff) { + struct mm_struct *mm = vma->vm_mm; int err; do { @@ -95,9 +97,9 @@ static int populate_range(struct mm_struct *mm, struct vm_area_struct *vma, pgoff++; } while (size); - return 0; - + return 0; } +EXPORT_SYMBOL(generic_file_remap_pages); /** * sys_remap_file_pages - remap arbitrary pages of an existing VM_SHARED vma @@ -167,7 +169,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, if (vma->vm_private_data && !(vma->vm_flags & VM_NONLINEAR)) goto out; - if (!(vma->vm_flags & VM_CAN_NONLINEAR)) + if (!vma->vm_ops->remap_pages) goto out; if (start < vma->vm_start || start + size > vma->vm_end) @@ -228,7 +230,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, } mmu_notifier_invalidate_range_start(mm, start, start + size); - err = populate_range(mm, vma, start, size, pgoff); + err = vma->vm_ops->remap_pages(vma, start, size, pgoff); mmu_notifier_invalidate_range_end(mm, start, start + size); if (!err && !(flags & MAP_NONBLOCK)) { if (vma->vm_flags & VM_LOCKED) { diff --git a/mm/mmap.c b/mm/mmap.c index b0989f4d4f0..d0686d35511 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -669,8 +669,7 @@ again: remove_next = 1 + (end > next->vm_end); static inline int is_mergeable_vma(struct vm_area_struct *vma, struct file *file, unsigned long vm_flags) { - /* VM_CAN_NONLINEAR may get set later by f_op->mmap() */ - if ((vma->vm_flags ^ vm_flags) & ~VM_CAN_NONLINEAR) + if (vma->vm_flags ^ vm_flags) return 0; if (vma->vm_file != file) return 0; diff --git a/mm/nommu.c b/mm/nommu.c index dee2ff89fd5..98318dcff74 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1961,6 +1961,14 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } EXPORT_SYMBOL(filemap_fault); +int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr, + unsigned long size, pgoff_t pgoff) +{ + BUG(); + return 0; +} +EXPORT_SYMBOL(generic_file_remap_pages); + static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, unsigned long addr, void *buf, int len, int write) { diff --git a/mm/shmem.c b/mm/shmem.c index d3752110c8c..cc12072f878 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1339,7 +1339,6 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) { file_accessed(file); vma->vm_ops = &shmem_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } @@ -2643,6 +2642,7 @@ static const struct vm_operations_struct shmem_vm_ops = { .set_policy = shmem_set_policy, .get_policy = shmem_get_policy, #endif + .remap_pages = generic_file_remap_pages, }; static struct dentry *shmem_mount(struct file_system_type *fs_type, @@ -2836,7 +2836,6 @@ int shmem_zero_setup(struct vm_area_struct *vma) fput(vma->vm_file); vma->vm_file = file; vma->vm_ops = &shmem_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } -- cgit v1.2.3-70-g09d2