diff options
author | Matthew Wilcox <matthew.r.wilcox@intel.com> | 2015-02-16 15:59:02 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-02-16 17:56:03 -0800 |
commit | f7ca90b160307d63aaedab8bd451c24a182db20f (patch) | |
tree | 687eb94acbc8ebfab6d5e12a57dc336ce21b7c64 /mm | |
parent | 289c6aedac981533331428bc933fff21ae332c9e (diff) |
dax,ext2: replace the XIP page fault handler with the DAX page fault handler
Instead of calling aops->get_xip_mem from the fault handler, the
filesystem passes a get_block_t that is used to find the appropriate
blocks.
This requires that all architectures implement copy_user_page(). At the
time of writing, mips and arm do not. Patches exist and are in progress.
[akpm@linux-foundation.org: remap_file_pages went away]
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Andreas Dilger <andreas.dilger@intel.com>
Cc: Boaz Harrosh <boaz@plexistor.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r-- | mm/filemap_xip.c | 206 |
1 files changed, 0 insertions, 206 deletions
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 9c869f402c07..59fb387b2238 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -23,212 +23,6 @@ #include <asm/io.h> /* - * We do use our own empty page to avoid interference with other users - * of ZERO_PAGE(), such as /dev/zero - */ -static DEFINE_MUTEX(xip_sparse_mutex); -static seqcount_t xip_sparse_seq = SEQCNT_ZERO(xip_sparse_seq); -static struct page *__xip_sparse_page; - -/* called under xip_sparse_mutex */ -static struct page *xip_sparse_page(void) -{ - if (!__xip_sparse_page) { - struct page *page = alloc_page(GFP_HIGHUSER | __GFP_ZERO); - - if (page) - __xip_sparse_page = page; - } - return __xip_sparse_page; -} - -/* - * __xip_unmap is invoked from xip_unmap and xip_write - * - * This function walks all vmas of the address_space and unmaps the - * __xip_sparse_page when found at pgoff. - */ -static void __xip_unmap(struct address_space * mapping, unsigned long pgoff) -{ - struct vm_area_struct *vma; - struct page *page; - unsigned count; - int locked = 0; - - count = read_seqcount_begin(&xip_sparse_seq); - - page = __xip_sparse_page; - if (!page) - return; - -retry: - i_mmap_lock_read(mapping); - vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { - pte_t *pte, pteval; - spinlock_t *ptl; - struct mm_struct *mm = vma->vm_mm; - unsigned long address = vma->vm_start + - ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); - - BUG_ON(address < vma->vm_start || address >= vma->vm_end); - pte = page_check_address(page, mm, address, &ptl, 1); - if (pte) { - /* Nuke the page table entry. */ - flush_cache_page(vma, address, pte_pfn(*pte)); - pteval = ptep_clear_flush(vma, address, pte); - page_remove_rmap(page); - dec_mm_counter(mm, MM_FILEPAGES); - BUG_ON(pte_dirty(pteval)); - pte_unmap_unlock(pte, ptl); - /* must invalidate_page _before_ freeing the page */ - mmu_notifier_invalidate_page(mm, address); - page_cache_release(page); - } - } - i_mmap_unlock_read(mapping); - - if (locked) { - mutex_unlock(&xip_sparse_mutex); - } else if (read_seqcount_retry(&xip_sparse_seq, count)) { - mutex_lock(&xip_sparse_mutex); - locked = 1; - goto retry; - } -} - -/* - * xip_fault() is invoked via the vma operations vector for a - * mapped memory region to read in file data during a page fault. - * - * This function is derived from filemap_fault, but used for execute in place - */ -static int xip_file_fault(struct vm_area_struct *vma, struct vm_fault *vmf) -{ - struct file *file = vma->vm_file; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - pgoff_t size; - void *xip_mem; - unsigned long xip_pfn; - struct page *page; - int error; - - /* XXX: are VM_FAULT_ codes OK? */ -again: - size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - if (vmf->pgoff >= size) - return VM_FAULT_SIGBUS; - - error = mapping->a_ops->get_xip_mem(mapping, vmf->pgoff, 0, - &xip_mem, &xip_pfn); - if (likely(!error)) - goto found; - if (error != -ENODATA) - return VM_FAULT_OOM; - - /* sparse block */ - if ((vma->vm_flags & (VM_WRITE | VM_MAYWRITE)) && - (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) && - (!(mapping->host->i_sb->s_flags & MS_RDONLY))) { - int err; - - /* maybe shared writable, allocate new block */ - mutex_lock(&xip_sparse_mutex); - error = mapping->a_ops->get_xip_mem(mapping, vmf->pgoff, 1, - &xip_mem, &xip_pfn); - mutex_unlock(&xip_sparse_mutex); - if (error) - return VM_FAULT_SIGBUS; - /* unmap sparse mappings at pgoff from all other vmas */ - __xip_unmap(mapping, vmf->pgoff); - -found: - /* - * We must recheck i_size under i_mmap_rwsem to prevent races - * with truncation - */ - i_mmap_lock_read(mapping); - size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT; - if (unlikely(vmf->pgoff >= size)) { - i_mmap_unlock_read(mapping); - return VM_FAULT_SIGBUS; - } - err = vm_insert_mixed(vma, (unsigned long)vmf->virtual_address, - xip_pfn); - i_mmap_unlock_read(mapping); - if (err == -ENOMEM) - return VM_FAULT_OOM; - /* - * err == -EBUSY is fine, we've raced against another thread - * that faulted-in the same page - */ - if (err != -EBUSY) - BUG_ON(err); - return VM_FAULT_NOPAGE; - } else { - int err, ret = VM_FAULT_OOM; - - mutex_lock(&xip_sparse_mutex); - write_seqcount_begin(&xip_sparse_seq); - error = mapping->a_ops->get_xip_mem(mapping, vmf->pgoff, 0, - &xip_mem, &xip_pfn); - if (unlikely(!error)) { - write_seqcount_end(&xip_sparse_seq); - mutex_unlock(&xip_sparse_mutex); - goto again; - } - if (error != -ENODATA) - goto out; - - /* - * We must recheck i_size under i_mmap_rwsem to prevent races - * with truncation - */ - i_mmap_lock_read(mapping); - size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT; - if (unlikely(vmf->pgoff >= size)) { - ret = VM_FAULT_SIGBUS; - goto unlock; - } - /* not shared and writable, use xip_sparse_page() */ - page = xip_sparse_page(); - if (!page) - goto unlock; - err = vm_insert_page(vma, (unsigned long)vmf->virtual_address, - page); - if (err == -ENOMEM) - goto unlock; - - ret = VM_FAULT_NOPAGE; -unlock: - i_mmap_unlock_read(mapping); -out: - write_seqcount_end(&xip_sparse_seq); - mutex_unlock(&xip_sparse_mutex); - - return ret; - } -} - -static const struct vm_operations_struct xip_file_vm_ops = { - .fault = xip_file_fault, - .page_mkwrite = filemap_page_mkwrite, -}; - -int xip_file_mmap(struct file * file, struct vm_area_struct * vma) -{ - BUG_ON(!file->f_mapping->a_ops->get_xip_mem); - - file_accessed(file); - vma->vm_ops = &xip_file_vm_ops; - vma->vm_flags |= VM_MIXEDMAP; - return 0; -} -EXPORT_SYMBOL_GPL(xip_file_mmap); - -/* * truncate a page used for execute in place * functionality is analog to block_truncate_page but does use get_xip_mem * to get the page instead of page cache |