X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Ffilemap.c;h=89ce6fe5f8be152e71218085af5396dcb72d315c;hb=da3f13c95a4c6e275a9b568f358c0c120ad83ecb;hp=195339b27e9a2d037e58921d099b1de30fe3461f;hpb=89e107877b65bf6eff1d63a1302dee9a091586f5;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/filemap.c b/mm/filemap.c index 195339b..89ce6fe 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -25,8 +25,10 @@ #include #include #include +#include #include #include +#include #include #include #include @@ -63,6 +65,7 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, * ->private_lock (__free_pte->__set_page_dirty_buffers) * ->swap_lock (exclusive_swap_page, others) * ->mapping->tree_lock + * ->zone.lock * * ->i_mutex * ->i_mmap_lock (truncate->unmap_mapping_range) @@ -121,6 +124,18 @@ void __remove_from_page_cache(struct page *page) mapping->nrpages--; __dec_zone_page_state(page, NR_FILE_PAGES); BUG_ON(page_mapped(page)); + + /* + * Some filesystems seem to re-dirty the page even after + * the VM has canceled the dirty bit (eg ext3 journaling). + * + * Fix it up by doing a final dirty accounting check after + * having removed the page entirely. + */ + if (PageDirty(page) && mapping_cap_account_dirty(mapping)) { + dec_zone_page_state(page, NR_FILE_DIRTY); + dec_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE); + } } void remove_from_page_cache(struct page *page) @@ -170,6 +185,12 @@ static int sync_page(void *word) return 0; } +static int sync_page_killable(void *word) +{ + sync_page(word); + return fatal_signal_pending(current) ? -EINTR : 0; +} + /** * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range * @mapping: address space structure to write @@ -574,6 +595,14 @@ void fastcall __lock_page(struct page *page) } EXPORT_SYMBOL(__lock_page); +int fastcall __lock_page_killable(struct page *page) +{ + DEFINE_WAIT_BIT(wait, &page->flags, PG_locked); + + return __wait_on_bit_lock(page_waitqueue(page), &wait, + sync_page_killable, TASK_KILLABLE); +} + /* * Variant of lock_page that does not require the caller to hold a reference * on the page's mapping. @@ -839,7 +868,7 @@ static void shrink_readahead_size_eio(struct file *filp, /** * do_generic_mapping_read - generic file read routine * @mapping: address_space to be read - * @_ra: file's readahead state + * @ra: file's readahead state * @filp: the file to read * @ppos: current file position * @desc: read_descriptor @@ -965,7 +994,8 @@ page_ok: page_not_up_to_date: /* Get exclusive access to the page ... */ - lock_page(page); + if (lock_page_killable(page)) + goto readpage_eio; /* Did it get truncated before we got the lock? */ if (!page->mapping) { @@ -993,7 +1023,8 @@ readpage: } if (!PageUptodate(page)) { - lock_page(page); + if (lock_page_killable(page)) + goto readpage_eio; if (!PageUptodate(page)) { if (page->mapping == NULL) { /* @@ -1004,15 +1035,16 @@ readpage: goto find_page; } unlock_page(page); - error = -EIO; shrink_readahead_size_eio(filp, ra); - goto readpage_error; + goto readpage_eio; } unlock_page(page); } goto page_ok; +readpage_eio: + error = -EIO; readpage_error: /* UHHUH! A synchronous read error occurred. Report it */ desc->error = error; @@ -1297,7 +1329,7 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; if (vmf->pgoff >= size) - goto outside_data_content; + return VM_FAULT_SIGBUS; /* If we don't want any read-ahead, don't bother */ if (VM_RandomReadHint(vma)) @@ -1374,7 +1406,7 @@ retry_find: if (unlikely(vmf->pgoff >= size)) { unlock_page(page); page_cache_release(page); - goto outside_data_content; + return VM_FAULT_SIGBUS; } /* @@ -1385,15 +1417,6 @@ retry_find: vmf->page = page; return ret | VM_FAULT_LOCKED; -outside_data_content: - /* - * An external ptracer can access pages that normally aren't - * accessible.. - */ - if (vma->vm_mm == current->mm) - return VM_FAULT_SIGBUS; - - /* Fall through to the non-read-ahead case */ no_cached_page: /* * We're only likely to ever get here if MADV_RANDOM is in @@ -1626,12 +1649,18 @@ int __remove_suid(struct dentry *dentry, int kill) int remove_suid(struct dentry *dentry) { - int kill = should_remove_suid(dentry); + int killsuid = should_remove_suid(dentry); + int killpriv = security_inode_need_killpriv(dentry); + int error = 0; - if (unlikely(kill)) - return __remove_suid(dentry, kill); + if (killpriv < 0) + return killpriv; + if (killpriv) + error = security_inode_killpriv(dentry); + if (!error && killsuid) + error = __remove_suid(dentry, killsuid); - return 0; + return error; } EXPORT_SYMBOL(remove_suid); @@ -1898,13 +1927,10 @@ again: ret = aops->prepare_write(file, page, offset, offset+len); if (ret) { - if (ret != AOP_TRUNCATED_PAGE) - unlock_page(page); + unlock_page(page); page_cache_release(page); if (pos + len > inode->i_size) vmtruncate(inode, inode->i_size); - if (ret == AOP_TRUNCATED_PAGE) - goto again; } return ret; } @@ -1931,7 +1957,6 @@ int pagecache_write_end(struct file *file, struct address_space *mapping, unlock_page(page); mark_page_accessed(page); page_cache_release(page); - BUG_ON(ret == AOP_TRUNCATED_PAGE); /* can't deal with */ if (ret < 0) { if (pos + len > inode->i_size) @@ -2142,7 +2167,7 @@ static ssize_t generic_perform_write_2copy(struct file *file, flush_dcache_page(page); status = a_ops->commit_write(file, page, offset, offset+bytes); - if (unlikely(status < 0 || status == AOP_TRUNCATED_PAGE)) + if (unlikely(status < 0)) goto fs_write_aop_error; if (unlikely(status > 0)) /* filesystem did partial write */ copied = min_t(size_t, copied, status); @@ -2162,8 +2187,7 @@ static ssize_t generic_perform_write_2copy(struct file *file, continue; fs_write_aop_error: - if (status != AOP_TRUNCATED_PAGE) - unlock_page(page); + unlock_page(page); page_cache_release(page); if (src_page) page_cache_release(src_page); @@ -2175,10 +2199,7 @@ fs_write_aop_error: */ if (pos + bytes > inode->i_size) vmtruncate(inode, inode->i_size); - if (status == AOP_TRUNCATED_PAGE) - continue; - else - break; + break; } while (iov_iter_count(i)); return written ? written : status; @@ -2510,21 +2531,17 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, } retval = mapping->a_ops->direct_IO(rw, iocb, iov, offset, nr_segs); - if (retval) - goto out; /* * Finally, try again to invalidate clean pages which might have been - * faulted in by get_user_pages() if the source of the write was an - * mmap()ed region of the file we're writing. That's a pretty crazy - * thing to do, so we don't support it 100%. If this invalidation - * fails and we have -EIOCBQUEUED we ignore the failure. + * cached by non-direct readahead, or faulted in by get_user_pages() + * if the source of the write was an mmap'ed region of the file + * we're writing. Either one is a pretty crazy thing to do, + * so we don't support it 100%. If this invalidation + * fails, tough, the write still worked... */ if (rw == WRITE && mapping->nrpages) { - int err = invalidate_inode_pages2_range(mapping, - offset >> PAGE_CACHE_SHIFT, end); - if (err && retval >= 0) - retval = err; + invalidate_inode_pages2_range(mapping, offset >> PAGE_CACHE_SHIFT, end); } out: return retval;