diff options
Diffstat (limited to 'fs')
400 files changed, 13468 insertions, 7373 deletions
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 099c7712631c..fb9ffcb43277 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -78,7 +78,6 @@ enum p9_cache_modes { * @cache: cache mode of type &p9_cache_modes * @cachetag: the tag of the cache associated with this session * @fscache: session cookie associated with FS-Cache - * @options: copy of options string given by user * @uname: string user name to mount hierarchy as * @aname: mount specifier for remote hierarchy * @maxdata: maximum data to be sent/recvd per protocol message diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h index b83ebfbf3fdc..5a0db6dec8d1 100644 --- a/fs/9p/v9fs_vfs.h +++ b/fs/9p/v9fs_vfs.h @@ -68,14 +68,10 @@ int v9fs_file_open(struct inode *inode, struct file *file); void v9fs_inode2stat(struct inode *inode, struct p9_wstat *stat); int v9fs_uflags2omode(int uflags, int extended); -ssize_t v9fs_file_readn(struct file *, char *, char __user *, u32, u64); -ssize_t v9fs_fid_readn(struct p9_fid *, char *, char __user *, u32, u64); void v9fs_blank_wstat(struct p9_wstat *wstat); int v9fs_vfs_setattr_dotl(struct dentry *, struct iattr *); int v9fs_file_fsync_dotl(struct file *filp, loff_t start, loff_t end, int datasync); -ssize_t v9fs_file_write_internal(struct inode *, struct p9_fid *, - const char __user *, size_t, loff_t *, int); int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode); int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode); static inline void v9fs_invalidate_inode_attr(struct inode *inode) diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index eb14e055ea83..e9e04376c52c 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -33,7 +33,7 @@ #include <linux/pagemap.h> #include <linux/idr.h> #include <linux/sched.h> -#include <linux/aio.h> +#include <linux/uio.h> #include <net/9p/9p.h> #include <net/9p/client.h> @@ -51,12 +51,11 @@ */ static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page) { - int retval; - loff_t offset; - char *buffer; - struct inode *inode; + struct inode *inode = page->mapping->host; + struct bio_vec bvec = {.bv_page = page, .bv_len = PAGE_SIZE}; + struct iov_iter to; + int retval, err; - inode = page->mapping->host; p9_debug(P9_DEBUG_VFS, "\n"); BUG_ON(!PageLocked(page)); @@ -65,16 +64,16 @@ static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page) if (retval == 0) return retval; - buffer = kmap(page); - offset = page_offset(page); + iov_iter_bvec(&to, ITER_BVEC | READ, &bvec, 1, PAGE_SIZE); - retval = v9fs_fid_readn(fid, buffer, NULL, PAGE_CACHE_SIZE, offset); - if (retval < 0) { + retval = p9_client_read(fid, page_offset(page), &to, &err); + if (err) { v9fs_uncache_page(inode, page); + retval = err; goto done; } - memset(buffer + retval, 0, PAGE_CACHE_SIZE - retval); + zero_user(page, retval, PAGE_SIZE - retval); flush_dcache_page(page); SetPageUptodate(page); @@ -82,7 +81,6 @@ static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page) retval = 0; done: - kunmap(page); unlock_page(page); return retval; } @@ -161,41 +159,32 @@ static void v9fs_invalidate_page(struct page *page, unsigned int offset, static int v9fs_vfs_writepage_locked(struct page *page) { - char *buffer; - int retval, len; - loff_t offset, size; - mm_segment_t old_fs; - struct v9fs_inode *v9inode; struct inode *inode = page->mapping->host; + struct v9fs_inode *v9inode = V9FS_I(inode); + loff_t size = i_size_read(inode); + struct iov_iter from; + struct bio_vec bvec; + int err, len; - v9inode = V9FS_I(inode); - size = i_size_read(inode); if (page->index == size >> PAGE_CACHE_SHIFT) len = size & ~PAGE_CACHE_MASK; else len = PAGE_CACHE_SIZE; - set_page_writeback(page); - - buffer = kmap(page); - offset = page_offset(page); + bvec.bv_page = page; + bvec.bv_offset = 0; + bvec.bv_len = len; + iov_iter_bvec(&from, ITER_BVEC | WRITE, &bvec, 1, len); - old_fs = get_fs(); - set_fs(get_ds()); /* We should have writeback_fid always set */ BUG_ON(!v9inode->writeback_fid); - retval = v9fs_file_write_internal(inode, - v9inode->writeback_fid, - (__force const char __user *)buffer, - len, &offset, 0); - if (retval > 0) - retval = 0; + set_page_writeback(page); + + p9_client_write(v9inode->writeback_fid, page_offset(page), &from, &err); - set_fs(old_fs); - kunmap(page); end_page_writeback(page); - return retval; + return err; } static int v9fs_vfs_writepage(struct page *page, struct writeback_control *wbc) @@ -241,11 +230,8 @@ static int v9fs_launder_page(struct page *page) /** * v9fs_direct_IO - 9P address space operation for direct I/O - * @rw: direction (read or write) * @iocb: target I/O control block - * @iov: array of vectors that define I/O buffer * @pos: offset in file to begin the operation - * @nr_segs: size of iovec array * * The presence of v9fs_direct_IO() in the address space ops vector * allowes open() O_DIRECT flags which would have failed otherwise. @@ -259,18 +245,23 @@ static int v9fs_launder_page(struct page *page) * */ static ssize_t -v9fs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos) +v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos) { - /* - * FIXME - * Now that we do caching with cache mode enabled, We need - * to support direct IO - */ - p9_debug(P9_DEBUG_VFS, "v9fs_direct_IO: v9fs_direct_IO (%pD) off/no(%lld/%lu) EINVAL\n", - iocb->ki_filp, - (long long)pos, iter->nr_segs); - - return -EINVAL; + struct file *file = iocb->ki_filp; + ssize_t n; + int err = 0; + if (iov_iter_rw(iter) == WRITE) { + n = p9_client_write(file->private_data, pos, iter, &err); + if (n) { + struct inode *inode = file_inode(file); + loff_t i_size = i_size_read(inode); + if (pos + n > i_size) + inode_add_bytes(inode, pos + n - i_size); + } + } else { + n = p9_client_read(file->private_data, pos, iter, &err); + } + return n ? n : err; } static int v9fs_write_begin(struct file *filp, struct address_space *mapping, diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c index 4f1151088ebe..76c3b1ab6361 100644 --- a/fs/9p/vfs_dir.c +++ b/fs/9p/vfs_dir.c @@ -33,6 +33,7 @@ #include <linux/inet.h> #include <linux/idr.h> #include <linux/slab.h> +#include <linux/uio.h> #include <net/9p/9p.h> #include <net/9p/client.h> @@ -115,6 +116,7 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx) int buflen; int reclen = 0; struct p9_rdir *rdir; + struct kvec kvec; p9_debug(P9_DEBUG_VFS, "name %pD\n", file); fid = file->private_data; @@ -124,16 +126,21 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx) rdir = v9fs_alloc_rdir_buf(file, buflen); if (!rdir) return -ENOMEM; + kvec.iov_base = rdir->buf; + kvec.iov_len = buflen; while (1) { if (rdir->tail == rdir->head) { - err = v9fs_file_readn(file, rdir->buf, NULL, - buflen, ctx->pos); - if (err <= 0) + struct iov_iter to; + int n; + iov_iter_kvec(&to, READ | ITER_KVEC, &kvec, 1, buflen); + n = p9_client_read(file->private_data, ctx->pos, &to, + &err); + if (err) return err; rdir->head = 0; - rdir->tail = err; + rdir->tail = n; } while (rdir->head < rdir->tail) { p9stat_init(&st); diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index b40133796b87..1ef16bd8280b 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -36,6 +36,8 @@ #include <linux/utsname.h> #include <asm/uaccess.h> #include <linux/idr.h> +#include <linux/uio.h> +#include <linux/slab.h> #include <net/9p/9p.h> #include <net/9p/client.h> @@ -149,7 +151,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) { struct p9_flock flock; struct p9_fid *fid; - uint8_t status; + uint8_t status = P9_LOCK_ERROR; int res = 0; unsigned char fl_type; @@ -194,7 +196,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) for (;;) { res = p9_client_lock_dotl(fid, &flock, &status); if (res < 0) - break; + goto out_unlock; if (status != P9_LOCK_BLOCKED) break; @@ -212,14 +214,16 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) case P9_LOCK_BLOCKED: res = -EAGAIN; break; + default: + WARN_ONCE(1, "unknown lock status code: %d\n", status); + /* fallthough */ case P9_LOCK_ERROR: case P9_LOCK_GRACE: res = -ENOLCK; break; - default: - BUG(); } +out_unlock: /* * incase server returned error for lock request, revert * it locally @@ -285,6 +289,7 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl) fl->fl_end = glock.start + glock.length - 1; fl->fl_pid = glock.proc_id; } + kfree(glock.client_id); return res; } @@ -364,63 +369,6 @@ out_err: } /** - * v9fs_fid_readn - read from a fid - * @fid: fid to read - * @data: data buffer to read data into - * @udata: user data buffer to read data into - * @count: size of buffer - * @offset: offset at which to read data - * - */ -ssize_t -v9fs_fid_readn(struct p9_fid *fid, char *data, char __user *udata, u32 count, - u64 offset) -{ - int n, total, size; - - p9_debug(P9_DEBUG_VFS, "fid %d offset %llu count %d\n", - fid->fid, (long long unsigned)offset, count); - n = 0; - total = 0; - size = fid->iounit ? fid->iounit : fid->clnt->msize - P9_IOHDRSZ; - do { - n = p9_client_read(fid, data, udata, offset, count); - if (n <= 0) - break; - - if (data) - data += n; - if (udata) - udata += n; - - offset += n; - count -= n; - total += n; - } while (count > 0 && n == size); - - if (n < 0) - total = n; - - return total; -} - -/** - * v9fs_file_readn - read from a file - * @filp: file pointer to read - * @data: data buffer to read data into - * @udata: user data buffer to read data into - * @count: size of buffer - * @offset: offset at which to read data - * - */ -ssize_t -v9fs_file_readn(struct file *filp, char *data, char __user *udata, u32 count, - u64 offset) -{ - return v9fs_fid_readn(filp->private_data, data, udata, count, offset); -} - -/** * v9fs_file_read - read from a file * @filp: file pointer to read * @udata: user data buffer to read data into @@ -430,69 +378,22 @@ v9fs_file_readn(struct file *filp, char *data, char __user *udata, u32 count, */ static ssize_t -v9fs_file_read(struct file *filp, char __user *udata, size_t count, - loff_t * offset) +v9fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { - int ret; - struct p9_fid *fid; - size_t size; - - p9_debug(P9_DEBUG_VFS, "count %zu offset %lld\n", count, *offset); - fid = filp->private_data; + struct p9_fid *fid = iocb->ki_filp->private_data; + int ret, err; - size = fid->iounit ? fid->iounit : fid->clnt->msize - P9_IOHDRSZ; - if (count > size) - ret = v9fs_file_readn(filp, NULL, udata, count, *offset); - else - ret = p9_client_read(fid, NULL, udata, *offset, count); + p9_debug(P9_DEBUG_VFS, "count %zu offset %lld\n", + iov_iter_count(to), iocb->ki_pos); - if (ret > 0) - *offset += ret; + ret = p9_client_read(fid, iocb->ki_pos, to, &err); + if (!ret) + return err; + iocb->ki_pos += ret; return ret; } -ssize_t -v9fs_file_write_internal(struct inode *inode, struct p9_fid *fid, - const char __user *data, size_t count, - loff_t *offset, int invalidate) -{ - int n; - loff_t i_size; - size_t total = 0; - loff_t origin = *offset; - unsigned long pg_start, pg_end; - - p9_debug(P9_DEBUG_VFS, "data %p count %d offset %x\n", - data, (int)count, (int)*offset); - - do { - n = p9_client_write(fid, NULL, data+total, origin+total, count); - if (n <= 0) - break; - count -= n; - total += n; - } while (count > 0); - - if (invalidate && (total > 0)) { - pg_start = origin >> PAGE_CACHE_SHIFT; - pg_end = (origin + total - 1) >> PAGE_CACHE_SHIFT; - if (inode->i_mapping && inode->i_mapping->nrpages) - invalidate_inode_pages2_range(inode->i_mapping, - pg_start, pg_end); - *offset += total; - i_size = i_size_read(inode); - if (*offset > i_size) { - inode_add_bytes(inode, *offset - i_size); - i_size_write(inode, *offset); - } - } - if (n < 0) - return n; - - return total; -} - /** * v9fs_file_write - write to a file * @filp: file pointer to write @@ -502,35 +403,39 @@ v9fs_file_write_internal(struct inode *inode, struct p9_fid *fid, * */ static ssize_t -v9fs_file_write(struct file *filp, const char __user * data, - size_t count, loff_t *offset) +v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { - ssize_t retval = 0; - loff_t origin = *offset; - - - retval = generic_write_checks(filp, &origin, &count, 0); - if (retval) - goto out; + struct file *file = iocb->ki_filp; + ssize_t retval; + loff_t origin; + int err = 0; - retval = -EINVAL; - if ((ssize_t) count < 0) - goto out; - retval = 0; - if (!count) - goto out; + retval = generic_write_checks(iocb, from); + if (retval <= 0) + return retval; - retval = v9fs_file_write_internal(file_inode(filp), - filp->private_data, - data, count, &origin, 1); - /* update offset on successful write */ - if (retval > 0) - *offset = origin; -out: - return retval; + origin = iocb->ki_pos; + retval = p9_client_write(file->private_data, iocb->ki_pos, from, &err); + if (retval > 0) { + struct inode *inode = file_inode(file); + loff_t i_size; + unsigned long pg_start, pg_end; + pg_start = origin >> PAGE_CACHE_SHIFT; + pg_end = (origin + retval - 1) >> PAGE_CACHE_SHIFT; + if (inode->i_mapping && inode->i_mapping->nrpages) + invalidate_inode_pages2_range(inode->i_mapping, + pg_start, pg_end); + iocb->ki_pos += retval; + i_size = i_size_read(inode); + if (iocb->ki_pos > i_size) { + inode_add_bytes(inode, iocb->ki_pos - i_size); + i_size_write(inode, iocb->ki_pos); + } + return retval; + } + return err; } - static int v9fs_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync) { @@ -657,44 +562,6 @@ out_unlock: return VM_FAULT_NOPAGE; } -static ssize_t -v9fs_direct_read(struct file *filp, char __user *udata, size_t count, - loff_t *offsetp) -{ - loff_t size, offset; - struct inode *inode; - struct address_space *mapping; - - offset = *offsetp; - mapping = filp->f_mapping; - inode = mapping->host; - if (!count) - return 0; - size = i_size_read(inode); - if (offset < size) - filemap_write_and_wait_range(mapping, offset, - offset + count - 1); - - return v9fs_file_read(filp, udata, count, offsetp); -} - -/** - * v9fs_cached_file_read - read from a file - * @filp: file pointer to read - * @data: user data buffer to read data into - * @count: size of buffer - * @offset: offset at which to read data - * - */ -static ssize_t -v9fs_cached_file_read(struct file *filp, char __user *data, size_t count, - loff_t *offset) -{ - if (filp->f_flags & O_DIRECT) - return v9fs_direct_read(filp, data, count, offset); - return new_sync_read(filp, data, count, offset); -} - /** * v9fs_mmap_file_read - read from a file * @filp: file pointer to read @@ -704,84 +571,12 @@ v9fs_cached_file_read(struct file *filp, char __user *data, size_t count, * */ static ssize_t -v9fs_mmap_file_read(struct file *filp, char __user *data, size_t count, - loff_t *offset) +v9fs_mmap_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { /* TODO: Check if there are dirty pages */ - return v9fs_file_read(filp, data, count, offset); -} - -static ssize_t -v9fs_direct_write(struct file *filp, const char __user * data, - size_t count, loff_t *offsetp) -{ - loff_t offset; - ssize_t retval; - struct inode *inode; - struct address_space *mapping; - - offset = *offsetp; - mapping = filp->f_mapping; - inode = mapping->host; - if (!count) - return 0; - - mutex_lock(&inode->i_mutex); - retval = filemap_write_and_wait_range(mapping, offset, - offset + count - 1); - if (retval) - goto err_out; - /* - * After a write we want buffered reads to be sure to go to disk to get - * the new data. We invalidate clean cached page from the region we're - * about to write. We do this *before* the write so that if we fail - * here we fall back to buffered write - */ - if (mapping->nrpages) { - pgoff_t pg_start = offset >> PAGE_CACHE_SHIFT; - pgoff_t pg_end = (offset + count - 1) >> PAGE_CACHE_SHIFT; - - retval = invalidate_inode_pages2_range(mapping, - pg_start, pg_end); - /* - * If a page can not be invalidated, fall back - * to buffered write. - */ - if (retval) { - if (retval == -EBUSY) - goto buff_write; - goto err_out; - } - } - retval = v9fs_file_write(filp, data, count, offsetp); -err_out: - mutex_unlock(&inode->i_mutex); - return retval; - -buff_write: - mutex_unlock(&inode->i_mutex); - return new_sync_write(filp, data, count, offsetp); -} - -/** - * v9fs_cached_file_write - write to a file - * @filp: file pointer to write - * @data: data buffer to write data from - * @count: size of buffer - * @offset: offset at which to write data - * - */ -static ssize_t -v9fs_cached_file_write(struct file *filp, const char __user * data, - size_t count, loff_t *offset) -{ - - if (filp->f_flags & O_DIRECT) - return v9fs_direct_write(filp, data, count, offset); - return new_sync_write(filp, data, count, offset); + return v9fs_file_read_iter(iocb, to); } - /** * v9fs_mmap_file_write - write to a file * @filp: file pointer to write @@ -791,14 +586,13 @@ v9fs_cached_file_write(struct file *filp, const char __user * data, * */ static ssize_t -v9fs_mmap_file_write(struct file *filp, const char __user *data, - size_t count, loff_t *offset) +v9fs_mmap_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { /* * TODO: invalidate mmaps on filp's inode between * offset and offset+count */ - return v9fs_file_write(filp, data, count, offset); + return v9fs_file_write_iter(iocb, from); } static void v9fs_mmap_vm_close(struct vm_area_struct *vma) @@ -843,8 +637,6 @@ static const struct vm_operations_struct v9fs_mmap_file_vm_ops = { const struct file_operations v9fs_cached_file_operations = { .llseek = generic_file_llseek, - .read = v9fs_cached_file_read, - .write = v9fs_cached_file_write, .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, .open = v9fs_file_open, @@ -856,8 +648,6 @@ const struct file_operations v9fs_cached_file_operations = { const struct file_operations v9fs_cached_file_operations_dotl = { .llseek = generic_file_llseek, - .read = v9fs_cached_file_read, - .write = v9fs_cached_file_write, .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, .open = v9fs_file_open, @@ -870,8 +660,8 @@ const struct file_operations v9fs_cached_file_operations_dotl = { const struct file_operations v9fs_file_operations = { .llseek = generic_file_llseek, - .read = v9fs_file_read, - .write = v9fs_file_write, + .read_iter = v9fs_file_read_iter, + .write_iter = v9fs_file_write_iter, .open = v9fs_file_open, .release = v9fs_dir_release, .lock = v9fs_file_lock, @@ -881,8 +671,8 @@ const struct file_operations v9fs_file_operations = { const struct file_operations v9fs_file_operations_dotl = { .llseek = generic_file_llseek, - .read = v9fs_file_read, - .write = v9fs_file_write, + .read_iter = v9fs_file_read_iter, + .write_iter = v9fs_file_write_iter, .open = v9fs_file_open, .release = v9fs_dir_release, .lock = v9fs_file_lock_dotl, @@ -893,8 +683,8 @@ const struct file_operations v9fs_file_operations_dotl = { const struct file_operations v9fs_mmap_file_operations = { .llseek = generic_file_llseek, - .read = v9fs_mmap_file_read, - .write = v9fs_mmap_file_write, + .read_iter = v9fs_mmap_file_read_iter, + .write_iter = v9fs_mmap_file_write_iter, .open = v9fs_file_open, .release = v9fs_dir_release, .lock = v9fs_file_lock, @@ -904,8 +694,8 @@ const struct file_operations v9fs_mmap_file_operations = { const struct file_operations v9fs_mmap_file_operations_dotl = { .llseek = generic_file_llseek, - .read = v9fs_mmap_file_read, - .write = v9fs_mmap_file_write, + .read_iter = v9fs_mmap_file_read_iter, + .write_iter = v9fs_mmap_file_write_iter, .open = v9fs_file_open, .release = v9fs_dir_release, .lock = v9fs_file_lock_dotl, diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c index f95e01e058e4..0cf44b6cccd6 100644 --- a/fs/9p/xattr.c +++ b/fs/9p/xattr.c @@ -15,6 +15,7 @@ #include <linux/module.h> #include <linux/fs.h> #include <linux/sched.h> +#include <linux/uio.h> #include <net/9p/9p.h> #include <net/9p/client.h> @@ -25,50 +26,34 @@ ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name, void *buffer, size_t buffer_size) { ssize_t retval; - int msize, read_count; - u64 offset = 0, attr_size; + u64 attr_size; struct p9_fid *attr_fid; + struct kvec kvec = {.iov_base = buffer, .iov_len = buffer_size}; + struct iov_iter to; + int err; + + iov_iter_kvec(&to, READ | ITER_KVEC, &kvec, 1, buffer_size); attr_fid = p9_client_xattrwalk(fid, name, &attr_size); if (IS_ERR(attr_fid)) { retval = PTR_ERR(attr_fid); p9_debug(P9_DEBUG_VFS, "p9_client_attrwalk failed %zd\n", retval); - attr_fid = NULL; - goto error; - } - if (!buffer_size) { - /* request to get the attr_size */ - retval = attr_size; - goto error; + return retval; } if (attr_size > buffer_size) { - retval = -ERANGE; - goto error; - } - msize = attr_fid->clnt->msize; - while (attr_size) { - if (attr_size > (msize - P9_IOHDRSZ)) - read_count = msize - P9_IOHDRSZ; + if (!buffer_size) /* request to get the attr_size */ + retval = attr_size; else - read_count = attr_size; - read_count = p9_client_read(attr_fid, ((char *)buffer)+offset, - NULL, offset, read_count); - if (read_count < 0) { - /* error in xattr read */ - retval = read_count; - goto error; - } - offset += read_count; - attr_size -= read_count; + retval = -ERANGE; + } else { + iov_iter_truncate(&to, attr_size); + retval = p9_client_read(attr_fid, 0, &to, &err); + if (err) + retval = err; } - /* Total read xattr bytes */ - retval = offset; -error: - if (attr_fid) - p9_client_clunk(attr_fid); + p9_client_clunk(attr_fid); return retval; - } @@ -120,8 +105,11 @@ int v9fs_xattr_set(struct dentry *dentry, const char *name, int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name, const void *value, size_t value_len, int flags) { - u64 offset = 0; - int retval, msize, write_count; + struct kvec kvec = {.iov_base = (void *)value, .iov_len = value_len}; + struct iov_iter from; + int retval; + + iov_iter_kvec(&from, WRITE | ITER_KVEC, &kvec, 1, value_len); p9_debug(P9_DEBUG_VFS, "name = %s value_len = %zu flags = %d\n", name, value_len, flags); @@ -135,29 +123,11 @@ int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name, * On success fid points to xattr */ retval = p9_client_xattrcreate(fid, name, value_len, flags); - if (retval < 0) { + if (retval < 0) p9_debug(P9_DEBUG_VFS, "p9_client_xattrcreate failed %d\n", retval); - goto err; - } - msize = fid->clnt->msize; - while (value_len) { - if (value_len > (msize - P9_IOHDRSZ)) - write_count = msize - P9_IOHDRSZ; - else - write_count = value_len; - write_count = p9_client_write(fid, ((char *)value)+offset, - NULL, offset, write_count); - if (write_count < 0) { - /* error in xattr write */ - retval = write_count; - goto err; - } - offset += write_count; - value_len -= write_count; - } - retval = 0; -err: + else + p9_client_write(fid, 0, &from, &retval); p9_client_clunk(fid); return retval; } diff --git a/fs/Kconfig b/fs/Kconfig index ec35851e5b71..011f43365d7b 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -32,6 +32,7 @@ source "fs/gfs2/Kconfig" source "fs/ocfs2/Kconfig" source "fs/btrfs/Kconfig" source "fs/nilfs2/Kconfig" +source "fs/f2fs/Kconfig" config FS_DAX bool "Direct Access (DAX) support" @@ -217,7 +218,6 @@ source "fs/pstore/Kconfig" source "fs/sysv/Kconfig" source "fs/ufs/Kconfig" source "fs/exofs/Kconfig" -source "fs/f2fs/Kconfig" endif # MISC_FILESYSTEMS diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index 270c48148f79..2d0cbbd14cfc 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -27,9 +27,6 @@ config COMPAT_BINFMT_ELF bool depends on COMPAT && BINFMT_ELF -config ARCH_BINFMT_ELF_RANDOMIZE_PIE - bool - config ARCH_BINFMT_ELF_STATE bool diff --git a/fs/Makefile b/fs/Makefile index a88ac4838c9e..cb92fd4c3172 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -118,6 +118,7 @@ obj-$(CONFIG_HOSTFS) += hostfs/ obj-$(CONFIG_HPPFS) += hppfs/ obj-$(CONFIG_CACHEFILES) += cachefiles/ obj-$(CONFIG_DEBUG_FS) += debugfs/ +obj-$(CONFIG_TRACING) += tracefs/ obj-$(CONFIG_OCFS2_FS) += ocfs2/ obj-$(CONFIG_BTRFS_FS) += btrfs/ obj-$(CONFIG_GFS2_FS) += gfs2/ diff --git a/fs/adfs/dir_fplus.c b/fs/adfs/dir_fplus.c index f2ba88ab4aed..82d14cdf70f9 100644 --- a/fs/adfs/dir_fplus.c +++ b/fs/adfs/dir_fplus.c @@ -61,6 +61,7 @@ adfs_fplus_read(struct super_block *sb, unsigned int id, unsigned int sz, struct kcalloc(size, sizeof(struct buffer_head *), GFP_KERNEL); if (!bh_fplus) { + ret = -ENOMEM; adfs_error(sb, "not enough memory for" " dir object %X (%d blocks)", id, size); goto out; diff --git a/fs/adfs/file.c b/fs/adfs/file.c index 07c9edce5aa7..46c0d5671cd5 100644 --- a/fs/adfs/file.c +++ b/fs/adfs/file.c @@ -23,11 +23,9 @@ const struct file_operations adfs_file_operations = { .llseek = generic_file_llseek, - .read = new_sync_read, .read_iter = generic_file_read_iter, .mmap = generic_file_mmap, .fsync = generic_file_fsync, - .write = new_sync_write, .write_iter = generic_file_write_iter, .splice_read = generic_file_splice_read, }; diff --git a/fs/adfs/super.c b/fs/adfs/super.c index 9852bdf34d76..a19c31d3f369 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -316,7 +316,7 @@ static struct adfs_discmap *adfs_read_map(struct super_block *sb, struct adfs_di dm = kmalloc(nzones * sizeof(*dm), GFP_KERNEL); if (dm == NULL) { adfs_error(sb, "not enough memory"); - return NULL; + return ERR_PTR(-ENOMEM); } for (zone = 0; zone < nzones; zone++, map_addr++) { @@ -349,7 +349,7 @@ error_free: brelse(dm[zone].dm_bh); kfree(dm); - return NULL; + return ERR_PTR(-EIO); } static inline unsigned long adfs_discsize(struct adfs_discrecord *dr, int block_bits) @@ -370,6 +370,7 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent) unsigned char *b_data; struct adfs_sb_info *asb; struct inode *root; + int ret = -EINVAL; sb->s_flags |= MS_NODIRATIME; @@ -391,6 +392,7 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent) sb_set_blocksize(sb, BLOCK_SIZE); if (!(bh = sb_bread(sb, ADFS_DISCRECORD / BLOCK_SIZE))) { adfs_error(sb, "unable to read superblock"); + ret = -EIO; goto error; } @@ -400,6 +402,7 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent) if (!silent) printk("VFS: Can't find an adfs filesystem on dev " "%s.\n", sb->s_id); + ret = -EINVAL; goto error_free_bh; } @@ -412,6 +415,7 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent) if (!silent) printk("VPS: Can't find an adfs filesystem on dev " "%s.\n", sb->s_id); + ret = -EINVAL; goto error_free_bh; } @@ -421,11 +425,13 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent) if (!bh) { adfs_error(sb, "couldn't read superblock on " "2nd try."); + ret = -EIO; goto error; } b_data = bh->b_data + (ADFS_DISCRECORD % sb->s_blocksize); if (adfs_checkbblk(b_data)) { adfs_error(sb, "disc record mismatch, very weird!"); + ret = -EINVAL; goto error_free_bh; } dr = (struct adfs_discrecord *)(b_data + ADFS_DR_OFFSET); @@ -433,6 +439,7 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent) if (!silent) printk(KERN_ERR "VFS: Unsupported blocksize on dev " "%s.\n", sb->s_id); + ret = -EINVAL; goto error; } @@ -447,10 +454,12 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent) asb->s_size = adfs_discsize(dr, sb->s_blocksize_bits); asb->s_version = dr->format_version; asb->s_log2sharesize = dr->log2sharesize; - + asb->s_map = adfs_read_map(sb, dr); - if (!asb->s_map) + if (IS_ERR(asb->s_map)) { + ret = PTR_ERR(asb->s_map); goto error_free_bh; + } brelse(bh); @@ -499,6 +508,7 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent) brelse(asb->s_map[i].dm_bh); kfree(asb->s_map); adfs_error(sb, "get root inode failed\n"); + ret = -EIO; goto error; } return 0; @@ -508,7 +518,7 @@ error_free_bh: error: sb->s_fs_info = NULL; kfree(asb); - return -EINVAL; + return ret; } static struct dentry *adfs_mount(struct file_system_type *fs_type, diff --git a/fs/affs/affs.h b/fs/affs/affs.h index c8764bd7497d..cffe8370fb44 100644 --- a/fs/affs/affs.h +++ b/fs/affs/affs.h @@ -106,18 +106,22 @@ struct affs_sb_info { spinlock_t work_lock; /* protects sb_work and work_queued */ }; -#define SF_INTL 0x0001 /* International filesystem. */ -#define SF_BM_VALID 0x0002 /* Bitmap is valid. */ -#define SF_IMMUTABLE 0x0004 /* Protection bits cannot be changed */ -#define SF_QUIET 0x0008 /* chmod errors will be not reported */ -#define SF_SETUID 0x0010 /* Ignore Amiga uid */ -#define SF_SETGID 0x0020 /* Ignore Amiga gid */ -#define SF_SETMODE 0x0040 /* Ignore Amiga protection bits */ -#define SF_MUFS 0x0100 /* Use MUFS uid/gid mapping */ -#define SF_OFS 0x0200 /* Old filesystem */ -#define SF_PREFIX 0x0400 /* Buffer for prefix is allocated */ -#define SF_VERBOSE 0x0800 /* Talk about fs when mounting */ -#define SF_NO_TRUNCATE 0x1000 /* Don't truncate filenames */ +#define AFFS_MOUNT_SF_INTL 0x0001 /* International filesystem. */ +#define AFFS_MOUNT_SF_BM_VALID 0x0002 /* Bitmap is valid. */ +#define AFFS_MOUNT_SF_IMMUTABLE 0x0004 /* Protection bits cannot be changed */ +#define AFFS_MOUNT_SF_QUIET 0x0008 /* chmod errors will be not reported */ +#define AFFS_MOUNT_SF_SETUID 0x0010 /* Ignore Amiga uid */ +#define AFFS_MOUNT_SF_SETGID 0x0020 /* Ignore Amiga gid */ +#define AFFS_MOUNT_SF_SETMODE 0x0040 /* Ignore Amiga protection bits */ +#define AFFS_MOUNT_SF_MUFS 0x0100 /* Use MUFS uid/gid mapping */ +#define AFFS_MOUNT_SF_OFS 0x0200 /* Old filesystem */ +#define AFFS_MOUNT_SF_PREFIX 0x0400 /* Buffer for prefix is allocated */ +#define AFFS_MOUNT_SF_VERBOSE 0x0800 /* Talk about fs when mounting */ +#define AFFS_MOUNT_SF_NO_TRUNCATE 0x1000 /* Don't truncate filenames */ + +#define affs_clear_opt(o, opt) (o &= ~AFFS_MOUNT_##opt) +#define affs_set_opt(o, opt) (o |= AFFS_MOUNT_##opt) +#define affs_test_opt(o, opt) ((o) & AFFS_MOUNT_##opt) /* short cut to get to the affs specific sb data */ static inline struct affs_sb_info *AFFS_SB(struct super_block *sb) diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c index 388da1ea815d..5022ac96aa40 100644 --- a/fs/affs/amigaffs.c +++ b/fs/affs/amigaffs.c @@ -472,7 +472,8 @@ bool affs_nofilenametruncate(const struct dentry *dentry) { struct inode *inode = dentry->d_inode; - return AFFS_SB(inode->i_sb)->s_flags & SF_NO_TRUNCATE; + + return affs_test_opt(AFFS_SB(inode->i_sb)->s_flags, SF_NO_TRUNCATE); } diff --git a/fs/affs/file.c b/fs/affs/file.c index d2468bf95669..659c579c4588 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -12,7 +12,7 @@ * affs regular file handling primitives */ -#include <linux/aio.h> +#include <linux/uio.h> #include "affs.h" static struct buffer_head *affs_get_extblock_slow(struct inode *inode, u32 ext); @@ -389,8 +389,7 @@ static void affs_write_failed(struct address_space *mapping, loff_t to) } static ssize_t -affs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -398,15 +397,15 @@ affs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, size_t count = iov_iter_count(iter); ssize_t ret; - if (rw == WRITE) { + if (iov_iter_rw(iter) == WRITE) { loff_t size = offset + count; if (AFFS_I(inode)->mmu_private < size) return 0; } - ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, affs_get_block); - if (ret < 0 && (rw & WRITE)) + ret = blockdev_direct_IO(iocb, inode, iter, offset, affs_get_block); + if (ret < 0 && iov_iter_rw(iter) == WRITE) affs_write_failed(mapping, offset + count); return ret; } @@ -699,8 +698,10 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping, boff = tmp % bsize; if (boff) { bh = affs_bread_ino(inode, bidx, 0); - if (IS_ERR(bh)) - return PTR_ERR(bh); + if (IS_ERR(bh)) { + written = PTR_ERR(bh); + goto err_first_bh; + } tmp = min(bsize - boff, to - from); BUG_ON(boff + tmp > bsize || tmp > bsize); memcpy(AFFS_DATA(bh) + boff, data + from, tmp); @@ -712,14 +713,16 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping, bidx++; } else if (bidx) { bh = affs_bread_ino(inode, bidx - 1, 0); - if (IS_ERR(bh)) - return PTR_ERR(bh); + if (IS_ERR(bh)) { + written = PTR_ERR(bh); + goto err_first_bh; + } } while (from + bsize <= to) { prev_bh = bh; bh = affs_getemptyblk_ino(inode, bidx); if (IS_ERR(bh)) - goto out; + goto err_bh; memcpy(AFFS_DATA(bh), data + from, bsize); if (buffer_new(bh)) { AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA); @@ -751,7 +754,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping, prev_bh = bh; bh = affs_bread_ino(inode, bidx, 1); if (IS_ERR(bh)) - goto out; + goto err_bh; tmp = min(bsize, to - from); BUG_ON(tmp > bsize); memcpy(AFFS_DATA(bh), data + from, tmp); @@ -790,12 +793,13 @@ done: if (tmp > inode->i_size) inode->i_size = AFFS_I(inode)->mmu_private = tmp; +err_first_bh: unlock_page(page); page_cache_release(page); return written; -out: +err_bh: bh = prev_bh; if (!written) written = PTR_ERR(bh); @@ -910,7 +914,7 @@ affs_truncate(struct inode *inode) if (inode->i_size) { AFFS_I(inode)->i_blkcnt = last_blk + 1; AFFS_I(inode)->i_extcnt = ext + 1; - if (AFFS_SB(sb)->s_flags & SF_OFS) { + if (affs_test_opt(AFFS_SB(sb)->s_flags, SF_OFS)) { struct buffer_head *bh = affs_bread_ino(inode, last_blk, 0); u32 tmp; if (IS_ERR(bh)) { @@ -964,9 +968,7 @@ int affs_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync) } const struct file_operations affs_file_operations = { .llseek = generic_file_llseek, - .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = new_sync_write, .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .open = affs_file_open, diff --git a/fs/affs/inode.c b/fs/affs/inode.c index 6f34510449e8..9628003ccd2f 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -66,23 +66,23 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino) AFFS_I(inode)->i_lastalloc = 0; AFFS_I(inode)->i_pa_cnt = 0; - if (sbi->s_flags & SF_SETMODE) + if (affs_test_opt(sbi->s_flags, SF_SETMODE)) inode->i_mode = sbi->s_mode; else inode->i_mode = prot_to_mode(prot); id = be16_to_cpu(tail->uid); - if (id == 0 || sbi->s_flags & SF_SETUID) + if (id == 0 || affs_test_opt(sbi->s_flags, SF_SETUID)) inode->i_uid = sbi->s_uid; - else if (id == 0xFFFF && sbi->s_flags & SF_MUFS) + else if (id == 0xFFFF && affs_test_opt(sbi->s_flags, SF_MUFS)) i_uid_write(inode, 0); else i_uid_write(inode, id); id = be16_to_cpu(tail->gid); - if (id == 0 || sbi->s_flags & SF_SETGID) + if (id == 0 || affs_test_opt(sbi->s_flags, SF_SETGID)) inode->i_gid = sbi->s_gid; - else if (id == 0xFFFF && sbi->s_flags & SF_MUFS) + else if (id == 0xFFFF && affs_test_opt(sbi->s_flags, SF_MUFS)) i_gid_write(inode, 0); else i_gid_write(inode, id); @@ -94,7 +94,7 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino) /* fall through */ case ST_USERDIR: if (be32_to_cpu(tail->stype) == ST_USERDIR || - sbi->s_flags & SF_SETMODE) { + affs_test_opt(sbi->s_flags, SF_SETMODE)) { if (inode->i_mode & S_IRUSR) inode->i_mode |= S_IXUSR; if (inode->i_mode & S_IRGRP) @@ -133,7 +133,8 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino) } if (tail->link_chain) set_nlink(inode, 2); - inode->i_mapping->a_ops = (sbi->s_flags & SF_OFS) ? &affs_aops_ofs : &affs_aops; + inode->i_mapping->a_ops = affs_test_opt(sbi->s_flags, SF_OFS) ? + &affs_aops_ofs : &affs_aops; inode->i_op = &affs_file_inode_operations; inode->i_fop = &affs_file_operations; break; @@ -190,15 +191,15 @@ affs_write_inode(struct inode *inode, struct writeback_control *wbc) if (!(inode->i_ino == AFFS_SB(sb)->s_root_block)) { uid = i_uid_read(inode); gid = i_gid_read(inode); - if (AFFS_SB(sb)->s_flags & SF_MUFS) { + if (affs_test_opt(AFFS_SB(sb)->s_flags, SF_MUFS)) { if (uid == 0 || uid == 0xFFFF) uid = uid ^ ~0; if (gid == 0 || gid == 0xFFFF) gid = gid ^ ~0; } - if (!(AFFS_SB(sb)->s_flags & SF_SETUID)) + if (!affs_test_opt(AFFS_SB(sb)->s_flags, SF_SETUID)) tail->uid = cpu_to_be16(uid); - if (!(AFFS_SB(sb)->s_flags & SF_SETGID)) + if (!affs_test_opt(AFFS_SB(sb)->s_flags, SF_SETGID)) tail->gid = cpu_to_be16(gid); } } @@ -221,11 +222,14 @@ affs_notify_change(struct dentry *dentry, struct iattr *attr) if (error) goto out; - if (((attr->ia_valid & ATTR_UID) && (AFFS_SB(inode->i_sb)->s_flags & SF_SETUID)) || - ((attr->ia_valid & ATTR_GID) && (AFFS_SB(inode->i_sb)->s_flags & SF_SETGID)) || + if (((attr->ia_valid & ATTR_UID) && + affs_test_opt(AFFS_SB(inode->i_sb)->s_flags, SF_SETUID)) || + ((attr->ia_valid & ATTR_GID) && + affs_test_opt(AFFS_SB(inode->i_sb)->s_flags, SF_SETGID)) || ((attr->ia_valid & ATTR_MODE) && - (AFFS_SB(inode->i_sb)->s_flags & (SF_SETMODE | SF_IMMUTABLE)))) { - if (!(AFFS_SB(inode->i_sb)->s_flags & SF_QUIET)) + (AFFS_SB(inode->i_sb)->s_flags & + (AFFS_MOUNT_SF_SETMODE | AFFS_MOUNT_SF_IMMUTABLE)))) { + if (!affs_test_opt(AFFS_SB(inode->i_sb)->s_flags, SF_QUIET)) error = -EPERM; goto out; } diff --git a/fs/affs/namei.c b/fs/affs/namei.c index ffb7bd82c2a5..ec8ca0efb960 100644 --- a/fs/affs/namei.c +++ b/fs/affs/namei.c @@ -53,7 +53,8 @@ affs_intl_toupper(int ch) static inline toupper_t affs_get_toupper(struct super_block *sb) { - return AFFS_SB(sb)->s_flags & SF_INTL ? affs_intl_toupper : affs_toupper; + return affs_test_opt(AFFS_SB(sb)->s_flags, SF_INTL) ? + affs_intl_toupper : affs_toupper; } /* @@ -275,7 +276,8 @@ affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) inode->i_op = &affs_file_inode_operations; inode->i_fop = &affs_file_operations; - inode->i_mapping->a_ops = (AFFS_SB(sb)->s_flags & SF_OFS) ? &affs_aops_ofs : &affs_aops; + inode->i_mapping->a_ops = affs_test_opt(AFFS_SB(sb)->s_flags, SF_OFS) ? + &affs_aops_ofs : &affs_aops; error = affs_add_entry(dir, inode, dentry, ST_FILE); if (error) { clear_nlink(inode); diff --git a/fs/affs/super.c b/fs/affs/super.c index 4cf0e9113fb6..3f89c9e05b40 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -227,22 +227,22 @@ parse_options(char *options, kuid_t *uid, kgid_t *gid, int *mode, int *reserved, if (match_octal(&args[0], &option)) return 0; *mode = option & 0777; - *mount_opts |= SF_SETMODE; + affs_set_opt(*mount_opts, SF_SETMODE); break; case Opt_mufs: - *mount_opts |= SF_MUFS; + affs_set_opt(*mount_opts, SF_MUFS); break; case Opt_notruncate: - *mount_opts |= SF_NO_TRUNCATE; + affs_set_opt(*mount_opts, SF_NO_TRUNCATE); break; case Opt_prefix: *prefix = match_strdup(&args[0]); if (!*prefix) return 0; - *mount_opts |= SF_PREFIX; + affs_set_opt(*mount_opts, SF_PREFIX); break; case Opt_protect: - *mount_opts |= SF_IMMUTABLE; + affs_set_opt(*mount_opts, SF_IMMUTABLE); break; case Opt_reserved: if (match_int(&args[0], reserved)) @@ -258,7 +258,7 @@ parse_options(char *options, kuid_t *uid, kgid_t *gid, int *mode, int *reserved, *gid = make_kgid(current_user_ns(), option); if (!gid_valid(*gid)) return 0; - *mount_opts |= SF_SETGID; + affs_set_opt(*mount_opts, SF_SETGID); break; case Opt_setuid: if (match_int(&args[0], &option)) @@ -266,10 +266,10 @@ parse_options(char *options, kuid_t *uid, kgid_t *gid, int *mode, int *reserved, *uid = make_kuid(current_user_ns(), option); if (!uid_valid(*uid)) return 0; - *mount_opts |= SF_SETUID; + affs_set_opt(*mount_opts, SF_SETUID); break; case Opt_verbose: - *mount_opts |= SF_VERBOSE; + affs_set_opt(*mount_opts, SF_VERBOSE); break; case Opt_volume: { char *vol = match_strdup(&args[0]); @@ -435,30 +435,31 @@ got_root: case MUFS_FS: case MUFS_INTLFFS: case MUFS_DCFFS: - sbi->s_flags |= SF_MUFS; + affs_set_opt(sbi->s_flags, SF_MUFS); /* fall thru */ case FS_INTLFFS: case FS_DCFFS: - sbi->s_flags |= SF_INTL; + affs_set_opt(sbi->s_flags, SF_INTL); break; case MUFS_FFS: - sbi->s_flags |= SF_MUFS; + affs_set_opt(sbi->s_flags, SF_MUFS); break; case FS_FFS: break; case MUFS_OFS: - sbi->s_flags |= SF_MUFS; + affs_set_opt(sbi->s_flags, SF_MUFS); /* fall thru */ case FS_OFS: - sbi->s_flags |= SF_OFS; + affs_set_opt(sbi->s_flags, SF_OFS); sb->s_flags |= MS_NOEXEC; break; case MUFS_DCOFS: case MUFS_INTLOFS: - sbi->s_flags |= SF_MUFS; + affs_set_opt(sbi->s_flags, SF_MUFS); case FS_DCOFS: case FS_INTLOFS: - sbi->s_flags |= SF_INTL | SF_OFS; + affs_set_opt(sbi->s_flags, SF_INTL); + affs_set_opt(sbi->s_flags, SF_OFS); sb->s_flags |= MS_NOEXEC; break; default: @@ -467,7 +468,7 @@ got_root: return -EINVAL; } - if (mount_flags & SF_VERBOSE) { + if (affs_test_opt(mount_flags, SF_VERBOSE)) { u8 len = AFFS_ROOT_TAIL(sb, root_bh)->disk_name[0]; pr_notice("Mounting volume \"%.*s\": Type=%.3s\\%c, Blocksize=%d\n", len > 31 ? 31 : len, @@ -478,7 +479,7 @@ got_root: sb->s_flags |= MS_NODEV | MS_NOSUID; sbi->s_data_blksize = sb->s_blocksize; - if (sbi->s_flags & SF_OFS) + if (affs_test_opt(sbi->s_flags, SF_OFS)) sbi->s_data_blksize -= 24; tmp_flags = sb->s_flags; @@ -493,7 +494,7 @@ got_root: if (IS_ERR(root_inode)) return PTR_ERR(root_inode); - if (AFFS_SB(sb)->s_flags & SF_INTL) + if (affs_test_opt(AFFS_SB(sb)->s_flags, SF_INTL)) sb->s_d_op = &affs_intl_dentry_operations; else sb->s_d_op = &affs_dentry_operations; @@ -520,10 +521,14 @@ affs_remount(struct super_block *sb, int *flags, char *data) int root_block; unsigned long mount_flags; int res = 0; - char *new_opts = kstrdup(data, GFP_KERNEL); + char *new_opts; char volume[32]; char *prefix = NULL; + new_opts = kstrdup(data, GFP_KERNEL); + if (!new_opts) + return -ENOMEM; + pr_debug("%s(flags=0x%x,opts=\"%s\")\n", __func__, *flags, data); sync_filesystem(sb); diff --git a/fs/afs/file.c b/fs/afs/file.c index 932ce07948b3..999bc3caec92 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -31,8 +31,6 @@ const struct file_operations afs_file_operations = { .open = afs_open, .release = afs_release, .llseek = generic_file_llseek, - .read = new_sync_read, - .write = new_sync_write, .read_iter = generic_file_read_iter, .write_iter = afs_file_write, .mmap = generic_file_readonly_mmap, diff --git a/fs/afs/misc.c b/fs/afs/misc.c index 0dd4dafee10b..91ea1aa0d8b3 100644 --- a/fs/afs/misc.c +++ b/fs/afs/misc.c @@ -22,9 +22,12 @@ int afs_abort_to_error(u32 abort_code) { switch (abort_code) { + /* low errno codes inserted into abort namespace */ case 13: return -EACCES; case 27: return -EFBIG; case 30: return -EROFS; + + /* VICE "special error" codes; 101 - 111 */ case VSALVAGE: return -EIO; case VNOVNODE: return -ENOENT; case VNOVOL: return -ENOMEDIUM; @@ -36,11 +39,18 @@ int afs_abort_to_error(u32 abort_code) case VOVERQUOTA: return -EDQUOT; case VBUSY: return -EBUSY; case VMOVED: return -ENXIO; - case 0x2f6df0a: return -EWOULDBLOCK; + + /* Unified AFS error table; ET "uae" == 0x2f6df00 */ + case 0x2f6df00: return -EPERM; + case 0x2f6df01: return -ENOENT; + case 0x2f6df04: return -EIO; + case 0x2f6df0a: return -EAGAIN; + case 0x2f6df0b: return -ENOMEM; case 0x2f6df0c: return -EACCES; case 0x2f6df0f: return -EBUSY; case 0x2f6df10: return -EEXIST; case 0x2f6df11: return -EXDEV; + case 0x2f6df12: return -ENODEV; case 0x2f6df13: return -ENOTDIR; case 0x2f6df14: return -EISDIR; case 0x2f6df15: return -EINVAL; @@ -54,8 +64,12 @@ int afs_abort_to_error(u32 abort_code) case 0x2f6df23: return -ENAMETOOLONG; case 0x2f6df24: return -ENOLCK; case 0x2f6df26: return -ENOTEMPTY; + case 0x2f6df28: return -EWOULDBLOCK; + case 0x2f6df69: return -ENOTCONN; + case 0x2f6df6c: return -ETIMEDOUT; case 0x2f6df78: return -EDQUOT; + /* RXKAD abort codes; from include/rxrpc/packet.h. ET "RXK" == 0x1260B00 */ case RXKADINCONSISTENCY: return -EPROTO; case RXKADPACKETSHORT: return -EPROTO; case RXKADLEVELFAIL: return -EKEYREJECTED; diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index dbc732e9a5c0..3a57a1b0fb51 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -770,15 +770,12 @@ static int afs_deliver_cm_op_id(struct afs_call *call, struct sk_buff *skb, void afs_send_empty_reply(struct afs_call *call) { struct msghdr msg; - struct kvec iov[1]; _enter(""); - iov[0].iov_base = NULL; - iov[0].iov_len = 0; msg.msg_name = NULL; msg.msg_namelen = 0; - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 0, 0); /* WTF? */ + iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, NULL, 0, 0); msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; diff --git a/fs/afs/write.c b/fs/afs/write.c index c13cb08964ed..0714abcd7f32 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -14,7 +14,6 @@ #include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/pagevec.h> -#include <linux/aio.h> #include "internal.h" static int afs_write_back_from_locked_page(struct afs_writeback *wb, @@ -77,6 +77,11 @@ struct kioctx_cpu { unsigned reqs_available; }; +struct ctx_rq_wait { + struct completion comp; + atomic_t count; +}; + struct kioctx { struct percpu_ref users; atomic_t dead; @@ -115,7 +120,7 @@ struct kioctx { /* * signals when all in-flight requests are done */ - struct completion *requests_done; + struct ctx_rq_wait *rq_wait; struct { /* @@ -151,6 +156,38 @@ struct kioctx { unsigned id; }; +/* + * We use ki_cancel == KIOCB_CANCELLED to indicate that a kiocb has been either + * cancelled or completed (this makes a certain amount of sense because + * successful cancellation - io_cancel() - does deliver the completion to + * userspace). + * + * And since most things don't implement kiocb cancellation and we'd really like + * kiocb completion to be lockless when possible, we use ki_cancel to + * synchronize cancellation and completion - we only set it to KIOCB_CANCELLED + * with xchg() or cmpxchg(), see batch_complete_aio() and kiocb_cancel(). + */ +#define KIOCB_CANCELLED ((void *) (~0ULL)) + +struct aio_kiocb { + struct kiocb common; + + struct kioctx *ki_ctx; + kiocb_cancel_fn *ki_cancel; + + struct iocb __user *ki_user_iocb; /* user's aiocb */ + __u64 ki_user_data; /* user's data for completion */ + + struct list_head ki_list; /* the aio core uses this + * for cancellation */ + + /* + * If the aio_resfd field of the userspace iocb is not zero, + * this is the underlying eventfd context to deliver events to. + */ + struct eventfd_ctx *ki_eventfd; +}; + /*------ sysctl variables----*/ static DEFINE_SPINLOCK(aio_nr_lock); unsigned long aio_nr; /* current system wide number of aio requests */ @@ -220,7 +257,7 @@ static int __init aio_setup(void) if (IS_ERR(aio_mnt)) panic("Failed to create aio fs mount."); - kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC); + kiocb_cachep = KMEM_CACHE(aio_kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC); kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC); pr_debug("sizeof(struct page) = %zu\n", sizeof(struct page)); @@ -278,11 +315,11 @@ static int aio_ring_mmap(struct file *file, struct vm_area_struct *vma) return 0; } -static void aio_ring_remap(struct file *file, struct vm_area_struct *vma) +static int aio_ring_remap(struct file *file, struct vm_area_struct *vma) { struct mm_struct *mm = vma->vm_mm; struct kioctx_table *table; - int i; + int i, res = -EINVAL; spin_lock(&mm->ioctx_lock); rcu_read_lock(); @@ -292,13 +329,17 @@ static void aio_ring_remap(struct file *file, struct vm_area_struct *vma) ctx = table->table[i]; if (ctx && ctx->aio_ring_file == file) { - ctx->user_id = ctx->mmap_base = vma->vm_start; + if (!atomic_read(&ctx->dead)) { + ctx->user_id = ctx->mmap_base = vma->vm_start; + res = 0; + } break; } } rcu_read_unlock(); spin_unlock(&mm->ioctx_lock); + return res; } static const struct file_operations aio_ring_fops = { @@ -480,8 +521,9 @@ static int aio_setup_ring(struct kioctx *ctx) #define AIO_EVENTS_FIRST_PAGE ((PAGE_SIZE - sizeof(struct aio_ring)) / sizeof(struct io_event)) #define AIO_EVENTS_OFFSET (AIO_EVENTS_PER_PAGE - AIO_EVENTS_FIRST_PAGE) -void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel) +void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) { + struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, common); struct kioctx *ctx = req->ki_ctx; unsigned long flags; @@ -496,7 +538,7 @@ void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel) } EXPORT_SYMBOL(kiocb_set_cancel_fn); -static int kiocb_cancel(struct kiocb *kiocb) +static int kiocb_cancel(struct aio_kiocb *kiocb) { kiocb_cancel_fn *old, *cancel; @@ -514,7 +556,7 @@ static int kiocb_cancel(struct kiocb *kiocb) cancel = cmpxchg(&kiocb->ki_cancel, old, KIOCB_CANCELLED); } while (cancel != old); - return cancel(kiocb); + return cancel(&kiocb->common); } static void free_ioctx(struct work_struct *work) @@ -535,8 +577,8 @@ static void free_ioctx_reqs(struct percpu_ref *ref) struct kioctx *ctx = container_of(ref, struct kioctx, reqs); /* At this point we know that there are no any in-flight requests */ - if (ctx->requests_done) - complete(ctx->requests_done); + if (ctx->rq_wait && atomic_dec_and_test(&ctx->rq_wait->count)) + complete(&ctx->rq_wait->comp); INIT_WORK(&ctx->free_work, free_ioctx); schedule_work(&ctx->free_work); @@ -550,13 +592,13 @@ static void free_ioctx_reqs(struct percpu_ref *ref) static void free_ioctx_users(struct percpu_ref *ref) { struct kioctx *ctx = container_of(ref, struct kioctx, users); - struct kiocb *req; + struct aio_kiocb *req; spin_lock_irq(&ctx->ctx_lock); while (!list_empty(&ctx->active_reqs)) { req = list_first_entry(&ctx->active_reqs, - struct kiocb, ki_list); + struct aio_kiocb, ki_list); list_del_init(&req->ki_list); kiocb_cancel(req); @@ -655,8 +697,7 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) nr_events *= 2; /* Prevent overflows */ - if ((nr_events > (0x10000000U / sizeof(struct io_event))) || - (nr_events > (0x10000000U / sizeof(struct kiocb)))) { + if (nr_events > (0x10000000U / sizeof(struct io_event))) { pr_debug("ENOMEM: nr_events too high\n"); return ERR_PTR(-EINVAL); } @@ -727,6 +768,9 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) err_cleanup: aio_nr_sub(ctx->max_reqs); err_ctx: + atomic_set(&ctx->dead, 1); + if (ctx->mmap_size) + vm_munmap(ctx->mmap_base, ctx->mmap_size); aio_free_ring(ctx); err: mutex_unlock(&ctx->ring_lock); @@ -744,15 +788,16 @@ err: * the rapid destruction of the kioctx. */ static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx, - struct completion *requests_done) + struct ctx_rq_wait *wait) { struct kioctx_table *table; - if (atomic_xchg(&ctx->dead, 1)) + spin_lock(&mm->ioctx_lock); + if (atomic_xchg(&ctx->dead, 1)) { + spin_unlock(&mm->ioctx_lock); return -EINVAL; + } - - spin_lock(&mm->ioctx_lock); table = rcu_dereference_raw(mm->ioctx_table); WARN_ON(ctx != table->table[ctx->id]); table->table[ctx->id] = NULL; @@ -773,27 +818,11 @@ static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx, if (ctx->mmap_size) vm_munmap(ctx->mmap_base, ctx->mmap_size); - ctx->requests_done = requests_done; + ctx->rq_wait = wait; percpu_ref_kill(&ctx->users); return 0; } -/* wait_on_sync_kiocb: - * Waits on the given sync kiocb to complete. - */ -ssize_t wait_on_sync_kiocb(struct kiocb *req) -{ - while (!req->ki_ctx) { - set_current_state(TASK_UNINTERRUPTIBLE); - if (req->ki_ctx) - break; - io_schedule(); - } - __set_current_state(TASK_RUNNING); - return req->ki_user_data; -} -EXPORT_SYMBOL(wait_on_sync_kiocb); - /* * exit_aio: called when the last user of mm goes away. At this point, there is * no way for any new requests to be submited or any of the io_* syscalls to be @@ -805,18 +834,24 @@ EXPORT_SYMBOL(wait_on_sync_kiocb); void exit_aio(struct mm_struct *mm) { struct kioctx_table *table = rcu_dereference_raw(mm->ioctx_table); - int i; + struct ctx_rq_wait wait; + int i, skipped; if (!table) return; + atomic_set(&wait.count, table->nr); + init_completion(&wait.comp); + + skipped = 0; for (i = 0; i < table->nr; ++i) { struct kioctx *ctx = table->table[i]; - struct completion requests_done = - COMPLETION_INITIALIZER_ONSTACK(requests_done); - if (!ctx) + if (!ctx) { + skipped++; continue; + } + /* * We don't need to bother with munmap() here - exit_mmap(mm) * is coming and it'll unmap everything. And we simply can't, @@ -825,10 +860,12 @@ void exit_aio(struct mm_struct *mm) * that it needs to unmap the area, just set it to 0. */ ctx->mmap_size = 0; - kill_ioctx(mm, ctx, &requests_done); + kill_ioctx(mm, ctx, &wait); + } + if (!atomic_sub_and_test(skipped, &wait.count)) { /* Wait until all IO for the context are done. */ - wait_for_completion(&requests_done); + wait_for_completion(&wait.comp); } RCU_INIT_POINTER(mm->ioctx_table, NULL); @@ -948,9 +985,9 @@ static void user_refill_reqs_available(struct kioctx *ctx) * Allocate a slot for an aio request. * Returns NULL if no requests are free. */ -static inline struct kiocb *aio_get_req(struct kioctx *ctx) +static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx) { - struct kiocb *req; + struct aio_kiocb *req; if (!get_reqs_available(ctx)) { user_refill_reqs_available(ctx); @@ -971,10 +1008,10 @@ out_put: return NULL; } -static void kiocb_free(struct kiocb *req) +static void kiocb_free(struct aio_kiocb *req) { - if (req->ki_filp) - fput(req->ki_filp); + if (req->common.ki_filp) + fput(req->common.ki_filp); if (req->ki_eventfd != NULL) eventfd_ctx_put(req->ki_eventfd); kmem_cache_free(kiocb_cachep, req); @@ -1010,8 +1047,9 @@ out: /* aio_complete * Called when the io request on the given iocb is complete. */ -void aio_complete(struct kiocb *iocb, long res, long res2) +static void aio_complete(struct kiocb *kiocb, long res, long res2) { + struct aio_kiocb *iocb = container_of(kiocb, struct aio_kiocb, common); struct kioctx *ctx = iocb->ki_ctx; struct aio_ring *ring; struct io_event *ev_page, *event; @@ -1025,13 +1063,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2) * ref, no other paths have a way to get another ref * - the sync task helpfully left a reference to itself in the iocb */ - if (is_sync_kiocb(iocb)) { - iocb->ki_user_data = res; - smp_wmb(); - iocb->ki_ctx = ERR_PTR(-EXDEV); - wake_up_process(iocb->ki_obj.tsk); - return; - } + BUG_ON(is_sync_kiocb(kiocb)); if (iocb->ki_list.next) { unsigned long flags; @@ -1057,7 +1089,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2) ev_page = kmap_atomic(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); event = ev_page + pos % AIO_EVENTS_PER_PAGE; - event->obj = (u64)(unsigned long)iocb->ki_obj.user; + event->obj = (u64)(unsigned long)iocb->ki_user_iocb; event->data = iocb->ki_user_data; event->res = res; event->res2 = res2; @@ -1066,7 +1098,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2) flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); pr_debug("%p[%u]: %p: %p %Lx %lx %lx\n", - ctx, tail, iocb, iocb->ki_obj.user, iocb->ki_user_data, + ctx, tail, iocb, iocb->ki_user_iocb, iocb->ki_user_data, res, res2); /* after flagging the request as done, we @@ -1113,7 +1145,6 @@ void aio_complete(struct kiocb *iocb, long res, long res2) percpu_ref_put(&ctx->reqs); } -EXPORT_SYMBOL(aio_complete); /* aio_read_events_ring * Pull an event off of the ioctx's event ring. Returns the number of @@ -1313,15 +1344,17 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx) { struct kioctx *ioctx = lookup_ioctx(ctx); if (likely(NULL != ioctx)) { - struct completion requests_done = - COMPLETION_INITIALIZER_ONSTACK(requests_done); + struct ctx_rq_wait wait; int ret; + init_completion(&wait.comp); + atomic_set(&wait.count, 1); + /* Pass requests_done to kill_ioctx() where it can be set * in a thread-safe way. If we try to set it here then we have * a race condition if two io_destroy() called simultaneously. */ - ret = kill_ioctx(current->mm, ioctx, &requests_done); + ret = kill_ioctx(current->mm, ioctx, &wait); percpu_ref_put(&ioctx->users); /* Wait until all IO for the context are done. Otherwise kernel @@ -1329,7 +1362,7 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx) * is destroyed. */ if (!ret) - wait_for_completion(&requests_done); + wait_for_completion(&wait.comp); return ret; } @@ -1337,50 +1370,21 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx) return -EINVAL; } -typedef ssize_t (aio_rw_op)(struct kiocb *, const struct iovec *, - unsigned long, loff_t); typedef ssize_t (rw_iter_op)(struct kiocb *, struct iov_iter *); -static ssize_t aio_setup_vectored_rw(struct kiocb *kiocb, - int rw, char __user *buf, - unsigned long *nr_segs, - struct iovec **iovec, - bool compat) +static int aio_setup_vectored_rw(int rw, char __user *buf, size_t len, + struct iovec **iovec, + bool compat, + struct iov_iter *iter) { - ssize_t ret; - - *nr_segs = kiocb->ki_nbytes; - #ifdef CONFIG_COMPAT if (compat) - ret = compat_rw_copy_check_uvector(rw, + return compat_import_iovec(rw, (struct compat_iovec __user *)buf, - *nr_segs, UIO_FASTIOV, *iovec, iovec); - else + len, UIO_FASTIOV, iovec, iter); #endif - ret = rw_copy_check_uvector(rw, - (struct iovec __user *)buf, - *nr_segs, UIO_FASTIOV, *iovec, iovec); - if (ret < 0) - return ret; - - /* ki_nbytes now reflect bytes instead of segs */ - kiocb->ki_nbytes = ret; - return 0; -} - -static ssize_t aio_setup_single_vector(struct kiocb *kiocb, - int rw, char __user *buf, - unsigned long *nr_segs, - struct iovec *iovec) -{ - if (unlikely(!access_ok(!rw, buf, kiocb->ki_nbytes))) - return -EFAULT; - - iovec->iov_base = buf; - iovec->iov_len = kiocb->ki_nbytes; - *nr_segs = 1; - return 0; + return import_iovec(rw, (struct iovec __user *)buf, + len, UIO_FASTIOV, iovec, iter); } /* @@ -1388,14 +1392,12 @@ static ssize_t aio_setup_single_vector(struct kiocb *kiocb, * Performs the initial checks and io submission. */ static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode, - char __user *buf, bool compat) + char __user *buf, size_t len, bool compat) { struct file *file = req->ki_filp; ssize_t ret; - unsigned long nr_segs; int rw; fmode_t mode; - aio_rw_op *rw_op; rw_iter_op *iter_op; struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct iov_iter iter; @@ -1405,7 +1407,6 @@ static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode, case IOCB_CMD_PREADV: mode = FMODE_READ; rw = READ; - rw_op = file->f_op->aio_read; iter_op = file->f_op->read_iter; goto rw_common; @@ -1413,51 +1414,40 @@ static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode, case IOCB_CMD_PWRITEV: mode = FMODE_WRITE; rw = WRITE; - rw_op = file->f_op->aio_write; iter_op = file->f_op->write_iter; goto rw_common; rw_common: if (unlikely(!(file->f_mode & mode))) return -EBADF; - if (!rw_op && !iter_op) + if (!iter_op) return -EINVAL; - ret = (opcode == IOCB_CMD_PREADV || - opcode == IOCB_CMD_PWRITEV) - ? aio_setup_vectored_rw(req, rw, buf, &nr_segs, - &iovec, compat) - : aio_setup_single_vector(req, rw, buf, &nr_segs, - iovec); + if (opcode == IOCB_CMD_PREADV || opcode == IOCB_CMD_PWRITEV) + ret = aio_setup_vectored_rw(rw, buf, len, + &iovec, compat, &iter); + else { + ret = import_single_range(rw, buf, len, iovec, &iter); + iovec = NULL; + } if (!ret) - ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes); + ret = rw_verify_area(rw, file, &req->ki_pos, + iov_iter_count(&iter)); if (ret < 0) { - if (iovec != inline_vecs) - kfree(iovec); + kfree(iovec); return ret; } - req->ki_nbytes = ret; - - /* XXX: move/kill - rw_verify_area()? */ - /* This matches the pread()/pwrite() logic */ - if (req->ki_pos < 0) { - ret = -EINVAL; - break; - } + len = ret; if (rw == WRITE) file_start_write(file); - if (iter_op) { - iov_iter_init(&iter, rw, iovec, nr_segs, req->ki_nbytes); - ret = iter_op(req, &iter); - } else { - ret = rw_op(req, iovec, nr_segs, req->ki_pos); - } + ret = iter_op(req, &iter); if (rw == WRITE) file_end_write(file); + kfree(iovec); break; case IOCB_CMD_FDSYNC: @@ -1479,9 +1469,6 @@ rw_common: return -EINVAL; } - if (iovec != inline_vecs) - kfree(iovec); - if (ret != -EIOCBQUEUED) { /* * There's no easy way to restart the syscall since other AIO's @@ -1500,7 +1487,7 @@ rw_common: static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, struct iocb *iocb, bool compat) { - struct kiocb *req; + struct aio_kiocb *req; ssize_t ret; /* enforce forwards compatibility on users */ @@ -1523,11 +1510,14 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, if (unlikely(!req)) return -EAGAIN; - req->ki_filp = fget(iocb->aio_fildes); - if (unlikely(!req->ki_filp)) { + req->common.ki_filp = fget(iocb->aio_fildes); + if (unlikely(!req->common.ki_filp)) { ret = -EBADF; goto out_put_req; } + req->common.ki_pos = iocb->aio_offset; + req->common.ki_complete = aio_complete; + req->common.ki_flags = iocb_flags(req->common.ki_filp); if (iocb->aio_flags & IOCB_FLAG_RESFD) { /* @@ -1542,6 +1532,8 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, req->ki_eventfd = NULL; goto out_put_req; } + + req->common.ki_flags |= IOCB_EVENTFD; } ret = put_user(KIOCB_KEY, &user_iocb->aio_key); @@ -1550,13 +1542,12 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, goto out_put_req; } - req->ki_obj.user = user_iocb; + req->ki_user_iocb = user_iocb; req->ki_user_data = iocb->aio_data; - req->ki_pos = iocb->aio_offset; - req->ki_nbytes = iocb->aio_nbytes; - ret = aio_run_iocb(req, iocb->aio_lio_opcode, + ret = aio_run_iocb(&req->common, iocb->aio_lio_opcode, (char __user *)(unsigned long)iocb->aio_buf, + iocb->aio_nbytes, compat); if (ret) goto out_put_req; @@ -1643,10 +1634,10 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr, /* lookup_kiocb * Finds a given iocb for cancellation. */ -static struct kiocb *lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb, - u32 key) +static struct aio_kiocb * +lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb, u32 key) { - struct list_head *pos; + struct aio_kiocb *kiocb; assert_spin_locked(&ctx->ctx_lock); @@ -1654,9 +1645,8 @@ static struct kiocb *lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb, return NULL; /* TODO: use a hash or array, this sucks. */ - list_for_each(pos, &ctx->active_reqs) { - struct kiocb *kiocb = list_kiocb(pos); - if (kiocb->ki_obj.user == iocb) + list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) { + if (kiocb->ki_user_iocb == iocb) return kiocb; } return NULL; @@ -1676,7 +1666,7 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, struct io_event __user *, result) { struct kioctx *ctx; - struct kiocb *kiocb; + struct aio_kiocb *kiocb; u32 key; int ret; diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h index 8e98cf954bab..d10e619632ab 100644 --- a/fs/autofs4/autofs_i.h +++ b/fs/autofs4/autofs_i.h @@ -213,7 +213,7 @@ void autofs4_clean_ino(struct autofs_info *); static inline int autofs_prepare_pipe(struct file *pipe) { - if (!pipe->f_op->write) + if (!(pipe->f_mode & FMODE_CAN_WRITE)) return -EINVAL; if (!S_ISFIFO(file_inode(pipe)->i_mode)) return -EINVAL; diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c index 116fd38ee472..2ad05ab93db8 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs4/waitq.c @@ -70,7 +70,7 @@ static int autofs4_write(struct autofs_sb_info *sbi, mutex_lock(&sbi->pipe_mutex); while (bytes && - (wr = file->f_op->write(file,data,bytes,&file->f_pos)) > 0) { + (wr = __vfs_write(file,data,bytes,&file->f_pos)) > 0) { data += wr; bytes -= wr; } diff --git a/fs/befs/befs.h b/fs/befs/befs.h index 3a7813ab8c95..1fead8d56a98 100644 --- a/fs/befs/befs.h +++ b/fs/befs/befs.h @@ -19,16 +19,16 @@ typedef u64 befs_blocknr_t; * BeFS in memory structures */ -typedef struct befs_mount_options { +struct befs_mount_options { kgid_t gid; kuid_t uid; int use_gid; int use_uid; int debug; char *iocharset; -} befs_mount_options; +}; -typedef struct befs_sb_info { +struct befs_sb_info { u32 magic1; u32 block_size; u32 block_shift; @@ -52,12 +52,11 @@ typedef struct befs_sb_info { befs_inode_addr indices; u32 magic3; - befs_mount_options mount_opts; + struct befs_mount_options mount_opts; struct nls_table *nls; +}; -} befs_sb_info; - -typedef struct befs_inode_info { +struct befs_inode_info { u32 i_flags; u32 i_type; @@ -71,8 +70,7 @@ typedef struct befs_inode_info { } i_data; struct inode vfs_inode; - -} befs_inode_info; +}; enum befs_err { BEFS_OK, @@ -105,13 +103,13 @@ void befs_dump_index_node(const struct super_block *sb, befs_btree_nodehead *); /* Gets a pointer to the private portion of the super_block * structure from the public part */ -static inline befs_sb_info * +static inline struct befs_sb_info * BEFS_SB(const struct super_block *super) { - return (befs_sb_info *) super->s_fs_info; + return (struct befs_sb_info *) super->s_fs_info; } -static inline befs_inode_info * +static inline struct befs_inode_info * BEFS_I(const struct inode *inode) { return list_entry(inode, struct befs_inode_info, vfs_inode); diff --git a/fs/befs/datastream.c b/fs/befs/datastream.c index 1e8e0b8d8836..ebd50718659f 100644 --- a/fs/befs/datastream.c +++ b/fs/befs/datastream.c @@ -168,7 +168,7 @@ befs_count_blocks(struct super_block * sb, befs_data_stream * ds) befs_blocknr_t blocks; befs_blocknr_t datablocks; /* File data blocks */ befs_blocknr_t metablocks; /* FS metadata blocks */ - befs_sb_info *befs_sb = BEFS_SB(sb); + struct befs_sb_info *befs_sb = BEFS_SB(sb); befs_debug(sb, "---> %s", __func__); @@ -428,7 +428,7 @@ befs_find_brun_dblindirect(struct super_block *sb, struct buffer_head *indir_block; befs_block_run indir_run; befs_disk_inode_addr *iaddr_array = NULL; - befs_sb_info *befs_sb = BEFS_SB(sb); + struct befs_sb_info *befs_sb = BEFS_SB(sb); befs_blocknr_t indir_start_blk = data->max_indirect_range >> befs_sb->block_shift; diff --git a/fs/befs/io.c b/fs/befs/io.c index 0408a3d601d0..7a5b4ec21c56 100644 --- a/fs/befs/io.c +++ b/fs/befs/io.c @@ -28,7 +28,7 @@ befs_bread_iaddr(struct super_block *sb, befs_inode_addr iaddr) { struct buffer_head *bh = NULL; befs_blocknr_t block = 0; - befs_sb_info *befs_sb = BEFS_SB(sb); + struct befs_sb_info *befs_sb = BEFS_SB(sb); befs_debug(sb, "---> Enter %s " "[%u, %hu, %hu]", __func__, iaddr.allocation_group, diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index e089f1985fca..16e0a48bfccd 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -51,7 +51,7 @@ static int befs_nls2utf(struct super_block *sb, const char *in, int in_len, static void befs_put_super(struct super_block *); static int befs_remount(struct super_block *, int *, char *); static int befs_statfs(struct dentry *, struct kstatfs *); -static int parse_options(char *, befs_mount_options *); +static int parse_options(char *, struct befs_mount_options *); static const struct super_operations befs_sops = { .alloc_inode = befs_alloc_inode, /* allocate a new inode */ @@ -304,9 +304,8 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino) { struct buffer_head *bh = NULL; befs_inode *raw_inode = NULL; - - befs_sb_info *befs_sb = BEFS_SB(sb); - befs_inode_info *befs_ino = NULL; + struct befs_sb_info *befs_sb = BEFS_SB(sb); + struct befs_inode_info *befs_ino = NULL; struct inode *inode; long ret = -EIO; @@ -472,7 +471,7 @@ static void * befs_follow_link(struct dentry *dentry, struct nameidata *nd) { struct super_block *sb = dentry->d_sb; - befs_inode_info *befs_ino = BEFS_I(dentry->d_inode); + struct befs_inode_info *befs_ino = BEFS_I(dentry->d_inode); befs_data_stream *data = &befs_ino->i_data.ds; befs_off_t len = data->size; char *link; @@ -502,7 +501,8 @@ befs_follow_link(struct dentry *dentry, struct nameidata *nd) static void * befs_fast_follow_link(struct dentry *dentry, struct nameidata *nd) { - befs_inode_info *befs_ino = BEFS_I(dentry->d_inode); + struct befs_inode_info *befs_ino = BEFS_I(dentry->d_inode); + nd_set_link(nd, befs_ino->i_data.symlink); return NULL; } @@ -669,7 +669,7 @@ static const match_table_t befs_tokens = { }; static int -parse_options(char *options, befs_mount_options * opts) +parse_options(char *options, struct befs_mount_options *opts) { char *p; substring_t args[MAX_OPT_ARGS]; @@ -769,7 +769,7 @@ static int befs_fill_super(struct super_block *sb, void *data, int silent) { struct buffer_head *bh; - befs_sb_info *befs_sb; + struct befs_sb_info *befs_sb; befs_super_block *disk_sb; struct inode *root; long ret = -EINVAL; diff --git a/fs/befs/super.c b/fs/befs/super.c index ca40f828f64d..aeafc4d84278 100644 --- a/fs/befs/super.c +++ b/fs/befs/super.c @@ -24,7 +24,7 @@ int befs_load_sb(struct super_block *sb, befs_super_block * disk_sb) { - befs_sb_info *befs_sb = BEFS_SB(sb); + struct befs_sb_info *befs_sb = BEFS_SB(sb); /* Check the byte order of the filesystem */ if (disk_sb->fs_byte_order == BEFS_BYTEORDER_NATIVE_LE) @@ -59,7 +59,7 @@ befs_load_sb(struct super_block *sb, befs_super_block * disk_sb) int befs_check_sb(struct super_block *sb) { - befs_sb_info *befs_sb = BEFS_SB(sb); + struct befs_sb_info *befs_sb = BEFS_SB(sb); /* Check magic headers of super block */ if ((befs_sb->magic1 != BEFS_SUPER_MAGIC1) diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index 08063ae0a17c..7a8182770649 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -86,7 +86,7 @@ static int bfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, inode = new_inode(s); if (!inode) - return -ENOSPC; + return -ENOMEM; mutex_lock(&info->bfs_lock); ino = find_first_zero_bit(info->si_imap, info->si_lasti + 1); if (ino > info->si_lasti) { @@ -293,7 +293,7 @@ static int bfs_add_entry(struct inode *dir, const unsigned char *name, for (block = sblock; block <= eblock; block++) { bh = sb_bread(dir->i_sb, block); if (!bh) - return -ENOSPC; + return -EIO; for (off = 0; off < BFS_BSIZE; off += BFS_DIRENT_SIZE) { de = (struct bfs_dirent *)(bh->b_data + off); if (!de->ino) { diff --git a/fs/bfs/file.c b/fs/bfs/file.c index e7f88ace1a25..97f1b5160155 100644 --- a/fs/bfs/file.c +++ b/fs/bfs/file.c @@ -23,9 +23,7 @@ const struct file_operations bfs_file_operations = { .llseek = generic_file_llseek, - .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = new_sync_write, .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .splice_read = generic_file_splice_read, diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index 90bc079d9982..fdcb4d69f430 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -15,6 +15,7 @@ #include <linux/buffer_head.h> #include <linux/vfs.h> #include <linux/writeback.h> +#include <linux/uio.h> #include <asm/uaccess.h> #include "bfs.h" diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 995986b8e36b..241ef68d2893 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -31,6 +31,7 @@ #include <linux/security.h> #include <linux/random.h> #include <linux/elf.h> +#include <linux/elf-randomize.h> #include <linux/utsname.h> #include <linux/coredump.h> #include <linux/sched.h> @@ -862,6 +863,7 @@ static int load_elf_binary(struct linux_binprm *bprm) i < loc->elf_ex.e_phnum; i++, elf_ppnt++) { int elf_prot = 0, elf_flags; unsigned long k, vaddr; + unsigned long total_size = 0; if (elf_ppnt->p_type != PT_LOAD) continue; @@ -909,25 +911,20 @@ static int load_elf_binary(struct linux_binprm *bprm) * default mmap base, as well as whatever program they * might try to exec. This is because the brk will * follow the loader, and is not movable. */ -#ifdef CONFIG_ARCH_BINFMT_ELF_RANDOMIZE_PIE - /* Memory randomization might have been switched off - * in runtime via sysctl or explicit setting of - * personality flags. - * If that is the case, retain the original non-zero - * load_bias value in order to establish proper - * non-randomized mappings. - */ + load_bias = ELF_ET_DYN_BASE - vaddr; if (current->flags & PF_RANDOMIZE) - load_bias = 0; - else - load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr); -#else - load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr); -#endif + load_bias += arch_mmap_rnd(); + load_bias = ELF_PAGESTART(load_bias); + total_size = total_mapping_size(elf_phdata, + loc->elf_ex.e_phnum); + if (!total_size) { + error = -EINVAL; + goto out_free_dentry; + } } error = elf_map(bprm->file, load_bias + vaddr, elf_ppnt, - elf_prot, elf_flags, 0); + elf_prot, elf_flags, total_size); if (BAD_ADDR(error)) { retval = IS_ERR((void *)error) ? PTR_ERR((void*)error) : -EINVAL; @@ -1053,15 +1050,13 @@ static int load_elf_binary(struct linux_binprm *bprm) current->mm->end_data = end_data; current->mm->start_stack = bprm->p; -#ifdef arch_randomize_brk if ((current->flags & PF_RANDOMIZE) && (randomize_va_space > 1)) { current->mm->brk = current->mm->start_brk = arch_randomize_brk(current->mm); -#ifdef CONFIG_COMPAT_BRK +#ifdef compat_brk_randomized current->brk_randomized = 1; #endif } -#endif if (current->personality & MMAP_PAGE_ZERO) { /* Why this, you ask??? Well SVr4 maps page 0 as read-only, diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 97aff2879cda..9dcb05409ba7 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -9,6 +9,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/sched.h> @@ -521,9 +522,8 @@ static int parse_command(const char __user *buffer, size_t count) static void entry_status(Node *e, char *page) { - char *dp; - char *status = "disabled"; - const char *flags = "flags: "; + char *dp = page; + const char *status = "disabled"; if (test_bit(Enabled, &e->flags)) status = "enabled"; @@ -533,12 +533,10 @@ static void entry_status(Node *e, char *page) return; } - sprintf(page, "%s\ninterpreter %s\n", status, e->interpreter); - dp = page + strlen(page); + dp += sprintf(dp, "%s\ninterpreter %s\n", status, e->interpreter); /* print the special flags */ - sprintf(dp, "%s", flags); - dp += strlen(flags); + dp += sprintf(dp, "flags: "); if (e->flags & MISC_FMT_PRESERVE_ARGV0) *dp++ = 'P'; if (e->flags & MISC_FMT_OPEN_BINARY) @@ -550,21 +548,11 @@ static void entry_status(Node *e, char *page) if (!test_bit(Magic, &e->flags)) { sprintf(dp, "extension .%s\n", e->magic); } else { - int i; - - sprintf(dp, "offset %i\nmagic ", e->offset); - dp = page + strlen(page); - for (i = 0; i < e->size; i++) { - sprintf(dp, "%02x", 0xff & (int) (e->magic[i])); - dp += 2; - } + dp += sprintf(dp, "offset %i\nmagic ", e->offset); + dp = bin2hex(dp, e->magic, e->size); if (e->mask) { - sprintf(dp, "\nmask "); - dp += 6; - for (i = 0; i < e->size; i++) { - sprintf(dp, "%02x", 0xff & (int) (e->mask[i])); - dp += 2; - } + dp += sprintf(dp, "\nmask "); + dp = bin2hex(dp, e->mask, e->size); } *dp++ = '\n'; *dp = '\0'; diff --git a/fs/block_dev.c b/fs/block_dev.c index 975266be67d3..897ee0503932 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -27,7 +27,6 @@ #include <linux/namei.h> #include <linux/log2.h> #include <linux/cleancache.h> -#include <linux/aio.h> #include <asm/uaccess.h> #include "internal.h" @@ -147,15 +146,13 @@ blkdev_get_block(struct inode *inode, sector_t iblock, } static ssize_t -blkdev_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; - return __blockdev_direct_IO(rw, iocb, inode, I_BDEV(inode), iter, - offset, blkdev_get_block, - NULL, NULL, 0); + return __blockdev_direct_IO(iocb, inode, I_BDEV(inode), iter, offset, + blkdev_get_block, NULL, NULL, 0); } int __sync_blockdev(struct block_device *bdev, int wait) @@ -1598,9 +1595,22 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg) ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; + struct inode *bd_inode = file->f_mapping->host; + loff_t size = i_size_read(bd_inode); struct blk_plug plug; ssize_t ret; + if (bdev_read_only(I_BDEV(bd_inode))) + return -EPERM; + + if (!iov_iter_count(from)) + return 0; + + if (iocb->ki_pos >= size) + return -ENOSPC; + + iov_iter_truncate(from, size - iocb->ki_pos); + blk_start_plug(&plug); ret = __generic_file_write_iter(iocb, from); if (ret > 0) { @@ -1660,8 +1670,6 @@ const struct file_operations def_blk_fops = { .open = blkdev_open, .release = blkdev_close, .llseek = block_llseek, - .read = new_sync_read, - .write = new_sync_write, .read_iter = blkdev_read_iter, .write_iter = blkdev_write_iter, .mmap = generic_file_mmap, diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index 4dabeb893b7c..df9932b00d08 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -87,7 +87,7 @@ BTRFS_WORK_HELPER(scrubwrc_helper); BTRFS_WORK_HELPER(scrubnc_helper); static struct __btrfs_workqueue * -__btrfs_alloc_workqueue(const char *name, int flags, int max_active, +__btrfs_alloc_workqueue(const char *name, unsigned int flags, int max_active, int thresh) { struct __btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_NOFS); @@ -132,7 +132,7 @@ static inline void __btrfs_destroy_workqueue(struct __btrfs_workqueue *wq); struct btrfs_workqueue *btrfs_alloc_workqueue(const char *name, - int flags, + unsigned int flags, int max_active, int thresh) { diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h index e386c29ef1f6..ec2ee477f8ba 100644 --- a/fs/btrfs/async-thread.h +++ b/fs/btrfs/async-thread.h @@ -66,7 +66,7 @@ BTRFS_WORK_HELPER_PROTO(scrubwrc_helper); BTRFS_WORK_HELPER_PROTO(scrubnc_helper); struct btrfs_workqueue *btrfs_alloc_workqueue(const char *name, - int flags, + unsigned int flags, int max_active, int thresh); void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t helper, diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index f55721ff9385..9de772ee0031 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1206,7 +1206,7 @@ int btrfs_check_shared(struct btrfs_trans_handle *trans, struct ulist *roots = NULL; struct ulist_iterator uiter; struct ulist_node *node; - struct seq_list elem = {}; + struct seq_list elem = SEQ_LIST_INIT(elem); int ret = 0; tmp = ulist_alloc(GFP_NOFS); @@ -1610,7 +1610,7 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info, struct ulist *roots = NULL; struct ulist_node *ref_node = NULL; struct ulist_node *root_node = NULL; - struct seq_list tree_mod_seq_elem = {}; + struct seq_list tree_mod_seq_elem = SEQ_LIST_INIT(tree_mod_seq_elem); struct ulist_iterator ref_uiter; struct ulist_iterator root_uiter; diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index de5e4f2adfea..0ef5cc13fae2 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -66,7 +66,11 @@ struct btrfs_inode { */ struct btrfs_key location; - /* Lock for counters */ + /* + * Lock for counters and all fields used to determine if the inode is in + * the log or not (last_trans, last_sub_trans, last_log_commit, + * logged_trans). + */ spinlock_t lock; /* the extent_tree has caches of all the extent mappings to disk */ @@ -250,6 +254,9 @@ static inline bool btrfs_is_free_space_inode(struct inode *inode) static inline int btrfs_inode_in_log(struct inode *inode, u64 generation) { + int ret = 0; + + spin_lock(&BTRFS_I(inode)->lock); if (BTRFS_I(inode)->logged_trans == generation && BTRFS_I(inode)->last_sub_trans <= BTRFS_I(inode)->last_log_commit && @@ -263,9 +270,10 @@ static inline int btrfs_inode_in_log(struct inode *inode, u64 generation) */ smp_mb(); if (list_empty(&BTRFS_I(inode)->extent_tree.modified_extents)) - return 1; + ret = 1; } - return 0; + spin_unlock(&BTRFS_I(inode)->lock); + return ret; } #define BTRFS_DIO_ORIG_BIO_SUBMITTED 0x1 diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index d897ef803b3b..ce7dec88f4b8 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -2990,8 +2990,8 @@ static void __btrfsic_submit_bio(int rw, struct bio *bio) (unsigned long long)bio->bi_iter.bi_sector, dev_bytenr, bio->bi_bdev); - mapped_datav = kmalloc(sizeof(*mapped_datav) * bio->bi_vcnt, - GFP_NOFS); + mapped_datav = kmalloc_array(bio->bi_vcnt, + sizeof(*mapped_datav), GFP_NOFS); if (!mapped_datav) goto leave; cur_bytenr = dev_bytenr; @@ -3241,8 +3241,5 @@ void btrfsic_unmount(struct btrfs_root *root, mutex_unlock(&btrfsic_mutex); - if (is_vmalloc_addr(state)) - vfree(state); - else - kfree(state); + kvfree(state); } diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index e9df8862012c..ce62324c78e7 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -622,7 +622,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, cb->orig_bio = bio; nr_pages = DIV_ROUND_UP(compressed_len, PAGE_CACHE_SIZE); - cb->compressed_pages = kzalloc(sizeof(struct page *) * nr_pages, + cb->compressed_pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS); if (!cb->compressed_pages) goto fail1; @@ -750,7 +750,7 @@ static int comp_num_workspace[BTRFS_COMPRESS_TYPES]; static atomic_t comp_alloc_workspace[BTRFS_COMPRESS_TYPES]; static wait_queue_head_t comp_workspace_wait[BTRFS_COMPRESS_TYPES]; -static struct btrfs_compress_op *btrfs_compress_op[] = { +static const struct btrfs_compress_op * const btrfs_compress_op[] = { &btrfs_zlib_compress, &btrfs_lzo_compress, }; diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h index d181f70caae0..13a4dc0436c9 100644 --- a/fs/btrfs/compression.h +++ b/fs/btrfs/compression.h @@ -77,7 +77,7 @@ struct btrfs_compress_op { size_t srclen, size_t destlen); }; -extern struct btrfs_compress_op btrfs_zlib_compress; -extern struct btrfs_compress_op btrfs_lzo_compress; +extern const struct btrfs_compress_op btrfs_zlib_compress; +extern const struct btrfs_compress_op btrfs_lzo_compress; #endif diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 6d67f32e648d..0f11ebc92f02 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -578,7 +578,7 @@ tree_mod_log_insert_move(struct btrfs_fs_info *fs_info, if (!tree_mod_need_log(fs_info, eb)) return 0; - tm_list = kzalloc(nr_items * sizeof(struct tree_mod_elem *), flags); + tm_list = kcalloc(nr_items, sizeof(struct tree_mod_elem *), flags); if (!tm_list) return -ENOMEM; @@ -677,7 +677,7 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info, if (log_removal && btrfs_header_level(old_root) > 0) { nritems = btrfs_header_nritems(old_root); - tm_list = kzalloc(nritems * sizeof(struct tree_mod_elem *), + tm_list = kcalloc(nritems, sizeof(struct tree_mod_elem *), flags); if (!tm_list) { ret = -ENOMEM; @@ -814,7 +814,7 @@ tree_mod_log_eb_copy(struct btrfs_fs_info *fs_info, struct extent_buffer *dst, if (btrfs_header_level(dst) == 0 && btrfs_header_level(src) == 0) return 0; - tm_list = kzalloc(nr_items * 2 * sizeof(struct tree_mod_elem *), + tm_list = kcalloc(nr_items * 2, sizeof(struct tree_mod_elem *), GFP_NOFS); if (!tm_list) return -ENOMEM; @@ -905,8 +905,7 @@ tree_mod_log_free_eb(struct btrfs_fs_info *fs_info, struct extent_buffer *eb) return 0; nritems = btrfs_header_nritems(eb); - tm_list = kzalloc(nritems * sizeof(struct tree_mod_elem *), - GFP_NOFS); + tm_list = kcalloc(nritems, sizeof(struct tree_mod_elem *), GFP_NOFS); if (!tm_list) return -ENOMEM; @@ -1073,7 +1072,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, ret = btrfs_dec_ref(trans, root, buf, 1); BUG_ON(ret); /* -ENOMEM */ } - clean_tree_block(trans, root, buf); + clean_tree_block(trans, root->fs_info, buf); *last_ref = 1; } return 0; @@ -1678,7 +1677,7 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans, continue; } - cur = btrfs_find_tree_block(root, blocknr); + cur = btrfs_find_tree_block(root->fs_info, blocknr); if (cur) uptodate = btrfs_buffer_uptodate(cur, gen, 0); else @@ -1943,7 +1942,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, path->locks[level] = 0; path->nodes[level] = NULL; - clean_tree_block(trans, root, mid); + clean_tree_block(trans, root->fs_info, mid); btrfs_tree_unlock(mid); /* once for the path */ free_extent_buffer(mid); @@ -1997,7 +1996,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, if (wret < 0 && wret != -ENOSPC) ret = wret; if (btrfs_header_nritems(right) == 0) { - clean_tree_block(trans, root, right); + clean_tree_block(trans, root->fs_info, right); btrfs_tree_unlock(right); del_ptr(root, path, level + 1, pslot + 1); root_sub_used(root, right->len); @@ -2041,7 +2040,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, BUG_ON(wret == 1); } if (btrfs_header_nritems(mid) == 0) { - clean_tree_block(trans, root, mid); + clean_tree_block(trans, root->fs_info, mid); btrfs_tree_unlock(mid); del_ptr(root, path, level + 1, pslot); root_sub_used(root, mid->len); @@ -2259,7 +2258,7 @@ static void reada_for_search(struct btrfs_root *root, search = btrfs_node_blockptr(node, slot); blocksize = root->nodesize; - eb = btrfs_find_tree_block(root, search); + eb = btrfs_find_tree_block(root->fs_info, search); if (eb) { free_extent_buffer(eb); return; @@ -2319,7 +2318,7 @@ static noinline void reada_for_balance(struct btrfs_root *root, if (slot > 0) { block1 = btrfs_node_blockptr(parent, slot - 1); gen = btrfs_node_ptr_generation(parent, slot - 1); - eb = btrfs_find_tree_block(root, block1); + eb = btrfs_find_tree_block(root->fs_info, block1); /* * if we get -eagain from btrfs_buffer_uptodate, we * don't want to return eagain here. That will loop @@ -2332,7 +2331,7 @@ static noinline void reada_for_balance(struct btrfs_root *root, if (slot + 1 < nritems) { block2 = btrfs_node_blockptr(parent, slot + 1); gen = btrfs_node_ptr_generation(parent, slot + 1); - eb = btrfs_find_tree_block(root, block2); + eb = btrfs_find_tree_block(root->fs_info, block2); if (eb && btrfs_buffer_uptodate(eb, gen, 1) != 0) block2 = 0; free_extent_buffer(eb); @@ -2450,7 +2449,7 @@ read_block_for_search(struct btrfs_trans_handle *trans, blocknr = btrfs_node_blockptr(b, slot); gen = btrfs_node_ptr_generation(b, slot); - tmp = btrfs_find_tree_block(root, blocknr); + tmp = btrfs_find_tree_block(root->fs_info, blocknr); if (tmp) { /* first we do an atomic uptodate check */ if (btrfs_buffer_uptodate(tmp, gen, 1) > 0) { @@ -3126,7 +3125,8 @@ again: * higher levels * */ -static void fixup_low_keys(struct btrfs_root *root, struct btrfs_path *path, +static void fixup_low_keys(struct btrfs_fs_info *fs_info, + struct btrfs_path *path, struct btrfs_disk_key *key, int level) { int i; @@ -3137,7 +3137,7 @@ static void fixup_low_keys(struct btrfs_root *root, struct btrfs_path *path, if (!path->nodes[i]) break; t = path->nodes[i]; - tree_mod_log_set_node_key(root->fs_info, t, tslot, 1); + tree_mod_log_set_node_key(fs_info, t, tslot, 1); btrfs_set_node_key(t, key, tslot); btrfs_mark_buffer_dirty(path->nodes[i]); if (tslot != 0) @@ -3151,7 +3151,8 @@ static void fixup_low_keys(struct btrfs_root *root, struct btrfs_path *path, * This function isn't completely safe. It's the caller's responsibility * that the new key won't break the order */ -void btrfs_set_item_key_safe(struct btrfs_root *root, struct btrfs_path *path, +void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info, + struct btrfs_path *path, struct btrfs_key *new_key) { struct btrfs_disk_key disk_key; @@ -3173,7 +3174,7 @@ void btrfs_set_item_key_safe(struct btrfs_root *root, struct btrfs_path *path, btrfs_set_item_key(eb, &disk_key, slot); btrfs_mark_buffer_dirty(eb); if (slot == 0) - fixup_low_keys(root, path, &disk_key, 1); + fixup_low_keys(fs_info, path, &disk_key, 1); } /* @@ -3692,7 +3693,7 @@ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans, if (left_nritems) btrfs_mark_buffer_dirty(left); else - clean_tree_block(trans, root, left); + clean_tree_block(trans, root->fs_info, left); btrfs_mark_buffer_dirty(right); @@ -3704,7 +3705,7 @@ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans, if (path->slots[0] >= left_nritems) { path->slots[0] -= left_nritems; if (btrfs_header_nritems(path->nodes[0]) == 0) - clean_tree_block(trans, root, path->nodes[0]); + clean_tree_block(trans, root->fs_info, path->nodes[0]); btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = right; @@ -3928,10 +3929,10 @@ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans, if (right_nritems) btrfs_mark_buffer_dirty(right); else - clean_tree_block(trans, root, right); + clean_tree_block(trans, root->fs_info, right); btrfs_item_key(right, &disk_key, 0); - fixup_low_keys(root, path, &disk_key, 1); + fixup_low_keys(root->fs_info, path, &disk_key, 1); /* then fixup the leaf pointer in the path */ if (path->slots[0] < push_items) { @@ -4168,6 +4169,7 @@ static noinline int split_leaf(struct btrfs_trans_handle *trans, int mid; int slot; struct extent_buffer *right; + struct btrfs_fs_info *fs_info = root->fs_info; int ret = 0; int wret; int split; @@ -4271,10 +4273,10 @@ again: btrfs_set_header_backref_rev(right, BTRFS_MIXED_BACKREF_REV); btrfs_set_header_owner(right, root->root_key.objectid); btrfs_set_header_level(right, 0); - write_extent_buffer(right, root->fs_info->fsid, + write_extent_buffer(right, fs_info->fsid, btrfs_header_fsid(), BTRFS_FSID_SIZE); - write_extent_buffer(right, root->fs_info->chunk_tree_uuid, + write_extent_buffer(right, fs_info->chunk_tree_uuid, btrfs_header_chunk_tree_uuid(right), BTRFS_UUID_SIZE); @@ -4297,7 +4299,7 @@ again: path->nodes[0] = right; path->slots[0] = 0; if (path->slots[1] == 0) - fixup_low_keys(root, path, &disk_key, 1); + fixup_low_keys(fs_info, path, &disk_key, 1); } btrfs_mark_buffer_dirty(right); return ret; @@ -4615,7 +4617,7 @@ void btrfs_truncate_item(struct btrfs_root *root, struct btrfs_path *path, btrfs_set_disk_key_offset(&disk_key, offset + size_diff); btrfs_set_item_key(leaf, &disk_key, slot); if (slot == 0) - fixup_low_keys(root, path, &disk_key, 1); + fixup_low_keys(root->fs_info, path, &disk_key, 1); } item = btrfs_item_nr(slot); @@ -4716,7 +4718,7 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path, if (path->slots[0] == 0) { btrfs_cpu_key_to_disk(&disk_key, cpu_key); - fixup_low_keys(root, path, &disk_key, 1); + fixup_low_keys(root->fs_info, path, &disk_key, 1); } btrfs_unlock_up_safe(path, 1); @@ -4888,7 +4890,7 @@ static void del_ptr(struct btrfs_root *root, struct btrfs_path *path, struct btrfs_disk_key disk_key; btrfs_node_key(parent, &disk_key, 0); - fixup_low_keys(root, path, &disk_key, level + 1); + fixup_low_keys(root->fs_info, path, &disk_key, level + 1); } btrfs_mark_buffer_dirty(parent); } @@ -4981,7 +4983,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, btrfs_set_header_level(leaf, 0); } else { btrfs_set_path_blocking(path); - clean_tree_block(trans, root, leaf); + clean_tree_block(trans, root->fs_info, leaf); btrfs_del_leaf(trans, root, path, leaf); } } else { @@ -4990,7 +4992,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_disk_key disk_key; btrfs_item_key(leaf, &disk_key, 0); - fixup_low_keys(root, path, &disk_key, 1); + fixup_low_keys(root->fs_info, path, &disk_key, 1); } /* delete the leaf if it is mostly empty */ diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index f9c89cae39ee..6f364e1d8d3d 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1061,6 +1061,12 @@ struct btrfs_block_group_item { __le64 flags; } __attribute__ ((__packed__)); +#define BTRFS_QGROUP_LEVEL_SHIFT 48 +static inline u64 btrfs_qgroup_level(u64 qgroupid) +{ + return qgroupid >> BTRFS_QGROUP_LEVEL_SHIFT; +} + /* * is subvolume quota turned on? */ @@ -1256,6 +1262,20 @@ struct btrfs_caching_control { atomic_t count; }; +struct btrfs_io_ctl { + void *cur, *orig; + struct page *page; + struct page **pages; + struct btrfs_root *root; + struct inode *inode; + unsigned long size; + int index; + int num_pages; + int entries; + int bitmaps; + unsigned check_crcs:1; +}; + struct btrfs_block_group_cache { struct btrfs_key key; struct btrfs_block_group_item item; @@ -1321,6 +1341,9 @@ struct btrfs_block_group_cache { /* For dirty block groups */ struct list_head dirty_list; + struct list_head io_list; + + struct btrfs_io_ctl io_ctl; }; /* delayed seq elem */ @@ -1329,6 +1352,8 @@ struct seq_list { u64 seq; }; +#define SEQ_LIST_INIT(name) { .list = LIST_HEAD_INIT((name).list), .seq = 0 } + enum btrfs_orphan_cleanup_state { ORPHAN_CLEANUP_STARTED = 1, ORPHAN_CLEANUP_DONE = 2, @@ -1472,6 +1497,12 @@ struct btrfs_fs_info { struct mutex chunk_mutex; struct mutex volume_mutex; + /* + * this is taken to make sure we don't set block groups ro after + * the free space cache has been allocated on them + */ + struct mutex ro_block_group_mutex; + /* this is used during read/modify/write to make sure * no two ios are trying to mod the same stripe at the same * time @@ -1513,6 +1544,7 @@ struct btrfs_fs_info { spinlock_t delayed_iput_lock; struct list_head delayed_iputs; + struct rw_semaphore delayed_iput_sem; /* this protects tree_mod_seq_list */ spinlock_t tree_mod_seq_lock; @@ -3295,6 +3327,9 @@ static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping) } /* extent-tree.c */ + +u64 btrfs_csum_bytes_to_leaves(struct btrfs_root *root, u64 csum_bytes); + static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_root *root, unsigned num_items) { @@ -3385,6 +3420,8 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, u64 owner, u64 offset, int no_quota); +int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans, + struct btrfs_root *root); int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans, struct btrfs_root *root); int btrfs_setup_space_cache(struct btrfs_trans_handle *trans, @@ -3417,7 +3454,7 @@ enum btrfs_reserve_flush_enum { BTRFS_RESERVE_FLUSH_ALL, }; -int btrfs_check_data_free_space(struct inode *inode, u64 bytes); +int btrfs_check_data_free_space(struct inode *inode, u64 bytes, u64 write_bytes); void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes); void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans, struct btrfs_root *root); @@ -3440,6 +3477,7 @@ struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_root *root, unsigned short type); void btrfs_free_block_rsv(struct btrfs_root *root, struct btrfs_block_rsv *rsv); +void __btrfs_free_block_rsv(struct btrfs_block_rsv *rsv); int btrfs_block_rsv_add(struct btrfs_root *root, struct btrfs_block_rsv *block_rsv, u64 num_bytes, enum btrfs_reserve_flush_enum flush); @@ -3486,7 +3524,8 @@ int btrfs_previous_item(struct btrfs_root *root, int type); int btrfs_previous_extent_item(struct btrfs_root *root, struct btrfs_path *path, u64 min_objectid); -void btrfs_set_item_key_safe(struct btrfs_root *root, struct btrfs_path *path, +void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info, + struct btrfs_path *path, struct btrfs_key *new_key); struct extent_buffer *btrfs_root_node(struct btrfs_root *root); struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root); @@ -4180,7 +4219,8 @@ int btree_readahead_hook(struct btrfs_root *root, struct extent_buffer *eb, static inline int is_fstree(u64 rootid) { if (rootid == BTRFS_FS_TREE_OBJECTID || - (s64)rootid >= (s64)BTRFS_FIRST_FREE_OBJECTID) + ((s64)rootid >= (s64)BTRFS_FIRST_FREE_OBJECTID && + !btrfs_qgroup_level(rootid))) return 1; return 0; } diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 82f0c7c95474..cde698a07d21 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1383,7 +1383,7 @@ out: static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root, - struct btrfs_root *root, int nr) + struct btrfs_fs_info *fs_info, int nr) { struct btrfs_async_delayed_work *async_work; @@ -1399,7 +1399,7 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root, btrfs_async_run_delayed_root, NULL, NULL); async_work->nr = nr; - btrfs_queue_work(root->fs_info->delayed_workers, &async_work->work); + btrfs_queue_work(fs_info->delayed_workers, &async_work->work); return 0; } @@ -1426,6 +1426,7 @@ static int could_end_wait(struct btrfs_delayed_root *delayed_root, int seq) void btrfs_balance_delayed_items(struct btrfs_root *root) { struct btrfs_delayed_root *delayed_root; + struct btrfs_fs_info *fs_info = root->fs_info; delayed_root = btrfs_get_delayed_root(root); @@ -1438,7 +1439,7 @@ void btrfs_balance_delayed_items(struct btrfs_root *root) seq = atomic_read(&delayed_root->items_seq); - ret = btrfs_wq_run_delayed_node(delayed_root, root, 0); + ret = btrfs_wq_run_delayed_node(delayed_root, fs_info, 0); if (ret) return; @@ -1447,7 +1448,7 @@ void btrfs_balance_delayed_items(struct btrfs_root *root) return; } - btrfs_wq_run_delayed_node(delayed_root, root, BTRFS_DELAYED_BATCH); + btrfs_wq_run_delayed_node(delayed_root, fs_info, BTRFS_DELAYED_BATCH); } /* Will return 0 or -ENOMEM */ diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 6d16bea94e1c..8f8ed7d20bac 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -489,11 +489,13 @@ update_existing_ref(struct btrfs_trans_handle *trans, * existing and update must have the same bytenr */ static noinline void -update_existing_head_ref(struct btrfs_delayed_ref_node *existing, +update_existing_head_ref(struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_delayed_ref_node *existing, struct btrfs_delayed_ref_node *update) { struct btrfs_delayed_ref_head *existing_ref; struct btrfs_delayed_ref_head *ref; + int old_ref_mod; existing_ref = btrfs_delayed_node_to_head(existing); ref = btrfs_delayed_node_to_head(update); @@ -541,7 +543,20 @@ update_existing_head_ref(struct btrfs_delayed_ref_node *existing, * only need the lock for this case cause we could be processing it * currently, for refs we just added we know we're a-ok. */ + old_ref_mod = existing_ref->total_ref_mod; existing->ref_mod += update->ref_mod; + existing_ref->total_ref_mod += update->ref_mod; + + /* + * If we are going to from a positive ref mod to a negative or vice + * versa we need to make sure to adjust pending_csums accordingly. + */ + if (existing_ref->is_data) { + if (existing_ref->total_ref_mod >= 0 && old_ref_mod < 0) + delayed_refs->pending_csums -= existing->num_bytes; + if (existing_ref->total_ref_mod < 0 && old_ref_mod >= 0) + delayed_refs->pending_csums += existing->num_bytes; + } spin_unlock(&existing_ref->lock); } @@ -605,6 +620,7 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, head_ref->is_data = is_data; head_ref->ref_root = RB_ROOT; head_ref->processing = 0; + head_ref->total_ref_mod = count_mod; spin_lock_init(&head_ref->lock); mutex_init(&head_ref->mutex); @@ -614,7 +630,7 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, existing = htree_insert(&delayed_refs->href_root, &head_ref->href_node); if (existing) { - update_existing_head_ref(&existing->node, ref); + update_existing_head_ref(delayed_refs, &existing->node, ref); /* * we've updated the existing ref, free the newly * allocated ref @@ -622,6 +638,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref); head_ref = existing; } else { + if (is_data && count_mod < 0) + delayed_refs->pending_csums += num_bytes; delayed_refs->num_heads++; delayed_refs->num_heads_ready++; atomic_inc(&delayed_refs->num_entries); diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index a764e2340d48..5eb0892396d0 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -88,6 +88,14 @@ struct btrfs_delayed_ref_head { struct rb_node href_node; struct btrfs_delayed_extent_op *extent_op; + + /* + * This is used to track the final ref_mod from all the refs associated + * with this head ref, this is not adjusted as delayed refs are run, + * this is meant to track if we need to do the csum accounting or not. + */ + int total_ref_mod; + /* * when a new extent is allocated, it is just reserved in memory * The actual extent isn't inserted into the extent allocation tree @@ -138,6 +146,8 @@ struct btrfs_delayed_ref_root { /* total number of head nodes ready for processing */ unsigned long num_heads_ready; + u64 pending_csums; + /* * set when the tree is flushing before a transaction commit, * used by the throttling code to decide if new updates need diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 5ec03d999c37..0573848c7333 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -670,8 +670,8 @@ void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info, case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED: srcdev = dev_replace->srcdev; - args->status.progress_1000 = div64_u64(dev_replace->cursor_left, - div64_u64(btrfs_device_get_total_bytes(srcdev), 1000)); + args->status.progress_1000 = div_u64(dev_replace->cursor_left, + div_u64(btrfs_device_get_total_bytes(srcdev), 1000)); break; } btrfs_dev_replace_unlock(dev_replace); @@ -806,7 +806,7 @@ static int btrfs_dev_replace_kthread(void *data) btrfs_dev_replace_status(fs_info, status_args); progress = status_args->status.progress_1000; kfree(status_args); - do_div(progress, 10); + progress = div_u64(progress, 10); printk_in_rcu(KERN_INFO "BTRFS: continuing dev_replace from %s (devid %llu) to %s @%u%%\n", dev_replace->srcdev->missing ? "<missing disk>" : diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 639f2663ed3f..2ef9a4b72d06 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -54,7 +54,7 @@ #include <asm/cpufeature.h> #endif -static struct extent_io_ops btree_extent_io_ops; +static const struct extent_io_ops btree_extent_io_ops; static void end_workqueue_fn(struct btrfs_work *work); static void free_fs_root(struct btrfs_root *root); static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, @@ -274,10 +274,11 @@ void btrfs_csum_final(u32 crc, char *result) * compute the csum for a btree block, and either verify it or write it * into the csum field of the block. */ -static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf, +static int csum_tree_block(struct btrfs_fs_info *fs_info, + struct extent_buffer *buf, int verify) { - u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy); + u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); char *result = NULL; unsigned long len; unsigned long cur_len; @@ -302,7 +303,7 @@ static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf, offset += cur_len; } if (csum_size > sizeof(inline_result)) { - result = kzalloc(csum_size * sizeof(char), GFP_NOFS); + result = kzalloc(csum_size, GFP_NOFS); if (!result) return 1; } else { @@ -321,7 +322,7 @@ static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf, printk_ratelimited(KERN_WARNING "BTRFS: %s checksum verify failed on %llu wanted %X found %X " "level %d\n", - root->fs_info->sb->s_id, buf->start, + fs_info->sb->s_id, buf->start, val, found, btrfs_header_level(buf)); if (result != (char *)&inline_result) kfree(result); @@ -418,12 +419,6 @@ static int btrfs_check_super_csum(char *raw_disk_sb) if (memcmp(raw_disk_sb, result, csum_size)) ret = 1; - - if (ret && btrfs_super_generation(disk_sb) < 10) { - printk(KERN_WARNING - "BTRFS: super block crcs don't match, older mkfs detected\n"); - ret = 0; - } } if (csum_type >= ARRAY_SIZE(btrfs_csum_sizes)) { @@ -501,7 +496,7 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root, * we only fill in the checksum field in the first page of a multi-page block */ -static int csum_dirty_buffer(struct btrfs_root *root, struct page *page) +static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page) { u64 start = page_offset(page); u64 found_start; @@ -513,14 +508,14 @@ static int csum_dirty_buffer(struct btrfs_root *root, struct page *page) found_start = btrfs_header_bytenr(eb); if (WARN_ON(found_start != start || !PageUptodate(page))) return 0; - csum_tree_block(root, eb, 0); + csum_tree_block(fs_info, eb, 0); return 0; } -static int check_tree_block_fsid(struct btrfs_root *root, +static int check_tree_block_fsid(struct btrfs_fs_info *fs_info, struct extent_buffer *eb) { - struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices; + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; u8 fsid[BTRFS_UUID_SIZE]; int ret = 1; @@ -640,7 +635,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, ret = -EIO; goto err; } - if (check_tree_block_fsid(root, eb)) { + if (check_tree_block_fsid(root->fs_info, eb)) { printk_ratelimited(KERN_ERR "BTRFS (device %s): bad fsid on block %llu\n", eb->fs_info->sb->s_id, eb->start); ret = -EIO; @@ -657,7 +652,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb), eb, found_level); - ret = csum_tree_block(root, eb, 1); + ret = csum_tree_block(root->fs_info, eb, 1); if (ret) { ret = -EIO; goto err; @@ -882,7 +877,7 @@ static int btree_csum_one_bio(struct bio *bio) bio_for_each_segment_all(bvec, bio, i) { root = BTRFS_I(bvec->bv_page->mapping->host)->root; - ret = csum_dirty_buffer(root, bvec->bv_page); + ret = csum_dirty_buffer(root->fs_info, bvec->bv_page); if (ret) break; } @@ -1119,10 +1114,10 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, return 0; } -struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root, +struct extent_buffer *btrfs_find_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr) { - return find_extent_buffer(root->fs_info, bytenr); + return find_extent_buffer(fs_info, bytenr); } struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root, @@ -1165,11 +1160,10 @@ struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr, } -void clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, +void clean_tree_block(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, struct extent_buffer *buf) { - struct btrfs_fs_info *fs_info = root->fs_info; - if (btrfs_header_generation(buf) == fs_info->running_transaction->transid) { btrfs_assert_tree_locked(buf); @@ -2146,6 +2140,267 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info) } } +static void btrfs_init_scrub(struct btrfs_fs_info *fs_info) +{ + mutex_init(&fs_info->scrub_lock); + atomic_set(&fs_info->scrubs_running, 0); + atomic_set(&fs_info->scrub_pause_req, 0); + atomic_set(&fs_info->scrubs_paused, 0); + atomic_set(&fs_info->scrub_cancel_req, 0); + init_waitqueue_head(&fs_info->scrub_pause_wait); + fs_info->scrub_workers_refcnt = 0; +} + +static void btrfs_init_balance(struct btrfs_fs_info *fs_info) +{ + spin_lock_init(&fs_info->balance_lock); + mutex_init(&fs_info->balance_mutex); + atomic_set(&fs_info->balance_running, 0); + atomic_set(&fs_info->balance_pause_req, 0); + atomic_set(&fs_info->balance_cancel_req, 0); + fs_info->balance_ctl = NULL; + init_waitqueue_head(&fs_info->balance_wait_q); +} + +static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info, + struct btrfs_root *tree_root) +{ + fs_info->btree_inode->i_ino = BTRFS_BTREE_INODE_OBJECTID; + set_nlink(fs_info->btree_inode, 1); + /* + * we set the i_size on the btree inode to the max possible int. + * the real end of the address space is determined by all of + * the devices in the system + */ + fs_info->btree_inode->i_size = OFFSET_MAX; + fs_info->btree_inode->i_mapping->a_ops = &btree_aops; + + RB_CLEAR_NODE(&BTRFS_I(fs_info->btree_inode)->rb_node); + extent_io_tree_init(&BTRFS_I(fs_info->btree_inode)->io_tree, + fs_info->btree_inode->i_mapping); + BTRFS_I(fs_info->btree_inode)->io_tree.track_uptodate = 0; + extent_map_tree_init(&BTRFS_I(fs_info->btree_inode)->extent_tree); + + BTRFS_I(fs_info->btree_inode)->io_tree.ops = &btree_extent_io_ops; + + BTRFS_I(fs_info->btree_inode)->root = tree_root; + memset(&BTRFS_I(fs_info->btree_inode)->location, 0, + sizeof(struct btrfs_key)); + set_bit(BTRFS_INODE_DUMMY, + &BTRFS_I(fs_info->btree_inode)->runtime_flags); + btrfs_insert_inode_hash(fs_info->btree_inode); +} + +static void btrfs_init_dev_replace_locks(struct btrfs_fs_info *fs_info) +{ + fs_info->dev_replace.lock_owner = 0; + atomic_set(&fs_info->dev_replace.nesting_level, 0); + mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount); + mutex_init(&fs_info->dev_replace.lock_management_lock); + mutex_init(&fs_info->dev_replace.lock); + init_waitqueue_head(&fs_info->replace_wait); +} + +static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info) +{ + spin_lock_init(&fs_info->qgroup_lock); + mutex_init(&fs_info->qgroup_ioctl_lock); + fs_info->qgroup_tree = RB_ROOT; + fs_info->qgroup_op_tree = RB_ROOT; + INIT_LIST_HEAD(&fs_info->dirty_qgroups); + fs_info->qgroup_seq = 1; + fs_info->quota_enabled = 0; + fs_info->pending_quota_state = 0; + fs_info->qgroup_ulist = NULL; + mutex_init(&fs_info->qgroup_rescan_lock); +} + +static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info, + struct btrfs_fs_devices *fs_devices) +{ + int max_active = fs_info->thread_pool_size; + unsigned int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND; + + fs_info->workers = + btrfs_alloc_workqueue("worker", flags | WQ_HIGHPRI, + max_active, 16); + + fs_info->delalloc_workers = + btrfs_alloc_workqueue("delalloc", flags, max_active, 2); + + fs_info->flush_workers = + btrfs_alloc_workqueue("flush_delalloc", flags, max_active, 0); + + fs_info->caching_workers = + btrfs_alloc_workqueue("cache", flags, max_active, 0); + + /* + * a higher idle thresh on the submit workers makes it much more + * likely that bios will be send down in a sane order to the + * devices + */ + fs_info->submit_workers = + btrfs_alloc_workqueue("submit", flags, + min_t(u64, fs_devices->num_devices, + max_active), 64); + + fs_info->fixup_workers = + btrfs_alloc_workqueue("fixup", flags, 1, 0); + + /* + * endios are largely parallel and should have a very + * low idle thresh + */ + fs_info->endio_workers = + btrfs_alloc_workqueue("endio", flags, max_active, 4); + fs_info->endio_meta_workers = + btrfs_alloc_workqueue("endio-meta", flags, max_active, 4); + fs_info->endio_meta_write_workers = + btrfs_alloc_workqueue("endio-meta-write", flags, max_active, 2); + fs_info->endio_raid56_workers = + btrfs_alloc_workqueue("endio-raid56", flags, max_active, 4); + fs_info->endio_repair_workers = + btrfs_alloc_workqueue("endio-repair", flags, 1, 0); + fs_info->rmw_workers = + btrfs_alloc_workqueue("rmw", flags, max_active, 2); + fs_info->endio_write_workers = + btrfs_alloc_workqueue("endio-write", flags, max_active, 2); + fs_info->endio_freespace_worker = + btrfs_alloc_workqueue("freespace-write", flags, max_active, 0); + fs_info->delayed_workers = + btrfs_alloc_workqueue("delayed-meta", flags, max_active, 0); + fs_info->readahead_workers = + btrfs_alloc_workqueue("readahead", flags, max_active, 2); + fs_info->qgroup_rescan_workers = + btrfs_alloc_workqueue("qgroup-rescan", flags, 1, 0); + fs_info->extent_workers = + btrfs_alloc_workqueue("extent-refs", flags, + min_t(u64, fs_devices->num_devices, + max_active), 8); + + if (!(fs_info->workers && fs_info->delalloc_workers && + fs_info->submit_workers && fs_info->flush_workers && + fs_info->endio_workers && fs_info->endio_meta_workers && + fs_info->endio_meta_write_workers && + fs_info->endio_repair_workers && + fs_info->endio_write_workers && fs_info->endio_raid56_workers && + fs_info->endio_freespace_worker && fs_info->rmw_workers && + fs_info->caching_workers && fs_info->readahead_workers && + fs_info->fixup_workers && fs_info->delayed_workers && + fs_info->extent_workers && + fs_info->qgroup_rescan_workers)) { + return -ENOMEM; + } + + return 0; +} + +static int btrfs_replay_log(struct btrfs_fs_info *fs_info, + struct btrfs_fs_devices *fs_devices) +{ + int ret; + struct btrfs_root *tree_root = fs_info->tree_root; + struct btrfs_root *log_tree_root; + struct btrfs_super_block *disk_super = fs_info->super_copy; + u64 bytenr = btrfs_super_log_root(disk_super); + + if (fs_devices->rw_devices == 0) { + printk(KERN_WARNING "BTRFS: log replay required " + "on RO media\n"); + return -EIO; + } + + log_tree_root = btrfs_alloc_root(fs_info); + if (!log_tree_root) + return -ENOMEM; + + __setup_root(tree_root->nodesize, tree_root->sectorsize, + tree_root->stripesize, log_tree_root, fs_info, + BTRFS_TREE_LOG_OBJECTID); + + log_tree_root->node = read_tree_block(tree_root, bytenr, + fs_info->generation + 1); + if (!log_tree_root->node || + !extent_buffer_uptodate(log_tree_root->node)) { + printk(KERN_ERR "BTRFS: failed to read log tree\n"); + free_extent_buffer(log_tree_root->node); + kfree(log_tree_root); + return -EIO; + } + /* returns with log_tree_root freed on success */ + ret = btrfs_recover_log_trees(log_tree_root); + if (ret) { + btrfs_error(tree_root->fs_info, ret, + "Failed to recover log tree"); + free_extent_buffer(log_tree_root->node); + kfree(log_tree_root); + return ret; + } + + if (fs_info->sb->s_flags & MS_RDONLY) { + ret = btrfs_commit_super(tree_root); + if (ret) + return ret; + } + + return 0; +} + +static int btrfs_read_roots(struct btrfs_fs_info *fs_info, + struct btrfs_root *tree_root) +{ + struct btrfs_root *root; + struct btrfs_key location; + int ret; + + location.objectid = BTRFS_EXTENT_TREE_OBJECTID; + location.type = BTRFS_ROOT_ITEM_KEY; + location.offset = 0; + + root = btrfs_read_tree_root(tree_root, &location); + if (IS_ERR(root)) + return PTR_ERR(root); + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->extent_root = root; + + location.objectid = BTRFS_DEV_TREE_OBJECTID; + root = btrfs_read_tree_root(tree_root, &location); + if (IS_ERR(root)) + return PTR_ERR(root); + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->dev_root = root; + btrfs_init_devices_late(fs_info); + + location.objectid = BTRFS_CSUM_TREE_OBJECTID; + root = btrfs_read_tree_root(tree_root, &location); + if (IS_ERR(root)) + return PTR_ERR(root); + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->csum_root = root; + + location.objectid = BTRFS_QUOTA_TREE_OBJECTID; + root = btrfs_read_tree_root(tree_root, &location); + if (!IS_ERR(root)) { + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->quota_enabled = 1; + fs_info->pending_quota_state = 1; + fs_info->quota_root = root; + } + + location.objectid = BTRFS_UUID_TREE_OBJECTID; + root = btrfs_read_tree_root(tree_root, &location); + if (IS_ERR(root)) { + ret = PTR_ERR(root); + if (ret != -ENOENT) + return ret; + } else { + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->uuid_root = root; + } + + return 0; +} + int open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices, char *options) @@ -2160,21 +2415,12 @@ int open_ctree(struct super_block *sb, struct btrfs_super_block *disk_super; struct btrfs_fs_info *fs_info = btrfs_sb(sb); struct btrfs_root *tree_root; - struct btrfs_root *extent_root; - struct btrfs_root *csum_root; struct btrfs_root *chunk_root; - struct btrfs_root *dev_root; - struct btrfs_root *quota_root; - struct btrfs_root *uuid_root; - struct btrfs_root *log_tree_root; int ret; int err = -EINVAL; int num_backups_tried = 0; int backup_index = 0; int max_active; - int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND; - bool create_uuid_tree; - bool check_uuid_tree; tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info); chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info); @@ -2241,11 +2487,12 @@ int open_ctree(struct super_block *sb, spin_lock_init(&fs_info->qgroup_op_lock); spin_lock_init(&fs_info->buffer_lock); spin_lock_init(&fs_info->unused_bgs_lock); - mutex_init(&fs_info->unused_bg_unpin_mutex); rwlock_init(&fs_info->tree_mod_log_lock); + mutex_init(&fs_info->unused_bg_unpin_mutex); mutex_init(&fs_info->reloc_mutex); mutex_init(&fs_info->delalloc_root_mutex); seqlock_init(&fs_info->profiles_lock); + init_rwsem(&fs_info->delayed_iput_sem); init_completion(&fs_info->kobj_unregister); INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots); @@ -2276,7 +2523,7 @@ int open_ctree(struct super_block *sb, fs_info->free_chunk_space = 0; fs_info->tree_mod_log = RB_ROOT; fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL; - fs_info->avg_delayed_ref_runtime = div64_u64(NSEC_PER_SEC, 64); + fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */ /* readahead state */ INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT); spin_lock_init(&fs_info->reada_lock); @@ -2294,55 +2541,18 @@ int open_ctree(struct super_block *sb, } btrfs_init_delayed_root(fs_info->delayed_root); - mutex_init(&fs_info->scrub_lock); - atomic_set(&fs_info->scrubs_running, 0); - atomic_set(&fs_info->scrub_pause_req, 0); - atomic_set(&fs_info->scrubs_paused, 0); - atomic_set(&fs_info->scrub_cancel_req, 0); - init_waitqueue_head(&fs_info->replace_wait); - init_waitqueue_head(&fs_info->scrub_pause_wait); - fs_info->scrub_workers_refcnt = 0; + btrfs_init_scrub(fs_info); #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY fs_info->check_integrity_print_mask = 0; #endif - - spin_lock_init(&fs_info->balance_lock); - mutex_init(&fs_info->balance_mutex); - atomic_set(&fs_info->balance_running, 0); - atomic_set(&fs_info->balance_pause_req, 0); - atomic_set(&fs_info->balance_cancel_req, 0); - fs_info->balance_ctl = NULL; - init_waitqueue_head(&fs_info->balance_wait_q); + btrfs_init_balance(fs_info); btrfs_init_async_reclaim_work(&fs_info->async_reclaim_work); sb->s_blocksize = 4096; sb->s_blocksize_bits = blksize_bits(4096); sb->s_bdi = &fs_info->bdi; - fs_info->btree_inode->i_ino = BTRFS_BTREE_INODE_OBJECTID; - set_nlink(fs_info->btree_inode, 1); - /* - * we set the i_size on the btree inode to the max possible int. - * the real end of the address space is determined by all of - * the devices in the system - */ - fs_info->btree_inode->i_size = OFFSET_MAX; - fs_info->btree_inode->i_mapping->a_ops = &btree_aops; - - RB_CLEAR_NODE(&BTRFS_I(fs_info->btree_inode)->rb_node); - extent_io_tree_init(&BTRFS_I(fs_info->btree_inode)->io_tree, - fs_info->btree_inode->i_mapping); - BTRFS_I(fs_info->btree_inode)->io_tree.track_uptodate = 0; - extent_map_tree_init(&BTRFS_I(fs_info->btree_inode)->extent_tree); - - BTRFS_I(fs_info->btree_inode)->io_tree.ops = &btree_extent_io_ops; - - BTRFS_I(fs_info->btree_inode)->root = tree_root; - memset(&BTRFS_I(fs_info->btree_inode)->location, 0, - sizeof(struct btrfs_key)); - set_bit(BTRFS_INODE_DUMMY, - &BTRFS_I(fs_info->btree_inode)->runtime_flags); - btrfs_insert_inode_hash(fs_info->btree_inode); + btrfs_init_btree_inode(fs_info, tree_root); spin_lock_init(&fs_info->block_group_cache_lock); fs_info->block_group_cache_tree = RB_ROOT; @@ -2363,26 +2573,14 @@ int open_ctree(struct super_block *sb, mutex_init(&fs_info->transaction_kthread_mutex); mutex_init(&fs_info->cleaner_mutex); mutex_init(&fs_info->volume_mutex); + mutex_init(&fs_info->ro_block_group_mutex); init_rwsem(&fs_info->commit_root_sem); init_rwsem(&fs_info->cleanup_work_sem); init_rwsem(&fs_info->subvol_sem); sema_init(&fs_info->uuid_tree_rescan_sem, 1); - fs_info->dev_replace.lock_owner = 0; - atomic_set(&fs_info->dev_replace.nesting_level, 0); - mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount); - mutex_init(&fs_info->dev_replace.lock_management_lock); - mutex_init(&fs_info->dev_replace.lock); - spin_lock_init(&fs_info->qgroup_lock); - mutex_init(&fs_info->qgroup_ioctl_lock); - fs_info->qgroup_tree = RB_ROOT; - fs_info->qgroup_op_tree = RB_ROOT; - INIT_LIST_HEAD(&fs_info->dirty_qgroups); - fs_info->qgroup_seq = 1; - fs_info->quota_enabled = 0; - fs_info->pending_quota_state = 0; - fs_info->qgroup_ulist = NULL; - mutex_init(&fs_info->qgroup_rescan_lock); + btrfs_init_dev_replace_locks(fs_info); + btrfs_init_qgroup(fs_info); btrfs_init_free_cluster(&fs_info->meta_alloc_cluster); btrfs_init_free_cluster(&fs_info->data_alloc_cluster); @@ -2554,75 +2752,9 @@ int open_ctree(struct super_block *sb, max_active = fs_info->thread_pool_size; - fs_info->workers = - btrfs_alloc_workqueue("worker", flags | WQ_HIGHPRI, - max_active, 16); - - fs_info->delalloc_workers = - btrfs_alloc_workqueue("delalloc", flags, max_active, 2); - - fs_info->flush_workers = - btrfs_alloc_workqueue("flush_delalloc", flags, max_active, 0); - - fs_info->caching_workers = - btrfs_alloc_workqueue("cache", flags, max_active, 0); - - /* - * a higher idle thresh on the submit workers makes it much more - * likely that bios will be send down in a sane order to the - * devices - */ - fs_info->submit_workers = - btrfs_alloc_workqueue("submit", flags, - min_t(u64, fs_devices->num_devices, - max_active), 64); - - fs_info->fixup_workers = - btrfs_alloc_workqueue("fixup", flags, 1, 0); - - /* - * endios are largely parallel and should have a very - * low idle thresh - */ - fs_info->endio_workers = - btrfs_alloc_workqueue("endio", flags, max_active, 4); - fs_info->endio_meta_workers = - btrfs_alloc_workqueue("endio-meta", flags, max_active, 4); - fs_info->endio_meta_write_workers = - btrfs_alloc_workqueue("endio-meta-write", flags, max_active, 2); - fs_info->endio_raid56_workers = - btrfs_alloc_workqueue("endio-raid56", flags, max_active, 4); - fs_info->endio_repair_workers = - btrfs_alloc_workqueue("endio-repair", flags, 1, 0); - fs_info->rmw_workers = - btrfs_alloc_workqueue("rmw", flags, max_active, 2); - fs_info->endio_write_workers = - btrfs_alloc_workqueue("endio-write", flags, max_active, 2); - fs_info->endio_freespace_worker = - btrfs_alloc_workqueue("freespace-write", flags, max_active, 0); - fs_info->delayed_workers = - btrfs_alloc_workqueue("delayed-meta", flags, max_active, 0); - fs_info->readahead_workers = - btrfs_alloc_workqueue("readahead", flags, max_active, 2); - fs_info->qgroup_rescan_workers = - btrfs_alloc_workqueue("qgroup-rescan", flags, 1, 0); - fs_info->extent_workers = - btrfs_alloc_workqueue("extent-refs", flags, - min_t(u64, fs_devices->num_devices, - max_active), 8); - - if (!(fs_info->workers && fs_info->delalloc_workers && - fs_info->submit_workers && fs_info->flush_workers && - fs_info->endio_workers && fs_info->endio_meta_workers && - fs_info->endio_meta_write_workers && - fs_info->endio_repair_workers && - fs_info->endio_write_workers && fs_info->endio_raid56_workers && - fs_info->endio_freespace_worker && fs_info->rmw_workers && - fs_info->caching_workers && fs_info->readahead_workers && - fs_info->fixup_workers && fs_info->delayed_workers && - fs_info->extent_workers && - fs_info->qgroup_rescan_workers)) { - err = -ENOMEM; + ret = btrfs_init_workqueues(fs_info, fs_devices); + if (ret) { + err = ret; goto fail_sb_buffer; } @@ -2688,7 +2820,7 @@ int open_ctree(struct super_block *sb, * keep the device that is marked to be the target device for the * dev_replace procedure */ - btrfs_close_extra_devices(fs_info, fs_devices, 0); + btrfs_close_extra_devices(fs_devices, 0); if (!fs_devices->latest_bdev) { printk(KERN_ERR "BTRFS: failed to read devices on %s\n", @@ -2714,61 +2846,9 @@ retry_root_backup: tree_root->commit_root = btrfs_root_node(tree_root); btrfs_set_root_refs(&tree_root->root_item, 1); - location.objectid = BTRFS_EXTENT_TREE_OBJECTID; - location.type = BTRFS_ROOT_ITEM_KEY; - location.offset = 0; - - extent_root = btrfs_read_tree_root(tree_root, &location); - if (IS_ERR(extent_root)) { - ret = PTR_ERR(extent_root); - goto recovery_tree_root; - } - set_bit(BTRFS_ROOT_TRACK_DIRTY, &extent_root->state); - fs_info->extent_root = extent_root; - - location.objectid = BTRFS_DEV_TREE_OBJECTID; - dev_root = btrfs_read_tree_root(tree_root, &location); - if (IS_ERR(dev_root)) { - ret = PTR_ERR(dev_root); - goto recovery_tree_root; - } - set_bit(BTRFS_ROOT_TRACK_DIRTY, &dev_root->state); - fs_info->dev_root = dev_root; - btrfs_init_devices_late(fs_info); - - location.objectid = BTRFS_CSUM_TREE_OBJECTID; - csum_root = btrfs_read_tree_root(tree_root, &location); - if (IS_ERR(csum_root)) { - ret = PTR_ERR(csum_root); + ret = btrfs_read_roots(fs_info, tree_root); + if (ret) goto recovery_tree_root; - } - set_bit(BTRFS_ROOT_TRACK_DIRTY, &csum_root->state); - fs_info->csum_root = csum_root; - - location.objectid = BTRFS_QUOTA_TREE_OBJECTID; - quota_root = btrfs_read_tree_root(tree_root, &location); - if (!IS_ERR(quota_root)) { - set_bit(BTRFS_ROOT_TRACK_DIRTY, "a_root->state); - fs_info->quota_enabled = 1; - fs_info->pending_quota_state = 1; - fs_info->quota_root = quota_root; - } - - location.objectid = BTRFS_UUID_TREE_OBJECTID; - uuid_root = btrfs_read_tree_root(tree_root, &location); - if (IS_ERR(uuid_root)) { - ret = PTR_ERR(uuid_root); - if (ret != -ENOENT) - goto recovery_tree_root; - create_uuid_tree = true; - check_uuid_tree = false; - } else { - set_bit(BTRFS_ROOT_TRACK_DIRTY, &uuid_root->state); - fs_info->uuid_root = uuid_root; - create_uuid_tree = false; - check_uuid_tree = - generation != btrfs_super_uuid_tree_generation(disk_super); - } fs_info->generation = generation; fs_info->last_trans_committed = generation; @@ -2792,7 +2872,7 @@ retry_root_backup: goto fail_block_groups; } - btrfs_close_extra_devices(fs_info, fs_devices, 1); + btrfs_close_extra_devices(fs_devices, 1); ret = btrfs_sysfs_add_one(fs_info); if (ret) { @@ -2806,7 +2886,7 @@ retry_root_backup: goto fail_sysfs; } - ret = btrfs_read_block_groups(extent_root); + ret = btrfs_read_block_groups(fs_info->extent_root); if (ret) { printk(KERN_ERR "BTRFS: Failed to read block groups: %d\n", ret); goto fail_sysfs; @@ -2864,48 +2944,11 @@ retry_root_backup: /* do not make disk changes in broken FS */ if (btrfs_super_log_root(disk_super) != 0) { - u64 bytenr = btrfs_super_log_root(disk_super); - - if (fs_devices->rw_devices == 0) { - printk(KERN_WARNING "BTRFS: log replay required " - "on RO media\n"); - err = -EIO; - goto fail_qgroup; - } - - log_tree_root = btrfs_alloc_root(fs_info); - if (!log_tree_root) { - err = -ENOMEM; - goto fail_qgroup; - } - - __setup_root(nodesize, sectorsize, stripesize, - log_tree_root, fs_info, BTRFS_TREE_LOG_OBJECTID); - - log_tree_root->node = read_tree_block(tree_root, bytenr, - generation + 1); - if (!log_tree_root->node || - !extent_buffer_uptodate(log_tree_root->node)) { - printk(KERN_ERR "BTRFS: failed to read log tree\n"); - free_extent_buffer(log_tree_root->node); - kfree(log_tree_root); - goto fail_qgroup; - } - /* returns with log_tree_root freed on success */ - ret = btrfs_recover_log_trees(log_tree_root); + ret = btrfs_replay_log(fs_info, fs_devices); if (ret) { - btrfs_error(tree_root->fs_info, ret, - "Failed to recover log tree"); - free_extent_buffer(log_tree_root->node); - kfree(log_tree_root); + err = ret; goto fail_qgroup; } - - if (sb->s_flags & MS_RDONLY) { - ret = btrfs_commit_super(tree_root); - if (ret) - goto fail_qgroup; - } } ret = btrfs_find_orphan_roots(tree_root); @@ -2966,7 +3009,7 @@ retry_root_backup: btrfs_qgroup_rescan_resume(fs_info); - if (create_uuid_tree) { + if (!fs_info->uuid_root) { pr_info("BTRFS: creating UUID tree\n"); ret = btrfs_create_uuid_tree(fs_info); if (ret) { @@ -2975,8 +3018,9 @@ retry_root_backup: close_ctree(tree_root); return ret; } - } else if (check_uuid_tree || - btrfs_test_opt(tree_root, RESCAN_UUID_TREE)) { + } else if (btrfs_test_opt(tree_root, RESCAN_UUID_TREE) || + fs_info->generation != + btrfs_super_uuid_tree_generation(disk_super)) { pr_info("BTRFS: checking UUID tree\n"); ret = btrfs_check_uuid_tree(fs_info); if (ret) { @@ -3668,7 +3712,7 @@ void close_ctree(struct btrfs_root *root) if (!(fs_info->sb->s_flags & MS_RDONLY)) { ret = btrfs_commit_super(root); if (ret) - btrfs_err(root->fs_info, "commit super ret %d", ret); + btrfs_err(fs_info, "commit super ret %d", ret); } if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) @@ -3680,10 +3724,10 @@ void close_ctree(struct btrfs_root *root) fs_info->closing = 2; smp_mb(); - btrfs_free_qgroup_config(root->fs_info); + btrfs_free_qgroup_config(fs_info); if (percpu_counter_sum(&fs_info->delalloc_bytes)) { - btrfs_info(root->fs_info, "at unmount delalloc count %lld", + btrfs_info(fs_info, "at unmount delalloc count %lld", percpu_counter_sum(&fs_info->delalloc_bytes)); } @@ -3723,7 +3767,7 @@ void close_ctree(struct btrfs_root *root) btrfs_free_stripe_hash_table(fs_info); - btrfs_free_block_rsv(root, root->orphan_block_rsv); + __btrfs_free_block_rsv(root->orphan_block_rsv); root->orphan_block_rsv = NULL; lock_chunks(root); @@ -4134,7 +4178,7 @@ static int btrfs_destroy_marked_extents(struct btrfs_root *root, clear_extent_bits(dirty_pages, start, end, mark, GFP_NOFS); while (start <= end) { - eb = btrfs_find_tree_block(root, start); + eb = btrfs_find_tree_block(root->fs_info, start); start += root->nodesize; if (!eb) continue; @@ -4285,7 +4329,7 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root) return 0; } -static struct extent_io_ops btree_extent_io_ops = { +static const struct extent_io_ops btree_extent_io_ops = { .readpage_end_io_hook = btree_readpage_end_io_hook, .readpage_io_failed_hook = btree_io_failed_hook, .submit_bio_hook = btree_submit_bio_hook, diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 27d44c0fd236..d4cbfeeeedd4 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -52,7 +52,7 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root, u64 bytenr); void clean_tree_block(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct extent_buffer *buf); + struct btrfs_fs_info *fs_info, struct extent_buffer *buf); int open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices, char *options); @@ -61,7 +61,7 @@ int write_ctree_super(struct btrfs_trans_handle *trans, struct btrfs_root *root, int max_mirrors); struct buffer_head *btrfs_read_dev_super(struct block_device *bdev); int btrfs_commit_super(struct btrfs_root *root); -struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root, +struct extent_buffer *btrfs_find_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr); struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root, struct btrfs_key *location); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 8b353ad02f03..1eef4ee01d1a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2538,6 +2538,12 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, * list before we release it. */ if (btrfs_delayed_ref_is_head(ref)) { + if (locked_ref->is_data && + locked_ref->total_ref_mod < 0) { + spin_lock(&delayed_refs->lock); + delayed_refs->pending_csums -= ref->num_bytes; + spin_unlock(&delayed_refs->lock); + } btrfs_delayed_ref_unlock(locked_ref); locked_ref = NULL; } @@ -2561,8 +2567,7 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, */ spin_lock(&delayed_refs->lock); avg = fs_info->avg_delayed_ref_runtime * 3 + runtime; - avg = div64_u64(avg, 4); - fs_info->avg_delayed_ref_runtime = avg; + fs_info->avg_delayed_ref_runtime = avg >> 2; /* div by 4 */ spin_unlock(&delayed_refs->lock); } return 0; @@ -2624,7 +2629,26 @@ static inline u64 heads_to_leaves(struct btrfs_root *root, u64 heads) * We don't ever fill up leaves all the way so multiply by 2 just to be * closer to what we're really going to want to ouse. */ - return div64_u64(num_bytes, BTRFS_LEAF_DATA_SIZE(root)); + return div_u64(num_bytes, BTRFS_LEAF_DATA_SIZE(root)); +} + +/* + * Takes the number of bytes to be csumm'ed and figures out how many leaves it + * would require to store the csums for that many bytes. + */ +u64 btrfs_csum_bytes_to_leaves(struct btrfs_root *root, u64 csum_bytes) +{ + u64 csum_size; + u64 num_csums_per_leaf; + u64 num_csums; + + csum_size = BTRFS_LEAF_DATA_SIZE(root) - sizeof(struct btrfs_item); + num_csums_per_leaf = div64_u64(csum_size, + (u64)btrfs_super_csum_size(root->fs_info->super_copy)); + num_csums = div64_u64(csum_bytes, root->sectorsize); + num_csums += num_csums_per_leaf - 1; + num_csums = div64_u64(num_csums, num_csums_per_leaf); + return num_csums; } int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans, @@ -2632,7 +2656,9 @@ int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans, { struct btrfs_block_rsv *global_rsv; u64 num_heads = trans->transaction->delayed_refs.num_heads_ready; - u64 num_bytes; + u64 csum_bytes = trans->transaction->delayed_refs.pending_csums; + u64 num_dirty_bgs = trans->transaction->num_dirty_bgs; + u64 num_bytes, num_dirty_bgs_bytes; int ret = 0; num_bytes = btrfs_calc_trans_metadata_size(root, 1); @@ -2640,17 +2666,22 @@ int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans, if (num_heads > 1) num_bytes += (num_heads - 1) * root->nodesize; num_bytes <<= 1; + num_bytes += btrfs_csum_bytes_to_leaves(root, csum_bytes) * root->nodesize; + num_dirty_bgs_bytes = btrfs_calc_trans_metadata_size(root, + num_dirty_bgs); global_rsv = &root->fs_info->global_block_rsv; /* * If we can't allocate any more chunks lets make sure we have _lots_ of * wiggle room since running delayed refs can create more delayed refs. */ - if (global_rsv->space_info->full) + if (global_rsv->space_info->full) { + num_dirty_bgs_bytes <<= 1; num_bytes <<= 1; + } spin_lock(&global_rsv->lock); - if (global_rsv->reserved <= num_bytes) + if (global_rsv->reserved <= num_bytes + num_dirty_bgs_bytes) ret = 1; spin_unlock(&global_rsv->lock); return ret; @@ -3193,7 +3224,7 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group, struct inode *inode = NULL; u64 alloc_hint = 0; int dcs = BTRFS_DC_ERROR; - int num_pages = 0; + u64 num_pages = 0; int retries = 0; int ret = 0; @@ -3267,7 +3298,7 @@ again: if (ret) goto out_put; - ret = btrfs_truncate_free_space_cache(root, trans, inode); + ret = btrfs_truncate_free_space_cache(root, trans, NULL, inode); if (ret) goto out_put; } @@ -3293,14 +3324,14 @@ again: * taking up quite a bit since it's not folded into the other space * cache. */ - num_pages = (int)div64_u64(block_group->key.offset, 256 * 1024 * 1024); + num_pages = div_u64(block_group->key.offset, 256 * 1024 * 1024); if (!num_pages) num_pages = 1; num_pages *= 16; num_pages *= PAGE_CACHE_SIZE; - ret = btrfs_check_data_free_space(inode, num_pages); + ret = btrfs_check_data_free_space(inode, num_pages, num_pages); if (ret) goto out_put; @@ -3351,16 +3382,156 @@ int btrfs_setup_space_cache(struct btrfs_trans_handle *trans, return 0; } -int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans, +/* + * transaction commit does final block group cache writeback during a + * critical section where nothing is allowed to change the FS. This is + * required in order for the cache to actually match the block group, + * but can introduce a lot of latency into the commit. + * + * So, btrfs_start_dirty_block_groups is here to kick off block group + * cache IO. There's a chance we'll have to redo some of it if the + * block group changes again during the commit, but it greatly reduces + * the commit latency by getting rid of the easy block groups while + * we're still allowing others to join the commit. + */ +int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans, struct btrfs_root *root) { struct btrfs_block_group_cache *cache; struct btrfs_transaction *cur_trans = trans->transaction; int ret = 0; - struct btrfs_path *path; + int should_put; + struct btrfs_path *path = NULL; + LIST_HEAD(dirty); + struct list_head *io = &cur_trans->io_bgs; + int num_started = 0; + int loops = 0; + + spin_lock(&cur_trans->dirty_bgs_lock); + if (!list_empty(&cur_trans->dirty_bgs)) { + list_splice_init(&cur_trans->dirty_bgs, &dirty); + } + spin_unlock(&cur_trans->dirty_bgs_lock); - if (list_empty(&cur_trans->dirty_bgs)) +again: + if (list_empty(&dirty)) { + btrfs_free_path(path); return 0; + } + + /* + * make sure all the block groups on our dirty list actually + * exist + */ + btrfs_create_pending_block_groups(trans, root); + + if (!path) { + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + } + + while (!list_empty(&dirty)) { + cache = list_first_entry(&dirty, + struct btrfs_block_group_cache, + dirty_list); + + /* + * cache_write_mutex is here only to save us from balance + * deleting this block group while we are writing out the + * cache + */ + mutex_lock(&trans->transaction->cache_write_mutex); + + /* + * this can happen if something re-dirties a block + * group that is already under IO. Just wait for it to + * finish and then do it all again + */ + if (!list_empty(&cache->io_list)) { + list_del_init(&cache->io_list); + btrfs_wait_cache_io(root, trans, cache, + &cache->io_ctl, path, + cache->key.objectid); + btrfs_put_block_group(cache); + } + + + /* + * btrfs_wait_cache_io uses the cache->dirty_list to decide + * if it should update the cache_state. Don't delete + * until after we wait. + * + * Since we're not running in the commit critical section + * we need the dirty_bgs_lock to protect from update_block_group + */ + spin_lock(&cur_trans->dirty_bgs_lock); + list_del_init(&cache->dirty_list); + spin_unlock(&cur_trans->dirty_bgs_lock); + + should_put = 1; + + cache_save_setup(cache, trans, path); + + if (cache->disk_cache_state == BTRFS_DC_SETUP) { + cache->io_ctl.inode = NULL; + ret = btrfs_write_out_cache(root, trans, cache, path); + if (ret == 0 && cache->io_ctl.inode) { + num_started++; + should_put = 0; + + /* + * the cache_write_mutex is protecting + * the io_list + */ + list_add_tail(&cache->io_list, io); + } else { + /* + * if we failed to write the cache, the + * generation will be bad and life goes on + */ + ret = 0; + } + } + if (!ret) + ret = write_one_cache_group(trans, root, path, cache); + mutex_unlock(&trans->transaction->cache_write_mutex); + + /* if its not on the io list, we need to put the block group */ + if (should_put) + btrfs_put_block_group(cache); + + if (ret) + break; + } + + /* + * go through delayed refs for all the stuff we've just kicked off + * and then loop back (just once) + */ + ret = btrfs_run_delayed_refs(trans, root, 0); + if (!ret && loops == 0) { + loops++; + spin_lock(&cur_trans->dirty_bgs_lock); + list_splice_init(&cur_trans->dirty_bgs, &dirty); + spin_unlock(&cur_trans->dirty_bgs_lock); + goto again; + } + + btrfs_free_path(path); + return ret; +} + +int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans, + struct btrfs_root *root) +{ + struct btrfs_block_group_cache *cache; + struct btrfs_transaction *cur_trans = trans->transaction; + int ret = 0; + int should_put; + struct btrfs_path *path; + struct list_head *io = &cur_trans->io_bgs; + int num_started = 0; path = btrfs_alloc_path(); if (!path) @@ -3376,16 +3547,61 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans, cache = list_first_entry(&cur_trans->dirty_bgs, struct btrfs_block_group_cache, dirty_list); + + /* + * this can happen if cache_save_setup re-dirties a block + * group that is already under IO. Just wait for it to + * finish and then do it all again + */ + if (!list_empty(&cache->io_list)) { + list_del_init(&cache->io_list); + btrfs_wait_cache_io(root, trans, cache, + &cache->io_ctl, path, + cache->key.objectid); + btrfs_put_block_group(cache); + } + + /* + * don't remove from the dirty list until after we've waited + * on any pending IO + */ list_del_init(&cache->dirty_list); - if (cache->disk_cache_state == BTRFS_DC_CLEAR) - cache_save_setup(cache, trans, path); + should_put = 1; + + cache_save_setup(cache, trans, path); + if (!ret) - ret = btrfs_run_delayed_refs(trans, root, - (unsigned long) -1); - if (!ret && cache->disk_cache_state == BTRFS_DC_SETUP) - btrfs_write_out_cache(root, trans, cache, path); + ret = btrfs_run_delayed_refs(trans, root, (unsigned long) -1); + + if (!ret && cache->disk_cache_state == BTRFS_DC_SETUP) { + cache->io_ctl.inode = NULL; + ret = btrfs_write_out_cache(root, trans, cache, path); + if (ret == 0 && cache->io_ctl.inode) { + num_started++; + should_put = 0; + list_add_tail(&cache->io_list, io); + } else { + /* + * if we failed to write the cache, the + * generation will be bad and life goes on + */ + ret = 0; + } + } if (!ret) ret = write_one_cache_group(trans, root, path, cache); + + /* if its not on the io list, we need to put the block group */ + if (should_put) + btrfs_put_block_group(cache); + } + + while (!list_empty(io)) { + cache = list_first_entry(io, struct btrfs_block_group_cache, + io_list); + list_del_init(&cache->io_list); + btrfs_wait_cache_io(root, trans, cache, + &cache->io_ctl, path, cache->key.objectid); btrfs_put_block_group(cache); } @@ -3635,19 +3851,21 @@ u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data) * This will check the space that the inode allocates from to make sure we have * enough space for bytes. */ -int btrfs_check_data_free_space(struct inode *inode, u64 bytes) +int btrfs_check_data_free_space(struct inode *inode, u64 bytes, u64 write_bytes) { struct btrfs_space_info *data_sinfo; struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_fs_info *fs_info = root->fs_info; u64 used; - int ret = 0, committed = 0, alloc_chunk = 1; + int ret = 0; + int need_commit = 2; + int have_pinned_space; /* make sure bytes are sectorsize aligned */ bytes = ALIGN(bytes, root->sectorsize); if (btrfs_is_free_space_inode(inode)) { - committed = 1; + need_commit = 0; ASSERT(current->journal_info); } @@ -3669,7 +3887,7 @@ again: * if we don't have enough free bytes in this space then we need * to alloc a new chunk. */ - if (!data_sinfo->full && alloc_chunk) { + if (!data_sinfo->full) { u64 alloc_target; data_sinfo->force_alloc = CHUNK_ALLOC_FORCE; @@ -3697,8 +3915,10 @@ alloc: if (ret < 0) { if (ret != -ENOSPC) return ret; - else + else { + have_pinned_space = 1; goto commit_trans; + } } if (!data_sinfo) @@ -3709,26 +3929,39 @@ alloc: /* * If we don't have enough pinned space to deal with this - * allocation don't bother committing the transaction. + * allocation, and no removed chunk in current transaction, + * don't bother committing the transaction. */ - if (percpu_counter_compare(&data_sinfo->total_bytes_pinned, - bytes) < 0) - committed = 1; + have_pinned_space = percpu_counter_compare( + &data_sinfo->total_bytes_pinned, + used + bytes - data_sinfo->total_bytes); spin_unlock(&data_sinfo->lock); /* commit the current transaction and try again */ commit_trans: - if (!committed && + if (need_commit && !atomic_read(&root->fs_info->open_ioctl_trans)) { - committed = 1; + need_commit--; trans = btrfs_join_transaction(root); if (IS_ERR(trans)) return PTR_ERR(trans); - ret = btrfs_commit_transaction(trans, root); - if (ret) - return ret; - goto again; + if (have_pinned_space >= 0 || + trans->transaction->have_free_bgs || + need_commit > 0) { + ret = btrfs_commit_transaction(trans, root); + if (ret) + return ret; + /* + * make sure that all running delayed iput are + * done + */ + down_write(&root->fs_info->delayed_iput_sem); + up_write(&root->fs_info->delayed_iput_sem); + goto again; + } else { + btrfs_end_transaction(trans, root); + } } trace_btrfs_space_reservation(root->fs_info, @@ -3736,12 +3969,16 @@ commit_trans: data_sinfo->flags, bytes, 1); return -ENOSPC; } + ret = btrfs_qgroup_reserve(root, write_bytes); + if (ret) + goto out; data_sinfo->bytes_may_use += bytes; trace_btrfs_space_reservation(root->fs_info, "space_info", data_sinfo->flags, bytes, 1); +out: spin_unlock(&data_sinfo->lock); - return 0; + return ret; } /* @@ -4298,8 +4535,13 @@ out: static inline int need_do_async_reclaim(struct btrfs_space_info *space_info, struct btrfs_fs_info *fs_info, u64 used) { - return (used >= div_factor_fine(space_info->total_bytes, 98) && - !btrfs_fs_closing(fs_info) && + u64 thresh = div_factor_fine(space_info->total_bytes, 98); + + /* If we're just plain full then async reclaim just slows us down. */ + if (space_info->bytes_used >= thresh) + return 0; + + return (used >= thresh && !btrfs_fs_closing(fs_info) && !test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state)); } @@ -4354,10 +4596,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) if (!btrfs_need_do_async_reclaim(space_info, fs_info, flush_state)) return; - } while (flush_state <= COMMIT_TRANS); - - if (btrfs_need_do_async_reclaim(space_info, fs_info, flush_state)) - queue_work(system_unbound_wq, work); + } while (flush_state < COMMIT_TRANS); } void btrfs_init_async_reclaim_work(struct work_struct *work) @@ -4700,6 +4939,11 @@ void btrfs_free_block_rsv(struct btrfs_root *root, kfree(rsv); } +void __btrfs_free_block_rsv(struct btrfs_block_rsv *rsv) +{ + kfree(rsv); +} + int btrfs_block_rsv_add(struct btrfs_root *root, struct btrfs_block_rsv *block_rsv, u64 num_bytes, enum btrfs_reserve_flush_enum flush) @@ -4812,10 +5056,10 @@ static u64 calc_global_metadata_size(struct btrfs_fs_info *fs_info) num_bytes = (data_used >> fs_info->sb->s_blocksize_bits) * csum_size * 2; - num_bytes += div64_u64(data_used + meta_used, 50); + num_bytes += div_u64(data_used + meta_used, 50); if (num_bytes * 3 > meta_used) - num_bytes = div64_u64(meta_used, 3); + num_bytes = div_u64(meta_used, 3); return ALIGN(num_bytes, fs_info->extent_root->nodesize << 10); } @@ -4998,8 +5242,6 @@ void btrfs_subvolume_release_metadata(struct btrfs_root *root, u64 qgroup_reserved) { btrfs_block_rsv_release(root, rsv, (u64)-1); - if (qgroup_reserved) - btrfs_qgroup_free(root, qgroup_reserved); } /** @@ -5066,30 +5308,18 @@ static u64 calc_csum_metadata_size(struct inode *inode, u64 num_bytes, int reserve) { struct btrfs_root *root = BTRFS_I(inode)->root; - u64 csum_size; - int num_csums_per_leaf; - int num_csums; - int old_csums; + u64 old_csums, num_csums; if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM && BTRFS_I(inode)->csum_bytes == 0) return 0; - old_csums = (int)div64_u64(BTRFS_I(inode)->csum_bytes, root->sectorsize); + old_csums = btrfs_csum_bytes_to_leaves(root, BTRFS_I(inode)->csum_bytes); if (reserve) BTRFS_I(inode)->csum_bytes += num_bytes; else BTRFS_I(inode)->csum_bytes -= num_bytes; - csum_size = BTRFS_LEAF_DATA_SIZE(root) - sizeof(struct btrfs_item); - num_csums_per_leaf = (int)div64_u64(csum_size, - sizeof(struct btrfs_csum_item) + - sizeof(struct btrfs_disk_key)); - num_csums = (int)div64_u64(BTRFS_I(inode)->csum_bytes, root->sectorsize); - num_csums = num_csums + num_csums_per_leaf - 1; - num_csums = num_csums / num_csums_per_leaf; - - old_csums = old_csums + num_csums_per_leaf - 1; - old_csums = old_csums / num_csums_per_leaf; + num_csums = btrfs_csum_bytes_to_leaves(root, BTRFS_I(inode)->csum_bytes); /* No change, no need to reserve more */ if (old_csums == num_csums) @@ -5163,8 +5393,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) spin_unlock(&BTRFS_I(inode)->lock); if (root->fs_info->quota_enabled) { - ret = btrfs_qgroup_reserve(root, num_bytes + - nr_extents * root->nodesize); + ret = btrfs_qgroup_reserve(root, nr_extents * root->nodesize); if (ret) goto out_fail; } @@ -5172,8 +5401,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) ret = reserve_metadata_bytes(root, block_rsv, to_reserve, flush); if (unlikely(ret)) { if (root->fs_info->quota_enabled) - btrfs_qgroup_free(root, num_bytes + - nr_extents * root->nodesize); + btrfs_qgroup_free(root, nr_extents * root->nodesize); goto out_fail; } @@ -5290,10 +5518,6 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes) trace_btrfs_space_reservation(root->fs_info, "delalloc", btrfs_ino(inode), to_free, 0); - if (root->fs_info->quota_enabled) { - btrfs_qgroup_free(root, num_bytes + - dropped * root->nodesize); - } btrfs_block_rsv_release(root, &root->fs_info->delalloc_block_rsv, to_free); @@ -5318,7 +5542,7 @@ int btrfs_delalloc_reserve_space(struct inode *inode, u64 num_bytes) { int ret; - ret = btrfs_check_data_free_space(inode, num_bytes); + ret = btrfs_check_data_free_space(inode, num_bytes, num_bytes); if (ret) return ret; @@ -5390,14 +5614,6 @@ static int update_block_group(struct btrfs_trans_handle *trans, if (!alloc && cache->cached == BTRFS_CACHE_NO) cache_block_group(cache, 1); - spin_lock(&trans->transaction->dirty_bgs_lock); - if (list_empty(&cache->dirty_list)) { - list_add_tail(&cache->dirty_list, - &trans->transaction->dirty_bgs); - btrfs_get_block_group(cache); - } - spin_unlock(&trans->transaction->dirty_bgs_lock); - byte_in_group = bytenr - cache->key.objectid; WARN_ON(byte_in_group > cache->key.offset); @@ -5446,6 +5662,16 @@ static int update_block_group(struct btrfs_trans_handle *trans, spin_unlock(&info->unused_bgs_lock); } } + + spin_lock(&trans->transaction->dirty_bgs_lock); + if (list_empty(&cache->dirty_list)) { + list_add_tail(&cache->dirty_list, + &trans->transaction->dirty_bgs); + trans->transaction->num_dirty_bgs++; + btrfs_get_block_group(cache); + } + spin_unlock(&trans->transaction->dirty_bgs_lock); + btrfs_put_block_group(cache); total -= num_bytes; bytenr += num_bytes; @@ -6956,15 +7182,15 @@ static int __btrfs_free_reserved_extent(struct btrfs_root *root, return -ENOSPC; } - if (btrfs_test_opt(root, DISCARD)) - ret = btrfs_discard_extent(root, start, len, NULL); - if (pin) pin_down_extent(root, cache, start, len, 1); else { + if (btrfs_test_opt(root, DISCARD)) + ret = btrfs_discard_extent(root, start, len, NULL); btrfs_add_free_space(cache, start, len); btrfs_update_reserved_bytes(cache, len, RESERVE_FREE, delalloc); } + btrfs_put_block_group(cache); trace_btrfs_reserved_extent_free(root, start, len); @@ -7095,9 +7321,9 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans, ret = btrfs_insert_empty_item(trans, fs_info->extent_root, path, ins, size); if (ret) { + btrfs_free_path(path); btrfs_free_and_pin_reserved_extent(root, ins->objectid, root->nodesize); - btrfs_free_path(path); return ret; } @@ -7217,7 +7443,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, btrfs_set_header_generation(buf, trans->transid); btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level); btrfs_tree_lock(buf); - clean_tree_block(trans, root, buf); + clean_tree_block(trans, root->fs_info, buf); clear_bit(EXTENT_BUFFER_STALE, &buf->bflags); btrfs_set_lock_blocking(buf); @@ -7815,7 +8041,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, bytenr = btrfs_node_blockptr(path->nodes[level], path->slots[level]); blocksize = root->nodesize; - next = btrfs_find_tree_block(root, bytenr); + next = btrfs_find_tree_block(root->fs_info, bytenr); if (!next) { next = btrfs_find_create_tree_block(root, bytenr); if (!next) @@ -8016,7 +8242,7 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans, btrfs_set_lock_blocking(eb); path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING; } - clean_tree_block(trans, root, eb); + clean_tree_block(trans, root->fs_info, eb); } if (eb == root->node) { @@ -8533,10 +8759,30 @@ int btrfs_set_block_group_ro(struct btrfs_root *root, BUG_ON(cache->ro); +again: trans = btrfs_join_transaction(root); if (IS_ERR(trans)) return PTR_ERR(trans); + /* + * we're not allowed to set block groups readonly after the dirty + * block groups cache has started writing. If it already started, + * back off and let this transaction commit + */ + mutex_lock(&root->fs_info->ro_block_group_mutex); + if (trans->transaction->dirty_bg_run) { + u64 transid = trans->transid; + + mutex_unlock(&root->fs_info->ro_block_group_mutex); + btrfs_end_transaction(trans, root); + + ret = btrfs_wait_for_commit(root, transid); + if (ret) + return ret; + goto again; + } + + ret = set_block_group_ro(cache, 0); if (!ret) goto out; @@ -8551,6 +8797,7 @@ out: alloc_flags = update_block_group_flags(root, cache->flags); check_system_chunk(trans, root, alloc_flags); } + mutex_unlock(&root->fs_info->ro_block_group_mutex); btrfs_end_transaction(trans, root); return ret; @@ -8720,7 +8967,7 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr) min_free <<= 1; } else if (index == BTRFS_RAID_RAID0) { dev_min = fs_devices->rw_devices; - do_div(min_free, dev_min); + min_free = div64_u64(min_free, dev_min); } /* We need to do this so that we can look at pending chunks */ @@ -8992,6 +9239,7 @@ btrfs_create_block_group_cache(struct btrfs_root *root, u64 start, u64 size) INIT_LIST_HEAD(&cache->bg_list); INIT_LIST_HEAD(&cache->ro_list); INIT_LIST_HEAD(&cache->dirty_list); + INIT_LIST_HEAD(&cache->io_list); btrfs_init_free_space_ctl(cache); atomic_set(&cache->trimming, 0); @@ -9355,7 +9603,38 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, goto out; } + /* + * get the inode first so any iput calls done for the io_list + * aren't the final iput (no unlinks allowed now) + */ inode = lookup_free_space_inode(tree_root, block_group, path); + + mutex_lock(&trans->transaction->cache_write_mutex); + /* + * make sure our free spache cache IO is done before remove the + * free space inode + */ + spin_lock(&trans->transaction->dirty_bgs_lock); + if (!list_empty(&block_group->io_list)) { + list_del_init(&block_group->io_list); + + WARN_ON(!IS_ERR(inode) && inode != block_group->io_ctl.inode); + + spin_unlock(&trans->transaction->dirty_bgs_lock); + btrfs_wait_cache_io(root, trans, block_group, + &block_group->io_ctl, path, + block_group->key.objectid); + btrfs_put_block_group(block_group); + spin_lock(&trans->transaction->dirty_bgs_lock); + } + + if (!list_empty(&block_group->dirty_list)) { + list_del_init(&block_group->dirty_list); + btrfs_put_block_group(block_group); + } + spin_unlock(&trans->transaction->dirty_bgs_lock); + mutex_unlock(&trans->transaction->cache_write_mutex); + if (!IS_ERR(inode)) { ret = btrfs_orphan_add(trans, inode); if (ret) { @@ -9448,18 +9727,29 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, spin_lock(&trans->transaction->dirty_bgs_lock); if (!list_empty(&block_group->dirty_list)) { - list_del_init(&block_group->dirty_list); - btrfs_put_block_group(block_group); + WARN_ON(1); + } + if (!list_empty(&block_group->io_list)) { + WARN_ON(1); } spin_unlock(&trans->transaction->dirty_bgs_lock); - btrfs_remove_free_space_cache(block_group); spin_lock(&block_group->space_info->lock); list_del_init(&block_group->ro_list); + + if (btrfs_test_opt(root, ENOSPC_DEBUG)) { + WARN_ON(block_group->space_info->total_bytes + < block_group->key.offset); + WARN_ON(block_group->space_info->bytes_readonly + < block_group->key.offset); + WARN_ON(block_group->space_info->disk_total + < block_group->key.offset * factor); + } block_group->space_info->total_bytes -= block_group->key.offset; block_group->space_info->bytes_readonly -= block_group->key.offset; block_group->space_info->disk_total -= block_group->key.offset * factor; + spin_unlock(&block_group->space_info->lock); memcpy(&key, &block_group->key, sizeof(key)); @@ -9647,8 +9937,18 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) mutex_unlock(&fs_info->unused_bg_unpin_mutex); /* Reset pinned so btrfs_put_block_group doesn't complain */ + spin_lock(&space_info->lock); + spin_lock(&block_group->lock); + + space_info->bytes_pinned -= block_group->pinned; + space_info->bytes_readonly += block_group->pinned; + percpu_counter_add(&space_info->total_bytes_pinned, + -block_group->pinned); block_group->pinned = 0; + spin_unlock(&block_group->lock); + spin_unlock(&space_info->lock); + /* * Btrfs_remove_chunk will abort the transaction if things go * horribly wrong. diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index d688cfe5d496..782f3bc4651d 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4514,8 +4514,11 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, } ret = fiemap_fill_next_extent(fieinfo, em_start, disko, em_len, flags); - if (ret) + if (ret) { + if (ret == 1) + ret = 0; goto out_free; + } } out_free: free_extent_map(em); diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 695b0ccfb755..c668f36898d3 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -97,7 +97,7 @@ struct extent_io_tree { u64 dirty_bytes; int track_uptodate; spinlock_t lock; - struct extent_io_ops *ops; + const struct extent_io_ops *ops; }; struct extent_state { diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 84a2d1868271..58ece6558430 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -185,8 +185,8 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root, nblocks = bio->bi_iter.bi_size >> inode->i_sb->s_blocksize_bits; if (!dst) { if (nblocks * csum_size > BTRFS_BIO_INLINE_CSUM_SIZE) { - btrfs_bio->csum_allocated = kmalloc(nblocks * csum_size, - GFP_NOFS); + btrfs_bio->csum_allocated = kmalloc_array(nblocks, + csum_size, GFP_NOFS); if (!btrfs_bio->csum_allocated) { btrfs_free_path(path); return -ENOMEM; @@ -553,7 +553,7 @@ static noinline void truncate_one_csum(struct btrfs_root *root, btrfs_truncate_item(root, path, new_size, 0); key->offset = end_byte; - btrfs_set_item_key_safe(root, path, key); + btrfs_set_item_key_safe(root->fs_info, path, key); } else { BUG(); } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 30982bbd31c3..467620a3b1f9 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -24,7 +24,6 @@ #include <linux/string.h> #include <linux/backing-dev.h> #include <linux/mpage.h> -#include <linux/aio.h> #include <linux/falloc.h> #include <linux/swap.h> #include <linux/writeback.h> @@ -32,6 +31,7 @@ #include <linux/compat.h> #include <linux/slab.h> #include <linux/btrfs.h> +#include <linux/uio.h> #include "ctree.h" #include "disk-io.h" #include "transaction.h" @@ -273,11 +273,7 @@ void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info) defrag = rb_entry(node, struct inode_defrag, rb_node); kmem_cache_free(btrfs_inode_defrag_cachep, defrag); - if (need_resched()) { - spin_unlock(&fs_info->defrag_inodes_lock); - cond_resched(); - spin_lock(&fs_info->defrag_inodes_lock); - } + cond_resched_lock(&fs_info->defrag_inodes_lock); node = rb_first(&fs_info->defrag_inodes); } @@ -868,7 +864,7 @@ next_slot: memcpy(&new_key, &key, sizeof(new_key)); new_key.offset = end; - btrfs_set_item_key_safe(root, path, &new_key); + btrfs_set_item_key_safe(root->fs_info, path, &new_key); extent_offset += end - key.offset; btrfs_set_file_extent_offset(leaf, fi, extent_offset); @@ -1126,7 +1122,7 @@ again: ino, bytenr, orig_offset, &other_start, &other_end)) { new_key.offset = end; - btrfs_set_item_key_safe(root, path, &new_key); + btrfs_set_item_key_safe(root->fs_info, path, &new_key); fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); btrfs_set_file_extent_generation(leaf, fi, @@ -1160,7 +1156,7 @@ again: trans->transid); path->slots[0]++; new_key.offset = start; - btrfs_set_item_key_safe(root, path, &new_key); + btrfs_set_item_key_safe(root->fs_info, path, &new_key); fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); @@ -1485,7 +1481,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, PAGE_CACHE_SIZE / (sizeof(struct page *))); nrptrs = min(nrptrs, current->nr_dirtied_pause - current->nr_dirtied); nrptrs = max(nrptrs, 8); - pages = kmalloc(nrptrs * sizeof(struct page *), GFP_KERNEL); + pages = kmalloc_array(nrptrs, sizeof(struct page *), GFP_KERNEL); if (!pages) return -ENOMEM; @@ -1514,7 +1510,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, } reserve_bytes = num_pages << PAGE_CACHE_SHIFT; - ret = btrfs_check_data_free_space(inode, reserve_bytes); + ret = btrfs_check_data_free_space(inode, reserve_bytes, write_bytes); if (ret == -ENOSPC && (BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC))) { @@ -1635,8 +1631,8 @@ again: btrfs_end_write_no_snapshoting(root); if (only_release_metadata && copied > 0) { - u64 lockstart = round_down(pos, root->sectorsize); - u64 lockend = lockstart + + lockstart = round_down(pos, root->sectorsize); + lockend = lockstart + (dirty_pages << PAGE_CACHE_SHIFT) - 1; set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, @@ -1739,27 +1735,19 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, u64 start_pos; u64 end_pos; ssize_t num_written = 0; - ssize_t err = 0; - size_t count = iov_iter_count(from); bool sync = (file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host); - loff_t pos = iocb->ki_pos; + ssize_t err; + loff_t pos; + size_t count; mutex_lock(&inode->i_mutex); - - current->backing_dev_info = inode_to_bdi(inode); - err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); - if (err) { + err = generic_write_checks(iocb, from); + if (err <= 0) { mutex_unlock(&inode->i_mutex); - goto out; - } - - if (count == 0) { - mutex_unlock(&inode->i_mutex); - goto out; + return err; } - iov_iter_truncate(from, count); - + current->backing_dev_info = inode_to_bdi(inode); err = file_remove_suid(file); if (err) { mutex_unlock(&inode->i_mutex); @@ -1786,6 +1774,8 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, */ update_time_for_write(inode); + pos = iocb->ki_pos; + count = iov_iter_count(from); start_pos = round_down(pos, root->sectorsize); if (start_pos > i_size_read(inode)) { /* Expand hole size to cover write data, preventing empty gap */ @@ -1800,7 +1790,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, if (sync) atomic_inc(&BTRFS_I(inode)->sync_writers); - if (file->f_flags & O_DIRECT) { + if (iocb->ki_flags & IOCB_DIRECT) { num_written = __btrfs_direct_write(iocb, from, pos); } else { num_written = __btrfs_buffered_write(file, from, pos); @@ -1815,7 +1805,9 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, * otherwise subsequent syncs to a file that's been synced in this * transaction will appear to have already occured. */ + spin_lock(&BTRFS_I(inode)->lock); BTRFS_I(inode)->last_sub_trans = root->log_transid; + spin_unlock(&BTRFS_I(inode)->lock); if (num_written > 0) { err = generic_write_sync(file, pos, num_written); if (err < 0) @@ -2168,7 +2160,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode, u64 num_bytes; key.offset = offset; - btrfs_set_item_key_safe(root, path, &key); + btrfs_set_item_key_safe(root->fs_info, path, &key); fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); num_bytes = btrfs_file_extent_num_bytes(leaf, fi) + end - @@ -2551,7 +2543,6 @@ static long btrfs_fallocate(struct file *file, int mode, { struct inode *inode = file_inode(file); struct extent_state *cached_state = NULL; - struct btrfs_root *root = BTRFS_I(inode)->root; u64 cur_offset; u64 last_byte; u64 alloc_start; @@ -2576,14 +2567,9 @@ static long btrfs_fallocate(struct file *file, int mode, * Make sure we have enough space before we do the * allocation. */ - ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start); + ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start, alloc_end - alloc_start); if (ret) return ret; - if (root->fs_info->quota_enabled) { - ret = btrfs_qgroup_reserve(root, alloc_end - alloc_start); - if (ret) - goto out_reserve_fail; - } mutex_lock(&inode->i_mutex); ret = inode_newsize_ok(inode, alloc_end); @@ -2673,23 +2659,35 @@ static long btrfs_fallocate(struct file *file, int mode, 1 << inode->i_blkbits, offset + len, &alloc_hint); - - if (ret < 0) { - free_extent_map(em); - break; - } } else if (actual_end > inode->i_size && !(mode & FALLOC_FL_KEEP_SIZE)) { + struct btrfs_trans_handle *trans; + struct btrfs_root *root = BTRFS_I(inode)->root; + /* * We didn't need to allocate any more space, but we * still extended the size of the file so we need to - * update i_size. + * update i_size and the inode item. */ - inode->i_ctime = CURRENT_TIME; - i_size_write(inode, actual_end); - btrfs_ordered_update_i_size(inode, actual_end, NULL); + trans = btrfs_start_transaction(root, 1); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + } else { + inode->i_ctime = CURRENT_TIME; + i_size_write(inode, actual_end); + btrfs_ordered_update_i_size(inode, actual_end, + NULL); + ret = btrfs_update_inode(trans, root, inode); + if (ret) + btrfs_end_transaction(trans, root); + else + ret = btrfs_end_transaction(trans, + root); + } } free_extent_map(em); + if (ret < 0) + break; cur_offset = last_byte; if (cur_offset >= alloc_end) { @@ -2701,9 +2699,6 @@ static long btrfs_fallocate(struct file *file, int mode, &cached_state, GFP_NOFS); out: mutex_unlock(&inode->i_mutex); - if (root->fs_info->quota_enabled) - btrfs_qgroup_free(root, alloc_end - alloc_start); -out_reserve_fail: /* Let go of our reservation. */ btrfs_free_reserved_data_space(inode, alloc_end - alloc_start); return ret; @@ -2806,8 +2801,6 @@ out: const struct file_operations btrfs_file_operations = { .llseek = btrfs_file_llseek, - .read = new_sync_read, - .write = new_sync_write, .read_iter = generic_file_read_iter, .splice_read = generic_file_splice_read, .write_iter = btrfs_file_write_iter, diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index a71978578fa7..253cb74b0e27 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -85,7 +85,8 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root, } mapping_set_gfp_mask(inode->i_mapping, - mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS); + mapping_gfp_mask(inode->i_mapping) & + ~(GFP_NOFS & ~__GFP_HIGHMEM)); return inode; } @@ -170,13 +171,13 @@ static int __create_free_space_inode(struct btrfs_root *root, key.objectid = BTRFS_FREE_SPACE_OBJECTID; key.offset = offset; key.type = 0; - ret = btrfs_insert_empty_item(trans, root, path, &key, sizeof(struct btrfs_free_space_header)); if (ret < 0) { btrfs_release_path(path); return ret; } + leaf = path->nodes[0]; header = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_free_space_header); @@ -225,9 +226,37 @@ int btrfs_check_trunc_cache_free_space(struct btrfs_root *root, int btrfs_truncate_free_space_cache(struct btrfs_root *root, struct btrfs_trans_handle *trans, + struct btrfs_block_group_cache *block_group, struct inode *inode) { int ret = 0; + struct btrfs_path *path = btrfs_alloc_path(); + + if (!path) { + ret = -ENOMEM; + goto fail; + } + + if (block_group) { + mutex_lock(&trans->transaction->cache_write_mutex); + if (!list_empty(&block_group->io_list)) { + list_del_init(&block_group->io_list); + + btrfs_wait_cache_io(root, trans, block_group, + &block_group->io_ctl, path, + block_group->key.objectid); + btrfs_put_block_group(block_group); + } + + /* + * now that we've truncated the cache away, its no longer + * setup or written + */ + spin_lock(&block_group->lock); + block_group->disk_cache_state = BTRFS_DC_CLEAR; + spin_unlock(&block_group->lock); + } + btrfs_free_path(path); btrfs_i_size_write(inode, 0); truncate_pagecache(inode, 0); @@ -235,15 +264,23 @@ int btrfs_truncate_free_space_cache(struct btrfs_root *root, /* * We don't need an orphan item because truncating the free space cache * will never be split across transactions. + * We don't need to check for -EAGAIN because we're a free space + * cache inode */ ret = btrfs_truncate_inode_items(trans, root, inode, 0, BTRFS_EXTENT_DATA_KEY); if (ret) { + mutex_unlock(&trans->transaction->cache_write_mutex); btrfs_abort_transaction(trans, root, ret); return ret; } ret = btrfs_update_inode(trans, root, inode); + + if (block_group) + mutex_unlock(&trans->transaction->cache_write_mutex); + +fail: if (ret) btrfs_abort_transaction(trans, root, ret); @@ -269,18 +306,7 @@ static int readahead_cache(struct inode *inode) return 0; } -struct io_ctl { - void *cur, *orig; - struct page *page; - struct page **pages; - struct btrfs_root *root; - unsigned long size; - int index; - int num_pages; - unsigned check_crcs:1; -}; - -static int io_ctl_init(struct io_ctl *io_ctl, struct inode *inode, +static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode, struct btrfs_root *root, int write) { int num_pages; @@ -296,45 +322,46 @@ static int io_ctl_init(struct io_ctl *io_ctl, struct inode *inode, (num_pages * sizeof(u32)) >= PAGE_CACHE_SIZE) return -ENOSPC; - memset(io_ctl, 0, sizeof(struct io_ctl)); + memset(io_ctl, 0, sizeof(struct btrfs_io_ctl)); - io_ctl->pages = kzalloc(sizeof(struct page *) * num_pages, GFP_NOFS); + io_ctl->pages = kcalloc(num_pages, sizeof(struct page *), GFP_NOFS); if (!io_ctl->pages) return -ENOMEM; io_ctl->num_pages = num_pages; io_ctl->root = root; io_ctl->check_crcs = check_crcs; + io_ctl->inode = inode; return 0; } -static void io_ctl_free(struct io_ctl *io_ctl) +static void io_ctl_free(struct btrfs_io_ctl *io_ctl) { kfree(io_ctl->pages); + io_ctl->pages = NULL; } -static void io_ctl_unmap_page(struct io_ctl *io_ctl) +static void io_ctl_unmap_page(struct btrfs_io_ctl *io_ctl) { if (io_ctl->cur) { - kunmap(io_ctl->page); io_ctl->cur = NULL; io_ctl->orig = NULL; } } -static void io_ctl_map_page(struct io_ctl *io_ctl, int clear) +static void io_ctl_map_page(struct btrfs_io_ctl *io_ctl, int clear) { ASSERT(io_ctl->index < io_ctl->num_pages); io_ctl->page = io_ctl->pages[io_ctl->index++]; - io_ctl->cur = kmap(io_ctl->page); + io_ctl->cur = page_address(io_ctl->page); io_ctl->orig = io_ctl->cur; io_ctl->size = PAGE_CACHE_SIZE; if (clear) memset(io_ctl->cur, 0, PAGE_CACHE_SIZE); } -static void io_ctl_drop_pages(struct io_ctl *io_ctl) +static void io_ctl_drop_pages(struct btrfs_io_ctl *io_ctl) { int i; @@ -349,7 +376,7 @@ static void io_ctl_drop_pages(struct io_ctl *io_ctl) } } -static int io_ctl_prepare_pages(struct io_ctl *io_ctl, struct inode *inode, +static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, struct inode *inode, int uptodate) { struct page *page; @@ -383,7 +410,7 @@ static int io_ctl_prepare_pages(struct io_ctl *io_ctl, struct inode *inode, return 0; } -static void io_ctl_set_generation(struct io_ctl *io_ctl, u64 generation) +static void io_ctl_set_generation(struct btrfs_io_ctl *io_ctl, u64 generation) { __le64 *val; @@ -406,7 +433,7 @@ static void io_ctl_set_generation(struct io_ctl *io_ctl, u64 generation) io_ctl->cur += sizeof(u64); } -static int io_ctl_check_generation(struct io_ctl *io_ctl, u64 generation) +static int io_ctl_check_generation(struct btrfs_io_ctl *io_ctl, u64 generation) { __le64 *gen; @@ -435,7 +462,7 @@ static int io_ctl_check_generation(struct io_ctl *io_ctl, u64 generation) return 0; } -static void io_ctl_set_crc(struct io_ctl *io_ctl, int index) +static void io_ctl_set_crc(struct btrfs_io_ctl *io_ctl, int index) { u32 *tmp; u32 crc = ~(u32)0; @@ -453,13 +480,12 @@ static void io_ctl_set_crc(struct io_ctl *io_ctl, int index) PAGE_CACHE_SIZE - offset); btrfs_csum_final(crc, (char *)&crc); io_ctl_unmap_page(io_ctl); - tmp = kmap(io_ctl->pages[0]); + tmp = page_address(io_ctl->pages[0]); tmp += index; *tmp = crc; - kunmap(io_ctl->pages[0]); } -static int io_ctl_check_crc(struct io_ctl *io_ctl, int index) +static int io_ctl_check_crc(struct btrfs_io_ctl *io_ctl, int index) { u32 *tmp, val; u32 crc = ~(u32)0; @@ -473,10 +499,9 @@ static int io_ctl_check_crc(struct io_ctl *io_ctl, int index) if (index == 0) offset = sizeof(u32) * io_ctl->num_pages; - tmp = kmap(io_ctl->pages[0]); + tmp = page_address(io_ctl->pages[0]); tmp += index; val = *tmp; - kunmap(io_ctl->pages[0]); io_ctl_map_page(io_ctl, 0); crc = btrfs_csum_data(io_ctl->orig + offset, crc, @@ -492,7 +517,7 @@ static int io_ctl_check_crc(struct io_ctl *io_ctl, int index) return 0; } -static int io_ctl_add_entry(struct io_ctl *io_ctl, u64 offset, u64 bytes, +static int io_ctl_add_entry(struct btrfs_io_ctl *io_ctl, u64 offset, u64 bytes, void *bitmap) { struct btrfs_free_space_entry *entry; @@ -522,7 +547,7 @@ static int io_ctl_add_entry(struct io_ctl *io_ctl, u64 offset, u64 bytes, return 0; } -static int io_ctl_add_bitmap(struct io_ctl *io_ctl, void *bitmap) +static int io_ctl_add_bitmap(struct btrfs_io_ctl *io_ctl, void *bitmap) { if (!io_ctl->cur) return -ENOSPC; @@ -545,7 +570,7 @@ static int io_ctl_add_bitmap(struct io_ctl *io_ctl, void *bitmap) return 0; } -static void io_ctl_zero_remaining_pages(struct io_ctl *io_ctl) +static void io_ctl_zero_remaining_pages(struct btrfs_io_ctl *io_ctl) { /* * If we're not on the boundary we know we've modified the page and we @@ -562,7 +587,7 @@ static void io_ctl_zero_remaining_pages(struct io_ctl *io_ctl) } } -static int io_ctl_read_entry(struct io_ctl *io_ctl, +static int io_ctl_read_entry(struct btrfs_io_ctl *io_ctl, struct btrfs_free_space *entry, u8 *type) { struct btrfs_free_space_entry *e; @@ -589,7 +614,7 @@ static int io_ctl_read_entry(struct io_ctl *io_ctl, return 0; } -static int io_ctl_read_bitmap(struct io_ctl *io_ctl, +static int io_ctl_read_bitmap(struct btrfs_io_ctl *io_ctl, struct btrfs_free_space *entry) { int ret; @@ -648,7 +673,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, { struct btrfs_free_space_header *header; struct extent_buffer *leaf; - struct io_ctl io_ctl; + struct btrfs_io_ctl io_ctl; struct btrfs_key key; struct btrfs_free_space *e, *n; LIST_HEAD(bitmaps); @@ -877,7 +902,7 @@ out: } static noinline_for_stack -int write_cache_extent_entries(struct io_ctl *io_ctl, +int write_cache_extent_entries(struct btrfs_io_ctl *io_ctl, struct btrfs_free_space_ctl *ctl, struct btrfs_block_group_cache *block_group, int *entries, int *bitmaps, @@ -885,6 +910,7 @@ int write_cache_extent_entries(struct io_ctl *io_ctl, { int ret; struct btrfs_free_cluster *cluster = NULL; + struct btrfs_free_cluster *cluster_locked = NULL; struct rb_node *node = rb_first(&ctl->free_space_offset); struct btrfs_trim_range *trim_entry; @@ -896,6 +922,8 @@ int write_cache_extent_entries(struct io_ctl *io_ctl, } if (!node && cluster) { + cluster_locked = cluster; + spin_lock(&cluster_locked->lock); node = rb_first(&cluster->root); cluster = NULL; } @@ -919,9 +947,15 @@ int write_cache_extent_entries(struct io_ctl *io_ctl, node = rb_next(node); if (!node && cluster) { node = rb_first(&cluster->root); + cluster_locked = cluster; + spin_lock(&cluster_locked->lock); cluster = NULL; } } + if (cluster_locked) { + spin_unlock(&cluster_locked->lock); + cluster_locked = NULL; + } /* * Make sure we don't miss any range that was removed from our rbtree @@ -939,6 +973,8 @@ int write_cache_extent_entries(struct io_ctl *io_ctl, return 0; fail: + if (cluster_locked) + spin_unlock(&cluster_locked->lock); return -ENOSPC; } @@ -1000,7 +1036,7 @@ fail: static noinline_for_stack int write_pinned_extent_entries(struct btrfs_root *root, struct btrfs_block_group_cache *block_group, - struct io_ctl *io_ctl, + struct btrfs_io_ctl *io_ctl, int *entries) { u64 start, extent_start, extent_end, len; @@ -1050,7 +1086,7 @@ write_pinned_extent_entries(struct btrfs_root *root, } static noinline_for_stack int -write_bitmap_entries(struct io_ctl *io_ctl, struct list_head *bitmap_list) +write_bitmap_entries(struct btrfs_io_ctl *io_ctl, struct list_head *bitmap_list) { struct list_head *pos, *n; int ret; @@ -1084,7 +1120,7 @@ static int flush_dirty_cache(struct inode *inode) static void noinline_for_stack cleanup_write_cache_enospc(struct inode *inode, - struct io_ctl *io_ctl, + struct btrfs_io_ctl *io_ctl, struct extent_state **cached_state, struct list_head *bitmap_list) { @@ -1101,6 +1137,70 @@ cleanup_write_cache_enospc(struct inode *inode, GFP_NOFS); } +int btrfs_wait_cache_io(struct btrfs_root *root, + struct btrfs_trans_handle *trans, + struct btrfs_block_group_cache *block_group, + struct btrfs_io_ctl *io_ctl, + struct btrfs_path *path, u64 offset) +{ + int ret; + struct inode *inode = io_ctl->inode; + + if (!inode) + return 0; + + root = root->fs_info->tree_root; + + /* Flush the dirty pages in the cache file. */ + ret = flush_dirty_cache(inode); + if (ret) + goto out; + + /* Update the cache item to tell everyone this cache file is valid. */ + ret = update_cache_item(trans, root, inode, path, offset, + io_ctl->entries, io_ctl->bitmaps); +out: + io_ctl_free(io_ctl); + if (ret) { + invalidate_inode_pages2(inode->i_mapping); + BTRFS_I(inode)->generation = 0; + if (block_group) { +#ifdef DEBUG + btrfs_err(root->fs_info, + "failed to write free space cache for block group %llu", + block_group->key.objectid); +#endif + } + } + btrfs_update_inode(trans, root, inode); + + if (block_group) { + /* the dirty list is protected by the dirty_bgs_lock */ + spin_lock(&trans->transaction->dirty_bgs_lock); + + /* the disk_cache_state is protected by the block group lock */ + spin_lock(&block_group->lock); + + /* + * only mark this as written if we didn't get put back on + * the dirty list while waiting for IO. Otherwise our + * cache state won't be right, and we won't get written again + */ + if (!ret && list_empty(&block_group->dirty_list)) + block_group->disk_cache_state = BTRFS_DC_WRITTEN; + else if (ret) + block_group->disk_cache_state = BTRFS_DC_ERROR; + + spin_unlock(&block_group->lock); + spin_unlock(&trans->transaction->dirty_bgs_lock); + io_ctl->inode = NULL; + iput(inode); + } + + return ret; + +} + /** * __btrfs_write_out_cache - write out cached info to an inode * @root - the root the inode belongs to @@ -1117,20 +1217,22 @@ cleanup_write_cache_enospc(struct inode *inode, static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, struct btrfs_free_space_ctl *ctl, struct btrfs_block_group_cache *block_group, + struct btrfs_io_ctl *io_ctl, struct btrfs_trans_handle *trans, struct btrfs_path *path, u64 offset) { struct extent_state *cached_state = NULL; - struct io_ctl io_ctl; LIST_HEAD(bitmap_list); int entries = 0; int bitmaps = 0; int ret; + int must_iput = 0; if (!i_size_read(inode)) return -1; - ret = io_ctl_init(&io_ctl, inode, root, 1); + WARN_ON(io_ctl->pages); + ret = io_ctl_init(io_ctl, inode, root, 1); if (ret) return -1; @@ -1143,24 +1245,27 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, up_write(&block_group->data_rwsem); BTRFS_I(inode)->generation = 0; ret = 0; + must_iput = 1; goto out; } spin_unlock(&block_group->lock); } /* Lock all pages first so we can lock the extent safely. */ - io_ctl_prepare_pages(&io_ctl, inode, 0); + io_ctl_prepare_pages(io_ctl, inode, 0); lock_extent_bits(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1, 0, &cached_state); - io_ctl_set_generation(&io_ctl, trans->transid); + io_ctl_set_generation(io_ctl, trans->transid); mutex_lock(&ctl->cache_writeout_mutex); /* Write out the extent entries in the free space cache */ - ret = write_cache_extent_entries(&io_ctl, ctl, + spin_lock(&ctl->tree_lock); + ret = write_cache_extent_entries(io_ctl, ctl, block_group, &entries, &bitmaps, &bitmap_list); + spin_unlock(&ctl->tree_lock); if (ret) { mutex_unlock(&ctl->cache_writeout_mutex); goto out_nospc; @@ -1170,8 +1275,11 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, * Some spaces that are freed in the current transaction are pinned, * they will be added into free space cache after the transaction is * committed, we shouldn't lose them. + * + * If this changes while we are working we'll get added back to + * the dirty list and redo it. No locking needed */ - ret = write_pinned_extent_entries(root, block_group, &io_ctl, &entries); + ret = write_pinned_extent_entries(root, block_group, io_ctl, &entries); if (ret) { mutex_unlock(&ctl->cache_writeout_mutex); goto out_nospc; @@ -1182,16 +1290,18 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, * locked while doing it because a concurrent trim can be manipulating * or freeing the bitmap. */ - ret = write_bitmap_entries(&io_ctl, &bitmap_list); + spin_lock(&ctl->tree_lock); + ret = write_bitmap_entries(io_ctl, &bitmap_list); + spin_unlock(&ctl->tree_lock); mutex_unlock(&ctl->cache_writeout_mutex); if (ret) goto out_nospc; /* Zero out the rest of the pages just to make sure */ - io_ctl_zero_remaining_pages(&io_ctl); + io_ctl_zero_remaining_pages(io_ctl); /* Everything is written out, now we dirty the pages in the file. */ - ret = btrfs_dirty_pages(root, inode, io_ctl.pages, io_ctl.num_pages, + ret = btrfs_dirty_pages(root, inode, io_ctl->pages, io_ctl->num_pages, 0, i_size_read(inode), &cached_state); if (ret) goto out_nospc; @@ -1202,30 +1312,39 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, * Release the pages and unlock the extent, we will flush * them out later */ - io_ctl_drop_pages(&io_ctl); + io_ctl_drop_pages(io_ctl); unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1, &cached_state, GFP_NOFS); - /* Flush the dirty pages in the cache file. */ - ret = flush_dirty_cache(inode); + /* + * at this point the pages are under IO and we're happy, + * The caller is responsible for waiting on them and updating the + * the cache and the inode + */ + io_ctl->entries = entries; + io_ctl->bitmaps = bitmaps; + + ret = btrfs_fdatawrite_range(inode, 0, (u64)-1); if (ret) goto out; - /* Update the cache item to tell everyone this cache file is valid. */ - ret = update_cache_item(trans, root, inode, path, offset, - entries, bitmaps); + return 0; + out: - io_ctl_free(&io_ctl); + io_ctl->inode = NULL; + io_ctl_free(io_ctl); if (ret) { invalidate_inode_pages2(inode->i_mapping); BTRFS_I(inode)->generation = 0; } btrfs_update_inode(trans, root, inode); + if (must_iput) + iput(inode); return ret; out_nospc: - cleanup_write_cache_enospc(inode, &io_ctl, &cached_state, &bitmap_list); + cleanup_write_cache_enospc(inode, io_ctl, &cached_state, &bitmap_list); if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA)) up_write(&block_group->data_rwsem); @@ -1241,7 +1360,6 @@ int btrfs_write_out_cache(struct btrfs_root *root, struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct inode *inode; int ret = 0; - enum btrfs_disk_cache_state dcs = BTRFS_DC_WRITTEN; root = root->fs_info->tree_root; @@ -1250,34 +1368,34 @@ int btrfs_write_out_cache(struct btrfs_root *root, spin_unlock(&block_group->lock); return 0; } - - if (block_group->delalloc_bytes) { - block_group->disk_cache_state = BTRFS_DC_WRITTEN; - spin_unlock(&block_group->lock); - return 0; - } spin_unlock(&block_group->lock); inode = lookup_free_space_inode(root, block_group, path); if (IS_ERR(inode)) return 0; - ret = __btrfs_write_out_cache(root, inode, ctl, block_group, trans, + ret = __btrfs_write_out_cache(root, inode, ctl, block_group, + &block_group->io_ctl, trans, path, block_group->key.objectid); if (ret) { - dcs = BTRFS_DC_ERROR; - ret = 0; #ifdef DEBUG btrfs_err(root->fs_info, "failed to write free space cache for block group %llu", block_group->key.objectid); #endif + spin_lock(&block_group->lock); + block_group->disk_cache_state = BTRFS_DC_ERROR; + spin_unlock(&block_group->lock); + + block_group->io_ctl.inode = NULL; + iput(inode); } - spin_lock(&block_group->lock); - block_group->disk_cache_state = dcs; - spin_unlock(&block_group->lock); - iput(inode); + /* + * if ret == 0 the caller is expected to call btrfs_wait_cache_io + * to wait for IO and put the inode + */ + return ret; } @@ -1298,11 +1416,11 @@ static inline u64 offset_to_bitmap(struct btrfs_free_space_ctl *ctl, u64 offset) { u64 bitmap_start; - u64 bytes_per_bitmap; + u32 bytes_per_bitmap; bytes_per_bitmap = BITS_PER_BITMAP * ctl->unit; bitmap_start = offset - ctl->start; - bitmap_start = div64_u64(bitmap_start, bytes_per_bitmap); + bitmap_start = div_u64(bitmap_start, bytes_per_bitmap); bitmap_start *= bytes_per_bitmap; bitmap_start += ctl->start; @@ -1521,10 +1639,10 @@ static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl) u64 bitmap_bytes; u64 extent_bytes; u64 size = block_group->key.offset; - u64 bytes_per_bg = BITS_PER_BITMAP * ctl->unit; - int max_bitmaps = div64_u64(size + bytes_per_bg - 1, bytes_per_bg); + u32 bytes_per_bg = BITS_PER_BITMAP * ctl->unit; + u32 max_bitmaps = div_u64(size + bytes_per_bg - 1, bytes_per_bg); - max_bitmaps = max(max_bitmaps, 1); + max_bitmaps = max_t(u32, max_bitmaps, 1); ASSERT(ctl->total_bitmaps <= max_bitmaps); @@ -1537,7 +1655,7 @@ static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl) max_bytes = MAX_CACHE_BYTES_PER_GIG; else max_bytes = MAX_CACHE_BYTES_PER_GIG * - div64_u64(size, 1024 * 1024 * 1024); + div_u64(size, 1024 * 1024 * 1024); /* * we want to account for 1 more bitmap than what we have so we can make @@ -1552,14 +1670,14 @@ static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl) } /* - * we want the extent entry threshold to always be at most 1/2 the maxw + * we want the extent entry threshold to always be at most 1/2 the max * bytes we can have, or whatever is less than that. */ extent_bytes = max_bytes - bitmap_bytes; - extent_bytes = min_t(u64, extent_bytes, div64_u64(max_bytes, 2)); + extent_bytes = min_t(u64, extent_bytes, max_bytes >> 1); ctl->extents_thresh = - div64_u64(extent_bytes, (sizeof(struct btrfs_free_space))); + div_u64(extent_bytes, sizeof(struct btrfs_free_space)); } static inline void __bitmap_clear_bits(struct btrfs_free_space_ctl *ctl, @@ -1673,7 +1791,7 @@ find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes, */ if (*bytes >= align) { tmp = entry->offset - ctl->start + align - 1; - do_div(tmp, align); + tmp = div64_u64(tmp, align); tmp = tmp * align + ctl->start; align_off = tmp - entry->offset; } else { @@ -2402,11 +2520,8 @@ static void __btrfs_remove_free_space_cache_locked( } else { free_bitmap(ctl, info); } - if (need_resched()) { - spin_unlock(&ctl->tree_lock); - cond_resched(); - spin_lock(&ctl->tree_lock); - } + + cond_resched_lock(&ctl->tree_lock); } } @@ -2431,11 +2546,8 @@ void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group) WARN_ON(cluster->block_group != block_group); __btrfs_return_cluster_to_free_space(block_group, cluster); - if (need_resched()) { - spin_unlock(&ctl->tree_lock); - cond_resched(); - spin_lock(&ctl->tree_lock); - } + + cond_resched_lock(&ctl->tree_lock); } __btrfs_remove_free_space_cache_locked(ctl); spin_unlock(&ctl->tree_lock); @@ -3346,11 +3458,14 @@ int btrfs_write_out_ino_cache(struct btrfs_root *root, { struct btrfs_free_space_ctl *ctl = root->free_ino_ctl; int ret; + struct btrfs_io_ctl io_ctl; if (!btrfs_test_opt(root, INODE_MAP_CACHE)) return 0; - ret = __btrfs_write_out_cache(root, inode, ctl, NULL, trans, path, 0); + ret = __btrfs_write_out_cache(root, inode, ctl, NULL, &io_ctl, + trans, path, 0) || + btrfs_wait_cache_io(root, trans, NULL, &io_ctl, path, 0); if (ret) { btrfs_delalloc_release_metadata(inode, inode->i_size); #ifdef DEBUG diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h index 88b2238a0aed..a16a029ad3b1 100644 --- a/fs/btrfs/free-space-cache.h +++ b/fs/btrfs/free-space-cache.h @@ -48,6 +48,8 @@ struct btrfs_free_space_op { struct btrfs_free_space *info); }; +struct btrfs_io_ctl; + struct inode *lookup_free_space_inode(struct btrfs_root *root, struct btrfs_block_group_cache *block_group, struct btrfs_path *path); @@ -60,14 +62,19 @@ int btrfs_check_trunc_cache_free_space(struct btrfs_root *root, struct btrfs_block_rsv *rsv); int btrfs_truncate_free_space_cache(struct btrfs_root *root, struct btrfs_trans_handle *trans, + struct btrfs_block_group_cache *block_group, struct inode *inode); int load_free_space_cache(struct btrfs_fs_info *fs_info, struct btrfs_block_group_cache *block_group); +int btrfs_wait_cache_io(struct btrfs_root *root, + struct btrfs_trans_handle *trans, + struct btrfs_block_group_cache *block_group, + struct btrfs_io_ctl *io_ctl, + struct btrfs_path *path, u64 offset); int btrfs_write_out_cache(struct btrfs_root *root, struct btrfs_trans_handle *trans, struct btrfs_block_group_cache *block_group, struct btrfs_path *path); - struct inode *lookup_free_ino_inode(struct btrfs_root *root, struct btrfs_path *path); int create_free_ino_inode(struct btrfs_root *root, diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index 74faea3a516e..f6a596d5a637 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -456,7 +456,7 @@ again: } if (i_size_read(inode) > 0) { - ret = btrfs_truncate_free_space_cache(root, trans, inode); + ret = btrfs_truncate_free_space_cache(root, trans, NULL, inode); if (ret) { if (ret != -ENOSPC) btrfs_abort_transaction(trans, root, ret); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d2e732d7af52..56f00a25c003 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -32,7 +32,6 @@ #include <linux/writeback.h> #include <linux/statfs.h> #include <linux/compat.h> -#include <linux/aio.h> #include <linux/bit_spinlock.h> #include <linux/xattr.h> #include <linux/posix_acl.h> @@ -43,6 +42,7 @@ #include <linux/btrfs.h> #include <linux/blkdev.h> #include <linux/posix_acl_xattr.h> +#include <linux/uio.h> #include "ctree.h" #include "disk-io.h" #include "transaction.h" @@ -59,6 +59,7 @@ #include "backref.h" #include "hash.h" #include "props.h" +#include "qgroup.h" struct btrfs_iget_args { struct btrfs_key *location; @@ -470,7 +471,7 @@ again: */ if (inode_need_compress(inode)) { WARN_ON(pages); - pages = kzalloc(sizeof(struct page *) * nr_pages, GFP_NOFS); + pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS); if (!pages) { /* just bail out to the uncompressed code */ goto cont; @@ -752,7 +753,6 @@ retry: } goto out_free; } - /* * here we're doing allocation and writeback of the * compressed pages @@ -3110,6 +3110,8 @@ void btrfs_run_delayed_iputs(struct btrfs_root *root) if (empty) return; + down_read(&fs_info->delayed_iput_sem); + spin_lock(&fs_info->delayed_iput_lock); list_splice_init(&fs_info->delayed_iputs, &list); spin_unlock(&fs_info->delayed_iput_lock); @@ -3120,6 +3122,8 @@ void btrfs_run_delayed_iputs(struct btrfs_root *root) iput(delayed->inode); kfree(delayed); } + + up_read(&root->fs_info->delayed_iput_sem); } /* @@ -4162,6 +4166,21 @@ out: return err; } +static int truncate_space_check(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + u64 bytes_deleted) +{ + int ret; + + bytes_deleted = btrfs_csum_bytes_to_leaves(root, bytes_deleted); + ret = btrfs_block_rsv_add(root, &root->fs_info->trans_block_rsv, + bytes_deleted, BTRFS_RESERVE_NO_FLUSH); + if (!ret) + trans->bytes_reserved += bytes_deleted; + return ret; + +} + /* * this can truncate away extent items, csum items and directory items. * It starts at a high offset and removes keys until it can't find @@ -4197,9 +4216,21 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, int ret; int err = 0; u64 ino = btrfs_ino(inode); + u64 bytes_deleted = 0; + bool be_nice = 0; + bool should_throttle = 0; + bool should_end = 0; BUG_ON(new_size > 0 && min_type != BTRFS_EXTENT_DATA_KEY); + /* + * for non-free space inodes and ref cows, we want to back off from + * time to time + */ + if (!btrfs_is_free_space_inode(inode) && + test_bit(BTRFS_ROOT_REF_COWS, &root->state)) + be_nice = 1; + path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -4229,6 +4260,19 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, key.type = (u8)-1; search_again: + /* + * with a 16K leaf size and 128MB extents, you can actually queue + * up a huge file in a single leaf. Most of the time that + * bytes_deleted is > 0, it will be huge by the time we get here + */ + if (be_nice && bytes_deleted > 32 * 1024 * 1024) { + if (btrfs_should_end_transaction(trans, root)) { + err = -EAGAIN; + goto error; + } + } + + path->leave_spinning = 1; ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret < 0) { @@ -4371,22 +4415,39 @@ delete: } else { break; } + should_throttle = 0; + if (found_extent && (test_bit(BTRFS_ROOT_REF_COWS, &root->state) || root == root->fs_info->tree_root)) { btrfs_set_path_blocking(path); + bytes_deleted += extent_num_bytes; ret = btrfs_free_extent(trans, root, extent_start, extent_num_bytes, 0, btrfs_header_owner(leaf), ino, extent_offset, 0); BUG_ON(ret); + if (btrfs_should_throttle_delayed_refs(trans, root)) + btrfs_async_run_delayed_refs(root, + trans->delayed_ref_updates * 2, 0); + if (be_nice) { + if (truncate_space_check(trans, root, + extent_num_bytes)) { + should_end = 1; + } + if (btrfs_should_throttle_delayed_refs(trans, + root)) { + should_throttle = 1; + } + } } if (found_type == BTRFS_INODE_ITEM_KEY) break; if (path->slots[0] == 0 || - path->slots[0] != pending_del_slot) { + path->slots[0] != pending_del_slot || + should_throttle || should_end) { if (pending_del_nr) { ret = btrfs_del_items(trans, root, path, pending_del_slot, @@ -4399,6 +4460,23 @@ delete: pending_del_nr = 0; } btrfs_release_path(path); + if (should_throttle) { + unsigned long updates = trans->delayed_ref_updates; + if (updates) { + trans->delayed_ref_updates = 0; + ret = btrfs_run_delayed_refs(trans, root, updates * 2); + if (ret && !err) + err = ret; + } + } + /* + * if we failed to refill our space rsv, bail out + * and let the transaction restart + */ + if (should_end) { + err = -EAGAIN; + goto error; + } goto search_again; } else { path->slots[0]--; @@ -4415,7 +4493,18 @@ error: if (last_size != (u64)-1 && root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) btrfs_ordered_update_i_size(inode, last_size, NULL); + btrfs_free_path(path); + + if (be_nice && bytes_deleted > 32 * 1024 * 1024) { + unsigned long updates = trans->delayed_ref_updates; + if (updates) { + trans->delayed_ref_updates = 0; + ret = btrfs_run_delayed_refs(trans, root, updates * 2); + if (ret && !err) + err = ret; + } + } return err; } @@ -4924,6 +5013,7 @@ void btrfs_evict_inode(struct inode *inode) struct btrfs_trans_handle *trans; struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_block_rsv *rsv, *global_rsv; + int steal_from_global = 0; u64 min_size = btrfs_calc_trunc_metadata_size(root, 1); int ret; @@ -4991,9 +5081,20 @@ void btrfs_evict_inode(struct inode *inode) * hard as possible to get this to work. */ if (ret) - ret = btrfs_block_rsv_migrate(global_rsv, rsv, min_size); + steal_from_global++; + else + steal_from_global = 0; + ret = 0; - if (ret) { + /* + * steal_from_global == 0: we reserved stuff, hooray! + * steal_from_global == 1: we didn't reserve stuff, boo! + * steal_from_global == 2: we've committed, still not a lot of + * room but maybe we'll have room in the global reserve this + * time. + * steal_from_global == 3: abandon all hope! + */ + if (steal_from_global > 2) { btrfs_warn(root->fs_info, "Could not get space for a delete, will truncate on mount %d", ret); @@ -5009,10 +5110,40 @@ void btrfs_evict_inode(struct inode *inode) goto no_delete; } + /* + * We can't just steal from the global reserve, we need tomake + * sure there is room to do it, if not we need to commit and try + * again. + */ + if (steal_from_global) { + if (!btrfs_check_space_for_delayed_refs(trans, root)) + ret = btrfs_block_rsv_migrate(global_rsv, rsv, + min_size); + else + ret = -ENOSPC; + } + + /* + * Couldn't steal from the global reserve, we have too much + * pending stuff built up, commit the transaction and try it + * again. + */ + if (ret) { + ret = btrfs_commit_transaction(trans, root); + if (ret) { + btrfs_orphan_del(NULL, inode); + btrfs_free_block_rsv(root, rsv); + goto no_delete; + } + continue; + } else { + steal_from_global = 0; + } + trans->block_rsv = rsv; ret = btrfs_truncate_inode_items(trans, root, inode, 0, 0); - if (ret != -ENOSPC) + if (ret != -ENOSPC && ret != -EAGAIN) break; trans->block_rsv = &root->fs_info->trans_block_rsv; @@ -8081,7 +8212,7 @@ free_ordered: bio_endio(dio_bio, ret); } -static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *iocb, +static ssize_t check_direct_IO(struct btrfs_root *root, struct kiocb *iocb, const struct iov_iter *iter, loff_t offset) { int seg; @@ -8096,7 +8227,7 @@ static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *io goto out; /* If this is a write we don't need to check anymore */ - if (rw & WRITE) + if (iov_iter_rw(iter) == WRITE) return 0; /* * Check to make sure we don't have duplicate iov_base's in this @@ -8114,8 +8245,8 @@ out: return retval; } -static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, - struct iov_iter *iter, loff_t offset) +static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; @@ -8126,7 +8257,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, bool relock = false; ssize_t ret; - if (check_direct_IO(BTRFS_I(inode)->root, rw, iocb, iter, offset)) + if (check_direct_IO(BTRFS_I(inode)->root, iocb, iter, offset)) return 0; atomic_inc(&inode->i_dio_count); @@ -8144,7 +8275,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, filemap_fdatawrite_range(inode->i_mapping, offset, offset + count - 1); - if (rw & WRITE) { + if (iov_iter_rw(iter) == WRITE) { /* * If the write DIO is beyond the EOF, we need update * the isize, but it is protected by i_mutex. So we can @@ -8174,11 +8305,11 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, wakeup = false; } - ret = __blockdev_direct_IO(rw, iocb, inode, - BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev, - iter, offset, btrfs_get_blocks_direct, NULL, - btrfs_submit_direct, flags); - if (rw & WRITE) { + ret = __blockdev_direct_IO(iocb, inode, + BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev, + iter, offset, btrfs_get_blocks_direct, NULL, + btrfs_submit_direct, flags); + if (iov_iter_rw(iter) == WRITE) { current->journal_info = NULL; if (ret < 0 && ret != -EIOCBQUEUED) btrfs_delalloc_release_space(inode, count); @@ -8581,7 +8712,7 @@ static int btrfs_truncate(struct inode *inode) ret = btrfs_truncate_inode_items(trans, root, inode, inode->i_size, BTRFS_EXTENT_DATA_KEY); - if (ret != -ENOSPC) { + if (ret != -ENOSPC && ret != -EAGAIN) { err = ret; break; } @@ -9451,6 +9582,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, btrfs_end_transaction(trans, root); break; } + btrfs_drop_extent_cache(inode, cur_offset, cur_offset + ins.offset -1, 0); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 74609b931ba5..ca5d968f4c37 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -456,6 +456,13 @@ static noinline int create_subvol(struct inode *dir, if (ret) return ret; + /* + * Don't create subvolume whose level is not zero. Or qgroup will be + * screwed up since it assume subvolme qgroup's level to be 0. + */ + if (btrfs_qgroup_level(objectid)) + return -ENOSPC; + btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP); /* * The same as the snapshot creation, please see the comment @@ -1564,7 +1571,7 @@ static noinline int btrfs_ioctl_resize(struct file *file, goto out_free; } - do_div(new_size, root->sectorsize); + new_size = div_u64(new_size, root->sectorsize); new_size *= root->sectorsize; printk_in_rcu(KERN_INFO "BTRFS: new size for %s is %llu\n", @@ -2897,6 +2904,9 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 len, if (src == dst) return -EINVAL; + if (len == 0) + return 0; + btrfs_double_lock(src, loff, dst, dst_loff, len); ret = extent_same_check_offsets(src, loff, len); @@ -3039,7 +3049,7 @@ out: static int check_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 disko) { - struct seq_list tree_mod_seq_elem = {}; + struct seq_list tree_mod_seq_elem = SEQ_LIST_INIT(tree_mod_seq_elem); struct ulist *roots; struct ulist_iterator uiter; struct ulist_node *root_node = NULL; @@ -3202,6 +3212,8 @@ static int btrfs_clone(struct inode *src, struct inode *inode, key.offset = off; while (1) { + u64 next_key_min_offset = key.offset + 1; + /* * note the key will change type as we walk through the * tree. @@ -3282,7 +3294,7 @@ process_slot: } else if (key.offset >= off + len) { break; } - + next_key_min_offset = key.offset + datal; size = btrfs_item_size_nr(leaf, slot); read_extent_buffer(leaf, buf, btrfs_item_ptr_offset(leaf, slot), @@ -3497,7 +3509,7 @@ process_slot: break; } btrfs_release_path(path); - key.offset++; + key.offset = next_key_min_offset; } ret = 0; @@ -3626,6 +3638,11 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, if (off + len == src->i_size) len = ALIGN(src->i_size, bs) - off; + if (len == 0) { + ret = 0; + goto out_unlock; + } + /* verify the end result is block aligned */ if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs) || !IS_ALIGNED(destoff, bs)) @@ -4624,6 +4641,11 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg) sa->src, sa->dst); } + /* update qgroup status and info */ + err = btrfs_run_qgroups(trans, root->fs_info); + if (err < 0) + btrfs_error(root->fs_info, ret, + "failed to update qgroup status and info\n"); err = btrfs_end_transaction(trans, root); if (err && !ret) ret = err; @@ -4669,8 +4691,7 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg) /* FIXME: check if the IDs really exist */ if (sa->create) { - ret = btrfs_create_qgroup(trans, root->fs_info, sa->qgroupid, - NULL); + ret = btrfs_create_qgroup(trans, root->fs_info, sa->qgroupid); } else { ret = btrfs_remove_qgroup(trans, root->fs_info, sa->qgroupid); } diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c index 617553cdb7d3..a2f051347731 100644 --- a/fs/btrfs/lzo.c +++ b/fs/btrfs/lzo.c @@ -434,7 +434,7 @@ out: return ret; } -struct btrfs_compress_op btrfs_lzo_compress = { +const struct btrfs_compress_op btrfs_lzo_compress = { .alloc_workspace = lzo_alloc_workspace, .free_workspace = lzo_free_workspace, .compress_pages = lzo_compress_pages, diff --git a/fs/btrfs/math.h b/fs/btrfs/math.h index b7816cefbd13..1b10a3cd1195 100644 --- a/fs/btrfs/math.h +++ b/fs/btrfs/math.h @@ -28,8 +28,7 @@ static inline u64 div_factor(u64 num, int factor) if (factor == 10) return num; num *= factor; - do_div(num, 10); - return num; + return div_u64(num, 10); } static inline u64 div_factor_fine(u64 num, int factor) @@ -37,8 +36,7 @@ static inline u64 div_factor_fine(u64 num, int factor) if (factor == 100) return num; num *= factor; - do_div(num, 100); - return num; + return div_u64(num, 100); } #endif diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c index 129b1dd28527..dca137b04095 100644 --- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -425,3 +425,5 @@ static const char *prop_compression_extract(struct inode *inode) return NULL; } + + diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 058c79eecbfb..3d6546581bb9 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -644,9 +644,8 @@ out: } static int update_qgroup_limit_item(struct btrfs_trans_handle *trans, - struct btrfs_root *root, u64 qgroupid, - u64 flags, u64 max_rfer, u64 max_excl, - u64 rsv_rfer, u64 rsv_excl) + struct btrfs_root *root, + struct btrfs_qgroup *qgroup) { struct btrfs_path *path; struct btrfs_key key; @@ -657,7 +656,7 @@ static int update_qgroup_limit_item(struct btrfs_trans_handle *trans, key.objectid = 0; key.type = BTRFS_QGROUP_LIMIT_KEY; - key.offset = qgroupid; + key.offset = qgroup->qgroupid; path = btrfs_alloc_path(); if (!path) @@ -673,11 +672,11 @@ static int update_qgroup_limit_item(struct btrfs_trans_handle *trans, l = path->nodes[0]; slot = path->slots[0]; qgroup_limit = btrfs_item_ptr(l, slot, struct btrfs_qgroup_limit_item); - btrfs_set_qgroup_limit_flags(l, qgroup_limit, flags); - btrfs_set_qgroup_limit_max_rfer(l, qgroup_limit, max_rfer); - btrfs_set_qgroup_limit_max_excl(l, qgroup_limit, max_excl); - btrfs_set_qgroup_limit_rsv_rfer(l, qgroup_limit, rsv_rfer); - btrfs_set_qgroup_limit_rsv_excl(l, qgroup_limit, rsv_excl); + btrfs_set_qgroup_limit_flags(l, qgroup_limit, qgroup->lim_flags); + btrfs_set_qgroup_limit_max_rfer(l, qgroup_limit, qgroup->max_rfer); + btrfs_set_qgroup_limit_max_excl(l, qgroup_limit, qgroup->max_excl); + btrfs_set_qgroup_limit_rsv_rfer(l, qgroup_limit, qgroup->rsv_rfer); + btrfs_set_qgroup_limit_rsv_excl(l, qgroup_limit, qgroup->rsv_excl); btrfs_mark_buffer_dirty(l); @@ -967,6 +966,7 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, fs_info->pending_quota_state = 0; quota_root = fs_info->quota_root; fs_info->quota_root = NULL; + fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_ON; spin_unlock(&fs_info->qgroup_lock); btrfs_free_qgroup_config(fs_info); @@ -982,7 +982,7 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, list_del("a_root->dirty_list); btrfs_tree_lock(quota_root->node); - clean_tree_block(trans, tree_root, quota_root->node); + clean_tree_block(trans, tree_root->fs_info, quota_root->node); btrfs_tree_unlock(quota_root->node); btrfs_free_tree_block(trans, quota_root, quota_root->node, 0, 1); @@ -1001,6 +1001,110 @@ static void qgroup_dirty(struct btrfs_fs_info *fs_info, list_add(&qgroup->dirty, &fs_info->dirty_qgroups); } +/* + * The easy accounting, if we are adding/removing the only ref for an extent + * then this qgroup and all of the parent qgroups get their refrence and + * exclusive counts adjusted. + * + * Caller should hold fs_info->qgroup_lock. + */ +static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, + struct ulist *tmp, u64 ref_root, + u64 num_bytes, int sign) +{ + struct btrfs_qgroup *qgroup; + struct btrfs_qgroup_list *glist; + struct ulist_node *unode; + struct ulist_iterator uiter; + int ret = 0; + + qgroup = find_qgroup_rb(fs_info, ref_root); + if (!qgroup) + goto out; + + qgroup->rfer += sign * num_bytes; + qgroup->rfer_cmpr += sign * num_bytes; + + WARN_ON(sign < 0 && qgroup->excl < num_bytes); + qgroup->excl += sign * num_bytes; + qgroup->excl_cmpr += sign * num_bytes; + if (sign > 0) + qgroup->reserved -= num_bytes; + + qgroup_dirty(fs_info, qgroup); + + /* Get all of the parent groups that contain this qgroup */ + list_for_each_entry(glist, &qgroup->groups, next_group) { + ret = ulist_add(tmp, glist->group->qgroupid, + ptr_to_u64(glist->group), GFP_ATOMIC); + if (ret < 0) + goto out; + } + + /* Iterate all of the parents and adjust their reference counts */ + ULIST_ITER_INIT(&uiter); + while ((unode = ulist_next(tmp, &uiter))) { + qgroup = u64_to_ptr(unode->aux); + qgroup->rfer += sign * num_bytes; + qgroup->rfer_cmpr += sign * num_bytes; + WARN_ON(sign < 0 && qgroup->excl < num_bytes); + qgroup->excl += sign * num_bytes; + if (sign > 0) + qgroup->reserved -= num_bytes; + qgroup->excl_cmpr += sign * num_bytes; + qgroup_dirty(fs_info, qgroup); + + /* Add any parents of the parents */ + list_for_each_entry(glist, &qgroup->groups, next_group) { + ret = ulist_add(tmp, glist->group->qgroupid, + ptr_to_u64(glist->group), GFP_ATOMIC); + if (ret < 0) + goto out; + } + } + ret = 0; +out: + return ret; +} + + +/* + * Quick path for updating qgroup with only excl refs. + * + * In that case, just update all parent will be enough. + * Or we needs to do a full rescan. + * Caller should also hold fs_info->qgroup_lock. + * + * Return 0 for quick update, return >0 for need to full rescan + * and mark INCONSISTENT flag. + * Return < 0 for other error. + */ +static int quick_update_accounting(struct btrfs_fs_info *fs_info, + struct ulist *tmp, u64 src, u64 dst, + int sign) +{ + struct btrfs_qgroup *qgroup; + int ret = 1; + int err = 0; + + qgroup = find_qgroup_rb(fs_info, src); + if (!qgroup) + goto out; + if (qgroup->excl == qgroup->rfer) { + ret = 0; + err = __qgroup_excl_accounting(fs_info, tmp, dst, + qgroup->excl, sign); + if (err < 0) { + ret = err; + goto out; + } + } +out: + if (ret) + fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; + return ret; +} + int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 src, u64 dst) { @@ -1008,8 +1112,17 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, struct btrfs_qgroup *parent; struct btrfs_qgroup *member; struct btrfs_qgroup_list *list; + struct ulist *tmp; int ret = 0; + tmp = ulist_alloc(GFP_NOFS); + if (!tmp) + return -ENOMEM; + + /* Check the level of src and dst first */ + if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst)) + return -EINVAL; + mutex_lock(&fs_info->qgroup_ioctl_lock); quota_root = fs_info->quota_root; if (!quota_root) { @@ -1043,23 +1156,33 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, spin_lock(&fs_info->qgroup_lock); ret = add_relation_rb(quota_root->fs_info, src, dst); + if (ret < 0) { + spin_unlock(&fs_info->qgroup_lock); + goto out; + } + ret = quick_update_accounting(fs_info, tmp, src, dst, 1); spin_unlock(&fs_info->qgroup_lock); out: mutex_unlock(&fs_info->qgroup_ioctl_lock); + ulist_free(tmp); return ret; } -int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, +int __del_qgroup_relation(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 src, u64 dst) { struct btrfs_root *quota_root; struct btrfs_qgroup *parent; struct btrfs_qgroup *member; struct btrfs_qgroup_list *list; + struct ulist *tmp; int ret = 0; int err; - mutex_lock(&fs_info->qgroup_ioctl_lock); + tmp = ulist_alloc(GFP_NOFS); + if (!tmp) + return -ENOMEM; + quota_root = fs_info->quota_root; if (!quota_root) { ret = -EINVAL; @@ -1088,14 +1211,27 @@ exist: spin_lock(&fs_info->qgroup_lock); del_relation_rb(fs_info, src, dst); + ret = quick_update_accounting(fs_info, tmp, src, dst, -1); spin_unlock(&fs_info->qgroup_lock); out: + ulist_free(tmp); + return ret; +} + +int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, u64 src, u64 dst) +{ + int ret = 0; + + mutex_lock(&fs_info->qgroup_ioctl_lock); + ret = __del_qgroup_relation(trans, fs_info, src, dst); mutex_unlock(&fs_info->qgroup_ioctl_lock); + return ret; } int btrfs_create_qgroup(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 qgroupid, char *name) + struct btrfs_fs_info *fs_info, u64 qgroupid) { struct btrfs_root *quota_root; struct btrfs_qgroup *qgroup; @@ -1133,6 +1269,7 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, { struct btrfs_root *quota_root; struct btrfs_qgroup *qgroup; + struct btrfs_qgroup_list *list; int ret = 0; mutex_lock(&fs_info->qgroup_ioctl_lock); @@ -1147,15 +1284,24 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, ret = -ENOENT; goto out; } else { - /* check if there are no relations to this qgroup */ - if (!list_empty(&qgroup->groups) || - !list_empty(&qgroup->members)) { + /* check if there are no children of this qgroup */ + if (!list_empty(&qgroup->members)) { ret = -EBUSY; goto out; } } ret = del_qgroup_item(trans, quota_root, qgroupid); + while (!list_empty(&qgroup->groups)) { + list = list_first_entry(&qgroup->groups, + struct btrfs_qgroup_list, next_group); + ret = __del_qgroup_relation(trans, fs_info, + qgroupid, + list->group->qgroupid); + if (ret) + goto out; + } + spin_lock(&fs_info->qgroup_lock); del_qgroup_rb(quota_root->fs_info, qgroupid); spin_unlock(&fs_info->qgroup_lock); @@ -1184,23 +1330,27 @@ int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, ret = -ENOENT; goto out; } - ret = update_qgroup_limit_item(trans, quota_root, qgroupid, - limit->flags, limit->max_rfer, - limit->max_excl, limit->rsv_rfer, - limit->rsv_excl); + + spin_lock(&fs_info->qgroup_lock); + if (limit->flags & BTRFS_QGROUP_LIMIT_MAX_RFER) + qgroup->max_rfer = limit->max_rfer; + if (limit->flags & BTRFS_QGROUP_LIMIT_MAX_EXCL) + qgroup->max_excl = limit->max_excl; + if (limit->flags & BTRFS_QGROUP_LIMIT_RSV_RFER) + qgroup->rsv_rfer = limit->rsv_rfer; + if (limit->flags & BTRFS_QGROUP_LIMIT_RSV_EXCL) + qgroup->rsv_excl = limit->rsv_excl; + qgroup->lim_flags |= limit->flags; + + spin_unlock(&fs_info->qgroup_lock); + + ret = update_qgroup_limit_item(trans, quota_root, qgroup); if (ret) { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; btrfs_info(fs_info, "unable to update quota limit for %llu", qgroupid); } - spin_lock(&fs_info->qgroup_lock); - qgroup->lim_flags = limit->flags; - qgroup->max_rfer = limit->max_rfer; - qgroup->max_excl = limit->max_excl; - qgroup->rsv_rfer = limit->rsv_rfer; - qgroup->rsv_excl = limit->rsv_excl; - spin_unlock(&fs_info->qgroup_lock); out: mutex_unlock(&fs_info->qgroup_ioctl_lock); return ret; @@ -1256,14 +1406,14 @@ static int comp_oper(struct btrfs_qgroup_operation *oper1, return -1; if (oper1->bytenr > oper2->bytenr) return 1; - if (oper1->seq < oper2->seq) - return -1; - if (oper1->seq > oper2->seq) - return 1; if (oper1->ref_root < oper2->ref_root) return -1; if (oper1->ref_root > oper2->ref_root) return 1; + if (oper1->seq < oper2->seq) + return -1; + if (oper1->seq > oper2->seq) + return 1; if (oper1->type < oper2->type) return -1; if (oper1->type > oper2->type) @@ -1372,19 +1522,10 @@ int btrfs_qgroup_record_ref(struct btrfs_trans_handle *trans, return 0; } -/* - * The easy accounting, if we are adding/removing the only ref for an extent - * then this qgroup and all of the parent qgroups get their refrence and - * exclusive counts adjusted. - */ static int qgroup_excl_accounting(struct btrfs_fs_info *fs_info, struct btrfs_qgroup_operation *oper) { - struct btrfs_qgroup *qgroup; struct ulist *tmp; - struct btrfs_qgroup_list *glist; - struct ulist_node *unode; - struct ulist_iterator uiter; int sign = 0; int ret = 0; @@ -1395,9 +1536,7 @@ static int qgroup_excl_accounting(struct btrfs_fs_info *fs_info, spin_lock(&fs_info->qgroup_lock); if (!fs_info->quota_root) goto out; - qgroup = find_qgroup_rb(fs_info, oper->ref_root); - if (!qgroup) - goto out; + switch (oper->type) { case BTRFS_QGROUP_OPER_ADD_EXCL: sign = 1; @@ -1408,43 +1547,8 @@ static int qgroup_excl_accounting(struct btrfs_fs_info *fs_info, default: ASSERT(0); } - qgroup->rfer += sign * oper->num_bytes; - qgroup->rfer_cmpr += sign * oper->num_bytes; - - WARN_ON(sign < 0 && qgroup->excl < oper->num_bytes); - qgroup->excl += sign * oper->num_bytes; - qgroup->excl_cmpr += sign * oper->num_bytes; - - qgroup_dirty(fs_info, qgroup); - - /* Get all of the parent groups that contain this qgroup */ - list_for_each_entry(glist, &qgroup->groups, next_group) { - ret = ulist_add(tmp, glist->group->qgroupid, - ptr_to_u64(glist->group), GFP_ATOMIC); - if (ret < 0) - goto out; - } - - /* Iterate all of the parents and adjust their reference counts */ - ULIST_ITER_INIT(&uiter); - while ((unode = ulist_next(tmp, &uiter))) { - qgroup = u64_to_ptr(unode->aux); - qgroup->rfer += sign * oper->num_bytes; - qgroup->rfer_cmpr += sign * oper->num_bytes; - WARN_ON(sign < 0 && qgroup->excl < oper->num_bytes); - qgroup->excl += sign * oper->num_bytes; - qgroup->excl_cmpr += sign * oper->num_bytes; - qgroup_dirty(fs_info, qgroup); - - /* Add any parents of the parents */ - list_for_each_entry(glist, &qgroup->groups, next_group) { - ret = ulist_add(tmp, glist->group->qgroupid, - ptr_to_u64(glist->group), GFP_ATOMIC); - if (ret < 0) - goto out; - } - } - ret = 0; + ret = __qgroup_excl_accounting(fs_info, tmp, oper->ref_root, + oper->num_bytes, sign); out: spin_unlock(&fs_info->qgroup_lock); ulist_free(tmp); @@ -1845,7 +1949,7 @@ static int qgroup_shared_accounting(struct btrfs_trans_handle *trans, struct ulist *roots = NULL; struct ulist *qgroups, *tmp; struct btrfs_qgroup *qgroup; - struct seq_list elem = {}; + struct seq_list elem = SEQ_LIST_INIT(elem); u64 seq; int old_roots = 0; int new_roots = 0; @@ -1967,7 +2071,7 @@ static int qgroup_subtree_accounting(struct btrfs_trans_handle *trans, int err; struct btrfs_qgroup *qg; u64 root_obj = 0; - struct seq_list elem = {}; + struct seq_list elem = SEQ_LIST_INIT(elem); parents = ulist_alloc(GFP_NOFS); if (!parents) @@ -2156,6 +2260,10 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans, if (ret) fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; + ret = update_qgroup_limit_item(trans, quota_root, qgroup); + if (ret) + fs_info->qgroup_flags |= + BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; spin_lock(&fs_info->qgroup_lock); } if (fs_info->quota_enabled) @@ -2219,6 +2327,11 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, ret = -EINVAL; goto out; } + + if ((srcgroup->qgroupid >> 48) <= (objectid >> 48)) { + ret = -EINVAL; + goto out; + } ++i_qgroups; } } @@ -2230,17 +2343,6 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, if (ret) goto out; - if (inherit && inherit->flags & BTRFS_QGROUP_INHERIT_SET_LIMITS) { - ret = update_qgroup_limit_item(trans, quota_root, objectid, - inherit->lim.flags, - inherit->lim.max_rfer, - inherit->lim.max_excl, - inherit->lim.rsv_rfer, - inherit->lim.rsv_excl); - if (ret) - goto out; - } - if (srcid) { struct btrfs_root *srcroot; struct btrfs_key srckey; @@ -2286,6 +2388,22 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, goto unlock; } + if (inherit && inherit->flags & BTRFS_QGROUP_INHERIT_SET_LIMITS) { + dstgroup->lim_flags = inherit->lim.flags; + dstgroup->max_rfer = inherit->lim.max_rfer; + dstgroup->max_excl = inherit->lim.max_excl; + dstgroup->rsv_rfer = inherit->lim.rsv_rfer; + dstgroup->rsv_excl = inherit->lim.rsv_excl; + + ret = update_qgroup_limit_item(trans, quota_root, dstgroup); + if (ret) { + fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; + btrfs_info(fs_info, "unable to update quota limit for %llu", + dstgroup->qgroupid); + goto unlock; + } + } + if (srcid) { srcgroup = find_qgroup_rb(fs_info, srcid); if (!srcgroup) @@ -2302,6 +2420,14 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, dstgroup->excl_cmpr = level_size; srcgroup->excl = level_size; srcgroup->excl_cmpr = level_size; + + /* inherit the limit info */ + dstgroup->lim_flags = srcgroup->lim_flags; + dstgroup->max_rfer = srcgroup->max_rfer; + dstgroup->max_excl = srcgroup->max_excl; + dstgroup->rsv_rfer = srcgroup->rsv_rfer; + dstgroup->rsv_excl = srcgroup->rsv_excl; + qgroup_dirty(fs_info, dstgroup); qgroup_dirty(fs_info, srcgroup); } @@ -2358,12 +2484,6 @@ out: return ret; } -/* - * reserve some space for a qgroup and all its parents. The reservation takes - * place with start_transaction or dealloc_reserve, similar to ENOSPC - * accounting. If not enough space is available, EDQUOT is returned. - * We assume that the requested space is new for all qgroups. - */ int btrfs_qgroup_reserve(struct btrfs_root *root, u64 num_bytes) { struct btrfs_root *quota_root; @@ -2513,7 +2633,7 @@ void assert_qgroups_uptodate(struct btrfs_trans_handle *trans) /* * returns < 0 on error, 0 when more leafs are to be scanned. - * returns 1 when done, 2 when done and FLAG_INCONSISTENT was cleared. + * returns 1 when done. */ static int qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path, @@ -2522,7 +2642,7 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path, { struct btrfs_key found; struct ulist *roots = NULL; - struct seq_list tree_mod_seq_elem = {}; + struct seq_list tree_mod_seq_elem = SEQ_LIST_INIT(tree_mod_seq_elem); u64 num_bytes; u64 seq; int new_roots; @@ -2618,6 +2738,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) struct ulist *tmp = NULL, *qgroups = NULL; struct extent_buffer *scratch_leaf = NULL; int err = -ENOMEM; + int ret = 0; path = btrfs_alloc_path(); if (!path) @@ -2660,7 +2781,7 @@ out: mutex_lock(&fs_info->qgroup_rescan_lock); fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; - if (err == 2 && + if (err > 0 && fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT) { fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; } else if (err < 0) { @@ -2668,13 +2789,33 @@ out: } mutex_unlock(&fs_info->qgroup_rescan_lock); + /* + * only update status, since the previous part has alreay updated the + * qgroup info. + */ + trans = btrfs_start_transaction(fs_info->quota_root, 1); + if (IS_ERR(trans)) { + err = PTR_ERR(trans); + btrfs_err(fs_info, + "fail to start transaction for status update: %d\n", + err); + goto done; + } + ret = update_qgroup_status_item(trans, fs_info, fs_info->quota_root); + if (ret < 0) { + err = ret; + btrfs_err(fs_info, "fail to update qgroup status: %d\n", err); + } + btrfs_end_transaction(trans, fs_info->quota_root); + if (err >= 0) { btrfs_info(fs_info, "qgroup scan completed%s", - err == 2 ? " (inconsistency flag cleared)" : ""); + err > 0 ? " (inconsistency flag cleared)" : ""); } else { btrfs_err(fs_info, "qgroup scan failed with %d", err); } +done: complete_all(&fs_info->qgroup_rescan_completion); } @@ -2709,7 +2850,6 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid, mutex_unlock(&fs_info->qgroup_rescan_lock); goto err; } - fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_RESCAN; } diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 18cc68ca3090..c5242aa9a4b2 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -70,8 +70,7 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 src, u64 dst); int btrfs_create_qgroup(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 qgroupid, - char *name); + struct btrfs_fs_info *fs_info, u64 qgroupid); int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 qgroupid); int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 5264858ed768..fa72068bd256 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -237,12 +237,8 @@ int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info) } x = cmpxchg(&info->stripe_hash_table, NULL, table); - if (x) { - if (is_vmalloc_addr(x)) - vfree(x); - else - kfree(x); - } + if (x) + kvfree(x); return 0; } @@ -453,10 +449,7 @@ void btrfs_free_stripe_hash_table(struct btrfs_fs_info *info) if (!info->stripe_hash_table) return; btrfs_clear_rbio_cache(info); - if (is_vmalloc_addr(info->stripe_hash_table)) - vfree(info->stripe_hash_table); - else - kfree(info->stripe_hash_table); + kvfree(info->stripe_hash_table); info->stripe_hash_table = NULL; } @@ -1807,8 +1800,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) int err; int i; - pointers = kzalloc(rbio->real_stripes * sizeof(void *), - GFP_NOFS); + pointers = kcalloc(rbio->real_stripes, sizeof(void *), GFP_NOFS); if (!pointers) { err = -ENOMEM; goto cleanup_io; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index d83085381bcc..74b24b01d574 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -3027,7 +3027,7 @@ int prealloc_file_extent_cluster(struct inode *inode, mutex_lock(&inode->i_mutex); ret = btrfs_check_data_free_space(inode, cluster->end + - 1 - cluster->start); + 1 - cluster->start, 0); if (ret) goto out; @@ -3430,7 +3430,9 @@ static int block_use_full_backref(struct reloc_control *rc, } static int delete_block_group_cache(struct btrfs_fs_info *fs_info, - struct inode *inode, u64 ino) + struct btrfs_block_group_cache *block_group, + struct inode *inode, + u64 ino) { struct btrfs_key key; struct btrfs_root *root = fs_info->tree_root; @@ -3463,7 +3465,7 @@ truncate: goto out; } - ret = btrfs_truncate_free_space_cache(root, trans, inode); + ret = btrfs_truncate_free_space_cache(root, trans, block_group, inode); btrfs_end_transaction(trans, root); btrfs_btree_balance_dirty(root); @@ -3509,6 +3511,7 @@ static int find_data_references(struct reloc_control *rc, */ if (ref_root == BTRFS_ROOT_TREE_OBJECTID) { ret = delete_block_group_cache(rc->extent_root->fs_info, + rc->block_group, NULL, ref_objectid); if (ret != -ENOENT) return ret; @@ -4223,7 +4226,7 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start) btrfs_free_path(path); if (!IS_ERR(inode)) - ret = delete_block_group_cache(fs_info, inode, 0); + ret = delete_block_group_cache(fs_info, rc->block_group, inode, 0); else ret = PTR_ERR(inode); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index ec57687c9a4d..ab5811545a98 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -964,9 +964,8 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) * the statistics. */ - sblocks_for_recheck = kzalloc(BTRFS_MAX_MIRRORS * - sizeof(*sblocks_for_recheck), - GFP_NOFS); + sblocks_for_recheck = kcalloc(BTRFS_MAX_MIRRORS, + sizeof(*sblocks_for_recheck), GFP_NOFS); if (!sblocks_for_recheck) { spin_lock(&sctx->stat_lock); sctx->stat.malloc_errors++; @@ -2319,7 +2318,7 @@ static inline void __scrub_mark_bitmap(struct scrub_parity *sparity, unsigned long *bitmap, u64 start, u64 len) { - int offset; + u32 offset; int nsectors; int sectorsize = sparity->sctx->dev_root->sectorsize; @@ -2329,7 +2328,7 @@ static inline void __scrub_mark_bitmap(struct scrub_parity *sparity, } start -= sparity->logic_start; - offset = (int)do_div(start, sparity->stripe_len); + start = div_u64_rem(start, sparity->stripe_len, &offset); offset /= sectorsize; nsectors = (int)len / sectorsize; @@ -2612,8 +2611,8 @@ static int get_raid56_logic_offset(u64 physical, int num, int j = 0; u64 stripe_nr; u64 last_offset; - int stripe_index; - int rot; + u32 stripe_index; + u32 rot; last_offset = (physical - map->stripes[num].physical) * nr_data_stripes(map); @@ -2624,12 +2623,11 @@ static int get_raid56_logic_offset(u64 physical, int num, for (i = 0; i < nr_data_stripes(map); i++) { *offset = last_offset + i * map->stripe_len; - stripe_nr = *offset; - do_div(stripe_nr, map->stripe_len); - do_div(stripe_nr, nr_data_stripes(map)); + stripe_nr = div_u64(*offset, map->stripe_len); + stripe_nr = div_u64(stripe_nr, nr_data_stripes(map)); /* Work out the disk rotation on this stripe-set */ - rot = do_div(stripe_nr, map->num_stripes); + stripe_nr = div_u64_rem(stripe_nr, map->num_stripes, &rot); /* calculate which stripe this data locates */ rot += i; stripe_index = rot % map->num_stripes; @@ -2995,10 +2993,9 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, int extent_mirror_num; int stop_loop = 0; - nstripes = length; physical = map->stripes[num].physical; offset = 0; - do_div(nstripes, map->stripe_len); + nstripes = div_u64(length, map->stripe_len); if (map->type & BTRFS_BLOCK_GROUP_RAID0) { offset = map->stripe_len * num; increment = map->stripe_len * map->num_stripes; @@ -3563,7 +3560,7 @@ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info, int is_dev_replace) { int ret = 0; - int flags = WQ_FREEZABLE | WQ_UNBOUND; + unsigned int flags = WQ_FREEZABLE | WQ_UNBOUND; int max_active = fs_info->thread_pool_size; if (fs_info->scrub_workers_refcnt == 0) { diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index d6033f540cc7..a1216f9b4917 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -3067,48 +3067,6 @@ static struct pending_dir_move *get_pending_dir_moves(struct send_ctx *sctx, return NULL; } -static int path_loop(struct send_ctx *sctx, struct fs_path *name, - u64 ino, u64 gen, u64 *ancestor_ino) -{ - int ret = 0; - u64 parent_inode = 0; - u64 parent_gen = 0; - u64 start_ino = ino; - - *ancestor_ino = 0; - while (ino != BTRFS_FIRST_FREE_OBJECTID) { - fs_path_reset(name); - - if (is_waiting_for_rm(sctx, ino)) - break; - if (is_waiting_for_move(sctx, ino)) { - if (*ancestor_ino == 0) - *ancestor_ino = ino; - ret = get_first_ref(sctx->parent_root, ino, - &parent_inode, &parent_gen, name); - } else { - ret = __get_cur_name_and_parent(sctx, ino, gen, - &parent_inode, - &parent_gen, name); - if (ret > 0) { - ret = 0; - break; - } - } - if (ret < 0) - break; - if (parent_inode == start_ino) { - ret = 1; - if (*ancestor_ino == 0) - *ancestor_ino = ino; - break; - } - ino = parent_inode; - gen = parent_gen; - } - return ret; -} - static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) { struct fs_path *from_path = NULL; @@ -3120,7 +3078,6 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) struct waiting_dir_move *dm = NULL; u64 rmdir_ino = 0; int ret; - u64 ancestor = 0; name = fs_path_alloc(); from_path = fs_path_alloc(); @@ -3152,22 +3109,6 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) goto out; sctx->send_progress = sctx->cur_ino + 1; - ret = path_loop(sctx, name, pm->ino, pm->gen, &ancestor); - if (ret) { - LIST_HEAD(deleted_refs); - ASSERT(ancestor > BTRFS_FIRST_FREE_OBJECTID); - ret = add_pending_dir_move(sctx, pm->ino, pm->gen, ancestor, - &pm->update_refs, &deleted_refs, - pm->is_orphan); - if (ret < 0) - goto out; - if (rmdir_ino) { - dm = get_waiting_dir_move(sctx, pm->ino); - ASSERT(dm); - dm->rmdir_ino = rmdir_ino; - } - goto out; - } fs_path_reset(name); to_path = name; name = NULL; @@ -3610,10 +3551,27 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino); if (ret < 0) goto out; if (ret) { + struct name_cache_entry *nce; + ret = orphanize_inode(sctx, ow_inode, ow_gen, cur->full_path); if (ret < 0) goto out; + /* + * Make sure we clear our orphanized inode's + * name from the name cache. This is because the + * inode ow_inode might be an ancestor of some + * other inode that will be orphanized as well + * later and has an inode number greater than + * sctx->send_progress. We need to prevent + * future name lookups from using the old name + * and get instead the orphan name. + */ + nce = name_cache_search(sctx, ow_inode, ow_gen); + if (nce) { + name_cache_delete(sctx, nce); + kfree(nce); + } } else { ret = send_unlink(sctx, cur->full_path); if (ret < 0) @@ -5852,19 +5810,20 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_) ret = PTR_ERR(clone_root); goto out; } - clone_sources_to_rollback = i + 1; spin_lock(&clone_root->root_item_lock); - clone_root->send_in_progress++; - if (!btrfs_root_readonly(clone_root)) { + if (!btrfs_root_readonly(clone_root) || + btrfs_root_dead(clone_root)) { spin_unlock(&clone_root->root_item_lock); srcu_read_unlock(&fs_info->subvol_srcu, index); ret = -EPERM; goto out; } + clone_root->send_in_progress++; spin_unlock(&clone_root->root_item_lock); srcu_read_unlock(&fs_info->subvol_srcu, index); sctx->clone_roots[i].root = clone_root; + clone_sources_to_rollback = i + 1; } vfree(clone_sources_tmp); clone_sources_tmp = NULL; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 05fef198ff94..f2c9f9db3b19 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -901,6 +901,15 @@ find_root: if (IS_ERR(new_root)) return ERR_CAST(new_root); + if (!(sb->s_flags & MS_RDONLY)) { + int ret; + down_read(&fs_info->cleanup_work_sem); + ret = btrfs_orphan_cleanup(new_root); + up_read(&fs_info->cleanup_work_sem); + if (ret) + return ERR_PTR(ret); + } + dir_id = btrfs_root_dirid(&new_root->root_item); setup_root: location.objectid = dir_id; @@ -1714,7 +1723,7 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes) avail_space = device->total_bytes - device->bytes_used; /* align with stripe_len */ - do_div(avail_space, BTRFS_STRIPE_LEN); + avail_space = div_u64(avail_space, BTRFS_STRIPE_LEN); avail_space *= BTRFS_STRIPE_LEN; /* @@ -1908,6 +1917,17 @@ static struct file_system_type btrfs_fs_type = { }; MODULE_ALIAS_FS("btrfs"); +static int btrfs_control_open(struct inode *inode, struct file *file) +{ + /* + * The control file's private_data is used to hold the + * transaction when it is started and is used to keep + * track of whether a transaction is already in progress. + */ + file->private_data = NULL; + return 0; +} + /* * used by btrfsctl to scan devices when no FS is mounted */ @@ -2009,6 +2029,7 @@ static const struct super_operations btrfs_super_ops = { }; static const struct file_operations btrfs_ctl_fops = { + .open = btrfs_control_open, .unlocked_ioctl = btrfs_control_ioctl, .compat_ioctl = btrfs_control_ioctl, .owner = THIS_MODULE, diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 94edb0a2a026..e8a4c86d274d 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -459,7 +459,7 @@ static inline struct btrfs_fs_info *to_fs_info(struct kobject *kobj) static char btrfs_unknown_feature_names[3][NUM_FEATURE_BITS][13]; static struct btrfs_feature_attr btrfs_feature_attrs[3][NUM_FEATURE_BITS]; -static u64 supported_feature_masks[3] = { +static const u64 supported_feature_masks[3] = { [FEAT_COMPAT] = BTRFS_FEATURE_COMPAT_SUPP, [FEAT_COMPAT_RO] = BTRFS_FEATURE_COMPAT_RO_SUPP, [FEAT_INCOMPAT] = BTRFS_FEATURE_INCOMPAT_SUPP, diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h index f7dd298b3cf6..3a4bbed723fd 100644 --- a/fs/btrfs/sysfs.h +++ b/fs/btrfs/sysfs.h @@ -61,11 +61,23 @@ static struct btrfs_feature_attr btrfs_attr_##_name = { \ BTRFS_FEAT_ATTR(name, FEAT_INCOMPAT, BTRFS_FEATURE_INCOMPAT, feature) /* convert from attribute */ -#define to_btrfs_feature_attr(a) \ - container_of(a, struct btrfs_feature_attr, kobj_attr) -#define attr_to_btrfs_attr(a) container_of(a, struct kobj_attribute, attr) -#define attr_to_btrfs_feature_attr(a) \ - to_btrfs_feature_attr(attr_to_btrfs_attr(a)) +static inline struct btrfs_feature_attr * +to_btrfs_feature_attr(struct kobj_attribute *a) +{ + return container_of(a, struct btrfs_feature_attr, kobj_attr); +} + +static inline struct kobj_attribute *attr_to_btrfs_attr(struct attribute *attr) +{ + return container_of(attr, struct kobj_attribute, attr); +} + +static inline struct btrfs_feature_attr * +attr_to_btrfs_feature_attr(struct attribute *attr) +{ + return to_btrfs_feature_attr(attr_to_btrfs_attr(attr)); +} + char *btrfs_printable_features(enum btrfs_feature_set set, u64 flags); extern const char * const btrfs_feature_set_names[3]; extern struct kobj_type space_info_ktype; diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index 73f299ebdabb..c32a7ba76bca 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -232,7 +232,7 @@ static int test_no_shared_qgroup(struct btrfs_root *root) init_dummy_trans(&trans); test_msg("Qgroup basic add\n"); - ret = btrfs_create_qgroup(NULL, fs_info, 5, NULL); + ret = btrfs_create_qgroup(NULL, fs_info, 5); if (ret) { test_msg("Couldn't create a qgroup %d\n", ret); return ret; @@ -301,7 +301,7 @@ static int test_multiple_refs(struct btrfs_root *root) test_msg("Qgroup multiple refs test\n"); /* We have 5 created already from the previous test */ - ret = btrfs_create_qgroup(NULL, fs_info, 256, NULL); + ret = btrfs_create_qgroup(NULL, fs_info, 256); if (ret) { test_msg("Couldn't create a qgroup %d\n", ret); return ret; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 8be4278e25e8..5628e25250c0 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -35,7 +35,7 @@ #define BTRFS_ROOT_TRANS_TAG 0 -static unsigned int btrfs_blocked_trans_types[TRANS_STATE_MAX] = { +static const unsigned int btrfs_blocked_trans_types[TRANS_STATE_MAX] = { [TRANS_STATE_RUNNING] = 0U, [TRANS_STATE_BLOCKED] = (__TRANS_USERSPACE | __TRANS_START), @@ -64,6 +64,9 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction) if (atomic_dec_and_test(&transaction->use_count)) { BUG_ON(!list_empty(&transaction->list)); WARN_ON(!RB_EMPTY_ROOT(&transaction->delayed_refs.href_root)); + if (transaction->delayed_refs.pending_csums) + printk(KERN_ERR "pending csums is %llu\n", + transaction->delayed_refs.pending_csums); while (!list_empty(&transaction->pending_chunks)) { struct extent_map *em; @@ -93,11 +96,8 @@ static void clear_btree_io_tree(struct extent_io_tree *tree) */ ASSERT(!waitqueue_active(&state->wq)); free_extent_state(state); - if (need_resched()) { - spin_unlock(&tree->lock); - cond_resched(); - spin_lock(&tree->lock); - } + + cond_resched_lock(&tree->lock); } spin_unlock(&tree->lock); } @@ -222,10 +222,12 @@ loop: atomic_set(&cur_trans->use_count, 2); cur_trans->have_free_bgs = 0; cur_trans->start_time = get_seconds(); + cur_trans->dirty_bg_run = 0; cur_trans->delayed_refs.href_root = RB_ROOT; atomic_set(&cur_trans->delayed_refs.num_entries, 0); cur_trans->delayed_refs.num_heads_ready = 0; + cur_trans->delayed_refs.pending_csums = 0; cur_trans->delayed_refs.num_heads = 0; cur_trans->delayed_refs.flushing = 0; cur_trans->delayed_refs.run_delayed_start = 0; @@ -250,6 +252,9 @@ loop: INIT_LIST_HEAD(&cur_trans->switch_commits); INIT_LIST_HEAD(&cur_trans->pending_ordered); INIT_LIST_HEAD(&cur_trans->dirty_bgs); + INIT_LIST_HEAD(&cur_trans->io_bgs); + mutex_init(&cur_trans->cache_write_mutex); + cur_trans->num_dirty_bgs = 0; spin_lock_init(&cur_trans->dirty_bgs_lock); list_add_tail(&cur_trans->list, &fs_info->trans_list); extent_io_tree_init(&cur_trans->dirty_pages, @@ -721,7 +726,7 @@ int btrfs_should_end_transaction(struct btrfs_trans_handle *trans, updates = trans->delayed_ref_updates; trans->delayed_ref_updates = 0; if (updates) { - err = btrfs_run_delayed_refs(trans, root, updates); + err = btrfs_run_delayed_refs(trans, root, updates * 2); if (err) /* Error code will also eval true */ return err; } @@ -1057,6 +1062,7 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans, { struct btrfs_fs_info *fs_info = root->fs_info; struct list_head *dirty_bgs = &trans->transaction->dirty_bgs; + struct list_head *io_bgs = &trans->transaction->io_bgs; struct list_head *next; struct extent_buffer *eb; int ret; @@ -1110,7 +1116,7 @@ again: return ret; } - while (!list_empty(dirty_bgs)) { + while (!list_empty(dirty_bgs) || !list_empty(io_bgs)) { ret = btrfs_write_dirty_block_groups(trans, root); if (ret) return ret; @@ -1810,6 +1816,37 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, return ret; } + if (!cur_trans->dirty_bg_run) { + int run_it = 0; + + /* this mutex is also taken before trying to set + * block groups readonly. We need to make sure + * that nobody has set a block group readonly + * after a extents from that block group have been + * allocated for cache files. btrfs_set_block_group_ro + * will wait for the transaction to commit if it + * finds dirty_bg_run = 1 + * + * The dirty_bg_run flag is also used to make sure only + * one process starts all the block group IO. It wouldn't + * hurt to have more than one go through, but there's no + * real advantage to it either. + */ + mutex_lock(&root->fs_info->ro_block_group_mutex); + if (!cur_trans->dirty_bg_run) { + run_it = 1; + cur_trans->dirty_bg_run = 1; + } + mutex_unlock(&root->fs_info->ro_block_group_mutex); + + if (run_it) + ret = btrfs_start_dirty_block_groups(trans, root); + } + if (ret) { + btrfs_end_transaction(trans, root); + return ret; + } + spin_lock(&root->fs_info->trans_lock); list_splice(&trans->ordered, &cur_trans->pending_ordered); if (cur_trans->state >= TRANS_STATE_COMMIT_START) { @@ -2003,6 +2040,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, assert_qgroups_uptodate(trans); ASSERT(list_empty(&cur_trans->dirty_bgs)); + ASSERT(list_empty(&cur_trans->io_bgs)); update_super_roots(root); btrfs_set_super_log_root(root->fs_info->super_copy, 0); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 937050a2b68e..0b24755596ba 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -64,9 +64,19 @@ struct btrfs_transaction { struct list_head pending_ordered; struct list_head switch_commits; struct list_head dirty_bgs; + struct list_head io_bgs; + u64 num_dirty_bgs; + + /* + * we need to make sure block group deletion doesn't race with + * free space cache writeout. This mutex keeps them from stomping + * on each other + */ + struct mutex cache_write_mutex; spinlock_t dirty_bgs_lock; struct btrfs_delayed_ref_root delayed_refs; int aborted; + int dirty_bg_run; }; #define __TRANS_FREEZABLE (1U << 0) @@ -136,9 +146,11 @@ struct btrfs_pending_snapshot { static inline void btrfs_set_inode_last_trans(struct btrfs_trans_handle *trans, struct inode *inode) { + spin_lock(&BTRFS_I(inode)->lock); BTRFS_I(inode)->last_trans = trans->transaction->transid; BTRFS_I(inode)->last_sub_trans = BTRFS_I(inode)->root->log_transid; BTRFS_I(inode)->last_log_commit = BTRFS_I(inode)->root->last_log_commit; + spin_unlock(&BTRFS_I(inode)->lock); } int btrfs_end_transaction(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index c5b8ba37f88e..a089b5944efc 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -492,11 +492,19 @@ insert: if (btrfs_inode_generation(eb, src_item) == 0) { struct extent_buffer *dst_eb = path->nodes[0]; + const u64 ino_size = btrfs_inode_size(eb, src_item); + /* + * For regular files an ino_size == 0 is used only when + * logging that an inode exists, as part of a directory + * fsync, and the inode wasn't fsynced before. In this + * case don't set the size of the inode in the fs/subvol + * tree, otherwise we would be throwing valid data away. + */ if (S_ISREG(btrfs_inode_mode(eb, src_item)) && - S_ISREG(btrfs_inode_mode(dst_eb, dst_item))) { + S_ISREG(btrfs_inode_mode(dst_eb, dst_item)) && + ino_size != 0) { struct btrfs_map_token token; - u64 ino_size = btrfs_inode_size(eb, src_item); btrfs_init_map_token(&token); btrfs_set_token_inode_size(dst_eb, dst_item, @@ -1951,6 +1959,104 @@ out: return ret; } +static int replay_xattr_deletes(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + struct btrfs_root *log, + struct btrfs_path *path, + const u64 ino) +{ + struct btrfs_key search_key; + struct btrfs_path *log_path; + int i; + int nritems; + int ret; + + log_path = btrfs_alloc_path(); + if (!log_path) + return -ENOMEM; + + search_key.objectid = ino; + search_key.type = BTRFS_XATTR_ITEM_KEY; + search_key.offset = 0; +again: + ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); + if (ret < 0) + goto out; +process_leaf: + nritems = btrfs_header_nritems(path->nodes[0]); + for (i = path->slots[0]; i < nritems; i++) { + struct btrfs_key key; + struct btrfs_dir_item *di; + struct btrfs_dir_item *log_di; + u32 total_size; + u32 cur; + + btrfs_item_key_to_cpu(path->nodes[0], &key, i); + if (key.objectid != ino || key.type != BTRFS_XATTR_ITEM_KEY) { + ret = 0; + goto out; + } + + di = btrfs_item_ptr(path->nodes[0], i, struct btrfs_dir_item); + total_size = btrfs_item_size_nr(path->nodes[0], i); + cur = 0; + while (cur < total_size) { + u16 name_len = btrfs_dir_name_len(path->nodes[0], di); + u16 data_len = btrfs_dir_data_len(path->nodes[0], di); + u32 this_len = sizeof(*di) + name_len + data_len; + char *name; + + name = kmalloc(name_len, GFP_NOFS); + if (!name) { + ret = -ENOMEM; + goto out; + } + read_extent_buffer(path->nodes[0], name, + (unsigned long)(di + 1), name_len); + + log_di = btrfs_lookup_xattr(NULL, log, log_path, ino, + name, name_len, 0); + btrfs_release_path(log_path); + if (!log_di) { + /* Doesn't exist in log tree, so delete it. */ + btrfs_release_path(path); + di = btrfs_lookup_xattr(trans, root, path, ino, + name, name_len, -1); + kfree(name); + if (IS_ERR(di)) { + ret = PTR_ERR(di); + goto out; + } + ASSERT(di); + ret = btrfs_delete_one_dir_name(trans, root, + path, di); + if (ret) + goto out; + btrfs_release_path(path); + search_key = key; + goto again; + } + kfree(name); + if (IS_ERR(log_di)) { + ret = PTR_ERR(log_di); + goto out; + } + cur += this_len; + di = (struct btrfs_dir_item *)((char *)di + this_len); + } + } + ret = btrfs_next_leaf(root, path); + if (ret > 0) + ret = 0; + else if (ret == 0) + goto process_leaf; +out: + btrfs_free_path(log_path); + btrfs_release_path(path); + return ret; +} + + /* * deletion replay happens before we copy any new directory items * out of the log or out of backreferences from inodes. It @@ -2104,6 +2210,10 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, inode_item = btrfs_item_ptr(eb, i, struct btrfs_inode_item); + ret = replay_xattr_deletes(wc->trans, root, log, + path, key.objectid); + if (ret) + break; mode = btrfs_inode_mode(eb, inode_item); if (S_ISDIR(mode)) { ret = replay_dir_deletes(wc->trans, @@ -2230,7 +2340,8 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, if (trans) { btrfs_tree_lock(next); btrfs_set_lock_blocking(next); - clean_tree_block(trans, root, next); + clean_tree_block(trans, root->fs_info, + next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); } @@ -2308,7 +2419,8 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans, if (trans) { btrfs_tree_lock(next); btrfs_set_lock_blocking(next); - clean_tree_block(trans, root, next); + clean_tree_block(trans, root->fs_info, + next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); } @@ -2384,7 +2496,7 @@ static int walk_log_tree(struct btrfs_trans_handle *trans, if (trans) { btrfs_tree_lock(next); btrfs_set_lock_blocking(next); - clean_tree_block(trans, log, next); + clean_tree_block(trans, log->fs_info, next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); } @@ -3020,6 +3132,7 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode, struct btrfs_path *path, struct btrfs_path *dst_path, int key_type, + struct btrfs_log_ctx *ctx, u64 min_offset, u64 *last_offset_ret) { struct btrfs_key min_key; @@ -3104,6 +3217,8 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans, src = path->nodes[0]; nritems = btrfs_header_nritems(src); for (i = path->slots[0]; i < nritems; i++) { + struct btrfs_dir_item *di; + btrfs_item_key_to_cpu(src, &min_key, i); if (min_key.objectid != ino || min_key.type != key_type) @@ -3114,6 +3229,37 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans, err = ret; goto done; } + + /* + * We must make sure that when we log a directory entry, + * the corresponding inode, after log replay, has a + * matching link count. For example: + * + * touch foo + * mkdir mydir + * sync + * ln foo mydir/bar + * xfs_io -c "fsync" mydir + * <crash> + * <mount fs and log replay> + * + * Would result in a fsync log that when replayed, our + * file inode would have a link count of 1, but we get + * two directory entries pointing to the same inode. + * After removing one of the names, it would not be + * possible to remove the other name, which resulted + * always in stale file handle errors, and would not + * be possible to rmdir the parent directory, since + * its i_size could never decrement to the value + * BTRFS_EMPTY_DIR_SIZE, resulting in -ENOTEMPTY errors. + */ + di = btrfs_item_ptr(src, i, struct btrfs_dir_item); + btrfs_dir_item_key_to_cpu(src, di, &tmp); + if (ctx && + (btrfs_dir_transid(src, di) == trans->transid || + btrfs_dir_type(src, di) == BTRFS_FT_DIR) && + tmp.type != BTRFS_ROOT_ITEM_KEY) + ctx->log_new_dentries = true; } path->slots[0] = nritems; @@ -3175,7 +3321,8 @@ done: static noinline int log_directory_changes(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode, struct btrfs_path *path, - struct btrfs_path *dst_path) + struct btrfs_path *dst_path, + struct btrfs_log_ctx *ctx) { u64 min_key; u64 max_key; @@ -3187,7 +3334,7 @@ again: max_key = 0; while (1) { ret = log_dir_items(trans, root, inode, path, - dst_path, key_type, min_key, + dst_path, key_type, ctx, min_key, &max_key); if (ret) return ret; @@ -3963,7 +4110,7 @@ static int logged_inode_size(struct btrfs_root *log, struct inode *inode, if (ret < 0) { return ret; } else if (ret > 0) { - *size_ret = i_size_read(inode); + *size_ret = 0; } else { struct btrfs_inode_item *item; @@ -4070,10 +4217,8 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, if (S_ISDIR(inode->i_mode)) { int max_key_type = BTRFS_DIR_LOG_INDEX_KEY; - if (inode_only == LOG_INODE_EXISTS) { - max_key_type = BTRFS_INODE_EXTREF_KEY; - max_key.type = max_key_type; - } + if (inode_only == LOG_INODE_EXISTS) + max_key_type = BTRFS_XATTR_ITEM_KEY; ret = drop_objectid_items(trans, log, path, ino, max_key_type); } else { if (inode_only == LOG_INODE_EXISTS) { @@ -4098,7 +4243,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags)) { if (inode_only == LOG_INODE_EXISTS) { - max_key.type = BTRFS_INODE_EXTREF_KEY; + max_key.type = BTRFS_XATTR_ITEM_KEY; ret = drop_objectid_items(trans, log, path, ino, max_key.type); } else { @@ -4106,20 +4251,19 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, &BTRFS_I(inode)->runtime_flags); clear_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags); - ret = btrfs_truncate_inode_items(trans, log, - inode, 0, 0); + while(1) { + ret = btrfs_truncate_inode_items(trans, + log, inode, 0, 0); + if (ret != -EAGAIN) + break; + } } - } else if (test_bit(BTRFS_INODE_COPY_EVERYTHING, - &BTRFS_I(inode)->runtime_flags) || + } else if (test_and_clear_bit(BTRFS_INODE_COPY_EVERYTHING, + &BTRFS_I(inode)->runtime_flags) || inode_only == LOG_INODE_EXISTS) { - if (inode_only == LOG_INODE_ALL) { - clear_bit(BTRFS_INODE_COPY_EVERYTHING, - &BTRFS_I(inode)->runtime_flags); + if (inode_only == LOG_INODE_ALL) fast_search = true; - max_key.type = BTRFS_XATTR_ITEM_KEY; - } else { - max_key.type = BTRFS_INODE_EXTREF_KEY; - } + max_key.type = BTRFS_XATTR_ITEM_KEY; ret = drop_objectid_items(trans, log, path, ino, max_key.type); } else { @@ -4277,15 +4421,18 @@ log_extents: } if (inode_only == LOG_INODE_ALL && S_ISDIR(inode->i_mode)) { - ret = log_directory_changes(trans, root, inode, path, dst_path); + ret = log_directory_changes(trans, root, inode, path, dst_path, + ctx); if (ret) { err = ret; goto out_unlock; } } + spin_lock(&BTRFS_I(inode)->lock); BTRFS_I(inode)->logged_trans = trans->transid; BTRFS_I(inode)->last_log_commit = BTRFS_I(inode)->last_sub_trans; + spin_unlock(&BTRFS_I(inode)->lock); out_unlock: if (unlikely(err)) btrfs_put_logged_extents(&logged_list); @@ -4372,6 +4519,181 @@ out: return ret; } +struct btrfs_dir_list { + u64 ino; + struct list_head list; +}; + +/* + * Log the inodes of the new dentries of a directory. See log_dir_items() for + * details about the why it is needed. + * This is a recursive operation - if an existing dentry corresponds to a + * directory, that directory's new entries are logged too (same behaviour as + * ext3/4, xfs, f2fs, reiserfs, nilfs2). Note that when logging the inodes + * the dentries point to we do not lock their i_mutex, otherwise lockdep + * complains about the following circular lock dependency / possible deadlock: + * + * CPU0 CPU1 + * ---- ---- + * lock(&type->i_mutex_dir_key#3/2); + * lock(sb_internal#2); + * lock(&type->i_mutex_dir_key#3/2); + * lock(&sb->s_type->i_mutex_key#14); + * + * Where sb_internal is the lock (a counter that works as a lock) acquired by + * sb_start_intwrite() in btrfs_start_transaction(). + * Not locking i_mutex of the inodes is still safe because: + * + * 1) For regular files we log with a mode of LOG_INODE_EXISTS. It's possible + * that while logging the inode new references (names) are added or removed + * from the inode, leaving the logged inode item with a link count that does + * not match the number of logged inode reference items. This is fine because + * at log replay time we compute the real number of links and correct the + * link count in the inode item (see replay_one_buffer() and + * link_to_fixup_dir()); + * + * 2) For directories we log with a mode of LOG_INODE_ALL. It's possible that + * while logging the inode's items new items with keys BTRFS_DIR_ITEM_KEY and + * BTRFS_DIR_INDEX_KEY are added to fs/subvol tree and the logged inode item + * has a size that doesn't match the sum of the lengths of all the logged + * names. This does not result in a problem because if a dir_item key is + * logged but its matching dir_index key is not logged, at log replay time we + * don't use it to replay the respective name (see replay_one_name()). On the + * other hand if only the dir_index key ends up being logged, the respective + * name is added to the fs/subvol tree with both the dir_item and dir_index + * keys created (see replay_one_name()). + * The directory's inode item with a wrong i_size is not a problem as well, + * since we don't use it at log replay time to set the i_size in the inode + * item of the fs/subvol tree (see overwrite_item()). + */ +static int log_new_dir_dentries(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + struct inode *start_inode, + struct btrfs_log_ctx *ctx) +{ + struct btrfs_root *log = root->log_root; + struct btrfs_path *path; + LIST_HEAD(dir_list); + struct btrfs_dir_list *dir_elem; + int ret = 0; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + dir_elem = kmalloc(sizeof(*dir_elem), GFP_NOFS); + if (!dir_elem) { + btrfs_free_path(path); + return -ENOMEM; + } + dir_elem->ino = btrfs_ino(start_inode); + list_add_tail(&dir_elem->list, &dir_list); + + while (!list_empty(&dir_list)) { + struct extent_buffer *leaf; + struct btrfs_key min_key; + int nritems; + int i; + + dir_elem = list_first_entry(&dir_list, struct btrfs_dir_list, + list); + if (ret) + goto next_dir_inode; + + min_key.objectid = dir_elem->ino; + min_key.type = BTRFS_DIR_ITEM_KEY; + min_key.offset = 0; +again: + btrfs_release_path(path); + ret = btrfs_search_forward(log, &min_key, path, trans->transid); + if (ret < 0) { + goto next_dir_inode; + } else if (ret > 0) { + ret = 0; + goto next_dir_inode; + } + +process_leaf: + leaf = path->nodes[0]; + nritems = btrfs_header_nritems(leaf); + for (i = path->slots[0]; i < nritems; i++) { + struct btrfs_dir_item *di; + struct btrfs_key di_key; + struct inode *di_inode; + struct btrfs_dir_list *new_dir_elem; + int log_mode = LOG_INODE_EXISTS; + int type; + + btrfs_item_key_to_cpu(leaf, &min_key, i); + if (min_key.objectid != dir_elem->ino || + min_key.type != BTRFS_DIR_ITEM_KEY) + goto next_dir_inode; + + di = btrfs_item_ptr(leaf, i, struct btrfs_dir_item); + type = btrfs_dir_type(leaf, di); + if (btrfs_dir_transid(leaf, di) < trans->transid && + type != BTRFS_FT_DIR) + continue; + btrfs_dir_item_key_to_cpu(leaf, di, &di_key); + if (di_key.type == BTRFS_ROOT_ITEM_KEY) + continue; + + di_inode = btrfs_iget(root->fs_info->sb, &di_key, + root, NULL); + if (IS_ERR(di_inode)) { + ret = PTR_ERR(di_inode); + goto next_dir_inode; + } + + if (btrfs_inode_in_log(di_inode, trans->transid)) { + iput(di_inode); + continue; + } + + ctx->log_new_dentries = false; + if (type == BTRFS_FT_DIR) + log_mode = LOG_INODE_ALL; + btrfs_release_path(path); + ret = btrfs_log_inode(trans, root, di_inode, + log_mode, 0, LLONG_MAX, ctx); + iput(di_inode); + if (ret) + goto next_dir_inode; + if (ctx->log_new_dentries) { + new_dir_elem = kmalloc(sizeof(*new_dir_elem), + GFP_NOFS); + if (!new_dir_elem) { + ret = -ENOMEM; + goto next_dir_inode; + } + new_dir_elem->ino = di_key.objectid; + list_add_tail(&new_dir_elem->list, &dir_list); + } + break; + } + if (i == nritems) { + ret = btrfs_next_leaf(log, path); + if (ret < 0) { + goto next_dir_inode; + } else if (ret > 0) { + ret = 0; + goto next_dir_inode; + } + goto process_leaf; + } + if (min_key.offset < (u64)-1) { + min_key.offset++; + goto again; + } +next_dir_inode: + list_del(&dir_elem->list); + kfree(dir_elem); + } + + btrfs_free_path(path); + return ret; +} + /* * helper function around btrfs_log_inode to make sure newly created * parent directories also end up in the log. A minimal inode and backref @@ -4394,6 +4716,8 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, const struct dentry * const first_parent = parent; const bool did_unlink = (BTRFS_I(inode)->last_unlink_trans > last_committed); + bool log_dentries = false; + struct inode *orig_inode = inode; sb = inode->i_sb; @@ -4449,6 +4773,9 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, goto end_trans; } + if (S_ISDIR(inode->i_mode) && ctx && ctx->log_new_dentries) + log_dentries = true; + while (1) { if (!parent || !parent->d_inode || sb != parent->d_inode->i_sb) break; @@ -4485,7 +4812,10 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, dput(old_parent); old_parent = parent; } - ret = 0; + if (log_dentries) + ret = log_new_dir_dentries(trans, root, orig_inode, ctx); + else + ret = 0; end_trans: dput(old_parent); if (ret < 0) { diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h index 154990c26dcb..6916a781ea02 100644 --- a/fs/btrfs/tree-log.h +++ b/fs/btrfs/tree-log.h @@ -29,6 +29,7 @@ struct btrfs_log_ctx { int log_ret; int log_transid; int io_err; + bool log_new_dentries; struct list_head list; }; @@ -37,6 +38,7 @@ static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx) ctx->log_ret = 0; ctx->log_transid = 0; ctx->io_err = 0; + ctx->log_new_dentries = false; INIT_LIST_HEAD(&ctx->list); } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 8222f6f74147..8bcd2a007517 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -366,8 +366,8 @@ loop_lock: btrfsic_submit_bio(cur->bi_rw, cur); num_run++; batch_run++; - if (need_resched()) - cond_resched(); + + cond_resched(); /* * we made progress, there is more work to do and the bdi @@ -400,8 +400,7 @@ loop_lock: * against it before looping */ last_waited = ioc->last_waited; - if (need_resched()) - cond_resched(); + cond_resched(); continue; } spin_lock(&device->io_lock); @@ -609,8 +608,7 @@ error: return ERR_PTR(-ENOMEM); } -void btrfs_close_extra_devices(struct btrfs_fs_info *fs_info, - struct btrfs_fs_devices *fs_devices, int step) +void btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices, int step) { struct btrfs_device *device, *next; struct btrfs_device *latest_dev = NULL; @@ -1136,11 +1134,11 @@ int find_free_dev_extent(struct btrfs_trans_handle *trans, path = btrfs_alloc_path(); if (!path) return -ENOMEM; -again: + max_hole_start = search_start; max_hole_size = 0; - hole_size = 0; +again: if (search_start >= search_end || device->is_tgtdev_for_dev_replace) { ret = -ENOSPC; goto out; @@ -1233,21 +1231,23 @@ next: * allocated dev extents, and when shrinking the device, * search_end may be smaller than search_start. */ - if (search_end > search_start) + if (search_end > search_start) { hole_size = search_end - search_start; - if (hole_size > max_hole_size) { - max_hole_start = search_start; - max_hole_size = hole_size; - } + if (contains_pending_extent(trans, device, &search_start, + hole_size)) { + btrfs_release_path(path); + goto again; + } - if (contains_pending_extent(trans, device, &search_start, hole_size)) { - btrfs_release_path(path); - goto again; + if (hole_size > max_hole_size) { + max_hole_start = search_start; + max_hole_size = hole_size; + } } /* See above. */ - if (hole_size < num_bytes) + if (max_hole_size < num_bytes) ret = -ENOSPC; else ret = 0; @@ -2487,8 +2487,7 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans, } static int btrfs_free_chunk(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - u64 chunk_tree, u64 chunk_objectid, + struct btrfs_root *root, u64 chunk_objectid, u64 chunk_offset) { int ret; @@ -2580,7 +2579,6 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, struct map_lookup *map; u64 dev_extent_len = 0; u64 chunk_objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID; - u64 chunk_tree = root->fs_info->chunk_root->objectid; int i, ret = 0; /* Just in case */ @@ -2634,8 +2632,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, } } } - ret = btrfs_free_chunk(trans, root, chunk_tree, chunk_objectid, - chunk_offset); + ret = btrfs_free_chunk(trans, root, chunk_objectid, chunk_offset); if (ret) { btrfs_abort_transaction(trans, root, ret); goto out; @@ -2664,8 +2661,8 @@ out: } static int btrfs_relocate_chunk(struct btrfs_root *root, - u64 chunk_tree, u64 chunk_objectid, - u64 chunk_offset) + u64 chunk_objectid, + u64 chunk_offset) { struct btrfs_root *extent_root; struct btrfs_trans_handle *trans; @@ -2707,7 +2704,6 @@ static int btrfs_relocate_sys_chunks(struct btrfs_root *root) struct btrfs_chunk *chunk; struct btrfs_key key; struct btrfs_key found_key; - u64 chunk_tree = chunk_root->root_key.objectid; u64 chunk_type; bool retried = false; int failed = 0; @@ -2744,7 +2740,7 @@ again: btrfs_release_path(path); if (chunk_type & BTRFS_BLOCK_GROUP_SYSTEM) { - ret = btrfs_relocate_chunk(chunk_root, chunk_tree, + ret = btrfs_relocate_chunk(chunk_root, found_key.objectid, found_key.offset); if (ret == -ENOSPC) @@ -3022,7 +3018,7 @@ static int chunk_drange_filter(struct extent_buffer *leaf, stripe_offset = btrfs_stripe_offset(leaf, stripe); stripe_length = btrfs_chunk_length(leaf, chunk); - do_div(stripe_length, factor); + stripe_length = div_u64(stripe_length, factor); if (stripe_offset < bargs->pend && stripe_offset + stripe_length > bargs->pstart) @@ -3255,7 +3251,6 @@ again: } ret = btrfs_relocate_chunk(chunk_root, - chunk_root->root_key.objectid, found_key.objectid, found_key.offset); if (ret && ret != -ENOSPC) @@ -3957,7 +3952,6 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size) struct btrfs_dev_extent *dev_extent = NULL; struct btrfs_path *path; u64 length; - u64 chunk_tree; u64 chunk_objectid; u64 chunk_offset; int ret; @@ -4027,13 +4021,11 @@ again: break; } - chunk_tree = btrfs_dev_extent_chunk_tree(l, dev_extent); chunk_objectid = btrfs_dev_extent_chunk_objectid(l, dev_extent); chunk_offset = btrfs_dev_extent_chunk_offset(l, dev_extent); btrfs_release_path(path); - ret = btrfs_relocate_chunk(root, chunk_tree, chunk_objectid, - chunk_offset); + ret = btrfs_relocate_chunk(root, chunk_objectid, chunk_offset); if (ret && ret != -ENOSPC) goto done; if (ret == -ENOSPC) @@ -4131,7 +4123,7 @@ static int btrfs_cmp_device_info(const void *a, const void *b) return 0; } -static struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { +static const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { [BTRFS_RAID_RAID10] = { .sub_stripes = 2, .dev_stripes = 1, @@ -4289,7 +4281,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, max_chunk_size = min(div_factor(fs_devices->total_rw_bytes, 1), max_chunk_size); - devices_info = kzalloc(sizeof(*devices_info) * fs_devices->rw_devices, + devices_info = kcalloc(fs_devices->rw_devices, sizeof(*devices_info), GFP_NOFS); if (!devices_info) return -ENOMEM; @@ -4400,8 +4392,8 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, */ if (stripe_size * data_stripes > max_chunk_size) { u64 mask = (1ULL << 24) - 1; - stripe_size = max_chunk_size; - do_div(stripe_size, data_stripes); + + stripe_size = div_u64(max_chunk_size, data_stripes); /* bump the answer up to a 16MB boundary */ stripe_size = (stripe_size + mask) & ~mask; @@ -4413,10 +4405,10 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, stripe_size = devices_info[ndevs-1].max_avail; } - do_div(stripe_size, dev_stripes); + stripe_size = div_u64(stripe_size, dev_stripes); /* align to BTRFS_STRIPE_LEN */ - do_div(stripe_size, raid_stripe_len); + stripe_size = div_u64(stripe_size, raid_stripe_len); stripe_size *= raid_stripe_len; map = kmalloc(map_lookup_size(num_stripes), GFP_NOFS); @@ -4954,7 +4946,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, u64 stripe_nr_orig; u64 stripe_nr_end; u64 stripe_len; - int stripe_index; + u32 stripe_index; int i; int ret = 0; int num_stripes; @@ -4995,7 +4987,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, * stripe_nr counts the total number of stripes we have to stride * to get to this block */ - do_div(stripe_nr, stripe_len); + stripe_nr = div64_u64(stripe_nr, stripe_len); stripe_offset = stripe_nr * stripe_len; BUG_ON(offset < stripe_offset); @@ -5011,7 +5003,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, /* allow a write of a full stripe, but make sure we don't * allow straddling of stripes */ - do_div(raid56_full_stripe_start, full_stripe_len); + raid56_full_stripe_start = div64_u64(raid56_full_stripe_start, + full_stripe_len); raid56_full_stripe_start *= full_stripe_len; } @@ -5136,7 +5129,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, stripe_index = 0; stripe_nr_orig = stripe_nr; stripe_nr_end = ALIGN(offset + *length, map->stripe_len); - do_div(stripe_nr_end, map->stripe_len); + stripe_nr_end = div_u64(stripe_nr_end, map->stripe_len); stripe_end_offset = stripe_nr_end * map->stripe_len - (offset + *length); @@ -5144,7 +5137,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, if (rw & REQ_DISCARD) num_stripes = min_t(u64, map->num_stripes, stripe_nr_end - stripe_nr_orig); - stripe_index = do_div(stripe_nr, map->num_stripes); + stripe_nr = div_u64_rem(stripe_nr, map->num_stripes, + &stripe_index); if (!(rw & (REQ_WRITE | REQ_DISCARD | REQ_GET_READ_MIRRORS))) mirror_num = 1; } else if (map->type & BTRFS_BLOCK_GROUP_RAID1) { @@ -5170,9 +5164,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, } } else if (map->type & BTRFS_BLOCK_GROUP_RAID10) { - int factor = map->num_stripes / map->sub_stripes; + u32 factor = map->num_stripes / map->sub_stripes; - stripe_index = do_div(stripe_nr, factor); + stripe_nr = div_u64_rem(stripe_nr, factor, &stripe_index); stripe_index *= map->sub_stripes; if (rw & (REQ_WRITE | REQ_GET_READ_MIRRORS)) @@ -5198,8 +5192,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, ((rw & (REQ_WRITE | REQ_GET_READ_MIRRORS)) || mirror_num > 1)) { /* push stripe_nr back to the start of the full stripe */ - stripe_nr = raid56_full_stripe_start; - do_div(stripe_nr, stripe_len * nr_data_stripes(map)); + stripe_nr = div_u64(raid56_full_stripe_start, + stripe_len * nr_data_stripes(map)); /* RAID[56] write or recovery. Return all stripes */ num_stripes = map->num_stripes; @@ -5209,32 +5203,32 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, stripe_index = 0; stripe_offset = 0; } else { - u64 tmp; - /* * Mirror #0 or #1 means the original data block. * Mirror #2 is RAID5 parity block. * Mirror #3 is RAID6 Q block. */ - stripe_index = do_div(stripe_nr, nr_data_stripes(map)); + stripe_nr = div_u64_rem(stripe_nr, + nr_data_stripes(map), &stripe_index); if (mirror_num > 1) stripe_index = nr_data_stripes(map) + mirror_num - 2; /* We distribute the parity blocks across stripes */ - tmp = stripe_nr + stripe_index; - stripe_index = do_div(tmp, map->num_stripes); + div_u64_rem(stripe_nr + stripe_index, map->num_stripes, + &stripe_index); if (!(rw & (REQ_WRITE | REQ_DISCARD | REQ_GET_READ_MIRRORS)) && mirror_num <= 1) mirror_num = 1; } } else { /* - * after this do_div call, stripe_nr is the number of stripes - * on this device we have to walk to find the data, and - * stripe_index is the number of our device in the stripe array + * after this, stripe_nr is the number of stripes on this + * device we have to walk to find the data, and stripe_index is + * the number of our device in the stripe array */ - stripe_index = do_div(stripe_nr, map->num_stripes); + stripe_nr = div_u64_rem(stripe_nr, map->num_stripes, + &stripe_index); mirror_num = stripe_index + 1; } BUG_ON(stripe_index >= map->num_stripes); @@ -5261,7 +5255,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, need_raid_map && ((rw & (REQ_WRITE | REQ_GET_READ_MIRRORS)) || mirror_num > 1)) { u64 tmp; - int i, rot; + unsigned rot; bbio->raid_map = (u64 *)((void *)bbio->stripes + sizeof(struct btrfs_bio_stripe) * @@ -5269,8 +5263,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, sizeof(int) * tgtdev_indexes); /* Work out the disk rotation on this stripe-set */ - tmp = stripe_nr; - rot = do_div(tmp, num_stripes); + div_u64_rem(stripe_nr, num_stripes, &rot); /* Fill in the logical address of each stripe */ tmp = stripe_nr * nr_data_stripes(map); @@ -5285,8 +5278,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, } if (rw & REQ_DISCARD) { - int factor = 0; - int sub_stripes = 0; + u32 factor = 0; + u32 sub_stripes = 0; u64 stripes_per_dev = 0; u32 remaining_stripes = 0; u32 last_stripe = 0; @@ -5437,9 +5430,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, } } if (found) { - u64 length = map->stripe_len; - - if (physical_of_found + length <= + if (physical_of_found + map->stripe_len <= dev_replace->cursor_left) { struct btrfs_bio_stripe *tgtdev_stripe = bbio->stripes + num_stripes; @@ -5535,15 +5526,15 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree, rmap_len = map->stripe_len; if (map->type & BTRFS_BLOCK_GROUP_RAID10) - do_div(length, map->num_stripes / map->sub_stripes); + length = div_u64(length, map->num_stripes / map->sub_stripes); else if (map->type & BTRFS_BLOCK_GROUP_RAID0) - do_div(length, map->num_stripes); + length = div_u64(length, map->num_stripes); else if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) { - do_div(length, nr_data_stripes(map)); + length = div_u64(length, nr_data_stripes(map)); rmap_len = map->stripe_len * nr_data_stripes(map); } - buf = kzalloc(sizeof(u64) * map->num_stripes, GFP_NOFS); + buf = kcalloc(map->num_stripes, sizeof(u64), GFP_NOFS); BUG_ON(!buf); /* -ENOMEM */ for (i = 0; i < map->num_stripes; i++) { @@ -5554,11 +5545,11 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree, continue; stripe_nr = physical - map->stripes[i].physical; - do_div(stripe_nr, map->stripe_len); + stripe_nr = div_u64(stripe_nr, map->stripe_len); if (map->type & BTRFS_BLOCK_GROUP_RAID10) { stripe_nr = stripe_nr * map->num_stripes + i; - do_div(stripe_nr, map->sub_stripes); + stripe_nr = div_u64(stripe_nr, map->sub_stripes); } else if (map->type & BTRFS_BLOCK_GROUP_RAID0) { stripe_nr = stripe_nr * map->num_stripes + i; } /* else if RAID[56], multiply by nr_data_stripes(). @@ -5835,8 +5826,8 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio, u64 length = 0; u64 map_length; int ret; - int dev_nr = 0; - int total_devs = 1; + int dev_nr; + int total_devs; struct btrfs_bio *bbio = NULL; length = bio->bi_iter.bi_size; @@ -5877,11 +5868,10 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio, BUG(); } - while (dev_nr < total_devs) { + for (dev_nr = 0; dev_nr < total_devs; dev_nr++) { dev = bbio->stripes[dev_nr].dev; if (!dev || !dev->bdev || (rw & WRITE && !dev->writeable)) { bbio_error(bbio, first_bio, logical); - dev_nr++; continue; } @@ -5894,7 +5884,6 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio, ret = breakup_stripe_bio(root, bbio, first_bio, dev, dev_nr, rw, async_submit); BUG_ON(ret); - dev_nr++; continue; } @@ -5909,7 +5898,6 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio, submit_stripe_bio(root, bbio, bio, bbio->stripes[dev_nr].physical, dev_nr, rw, async_submit); - dev_nr++; } btrfs_bio_counter_dec(root->fs_info); return 0; diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 83069dec6898..ebc31331a837 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -421,8 +421,7 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder, struct btrfs_fs_devices **fs_devices_ret); int btrfs_close_devices(struct btrfs_fs_devices *fs_devices); -void btrfs_close_extra_devices(struct btrfs_fs_info *fs_info, - struct btrfs_fs_devices *fs_devices, int step); +void btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices, int step); int btrfs_find_device_missing_or_by_path(struct btrfs_root *root, char *device_path, struct btrfs_device **device); diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 883b93623bc5..45ea704be030 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -364,22 +364,42 @@ const struct xattr_handler *btrfs_xattr_handlers[] = { /* * Check if the attribute is in a supported namespace. * - * This applied after the check for the synthetic attributes in the system + * This is applied after the check for the synthetic attributes in the system * namespace. */ -static bool btrfs_is_valid_xattr(const char *name) +static int btrfs_is_valid_xattr(const char *name) { - return !strncmp(name, XATTR_SECURITY_PREFIX, - XATTR_SECURITY_PREFIX_LEN) || - !strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN) || - !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) || - !strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) || - !strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN); + int len = strlen(name); + int prefixlen = 0; + + if (!strncmp(name, XATTR_SECURITY_PREFIX, + XATTR_SECURITY_PREFIX_LEN)) + prefixlen = XATTR_SECURITY_PREFIX_LEN; + else if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) + prefixlen = XATTR_SYSTEM_PREFIX_LEN; + else if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) + prefixlen = XATTR_TRUSTED_PREFIX_LEN; + else if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) + prefixlen = XATTR_USER_PREFIX_LEN; + else if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN)) + prefixlen = XATTR_BTRFS_PREFIX_LEN; + else + return -EOPNOTSUPP; + + /* + * The name cannot consist of just prefix + */ + if (len <= prefixlen) + return -EINVAL; + + return 0; } ssize_t btrfs_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t size) { + int ret; + /* * If this is a request for a synthetic attribute in the system.* * namespace use the generic infrastructure to resolve a handler @@ -388,8 +408,9 @@ ssize_t btrfs_getxattr(struct dentry *dentry, const char *name, if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) return generic_getxattr(dentry, name, buffer, size); - if (!btrfs_is_valid_xattr(name)) - return -EOPNOTSUPP; + ret = btrfs_is_valid_xattr(name); + if (ret) + return ret; return __btrfs_getxattr(dentry->d_inode, name, buffer, size); } @@ -397,6 +418,7 @@ int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct btrfs_root *root = BTRFS_I(dentry->d_inode)->root; + int ret; /* * The permission on security.* and system.* is not checked @@ -413,8 +435,9 @@ int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value, if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) return generic_setxattr(dentry, name, value, size, flags); - if (!btrfs_is_valid_xattr(name)) - return -EOPNOTSUPP; + ret = btrfs_is_valid_xattr(name); + if (ret) + return ret; if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN)) return btrfs_set_prop(dentry->d_inode, name, @@ -430,6 +453,7 @@ int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value, int btrfs_removexattr(struct dentry *dentry, const char *name) { struct btrfs_root *root = BTRFS_I(dentry->d_inode)->root; + int ret; /* * The permission on security.* and system.* is not checked @@ -446,8 +470,9 @@ int btrfs_removexattr(struct dentry *dentry, const char *name) if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) return generic_removexattr(dentry, name); - if (!btrfs_is_valid_xattr(name)) - return -EOPNOTSUPP; + ret = btrfs_is_valid_xattr(name); + if (ret) + return ret; if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN)) return btrfs_set_prop(dentry->d_inode, name, diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index fb22fd8d8fb8..82990b8f872b 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -403,7 +403,7 @@ next: return ret; } -struct btrfs_compress_op btrfs_zlib_compress = { +const struct btrfs_compress_op btrfs_zlib_compress = { .alloc_workspace = zlib_alloc_workspace, .free_workspace = zlib_free_workspace, .compress_pages = zlib_compress_pages, diff --git a/fs/buffer.c b/fs/buffer.c index 20805db2c987..c7a5602d01ee 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3243,8 +3243,8 @@ int try_to_free_buffers(struct page *page) * to synchronise against __set_page_dirty_buffers and prevent the * dirty bit from being lost. */ - if (ret) - cancel_dirty_page(page, PAGE_CACHE_SIZE); + if (ret && TestClearPageDirty(page)) + account_page_cleaned(page, mapping); spin_unlock(&mapping->private_lock); out: if (buffers_to_free) { diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index fd5599d32362..e162bcd105ee 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1146,6 +1146,10 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping, inode, page, (int)pos, (int)len); r = ceph_update_writeable_page(file, pos, len, page); + if (r < 0) + page_cache_release(page); + else + *pagep = page; } while (r == -EAGAIN); return r; @@ -1198,8 +1202,7 @@ static int ceph_write_end(struct file *file, struct address_space *mapping, * intercept O_DIRECT reads and writes early, this function should * never get called. */ -static ssize_t ceph_direct_io(int rw, struct kiocb *iocb, - struct iov_iter *iter, +static ssize_t ceph_direct_io(struct kiocb *iocb, struct iov_iter *iter, loff_t pos) { WARN_ON(1); @@ -1535,19 +1538,27 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page) osd_req_op_extent_osd_data_pages(req, 1, &page, len, 0, false, false); - err = osd_req_op_xattr_init(req, 0, CEPH_OSD_OP_CMPXATTR, - "inline_version", &inline_version, - sizeof(inline_version), - CEPH_OSD_CMPXATTR_OP_GT, - CEPH_OSD_CMPXATTR_MODE_U64); - if (err) - goto out_put; - - err = osd_req_op_xattr_init(req, 2, CEPH_OSD_OP_SETXATTR, - "inline_version", &inline_version, - sizeof(inline_version), 0, 0); - if (err) - goto out_put; + { + __le64 xattr_buf = cpu_to_le64(inline_version); + err = osd_req_op_xattr_init(req, 0, CEPH_OSD_OP_CMPXATTR, + "inline_version", &xattr_buf, + sizeof(xattr_buf), + CEPH_OSD_CMPXATTR_OP_GT, + CEPH_OSD_CMPXATTR_MODE_U64); + if (err) + goto out_put; + } + + { + char xattr_buf[32]; + int xattr_len = snprintf(xattr_buf, sizeof(xattr_buf), + "%llu", inline_version); + err = osd_req_op_xattr_init(req, 2, CEPH_OSD_OP_SETXATTR, + "inline_version", + xattr_buf, xattr_len, 0, 0); + if (err) + goto out_put; + } ceph_osdc_build_request(req, 0, NULL, CEPH_NOSNAP, &inode->i_mtime); err = ceph_osdc_start_request(&fsc->client->osdc, req, false); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 8172775428a0..11631c4c7d14 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -896,6 +896,18 @@ int ceph_is_any_caps(struct inode *inode) return ret; } +static void drop_inode_snap_realm(struct ceph_inode_info *ci) +{ + struct ceph_snap_realm *realm = ci->i_snap_realm; + spin_lock(&realm->inodes_with_caps_lock); + list_del_init(&ci->i_snap_realm_item); + ci->i_snap_realm_counter++; + ci->i_snap_realm = NULL; + spin_unlock(&realm->inodes_with_caps_lock); + ceph_put_snap_realm(ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc, + realm); +} + /* * Remove a cap. Take steps to deal with a racing iterate_session_caps. * @@ -946,15 +958,13 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release) if (removed) ceph_put_cap(mdsc, cap); - if (!__ceph_is_any_caps(ci) && ci->i_snap_realm) { - struct ceph_snap_realm *realm = ci->i_snap_realm; - spin_lock(&realm->inodes_with_caps_lock); - list_del_init(&ci->i_snap_realm_item); - ci->i_snap_realm_counter++; - ci->i_snap_realm = NULL; - spin_unlock(&realm->inodes_with_caps_lock); - ceph_put_snap_realm(mdsc, realm); - } + /* when reconnect denied, we remove session caps forcibly, + * i_wr_ref can be non-zero. If there are ongoing write, + * keep i_snap_realm. + */ + if (!__ceph_is_any_caps(ci) && ci->i_wr_ref == 0 && ci->i_snap_realm) + drop_inode_snap_realm(ci); + if (!__ceph_is_any_real_caps(ci)) __cap_delay_cancel(mdsc, ci); } @@ -1394,6 +1404,13 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask) int was = ci->i_dirty_caps; int dirty = 0; + if (!ci->i_auth_cap) { + pr_warn("__mark_dirty_caps %p %llx mask %s, " + "but no auth cap (session was closed?)\n", + inode, ceph_ino(inode), ceph_cap_string(mask)); + return 0; + } + dout("__mark_dirty_caps %p %s dirty %s -> %s\n", &ci->vfs_inode, ceph_cap_string(mask), ceph_cap_string(was), ceph_cap_string(was | mask)); @@ -1404,7 +1421,6 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask) ci->i_snap_realm->cached_context); dout(" inode %p now dirty snapc %p auth cap %p\n", &ci->vfs_inode, ci->i_head_snapc, ci->i_auth_cap); - WARN_ON(!ci->i_auth_cap); BUG_ON(!list_empty(&ci->i_dirty_item)); spin_lock(&mdsc->cap_dirty_lock); list_add(&ci->i_dirty_item, &mdsc->cap_dirty); @@ -1545,7 +1561,19 @@ retry_locked: if (!mdsc->stopping && inode->i_nlink > 0) { if (want) { retain |= CEPH_CAP_ANY; /* be greedy */ + } else if (S_ISDIR(inode->i_mode) && + (issued & CEPH_CAP_FILE_SHARED) && + __ceph_dir_is_complete(ci)) { + /* + * If a directory is complete, we want to keep + * the exclusive cap. So that MDS does not end up + * revoking the shared cap on every create/unlink + * operation. + */ + want = CEPH_CAP_ANY_SHARED | CEPH_CAP_FILE_EXCL; + retain |= want; } else { + retain |= CEPH_CAP_ANY_SHARED; /* * keep RD only if we didn't have the file open RW, @@ -2309,6 +2337,9 @@ void ceph_put_cap_refs(struct ceph_inode_info *ci, int had) wake = 1; } } + /* see comment in __ceph_remove_cap() */ + if (!__ceph_is_any_caps(ci) && ci->i_snap_realm) + drop_inode_snap_realm(ci); } spin_unlock(&ci->i_ceph_lock); diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 83e9976f7189..e729b79812b4 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -281,6 +281,7 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx) /* can we use the dcache? */ spin_lock(&ci->i_ceph_lock); if ((ctx->pos == 2 || fi->dentry) && + ceph_test_mount_opt(fsc, DCACHE) && !ceph_test_mount_opt(fsc, NOASYNCREADDIR) && ceph_snap(inode) != CEPH_SNAPDIR && __ceph_dir_is_complete_ordered(ci) && @@ -336,16 +337,23 @@ more: ceph_mdsc_put_request(req); return err; } - req->r_inode = inode; - ihold(inode); - req->r_dentry = dget(file->f_path.dentry); /* hints to request -> mds selection code */ req->r_direct_mode = USE_AUTH_MDS; req->r_direct_hash = ceph_frag_value(frag); req->r_direct_is_hash = true; - req->r_path2 = kstrdup(fi->last_name, GFP_NOFS); + if (fi->last_name) { + req->r_path2 = kstrdup(fi->last_name, GFP_NOFS); + if (!req->r_path2) { + ceph_mdsc_put_request(req); + return -ENOMEM; + } + } req->r_readdir_offset = fi->next_offset; req->r_args.readdir.frag = cpu_to_le32(frag); + + req->r_inode = inode; + ihold(inode); + req->r_dentry = dget(file->f_path.dentry); err = ceph_mdsc_do_request(mdsc, NULL, req); if (err < 0) { ceph_mdsc_put_request(req); @@ -629,6 +637,7 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry, fsc->mount_options->snapdir_name, dentry->d_name.len) && !is_root_ceph_dentry(dir, dentry) && + ceph_test_mount_opt(fsc, DCACHE) && __ceph_dir_is_complete(ci) && (__ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1))) { spin_unlock(&ci->i_ceph_lock); @@ -755,10 +764,15 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry, err = PTR_ERR(req); goto out; } - req->r_dentry = dget(dentry); - req->r_num_caps = 2; req->r_path2 = kstrdup(dest, GFP_NOFS); + if (!req->r_path2) { + err = -ENOMEM; + ceph_mdsc_put_request(req); + goto out; + } req->r_locked_dir = dir; + req->r_dentry = dget(dentry); + req->r_num_caps = 2; req->r_dentry_drop = CEPH_CAP_FILE_SHARED; req->r_dentry_unless = CEPH_CAP_FILE_EXCL; err = ceph_mdsc_do_request(mdsc, dir, req); @@ -933,16 +947,20 @@ static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry, struct ceph_fs_client *fsc = ceph_sb_to_client(old_dir->i_sb); struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_mds_request *req; + int op = CEPH_MDS_OP_RENAME; int err; if (ceph_snap(old_dir) != ceph_snap(new_dir)) return -EXDEV; - if (ceph_snap(old_dir) != CEPH_NOSNAP || - ceph_snap(new_dir) != CEPH_NOSNAP) - return -EROFS; + if (ceph_snap(old_dir) != CEPH_NOSNAP) { + if (old_dir == new_dir && ceph_snap(old_dir) == CEPH_SNAPDIR) + op = CEPH_MDS_OP_RENAMESNAP; + else + return -EROFS; + } dout("rename dir %p dentry %p to dir %p dentry %p\n", old_dir, old_dentry, new_dir, new_dentry); - req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_RENAME, USE_AUTH_MDS); + req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS); if (IS_ERR(req)) return PTR_ERR(req); ihold(old_dir); @@ -1240,11 +1258,12 @@ static int ceph_dir_fsync(struct file *file, loff_t start, loff_t end, dout("dir_fsync %p wait on tid %llu (until %llu)\n", inode, req->r_tid, last_tid); if (req->r_timeout) { - ret = wait_for_completion_timeout( - &req->r_safe_completion, req->r_timeout); - if (ret > 0) + unsigned long time_left = wait_for_completion_timeout( + &req->r_safe_completion, + req->r_timeout); + if (time_left > 0) ret = 0; - else if (ret == 0) + else ret = -EIO; /* timed out */ } else { wait_for_completion(&req->r_safe_completion); @@ -1372,6 +1391,7 @@ const struct inode_operations ceph_snapdir_iops = { .getattr = ceph_getattr, .mkdir = ceph_mkdir, .rmdir = ceph_unlink, + .rename = ceph_rename, }; const struct dentry_operations ceph_dentry_ops = { diff --git a/fs/ceph/file.c b/fs/ceph/file.c index d533075a823d..b9b8eb225f66 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -7,7 +7,6 @@ #include <linux/mount.h> #include <linux/namei.h> #include <linux/writeback.h> -#include <linux/aio.h> #include <linux/falloc.h> #include "super.h" @@ -458,7 +457,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *i, if (ret < 0) return ret; - if (file->f_flags & O_DIRECT) { + if (iocb->ki_flags & IOCB_DIRECT) { while (iov_iter_count(i)) { size_t start; ssize_t n; @@ -808,7 +807,7 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *filp = iocb->ki_filp; struct ceph_file_info *fi = filp->private_data; - size_t len = iocb->ki_nbytes; + size_t len = iov_iter_count(to); struct inode *inode = file_inode(filp); struct ceph_inode_info *ci = ceph_inode(inode); struct page *pinned_page = NULL; @@ -829,7 +828,7 @@ again: return ret; if ((got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0 || - (iocb->ki_filp->f_flags & O_DIRECT) || + (iocb->ki_flags & IOCB_DIRECT) || (fi->flags & CEPH_F_SYNC)) { dout("aio_sync_read %p %llx.%llx %llu~%u got cap refs on %s\n", @@ -942,9 +941,9 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_osd_client *osdc = &ceph_sb_to_client(inode->i_sb)->client->osdc; - ssize_t count = iov_iter_count(from), written = 0; + ssize_t count, written = 0; int err, want, got; - loff_t pos = iocb->ki_pos; + loff_t pos; if (ceph_snap(inode) != CEPH_NOSNAP) return -EROFS; @@ -954,14 +953,12 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) /* We can write back this queue in page reclaim */ current->backing_dev_info = inode_to_bdi(inode); - err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); - if (err) - goto out; - - if (count == 0) + err = generic_write_checks(iocb, from); + if (err <= 0) goto out; - iov_iter_truncate(from, count); + pos = iocb->ki_pos; + count = iov_iter_count(from); err = file_remove_suid(file); if (err) goto out; @@ -998,12 +995,12 @@ retry_snap: inode, ceph_vinop(inode), pos, count, ceph_cap_string(got)); if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 || - (file->f_flags & O_DIRECT) || (fi->flags & CEPH_F_SYNC)) { + (iocb->ki_flags & IOCB_DIRECT) || (fi->flags & CEPH_F_SYNC)) { struct iov_iter data; mutex_unlock(&inode->i_mutex); /* we might need to revert back to that point */ data = *from; - if (file->f_flags & O_DIRECT) + if (iocb->ki_flags & IOCB_DIRECT) written = ceph_sync_direct_write(iocb, &data, pos); else written = ceph_sync_write(iocb, &data, pos); @@ -1332,8 +1329,6 @@ const struct file_operations ceph_file_fops = { .open = ceph_open, .release = ceph_release, .llseek = ceph_llseek, - .read = new_sync_read, - .write = new_sync_write, .read_iter = ceph_read_iter, .write_iter = ceph_write_iter, .mmap = ceph_mmap, diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 71c073f38e54..0a2eb32ffe43 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1021,6 +1021,33 @@ static void cleanup_cap_releases(struct ceph_mds_session *session) spin_unlock(&session->s_cap_lock); } +static void cleanup_session_requests(struct ceph_mds_client *mdsc, + struct ceph_mds_session *session) +{ + struct ceph_mds_request *req; + struct rb_node *p; + + dout("cleanup_session_requests mds%d\n", session->s_mds); + mutex_lock(&mdsc->mutex); + while (!list_empty(&session->s_unsafe)) { + req = list_first_entry(&session->s_unsafe, + struct ceph_mds_request, r_unsafe_item); + list_del_init(&req->r_unsafe_item); + pr_info(" dropping unsafe request %llu\n", req->r_tid); + __unregister_request(mdsc, req); + } + /* zero r_attempts, so kick_requests() will re-send requests */ + p = rb_first(&mdsc->request_tree); + while (p) { + req = rb_entry(p, struct ceph_mds_request, r_node); + p = rb_next(p); + if (req->r_session && + req->r_session->s_mds == session->s_mds) + req->r_attempts = 0; + } + mutex_unlock(&mdsc->mutex); +} + /* * Helper to safely iterate over all caps associated with a session, with * special care taken to handle a racing __ceph_remove_cap(). @@ -1098,7 +1125,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap, cap, ci, &ci->vfs_inode); spin_lock(&ci->i_ceph_lock); __ceph_remove_cap(cap, false); - if (!__ceph_is_any_real_caps(ci)) { + if (!ci->i_auth_cap) { struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; @@ -1120,13 +1147,6 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap, mdsc->num_cap_flushing--; drop = 1; } - if (drop && ci->i_wrbuffer_ref) { - pr_info(" dropping dirty data for %p %lld\n", - inode, ceph_ino(inode)); - ci->i_wrbuffer_ref = 0; - ci->i_wrbuffer_ref_head = 0; - drop++; - } spin_unlock(&mdsc->cap_dirty_lock); } spin_unlock(&ci->i_ceph_lock); @@ -1853,7 +1873,7 @@ static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry, */ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, struct ceph_mds_request *req, - int mds) + int mds, bool drop_cap_releases) { struct ceph_msg *msg; struct ceph_mds_request_head *head; @@ -1937,6 +1957,12 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, releases += ceph_encode_inode_release(&p, req->r_old_dentry->d_inode, mds, req->r_old_inode_drop, req->r_old_inode_unless, 0); + + if (drop_cap_releases) { + releases = 0; + p = msg->front.iov_base + req->r_request_release_offset; + } + head->num_releases = cpu_to_le16(releases); /* time stamp */ @@ -1989,7 +2015,7 @@ static void complete_request(struct ceph_mds_client *mdsc, */ static int __prepare_send_request(struct ceph_mds_client *mdsc, struct ceph_mds_request *req, - int mds) + int mds, bool drop_cap_releases) { struct ceph_mds_request_head *rhead; struct ceph_msg *msg; @@ -2048,7 +2074,7 @@ static int __prepare_send_request(struct ceph_mds_client *mdsc, ceph_msg_put(req->r_request); req->r_request = NULL; } - msg = create_request_message(mdsc, req, mds); + msg = create_request_message(mdsc, req, mds, drop_cap_releases); if (IS_ERR(msg)) { req->r_err = PTR_ERR(msg); complete_request(mdsc, req); @@ -2132,7 +2158,7 @@ static int __do_request(struct ceph_mds_client *mdsc, if (req->r_request_started == 0) /* note request start time */ req->r_request_started = jiffies; - err = __prepare_send_request(mdsc, req, mds); + err = __prepare_send_request(mdsc, req, mds, false); if (!err) { ceph_msg_get(req->r_request); ceph_con_send(&session->s_con, req->r_request); @@ -2590,6 +2616,7 @@ static void handle_session(struct ceph_mds_session *session, case CEPH_SESSION_CLOSE: if (session->s_state == CEPH_MDS_SESSION_RECONNECTING) pr_info("mds%d reconnect denied\n", session->s_mds); + cleanup_session_requests(mdsc, session); remove_session_caps(session); wake = 2; /* for good measure */ wake_up_all(&mdsc->session_close_wq); @@ -2658,7 +2685,7 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc, mutex_lock(&mdsc->mutex); list_for_each_entry_safe(req, nreq, &session->s_unsafe, r_unsafe_item) { - err = __prepare_send_request(mdsc, req, session->s_mds); + err = __prepare_send_request(mdsc, req, session->s_mds, true); if (!err) { ceph_msg_get(req->r_request); ceph_con_send(&session->s_con, req->r_request); @@ -2679,7 +2706,8 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc, continue; /* only old requests */ if (req->r_session && req->r_session->s_mds == session->s_mds) { - err = __prepare_send_request(mdsc, req, session->s_mds); + err = __prepare_send_request(mdsc, req, + session->s_mds, true); if (!err) { ceph_msg_get(req->r_request); ceph_con_send(&session->s_con, req->r_request); @@ -2864,7 +2892,8 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, spin_unlock(&session->s_cap_lock); /* trim unused caps to reduce MDS's cache rejoin time */ - shrink_dcache_parent(mdsc->fsc->sb->s_root); + if (mdsc->fsc->sb->s_root) + shrink_dcache_parent(mdsc->fsc->sb->s_root); ceph_con_close(&session->s_con); ceph_con_open(&session->s_con, @@ -3133,7 +3162,7 @@ static void handle_lease(struct ceph_mds_client *mdsc, di->lease_renew_from && di->lease_renew_after == 0) { unsigned long duration = - le32_to_cpu(h->duration_ms) * HZ / 1000; + msecs_to_jiffies(le32_to_cpu(h->duration_ms)); di->lease_seq = seq; dentry->d_time = di->lease_renew_from + duration; diff --git a/fs/ceph/strings.c b/fs/ceph/strings.c index 51cc23e48111..89e6bc321df3 100644 --- a/fs/ceph/strings.c +++ b/fs/ceph/strings.c @@ -75,6 +75,7 @@ const char *ceph_mds_op_name(int op) case CEPH_MDS_OP_LSSNAP: return "lssnap"; case CEPH_MDS_OP_MKSNAP: return "mksnap"; case CEPH_MDS_OP_RMSNAP: return "rmsnap"; + case CEPH_MDS_OP_RENAMESNAP: return "renamesnap"; case CEPH_MDS_OP_SETFILELOCK: return "setfilelock"; case CEPH_MDS_OP_GETFILELOCK: return "getfilelock"; } diff --git a/fs/ceph/super.c b/fs/ceph/super.c index a63997b8bcff..e463ebd69a9c 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -345,6 +345,11 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt, fsopt->rsize = CEPH_RSIZE_DEFAULT; fsopt->rasize = CEPH_RASIZE_DEFAULT; fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL); + if (!fsopt->snapdir_name) { + err = -ENOMEM; + goto out; + } + fsopt->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT; fsopt->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT; fsopt->cap_release_safety = CEPH_CAP_RELEASE_SAFETY_DEFAULT; @@ -406,31 +411,20 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) { struct ceph_fs_client *fsc = ceph_sb_to_client(root->d_sb); struct ceph_mount_options *fsopt = fsc->mount_options; - struct ceph_options *opt = fsc->client->options; - - if (opt->flags & CEPH_OPT_FSID) - seq_printf(m, ",fsid=%pU", &opt->fsid); - if (opt->flags & CEPH_OPT_NOSHARE) - seq_puts(m, ",noshare"); - if (opt->flags & CEPH_OPT_NOCRC) - seq_puts(m, ",nocrc"); - if (opt->flags & CEPH_OPT_NOMSGAUTH) - seq_puts(m, ",nocephx_require_signatures"); - if ((opt->flags & CEPH_OPT_TCP_NODELAY) == 0) - seq_puts(m, ",notcp_nodelay"); - - if (opt->name) - seq_printf(m, ",name=%s", opt->name); - if (opt->key) - seq_puts(m, ",secret=<hidden>"); - - if (opt->mount_timeout != CEPH_MOUNT_TIMEOUT_DEFAULT) - seq_printf(m, ",mount_timeout=%d", opt->mount_timeout); - if (opt->osd_idle_ttl != CEPH_OSD_IDLE_TTL_DEFAULT) - seq_printf(m, ",osd_idle_ttl=%d", opt->osd_idle_ttl); - if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT) - seq_printf(m, ",osdkeepalivetimeout=%d", - opt->osd_keepalive_timeout); + size_t pos; + int ret; + + /* a comma between MNT/MS and client options */ + seq_putc(m, ','); + pos = m->count; + + ret = ceph_print_client_options(m, fsc->client); + if (ret) + return ret; + + /* retract our comma if no client options */ + if (m->count == pos) + m->count--; if (fsopt->flags & CEPH_MOUNT_OPT_DIRSTAT) seq_puts(m, ",dirstat"); @@ -438,14 +432,10 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) seq_puts(m, ",norbytes"); if (fsopt->flags & CEPH_MOUNT_OPT_NOASYNCREADDIR) seq_puts(m, ",noasyncreaddir"); - if (fsopt->flags & CEPH_MOUNT_OPT_DCACHE) - seq_puts(m, ",dcache"); - else + if ((fsopt->flags & CEPH_MOUNT_OPT_DCACHE) == 0) seq_puts(m, ",nodcache"); if (fsopt->flags & CEPH_MOUNT_OPT_FSCACHE) seq_puts(m, ",fsc"); - else - seq_puts(m, ",nofsc"); #ifdef CONFIG_CEPH_FS_POSIX_ACL if (fsopt->sb_flags & MS_POSIXACL) @@ -477,6 +467,7 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) seq_printf(m, ",readdir_max_bytes=%d", fsopt->max_readdir_bytes); if (strcmp(fsopt->snapdir_name, CEPH_SNAPDIRNAME_DEFAULT)) seq_printf(m, ",snapdirname=%s", fsopt->snapdir_name); + return 0; } @@ -730,6 +721,11 @@ static struct dentry *open_root_dentry(struct ceph_fs_client *fsc, if (IS_ERR(req)) return ERR_CAST(req); req->r_path1 = kstrdup(path, GFP_NOFS); + if (!req->r_path1) { + root = ERR_PTR(-ENOMEM); + goto out; + } + req->r_ino1.ino = CEPH_INO_ROOT; req->r_ino1.snap = CEPH_NOSNAP; req->r_started = started; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 04c8124ed30e..fa20e1318939 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -36,7 +36,8 @@ #define CEPH_MOUNT_OPT_DCACHE (1<<9) /* use dcache for readdir etc */ #define CEPH_MOUNT_OPT_FSCACHE (1<<10) /* use fscache */ -#define CEPH_MOUNT_OPT_DEFAULT (CEPH_MOUNT_OPT_RBYTES) +#define CEPH_MOUNT_OPT_DEFAULT (CEPH_MOUNT_OPT_RBYTES | \ + CEPH_MOUNT_OPT_DCACHE) #define ceph_set_mount_opt(fsc, opt) \ (fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt; @@ -881,7 +882,6 @@ extern int ceph_mmap(struct file *file, struct vm_area_struct *vma); /* file.c */ extern const struct file_operations ceph_file_fops; -extern const struct address_space_operations ceph_aops; extern int ceph_open(struct inode *inode, struct file *file); extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry, diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 5a492caf34cb..5c4c9c256931 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -877,16 +877,23 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name, err = PTR_ERR(req); goto out; } - req->r_inode = inode; - ihold(inode); - req->r_inode_drop = CEPH_CAP_XATTR_SHARED; - req->r_num_caps = 1; + req->r_args.setxattr.flags = cpu_to_le32(flags); req->r_path2 = kstrdup(name, GFP_NOFS); + if (!req->r_path2) { + ceph_mdsc_put_request(req); + err = -ENOMEM; + goto out; + } req->r_pagelist = pagelist; pagelist = NULL; + req->r_inode = inode; + ihold(inode); + req->r_num_caps = 1; + req->r_inode_drop = CEPH_CAP_XATTR_SHARED; + dout("xattr.ver (before): %lld\n", ci->i_xattrs.version); err = ceph_mdsc_do_request(mdsc, NULL, req); ceph_mdsc_put_request(req); @@ -1019,12 +1026,14 @@ static int ceph_send_removexattr(struct dentry *dentry, const char *name) USE_AUTH_MDS); if (IS_ERR(req)) return PTR_ERR(req); + req->r_path2 = kstrdup(name, GFP_NOFS); + if (!req->r_path2) + return -ENOMEM; + req->r_inode = inode; ihold(inode); - req->r_inode_drop = CEPH_CAP_XATTR_SHARED; req->r_num_caps = 1; - req->r_path2 = kstrdup(name, GFP_NOFS); - + req->r_inode_drop = CEPH_CAP_XATTR_SHARED; err = ceph_mdsc_do_request(mdsc, NULL, req); ceph_mdsc_put_request(req); return err; diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 4ac7445e6ec7..aa0dc2573374 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -1,6 +1,9 @@ /* * fs/cifs/cifsencrypt.c * + * Encryption and hashing operations relating to NTLM, NTLMv2. See MS-NLMP + * for more detailed information + * * Copyright (C) International Business Machines Corp., 2005,2013 * Author(s): Steve French (sfrench@us.ibm.com) * @@ -515,7 +518,8 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash, __func__); return rc; } - } else if (ses->serverName) { + } else { + /* We use ses->serverName if no domain name available */ len = strlen(ses->serverName); server = kmalloc(2 + (len * 2), GFP_KERNEL); diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index d72fe37f5420..eaab4b2a0595 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -906,8 +906,6 @@ const struct inode_operations cifs_symlink_inode_ops = { }; const struct file_operations cifs_file_ops = { - .read = new_sync_read, - .write = new_sync_write, .read_iter = cifs_loose_read_iter, .write_iter = cifs_file_write_iter, .open = cifs_open, @@ -926,8 +924,6 @@ const struct file_operations cifs_file_ops = { }; const struct file_operations cifs_file_strict_ops = { - .read = new_sync_read, - .write = new_sync_write, .read_iter = cifs_strict_readv, .write_iter = cifs_strict_writev, .open = cifs_open, @@ -947,8 +943,6 @@ const struct file_operations cifs_file_strict_ops = { const struct file_operations cifs_file_direct_ops = { /* BB reevaluate whether they can be done with directio, no cache */ - .read = new_sync_read, - .write = new_sync_write, .read_iter = cifs_user_readv, .write_iter = cifs_user_writev, .open = cifs_open, @@ -967,8 +961,6 @@ const struct file_operations cifs_file_direct_ops = { }; const struct file_operations cifs_file_nobrl_ops = { - .read = new_sync_read, - .write = new_sync_write, .read_iter = cifs_loose_read_iter, .write_iter = cifs_file_write_iter, .open = cifs_open, @@ -986,8 +978,6 @@ const struct file_operations cifs_file_nobrl_ops = { }; const struct file_operations cifs_file_strict_nobrl_ops = { - .read = new_sync_read, - .write = new_sync_write, .read_iter = cifs_strict_readv, .write_iter = cifs_strict_writev, .open = cifs_open, @@ -1006,8 +996,6 @@ const struct file_operations cifs_file_strict_nobrl_ops = { const struct file_operations cifs_file_direct_nobrl_ops = { /* BB reevaluate whether they can be done with directio, no cache */ - .read = new_sync_read, - .write = new_sync_write, .read_iter = cifs_user_readv, .write_iter = cifs_user_writev, .open = cifs_open, diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index d3aa999ab785..f3bfe08e177b 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -773,8 +773,7 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) length = atomic_dec_return(&tcpSesAllocCount); if (length > 0) - mempool_resize(cifs_req_poolp, length + cifs_min_rcv, - GFP_KERNEL); + mempool_resize(cifs_req_poolp, length + cifs_min_rcv); } static int @@ -848,8 +847,7 @@ cifs_demultiplex_thread(void *p) length = atomic_inc_return(&tcpSesAllocCount); if (length > 1) - mempool_resize(cifs_req_poolp, length + cifs_min_rcv, - GFP_KERNEL); + mempool_resize(cifs_req_poolp, length + cifs_min_rcv); set_freezable(); while (server->tcpStatus != CifsExiting) { @@ -1599,6 +1597,8 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, pr_warn("CIFS: username too long\n"); goto cifs_parse_mount_err; } + + kfree(vol->username); vol->username = kstrdup(string, GFP_KERNEL); if (!vol->username) goto cifs_parse_mount_err; @@ -1700,6 +1700,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, goto cifs_parse_mount_err; } + kfree(vol->domainname); vol->domainname = kstrdup(string, GFP_KERNEL); if (!vol->domainname) { pr_warn("CIFS: no memory for domainname\n"); @@ -1731,6 +1732,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, } if (strncasecmp(string, "default", 7) != 0) { + kfree(vol->iocharset); vol->iocharset = kstrdup(string, GFP_KERNEL); if (!vol->iocharset) { @@ -2913,8 +2915,7 @@ ip_rfc1001_connect(struct TCP_Server_Info *server) * calling name ends in null (byte 16) from old smb * convention. */ - if (server->workstation_RFC1001_name && - server->workstation_RFC1001_name[0] != 0) + if (server->workstation_RFC1001_name[0] != 0) rfc1002mangle(ses_init_buf->trailer. session_req.calling_name, server->workstation_RFC1001_name, @@ -3692,6 +3693,12 @@ CIFSTCon(const unsigned int xid, struct cifs_ses *ses, #endif /* CIFS_WEAK_PW_HASH */ rc = SMBNTencrypt(tcon->password, ses->server->cryptkey, bcc_ptr, nls_codepage); + if (rc) { + cifs_dbg(FYI, "%s Can't generate NTLM rsp. Error: %d\n", + __func__, rc); + cifs_buf_release(smb_buffer); + return rc; + } bcc_ptr += CIFS_AUTH_RESP_SIZE; if (ses->capabilities & CAP_UNICODE) { diff --git a/fs/cifs/file.c b/fs/cifs/file.c index a94b3e673182..ca2bc5406306 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1823,6 +1823,7 @@ refind_writable: cifsFileInfo_put(inv_file); spin_lock(&cifs_file_list_lock); ++refind; + inv_file = NULL; goto refind_writable; } } @@ -2559,10 +2560,9 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, return rc; } -static ssize_t -cifs_iovec_write(struct file *file, struct iov_iter *from, loff_t *poffset) +ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from) { - size_t len; + struct file *file = iocb->ki_filp; ssize_t total_written = 0; struct cifsFileInfo *open_file; struct cifs_tcon *tcon; @@ -2572,15 +2572,15 @@ cifs_iovec_write(struct file *file, struct iov_iter *from, loff_t *poffset) struct iov_iter saved_from; int rc; - len = iov_iter_count(from); - rc = generic_write_checks(file, poffset, &len, 0); - if (rc) - return rc; - - if (!len) - return 0; + /* + * BB - optimize the way when signing is disabled. We can drop this + * extra memory-to-memory copying and use iovec buffers for constructing + * write request. + */ - iov_iter_truncate(from, len); + rc = generic_write_checks(iocb, from); + if (rc <= 0) + return rc; INIT_LIST_HEAD(&wdata_list); cifs_sb = CIFS_FILE_SB(file); @@ -2592,8 +2592,8 @@ cifs_iovec_write(struct file *file, struct iov_iter *from, loff_t *poffset) memcpy(&saved_from, from, sizeof(struct iov_iter)); - rc = cifs_write_from_iter(*poffset, len, from, open_file, cifs_sb, - &wdata_list); + rc = cifs_write_from_iter(iocb->ki_pos, iov_iter_count(from), from, + open_file, cifs_sb, &wdata_list); /* * If at least one write was successfully sent, then discard any rc @@ -2632,7 +2632,7 @@ restart_loop: memcpy(&tmp_from, &saved_from, sizeof(struct iov_iter)); iov_iter_advance(&tmp_from, - wdata->offset - *poffset); + wdata->offset - iocb->ki_pos); rc = cifs_write_from_iter(wdata->offset, wdata->bytes, &tmp_from, @@ -2649,34 +2649,13 @@ restart_loop: kref_put(&wdata->refcount, cifs_uncached_writedata_release); } - if (total_written > 0) - *poffset += total_written; + if (unlikely(!total_written)) + return rc; + iocb->ki_pos += total_written; + set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(file_inode(file))->flags); cifs_stats_bytes_written(tcon, total_written); - return total_written ? total_written : (ssize_t)rc; -} - -ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from) -{ - ssize_t written; - struct inode *inode; - loff_t pos = iocb->ki_pos; - - inode = file_inode(iocb->ki_filp); - - /* - * BB - optimize the way when signing is disabled. We can drop this - * extra memory-to-memory copying and use iovec buffers for constructing - * write request. - */ - - written = cifs_iovec_write(iocb->ki_filp, from, &pos); - if (written > 0) { - set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(inode)->flags); - iocb->ki_pos = pos; - } - - return written; + return total_written; } static ssize_t @@ -2687,8 +2666,7 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = file->f_mapping->host; struct cifsInodeInfo *cinode = CIFS_I(inode); struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server; - ssize_t rc = -EACCES; - loff_t lock_pos = iocb->ki_pos; + ssize_t rc; /* * We need to hold the sem to be sure nobody modifies lock list @@ -2696,23 +2674,24 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from) */ down_read(&cinode->lock_sem); mutex_lock(&inode->i_mutex); - if (file->f_flags & O_APPEND) - lock_pos = i_size_read(inode); - if (!cifs_find_lock_conflict(cfile, lock_pos, iov_iter_count(from), + + rc = generic_write_checks(iocb, from); + if (rc <= 0) + goto out; + + if (!cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(from), server->vals->exclusive_lock_type, NULL, - CIFS_WRITE_OP)) { + CIFS_WRITE_OP)) rc = __generic_file_write_iter(iocb, from); - mutex_unlock(&inode->i_mutex); - - if (rc > 0) { - ssize_t err; + else + rc = -EACCES; +out: + mutex_unlock(&inode->i_mutex); - err = generic_write_sync(file, iocb->ki_pos - rc, rc); - if (err < 0) - rc = err; - } - } else { - mutex_unlock(&inode->i_mutex); + if (rc > 0) { + ssize_t err = generic_write_sync(file, iocb->ki_pos - rc, rc); + if (err < 0) + rc = err; } up_read(&cinode->lock_sem); return rc; @@ -3876,8 +3855,7 @@ void cifs_oplock_break(struct work_struct *work) * Direct IO is not yet supported in the cached mode. */ static ssize_t -cifs_direct_io(int rw, struct kiocb *iocb, struct iov_iter *iter, - loff_t pos) +cifs_direct_io(struct kiocb *iocb, struct iov_iter *iter, loff_t pos) { /* * FIXME diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 2d4f37235ed0..3e126d7bb2ea 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -771,6 +771,8 @@ cifs_get_inode_info(struct inode **inode, const char *full_path, cifs_buf_release(srchinf->ntwrk_buf_start); } kfree(srchinf); + if (rc) + goto cgii_exit; } else goto cgii_exit; diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 689f035915cf..22dfdf17d065 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -322,7 +322,7 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr) /* return pointer to beginning of data area, ie offset from SMB start */ if ((*off != 0) && (*len != 0)) - return hdr->ProtocolId + *off; + return (char *)(&hdr->ProtocolId[0]) + *off; else return NULL; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 96b5d40a2ece..eab05e1aa587 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -684,7 +684,8 @@ smb2_clone_range(const unsigned int xid, /* No need to change MaxChunks since already set to 1 */ chunk_sizes_updated = true; - } + } else + goto cchunk_out; } cchunk_out: diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 3417340bf89e..65cd7a84c8bc 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1218,7 +1218,7 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, struct smb2_ioctl_req *req; struct smb2_ioctl_rsp *rsp; struct TCP_Server_Info *server; - struct cifs_ses *ses = tcon->ses; + struct cifs_ses *ses; struct kvec iov[2]; int resp_buftype; int num_iovecs; @@ -1233,6 +1233,11 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, if (plen) *plen = 0; + if (tcon) + ses = tcon->ses; + else + return -EIO; + if (ses && (ses->server)) server = ses->server; else @@ -1296,14 +1301,12 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, rsp = (struct smb2_ioctl_rsp *)iov[0].iov_base; if ((rc != 0) && (rc != -EINVAL)) { - if (tcon) - cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE); + cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE); goto ioctl_exit; } else if (rc == -EINVAL) { if ((opcode != FSCTL_SRV_COPYCHUNK_WRITE) && (opcode != FSCTL_SRV_COPYCHUNK)) { - if (tcon) - cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE); + cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE); goto ioctl_exit; } } @@ -1629,7 +1632,7 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, rc = SendReceive2(xid, ses, iov, 1, &resp_buftype, 0); - if ((rc != 0) && tcon) + if (rc != 0) cifs_stats_fail_inc(tcon, SMB2_FLUSH_HE); free_rsp_buf(resp_buftype, iov[0].iov_base); @@ -2114,7 +2117,7 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, struct kvec iov[2]; int rc = 0; int len; - int resp_buftype; + int resp_buftype = CIFS_NO_BUFFER; unsigned char *bufptr; struct TCP_Server_Info *server; struct cifs_ses *ses = tcon->ses; diff --git a/fs/coda/file.c b/fs/coda/file.c index d244d743a232..1da3805f3ddc 100644 --- a/fs/coda/file.c +++ b/fs/coda/file.c @@ -27,19 +27,14 @@ #include "coda_int.h" static ssize_t -coda_file_read(struct file *coda_file, char __user *buf, size_t count, loff_t *ppos) +coda_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { - struct coda_file_info *cfi; - struct file *host_file; + struct file *coda_file = iocb->ki_filp; + struct coda_file_info *cfi = CODA_FTOC(coda_file); - cfi = CODA_FTOC(coda_file); BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC); - host_file = cfi->cfi_container; - if (!host_file->f_op->read) - return -EINVAL; - - return host_file->f_op->read(host_file, buf, count, ppos); + return vfs_iter_read(cfi->cfi_container, to, &iocb->ki_pos); } static ssize_t @@ -64,32 +59,25 @@ coda_file_splice_read(struct file *coda_file, loff_t *ppos, } static ssize_t -coda_file_write(struct file *coda_file, const char __user *buf, size_t count, loff_t *ppos) +coda_file_write_iter(struct kiocb *iocb, struct iov_iter *to) { - struct inode *host_inode, *coda_inode = file_inode(coda_file); - struct coda_file_info *cfi; + struct file *coda_file = iocb->ki_filp; + struct inode *coda_inode = file_inode(coda_file); + struct coda_file_info *cfi = CODA_FTOC(coda_file); struct file *host_file; ssize_t ret; - cfi = CODA_FTOC(coda_file); BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC); - host_file = cfi->cfi_container; - - if (!host_file->f_op->write) - return -EINVAL; - host_inode = file_inode(host_file); + host_file = cfi->cfi_container; file_start_write(host_file); mutex_lock(&coda_inode->i_mutex); - - ret = host_file->f_op->write(host_file, buf, count, ppos); - - coda_inode->i_size = host_inode->i_size; + ret = vfs_iter_write(cfi->cfi_container, to, &iocb->ki_pos); + coda_inode->i_size = file_inode(host_file)->i_size; coda_inode->i_blocks = (coda_inode->i_size + 511) >> 9; coda_inode->i_mtime = coda_inode->i_ctime = CURRENT_TIME_SEC; mutex_unlock(&coda_inode->i_mutex); file_end_write(host_file); - return ret; } @@ -231,8 +219,8 @@ int coda_fsync(struct file *coda_file, loff_t start, loff_t end, int datasync) const struct file_operations coda_file_operations = { .llseek = generic_file_llseek, - .read = coda_file_read, - .write = coda_file_write, + .read_iter = coda_file_read_iter, + .write_iter = coda_file_write_iter, .mmap = coda_file_mmap, .open = coda_open, .release = coda_release, diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index afec6450450f..6b8e2f091f5b 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -570,6 +570,7 @@ static int mt_ioctl_trans(unsigned int fd, unsigned int cmd, void __user *argp) #define BNEPCONNDEL _IOW('B', 201, int) #define BNEPGETCONNLIST _IOR('B', 210, int) #define BNEPGETCONNINFO _IOR('B', 211, int) +#define BNEPGETSUPPFEAT _IOR('B', 212, int) #define CMTPCONNADD _IOW('C', 200, int) #define CMTPCONNDEL _IOW('C', 201, int) @@ -1247,6 +1248,7 @@ COMPATIBLE_IOCTL(BNEPCONNADD) COMPATIBLE_IOCTL(BNEPCONNDEL) COMPATIBLE_IOCTL(BNEPGETCONNLIST) COMPATIBLE_IOCTL(BNEPGETCONNINFO) +COMPATIBLE_IOCTL(BNEPGETSUPPFEAT) COMPATIBLE_IOCTL(CMTPCONNADD) COMPATIBLE_IOCTL(CMTPCONNDEL) COMPATIBLE_IOCTL(CMTPGETCONNLIST) diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index cf0db005d2f5..acb3d63bc9dc 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1598,7 +1598,7 @@ static loff_t configfs_dir_lseek(struct file *file, loff_t offset, int whence) if (offset >= 0) break; default: - mutex_unlock(&file_inode(file)->i_mutex); + mutex_unlock(&dentry->d_inode->i_mutex); return -EINVAL; } if (offset != file->f_pos) { diff --git a/fs/coredump.c b/fs/coredump.c index f319926ddf8c..bbbe139ab280 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -657,7 +657,7 @@ void do_coredump(const siginfo_t *siginfo) */ if (!uid_eq(inode->i_uid, current_fsuid())) goto close_fail; - if (!cprm.file->f_op->write) + if (!(cprm.file->f_mode & FMODE_CAN_WRITE)) goto close_fail; if (do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file)) goto close_fail; @@ -98,9 +98,9 @@ static bool buffer_size_valid(struct buffer_head *bh) return bh->b_state != 0; } -static ssize_t dax_io(int rw, struct inode *inode, struct iov_iter *iter, - loff_t start, loff_t end, get_block_t get_block, - struct buffer_head *bh) +static ssize_t dax_io(struct inode *inode, struct iov_iter *iter, + loff_t start, loff_t end, get_block_t get_block, + struct buffer_head *bh) { ssize_t retval = 0; loff_t pos = start; @@ -109,7 +109,7 @@ static ssize_t dax_io(int rw, struct inode *inode, struct iov_iter *iter, void *addr; bool hole = false; - if (rw != WRITE) + if (iov_iter_rw(iter) != WRITE) end = min(end, i_size_read(inode)); while (pos < end) { @@ -124,7 +124,7 @@ static ssize_t dax_io(int rw, struct inode *inode, struct iov_iter *iter, bh->b_size = PAGE_ALIGN(end - pos); bh->b_state = 0; retval = get_block(inode, block, bh, - rw == WRITE); + iov_iter_rw(iter) == WRITE); if (retval) break; if (!buffer_size_valid(bh)) @@ -137,7 +137,7 @@ static ssize_t dax_io(int rw, struct inode *inode, struct iov_iter *iter, bh->b_size -= done; } - hole = (rw != WRITE) && !buffer_written(bh); + hole = iov_iter_rw(iter) != WRITE && !buffer_written(bh); if (hole) { addr = NULL; size = bh->b_size - first; @@ -154,7 +154,7 @@ static ssize_t dax_io(int rw, struct inode *inode, struct iov_iter *iter, max = min(pos + size, end); } - if (rw == WRITE) + if (iov_iter_rw(iter) == WRITE) len = copy_from_iter(addr, max - pos, iter); else if (!hole) len = copy_to_iter(addr, max - pos, iter); @@ -173,7 +173,6 @@ static ssize_t dax_io(int rw, struct inode *inode, struct iov_iter *iter, /** * dax_do_io - Perform I/O to a DAX file - * @rw: READ to read or WRITE to write * @iocb: The control block for this I/O * @inode: The file which the I/O is directed at * @iter: The addresses to do I/O from or to @@ -189,9 +188,9 @@ static ssize_t dax_io(int rw, struct inode *inode, struct iov_iter *iter, * As with do_blockdev_direct_IO(), we increment i_dio_count while the I/O * is in progress. */ -ssize_t dax_do_io(int rw, struct kiocb *iocb, struct inode *inode, - struct iov_iter *iter, loff_t pos, - get_block_t get_block, dio_iodone_t end_io, int flags) +ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode, + struct iov_iter *iter, loff_t pos, get_block_t get_block, + dio_iodone_t end_io, int flags) { struct buffer_head bh; ssize_t retval = -EINVAL; @@ -199,7 +198,7 @@ ssize_t dax_do_io(int rw, struct kiocb *iocb, struct inode *inode, memset(&bh, 0, sizeof(bh)); - if ((flags & DIO_LOCKING) && (rw == READ)) { + if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ) { struct address_space *mapping = inode->i_mapping; mutex_lock(&inode->i_mutex); retval = filemap_write_and_wait_range(mapping, pos, end - 1); @@ -212,9 +211,9 @@ ssize_t dax_do_io(int rw, struct kiocb *iocb, struct inode *inode, /* Protects against truncate */ atomic_inc(&inode->i_dio_count); - retval = dax_io(rw, inode, iter, pos, end, get_block, &bh); + retval = dax_io(inode, iter, pos, end, get_block, &bh); - if ((flags & DIO_LOCKING) && (rw == READ)) + if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ) mutex_unlock(&inode->i_mutex); if ((retval > 0) && end_io) @@ -464,6 +463,23 @@ int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, EXPORT_SYMBOL_GPL(dax_fault); /** + * dax_pfn_mkwrite - handle first write to DAX page + * @vma: The virtual memory area where the fault occurred + * @vmf: The description of the fault + * + */ +int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct super_block *sb = file_inode(vma->vm_file)->i_sb; + + sb_start_pagefault(sb); + file_update_time(vma->vm_file); + sb_end_pagefault(sb); + return VM_FAULT_NOPAGE; +} +EXPORT_SYMBOL_GPL(dax_pfn_mkwrite); + +/** * dax_zero_page_range - zero a range within a page of a DAX file * @inode: The file being truncated * @from: The file offset that is being truncated to diff --git a/fs/dcache.c b/fs/dcache.c index c71e3732e53b..656ce522a218 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -269,6 +269,41 @@ static inline int dname_external(const struct dentry *dentry) return dentry->d_name.name != dentry->d_iname; } +/* + * Make sure other CPUs see the inode attached before the type is set. + */ +static inline void __d_set_inode_and_type(struct dentry *dentry, + struct inode *inode, + unsigned type_flags) +{ + unsigned flags; + + dentry->d_inode = inode; + smp_wmb(); + flags = READ_ONCE(dentry->d_flags); + flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); + flags |= type_flags; + WRITE_ONCE(dentry->d_flags, flags); +} + +/* + * Ideally, we want to make sure that other CPUs see the flags cleared before + * the inode is detached, but this is really a violation of RCU principles + * since the ordering suggests we should always set inode before flags. + * + * We should instead replace or discard the entire dentry - but that sucks + * performancewise on mass deletion/rename. + */ +static inline void __d_clear_type_and_inode(struct dentry *dentry) +{ + unsigned flags = READ_ONCE(dentry->d_flags); + + flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); + WRITE_ONCE(dentry->d_flags, flags); + smp_wmb(); + dentry->d_inode = NULL; +} + static void dentry_free(struct dentry *dentry) { WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias)); @@ -311,7 +346,7 @@ static void dentry_iput(struct dentry * dentry) { struct inode *inode = dentry->d_inode; if (inode) { - dentry->d_inode = NULL; + __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); @@ -335,8 +370,7 @@ static void dentry_unlink_inode(struct dentry * dentry) __releases(dentry->d_inode->i_lock) { struct inode *inode = dentry->d_inode; - __d_clear_type(dentry); - dentry->d_inode = NULL; + __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias); dentry_rcuwalk_barrier(dentry); spin_unlock(&dentry->d_lock); @@ -1715,11 +1749,9 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) unsigned add_flags = d_flags_for_inode(inode); spin_lock(&dentry->d_lock); - dentry->d_flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); - dentry->d_flags |= add_flags; if (inode) hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); - dentry->d_inode = inode; + __d_set_inode_and_type(dentry, inode, add_flags); dentry_rcuwalk_barrier(dentry); spin_unlock(&dentry->d_lock); fsnotify_d_instantiate(dentry, inode); @@ -1937,8 +1969,7 @@ static struct dentry *__d_obtain_alias(struct inode *inode, int disconnected) add_flags |= DCACHE_DISCONNECTED; spin_lock(&tmp->d_lock); - tmp->d_inode = inode; - tmp->d_flags |= add_flags; + __d_set_inode_and_type(tmp, inode, add_flags); hlist_add_head(&tmp->d_u.d_alias, &inode->i_dentry); hlist_bl_lock(&tmp->d_sb->s_anon); hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon); @@ -2690,7 +2721,7 @@ static int __d_unalias(struct inode *inode, struct dentry *dentry, struct dentry *alias) { struct mutex *m1 = NULL, *m2 = NULL; - int ret = -EBUSY; + int ret = -ESTALE; /* If alias and dentry share a parent, then no extra locks required */ if (alias->d_parent == dentry->d_parent) diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 96400ab42d13..c9ee0dfe90b5 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -254,6 +254,9 @@ static struct dentry *start_creating(const char *name, struct dentry *parent) pr_debug("debugfs: creating file '%s'\n",name); + if (IS_ERR(parent)) + return parent; + error = simple_pin_fs(&debug_fs_type, &debugfs_mount, &debugfs_mount_count); if (error) @@ -521,7 +524,7 @@ static int __debugfs_remove(struct dentry *dentry, struct dentry *parent) if (debugfs_positive(dentry)) { dget(dentry); - if (S_ISDIR(dentry->d_inode->i_mode)) + if (d_is_dir(dentry)) ret = simple_rmdir(parent->d_inode, dentry); else simple_unlink(parent->d_inode, dentry); diff --git a/fs/direct-io.c b/fs/direct-io.c index e181b6b2e297..c3b560b24a46 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -37,7 +37,6 @@ #include <linux/uio.h> #include <linux/atomic.h> #include <linux/prefetch.h> -#include <linux/aio.h> /* * How many user pages to map in one call to get_user_pages(). This determines @@ -265,7 +264,7 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, ret = err; } - aio_complete(dio->iocb, ret, 0); + dio->iocb->ki_complete(dio->iocb, ret, 0); } kmem_cache_free(dio_cache, dio); @@ -1056,7 +1055,7 @@ static inline int drop_refcount(struct dio *dio) * operation. AIO can if it was a broken operation described above or * in fact if all the bios race to complete before we get here. In * that case dio_complete() translates the EIOCBQUEUED into the proper - * return code that the caller will hand to aio_complete(). + * return code that the caller will hand to ->complete(). * * This is managed by the bio_lock instead of being an atomic_t so that * completion paths can drop their ref and use the remaining count to @@ -1094,10 +1093,10 @@ static inline int drop_refcount(struct dio *dio) * for the whole file. */ static inline ssize_t -do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, - struct block_device *bdev, struct iov_iter *iter, loff_t offset, - get_block_t get_block, dio_iodone_t end_io, - dio_submit_t submit_io, int flags) +do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, + struct block_device *bdev, struct iov_iter *iter, + loff_t offset, get_block_t get_block, dio_iodone_t end_io, + dio_submit_t submit_io, int flags) { unsigned i_blkbits = ACCESS_ONCE(inode->i_blkbits); unsigned blkbits = i_blkbits; @@ -1111,9 +1110,6 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, struct blk_plug plug; unsigned long align = offset | iov_iter_alignment(iter); - if (rw & WRITE) - rw = WRITE_ODIRECT; - /* * Avoid references to bdev if not absolutely needed to give * the early prefetch in the caller enough time. @@ -1128,7 +1124,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, } /* watch out for a 0 len io from a tricksy fs */ - if (rw == READ && !iov_iter_count(iter)) + if (iov_iter_rw(iter) == READ && !iov_iter_count(iter)) return 0; dio = kmem_cache_alloc(dio_cache, GFP_KERNEL); @@ -1144,7 +1140,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, dio->flags = flags; if (dio->flags & DIO_LOCKING) { - if (rw == READ) { + if (iov_iter_rw(iter) == READ) { struct address_space *mapping = iocb->ki_filp->f_mapping; @@ -1170,19 +1166,19 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, if (is_sync_kiocb(iocb)) dio->is_async = false; else if (!(dio->flags & DIO_ASYNC_EXTEND) && - (rw & WRITE) && end > i_size_read(inode)) + iov_iter_rw(iter) == WRITE && end > i_size_read(inode)) dio->is_async = false; else dio->is_async = true; dio->inode = inode; - dio->rw = rw; + dio->rw = iov_iter_rw(iter) == WRITE ? WRITE_ODIRECT : READ; /* * For AIO O_(D)SYNC writes we need to defer completions to a workqueue * so that we can call ->fsync. */ - if (dio->is_async && (rw & WRITE) && + if (dio->is_async && iov_iter_rw(iter) == WRITE && ((iocb->ki_filp->f_flags & O_DSYNC) || IS_SYNC(iocb->ki_filp->f_mapping->host))) { retval = dio_set_defer_completion(dio); @@ -1275,7 +1271,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, * we can let i_mutex go now that its achieved its purpose * of protecting us from looking up uninitialized blocks. */ - if (rw == READ && (dio->flags & DIO_LOCKING)) + if (iov_iter_rw(iter) == READ && (dio->flags & DIO_LOCKING)) mutex_unlock(&dio->inode->i_mutex); /* @@ -1287,7 +1283,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, */ BUG_ON(retval == -EIOCBQUEUED); if (dio->is_async && retval == 0 && dio->result && - (rw == READ || dio->result == count)) + (iov_iter_rw(iter) == READ || dio->result == count)) retval = -EIOCBQUEUED; else dio_await_completion(dio); @@ -1301,11 +1297,11 @@ out: return retval; } -ssize_t -__blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, - struct block_device *bdev, struct iov_iter *iter, loff_t offset, - get_block_t get_block, dio_iodone_t end_io, - dio_submit_t submit_io, int flags) +ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, + struct block_device *bdev, struct iov_iter *iter, + loff_t offset, get_block_t get_block, + dio_iodone_t end_io, dio_submit_t submit_io, + int flags) { /* * The block device state is needed in the end to finally @@ -1319,8 +1315,8 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, prefetch(bdev->bd_queue); prefetch((char *)bdev->bd_queue + SMP_CACHE_BYTES); - return do_blockdev_direct_IO(rw, iocb, inode, bdev, iter, offset, - get_block, end_io, submit_io, flags); + return do_blockdev_direct_IO(iocb, inode, bdev, iter, offset, get_block, + end_io, submit_io, flags); } EXPORT_SYMBOL(__blockdev_direct_IO); diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index fd39bad6f1bd..a65786e26b05 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -31,7 +31,6 @@ #include <linux/security.h> #include <linux/compat.h> #include <linux/fs_stack.h> -#include <linux/aio.h> #include "ecryptfs_kernel.h" /** @@ -52,12 +51,6 @@ static ssize_t ecryptfs_read_update_atime(struct kiocb *iocb, struct file *file = iocb->ki_filp; rc = generic_file_read_iter(iocb, to); - /* - * Even though this is a async interface, we need to wait - * for IO to finish to update atime - */ - if (-EIOCBQUEUED == rc) - rc = wait_on_sync_kiocb(iocb); if (rc >= 0) { path = ecryptfs_dentry_to_lower_path(file->f_path.dentry); touch_atime(path); @@ -365,9 +358,7 @@ const struct file_operations ecryptfs_dir_fops = { const struct file_operations ecryptfs_main_fops = { .llseek = generic_file_llseek, - .read = new_sync_read, .read_iter = ecryptfs_read_update_atime, - .write = new_sync_write, .write_iter = generic_file_write_iter, .iterate = ecryptfs_readdir, .unlocked_ioctl = ecryptfs_unlocked_ioctl, diff --git a/fs/exec.c b/fs/exec.c index c7f9b733406d..49a1c61433b7 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -926,10 +926,14 @@ static int de_thread(struct task_struct *tsk) if (!thread_group_leader(tsk)) { struct task_struct *leader = tsk->group_leader; - sig->notify_count = -1; /* for exit_notify() */ for (;;) { threadgroup_change_begin(tsk); write_lock_irq(&tasklist_lock); + /* + * Do this under tasklist_lock to ensure that + * exit_notify() can't miss ->group_exit_task + */ + sig->notify_count = -1; if (likely(leader->exit_state)) break; __set_current_state(TASK_KILLABLE); @@ -1078,7 +1082,13 @@ int flush_old_exec(struct linux_binprm * bprm) if (retval) goto out; + /* + * Must be called _before_ exec_mmap() as bprm->mm is + * not visibile until then. This also enables the update + * to be lockless. + */ set_mm_exe_file(bprm->mm, bprm->file); + /* * Release all of the old mmap stuff */ @@ -1265,6 +1275,53 @@ static void check_unsafe_exec(struct linux_binprm *bprm) spin_unlock(&p->fs->lock); } +static void bprm_fill_uid(struct linux_binprm *bprm) +{ + struct inode *inode; + unsigned int mode; + kuid_t uid; + kgid_t gid; + + /* clear any previous set[ug]id data from a previous binary */ + bprm->cred->euid = current_euid(); + bprm->cred->egid = current_egid(); + + if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) + return; + + if (task_no_new_privs(current)) + return; + + inode = file_inode(bprm->file); + mode = READ_ONCE(inode->i_mode); + if (!(mode & (S_ISUID|S_ISGID))) + return; + + /* Be careful if suid/sgid is set */ + mutex_lock(&inode->i_mutex); + + /* reload atomically mode/uid/gid now that lock held */ + mode = inode->i_mode; + uid = inode->i_uid; + gid = inode->i_gid; + mutex_unlock(&inode->i_mutex); + + /* We ignore suid/sgid if there are no mappings for them in the ns */ + if (!kuid_has_mapping(bprm->cred->user_ns, uid) || + !kgid_has_mapping(bprm->cred->user_ns, gid)) + return; + + if (mode & S_ISUID) { + bprm->per_clear |= PER_CLEAR_ON_SETID; + bprm->cred->euid = uid; + } + + if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { + bprm->per_clear |= PER_CLEAR_ON_SETID; + bprm->cred->egid = gid; + } +} + /* * Fill the binprm structure from the inode. * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes @@ -1273,36 +1330,9 @@ static void check_unsafe_exec(struct linux_binprm *bprm) */ int prepare_binprm(struct linux_binprm *bprm) { - struct inode *inode = file_inode(bprm->file); - umode_t mode = inode->i_mode; int retval; - - /* clear any previous set[ug]id data from a previous binary */ - bprm->cred->euid = current_euid(); - bprm->cred->egid = current_egid(); - - if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) && - !task_no_new_privs(current) && - kuid_has_mapping(bprm->cred->user_ns, inode->i_uid) && - kgid_has_mapping(bprm->cred->user_ns, inode->i_gid)) { - /* Set-uid? */ - if (mode & S_ISUID) { - bprm->per_clear |= PER_CLEAR_ON_SETID; - bprm->cred->euid = inode->i_uid; - } - - /* Set-gid? */ - /* - * If setgid is set but no group execute bit then this - * is a candidate for mandatory locking, not a setgid - * executable. - */ - if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { - bprm->per_clear |= PER_CLEAR_ON_SETID; - bprm->cred->egid = inode->i_gid; - } - } + bprm_fill_uid(bprm); /* fill in binprm security blob */ retval = security_bprm_set_creds(bprm); diff --git a/fs/exofs/file.c b/fs/exofs/file.c index 1a376b42d305..906de66e8e7e 100644 --- a/fs/exofs/file.c +++ b/fs/exofs/file.c @@ -67,8 +67,6 @@ static int exofs_flush(struct file *file, fl_owner_t id) const struct file_operations exofs_file_operations = { .llseek = generic_file_llseek, - .read = new_sync_read, - .write = new_sync_write, .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index a198e94813fe..35073aaec6e0 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -963,8 +963,8 @@ static void exofs_invalidatepage(struct page *page, unsigned int offset, /* TODO: Should be easy enough to do proprly */ -static ssize_t exofs_direct_IO(int rw, struct kiocb *iocb, - struct iov_iter *iter, loff_t offset) +static ssize_t exofs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) { return 0; } diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 678f9ab08c48..8d15febd0aa3 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -793,7 +793,6 @@ extern int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync); extern const struct inode_operations ext2_file_inode_operations; extern const struct file_operations ext2_file_operations; -extern const struct file_operations ext2_dax_file_operations; /* inode.c */ extern const struct address_space_operations ext2_aops; diff --git a/fs/ext2/file.c b/fs/ext2/file.c index e31701713516..3a0a6c6406d0 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -39,6 +39,7 @@ static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) static const struct vm_operations_struct ext2_dax_vm_ops = { .fault = ext2_dax_fault, .page_mkwrite = ext2_dax_mkwrite, + .pfn_mkwrite = dax_pfn_mkwrite, }; static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma) @@ -92,8 +93,6 @@ int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync) */ const struct file_operations ext2_file_operations = { .llseek = generic_file_llseek, - .read = new_sync_read, - .write = new_sync_write, .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, .unlocked_ioctl = ext2_ioctl, @@ -108,24 +107,6 @@ const struct file_operations ext2_file_operations = { .splice_write = iter_file_splice_write, }; -#ifdef CONFIG_FS_DAX -const struct file_operations ext2_dax_file_operations = { - .llseek = generic_file_llseek, - .read = new_sync_read, - .write = new_sync_write, - .read_iter = generic_file_read_iter, - .write_iter = generic_file_write_iter, - .unlocked_ioctl = ext2_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = ext2_compat_ioctl, -#endif - .mmap = ext2_file_mmap, - .open = dquot_file_open, - .release = ext2_release_file, - .fsync = ext2_fsync, -}; -#endif - const struct inode_operations ext2_file_inode_operations = { #ifdef CONFIG_EXT2_FS_XATTR .setxattr = generic_setxattr, diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 6434bc000125..5d9213963fae 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -31,7 +31,7 @@ #include <linux/mpage.h> #include <linux/fiemap.h> #include <linux/namei.h> -#include <linux/aio.h> +#include <linux/uio.h> #include "ext2.h" #include "acl.h" #include "xattr.h" @@ -851,8 +851,7 @@ static sector_t ext2_bmap(struct address_space *mapping, sector_t block) } static ssize_t -ext2_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -861,12 +860,12 @@ ext2_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, ssize_t ret; if (IS_DAX(inode)) - ret = dax_do_io(rw, iocb, inode, iter, offset, ext2_get_block, - NULL, DIO_LOCKING); + ret = dax_do_io(iocb, inode, iter, offset, ext2_get_block, NULL, + DIO_LOCKING); else - ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, + ret = blockdev_direct_IO(iocb, inode, iter, offset, ext2_get_block); - if (ret < 0 && (rw & WRITE)) + if (ret < 0 && iov_iter_rw(iter) == WRITE) ext2_write_failed(mapping, offset + count); return ret; } @@ -1388,10 +1387,7 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino) if (S_ISREG(inode->i_mode)) { inode->i_op = &ext2_file_inode_operations; - if (test_opt(inode->i_sb, DAX)) { - inode->i_mapping->a_ops = &ext2_aops; - inode->i_fop = &ext2_dax_file_operations; - } else if (test_opt(inode->i_sb, NOBH)) { + if (test_opt(inode->i_sb, NOBH)) { inode->i_mapping->a_ops = &ext2_nobh_aops; inode->i_fop = &ext2_file_operations; } else { diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 148f6e3789ea..ce422931f411 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -104,10 +104,7 @@ static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode return PTR_ERR(inode); inode->i_op = &ext2_file_inode_operations; - if (test_opt(inode->i_sb, DAX)) { - inode->i_mapping->a_ops = &ext2_aops; - inode->i_fop = &ext2_dax_file_operations; - } else if (test_opt(inode->i_sb, NOBH)) { + if (test_opt(inode->i_sb, NOBH)) { inode->i_mapping->a_ops = &ext2_nobh_aops; inode->i_fop = &ext2_file_operations; } else { @@ -125,10 +122,7 @@ static int ext2_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) return PTR_ERR(inode); inode->i_op = &ext2_file_inode_operations; - if (test_opt(inode->i_sb, DAX)) { - inode->i_mapping->a_ops = &ext2_aops; - inode->i_fop = &ext2_dax_file_operations; - } else if (test_opt(inode->i_sb, NOBH)) { + if (test_opt(inode->i_sb, NOBH)) { inode->i_mapping->a_ops = &ext2_nobh_aops; inode->i_fop = &ext2_file_operations; } else { diff --git a/fs/ext3/file.c b/fs/ext3/file.c index a062fa1e1b11..3b8f650de22c 100644 --- a/fs/ext3/file.c +++ b/fs/ext3/file.c @@ -50,8 +50,6 @@ static int ext3_release_file (struct inode * inode, struct file * filp) const struct file_operations ext3_file_operations = { .llseek = generic_file_llseek, - .read = new_sync_read, - .write = new_sync_write, .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, .unlocked_ioctl = ext3_ioctl, diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 2c6ccc49ba27..13c0868c7160 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -27,7 +27,7 @@ #include <linux/writeback.h> #include <linux/mpage.h> #include <linux/namei.h> -#include <linux/aio.h> +#include <linux/uio.h> #include "ext3.h" #include "xattr.h" #include "acl.h" @@ -1820,8 +1820,8 @@ static int ext3_releasepage(struct page *page, gfp_t wait) * crashes then stale disk data _may_ be exposed inside the file. But current * VFS code falls back into buffered path in that case so we are safe. */ -static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, - struct iov_iter *iter, loff_t offset) +static ssize_t ext3_direct_IO(struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; @@ -1832,9 +1832,9 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, size_t count = iov_iter_count(iter); int retries = 0; - trace_ext3_direct_IO_enter(inode, offset, count, rw); + trace_ext3_direct_IO_enter(inode, offset, count, iov_iter_rw(iter)); - if (rw == WRITE) { + if (iov_iter_rw(iter) == WRITE) { loff_t final_size = offset + count; if (final_size > inode->i_size) { @@ -1856,12 +1856,12 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, } retry: - ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, ext3_get_block); + ret = blockdev_direct_IO(iocb, inode, iter, offset, ext3_get_block); /* * In case of error extending write may have instantiated a few * blocks outside i_size. Trim these off again. */ - if (unlikely((rw & WRITE) && ret < 0)) { + if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) { loff_t isize = i_size_read(inode); loff_t end = offset + count; @@ -1908,7 +1908,7 @@ retry: ret = err; } out: - trace_ext3_direct_IO_exit(inode, offset, count, rw, ret); + trace_ext3_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret); return ret; } diff --git a/fs/ext3/super.c b/fs/ext3/super.c index d4dbf3c259b3..f037b4b27300 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -789,7 +789,7 @@ static const struct quotactl_ops ext3_qctl_operations = { .quota_on = ext3_quota_on, .quota_off = dquot_quota_off, .quota_sync = dquot_quota_sync, - .get_info = dquot_get_dqinfo, + .get_state = dquot_get_state, .set_info = dquot_set_dqinfo, .get_dqblk = dquot_get_dqblk, .set_dqblk = dquot_set_dqblk diff --git a/fs/ext3/xattr.c b/fs/ext3/xattr.c index c6874be6d58b..24215dc09a18 100644 --- a/fs/ext3/xattr.c +++ b/fs/ext3/xattr.c @@ -546,8 +546,7 @@ ext3_xattr_set_entry(struct ext3_xattr_info *i, struct ext3_xattr_search *s) free += EXT3_XATTR_LEN(name_len); } if (i->value) { - if (free < EXT3_XATTR_SIZE(i->value_len) || - free < EXT3_XATTR_LEN(name_len) + + if (free < EXT3_XATTR_LEN(name_len) + EXT3_XATTR_SIZE(i->value_len)) return -ENOSPC; } diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index efea5d5c44ce..18228c201f7f 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -64,6 +64,23 @@ config EXT4_FS_SECURITY If you are not using a security module that requires using extended attributes for file security labels, say N. +config EXT4_FS_ENCRYPTION + bool "Ext4 Encryption" + depends on EXT4_FS + select CRYPTO_AES + select CRYPTO_CBC + select CRYPTO_ECB + select CRYPTO_XTS + select CRYPTO_CTS + select CRYPTO_SHA256 + select KEYS + select ENCRYPTED_KEYS + help + Enable encryption of ext4 files and directories. This + feature is similar to ecryptfs, but it is more memory + efficient since it avoids caching the encrypted and + decrypted pages in the page cache. + config EXT4_DEBUG bool "EXT4 debugging support" depends on EXT4_FS diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index 0310fec2ee3d..75285ea9aa05 100644 --- a/fs/ext4/Makefile +++ b/fs/ext4/Makefile @@ -8,7 +8,9 @@ ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.o \ ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \ ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o \ mmp.o indirect.o extents_status.o xattr.o xattr_user.o \ - xattr_trusted.o inline.o + xattr_trusted.o inline.o readpage.o ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o ext4-$(CONFIG_EXT4_FS_SECURITY) += xattr_security.o +ext4-$(CONFIG_EXT4_FS_ENCRYPTION) += crypto_policy.o crypto.o \ + crypto_key.o crypto_fname.o diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index d40c8dbbb0d6..69b1e73026a5 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -4,11 +4,6 @@ * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> */ -#include <linux/init.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/capability.h> -#include <linux/fs.h> #include "ext4_jbd2.h" #include "ext4.h" #include "xattr.h" diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 83a6f497c4e0..955bf49a7945 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -14,7 +14,6 @@ #include <linux/time.h> #include <linux/capability.h> #include <linux/fs.h> -#include <linux/jbd2.h> #include <linux/quotaops.h> #include <linux/buffer_head.h> #include "ext4.h" @@ -641,8 +640,6 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode, * fail EDQUOT for metdata, but we do account for it. */ if (!(*errp) && (flags & EXT4_MB_DELALLOC_RESERVED)) { - spin_lock(&EXT4_I(inode)->i_block_reservation_lock); - spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); dquot_alloc_block_nofail(inode, EXT4_C2B(EXT4_SB(inode->i_sb), ar.len)); } diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c index b610779a958c..4a606afb171f 100644 --- a/fs/ext4/bitmap.c +++ b/fs/ext4/bitmap.c @@ -8,7 +8,6 @@ */ #include <linux/buffer_head.h> -#include <linux/jbd2.h> #include "ext4.h" unsigned int ext4_count_free(char *bitmap, unsigned int numchars) diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 41eb9dcfac7e..3522340c7a99 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -16,7 +16,6 @@ #include <linux/swap.h> #include <linux/pagemap.h> #include <linux/blkdev.h> -#include <linux/mutex.h> #include <linux/slab.h> #include "ext4.h" diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c new file mode 100644 index 000000000000..8ff15273ab0c --- /dev/null +++ b/fs/ext4/crypto.c @@ -0,0 +1,558 @@ +/* + * linux/fs/ext4/crypto.c + * + * Copyright (C) 2015, Google, Inc. + * + * This contains encryption functions for ext4 + * + * Written by Michael Halcrow, 2014. + * + * Filename encryption additions + * Uday Savagaonkar, 2014 + * Encryption policy handling additions + * Ildar Muslukhov, 2014 + * + * This has not yet undergone a rigorous security audit. + * + * The usage of AES-XTS should conform to recommendations in NIST + * Special Publication 800-38E and IEEE P1619/D16. + */ + +#include <crypto/hash.h> +#include <crypto/sha.h> +#include <keys/user-type.h> +#include <keys/encrypted-type.h> +#include <linux/crypto.h> +#include <linux/ecryptfs.h> +#include <linux/gfp.h> +#include <linux/kernel.h> +#include <linux/key.h> +#include <linux/list.h> +#include <linux/mempool.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/random.h> +#include <linux/scatterlist.h> +#include <linux/spinlock_types.h> + +#include "ext4_extents.h" +#include "xattr.h" + +/* Encryption added and removed here! (L: */ + +static unsigned int num_prealloc_crypto_pages = 32; +static unsigned int num_prealloc_crypto_ctxs = 128; + +module_param(num_prealloc_crypto_pages, uint, 0444); +MODULE_PARM_DESC(num_prealloc_crypto_pages, + "Number of crypto pages to preallocate"); +module_param(num_prealloc_crypto_ctxs, uint, 0444); +MODULE_PARM_DESC(num_prealloc_crypto_ctxs, + "Number of crypto contexts to preallocate"); + +static mempool_t *ext4_bounce_page_pool; + +static LIST_HEAD(ext4_free_crypto_ctxs); +static DEFINE_SPINLOCK(ext4_crypto_ctx_lock); + +/** + * ext4_release_crypto_ctx() - Releases an encryption context + * @ctx: The encryption context to release. + * + * If the encryption context was allocated from the pre-allocated pool, returns + * it to that pool. Else, frees it. + * + * If there's a bounce page in the context, this frees that. + */ +void ext4_release_crypto_ctx(struct ext4_crypto_ctx *ctx) +{ + unsigned long flags; + + if (ctx->bounce_page) { + if (ctx->flags & EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL) + __free_page(ctx->bounce_page); + else + mempool_free(ctx->bounce_page, ext4_bounce_page_pool); + ctx->bounce_page = NULL; + } + ctx->control_page = NULL; + if (ctx->flags & EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL) { + if (ctx->tfm) + crypto_free_tfm(ctx->tfm); + kfree(ctx); + } else { + spin_lock_irqsave(&ext4_crypto_ctx_lock, flags); + list_add(&ctx->free_list, &ext4_free_crypto_ctxs); + spin_unlock_irqrestore(&ext4_crypto_ctx_lock, flags); + } +} + +/** + * ext4_alloc_and_init_crypto_ctx() - Allocates and inits an encryption context + * @mask: The allocation mask. + * + * Return: An allocated and initialized encryption context on success. An error + * value or NULL otherwise. + */ +static struct ext4_crypto_ctx *ext4_alloc_and_init_crypto_ctx(gfp_t mask) +{ + struct ext4_crypto_ctx *ctx = kzalloc(sizeof(struct ext4_crypto_ctx), + mask); + + if (!ctx) + return ERR_PTR(-ENOMEM); + return ctx; +} + +/** + * ext4_get_crypto_ctx() - Gets an encryption context + * @inode: The inode for which we are doing the crypto + * + * Allocates and initializes an encryption context. + * + * Return: An allocated and initialized encryption context on success; error + * value or NULL otherwise. + */ +struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode) +{ + struct ext4_crypto_ctx *ctx = NULL; + int res = 0; + unsigned long flags; + struct ext4_encryption_key *key = &EXT4_I(inode)->i_encryption_key; + + if (!ext4_read_workqueue) + ext4_init_crypto(); + + /* + * We first try getting the ctx from a free list because in + * the common case the ctx will have an allocated and + * initialized crypto tfm, so it's probably a worthwhile + * optimization. For the bounce page, we first try getting it + * from the kernel allocator because that's just about as fast + * as getting it from a list and because a cache of free pages + * should generally be a "last resort" option for a filesystem + * to be able to do its job. + */ + spin_lock_irqsave(&ext4_crypto_ctx_lock, flags); + ctx = list_first_entry_or_null(&ext4_free_crypto_ctxs, + struct ext4_crypto_ctx, free_list); + if (ctx) + list_del(&ctx->free_list); + spin_unlock_irqrestore(&ext4_crypto_ctx_lock, flags); + if (!ctx) { + ctx = ext4_alloc_and_init_crypto_ctx(GFP_NOFS); + if (IS_ERR(ctx)) { + res = PTR_ERR(ctx); + goto out; + } + ctx->flags |= EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL; + } else { + ctx->flags &= ~EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL; + } + + /* Allocate a new Crypto API context if we don't already have + * one or if it isn't the right mode. */ + BUG_ON(key->mode == EXT4_ENCRYPTION_MODE_INVALID); + if (ctx->tfm && (ctx->mode != key->mode)) { + crypto_free_tfm(ctx->tfm); + ctx->tfm = NULL; + ctx->mode = EXT4_ENCRYPTION_MODE_INVALID; + } + if (!ctx->tfm) { + switch (key->mode) { + case EXT4_ENCRYPTION_MODE_AES_256_XTS: + ctx->tfm = crypto_ablkcipher_tfm( + crypto_alloc_ablkcipher("xts(aes)", 0, 0)); + break; + case EXT4_ENCRYPTION_MODE_AES_256_GCM: + /* TODO(mhalcrow): AEAD w/ gcm(aes); + * crypto_aead_setauthsize() */ + ctx->tfm = ERR_PTR(-ENOTSUPP); + break; + default: + BUG(); + } + if (IS_ERR_OR_NULL(ctx->tfm)) { + res = PTR_ERR(ctx->tfm); + ctx->tfm = NULL; + goto out; + } + ctx->mode = key->mode; + } + BUG_ON(key->size != ext4_encryption_key_size(key->mode)); + + /* There shouldn't be a bounce page attached to the crypto + * context at this point. */ + BUG_ON(ctx->bounce_page); + +out: + if (res) { + if (!IS_ERR_OR_NULL(ctx)) + ext4_release_crypto_ctx(ctx); + ctx = ERR_PTR(res); + } + return ctx; +} + +struct workqueue_struct *ext4_read_workqueue; +static DEFINE_MUTEX(crypto_init); + +/** + * ext4_exit_crypto() - Shutdown the ext4 encryption system + */ +void ext4_exit_crypto(void) +{ + struct ext4_crypto_ctx *pos, *n; + + list_for_each_entry_safe(pos, n, &ext4_free_crypto_ctxs, free_list) { + if (pos->bounce_page) { + if (pos->flags & + EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL) { + __free_page(pos->bounce_page); + } else { + mempool_free(pos->bounce_page, + ext4_bounce_page_pool); + } + } + if (pos->tfm) + crypto_free_tfm(pos->tfm); + kfree(pos); + } + INIT_LIST_HEAD(&ext4_free_crypto_ctxs); + if (ext4_bounce_page_pool) + mempool_destroy(ext4_bounce_page_pool); + ext4_bounce_page_pool = NULL; + if (ext4_read_workqueue) + destroy_workqueue(ext4_read_workqueue); + ext4_read_workqueue = NULL; +} + +/** + * ext4_init_crypto() - Set up for ext4 encryption. + * + * We only call this when we start accessing encrypted files, since it + * results in memory getting allocated that wouldn't otherwise be used. + * + * Return: Zero on success, non-zero otherwise. + */ +int ext4_init_crypto(void) +{ + int i, res; + + mutex_lock(&crypto_init); + if (ext4_read_workqueue) + goto already_initialized; + ext4_read_workqueue = alloc_workqueue("ext4_crypto", WQ_HIGHPRI, 0); + if (!ext4_read_workqueue) { + res = -ENOMEM; + goto fail; + } + + for (i = 0; i < num_prealloc_crypto_ctxs; i++) { + struct ext4_crypto_ctx *ctx; + + ctx = ext4_alloc_and_init_crypto_ctx(GFP_KERNEL); + if (IS_ERR(ctx)) { + res = PTR_ERR(ctx); + goto fail; + } + list_add(&ctx->free_list, &ext4_free_crypto_ctxs); + } + + ext4_bounce_page_pool = + mempool_create_page_pool(num_prealloc_crypto_pages, 0); + if (!ext4_bounce_page_pool) { + res = -ENOMEM; + goto fail; + } +already_initialized: + mutex_unlock(&crypto_init); + return 0; +fail: + ext4_exit_crypto(); + mutex_unlock(&crypto_init); + return res; +} + +void ext4_restore_control_page(struct page *data_page) +{ + struct ext4_crypto_ctx *ctx = + (struct ext4_crypto_ctx *)page_private(data_page); + + set_page_private(data_page, (unsigned long)NULL); + ClearPagePrivate(data_page); + unlock_page(data_page); + ext4_release_crypto_ctx(ctx); +} + +/** + * ext4_crypt_complete() - The completion callback for page encryption + * @req: The asynchronous encryption request context + * @res: The result of the encryption operation + */ +static void ext4_crypt_complete(struct crypto_async_request *req, int res) +{ + struct ext4_completion_result *ecr = req->data; + + if (res == -EINPROGRESS) + return; + ecr->res = res; + complete(&ecr->completion); +} + +typedef enum { + EXT4_DECRYPT = 0, + EXT4_ENCRYPT, +} ext4_direction_t; + +static int ext4_page_crypto(struct ext4_crypto_ctx *ctx, + struct inode *inode, + ext4_direction_t rw, + pgoff_t index, + struct page *src_page, + struct page *dest_page) + +{ + u8 xts_tweak[EXT4_XTS_TWEAK_SIZE]; + struct ablkcipher_request *req = NULL; + DECLARE_EXT4_COMPLETION_RESULT(ecr); + struct scatterlist dst, src; + struct ext4_inode_info *ei = EXT4_I(inode); + struct crypto_ablkcipher *atfm = __crypto_ablkcipher_cast(ctx->tfm); + int res = 0; + + BUG_ON(!ctx->tfm); + BUG_ON(ctx->mode != ei->i_encryption_key.mode); + + if (ctx->mode != EXT4_ENCRYPTION_MODE_AES_256_XTS) { + printk_ratelimited(KERN_ERR + "%s: unsupported crypto algorithm: %d\n", + __func__, ctx->mode); + return -ENOTSUPP; + } + + crypto_ablkcipher_clear_flags(atfm, ~0); + crypto_tfm_set_flags(ctx->tfm, CRYPTO_TFM_REQ_WEAK_KEY); + + res = crypto_ablkcipher_setkey(atfm, ei->i_encryption_key.raw, + ei->i_encryption_key.size); + if (res) { + printk_ratelimited(KERN_ERR + "%s: crypto_ablkcipher_setkey() failed\n", + __func__); + return res; + } + req = ablkcipher_request_alloc(atfm, GFP_NOFS); + if (!req) { + printk_ratelimited(KERN_ERR + "%s: crypto_request_alloc() failed\n", + __func__); + return -ENOMEM; + } + ablkcipher_request_set_callback( + req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + ext4_crypt_complete, &ecr); + + BUILD_BUG_ON(EXT4_XTS_TWEAK_SIZE < sizeof(index)); + memcpy(xts_tweak, &index, sizeof(index)); + memset(&xts_tweak[sizeof(index)], 0, + EXT4_XTS_TWEAK_SIZE - sizeof(index)); + + sg_init_table(&dst, 1); + sg_set_page(&dst, dest_page, PAGE_CACHE_SIZE, 0); + sg_init_table(&src, 1); + sg_set_page(&src, src_page, PAGE_CACHE_SIZE, 0); + ablkcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE, + xts_tweak); + if (rw == EXT4_DECRYPT) + res = crypto_ablkcipher_decrypt(req); + else + res = crypto_ablkcipher_encrypt(req); + if (res == -EINPROGRESS || res == -EBUSY) { + BUG_ON(req->base.data != &ecr); + wait_for_completion(&ecr.completion); + res = ecr.res; + } + ablkcipher_request_free(req); + if (res) { + printk_ratelimited( + KERN_ERR + "%s: crypto_ablkcipher_encrypt() returned %d\n", + __func__, res); + return res; + } + return 0; +} + +/** + * ext4_encrypt() - Encrypts a page + * @inode: The inode for which the encryption should take place + * @plaintext_page: The page to encrypt. Must be locked. + * + * Allocates a ciphertext page and encrypts plaintext_page into it using the ctx + * encryption context. + * + * Called on the page write path. The caller must call + * ext4_restore_control_page() on the returned ciphertext page to + * release the bounce buffer and the encryption context. + * + * Return: An allocated page with the encrypted content on success. Else, an + * error value or NULL. + */ +struct page *ext4_encrypt(struct inode *inode, + struct page *plaintext_page) +{ + struct ext4_crypto_ctx *ctx; + struct page *ciphertext_page = NULL; + int err; + + BUG_ON(!PageLocked(plaintext_page)); + + ctx = ext4_get_crypto_ctx(inode); + if (IS_ERR(ctx)) + return (struct page *) ctx; + + /* The encryption operation will require a bounce page. */ + ciphertext_page = alloc_page(GFP_NOFS); + if (!ciphertext_page) { + /* This is a potential bottleneck, but at least we'll have + * forward progress. */ + ciphertext_page = mempool_alloc(ext4_bounce_page_pool, + GFP_NOFS); + if (WARN_ON_ONCE(!ciphertext_page)) { + ciphertext_page = mempool_alloc(ext4_bounce_page_pool, + GFP_NOFS | __GFP_WAIT); + } + ctx->flags &= ~EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL; + } else { + ctx->flags |= EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL; + } + ctx->bounce_page = ciphertext_page; + ctx->control_page = plaintext_page; + err = ext4_page_crypto(ctx, inode, EXT4_ENCRYPT, plaintext_page->index, + plaintext_page, ciphertext_page); + if (err) { + ext4_release_crypto_ctx(ctx); + return ERR_PTR(err); + } + SetPagePrivate(ciphertext_page); + set_page_private(ciphertext_page, (unsigned long)ctx); + lock_page(ciphertext_page); + return ciphertext_page; +} + +/** + * ext4_decrypt() - Decrypts a page in-place + * @ctx: The encryption context. + * @page: The page to decrypt. Must be locked. + * + * Decrypts page in-place using the ctx encryption context. + * + * Called from the read completion callback. + * + * Return: Zero on success, non-zero otherwise. + */ +int ext4_decrypt(struct ext4_crypto_ctx *ctx, struct page *page) +{ + BUG_ON(!PageLocked(page)); + + return ext4_page_crypto(ctx, page->mapping->host, + EXT4_DECRYPT, page->index, page, page); +} + +/* + * Convenience function which takes care of allocating and + * deallocating the encryption context + */ +int ext4_decrypt_one(struct inode *inode, struct page *page) +{ + int ret; + + struct ext4_crypto_ctx *ctx = ext4_get_crypto_ctx(inode); + + if (!ctx) + return -ENOMEM; + ret = ext4_decrypt(ctx, page); + ext4_release_crypto_ctx(ctx); + return ret; +} + +int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex) +{ + struct ext4_crypto_ctx *ctx; + struct page *ciphertext_page = NULL; + struct bio *bio; + ext4_lblk_t lblk = ex->ee_block; + ext4_fsblk_t pblk = ext4_ext_pblock(ex); + unsigned int len = ext4_ext_get_actual_len(ex); + int err = 0; + + BUG_ON(inode->i_sb->s_blocksize != PAGE_CACHE_SIZE); + + ctx = ext4_get_crypto_ctx(inode); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + ciphertext_page = alloc_page(GFP_NOFS); + if (!ciphertext_page) { + /* This is a potential bottleneck, but at least we'll have + * forward progress. */ + ciphertext_page = mempool_alloc(ext4_bounce_page_pool, + GFP_NOFS); + if (WARN_ON_ONCE(!ciphertext_page)) { + ciphertext_page = mempool_alloc(ext4_bounce_page_pool, + GFP_NOFS | __GFP_WAIT); + } + ctx->flags &= ~EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL; + } else { + ctx->flags |= EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL; + } + ctx->bounce_page = ciphertext_page; + + while (len--) { + err = ext4_page_crypto(ctx, inode, EXT4_ENCRYPT, lblk, + ZERO_PAGE(0), ciphertext_page); + if (err) + goto errout; + + bio = bio_alloc(GFP_KERNEL, 1); + if (!bio) { + err = -ENOMEM; + goto errout; + } + bio->bi_bdev = inode->i_sb->s_bdev; + bio->bi_iter.bi_sector = pblk; + err = bio_add_page(bio, ciphertext_page, + inode->i_sb->s_blocksize, 0); + if (err) { + bio_put(bio); + goto errout; + } + err = submit_bio_wait(WRITE, bio); + if (err) + goto errout; + } + err = 0; +errout: + ext4_release_crypto_ctx(ctx); + return err; +} + +bool ext4_valid_contents_enc_mode(uint32_t mode) +{ + return (mode == EXT4_ENCRYPTION_MODE_AES_256_XTS); +} + +/** + * ext4_validate_encryption_key_size() - Validate the encryption key size + * @mode: The key mode. + * @size: The key size to validate. + * + * Return: The validated key size for @mode. Zero if invalid. + */ +uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size) +{ + if (size == ext4_encryption_key_size(mode)) + return size; + return 0; +} diff --git a/fs/ext4/crypto_fname.c b/fs/ext4/crypto_fname.c new file mode 100644 index 000000000000..ca2f5948c1ac --- /dev/null +++ b/fs/ext4/crypto_fname.c @@ -0,0 +1,709 @@ +/* + * linux/fs/ext4/crypto_fname.c + * + * Copyright (C) 2015, Google, Inc. + * + * This contains functions for filename crypto management in ext4 + * + * Written by Uday Savagaonkar, 2014. + * + * This has not yet undergone a rigorous security audit. + * + */ + +#include <crypto/hash.h> +#include <crypto/sha.h> +#include <keys/encrypted-type.h> +#include <keys/user-type.h> +#include <linux/crypto.h> +#include <linux/gfp.h> +#include <linux/kernel.h> +#include <linux/key.h> +#include <linux/key.h> +#include <linux/list.h> +#include <linux/mempool.h> +#include <linux/random.h> +#include <linux/scatterlist.h> +#include <linux/spinlock_types.h> + +#include "ext4.h" +#include "ext4_crypto.h" +#include "xattr.h" + +/** + * ext4_dir_crypt_complete() - + */ +static void ext4_dir_crypt_complete(struct crypto_async_request *req, int res) +{ + struct ext4_completion_result *ecr = req->data; + + if (res == -EINPROGRESS) + return; + ecr->res = res; + complete(&ecr->completion); +} + +bool ext4_valid_filenames_enc_mode(uint32_t mode) +{ + return (mode == EXT4_ENCRYPTION_MODE_AES_256_CTS); +} + +/** + * ext4_fname_encrypt() - + * + * This function encrypts the input filename, and returns the length of the + * ciphertext. Errors are returned as negative numbers. We trust the caller to + * allocate sufficient memory to oname string. + */ +static int ext4_fname_encrypt(struct ext4_fname_crypto_ctx *ctx, + const struct qstr *iname, + struct ext4_str *oname) +{ + u32 ciphertext_len; + struct ablkcipher_request *req = NULL; + DECLARE_EXT4_COMPLETION_RESULT(ecr); + struct crypto_ablkcipher *tfm = ctx->ctfm; + int res = 0; + char iv[EXT4_CRYPTO_BLOCK_SIZE]; + struct scatterlist sg[1]; + char *workbuf; + + if (iname->len <= 0 || iname->len > ctx->lim) + return -EIO; + + ciphertext_len = (iname->len < EXT4_CRYPTO_BLOCK_SIZE) ? + EXT4_CRYPTO_BLOCK_SIZE : iname->len; + ciphertext_len = (ciphertext_len > ctx->lim) + ? ctx->lim : ciphertext_len; + + /* Allocate request */ + req = ablkcipher_request_alloc(tfm, GFP_NOFS); + if (!req) { + printk_ratelimited( + KERN_ERR "%s: crypto_request_alloc() failed\n", __func__); + return -ENOMEM; + } + ablkcipher_request_set_callback(req, + CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + ext4_dir_crypt_complete, &ecr); + + /* Map the workpage */ + workbuf = kmap(ctx->workpage); + + /* Copy the input */ + memcpy(workbuf, iname->name, iname->len); + if (iname->len < ciphertext_len) + memset(workbuf + iname->len, 0, ciphertext_len - iname->len); + + /* Initialize IV */ + memset(iv, 0, EXT4_CRYPTO_BLOCK_SIZE); + + /* Create encryption request */ + sg_init_table(sg, 1); + sg_set_page(sg, ctx->workpage, PAGE_SIZE, 0); + ablkcipher_request_set_crypt(req, sg, sg, iname->len, iv); + res = crypto_ablkcipher_encrypt(req); + if (res == -EINPROGRESS || res == -EBUSY) { + BUG_ON(req->base.data != &ecr); + wait_for_completion(&ecr.completion); + res = ecr.res; + } + if (res >= 0) { + /* Copy the result to output */ + memcpy(oname->name, workbuf, ciphertext_len); + res = ciphertext_len; + } + kunmap(ctx->workpage); + ablkcipher_request_free(req); + if (res < 0) { + printk_ratelimited( + KERN_ERR "%s: Error (error code %d)\n", __func__, res); + } + oname->len = ciphertext_len; + return res; +} + +/* + * ext4_fname_decrypt() + * This function decrypts the input filename, and returns + * the length of the plaintext. + * Errors are returned as negative numbers. + * We trust the caller to allocate sufficient memory to oname string. + */ +static int ext4_fname_decrypt(struct ext4_fname_crypto_ctx *ctx, + const struct ext4_str *iname, + struct ext4_str *oname) +{ + struct ext4_str tmp_in[2], tmp_out[1]; + struct ablkcipher_request *req = NULL; + DECLARE_EXT4_COMPLETION_RESULT(ecr); + struct scatterlist sg[1]; + struct crypto_ablkcipher *tfm = ctx->ctfm; + int res = 0; + char iv[EXT4_CRYPTO_BLOCK_SIZE]; + char *workbuf; + + if (iname->len <= 0 || iname->len > ctx->lim) + return -EIO; + + tmp_in[0].name = iname->name; + tmp_in[0].len = iname->len; + tmp_out[0].name = oname->name; + + /* Allocate request */ + req = ablkcipher_request_alloc(tfm, GFP_NOFS); + if (!req) { + printk_ratelimited( + KERN_ERR "%s: crypto_request_alloc() failed\n", __func__); + return -ENOMEM; + } + ablkcipher_request_set_callback(req, + CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + ext4_dir_crypt_complete, &ecr); + + /* Map the workpage */ + workbuf = kmap(ctx->workpage); + + /* Copy the input */ + memcpy(workbuf, iname->name, iname->len); + + /* Initialize IV */ + memset(iv, 0, EXT4_CRYPTO_BLOCK_SIZE); + + /* Create encryption request */ + sg_init_table(sg, 1); + sg_set_page(sg, ctx->workpage, PAGE_SIZE, 0); + ablkcipher_request_set_crypt(req, sg, sg, iname->len, iv); + res = crypto_ablkcipher_decrypt(req); + if (res == -EINPROGRESS || res == -EBUSY) { + BUG_ON(req->base.data != &ecr); + wait_for_completion(&ecr.completion); + res = ecr.res; + } + if (res >= 0) { + /* Copy the result to output */ + memcpy(oname->name, workbuf, iname->len); + res = iname->len; + } + kunmap(ctx->workpage); + ablkcipher_request_free(req); + if (res < 0) { + printk_ratelimited( + KERN_ERR "%s: Error in ext4_fname_encrypt (error code %d)\n", + __func__, res); + return res; + } + + oname->len = strnlen(oname->name, iname->len); + return oname->len; +} + +/** + * ext4_fname_encode_digest() - + * + * Encodes the input digest using characters from the set [a-zA-Z0-9_+]. + * The encoded string is roughly 4/3 times the size of the input string. + */ +int ext4_fname_encode_digest(char *dst, char *src, u32 len) +{ + static const char *lookup_table = + "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789_+"; + u32 current_chunk, num_chunks, i; + char tmp_buf[3]; + u32 c0, c1, c2, c3; + + current_chunk = 0; + num_chunks = len/3; + for (i = 0; i < num_chunks; i++) { + c0 = src[3*i] & 0x3f; + c1 = (((src[3*i]>>6)&0x3) | ((src[3*i+1] & 0xf)<<2)) & 0x3f; + c2 = (((src[3*i+1]>>4)&0xf) | ((src[3*i+2] & 0x3)<<4)) & 0x3f; + c3 = (src[3*i+2]>>2) & 0x3f; + dst[4*i] = lookup_table[c0]; + dst[4*i+1] = lookup_table[c1]; + dst[4*i+2] = lookup_table[c2]; + dst[4*i+3] = lookup_table[c3]; + } + if (i*3 < len) { + memset(tmp_buf, 0, 3); + memcpy(tmp_buf, &src[3*i], len-3*i); + c0 = tmp_buf[0] & 0x3f; + c1 = (((tmp_buf[0]>>6)&0x3) | ((tmp_buf[1] & 0xf)<<2)) & 0x3f; + c2 = (((tmp_buf[1]>>4)&0xf) | ((tmp_buf[2] & 0x3)<<4)) & 0x3f; + c3 = (tmp_buf[2]>>2) & 0x3f; + dst[4*i] = lookup_table[c0]; + dst[4*i+1] = lookup_table[c1]; + dst[4*i+2] = lookup_table[c2]; + dst[4*i+3] = lookup_table[c3]; + i++; + } + return (i * 4); +} + +/** + * ext4_fname_hash() - + * + * This function computes the hash of the input filename, and sets the output + * buffer to the *encoded* digest. It returns the length of the digest as its + * return value. Errors are returned as negative numbers. We trust the caller + * to allocate sufficient memory to oname string. + */ +static int ext4_fname_hash(struct ext4_fname_crypto_ctx *ctx, + const struct ext4_str *iname, + struct ext4_str *oname) +{ + struct scatterlist sg; + struct hash_desc desc = { + .tfm = (struct crypto_hash *)ctx->htfm, + .flags = CRYPTO_TFM_REQ_MAY_SLEEP + }; + int res = 0; + + if (iname->len <= EXT4_FNAME_CRYPTO_DIGEST_SIZE) { + res = ext4_fname_encode_digest(oname->name, iname->name, + iname->len); + oname->len = res; + return res; + } + + sg_init_one(&sg, iname->name, iname->len); + res = crypto_hash_init(&desc); + if (res) { + printk(KERN_ERR + "%s: Error initializing crypto hash; res = [%d]\n", + __func__, res); + goto out; + } + res = crypto_hash_update(&desc, &sg, iname->len); + if (res) { + printk(KERN_ERR + "%s: Error updating crypto hash; res = [%d]\n", + __func__, res); + goto out; + } + res = crypto_hash_final(&desc, + &oname->name[EXT4_FNAME_CRYPTO_DIGEST_SIZE]); + if (res) { + printk(KERN_ERR + "%s: Error finalizing crypto hash; res = [%d]\n", + __func__, res); + goto out; + } + /* Encode the digest as a printable string--this will increase the + * size of the digest */ + oname->name[0] = 'I'; + res = ext4_fname_encode_digest(oname->name+1, + &oname->name[EXT4_FNAME_CRYPTO_DIGEST_SIZE], + EXT4_FNAME_CRYPTO_DIGEST_SIZE) + 1; + oname->len = res; +out: + return res; +} + +/** + * ext4_free_fname_crypto_ctx() - + * + * Frees up a crypto context. + */ +void ext4_free_fname_crypto_ctx(struct ext4_fname_crypto_ctx *ctx) +{ + if (ctx == NULL || IS_ERR(ctx)) + return; + + if (ctx->ctfm && !IS_ERR(ctx->ctfm)) + crypto_free_ablkcipher(ctx->ctfm); + if (ctx->htfm && !IS_ERR(ctx->htfm)) + crypto_free_hash(ctx->htfm); + if (ctx->workpage && !IS_ERR(ctx->workpage)) + __free_page(ctx->workpage); + kfree(ctx); +} + +/** + * ext4_put_fname_crypto_ctx() - + * + * Return: The crypto context onto free list. If the free list is above a + * threshold, completely frees up the context, and returns the memory. + * + * TODO: Currently we directly free the crypto context. Eventually we should + * add code it to return to free list. Such an approach will increase + * efficiency of directory lookup. + */ +void ext4_put_fname_crypto_ctx(struct ext4_fname_crypto_ctx **ctx) +{ + if (*ctx == NULL || IS_ERR(*ctx)) + return; + ext4_free_fname_crypto_ctx(*ctx); + *ctx = NULL; +} + +/** + * ext4_search_fname_crypto_ctx() - + */ +static struct ext4_fname_crypto_ctx *ext4_search_fname_crypto_ctx( + const struct ext4_encryption_key *key) +{ + return NULL; +} + +/** + * ext4_alloc_fname_crypto_ctx() - + */ +struct ext4_fname_crypto_ctx *ext4_alloc_fname_crypto_ctx( + const struct ext4_encryption_key *key) +{ + struct ext4_fname_crypto_ctx *ctx; + + ctx = kmalloc(sizeof(struct ext4_fname_crypto_ctx), GFP_NOFS); + if (ctx == NULL) + return ERR_PTR(-ENOMEM); + if (key->mode == EXT4_ENCRYPTION_MODE_INVALID) { + /* This will automatically set key mode to invalid + * As enum for ENCRYPTION_MODE_INVALID is zero */ + memset(&ctx->key, 0, sizeof(ctx->key)); + } else { + memcpy(&ctx->key, key, sizeof(struct ext4_encryption_key)); + } + ctx->has_valid_key = (EXT4_ENCRYPTION_MODE_INVALID == key->mode) + ? 0 : 1; + ctx->ctfm_key_is_ready = 0; + ctx->ctfm = NULL; + ctx->htfm = NULL; + ctx->workpage = NULL; + return ctx; +} + +/** + * ext4_get_fname_crypto_ctx() - + * + * Allocates a free crypto context and initializes it to hold + * the crypto material for the inode. + * + * Return: NULL if not encrypted. Error value on error. Valid pointer otherwise. + */ +struct ext4_fname_crypto_ctx *ext4_get_fname_crypto_ctx( + struct inode *inode, u32 max_ciphertext_len) +{ + struct ext4_fname_crypto_ctx *ctx; + struct ext4_inode_info *ei = EXT4_I(inode); + int res; + + /* Check if the crypto policy is set on the inode */ + res = ext4_encrypted_inode(inode); + if (res == 0) + return NULL; + + if (!ext4_has_encryption_key(inode)) + ext4_generate_encryption_key(inode); + + /* Get a crypto context based on the key. + * A new context is allocated if no context matches the requested key. + */ + ctx = ext4_search_fname_crypto_ctx(&(ei->i_encryption_key)); + if (ctx == NULL) + ctx = ext4_alloc_fname_crypto_ctx(&(ei->i_encryption_key)); + if (IS_ERR(ctx)) + return ctx; + + if (ctx->has_valid_key) { + if (ctx->key.mode != EXT4_ENCRYPTION_MODE_AES_256_CTS) { + printk_once(KERN_WARNING + "ext4: unsupported key mode %d\n", + ctx->key.mode); + return ERR_PTR(-ENOKEY); + } + + /* As a first cut, we will allocate new tfm in every call. + * later, we will keep the tfm around, in case the key gets + * re-used */ + if (ctx->ctfm == NULL) { + ctx->ctfm = crypto_alloc_ablkcipher("cts(cbc(aes))", + 0, 0); + } + if (IS_ERR(ctx->ctfm)) { + res = PTR_ERR(ctx->ctfm); + printk( + KERN_DEBUG "%s: error (%d) allocating crypto tfm\n", + __func__, res); + ctx->ctfm = NULL; + ext4_put_fname_crypto_ctx(&ctx); + return ERR_PTR(res); + } + if (ctx->ctfm == NULL) { + printk( + KERN_DEBUG "%s: could not allocate crypto tfm\n", + __func__); + ext4_put_fname_crypto_ctx(&ctx); + return ERR_PTR(-ENOMEM); + } + if (ctx->workpage == NULL) + ctx->workpage = alloc_page(GFP_NOFS); + if (IS_ERR(ctx->workpage)) { + res = PTR_ERR(ctx->workpage); + printk( + KERN_DEBUG "%s: error (%d) allocating work page\n", + __func__, res); + ctx->workpage = NULL; + ext4_put_fname_crypto_ctx(&ctx); + return ERR_PTR(res); + } + if (ctx->workpage == NULL) { + printk( + KERN_DEBUG "%s: could not allocate work page\n", + __func__); + ext4_put_fname_crypto_ctx(&ctx); + return ERR_PTR(-ENOMEM); + } + ctx->lim = max_ciphertext_len; + crypto_ablkcipher_clear_flags(ctx->ctfm, ~0); + crypto_tfm_set_flags(crypto_ablkcipher_tfm(ctx->ctfm), + CRYPTO_TFM_REQ_WEAK_KEY); + + /* If we are lucky, we will get a context that is already + * set up with the right key. Else, we will have to + * set the key */ + if (!ctx->ctfm_key_is_ready) { + /* Since our crypto objectives for filename encryption + * are pretty weak, + * we directly use the inode master key */ + res = crypto_ablkcipher_setkey(ctx->ctfm, + ctx->key.raw, ctx->key.size); + if (res) { + ext4_put_fname_crypto_ctx(&ctx); + return ERR_PTR(-EIO); + } + ctx->ctfm_key_is_ready = 1; + } else { + /* In the current implementation, key should never be + * marked "ready" for a context that has just been + * allocated. So we should never reach here */ + BUG(); + } + } + if (ctx->htfm == NULL) + ctx->htfm = crypto_alloc_hash("sha256", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(ctx->htfm)) { + res = PTR_ERR(ctx->htfm); + printk(KERN_DEBUG "%s: error (%d) allocating hash tfm\n", + __func__, res); + ctx->htfm = NULL; + ext4_put_fname_crypto_ctx(&ctx); + return ERR_PTR(res); + } + if (ctx->htfm == NULL) { + printk(KERN_DEBUG "%s: could not allocate hash tfm\n", + __func__); + ext4_put_fname_crypto_ctx(&ctx); + return ERR_PTR(-ENOMEM); + } + + return ctx; +} + +/** + * ext4_fname_crypto_round_up() - + * + * Return: The next multiple of block size + */ +u32 ext4_fname_crypto_round_up(u32 size, u32 blksize) +{ + return ((size+blksize-1)/blksize)*blksize; +} + +/** + * ext4_fname_crypto_namelen_on_disk() - + */ +int ext4_fname_crypto_namelen_on_disk(struct ext4_fname_crypto_ctx *ctx, + u32 namelen) +{ + u32 ciphertext_len; + + if (ctx == NULL) + return -EIO; + if (!(ctx->has_valid_key)) + return -EACCES; + ciphertext_len = (namelen < EXT4_CRYPTO_BLOCK_SIZE) ? + EXT4_CRYPTO_BLOCK_SIZE : namelen; + ciphertext_len = (ciphertext_len > ctx->lim) + ? ctx->lim : ciphertext_len; + return (int) ciphertext_len; +} + +/** + * ext4_fname_crypto_alloc_obuff() - + * + * Allocates an output buffer that is sufficient for the crypto operation + * specified by the context and the direction. + */ +int ext4_fname_crypto_alloc_buffer(struct ext4_fname_crypto_ctx *ctx, + u32 ilen, struct ext4_str *crypto_str) +{ + unsigned int olen; + + if (!ctx) + return -EIO; + olen = ext4_fname_crypto_round_up(ilen, EXT4_CRYPTO_BLOCK_SIZE); + crypto_str->len = olen; + if (olen < EXT4_FNAME_CRYPTO_DIGEST_SIZE*2) + olen = EXT4_FNAME_CRYPTO_DIGEST_SIZE*2; + /* Allocated buffer can hold one more character to null-terminate the + * string */ + crypto_str->name = kmalloc(olen+1, GFP_NOFS); + if (!(crypto_str->name)) + return -ENOMEM; + return 0; +} + +/** + * ext4_fname_crypto_free_buffer() - + * + * Frees the buffer allocated for crypto operation. + */ +void ext4_fname_crypto_free_buffer(struct ext4_str *crypto_str) +{ + if (!crypto_str) + return; + kfree(crypto_str->name); + crypto_str->name = NULL; +} + +/** + * ext4_fname_disk_to_usr() - converts a filename from disk space to user space + */ +int _ext4_fname_disk_to_usr(struct ext4_fname_crypto_ctx *ctx, + const struct ext4_str *iname, + struct ext4_str *oname) +{ + if (ctx == NULL) + return -EIO; + if (iname->len < 3) { + /*Check for . and .. */ + if (iname->name[0] == '.' && iname->name[iname->len-1] == '.') { + oname->name[0] = '.'; + oname->name[iname->len-1] = '.'; + oname->len = iname->len; + return oname->len; + } + } + if (ctx->has_valid_key) + return ext4_fname_decrypt(ctx, iname, oname); + else + return ext4_fname_hash(ctx, iname, oname); +} + +int ext4_fname_disk_to_usr(struct ext4_fname_crypto_ctx *ctx, + const struct ext4_dir_entry_2 *de, + struct ext4_str *oname) +{ + struct ext4_str iname = {.name = (unsigned char *) de->name, + .len = de->name_len }; + + return _ext4_fname_disk_to_usr(ctx, &iname, oname); +} + + +/** + * ext4_fname_usr_to_disk() - converts a filename from user space to disk space + */ +int ext4_fname_usr_to_disk(struct ext4_fname_crypto_ctx *ctx, + const struct qstr *iname, + struct ext4_str *oname) +{ + int res; + + if (ctx == NULL) + return -EIO; + if (iname->len < 3) { + /*Check for . and .. */ + if (iname->name[0] == '.' && + iname->name[iname->len-1] == '.') { + oname->name[0] = '.'; + oname->name[iname->len-1] = '.'; + oname->len = iname->len; + return oname->len; + } + } + if (ctx->has_valid_key) { + res = ext4_fname_encrypt(ctx, iname, oname); + return res; + } + /* Without a proper key, a user is not allowed to modify the filenames + * in a directory. Consequently, a user space name cannot be mapped to + * a disk-space name */ + return -EACCES; +} + +/* + * Calculate the htree hash from a filename from user space + */ +int ext4_fname_usr_to_hash(struct ext4_fname_crypto_ctx *ctx, + const struct qstr *iname, + struct dx_hash_info *hinfo) +{ + struct ext4_str tmp, tmp2; + int ret = 0; + + if (!ctx || !ctx->has_valid_key || + ((iname->name[0] == '.') && + ((iname->len == 1) || + ((iname->name[1] == '.') && (iname->len == 2))))) { + ext4fs_dirhash(iname->name, iname->len, hinfo); + return 0; + } + + /* First encrypt the plaintext name */ + ret = ext4_fname_crypto_alloc_buffer(ctx, iname->len, &tmp); + if (ret < 0) + return ret; + + ret = ext4_fname_encrypt(ctx, iname, &tmp); + if (ret < 0) + goto out; + + tmp2.len = (4 * ((EXT4_FNAME_CRYPTO_DIGEST_SIZE + 2) / 3)) + 1; + tmp2.name = kmalloc(tmp2.len + 1, GFP_KERNEL); + if (tmp2.name == NULL) { + ret = -ENOMEM; + goto out; + } + + ret = ext4_fname_hash(ctx, &tmp, &tmp2); + if (ret > 0) + ext4fs_dirhash(tmp2.name, tmp2.len, hinfo); + ext4_fname_crypto_free_buffer(&tmp2); +out: + ext4_fname_crypto_free_buffer(&tmp); + return ret; +} + +/** + * ext4_fname_disk_to_htree() - converts a filename from disk space to htree-access string + */ +int ext4_fname_disk_to_hash(struct ext4_fname_crypto_ctx *ctx, + const struct ext4_dir_entry_2 *de, + struct dx_hash_info *hinfo) +{ + struct ext4_str iname = {.name = (unsigned char *) de->name, + .len = de->name_len}; + struct ext4_str tmp; + int ret; + + if (!ctx || + ((iname.name[0] == '.') && + ((iname.len == 1) || + ((iname.name[1] == '.') && (iname.len == 2))))) { + ext4fs_dirhash(iname.name, iname.len, hinfo); + return 0; + } + + tmp.len = (4 * ((EXT4_FNAME_CRYPTO_DIGEST_SIZE + 2) / 3)) + 1; + tmp.name = kmalloc(tmp.len + 1, GFP_KERNEL); + if (tmp.name == NULL) + return -ENOMEM; + + ret = ext4_fname_hash(ctx, &iname, &tmp); + if (ret > 0) + ext4fs_dirhash(tmp.name, tmp.len, hinfo); + ext4_fname_crypto_free_buffer(&tmp); + return ret; +} diff --git a/fs/ext4/crypto_key.c b/fs/ext4/crypto_key.c new file mode 100644 index 000000000000..c8392af8abbb --- /dev/null +++ b/fs/ext4/crypto_key.c @@ -0,0 +1,165 @@ +/* + * linux/fs/ext4/crypto_key.c + * + * Copyright (C) 2015, Google, Inc. + * + * This contains encryption key functions for ext4 + * + * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015. + */ + +#include <keys/encrypted-type.h> +#include <keys/user-type.h> +#include <linux/random.h> +#include <linux/scatterlist.h> +#include <uapi/linux/keyctl.h> + +#include "ext4.h" +#include "xattr.h" + +static void derive_crypt_complete(struct crypto_async_request *req, int rc) +{ + struct ext4_completion_result *ecr = req->data; + + if (rc == -EINPROGRESS) + return; + + ecr->res = rc; + complete(&ecr->completion); +} + +/** + * ext4_derive_key_aes() - Derive a key using AES-128-ECB + * @deriving_key: Encryption key used for derivatio. + * @source_key: Source key to which to apply derivation. + * @derived_key: Derived key. + * + * Return: Zero on success; non-zero otherwise. + */ +static int ext4_derive_key_aes(char deriving_key[EXT4_AES_128_ECB_KEY_SIZE], + char source_key[EXT4_AES_256_XTS_KEY_SIZE], + char derived_key[EXT4_AES_256_XTS_KEY_SIZE]) +{ + int res = 0; + struct ablkcipher_request *req = NULL; + DECLARE_EXT4_COMPLETION_RESULT(ecr); + struct scatterlist src_sg, dst_sg; + struct crypto_ablkcipher *tfm = crypto_alloc_ablkcipher("ecb(aes)", 0, + 0); + + if (IS_ERR(tfm)) { + res = PTR_ERR(tfm); + tfm = NULL; + goto out; + } + crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY); + req = ablkcipher_request_alloc(tfm, GFP_NOFS); + if (!req) { + res = -ENOMEM; + goto out; + } + ablkcipher_request_set_callback(req, + CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + derive_crypt_complete, &ecr); + res = crypto_ablkcipher_setkey(tfm, deriving_key, + EXT4_AES_128_ECB_KEY_SIZE); + if (res < 0) + goto out; + sg_init_one(&src_sg, source_key, EXT4_AES_256_XTS_KEY_SIZE); + sg_init_one(&dst_sg, derived_key, EXT4_AES_256_XTS_KEY_SIZE); + ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, + EXT4_AES_256_XTS_KEY_SIZE, NULL); + res = crypto_ablkcipher_encrypt(req); + if (res == -EINPROGRESS || res == -EBUSY) { + BUG_ON(req->base.data != &ecr); + wait_for_completion(&ecr.completion); + res = ecr.res; + } + +out: + if (req) + ablkcipher_request_free(req); + if (tfm) + crypto_free_ablkcipher(tfm); + return res; +} + +/** + * ext4_generate_encryption_key() - generates an encryption key + * @inode: The inode to generate the encryption key for. + */ +int ext4_generate_encryption_key(struct inode *inode) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + struct ext4_encryption_key *crypt_key = &ei->i_encryption_key; + char full_key_descriptor[EXT4_KEY_DESC_PREFIX_SIZE + + (EXT4_KEY_DESCRIPTOR_SIZE * 2) + 1]; + struct key *keyring_key = NULL; + struct ext4_encryption_key *master_key; + struct ext4_encryption_context ctx; + struct user_key_payload *ukp; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, + &ctx, sizeof(ctx)); + + if (res != sizeof(ctx)) { + if (res > 0) + res = -EINVAL; + goto out; + } + res = 0; + + if (S_ISREG(inode->i_mode)) + crypt_key->mode = ctx.contents_encryption_mode; + else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) + crypt_key->mode = ctx.filenames_encryption_mode; + else { + printk(KERN_ERR "ext4 crypto: Unsupported inode type.\n"); + BUG(); + } + crypt_key->size = ext4_encryption_key_size(crypt_key->mode); + BUG_ON(!crypt_key->size); + if (DUMMY_ENCRYPTION_ENABLED(sbi)) { + memset(crypt_key->raw, 0x42, EXT4_AES_256_XTS_KEY_SIZE); + goto out; + } + memcpy(full_key_descriptor, EXT4_KEY_DESC_PREFIX, + EXT4_KEY_DESC_PREFIX_SIZE); + sprintf(full_key_descriptor + EXT4_KEY_DESC_PREFIX_SIZE, + "%*phN", EXT4_KEY_DESCRIPTOR_SIZE, + ctx.master_key_descriptor); + full_key_descriptor[EXT4_KEY_DESC_PREFIX_SIZE + + (2 * EXT4_KEY_DESCRIPTOR_SIZE)] = '\0'; + keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL); + if (IS_ERR(keyring_key)) { + res = PTR_ERR(keyring_key); + keyring_key = NULL; + goto out; + } + BUG_ON(keyring_key->type != &key_type_logon); + ukp = ((struct user_key_payload *)keyring_key->payload.data); + if (ukp->datalen != sizeof(struct ext4_encryption_key)) { + res = -EINVAL; + goto out; + } + master_key = (struct ext4_encryption_key *)ukp->data; + BUILD_BUG_ON(EXT4_AES_128_ECB_KEY_SIZE != + EXT4_KEY_DERIVATION_NONCE_SIZE); + BUG_ON(master_key->size != EXT4_AES_256_XTS_KEY_SIZE); + res = ext4_derive_key_aes(ctx.nonce, master_key->raw, crypt_key->raw); +out: + if (keyring_key) + key_put(keyring_key); + if (res < 0) + crypt_key->mode = EXT4_ENCRYPTION_MODE_INVALID; + return res; +} + +int ext4_has_encryption_key(struct inode *inode) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + struct ext4_encryption_key *crypt_key = &ei->i_encryption_key; + + return (crypt_key->mode != EXT4_ENCRYPTION_MODE_INVALID); +} diff --git a/fs/ext4/crypto_policy.c b/fs/ext4/crypto_policy.c new file mode 100644 index 000000000000..30eaf9e9864a --- /dev/null +++ b/fs/ext4/crypto_policy.c @@ -0,0 +1,194 @@ +/* + * linux/fs/ext4/crypto_policy.c + * + * Copyright (C) 2015, Google, Inc. + * + * This contains encryption policy functions for ext4 + * + * Written by Michael Halcrow, 2015. + */ + +#include <linux/random.h> +#include <linux/string.h> +#include <linux/types.h> + +#include "ext4.h" +#include "xattr.h" + +static int ext4_inode_has_encryption_context(struct inode *inode) +{ + int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, NULL, 0); + return (res > 0); +} + +/* + * check whether the policy is consistent with the encryption context + * for the inode + */ +static int ext4_is_encryption_context_consistent_with_policy( + struct inode *inode, const struct ext4_encryption_policy *policy) +{ + struct ext4_encryption_context ctx; + int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx, + sizeof(ctx)); + if (res != sizeof(ctx)) + return 0; + return (memcmp(ctx.master_key_descriptor, policy->master_key_descriptor, + EXT4_KEY_DESCRIPTOR_SIZE) == 0 && + (ctx.contents_encryption_mode == + policy->contents_encryption_mode) && + (ctx.filenames_encryption_mode == + policy->filenames_encryption_mode)); +} + +static int ext4_create_encryption_context_from_policy( + struct inode *inode, const struct ext4_encryption_policy *policy) +{ + struct ext4_encryption_context ctx; + int res = 0; + + ctx.format = EXT4_ENCRYPTION_CONTEXT_FORMAT_V1; + memcpy(ctx.master_key_descriptor, policy->master_key_descriptor, + EXT4_KEY_DESCRIPTOR_SIZE); + if (!ext4_valid_contents_enc_mode(policy->contents_encryption_mode)) { + printk(KERN_WARNING + "%s: Invalid contents encryption mode %d\n", __func__, + policy->contents_encryption_mode); + res = -EINVAL; + goto out; + } + if (!ext4_valid_filenames_enc_mode(policy->filenames_encryption_mode)) { + printk(KERN_WARNING + "%s: Invalid filenames encryption mode %d\n", __func__, + policy->filenames_encryption_mode); + res = -EINVAL; + goto out; + } + ctx.contents_encryption_mode = policy->contents_encryption_mode; + ctx.filenames_encryption_mode = policy->filenames_encryption_mode; + BUILD_BUG_ON(sizeof(ctx.nonce) != EXT4_KEY_DERIVATION_NONCE_SIZE); + get_random_bytes(ctx.nonce, EXT4_KEY_DERIVATION_NONCE_SIZE); + + res = ext4_xattr_set(inode, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx, + sizeof(ctx), 0); +out: + if (!res) + ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT); + return res; +} + +int ext4_process_policy(const struct ext4_encryption_policy *policy, + struct inode *inode) +{ + if (policy->version != 0) + return -EINVAL; + + if (!ext4_inode_has_encryption_context(inode)) { + if (!ext4_empty_dir(inode)) + return -ENOTEMPTY; + return ext4_create_encryption_context_from_policy(inode, + policy); + } + + if (ext4_is_encryption_context_consistent_with_policy(inode, policy)) + return 0; + + printk(KERN_WARNING "%s: Policy inconsistent with encryption context\n", + __func__); + return -EINVAL; +} + +int ext4_get_policy(struct inode *inode, struct ext4_encryption_policy *policy) +{ + struct ext4_encryption_context ctx; + + int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, + &ctx, sizeof(ctx)); + if (res != sizeof(ctx)) + return -ENOENT; + if (ctx.format != EXT4_ENCRYPTION_CONTEXT_FORMAT_V1) + return -EINVAL; + policy->version = 0; + policy->contents_encryption_mode = ctx.contents_encryption_mode; + policy->filenames_encryption_mode = ctx.filenames_encryption_mode; + memcpy(&policy->master_key_descriptor, ctx.master_key_descriptor, + EXT4_KEY_DESCRIPTOR_SIZE); + return 0; +} + +int ext4_is_child_context_consistent_with_parent(struct inode *parent, + struct inode *child) +{ + struct ext4_encryption_context parent_ctx, child_ctx; + int res; + + if ((parent == NULL) || (child == NULL)) { + pr_err("parent %p child %p\n", parent, child); + BUG_ON(1); + } + /* no restrictions if the parent directory is not encrypted */ + if (!ext4_encrypted_inode(parent)) + return 1; + res = ext4_xattr_get(parent, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, + &parent_ctx, sizeof(parent_ctx)); + if (res != sizeof(parent_ctx)) + return 0; + /* if the child directory is not encrypted, this is always a problem */ + if (!ext4_encrypted_inode(child)) + return 0; + res = ext4_xattr_get(child, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, + &child_ctx, sizeof(child_ctx)); + if (res != sizeof(child_ctx)) + return 0; + return (memcmp(parent_ctx.master_key_descriptor, + child_ctx.master_key_descriptor, + EXT4_KEY_DESCRIPTOR_SIZE) == 0 && + (parent_ctx.contents_encryption_mode == + child_ctx.contents_encryption_mode) && + (parent_ctx.filenames_encryption_mode == + child_ctx.filenames_encryption_mode)); +} + +/** + * ext4_inherit_context() - Sets a child context from its parent + * @parent: Parent inode from which the context is inherited. + * @child: Child inode that inherits the context from @parent. + * + * Return: Zero on success, non-zero otherwise + */ +int ext4_inherit_context(struct inode *parent, struct inode *child) +{ + struct ext4_encryption_context ctx; + int res = ext4_xattr_get(parent, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, + &ctx, sizeof(ctx)); + + if (res != sizeof(ctx)) { + if (DUMMY_ENCRYPTION_ENABLED(EXT4_SB(parent->i_sb))) { + ctx.format = EXT4_ENCRYPTION_CONTEXT_FORMAT_V1; + ctx.contents_encryption_mode = + EXT4_ENCRYPTION_MODE_AES_256_XTS; + ctx.filenames_encryption_mode = + EXT4_ENCRYPTION_MODE_AES_256_CTS; + memset(ctx.master_key_descriptor, 0x42, + EXT4_KEY_DESCRIPTOR_SIZE); + res = 0; + } else { + goto out; + } + } + get_random_bytes(ctx.nonce, EXT4_KEY_DERIVATION_NONCE_SIZE); + res = ext4_xattr_set(child, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx, + sizeof(ctx), 0); +out: + if (!res) + ext4_set_inode_flag(child, EXT4_INODE_ENCRYPT); + return res; +} diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index c24143ea9c08..61db51a5ce4c 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -22,10 +22,8 @@ */ #include <linux/fs.h> -#include <linux/jbd2.h> #include <linux/buffer_head.h> #include <linux/slab.h> -#include <linux/rbtree.h> #include "ext4.h" #include "xattr.h" @@ -110,7 +108,10 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) int err; struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; + struct buffer_head *bh = NULL; int dir_has_error = 0; + struct ext4_fname_crypto_ctx *enc_ctx = NULL; + struct ext4_str fname_crypto_str = {.name = NULL, .len = 0}; if (is_dx_dir(inode)) { err = ext4_dx_readdir(file, ctx); @@ -127,17 +128,28 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) if (ext4_has_inline_data(inode)) { int has_inline_data = 1; - int ret = ext4_read_inline_dir(file, ctx, + err = ext4_read_inline_dir(file, ctx, &has_inline_data); if (has_inline_data) - return ret; + return err; + } + + enc_ctx = ext4_get_fname_crypto_ctx(inode, EXT4_NAME_LEN); + if (IS_ERR(enc_ctx)) + return PTR_ERR(enc_ctx); + if (enc_ctx) { + err = ext4_fname_crypto_alloc_buffer(enc_ctx, EXT4_NAME_LEN, + &fname_crypto_str); + if (err < 0) { + ext4_put_fname_crypto_ctx(&enc_ctx); + return err; + } } offset = ctx->pos & (sb->s_blocksize - 1); while (ctx->pos < inode->i_size) { struct ext4_map_blocks map; - struct buffer_head *bh = NULL; map.m_lblk = ctx->pos >> EXT4_BLOCK_SIZE_BITS(sb); map.m_len = 1; @@ -180,6 +192,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) (unsigned long long)ctx->pos); ctx->pos += sb->s_blocksize - offset; brelse(bh); + bh = NULL; continue; } set_buffer_verified(bh); @@ -226,25 +239,44 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); if (le32_to_cpu(de->inode)) { - if (!dir_emit(ctx, de->name, - de->name_len, - le32_to_cpu(de->inode), - get_dtype(sb, de->file_type))) { - brelse(bh); - return 0; + if (enc_ctx == NULL) { + /* Directory is not encrypted */ + if (!dir_emit(ctx, de->name, + de->name_len, + le32_to_cpu(de->inode), + get_dtype(sb, de->file_type))) + goto done; + } else { + /* Directory is encrypted */ + err = ext4_fname_disk_to_usr(enc_ctx, + de, &fname_crypto_str); + if (err < 0) + goto errout; + if (!dir_emit(ctx, + fname_crypto_str.name, err, + le32_to_cpu(de->inode), + get_dtype(sb, de->file_type))) + goto done; } } ctx->pos += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); } - offset = 0; + if ((ctx->pos < inode->i_size) && !dir_relax(inode)) + goto done; brelse(bh); - if (ctx->pos < inode->i_size) { - if (!dir_relax(inode)) - return 0; - } + bh = NULL; + offset = 0; } - return 0; +done: + err = 0; +errout: +#ifdef CONFIG_EXT4_FS_ENCRYPTION + ext4_put_fname_crypto_ctx(&enc_ctx); + ext4_fname_crypto_free_buffer(&fname_crypto_str); +#endif + brelse(bh); + return err; } static inline int is_32bit_api(void) @@ -384,10 +416,15 @@ void ext4_htree_free_dir_info(struct dir_private_info *p) /* * Given a directory entry, enter it into the fname rb tree. + * + * When filename encryption is enabled, the dirent will hold the + * encrypted filename, while the htree will hold decrypted filename. + * The decrypted filename is passed in via ent_name. parameter. */ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, __u32 minor_hash, - struct ext4_dir_entry_2 *dirent) + struct ext4_dir_entry_2 *dirent, + struct ext4_str *ent_name) { struct rb_node **p, *parent = NULL; struct fname *fname, *new_fn; @@ -398,17 +435,17 @@ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, p = &info->root.rb_node; /* Create and allocate the fname structure */ - len = sizeof(struct fname) + dirent->name_len + 1; + len = sizeof(struct fname) + ent_name->len + 1; new_fn = kzalloc(len, GFP_KERNEL); if (!new_fn) return -ENOMEM; new_fn->hash = hash; new_fn->minor_hash = minor_hash; new_fn->inode = le32_to_cpu(dirent->inode); - new_fn->name_len = dirent->name_len; + new_fn->name_len = ent_name->len; new_fn->file_type = dirent->file_type; - memcpy(new_fn->name, dirent->name, dirent->name_len); - new_fn->name[dirent->name_len] = 0; + memcpy(new_fn->name, ent_name->name, ent_name->len); + new_fn->name[ent_name->len] = 0; while (*p) { parent = *p; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index f63c3d5805c4..ef267adce19a 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -422,7 +422,7 @@ enum { EXT4_INODE_DIRTY = 8, EXT4_INODE_COMPRBLK = 9, /* One or more compressed clusters */ EXT4_INODE_NOCOMPR = 10, /* Don't compress */ - EXT4_INODE_ENCRYPT = 11, /* Compression error */ + EXT4_INODE_ENCRYPT = 11, /* Encrypted file */ /* End compression flags --- maybe not all used */ EXT4_INODE_INDEX = 12, /* hash-indexed directory */ EXT4_INODE_IMAGIC = 13, /* AFS directory */ @@ -582,6 +582,15 @@ enum { #define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER 0x0010 #define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER 0x0020 +/* Encryption algorithms */ +#define EXT4_ENCRYPTION_MODE_INVALID 0 +#define EXT4_ENCRYPTION_MODE_AES_256_XTS 1 +#define EXT4_ENCRYPTION_MODE_AES_256_GCM 2 +#define EXT4_ENCRYPTION_MODE_AES_256_CBC 3 +#define EXT4_ENCRYPTION_MODE_AES_256_CTS 4 + +#include "ext4_crypto.h" + /* * ioctl commands */ @@ -603,6 +612,9 @@ enum { #define EXT4_IOC_RESIZE_FS _IOW('f', 16, __u64) #define EXT4_IOC_SWAP_BOOT _IO('f', 17) #define EXT4_IOC_PRECACHE_EXTENTS _IO('f', 18) +#define EXT4_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct ext4_encryption_policy) +#define EXT4_IOC_GET_ENCRYPTION_PWSALT _IOW('f', 20, __u8[16]) +#define EXT4_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct ext4_encryption_policy) #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* @@ -939,6 +951,11 @@ struct ext4_inode_info { /* Precomputed uuid+inum+igen checksum for seeding inode checksums */ __u32 i_csum_seed; + +#ifdef CONFIG_EXT4_FS_ENCRYPTION + /* Encryption params */ + struct ext4_encryption_key i_encryption_key; +#endif }; /* @@ -1142,7 +1159,8 @@ struct ext4_super_block { __le32 s_raid_stripe_width; /* blocks on all data disks (N*stride)*/ __u8 s_log_groups_per_flex; /* FLEX_BG group size */ __u8 s_checksum_type; /* metadata checksum algorithm used */ - __le16 s_reserved_pad; + __u8 s_encryption_level; /* versioning level for encryption */ + __u8 s_reserved_pad; /* Padding to next 32bits */ __le64 s_kbytes_written; /* nr of lifetime kilobytes written */ __le32 s_snapshot_inum; /* Inode number of active snapshot */ __le32 s_snapshot_id; /* sequential ID of active snapshot */ @@ -1169,7 +1187,9 @@ struct ext4_super_block { __le32 s_overhead_clusters; /* overhead blocks/clusters in fs */ __le32 s_backup_bgs[2]; /* groups with sparse_super2 SBs */ __u8 s_encrypt_algos[4]; /* Encryption algorithms in use */ - __le32 s_reserved[105]; /* Padding to the end of the block */ + __u8 s_encrypt_pw_salt[16]; /* Salt used for string2key algorithm */ + __le32 s_lpf_ino; /* Location of the lost+found inode */ + __le32 s_reserved[100]; /* Padding to the end of the block */ __le32 s_checksum; /* crc32c(superblock) */ }; @@ -1180,8 +1200,16 @@ struct ext4_super_block { /* * run-time mount flags */ -#define EXT4_MF_MNTDIR_SAMPLED 0x0001 -#define EXT4_MF_FS_ABORTED 0x0002 /* Fatal error detected */ +#define EXT4_MF_MNTDIR_SAMPLED 0x0001 +#define EXT4_MF_FS_ABORTED 0x0002 /* Fatal error detected */ +#define EXT4_MF_TEST_DUMMY_ENCRYPTION 0x0004 + +#ifdef CONFIG_EXT4_FS_ENCRYPTION +#define DUMMY_ENCRYPTION_ENABLED(sbi) (unlikely((sbi)->s_mount_flags & \ + EXT4_MF_TEST_DUMMY_ENCRYPTION)) +#else +#define DUMMY_ENCRYPTION_ENABLED(sbi) (0) +#endif /* Number of quota types we support */ #define EXT4_MAXQUOTAS 2 @@ -1351,6 +1379,12 @@ struct ext4_sb_info { struct ratelimit_state s_err_ratelimit_state; struct ratelimit_state s_warning_ratelimit_state; struct ratelimit_state s_msg_ratelimit_state; + +#ifdef CONFIG_EXT4_FS_ENCRYPTION + /* Encryption */ + uint32_t s_file_encryption_mode; + uint32_t s_dir_encryption_mode; +#endif }; static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb) @@ -1466,6 +1500,18 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) #define EXT4_SB(sb) (sb) #endif +/* + * Returns true if the inode is inode is encrypted + */ +static inline int ext4_encrypted_inode(struct inode *inode) +{ +#ifdef CONFIG_EXT4_FS_ENCRYPTION + return ext4_test_inode_flag(inode, EXT4_INODE_ENCRYPT); +#else + return 0; +#endif +} + #define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime /* @@ -1575,8 +1621,9 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) EXT4_FEATURE_INCOMPAT_EXTENTS| \ EXT4_FEATURE_INCOMPAT_64BIT| \ EXT4_FEATURE_INCOMPAT_FLEX_BG| \ - EXT4_FEATURE_INCOMPAT_MMP | \ - EXT4_FEATURE_INCOMPAT_INLINE_DATA) + EXT4_FEATURE_INCOMPAT_MMP | \ + EXT4_FEATURE_INCOMPAT_INLINE_DATA | \ + EXT4_FEATURE_INCOMPAT_ENCRYPT) #define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \ EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \ @@ -2001,6 +2048,99 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb, struct ext4_group_desc *gdp); ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); +/* crypto_policy.c */ +int ext4_is_child_context_consistent_with_parent(struct inode *parent, + struct inode *child); +int ext4_inherit_context(struct inode *parent, struct inode *child); +void ext4_to_hex(char *dst, char *src, size_t src_size); +int ext4_process_policy(const struct ext4_encryption_policy *policy, + struct inode *inode); +int ext4_get_policy(struct inode *inode, + struct ext4_encryption_policy *policy); + +/* crypto.c */ +bool ext4_valid_contents_enc_mode(uint32_t mode); +uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size); +extern struct workqueue_struct *ext4_read_workqueue; +struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode); +void ext4_release_crypto_ctx(struct ext4_crypto_ctx *ctx); +void ext4_restore_control_page(struct page *data_page); +struct page *ext4_encrypt(struct inode *inode, + struct page *plaintext_page); +int ext4_decrypt(struct ext4_crypto_ctx *ctx, struct page *page); +int ext4_decrypt_one(struct inode *inode, struct page *page); +int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex); + +#ifdef CONFIG_EXT4_FS_ENCRYPTION +int ext4_init_crypto(void); +void ext4_exit_crypto(void); +static inline int ext4_sb_has_crypto(struct super_block *sb) +{ + return EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT); +} +#else +static inline int ext4_init_crypto(void) { return 0; } +static inline void ext4_exit_crypto(void) { } +static inline int ext4_sb_has_crypto(struct super_block *sb) +{ + return 0; +} +#endif + +/* crypto_fname.c */ +bool ext4_valid_filenames_enc_mode(uint32_t mode); +u32 ext4_fname_crypto_round_up(u32 size, u32 blksize); +int ext4_fname_crypto_alloc_buffer(struct ext4_fname_crypto_ctx *ctx, + u32 ilen, struct ext4_str *crypto_str); +int _ext4_fname_disk_to_usr(struct ext4_fname_crypto_ctx *ctx, + const struct ext4_str *iname, + struct ext4_str *oname); +int ext4_fname_disk_to_usr(struct ext4_fname_crypto_ctx *ctx, + const struct ext4_dir_entry_2 *de, + struct ext4_str *oname); +int ext4_fname_usr_to_disk(struct ext4_fname_crypto_ctx *ctx, + const struct qstr *iname, + struct ext4_str *oname); +int ext4_fname_usr_to_hash(struct ext4_fname_crypto_ctx *ctx, + const struct qstr *iname, + struct dx_hash_info *hinfo); +int ext4_fname_disk_to_hash(struct ext4_fname_crypto_ctx *ctx, + const struct ext4_dir_entry_2 *de, + struct dx_hash_info *hinfo); +int ext4_fname_crypto_namelen_on_disk(struct ext4_fname_crypto_ctx *ctx, + u32 namelen); + +#ifdef CONFIG_EXT4_FS_ENCRYPTION +void ext4_put_fname_crypto_ctx(struct ext4_fname_crypto_ctx **ctx); +struct ext4_fname_crypto_ctx *ext4_get_fname_crypto_ctx(struct inode *inode, + u32 max_len); +void ext4_fname_crypto_free_buffer(struct ext4_str *crypto_str); +#else +static inline +void ext4_put_fname_crypto_ctx(struct ext4_fname_crypto_ctx **ctx) { } +static inline +struct ext4_fname_crypto_ctx *ext4_get_fname_crypto_ctx(struct inode *inode, + u32 max_len) +{ + return NULL; +} +static inline void ext4_fname_crypto_free_buffer(struct ext4_str *p) { } +#endif + + +/* crypto_key.c */ +int ext4_generate_encryption_key(struct inode *inode); + +#ifdef CONFIG_EXT4_FS_ENCRYPTION +int ext4_has_encryption_key(struct inode *inode); +#else +static inline int ext4_has_encryption_key(struct inode *inode) +{ + return 0; +} +#endif + + /* dir.c */ extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *, struct file *, @@ -2011,17 +2151,20 @@ extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *, unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \ (de), (bh), (buf), (size), (offset))) extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, - __u32 minor_hash, - struct ext4_dir_entry_2 *dirent); + __u32 minor_hash, + struct ext4_dir_entry_2 *dirent, + struct ext4_str *ent_name); extern void ext4_htree_free_dir_info(struct dir_private_info *p); extern int ext4_find_dest_de(struct inode *dir, struct inode *inode, struct buffer_head *bh, void *buf, int buf_size, const char *name, int namelen, struct ext4_dir_entry_2 **dest_de); -void ext4_insert_dentry(struct inode *inode, +int ext4_insert_dentry(struct inode *dir, + struct inode *inode, struct ext4_dir_entry_2 *de, int buf_size, + const struct qstr *iname, const char *name, int namelen); static inline void ext4_update_dx_flag(struct inode *inode) { @@ -2099,6 +2242,7 @@ extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, extern int ext4_trim_fs(struct super_block *, struct fstrim_range *); /* inode.c */ +int ext4_inode_is_fast_symlink(struct inode *inode); struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int); struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int); int ext4_get_block_write(struct inode *inode, sector_t iblock, @@ -2152,8 +2296,8 @@ extern void ext4_da_update_reserve_space(struct inode *inode, /* indirect.c */ extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags); -extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, - struct iov_iter *iter, loff_t offset); +extern ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter, + loff_t offset); extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock); extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks); extern void ext4_ind_truncate(handle_t *, struct inode *inode); @@ -2189,6 +2333,7 @@ extern int ext4_generic_delete_entry(handle_t *handle, void *entry_buf, int buf_size, int csum_size); +extern int ext4_empty_dir(struct inode *inode); /* resize.c */ extern int ext4_group_add(struct super_block *sb, @@ -2593,7 +2738,6 @@ extern const struct file_operations ext4_dir_operations; /* file.c */ extern const struct inode_operations ext4_file_inode_operations; extern const struct file_operations ext4_file_operations; -extern const struct file_operations ext4_dax_file_operations; extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin); /* inline.c */ @@ -2699,6 +2843,10 @@ static inline void ext4_set_de_type(struct super_block *sb, de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT]; } +/* readpages.c */ +extern int ext4_mpage_readpages(struct address_space *mapping, + struct list_head *pages, struct page *page, + unsigned nr_pages); /* symlink.c */ extern const struct inode_operations ext4_symlink_inode_operations; diff --git a/fs/ext4/ext4_crypto.h b/fs/ext4/ext4_crypto.h new file mode 100644 index 000000000000..c2ba35a914b6 --- /dev/null +++ b/fs/ext4/ext4_crypto.h @@ -0,0 +1,147 @@ +/* + * linux/fs/ext4/ext4_crypto.h + * + * Copyright (C) 2015, Google, Inc. + * + * This contains encryption header content for ext4 + * + * Written by Michael Halcrow, 2015. + */ + +#ifndef _EXT4_CRYPTO_H +#define _EXT4_CRYPTO_H + +#include <linux/fs.h> + +#define EXT4_KEY_DESCRIPTOR_SIZE 8 + +/* Policy provided via an ioctl on the topmost directory */ +struct ext4_encryption_policy { + char version; + char contents_encryption_mode; + char filenames_encryption_mode; + char master_key_descriptor[EXT4_KEY_DESCRIPTOR_SIZE]; +} __attribute__((__packed__)); + +#define EXT4_ENCRYPTION_CONTEXT_FORMAT_V1 1 +#define EXT4_KEY_DERIVATION_NONCE_SIZE 16 + +/** + * Encryption context for inode + * + * Protector format: + * 1 byte: Protector format (1 = this version) + * 1 byte: File contents encryption mode + * 1 byte: File names encryption mode + * 1 byte: Reserved + * 8 bytes: Master Key descriptor + * 16 bytes: Encryption Key derivation nonce + */ +struct ext4_encryption_context { + char format; + char contents_encryption_mode; + char filenames_encryption_mode; + char reserved; + char master_key_descriptor[EXT4_KEY_DESCRIPTOR_SIZE]; + char nonce[EXT4_KEY_DERIVATION_NONCE_SIZE]; +} __attribute__((__packed__)); + +/* Encryption parameters */ +#define EXT4_XTS_TWEAK_SIZE 16 +#define EXT4_AES_128_ECB_KEY_SIZE 16 +#define EXT4_AES_256_GCM_KEY_SIZE 32 +#define EXT4_AES_256_CBC_KEY_SIZE 32 +#define EXT4_AES_256_CTS_KEY_SIZE 32 +#define EXT4_AES_256_XTS_KEY_SIZE 64 +#define EXT4_MAX_KEY_SIZE 64 + +#define EXT4_KEY_DESC_PREFIX "ext4:" +#define EXT4_KEY_DESC_PREFIX_SIZE 5 + +struct ext4_encryption_key { + uint32_t mode; + char raw[EXT4_MAX_KEY_SIZE]; + uint32_t size; +}; + +#define EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL 0x00000001 +#define EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL 0x00000002 + +struct ext4_crypto_ctx { + struct crypto_tfm *tfm; /* Crypto API context */ + struct page *bounce_page; /* Ciphertext page on write path */ + struct page *control_page; /* Original page on write path */ + struct bio *bio; /* The bio for this context */ + struct work_struct work; /* Work queue for read complete path */ + struct list_head free_list; /* Free list */ + int flags; /* Flags */ + int mode; /* Encryption mode for tfm */ +}; + +struct ext4_completion_result { + struct completion completion; + int res; +}; + +#define DECLARE_EXT4_COMPLETION_RESULT(ecr) \ + struct ext4_completion_result ecr = { \ + COMPLETION_INITIALIZER((ecr).completion), 0 } + +static inline int ext4_encryption_key_size(int mode) +{ + switch (mode) { + case EXT4_ENCRYPTION_MODE_AES_256_XTS: + return EXT4_AES_256_XTS_KEY_SIZE; + case EXT4_ENCRYPTION_MODE_AES_256_GCM: + return EXT4_AES_256_GCM_KEY_SIZE; + case EXT4_ENCRYPTION_MODE_AES_256_CBC: + return EXT4_AES_256_CBC_KEY_SIZE; + case EXT4_ENCRYPTION_MODE_AES_256_CTS: + return EXT4_AES_256_CTS_KEY_SIZE; + default: + BUG(); + } + return 0; +} + +#define EXT4_FNAME_NUM_SCATTER_ENTRIES 4 +#define EXT4_CRYPTO_BLOCK_SIZE 16 +#define EXT4_FNAME_CRYPTO_DIGEST_SIZE 32 + +struct ext4_str { + unsigned char *name; + u32 len; +}; + +struct ext4_fname_crypto_ctx { + u32 lim; + char tmp_buf[EXT4_CRYPTO_BLOCK_SIZE]; + struct crypto_ablkcipher *ctfm; + struct crypto_hash *htfm; + struct page *workpage; + struct ext4_encryption_key key; + unsigned has_valid_key : 1; + unsigned ctfm_key_is_ready : 1; +}; + +/** + * For encrypted symlinks, the ciphertext length is stored at the beginning + * of the string in little-endian format. + */ +struct ext4_encrypted_symlink_data { + __le16 len; + char encrypted_path[1]; +} __attribute__((__packed__)); + +/** + * This function is used to calculate the disk space required to + * store a filename of length l in encrypted symlink format. + */ +static inline u32 encrypted_symlink_data_len(u32 l) +{ + if (l < EXT4_CRYPTO_BLOCK_SIZE) + l = EXT4_CRYPTO_BLOCK_SIZE; + return (l + sizeof(struct ext4_encrypted_symlink_data) - 1); +} + +#endif /* _EXT4_CRYPTO_H */ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index bed43081720f..973816bfe4a9 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1717,12 +1717,6 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, { unsigned short ext1_ee_len, ext2_ee_len; - /* - * Make sure that both extents are initialized. We don't merge - * unwritten extents so that we can be sure that end_io code has - * the extent that was written properly split out and conversion to - * initialized is trivial. - */ if (ext4_ext_is_unwritten(ex1) != ext4_ext_is_unwritten(ex2)) return 0; @@ -3128,6 +3122,9 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex) ee_len = ext4_ext_get_actual_len(ex); ee_pblock = ext4_ext_pblock(ex); + if (ext4_encrypted_inode(inode)) + return ext4_encrypted_zeroout(inode, ex); + ret = sb_issue_zeroout(inode->i_sb, ee_pblock, ee_len, GFP_NOFS); if (ret > 0) ret = 0; @@ -4535,19 +4532,7 @@ got_allocated_blocks: */ reserved_clusters = get_reserved_cluster_alloc(inode, map->m_lblk, allocated); - if (map_from_cluster) { - if (reserved_clusters) { - /* - * We have clusters reserved for this range. - * But since we are not doing actual allocation - * and are simply using blocks from previously - * allocated cluster, we should release the - * reservation and not claim quota. - */ - ext4_da_update_reserve_space(inode, - reserved_clusters, 0); - } - } else { + if (!map_from_cluster) { BUG_ON(allocated_clusters < reserved_clusters); if (reserved_clusters < allocated_clusters) { struct ext4_inode_info *ei = EXT4_I(inode); @@ -4803,12 +4788,6 @@ static long ext4_zero_range(struct file *file, loff_t offset, else max_blocks -= lblk; - flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT | - EXT4_GET_BLOCKS_CONVERT_UNWRITTEN | - EXT4_EX_NOCACHE; - if (mode & FALLOC_FL_KEEP_SIZE) - flags |= EXT4_GET_BLOCKS_KEEP_SIZE; - mutex_lock(&inode->i_mutex); /* @@ -4825,15 +4804,28 @@ static long ext4_zero_range(struct file *file, loff_t offset, ret = inode_newsize_ok(inode, new_size); if (ret) goto out_mutex; - /* - * If we have a partial block after EOF we have to allocate - * the entire block. - */ - if (partial_end) - max_blocks += 1; } + flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT; + if (mode & FALLOC_FL_KEEP_SIZE) + flags |= EXT4_GET_BLOCKS_KEEP_SIZE; + + /* Preallocate the range including the unaligned edges */ + if (partial_begin || partial_end) { + ret = ext4_alloc_file_blocks(file, + round_down(offset, 1 << blkbits) >> blkbits, + (round_up((offset + len), 1 << blkbits) - + round_down(offset, 1 << blkbits)) >> blkbits, + new_size, flags, mode); + if (ret) + goto out_mutex; + + } + + /* Zero range excluding the unaligned edges */ if (max_blocks > 0) { + flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN | + EXT4_EX_NOCACHE); /* Now release the pages and zero block aligned part of pages*/ truncate_pagecache_range(inode, start, end - 1); @@ -4847,19 +4839,6 @@ static long ext4_zero_range(struct file *file, loff_t offset, flags, mode); if (ret) goto out_dio; - /* - * Remove entire range from the extent status tree. - * - * ext4_es_remove_extent(inode, lblk, max_blocks) is - * NOT sufficient. I'm not sure why this is the case, - * but let's be conservative and remove the extent - * status tree for the entire inode. There should be - * no outstanding delalloc extents thanks to the - * filemap_write_and_wait_range() call above. - */ - ret = ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); - if (ret) - goto out_dio; } if (!partial_begin && !partial_end) goto out_dio; @@ -4922,6 +4901,20 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) ext4_lblk_t lblk; unsigned int blkbits = inode->i_blkbits; + /* + * Encrypted inodes can't handle collapse range or insert + * range since we would need to re-encrypt blocks with a + * different IV or XTS tweak (which are based on the logical + * block number). + * + * XXX It's not clear why zero range isn't working, but we'll + * leave it disabled for encrypted inodes for now. This is a + * bug we should fix.... + */ + if (ext4_encrypted_inode(inode) && + (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE))) + return -EOPNOTSUPP; + /* Return error if mode is not supported */ if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE)) diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index e04d45733976..d33d5a6852b9 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -9,12 +9,10 @@ * * Ext4 extents status tree core functions. */ -#include <linux/rbtree.h> #include <linux/list_sort.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include "ext4.h" -#include "extents_status.h" #include <trace/events/ext4.h> diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 33a09da16c9c..0613c256c344 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -20,12 +20,11 @@ #include <linux/time.h> #include <linux/fs.h> -#include <linux/jbd2.h> #include <linux/mount.h> #include <linux/path.h> -#include <linux/aio.h> #include <linux/quotaops.h> #include <linux/pagevec.h> +#include <linux/uio.h> #include "ext4.h" #include "ext4_jbd2.h" #include "xattr.h" @@ -95,11 +94,9 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = file_inode(iocb->ki_filp); struct mutex *aio_mutex = NULL; struct blk_plug plug; - int o_direct = io_is_direct(file); + int o_direct = iocb->ki_flags & IOCB_DIRECT; int overwrite = 0; - size_t length = iov_iter_count(from); ssize_t ret; - loff_t pos = iocb->ki_pos; /* * Unaligned direct AIO must be serialized; see comment above @@ -108,16 +105,17 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (o_direct && ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) && !is_sync_kiocb(iocb) && - (file->f_flags & O_APPEND || - ext4_unaligned_aio(inode, from, pos))) { + (iocb->ki_flags & IOCB_APPEND || + ext4_unaligned_aio(inode, from, iocb->ki_pos))) { aio_mutex = ext4_aio_mutex(inode); mutex_lock(aio_mutex); ext4_unwritten_wait(inode); } mutex_lock(&inode->i_mutex); - if (file->f_flags & O_APPEND) - iocb->ki_pos = pos = i_size_read(inode); + ret = generic_write_checks(iocb, from); + if (ret <= 0) + goto out; /* * If we have encountered a bitmap-format file, the size limit @@ -126,22 +124,19 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - if ((pos > sbi->s_bitmap_maxbytes) || - (pos == sbi->s_bitmap_maxbytes && length > 0)) { - mutex_unlock(&inode->i_mutex); + if (iocb->ki_pos >= sbi->s_bitmap_maxbytes) { ret = -EFBIG; - goto errout; + goto out; } - - if (pos + length > sbi->s_bitmap_maxbytes) - iov_iter_truncate(from, sbi->s_bitmap_maxbytes - pos); + iov_iter_truncate(from, sbi->s_bitmap_maxbytes - iocb->ki_pos); } iocb->private = &overwrite; if (o_direct) { + size_t length = iov_iter_count(from); + loff_t pos = iocb->ki_pos; blk_start_plug(&plug); - /* check whether we do a DIO overwrite or not */ if (ext4_should_dioread_nolock(inode) && !aio_mutex && !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) { @@ -185,7 +180,12 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (o_direct) blk_finish_plug(&plug); -errout: + if (aio_mutex) + mutex_unlock(aio_mutex); + return ret; + +out: + mutex_unlock(&inode->i_mutex); if (aio_mutex) mutex_unlock(aio_mutex); return ret; @@ -206,6 +206,7 @@ static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) static const struct vm_operations_struct ext4_dax_vm_ops = { .fault = ext4_dax_fault, .page_mkwrite = ext4_dax_mkwrite, + .pfn_mkwrite = dax_pfn_mkwrite, }; #else #define ext4_dax_vm_ops ext4_file_vm_ops @@ -219,6 +220,13 @@ static const struct vm_operations_struct ext4_file_vm_ops = { static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) { + struct inode *inode = file->f_mapping->host; + + if (ext4_encrypted_inode(inode)) { + int err = ext4_generate_encryption_key(inode); + if (err) + return 0; + } file_accessed(file); if (IS_DAX(file_inode(file))) { vma->vm_ops = &ext4_dax_vm_ops; @@ -236,6 +244,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp) struct vfsmount *mnt = filp->f_path.mnt; struct path path; char buf[64], *cp; + int ret; if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) && !(sb->s_flags & MS_RDONLY))) { @@ -274,11 +283,17 @@ static int ext4_file_open(struct inode * inode, struct file * filp) * writing and the journal is present */ if (filp->f_mode & FMODE_WRITE) { - int ret = ext4_inode_attach_jinode(inode); + ret = ext4_inode_attach_jinode(inode); if (ret < 0) return ret; } - return dquot_file_open(inode, filp); + ret = dquot_file_open(inode, filp); + if (!ret && ext4_encrypted_inode(inode)) { + ret = ext4_generate_encryption_key(inode); + if (ret) + ret = -EACCES; + } + return ret; } /* @@ -607,8 +622,6 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int whence) const struct file_operations ext4_file_operations = { .llseek = ext4_llseek, - .read = new_sync_read, - .write = new_sync_write, .read_iter = generic_file_read_iter, .write_iter = ext4_file_write_iter, .unlocked_ioctl = ext4_ioctl, @@ -624,26 +637,6 @@ const struct file_operations ext4_file_operations = { .fallocate = ext4_fallocate, }; -#ifdef CONFIG_FS_DAX -const struct file_operations ext4_dax_file_operations = { - .llseek = ext4_llseek, - .read = new_sync_read, - .write = new_sync_write, - .read_iter = generic_file_read_iter, - .write_iter = ext4_file_write_iter, - .unlocked_ioctl = ext4_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = ext4_compat_ioctl, -#endif - .mmap = ext4_file_mmap, - .open = ext4_file_open, - .release = ext4_release_file, - .fsync = ext4_sync_file, - /* Splice not yet supported with DAX */ - .fallocate = ext4_fallocate, -}; -#endif - const struct inode_operations ext4_file_inode_operations = { .setattr = ext4_setattr, .getattr = ext4_getattr, diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index a8bc47f75fa0..e9d632e9aa4b 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -26,7 +26,6 @@ #include <linux/fs.h> #include <linux/sched.h> #include <linux/writeback.h> -#include <linux/jbd2.h> #include <linux/blkdev.h> #include "ext4.h" diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c index 3d586f02883e..e026aa941fd5 100644 --- a/fs/ext4/hash.c +++ b/fs/ext4/hash.c @@ -10,7 +10,6 @@ */ #include <linux/fs.h> -#include <linux/jbd2.h> #include <linux/cryptohash.h> #include "ext4.h" diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index ac644c31ca67..2cf18a2d5c72 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -14,7 +14,6 @@ #include <linux/time.h> #include <linux/fs.h> -#include <linux/jbd2.h> #include <linux/stat.h> #include <linux/string.h> #include <linux/quotaops.h> @@ -997,6 +996,12 @@ got: ei->i_block_group = group; ei->i_last_alloc_group = ~0; + /* If the directory encrypted, then we should encrypt the inode. */ + if ((S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode)) && + (ext4_encrypted_inode(dir) || + DUMMY_ENCRYPTION_ENABLED(sbi))) + ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT); + ext4_set_inode_flags(inode); if (IS_DIRSYNC(inode)) ext4_handle_sync(handle); @@ -1029,11 +1034,28 @@ got: ext4_set_inode_state(inode, EXT4_STATE_NEW); ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize; - +#ifdef CONFIG_EXT4_FS_ENCRYPTION + if ((sbi->s_file_encryption_mode == EXT4_ENCRYPTION_MODE_INVALID) && + (sbi->s_dir_encryption_mode == EXT4_ENCRYPTION_MODE_INVALID)) { + ei->i_inline_off = 0; + if (EXT4_HAS_INCOMPAT_FEATURE(sb, + EXT4_FEATURE_INCOMPAT_INLINE_DATA)) + ext4_set_inode_state(inode, + EXT4_STATE_MAY_INLINE_DATA); + } else { + /* Inline data and encryption are incompatible + * We turn off inline data since encryption is enabled */ + ei->i_inline_off = 1; + if (EXT4_HAS_INCOMPAT_FEATURE(sb, + EXT4_FEATURE_INCOMPAT_INLINE_DATA)) + ext4_clear_inode_state(inode, + EXT4_STATE_MAY_INLINE_DATA); + } +#else ei->i_inline_off = 0; if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_INLINE_DATA)) ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); - +#endif ret = inode; err = dquot_alloc_inode(inode); if (err) diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 45fe924f82bc..3580629e42d3 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -20,9 +20,9 @@ * (sct@redhat.com), 1993, 1998 */ -#include <linux/aio.h> #include "ext4_jbd2.h" #include "truncate.h" +#include <linux/uio.h> #include <trace/events/ext4.h> @@ -642,8 +642,8 @@ out: * crashes then stale disk data _may_ be exposed inside the file. But current * VFS code falls back into buffered path in that case so we are safe. */ -ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, - struct iov_iter *iter, loff_t offset) +ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; @@ -654,7 +654,7 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, size_t count = iov_iter_count(iter); int retries = 0; - if (rw == WRITE) { + if (iov_iter_rw(iter) == WRITE) { loff_t final_size = offset + count; if (final_size > inode->i_size) { @@ -676,7 +676,7 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, } retry: - if (rw == READ && ext4_should_dioread_nolock(inode)) { + if (iov_iter_rw(iter) == READ && ext4_should_dioread_nolock(inode)) { /* * Nolock dioread optimization may be dynamically disabled * via ext4_inode_block_unlocked_dio(). Check inode's state @@ -690,23 +690,24 @@ retry: goto locked; } if (IS_DAX(inode)) - ret = dax_do_io(rw, iocb, inode, iter, offset, + ret = dax_do_io(iocb, inode, iter, offset, ext4_get_block, NULL, 0); else - ret = __blockdev_direct_IO(rw, iocb, inode, - inode->i_sb->s_bdev, iter, offset, - ext4_get_block, NULL, NULL, 0); + ret = __blockdev_direct_IO(iocb, inode, + inode->i_sb->s_bdev, iter, + offset, ext4_get_block, NULL, + NULL, 0); inode_dio_done(inode); } else { locked: if (IS_DAX(inode)) - ret = dax_do_io(rw, iocb, inode, iter, offset, + ret = dax_do_io(iocb, inode, iter, offset, ext4_get_block, NULL, DIO_LOCKING); else - ret = blockdev_direct_IO(rw, iocb, inode, iter, - offset, ext4_get_block); + ret = blockdev_direct_IO(iocb, inode, iter, offset, + ext4_get_block); - if (unlikely((rw & WRITE) && ret < 0)) { + if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) { loff_t isize = i_size_read(inode); loff_t end = offset + count; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 4b143febf21f..feb2cafbeace 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -11,11 +11,13 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. */ + +#include <linux/fiemap.h> + #include "ext4_jbd2.h" #include "ext4.h" #include "xattr.h" #include "truncate.h" -#include <linux/fiemap.h> #define EXT4_XATTR_SYSTEM_DATA "data" #define EXT4_MIN_INLINE_DATA_SIZE ((sizeof(__le32) * EXT4_N_BLOCKS)) @@ -972,7 +974,7 @@ void ext4_show_inline_dir(struct inode *dir, struct buffer_head *bh, offset = 0; while ((void *)de < dlimit) { de_len = ext4_rec_len_from_disk(de->rec_len, inline_size); - trace_printk("de: off %u rlen %u name %*.s nlen %u ino %u\n", + trace_printk("de: off %u rlen %u name %.*s nlen %u ino %u\n", offset, de_len, de->name_len, de->name, de->name_len, le32_to_cpu(de->inode)); if (ext4_check_dir_entry(dir, NULL, de, bh, @@ -1014,7 +1016,8 @@ static int ext4_add_dirent_to_inline(handle_t *handle, err = ext4_journal_get_write_access(handle, iloc->bh); if (err) return err; - ext4_insert_dentry(inode, de, inline_size, name, namelen); + ext4_insert_dentry(dir, inode, de, inline_size, &dentry->d_name, + name, namelen); ext4_show_inline_dir(dir, iloc->bh, inline_start, inline_size); @@ -1327,6 +1330,7 @@ int htree_inlinedir_to_tree(struct file *dir_file, struct ext4_iloc iloc; void *dir_buf = NULL; struct ext4_dir_entry_2 fake; + struct ext4_str tmp_str; ret = ext4_get_inode_loc(inode, &iloc); if (ret) @@ -1398,8 +1402,10 @@ int htree_inlinedir_to_tree(struct file *dir_file, continue; if (de->inode == 0) continue; - err = ext4_htree_store_dirent(dir_file, - hinfo->hash, hinfo->minor_hash, de); + tmp_str.name = de->name; + tmp_str.len = de->name_len; + err = ext4_htree_store_dirent(dir_file, hinfo->hash, + hinfo->minor_hash, de, &tmp_str); if (err) { count = err; goto out; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 5cb9a212b86f..366476e71e10 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -20,7 +20,6 @@ #include <linux/fs.h> #include <linux/time.h> -#include <linux/jbd2.h> #include <linux/highuid.h> #include <linux/pagemap.h> #include <linux/quotaops.h> @@ -36,8 +35,6 @@ #include <linux/kernel.h> #include <linux/printk.h> #include <linux/slab.h> -#include <linux/ratelimit.h> -#include <linux/aio.h> #include <linux/bitops.h> #include "ext4_jbd2.h" @@ -141,7 +138,7 @@ static int ext4_meta_trans_blocks(struct inode *inode, int lblocks, /* * Test whether an inode is a fast symlink. */ -static int ext4_inode_is_fast_symlink(struct inode *inode) +int ext4_inode_is_fast_symlink(struct inode *inode) { int ea_blocks = EXT4_I(inode)->i_file_acl ? EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0; @@ -888,6 +885,95 @@ int do_journal_get_write_access(handle_t *handle, static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); + +#ifdef CONFIG_EXT4_FS_ENCRYPTION +static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len, + get_block_t *get_block) +{ + unsigned from = pos & (PAGE_CACHE_SIZE - 1); + unsigned to = from + len; + struct inode *inode = page->mapping->host; + unsigned block_start, block_end; + sector_t block; + int err = 0; + unsigned blocksize = inode->i_sb->s_blocksize; + unsigned bbits; + struct buffer_head *bh, *head, *wait[2], **wait_bh = wait; + bool decrypt = false; + + BUG_ON(!PageLocked(page)); + BUG_ON(from > PAGE_CACHE_SIZE); + BUG_ON(to > PAGE_CACHE_SIZE); + BUG_ON(from > to); + + if (!page_has_buffers(page)) + create_empty_buffers(page, blocksize, 0); + head = page_buffers(page); + bbits = ilog2(blocksize); + block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits); + + for (bh = head, block_start = 0; bh != head || !block_start; + block++, block_start = block_end, bh = bh->b_this_page) { + block_end = block_start + blocksize; + if (block_end <= from || block_start >= to) { + if (PageUptodate(page)) { + if (!buffer_uptodate(bh)) + set_buffer_uptodate(bh); + } + continue; + } + if (buffer_new(bh)) + clear_buffer_new(bh); + if (!buffer_mapped(bh)) { + WARN_ON(bh->b_size != blocksize); + err = get_block(inode, block, bh, 1); + if (err) + break; + if (buffer_new(bh)) { + unmap_underlying_metadata(bh->b_bdev, + bh->b_blocknr); + if (PageUptodate(page)) { + clear_buffer_new(bh); + set_buffer_uptodate(bh); + mark_buffer_dirty(bh); + continue; + } + if (block_end > to || block_start < from) + zero_user_segments(page, to, block_end, + block_start, from); + continue; + } + } + if (PageUptodate(page)) { + if (!buffer_uptodate(bh)) + set_buffer_uptodate(bh); + continue; + } + if (!buffer_uptodate(bh) && !buffer_delay(bh) && + !buffer_unwritten(bh) && + (block_start < from || block_end > to)) { + ll_rw_block(READ, 1, &bh); + *wait_bh++ = bh; + decrypt = ext4_encrypted_inode(inode) && + S_ISREG(inode->i_mode); + } + } + /* + * If we issued read requests, let them complete. + */ + while (wait_bh > wait) { + wait_on_buffer(*--wait_bh); + if (!buffer_uptodate(*wait_bh)) + err = -EIO; + } + if (unlikely(err)) + page_zero_new_buffers(page, from, to); + else if (decrypt) + err = ext4_decrypt_one(inode, page); + return err; +} +#endif + static int ext4_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) @@ -950,11 +1036,19 @@ retry_journal: /* In case writeback began while the page was unlocked */ wait_for_stable_page(page); +#ifdef CONFIG_EXT4_FS_ENCRYPTION + if (ext4_should_dioread_nolock(inode)) + ret = ext4_block_write_begin(page, pos, len, + ext4_get_block_write); + else + ret = ext4_block_write_begin(page, pos, len, + ext4_get_block); +#else if (ext4_should_dioread_nolock(inode)) ret = __block_write_begin(page, pos, len, ext4_get_block_write); else ret = __block_write_begin(page, pos, len, ext4_get_block); - +#endif if (!ret && ext4_should_journal_data(inode)) { ret = ext4_walk_page_buffers(handle, page_buffers(page), from, to, NULL, @@ -2576,7 +2670,12 @@ retry_journal: /* In case writeback began while the page was unlocked */ wait_for_stable_page(page); +#ifdef CONFIG_EXT4_FS_ENCRYPTION + ret = ext4_block_write_begin(page, pos, len, + ext4_da_get_block_prep); +#else ret = __block_write_begin(page, pos, len, ext4_da_get_block_prep); +#endif if (ret < 0) { unlock_page(page); ext4_journal_stop(handle); @@ -2822,7 +2921,7 @@ static int ext4_readpage(struct file *file, struct page *page) ret = ext4_readpage_inline(inode, page); if (ret == -EAGAIN) - return mpage_readpage(page, ext4_get_block); + return ext4_mpage_readpages(page->mapping, NULL, page, 1); return ret; } @@ -2837,7 +2936,7 @@ ext4_readpages(struct file *file, struct address_space *mapping, if (ext4_has_inline_data(inode)) return 0; - return mpage_readpages(mapping, pages, nr_pages, ext4_get_block); + return ext4_mpage_readpages(mapping, pages, NULL, nr_pages); } static void ext4_invalidatepage(struct page *page, unsigned int offset, @@ -2953,8 +3052,8 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, * if the machine crashes during the write. * */ -static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, - struct iov_iter *iter, loff_t offset) +static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; @@ -2967,8 +3066,8 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, ext4_io_end_t *io_end = NULL; /* Use the old path for reads and writes beyond i_size. */ - if (rw != WRITE || final_size > inode->i_size) - return ext4_ind_direct_IO(rw, iocb, iter, offset); + if (iov_iter_rw(iter) != WRITE || final_size > inode->i_size) + return ext4_ind_direct_IO(iocb, iter, offset); BUG_ON(iocb->private == NULL); @@ -2977,7 +3076,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, * conversion. This also disallows race between truncate() and * overwrite DIO as i_dio_count needs to be incremented under i_mutex. */ - if (rw == WRITE) + if (iov_iter_rw(iter) == WRITE) atomic_inc(&inode->i_dio_count); /* If we do a overwrite dio, i_mutex locking can be released */ @@ -3034,11 +3133,14 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, get_block_func = ext4_get_block_write; dio_flags = DIO_LOCKING; } +#ifdef CONFIG_EXT4_FS_ENCRYPTION + BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode)); +#endif if (IS_DAX(inode)) - ret = dax_do_io(rw, iocb, inode, iter, offset, get_block_func, + ret = dax_do_io(iocb, inode, iter, offset, get_block_func, ext4_end_io_dio, dio_flags); else - ret = __blockdev_direct_IO(rw, iocb, inode, + ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, offset, get_block_func, ext4_end_io_dio, NULL, dio_flags); @@ -3079,7 +3181,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, } retake_lock: - if (rw == WRITE) + if (iov_iter_rw(iter) == WRITE) inode_dio_done(inode); /* take i_mutex locking again if we do a ovewrite dio */ if (overwrite) { @@ -3090,14 +3192,19 @@ retake_lock: return ret; } -static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, - struct iov_iter *iter, loff_t offset) +static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; size_t count = iov_iter_count(iter); ssize_t ret; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode)) + return 0; +#endif + /* * If we are doing data journalling we don't support O_DIRECT */ @@ -3108,12 +3215,12 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, if (ext4_has_inline_data(inode)) return 0; - trace_ext4_direct_IO_enter(inode, offset, count, rw); + trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter)); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - ret = ext4_ext_direct_IO(rw, iocb, iter, offset); + ret = ext4_ext_direct_IO(iocb, iter, offset); else - ret = ext4_ind_direct_IO(rw, iocb, iter, offset); - trace_ext4_direct_IO_exit(inode, offset, count, rw, ret); + ret = ext4_ind_direct_IO(iocb, iter, offset); + trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret); return ret; } @@ -3262,6 +3369,13 @@ static int __ext4_block_zero_page_range(handle_t *handle, /* Uhhuh. Read error. Complain and punt. */ if (!buffer_uptodate(bh)) goto unlock; + if (S_ISREG(inode->i_mode) && + ext4_encrypted_inode(inode)) { + /* We expect the key to be set. */ + BUG_ON(!ext4_has_encryption_key(inode)); + BUG_ON(blocksize != PAGE_CACHE_SIZE); + WARN_ON_ONCE(ext4_decrypt_one(inode, page)); + } } if (ext4_should_journal_data(inode)) { BUFFER_TRACE(bh, "get write access"); @@ -4091,16 +4205,14 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) if (S_ISREG(inode->i_mode)) { inode->i_op = &ext4_file_inode_operations; - if (test_opt(inode->i_sb, DAX)) - inode->i_fop = &ext4_dax_file_operations; - else - inode->i_fop = &ext4_file_operations; + inode->i_fop = &ext4_file_operations; ext4_set_aops(inode); } else if (S_ISDIR(inode->i_mode)) { inode->i_op = &ext4_dir_inode_operations; inode->i_fop = &ext4_dir_operations; } else if (S_ISLNK(inode->i_mode)) { - if (ext4_inode_is_fast_symlink(inode)) { + if (ext4_inode_is_fast_symlink(inode) && + !ext4_encrypted_inode(inode)) { inode->i_op = &ext4_fast_symlink_inode_operations; nd_terminate_link(ei->i_data, inode->i_size, sizeof(ei->i_data) - 1); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index f58a0d106726..2cb9e178d1c5 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -8,12 +8,12 @@ */ #include <linux/fs.h> -#include <linux/jbd2.h> #include <linux/capability.h> #include <linux/time.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/file.h> +#include <linux/random.h> #include <asm/uaccess.h> #include "ext4_jbd2.h" #include "ext4.h" @@ -196,6 +196,16 @@ journal_err_out: return err; } +static int uuid_is_zero(__u8 u[16]) +{ + int i; + + for (i = 0; i < 16; i++) + if (u[i]) + return 0; + return 1; +} + long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -615,7 +625,78 @@ resizefs_out: } case EXT4_IOC_PRECACHE_EXTENTS: return ext4_ext_precache(inode); + case EXT4_IOC_SET_ENCRYPTION_POLICY: { +#ifdef CONFIG_EXT4_FS_ENCRYPTION + struct ext4_encryption_policy policy; + int err = 0; + + if (copy_from_user(&policy, + (struct ext4_encryption_policy __user *)arg, + sizeof(policy))) { + err = -EFAULT; + goto encryption_policy_out; + } + err = ext4_process_policy(&policy, inode); +encryption_policy_out: + return err; +#else + return -EOPNOTSUPP; +#endif + } + case EXT4_IOC_GET_ENCRYPTION_PWSALT: { + int err, err2; + struct ext4_sb_info *sbi = EXT4_SB(sb); + handle_t *handle; + + if (!ext4_sb_has_crypto(sb)) + return -EOPNOTSUPP; + if (uuid_is_zero(sbi->s_es->s_encrypt_pw_salt)) { + err = mnt_want_write_file(filp); + if (err) + return err; + handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto pwsalt_err_exit; + } + err = ext4_journal_get_write_access(handle, sbi->s_sbh); + if (err) + goto pwsalt_err_journal; + generate_random_uuid(sbi->s_es->s_encrypt_pw_salt); + err = ext4_handle_dirty_metadata(handle, NULL, + sbi->s_sbh); + pwsalt_err_journal: + err2 = ext4_journal_stop(handle); + if (err2 && !err) + err = err2; + pwsalt_err_exit: + mnt_drop_write_file(filp); + if (err) + return err; + } + if (copy_to_user((void *) arg, sbi->s_es->s_encrypt_pw_salt, + 16)) + return -EFAULT; + return 0; + } + case EXT4_IOC_GET_ENCRYPTION_POLICY: { +#ifdef CONFIG_EXT4_FS_ENCRYPTION + struct ext4_encryption_policy policy; + int err = 0; + + if (!ext4_encrypted_inode(inode)) + return -ENOENT; + err = ext4_get_policy(inode, &policy); + if (err) + return err; + if (copy_to_user((void *)arg, &policy, sizeof(policy))) + return -EFAULT; + return 0; +#else + return -EOPNOTSUPP; +#endif + } default: return -ENOTTY; } @@ -680,6 +761,9 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case FITRIM: case EXT4_IOC_RESIZE_FS: case EXT4_IOC_PRECACHE_EXTENTS: + case EXT4_IOC_SET_ENCRYPTION_POLICY: + case EXT4_IOC_GET_ENCRYPTION_PWSALT: + case EXT4_IOC_GET_ENCRYPTION_POLICY: break; default: return -ENOIOCTLCMD; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 28fe71a2904c..ef22cd951c0c 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -26,7 +26,6 @@ #include <linux/fs.h> #include <linux/pagemap.h> -#include <linux/jbd2.h> #include <linux/time.h> #include <linux/fcntl.h> #include <linux/stat.h> @@ -254,8 +253,9 @@ static struct dx_frame *dx_probe(const struct qstr *d_name, struct dx_hash_info *hinfo, struct dx_frame *frame); static void dx_release(struct dx_frame *frames); -static int dx_make_map(struct ext4_dir_entry_2 *de, unsigned blocksize, - struct dx_hash_info *hinfo, struct dx_map_entry map[]); +static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de, + unsigned blocksize, struct dx_hash_info *hinfo, + struct dx_map_entry map[]); static void dx_sort_map(struct dx_map_entry *map, unsigned count); static struct ext4_dir_entry_2 *dx_move_dirents(char *from, char *to, struct dx_map_entry *offsets, int count, unsigned blocksize); @@ -586,8 +586,10 @@ struct stats unsigned bcount; }; -static struct stats dx_show_leaf(struct dx_hash_info *hinfo, struct ext4_dir_entry_2 *de, - int size, int show_names) +static struct stats dx_show_leaf(struct inode *dir, + struct dx_hash_info *hinfo, + struct ext4_dir_entry_2 *de, + int size, int show_names) { unsigned names = 0, space = 0; char *base = (char *) de; @@ -600,12 +602,80 @@ static struct stats dx_show_leaf(struct dx_hash_info *hinfo, struct ext4_dir_ent { if (show_names) { +#ifdef CONFIG_EXT4_FS_ENCRYPTION + int len; + char *name; + struct ext4_str fname_crypto_str + = {.name = NULL, .len = 0}; + struct ext4_fname_crypto_ctx *ctx = NULL; + int res; + + name = de->name; + len = de->name_len; + ctx = ext4_get_fname_crypto_ctx(dir, + EXT4_NAME_LEN); + if (IS_ERR(ctx)) { + printk(KERN_WARNING "Error acquiring" + " crypto ctxt--skipping crypto\n"); + ctx = NULL; + } + if (ctx == NULL) { + /* Directory is not encrypted */ + ext4fs_dirhash(de->name, + de->name_len, &h); + printk("%*.s:(U)%x.%u ", len, + name, h.hash, + (unsigned) ((char *) de + - base)); + } else { + /* Directory is encrypted */ + res = ext4_fname_crypto_alloc_buffer( + ctx, de->name_len, + &fname_crypto_str); + if (res < 0) { + printk(KERN_WARNING "Error " + "allocating crypto " + "buffer--skipping " + "crypto\n"); + ext4_put_fname_crypto_ctx(&ctx); + ctx = NULL; + } + res = ext4_fname_disk_to_usr(ctx, de, + &fname_crypto_str); + if (res < 0) { + printk(KERN_WARNING "Error " + "converting filename " + "from disk to usr" + "\n"); + name = "??"; + len = 2; + } else { + name = fname_crypto_str.name; + len = fname_crypto_str.len; + } + res = ext4_fname_disk_to_hash(ctx, de, + &h); + if (res < 0) { + printk(KERN_WARNING "Error " + "converting filename " + "from disk to htree" + "\n"); + h.hash = 0xDEADBEEF; + } + printk("%*.s:(E)%x.%u ", len, name, + h.hash, (unsigned) ((char *) de + - base)); + ext4_put_fname_crypto_ctx(&ctx); + ext4_fname_crypto_free_buffer( + &fname_crypto_str); + } +#else int len = de->name_len; char *name = de->name; - while (len--) printk("%c", *name++); ext4fs_dirhash(de->name, de->name_len, &h); - printk(":%x.%u ", h.hash, + printk("%*.s:%x.%u ", len, name, h.hash, (unsigned) ((char *) de - base)); +#endif } space += EXT4_DIR_REC_LEN(de->name_len); names++; @@ -623,7 +693,6 @@ struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir, unsigned count = dx_get_count(entries), names = 0, space = 0, i; unsigned bcount = 0; struct buffer_head *bh; - int err; printk("%i indexed blocks...\n", count); for (i = 0; i < count; i++, entries++) { @@ -637,7 +706,8 @@ struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir, continue; stats = levels? dx_show_entries(hinfo, dir, ((struct dx_node *) bh->b_data)->entries, levels - 1): - dx_show_leaf(hinfo, (struct ext4_dir_entry_2 *) bh->b_data, blocksize, 0); + dx_show_leaf(dir, hinfo, (struct ext4_dir_entry_2 *) + bh->b_data, blocksize, 0); names += stats.names; space += stats.space; bcount += stats.bcount; @@ -687,8 +757,28 @@ dx_probe(const struct qstr *d_name, struct inode *dir, if (hinfo->hash_version <= DX_HASH_TEA) hinfo->hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned; hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + if (d_name) { + struct ext4_fname_crypto_ctx *ctx = NULL; + int res; + + /* Check if the directory is encrypted */ + ctx = ext4_get_fname_crypto_ctx(dir, EXT4_NAME_LEN); + if (IS_ERR(ctx)) { + ret_err = ERR_PTR(PTR_ERR(ctx)); + goto fail; + } + res = ext4_fname_usr_to_hash(ctx, d_name, hinfo); + if (res < 0) { + ret_err = ERR_PTR(res); + goto fail; + } + ext4_put_fname_crypto_ctx(&ctx); + } +#else if (d_name) ext4fs_dirhash(d_name->name, d_name->len, hinfo); +#endif hash = hinfo->hash; if (root->info.unused_flags & 1) { @@ -773,6 +863,7 @@ fail: brelse(frame->bh); frame--; } + if (ret_err == ERR_PTR(ERR_BAD_DX_DIR)) ext4_warning(dir->i_sb, "Corrupt dir inode %lu, running e2fsck is " @@ -878,6 +969,8 @@ static int htree_dirblock_to_tree(struct file *dir_file, struct buffer_head *bh; struct ext4_dir_entry_2 *de, *top; int err = 0, count = 0; + struct ext4_fname_crypto_ctx *ctx = NULL; + struct ext4_str fname_crypto_str = {.name = NULL, .len = 0}, tmp_str; dxtrace(printk(KERN_INFO "In htree dirblock_to_tree: block %lu\n", (unsigned long)block)); @@ -889,6 +982,24 @@ static int htree_dirblock_to_tree(struct file *dir_file, top = (struct ext4_dir_entry_2 *) ((char *) de + dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0)); +#ifdef CONFIG_EXT4_FS_ENCRYPTION + /* Check if the directory is encrypted */ + ctx = ext4_get_fname_crypto_ctx(dir, EXT4_NAME_LEN); + if (IS_ERR(ctx)) { + err = PTR_ERR(ctx); + brelse(bh); + return err; + } + if (ctx != NULL) { + err = ext4_fname_crypto_alloc_buffer(ctx, EXT4_NAME_LEN, + &fname_crypto_str); + if (err < 0) { + ext4_put_fname_crypto_ctx(&ctx); + brelse(bh); + return err; + } + } +#endif for (; de < top; de = ext4_next_entry(de, dir->i_sb->s_blocksize)) { if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data, bh->b_size, @@ -897,21 +1008,52 @@ static int htree_dirblock_to_tree(struct file *dir_file, /* silently ignore the rest of the block */ break; } +#ifdef CONFIG_EXT4_FS_ENCRYPTION + err = ext4_fname_disk_to_hash(ctx, de, hinfo); + if (err < 0) { + count = err; + goto errout; + } +#else ext4fs_dirhash(de->name, de->name_len, hinfo); +#endif if ((hinfo->hash < start_hash) || ((hinfo->hash == start_hash) && (hinfo->minor_hash < start_minor_hash))) continue; if (de->inode == 0) continue; - if ((err = ext4_htree_store_dirent(dir_file, - hinfo->hash, hinfo->minor_hash, de)) != 0) { - brelse(bh); - return err; + if (ctx == NULL) { + /* Directory is not encrypted */ + tmp_str.name = de->name; + tmp_str.len = de->name_len; + err = ext4_htree_store_dirent(dir_file, + hinfo->hash, hinfo->minor_hash, de, + &tmp_str); + } else { + /* Directory is encrypted */ + err = ext4_fname_disk_to_usr(ctx, de, + &fname_crypto_str); + if (err < 0) { + count = err; + goto errout; + } + err = ext4_htree_store_dirent(dir_file, + hinfo->hash, hinfo->minor_hash, de, + &fname_crypto_str); + } + if (err != 0) { + count = err; + goto errout; } count++; } +errout: brelse(bh); +#ifdef CONFIG_EXT4_FS_ENCRYPTION + ext4_put_fname_crypto_ctx(&ctx); + ext4_fname_crypto_free_buffer(&fname_crypto_str); +#endif return count; } @@ -935,6 +1077,7 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, int count = 0; int ret, err; __u32 hashval; + struct ext4_str tmp_str; dxtrace(printk(KERN_DEBUG "In htree_fill_tree, start hash: %x:%x\n", start_hash, start_minor_hash)); @@ -970,14 +1113,22 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, /* Add '.' and '..' from the htree header */ if (!start_hash && !start_minor_hash) { de = (struct ext4_dir_entry_2 *) frames[0].bh->b_data; - if ((err = ext4_htree_store_dirent(dir_file, 0, 0, de)) != 0) + tmp_str.name = de->name; + tmp_str.len = de->name_len; + err = ext4_htree_store_dirent(dir_file, 0, 0, + de, &tmp_str); + if (err != 0) goto errout; count++; } if (start_hash < 2 || (start_hash ==2 && start_minor_hash==0)) { de = (struct ext4_dir_entry_2 *) frames[0].bh->b_data; de = ext4_next_entry(de, dir->i_sb->s_blocksize); - if ((err = ext4_htree_store_dirent(dir_file, 2, 0, de)) != 0) + tmp_str.name = de->name; + tmp_str.len = de->name_len; + err = ext4_htree_store_dirent(dir_file, 2, 0, + de, &tmp_str); + if (err != 0) goto errout; count++; } @@ -1035,17 +1186,33 @@ static inline int search_dirblock(struct buffer_head *bh, * Create map of hash values, offsets, and sizes, stored at end of block. * Returns number of entries mapped. */ -static int dx_make_map(struct ext4_dir_entry_2 *de, unsigned blocksize, - struct dx_hash_info *hinfo, +static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de, + unsigned blocksize, struct dx_hash_info *hinfo, struct dx_map_entry *map_tail) { int count = 0; char *base = (char *) de; struct dx_hash_info h = *hinfo; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + struct ext4_fname_crypto_ctx *ctx = NULL; + int err; + + ctx = ext4_get_fname_crypto_ctx(dir, EXT4_NAME_LEN); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); +#endif while ((char *) de < base + blocksize) { if (de->name_len && de->inode) { +#ifdef CONFIG_EXT4_FS_ENCRYPTION + err = ext4_fname_disk_to_hash(ctx, de, &h); + if (err < 0) { + ext4_put_fname_crypto_ctx(&ctx); + return err; + } +#else ext4fs_dirhash(de->name, de->name_len, &h); +#endif map_tail--; map_tail->hash = h.hash; map_tail->offs = ((char *) de - base)>>2; @@ -1056,6 +1223,9 @@ static int dx_make_map(struct ext4_dir_entry_2 *de, unsigned blocksize, /* XXX: do we need to check rec_len == 0 case? -Chris */ de = ext4_next_entry(de, blocksize); } +#ifdef CONFIG_EXT4_FS_ENCRYPTION + ext4_put_fname_crypto_ctx(&ctx); +#endif return count; } @@ -1106,57 +1276,107 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block) * `len <= EXT4_NAME_LEN' is guaranteed by caller. * `de != NULL' is guaranteed by caller. */ -static inline int ext4_match (int len, const char * const name, - struct ext4_dir_entry_2 * de) +static inline int ext4_match(struct ext4_fname_crypto_ctx *ctx, + struct ext4_str *fname_crypto_str, + int len, const char * const name, + struct ext4_dir_entry_2 *de) { - if (len != de->name_len) - return 0; + int res; + if (!de->inode) return 0; - return !memcmp(name, de->name, len); + +#ifdef CONFIG_EXT4_FS_ENCRYPTION + if (ctx) { + /* Directory is encrypted */ + res = ext4_fname_disk_to_usr(ctx, de, fname_crypto_str); + if (res < 0) + return res; + if (len != res) + return 0; + res = memcmp(name, fname_crypto_str->name, len); + return (res == 0) ? 1 : 0; + } +#endif + if (len != de->name_len) + return 0; + res = memcmp(name, de->name, len); + return (res == 0) ? 1 : 0; } /* * Returns 0 if not found, -1 on failure, and 1 on success */ -int search_dir(struct buffer_head *bh, - char *search_buf, - int buf_size, - struct inode *dir, - const struct qstr *d_name, - unsigned int offset, - struct ext4_dir_entry_2 **res_dir) +int search_dir(struct buffer_head *bh, char *search_buf, int buf_size, + struct inode *dir, const struct qstr *d_name, + unsigned int offset, struct ext4_dir_entry_2 **res_dir) { struct ext4_dir_entry_2 * de; char * dlimit; int de_len; const char *name = d_name->name; int namelen = d_name->len; + struct ext4_fname_crypto_ctx *ctx = NULL; + struct ext4_str fname_crypto_str = {.name = NULL, .len = 0}; + int res; + + ctx = ext4_get_fname_crypto_ctx(dir, EXT4_NAME_LEN); + if (IS_ERR(ctx)) + return -1; + + if (ctx != NULL) { + /* Allocate buffer to hold maximum name length */ + res = ext4_fname_crypto_alloc_buffer(ctx, EXT4_NAME_LEN, + &fname_crypto_str); + if (res < 0) { + ext4_put_fname_crypto_ctx(&ctx); + return -1; + } + } de = (struct ext4_dir_entry_2 *)search_buf; dlimit = search_buf + buf_size; while ((char *) de < dlimit) { /* this code is executed quadratically often */ /* do minimal checking `by hand' */ + if ((char *) de + de->name_len <= dlimit) { + res = ext4_match(ctx, &fname_crypto_str, namelen, + name, de); + if (res < 0) { + res = -1; + goto return_result; + } + if (res > 0) { + /* found a match - just to be sure, do + * a full check */ + if (ext4_check_dir_entry(dir, NULL, de, bh, + bh->b_data, + bh->b_size, offset)) { + res = -1; + goto return_result; + } + *res_dir = de; + res = 1; + goto return_result; + } - if ((char *) de + namelen <= dlimit && - ext4_match (namelen, name, de)) { - /* found a match - just to be sure, do a full check */ - if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data, - bh->b_size, offset)) - return -1; - *res_dir = de; - return 1; } /* prevent looping on a bad block */ de_len = ext4_rec_len_from_disk(de->rec_len, dir->i_sb->s_blocksize); - if (de_len <= 0) - return -1; + if (de_len <= 0) { + res = -1; + goto return_result; + } offset += de_len; de = (struct ext4_dir_entry_2 *) ((char *) de + de_len); } - return 0; + + res = 0; +return_result: + ext4_put_fname_crypto_ctx(&ctx); + ext4_fname_crypto_free_buffer(&fname_crypto_str); + return res; } static int is_dx_internal_node(struct inode *dir, ext4_lblk_t block, @@ -1345,6 +1565,9 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, const struct q ext4_lblk_t block; int retval; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + *res_dir = NULL; +#endif frame = dx_probe(d_name, dir, &hinfo, frames); if (IS_ERR(frame)) return (struct buffer_head *) frame; @@ -1417,6 +1640,18 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi ino); return ERR_PTR(-EIO); } + if (!IS_ERR(inode) && ext4_encrypted_inode(dir) && + (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode)) && + !ext4_is_child_context_consistent_with_parent(dir, + inode)) { + iput(inode); + ext4_warning(inode->i_sb, + "Inconsistent encryption contexts: %lu/%lu\n", + (unsigned long) dir->i_ino, + (unsigned long) inode->i_ino); + return ERR_PTR(-EPERM); + } } return d_splice_alias(inode, dentry); } @@ -1541,7 +1776,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, /* create map in the end of data2 block */ map = (struct dx_map_entry *) (data2 + blocksize); - count = dx_make_map((struct ext4_dir_entry_2 *) data1, + count = dx_make_map(dir, (struct ext4_dir_entry_2 *) data1, blocksize, hinfo, map); map -= count; dx_sort_map(map, count); @@ -1564,7 +1799,8 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, hash2, split, count-split)); /* Fancy dance to stay within two buffers */ - de2 = dx_move_dirents(data1, data2, map + split, count - split, blocksize); + de2 = dx_move_dirents(data1, data2, map + split, count - split, + blocksize); de = dx_pack_dirents(data1, blocksize); de->rec_len = ext4_rec_len_to_disk(data1 + (blocksize - csum_size) - (char *) de, @@ -1580,8 +1816,10 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, initialize_dirent_tail(t, blocksize); } - dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data1, blocksize, 1)); - dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data2, blocksize, 1)); + dxtrace(dx_show_leaf(dir, hinfo, (struct ext4_dir_entry_2 *) data1, + blocksize, 1)); + dxtrace(dx_show_leaf(dir, hinfo, (struct ext4_dir_entry_2 *) data2, + blocksize, 1)); /* Which block gets the new entry? */ if (hinfo->hash >= hash2) { @@ -1618,15 +1856,48 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode, int nlen, rlen; unsigned int offset = 0; char *top; + struct ext4_fname_crypto_ctx *ctx = NULL; + struct ext4_str fname_crypto_str = {.name = NULL, .len = 0}; + int res; + + ctx = ext4_get_fname_crypto_ctx(dir, EXT4_NAME_LEN); + if (IS_ERR(ctx)) + return -1; + + if (ctx != NULL) { + /* Calculate record length needed to store the entry */ + res = ext4_fname_crypto_namelen_on_disk(ctx, namelen); + if (res < 0) { + ext4_put_fname_crypto_ctx(&ctx); + return res; + } + reclen = EXT4_DIR_REC_LEN(res); + + /* Allocate buffer to hold maximum name length */ + res = ext4_fname_crypto_alloc_buffer(ctx, EXT4_NAME_LEN, + &fname_crypto_str); + if (res < 0) { + ext4_put_fname_crypto_ctx(&ctx); + return -1; + } + } de = (struct ext4_dir_entry_2 *)buf; top = buf + buf_size - reclen; while ((char *) de <= top) { if (ext4_check_dir_entry(dir, NULL, de, bh, - buf, buf_size, offset)) - return -EIO; - if (ext4_match(namelen, name, de)) - return -EEXIST; + buf, buf_size, offset)) { + res = -EIO; + goto return_result; + } + /* Provide crypto context and crypto buffer to ext4 match */ + res = ext4_match(ctx, &fname_crypto_str, namelen, name, de); + if (res < 0) + goto return_result; + if (res > 0) { + res = -EEXIST; + goto return_result; + } nlen = EXT4_DIR_REC_LEN(de->name_len); rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); if ((de->inode ? rlen - nlen : rlen) >= reclen) @@ -1634,26 +1905,62 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode, de = (struct ext4_dir_entry_2 *)((char *)de + rlen); offset += rlen; } - if ((char *) de > top) - return -ENOSPC; - *dest_de = de; - return 0; + if ((char *) de > top) + res = -ENOSPC; + else { + *dest_de = de; + res = 0; + } +return_result: + ext4_put_fname_crypto_ctx(&ctx); + ext4_fname_crypto_free_buffer(&fname_crypto_str); + return res; } -void ext4_insert_dentry(struct inode *inode, - struct ext4_dir_entry_2 *de, - int buf_size, - const char *name, int namelen) +int ext4_insert_dentry(struct inode *dir, + struct inode *inode, + struct ext4_dir_entry_2 *de, + int buf_size, + const struct qstr *iname, + const char *name, int namelen) { int nlen, rlen; + struct ext4_fname_crypto_ctx *ctx = NULL; + struct ext4_str fname_crypto_str = {.name = NULL, .len = 0}; + struct ext4_str tmp_str; + int res; + + ctx = ext4_get_fname_crypto_ctx(dir, EXT4_NAME_LEN); + if (IS_ERR(ctx)) + return -EIO; + /* By default, the input name would be written to the disk */ + tmp_str.name = (unsigned char *)name; + tmp_str.len = namelen; + if (ctx != NULL) { + /* Directory is encrypted */ + res = ext4_fname_crypto_alloc_buffer(ctx, EXT4_NAME_LEN, + &fname_crypto_str); + if (res < 0) { + ext4_put_fname_crypto_ctx(&ctx); + return -ENOMEM; + } + res = ext4_fname_usr_to_disk(ctx, iname, &fname_crypto_str); + if (res < 0) { + ext4_put_fname_crypto_ctx(&ctx); + ext4_fname_crypto_free_buffer(&fname_crypto_str); + return res; + } + tmp_str.name = fname_crypto_str.name; + tmp_str.len = fname_crypto_str.len; + } nlen = EXT4_DIR_REC_LEN(de->name_len); rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); if (de->inode) { struct ext4_dir_entry_2 *de1 = - (struct ext4_dir_entry_2 *)((char *)de + nlen); + (struct ext4_dir_entry_2 *)((char *)de + nlen); de1->rec_len = ext4_rec_len_to_disk(rlen - nlen, buf_size); de->rec_len = ext4_rec_len_to_disk(nlen, buf_size); de = de1; @@ -1661,9 +1968,14 @@ void ext4_insert_dentry(struct inode *inode, de->file_type = EXT4_FT_UNKNOWN; de->inode = cpu_to_le32(inode->i_ino); ext4_set_de_type(inode->i_sb, de, inode->i_mode); - de->name_len = namelen; - memcpy(de->name, name, namelen); + de->name_len = tmp_str.len; + + memcpy(de->name, tmp_str.name, tmp_str.len); + ext4_put_fname_crypto_ctx(&ctx); + ext4_fname_crypto_free_buffer(&fname_crypto_str); + return 0; } + /* * Add a new entry into a directory (leaf) block. If de is non-NULL, * it points to a directory entry which is guaranteed to be large @@ -1700,8 +2012,12 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry, return err; } - /* By now the buffer is marked for journaling */ - ext4_insert_dentry(inode, de, blocksize, name, namelen); + /* By now the buffer is marked for journaling. Due to crypto operations, + * the following function call may fail */ + err = ext4_insert_dentry(dir, inode, de, blocksize, &dentry->d_name, + name, namelen); + if (err < 0) + return err; /* * XXX shouldn't update any times until successful @@ -1733,8 +2049,13 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, struct inode *inode, struct buffer_head *bh) { struct inode *dir = dentry->d_parent->d_inode; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + struct ext4_fname_crypto_ctx *ctx = NULL; + int res; +#else const char *name = dentry->d_name.name; int namelen = dentry->d_name.len; +#endif struct buffer_head *bh2; struct dx_root *root; struct dx_frame frames[2], *frame; @@ -1748,7 +2069,13 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, struct dx_hash_info hinfo; ext4_lblk_t block; struct fake_dirent *fde; - int csum_size = 0; + int csum_size = 0; + +#ifdef CONFIG_EXT4_FS_ENCRYPTION + ctx = ext4_get_fname_crypto_ctx(dir, EXT4_NAME_LEN); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); +#endif if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); @@ -1815,7 +2142,18 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, if (hinfo.hash_version <= DX_HASH_TEA) hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned; hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + res = ext4_fname_usr_to_hash(ctx, &dentry->d_name, &hinfo); + if (res < 0) { + ext4_put_fname_crypto_ctx(&ctx); + ext4_mark_inode_dirty(handle, dir); + brelse(bh); + return res; + } + ext4_put_fname_crypto_ctx(&ctx); +#else ext4fs_dirhash(name, namelen, &hinfo); +#endif memset(frames, 0, sizeof(frames)); frame = frames; frame->entries = entries; @@ -1865,7 +2203,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, struct inode *inode) { struct inode *dir = dentry->d_parent->d_inode; - struct buffer_head *bh; + struct buffer_head *bh = NULL; struct ext4_dir_entry_2 *de; struct ext4_dir_entry_tail *t; struct super_block *sb; @@ -1889,14 +2227,14 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, return retval; if (retval == 1) { retval = 0; - return retval; + goto out; } } if (is_dx(dir)) { retval = ext4_dx_add_entry(handle, dentry, inode); if (!retval || (retval != ERR_BAD_DX_DIR)) - return retval; + goto out; ext4_clear_inode_flag(dir, EXT4_INODE_INDEX); dx_fallback++; ext4_mark_inode_dirty(handle, dir); @@ -1908,14 +2246,15 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, return PTR_ERR(bh); retval = add_dirent_to_buf(handle, dentry, inode, NULL, bh); - if (retval != -ENOSPC) { - brelse(bh); - return retval; - } + if (retval != -ENOSPC) + goto out; if (blocks == 1 && !dx_fallback && - EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) - return make_indexed_dir(handle, dentry, inode, bh); + EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) { + retval = make_indexed_dir(handle, dentry, inode, bh); + bh = NULL; /* make_indexed_dir releases bh */ + goto out; + } brelse(bh); } bh = ext4_append(handle, dir, &block); @@ -1931,6 +2270,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, } retval = add_dirent_to_buf(handle, dentry, inode, de, bh); +out: brelse(bh); if (retval == 0) ext4_set_inode_state(inode, EXT4_STATE_NEWENTRY); @@ -2235,12 +2575,22 @@ retry: err = PTR_ERR(inode); if (!IS_ERR(inode)) { inode->i_op = &ext4_file_inode_operations; - if (test_opt(inode->i_sb, DAX)) - inode->i_fop = &ext4_dax_file_operations; - else - inode->i_fop = &ext4_file_operations; + inode->i_fop = &ext4_file_operations; ext4_set_aops(inode); - err = ext4_add_nondir(handle, dentry, inode); + err = 0; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + if (!err && (ext4_encrypted_inode(dir) || + DUMMY_ENCRYPTION_ENABLED(EXT4_SB(dir->i_sb)))) { + err = ext4_inherit_context(dir, inode); + if (err) { + clear_nlink(inode); + unlock_new_inode(inode); + iput(inode); + } + } +#endif + if (!err) + err = ext4_add_nondir(handle, dentry, inode); if (!err && IS_DIRSYNC(dir)) ext4_handle_sync(handle); } @@ -2302,10 +2652,7 @@ retry: err = PTR_ERR(inode); if (!IS_ERR(inode)) { inode->i_op = &ext4_file_inode_operations; - if (test_opt(inode->i_sb, DAX)) - inode->i_fop = &ext4_dax_file_operations; - else - inode->i_fop = &ext4_file_operations; + inode->i_fop = &ext4_file_operations; ext4_set_aops(inode); d_tmpfile(dentry, inode); err = ext4_orphan_add(handle, inode); @@ -2424,6 +2771,14 @@ retry: err = ext4_init_new_dir(handle, dir, inode); if (err) goto out_clear_inode; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + if (ext4_encrypted_inode(dir) || + DUMMY_ENCRYPTION_ENABLED(EXT4_SB(dir->i_sb))) { + err = ext4_inherit_context(dir, inode); + if (err) + goto out_clear_inode; + } +#endif err = ext4_mark_inode_dirty(handle, inode); if (!err) err = ext4_add_entry(handle, dentry, inode); @@ -2456,7 +2811,7 @@ out_stop: /* * routine to check that the specified directory is empty (for rmdir) */ -static int empty_dir(struct inode *inode) +int ext4_empty_dir(struct inode *inode) { unsigned int offset; struct buffer_head *bh; @@ -2724,7 +3079,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry) goto end_rmdir; retval = -ENOTEMPTY; - if (!empty_dir(inode)) + if (!ext4_empty_dir(inode)) goto end_rmdir; handle = ext4_journal_start(dir, EXT4_HT_DIR, @@ -2834,16 +3189,25 @@ static int ext4_symlink(struct inode *dir, { handle_t *handle; struct inode *inode; - int l, err, retries = 0; + int err, len = strlen(symname); int credits; - - l = strlen(symname)+1; - if (l > dir->i_sb->s_blocksize) + bool encryption_required; + struct ext4_str disk_link; + struct ext4_encrypted_symlink_data *sd = NULL; + + disk_link.len = len + 1; + disk_link.name = (char *) symname; + + encryption_required = (ext4_encrypted_inode(dir) || + DUMMY_ENCRYPTION_ENABLED(EXT4_SB(dir->i_sb))); + if (encryption_required) + disk_link.len = encrypted_symlink_data_len(len) + 1; + if (disk_link.len > dir->i_sb->s_blocksize) return -ENAMETOOLONG; dquot_initialize(dir); - if (l > EXT4_N_BLOCKS * 4) { + if ((disk_link.len > EXT4_N_BLOCKS * 4)) { /* * For non-fast symlinks, we just allocate inode and put it on * orphan list in the first transaction => we need bitmap, @@ -2862,16 +3226,49 @@ static int ext4_symlink(struct inode *dir, credits = EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3; } -retry: + inode = ext4_new_inode_start_handle(dir, S_IFLNK|S_IRWXUGO, &dentry->d_name, 0, NULL, EXT4_HT_DIR, credits); handle = ext4_journal_current_handle(); - err = PTR_ERR(inode); - if (IS_ERR(inode)) - goto out_stop; + if (IS_ERR(inode)) { + if (handle) + ext4_journal_stop(handle); + return PTR_ERR(inode); + } + + if (encryption_required) { + struct ext4_fname_crypto_ctx *ctx = NULL; + struct qstr istr; + struct ext4_str ostr; + + sd = kzalloc(disk_link.len, GFP_NOFS); + if (!sd) { + err = -ENOMEM; + goto err_drop_inode; + } + err = ext4_inherit_context(dir, inode); + if (err) + goto err_drop_inode; + ctx = ext4_get_fname_crypto_ctx(inode, + inode->i_sb->s_blocksize); + if (IS_ERR_OR_NULL(ctx)) { + /* We just set the policy, so ctx should not be NULL */ + err = (ctx == NULL) ? -EIO : PTR_ERR(ctx); + goto err_drop_inode; + } + istr.name = (const unsigned char *) symname; + istr.len = len; + ostr.name = sd->encrypted_path; + err = ext4_fname_usr_to_disk(ctx, &istr, &ostr); + ext4_put_fname_crypto_ctx(&ctx); + if (err < 0) + goto err_drop_inode; + sd->len = cpu_to_le16(ostr.len); + disk_link.name = (char *) sd; + } - if (l > EXT4_N_BLOCKS * 4) { + if ((disk_link.len > EXT4_N_BLOCKS * 4)) { inode->i_op = &ext4_symlink_inode_operations; ext4_set_aops(inode); /* @@ -2887,9 +3284,10 @@ retry: drop_nlink(inode); err = ext4_orphan_add(handle, inode); ext4_journal_stop(handle); + handle = NULL; if (err) goto err_drop_inode; - err = __page_symlink(inode, symname, l, 1); + err = __page_symlink(inode, disk_link.name, disk_link.len, 1); if (err) goto err_drop_inode; /* @@ -2901,34 +3299,37 @@ retry: EXT4_INDEX_EXTRA_TRANS_BLOCKS + 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); + handle = NULL; goto err_drop_inode; } set_nlink(inode, 1); err = ext4_orphan_del(handle, inode); - if (err) { - ext4_journal_stop(handle); - clear_nlink(inode); + if (err) goto err_drop_inode; - } } else { /* clear the extent format for fast symlink */ ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS); - inode->i_op = &ext4_fast_symlink_inode_operations; - memcpy((char *)&EXT4_I(inode)->i_data, symname, l); - inode->i_size = l-1; + inode->i_op = encryption_required ? + &ext4_symlink_inode_operations : + &ext4_fast_symlink_inode_operations; + memcpy((char *)&EXT4_I(inode)->i_data, disk_link.name, + disk_link.len); + inode->i_size = disk_link.len - 1; } EXT4_I(inode)->i_disksize = inode->i_size; err = ext4_add_nondir(handle, dentry, inode); if (!err && IS_DIRSYNC(dir)) ext4_handle_sync(handle); -out_stop: if (handle) ext4_journal_stop(handle); - if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries)) - goto retry; + kfree(sd); return err; err_drop_inode: + if (handle) + ext4_journal_stop(handle); + kfree(sd); + clear_nlink(inode); unlock_new_inode(inode); iput(inode); return err; @@ -2943,7 +3344,9 @@ static int ext4_link(struct dentry *old_dentry, if (inode->i_nlink >= EXT4_LINK_MAX) return -EMLINK; - + if (ext4_encrypted_inode(dir) && + !ext4_is_child_context_consistent_with_parent(dir, inode)) + return -EPERM; dquot_initialize(dir); retry: @@ -3244,6 +3647,14 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, if (!old.bh || le32_to_cpu(old.de->inode) != old.inode->i_ino) goto end_rename; + if ((old.dir != new.dir) && + ext4_encrypted_inode(new.dir) && + !ext4_is_child_context_consistent_with_parent(new.dir, + old.inode)) { + retval = -EPERM; + goto end_rename; + } + new.bh = ext4_find_entry(new.dir, &new.dentry->d_name, &new.de, &new.inlined); if (IS_ERR(new.bh)) { @@ -3264,12 +3675,18 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2); if (!(flags & RENAME_WHITEOUT)) { handle = ext4_journal_start(old.dir, EXT4_HT_DIR, credits); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + retval = PTR_ERR(handle); + handle = NULL; + goto end_rename; + } } else { whiteout = ext4_whiteout_for_rename(&old, credits, &handle); - if (IS_ERR(whiteout)) - return PTR_ERR(whiteout); + if (IS_ERR(whiteout)) { + retval = PTR_ERR(whiteout); + whiteout = NULL; + goto end_rename; + } } if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir)) @@ -3278,7 +3695,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, if (S_ISDIR(old.inode->i_mode)) { if (new.inode) { retval = -ENOTEMPTY; - if (!empty_dir(new.inode)) + if (!ext4_empty_dir(new.inode)) goto end_rename; } else { retval = -EMLINK; @@ -3352,8 +3769,9 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, ext4_dec_count(handle, old.dir); if (new.inode) { - /* checked empty_dir above, can't have another parent, - * ext4_dec_count() won't work for many-linked dirs */ + /* checked ext4_empty_dir above, can't have another + * parent, ext4_dec_count() won't work for many-linked + * dirs */ clear_nlink(new.inode); } else { ext4_inc_count(handle, new.dir); @@ -3433,8 +3851,11 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry, handle = ext4_journal_start(old.dir, EXT4_HT_DIR, (2 * EXT4_DATA_TRANS_BLOCKS(old.dir->i_sb) + 2 * EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2)); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + retval = PTR_ERR(handle); + handle = NULL; + goto end_rename; + } if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir)) ext4_handle_sync(handle); diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index b24a2541a9ba..5765f88b3904 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -8,7 +8,6 @@ #include <linux/fs.h> #include <linux/time.h> -#include <linux/jbd2.h> #include <linux/highuid.h> #include <linux/pagemap.h> #include <linux/quotaops.h> @@ -18,14 +17,12 @@ #include <linux/pagevec.h> #include <linux/mpage.h> #include <linux/namei.h> -#include <linux/aio.h> #include <linux/uio.h> #include <linux/bio.h> #include <linux/workqueue.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/mm.h> -#include <linux/ratelimit.h> #include "ext4_jbd2.h" #include "xattr.h" @@ -69,6 +66,10 @@ static void ext4_finish_bio(struct bio *bio) bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + struct page *data_page = NULL; + struct ext4_crypto_ctx *ctx = NULL; +#endif struct buffer_head *bh, *head; unsigned bio_start = bvec->bv_offset; unsigned bio_end = bio_start + bvec->bv_len; @@ -78,6 +79,15 @@ static void ext4_finish_bio(struct bio *bio) if (!page) continue; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + if (!page->mapping) { + /* The bounce data pages are unmapped. */ + data_page = page; + ctx = (struct ext4_crypto_ctx *)page_private(data_page); + page = ctx->control_page; + } +#endif + if (error) { SetPageError(page); set_bit(AS_EIO, &page->mapping->flags); @@ -102,8 +112,13 @@ static void ext4_finish_bio(struct bio *bio) } while ((bh = bh->b_this_page) != head); bit_spin_unlock(BH_Uptodate_Lock, &head->b_state); local_irq_restore(flags); - if (!under_io) + if (!under_io) { +#ifdef CONFIG_EXT4_FS_ENCRYPTION + if (ctx) + ext4_restore_control_page(data_page); +#endif end_page_writeback(page); + } } } @@ -378,6 +393,7 @@ static int io_submit_init_bio(struct ext4_io_submit *io, static int io_submit_add_bh(struct ext4_io_submit *io, struct inode *inode, + struct page *page, struct buffer_head *bh) { int ret; @@ -391,7 +407,7 @@ submit_and_retry: if (ret) return ret; } - ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh)); + ret = bio_add_page(io->io_bio, page, bh->b_size, bh_offset(bh)); if (ret != bh->b_size) goto submit_and_retry; io->io_next_block++; @@ -404,6 +420,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io, struct writeback_control *wbc, bool keep_towrite) { + struct page *data_page = NULL; struct inode *inode = page->mapping->host; unsigned block_start, blocksize; struct buffer_head *bh, *head; @@ -463,19 +480,29 @@ int ext4_bio_write_page(struct ext4_io_submit *io, set_buffer_async_write(bh); } while ((bh = bh->b_this_page) != head); - /* Now submit buffers to write */ bh = head = page_buffers(page); + + if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode)) { + data_page = ext4_encrypt(inode, page); + if (IS_ERR(data_page)) { + ret = PTR_ERR(data_page); + data_page = NULL; + goto out; + } + } + + /* Now submit buffers to write */ do { if (!buffer_async_write(bh)) continue; - ret = io_submit_add_bh(io, inode, bh); + ret = io_submit_add_bh(io, inode, + data_page ? data_page : page, bh); if (ret) { /* * We only get here on ENOMEM. Not much else * we can do but mark the page as dirty, and * better luck next time. */ - redirty_page_for_writepage(wbc, page); break; } nr_submitted++; @@ -484,6 +511,11 @@ int ext4_bio_write_page(struct ext4_io_submit *io, /* Error stopped previous loop? Clean up buffers... */ if (ret) { + out: + if (data_page) + ext4_restore_control_page(data_page); + printk_ratelimited(KERN_ERR "%s: ret = %d\n", __func__, ret); + redirty_page_for_writepage(wbc, page); do { clear_buffer_async_write(bh); bh = bh->b_this_page; diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c new file mode 100644 index 000000000000..171b9ac4b45e --- /dev/null +++ b/fs/ext4/readpage.c @@ -0,0 +1,328 @@ +/* + * linux/fs/ext4/readpage.c + * + * Copyright (C) 2002, Linus Torvalds. + * Copyright (C) 2015, Google, Inc. + * + * This was originally taken from fs/mpage.c + * + * The intent is the ext4_mpage_readpages() function here is intended + * to replace mpage_readpages() in the general case, not just for + * encrypted files. It has some limitations (see below), where it + * will fall back to read_block_full_page(), but these limitations + * should only be hit when page_size != block_size. + * + * This will allow us to attach a callback function to support ext4 + * encryption. + * + * If anything unusual happens, such as: + * + * - encountering a page which has buffers + * - encountering a page which has a non-hole after a hole + * - encountering a page with non-contiguous blocks + * + * then this code just gives up and calls the buffer_head-based read function. + * It does handle a page which has holes at the end - that is a common case: + * the end-of-file on blocksize < PAGE_CACHE_SIZE setups. + * + */ + +#include <linux/kernel.h> +#include <linux/export.h> +#include <linux/mm.h> +#include <linux/kdev_t.h> +#include <linux/gfp.h> +#include <linux/bio.h> +#include <linux/fs.h> +#include <linux/buffer_head.h> +#include <linux/blkdev.h> +#include <linux/highmem.h> +#include <linux/prefetch.h> +#include <linux/mpage.h> +#include <linux/writeback.h> +#include <linux/backing-dev.h> +#include <linux/pagevec.h> +#include <linux/cleancache.h> + +#include "ext4.h" + +/* + * Call ext4_decrypt on every single page, reusing the encryption + * context. + */ +static void completion_pages(struct work_struct *work) +{ +#ifdef CONFIG_EXT4_FS_ENCRYPTION + struct ext4_crypto_ctx *ctx = + container_of(work, struct ext4_crypto_ctx, work); + struct bio *bio = ctx->bio; + struct bio_vec *bv; + int i; + + bio_for_each_segment_all(bv, bio, i) { + struct page *page = bv->bv_page; + + int ret = ext4_decrypt(ctx, page); + if (ret) { + WARN_ON_ONCE(1); + SetPageError(page); + } else + SetPageUptodate(page); + unlock_page(page); + } + ext4_release_crypto_ctx(ctx); + bio_put(bio); +#else + BUG(); +#endif +} + +static inline bool ext4_bio_encrypted(struct bio *bio) +{ +#ifdef CONFIG_EXT4_FS_ENCRYPTION + return unlikely(bio->bi_private != NULL); +#else + return false; +#endif +} + +/* + * I/O completion handler for multipage BIOs. + * + * The mpage code never puts partial pages into a BIO (except for end-of-file). + * If a page does not map to a contiguous run of blocks then it simply falls + * back to block_read_full_page(). + * + * Why is this? If a page's completion depends on a number of different BIOs + * which can complete in any order (or at the same time) then determining the + * status of that page is hard. See end_buffer_async_read() for the details. + * There is no point in duplicating all that complexity. + */ +static void mpage_end_io(struct bio *bio, int err) +{ + struct bio_vec *bv; + int i; + + if (ext4_bio_encrypted(bio)) { + struct ext4_crypto_ctx *ctx = bio->bi_private; + + if (err) { + ext4_release_crypto_ctx(ctx); + } else { + INIT_WORK(&ctx->work, completion_pages); + ctx->bio = bio; + queue_work(ext4_read_workqueue, &ctx->work); + return; + } + } + bio_for_each_segment_all(bv, bio, i) { + struct page *page = bv->bv_page; + + if (!err) { + SetPageUptodate(page); + } else { + ClearPageUptodate(page); + SetPageError(page); + } + unlock_page(page); + } + + bio_put(bio); +} + +int ext4_mpage_readpages(struct address_space *mapping, + struct list_head *pages, struct page *page, + unsigned nr_pages) +{ + struct bio *bio = NULL; + unsigned page_idx; + sector_t last_block_in_bio = 0; + + struct inode *inode = mapping->host; + const unsigned blkbits = inode->i_blkbits; + const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits; + const unsigned blocksize = 1 << blkbits; + sector_t block_in_file; + sector_t last_block; + sector_t last_block_in_file; + sector_t blocks[MAX_BUF_PER_PAGE]; + unsigned page_block; + struct block_device *bdev = inode->i_sb->s_bdev; + int length; + unsigned relative_block = 0; + struct ext4_map_blocks map; + + map.m_pblk = 0; + map.m_lblk = 0; + map.m_len = 0; + map.m_flags = 0; + + for (page_idx = 0; nr_pages; page_idx++, nr_pages--) { + int fully_mapped = 1; + unsigned first_hole = blocks_per_page; + + prefetchw(&page->flags); + if (pages) { + page = list_entry(pages->prev, struct page, lru); + list_del(&page->lru); + if (add_to_page_cache_lru(page, mapping, + page->index, GFP_KERNEL)) + goto next_page; + } + + if (page_has_buffers(page)) + goto confused; + + block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits); + last_block = block_in_file + nr_pages * blocks_per_page; + last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits; + if (last_block > last_block_in_file) + last_block = last_block_in_file; + page_block = 0; + + /* + * Map blocks using the previous result first. + */ + if ((map.m_flags & EXT4_MAP_MAPPED) && + block_in_file > map.m_lblk && + block_in_file < (map.m_lblk + map.m_len)) { + unsigned map_offset = block_in_file - map.m_lblk; + unsigned last = map.m_len - map_offset; + + for (relative_block = 0; ; relative_block++) { + if (relative_block == last) { + /* needed? */ + map.m_flags &= ~EXT4_MAP_MAPPED; + break; + } + if (page_block == blocks_per_page) + break; + blocks[page_block] = map.m_pblk + map_offset + + relative_block; + page_block++; + block_in_file++; + } + } + + /* + * Then do more ext4_map_blocks() calls until we are + * done with this page. + */ + while (page_block < blocks_per_page) { + if (block_in_file < last_block) { + map.m_lblk = block_in_file; + map.m_len = last_block - block_in_file; + + if (ext4_map_blocks(NULL, inode, &map, 0) < 0) { + set_error_page: + SetPageError(page); + zero_user_segment(page, 0, + PAGE_CACHE_SIZE); + unlock_page(page); + goto next_page; + } + } + if ((map.m_flags & EXT4_MAP_MAPPED) == 0) { + fully_mapped = 0; + if (first_hole == blocks_per_page) + first_hole = page_block; + page_block++; + block_in_file++; + continue; + } + if (first_hole != blocks_per_page) + goto confused; /* hole -> non-hole */ + + /* Contiguous blocks? */ + if (page_block && blocks[page_block-1] != map.m_pblk-1) + goto confused; + for (relative_block = 0; ; relative_block++) { + if (relative_block == map.m_len) { + /* needed? */ + map.m_flags &= ~EXT4_MAP_MAPPED; + break; + } else if (page_block == blocks_per_page) + break; + blocks[page_block] = map.m_pblk+relative_block; + page_block++; + block_in_file++; + } + } + if (first_hole != blocks_per_page) { + zero_user_segment(page, first_hole << blkbits, + PAGE_CACHE_SIZE); + if (first_hole == 0) { + SetPageUptodate(page); + unlock_page(page); + goto next_page; + } + } else if (fully_mapped) { + SetPageMappedToDisk(page); + } + if (fully_mapped && blocks_per_page == 1 && + !PageUptodate(page) && cleancache_get_page(page) == 0) { + SetPageUptodate(page); + goto confused; + } + + /* + * This page will go to BIO. Do we need to send this + * BIO off first? + */ + if (bio && (last_block_in_bio != blocks[0] - 1)) { + submit_and_realloc: + submit_bio(READ, bio); + bio = NULL; + } + if (bio == NULL) { + struct ext4_crypto_ctx *ctx = NULL; + + if (ext4_encrypted_inode(inode) && + S_ISREG(inode->i_mode)) { + ctx = ext4_get_crypto_ctx(inode); + if (IS_ERR(ctx)) + goto set_error_page; + } + bio = bio_alloc(GFP_KERNEL, + min_t(int, nr_pages, bio_get_nr_vecs(bdev))); + if (!bio) { + if (ctx) + ext4_release_crypto_ctx(ctx); + goto set_error_page; + } + bio->bi_bdev = bdev; + bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9); + bio->bi_end_io = mpage_end_io; + bio->bi_private = ctx; + } + + length = first_hole << blkbits; + if (bio_add_page(bio, page, length, 0) < length) + goto submit_and_realloc; + + if (((map.m_flags & EXT4_MAP_BOUNDARY) && + (relative_block == map.m_len)) || + (first_hole != blocks_per_page)) { + submit_bio(READ, bio); + bio = NULL; + } else + last_block_in_bio = blocks[blocks_per_page - 1]; + goto next_page; + confused: + if (bio) { + submit_bio(READ, bio); + bio = NULL; + } + if (!PageUptodate(page)) + block_read_full_page(page, ext4_get_block); + else + unlock_page(page); + next_page: + if (pages) + page_cache_release(page); + } + BUG_ON(pages && !list_empty(pages)); + if (bio) + submit_bio(READ, bio); + return 0; +} diff --git a/fs/ext4/super.c b/fs/ext4/super.c index e061e66c8280..821f22dbe825 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -21,7 +21,6 @@ #include <linux/fs.h> #include <linux/time.h> #include <linux/vmalloc.h> -#include <linux/jbd2.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/blkdev.h> @@ -323,22 +322,6 @@ static void save_error_info(struct super_block *sb, const char *func, ext4_commit_super(sb, 1); } -/* - * The del_gendisk() function uninitializes the disk-specific data - * structures, including the bdi structure, without telling anyone - * else. Once this happens, any attempt to call mark_buffer_dirty() - * (for example, by ext4_commit_super), will cause a kernel OOPS. - * This is a kludge to prevent these oops until we can put in a proper - * hook in del_gendisk() to inform the VFS and file system layers. - */ -static int block_device_ejected(struct super_block *sb) -{ - struct inode *bd_inode = sb->s_bdev->bd_inode; - struct backing_dev_info *bdi = inode_to_bdi(bd_inode); - - return bdi->dev == NULL; -} - static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn) { struct super_block *sb = journal->j_private; @@ -893,6 +876,9 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) atomic_set(&ei->i_ioend_count, 0); atomic_set(&ei->i_unwritten, 0); INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work); +#ifdef CONFIG_EXT4_FS_ENCRYPTION + ei->i_encryption_key.mode = EXT4_ENCRYPTION_MODE_INVALID; +#endif return &ei->vfs_inode; } @@ -1076,7 +1062,7 @@ static const struct quotactl_ops ext4_qctl_operations = { .quota_on = ext4_quota_on, .quota_off = ext4_quota_off, .quota_sync = dquot_quota_sync, - .get_info = dquot_get_dqinfo, + .get_state = dquot_get_state, .set_info = dquot_set_dqinfo, .get_dqblk = dquot_get_dqblk, .set_dqblk = dquot_set_dqblk @@ -1120,7 +1106,7 @@ enum { Opt_commit, Opt_min_batch_time, Opt_max_batch_time, Opt_journal_dev, Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit, Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, - Opt_data_err_abort, Opt_data_err_ignore, + Opt_data_err_abort, Opt_data_err_ignore, Opt_test_dummy_encryption, Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota, Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota, Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err, @@ -1211,6 +1197,7 @@ static const match_table_t tokens = { {Opt_init_itable, "init_itable"}, {Opt_noinit_itable, "noinit_itable"}, {Opt_max_dir_size_kb, "max_dir_size_kb=%u"}, + {Opt_test_dummy_encryption, "test_dummy_encryption"}, {Opt_removed, "check=none"}, /* mount option from ext2/3 */ {Opt_removed, "nocheck"}, /* mount option from ext2/3 */ {Opt_removed, "reservation"}, /* mount option from ext2/3 */ @@ -1412,6 +1399,7 @@ static const struct mount_opts { {Opt_jqfmt_vfsv0, QFMT_VFS_V0, MOPT_QFMT}, {Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT}, {Opt_max_dir_size_kb, 0, MOPT_GTE0}, + {Opt_test_dummy_encryption, 0, MOPT_GTE0}, {Opt_err, 0, 0} }; @@ -1588,6 +1576,15 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, } *journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, arg); + } else if (token == Opt_test_dummy_encryption) { +#ifdef CONFIG_EXT4_FS_ENCRYPTION + sbi->s_mount_flags |= EXT4_MF_TEST_DUMMY_ENCRYPTION; + ext4_msg(sb, KERN_WARNING, + "Test dummy encryption mode enabled"); +#else + ext4_msg(sb, KERN_WARNING, + "Test dummy encryption mount option ignored"); +#endif } else if (m->flags & MOPT_DATAJ) { if (is_remount) { if (!sbi->s_journal) @@ -2685,11 +2682,13 @@ static struct attribute *ext4_attrs[] = { EXT4_INFO_ATTR(lazy_itable_init); EXT4_INFO_ATTR(batched_discard); EXT4_INFO_ATTR(meta_bg_resize); +EXT4_INFO_ATTR(encryption); static struct attribute *ext4_feat_attrs[] = { ATTR_LIST(lazy_itable_init), ATTR_LIST(batched_discard), ATTR_LIST(meta_bg_resize), + ATTR_LIST(encryption), NULL, }; @@ -3448,6 +3447,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (sb->s_bdev->bd_part) sbi->s_sectors_written_start = part_stat_read(sb->s_bdev->bd_part, sectors[1]); +#ifdef CONFIG_EXT4_FS_ENCRYPTION + /* Modes of operations for file and directory encryption. */ + sbi->s_file_encryption_mode = EXT4_ENCRYPTION_MODE_AES_256_XTS; + sbi->s_dir_encryption_mode = EXT4_ENCRYPTION_MODE_INVALID; +#endif /* Cleanup superblock name */ for (cp = sb->s_id; (cp = strchr(cp, '/'));) @@ -3692,6 +3696,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } } + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT) && + es->s_encryption_level) { + ext4_msg(sb, KERN_ERR, "Unsupported encryption level %d", + es->s_encryption_level); + goto failed_mount; + } + if (sb->s_blocksize != blocksize) { /* Validate the filesystem blocksize */ if (!sb_set_blocksize(sb, blocksize)) { @@ -4054,6 +4065,13 @@ no_journal: } } + if (unlikely(sbi->s_mount_flags & EXT4_MF_TEST_DUMMY_ENCRYPTION) && + !(sb->s_flags & MS_RDONLY) && + !EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT)) { + EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT); + ext4_commit_super(sb, 1); + } + /* * Get the # of file system overhead blocks from the * superblock if present. @@ -4570,7 +4588,7 @@ static int ext4_commit_super(struct super_block *sb, int sync) struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; int error = 0; - if (!sbh || block_device_ejected(sb)) + if (!sbh) return error; if (buffer_write_io_error(sbh)) { /* diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c index ff3711932018..136ca0e911fd 100644 --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -18,13 +18,101 @@ */ #include <linux/fs.h> -#include <linux/jbd2.h> #include <linux/namei.h> #include "ext4.h" #include "xattr.h" +#ifdef CONFIG_EXT4_FS_ENCRYPTION static void *ext4_follow_link(struct dentry *dentry, struct nameidata *nd) { + struct page *cpage = NULL; + char *caddr, *paddr = NULL; + struct ext4_str cstr, pstr; + struct inode *inode = dentry->d_inode; + struct ext4_fname_crypto_ctx *ctx = NULL; + struct ext4_encrypted_symlink_data *sd; + loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1); + int res; + u32 plen, max_size = inode->i_sb->s_blocksize; + + if (!ext4_encrypted_inode(inode)) + return page_follow_link_light(dentry, nd); + + ctx = ext4_get_fname_crypto_ctx(inode, inode->i_sb->s_blocksize); + if (IS_ERR(ctx)) + return ctx; + + if (ext4_inode_is_fast_symlink(inode)) { + caddr = (char *) EXT4_I(dentry->d_inode)->i_data; + max_size = sizeof(EXT4_I(dentry->d_inode)->i_data); + } else { + cpage = read_mapping_page(inode->i_mapping, 0, NULL); + if (IS_ERR(cpage)) { + ext4_put_fname_crypto_ctx(&ctx); + return cpage; + } + caddr = kmap(cpage); + caddr[size] = 0; + } + + /* Symlink is encrypted */ + sd = (struct ext4_encrypted_symlink_data *)caddr; + cstr.name = sd->encrypted_path; + cstr.len = le32_to_cpu(sd->len); + if ((cstr.len + + sizeof(struct ext4_encrypted_symlink_data) - 1) > + max_size) { + /* Symlink data on the disk is corrupted */ + res = -EIO; + goto errout; + } + plen = (cstr.len < EXT4_FNAME_CRYPTO_DIGEST_SIZE*2) ? + EXT4_FNAME_CRYPTO_DIGEST_SIZE*2 : cstr.len; + paddr = kmalloc(plen + 1, GFP_NOFS); + if (!paddr) { + res = -ENOMEM; + goto errout; + } + pstr.name = paddr; + res = _ext4_fname_disk_to_usr(ctx, &cstr, &pstr); + if (res < 0) + goto errout; + /* Null-terminate the name */ + if (res <= plen) + paddr[res] = '\0'; + nd_set_link(nd, paddr); + ext4_put_fname_crypto_ctx(&ctx); + if (cpage) { + kunmap(cpage); + page_cache_release(cpage); + } + return NULL; +errout: + ext4_put_fname_crypto_ctx(&ctx); + if (cpage) { + kunmap(cpage); + page_cache_release(cpage); + } + kfree(paddr); + return ERR_PTR(res); +} + +static void ext4_put_link(struct dentry *dentry, struct nameidata *nd, + void *cookie) +{ + struct page *page = cookie; + + if (!page) { + kfree(nd_get_link(nd)); + } else { + kunmap(page); + page_cache_release(page); + } +} +#endif + +static void *ext4_follow_fast_link(struct dentry *dentry, struct nameidata *nd) +{ struct ext4_inode_info *ei = EXT4_I(dentry->d_inode); nd_set_link(nd, (char *) ei->i_data); return NULL; @@ -32,8 +120,13 @@ static void *ext4_follow_link(struct dentry *dentry, struct nameidata *nd) const struct inode_operations ext4_symlink_inode_operations = { .readlink = generic_readlink, +#ifdef CONFIG_EXT4_FS_ENCRYPTION + .follow_link = ext4_follow_link, + .put_link = ext4_put_link, +#else .follow_link = page_follow_link_light, .put_link = page_put_link, +#endif .setattr = ext4_setattr, .setxattr = generic_setxattr, .getxattr = generic_getxattr, @@ -43,7 +136,7 @@ const struct inode_operations ext4_symlink_inode_operations = { const struct inode_operations ext4_fast_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = ext4_follow_link, + .follow_link = ext4_follow_fast_link, .setattr = ext4_setattr, .setxattr = generic_setxattr, .getxattr = generic_getxattr, diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 1e09fc77395c..759842ff8af0 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -55,7 +55,6 @@ #include <linux/slab.h> #include <linux/mbcache.h> #include <linux/quotaops.h> -#include <linux/rwsem.h> #include "ext4_jbd2.h" #include "ext4.h" #include "xattr.h" @@ -639,8 +638,7 @@ ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s) free += EXT4_XATTR_LEN(name_len); } if (i->value) { - if (free < EXT4_XATTR_SIZE(i->value_len) || - free < EXT4_XATTR_LEN(name_len) + + if (free < EXT4_XATTR_LEN(name_len) + EXT4_XATTR_SIZE(i->value_len)) return -ENOSPC; } diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index 29bedf5589f6..ddc0957760ba 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -23,6 +23,7 @@ #define EXT4_XATTR_INDEX_SECURITY 6 #define EXT4_XATTR_INDEX_SYSTEM 7 #define EXT4_XATTR_INDEX_RICHACL 8 +#define EXT4_XATTR_INDEX_ENCRYPTION 9 struct ext4_xattr_header { __le32 h_magic; /* magic number for identification */ @@ -98,6 +99,8 @@ extern const struct xattr_handler ext4_xattr_user_handler; extern const struct xattr_handler ext4_xattr_trusted_handler; extern const struct xattr_handler ext4_xattr_security_handler; +#define EXT4_XATTR_NAME_ENCRYPTION_CONTEXT "c" + extern ssize_t ext4_listxattr(struct dentry *, char *, size_t); extern int ext4_xattr_get(struct inode *, int, const char *, void *, size_t); diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig index 94e2d2ffabe1..05f0f663f14c 100644 --- a/fs/f2fs/Kconfig +++ b/fs/f2fs/Kconfig @@ -1,5 +1,5 @@ config F2FS_FS - tristate "F2FS filesystem support (EXPERIMENTAL)" + tristate "F2FS filesystem support" depends on BLOCK help F2FS is based on Log-structured File System (LFS), which supports diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 742202779bd5..4320ffab3495 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -351,13 +351,11 @@ static int f2fs_acl_create(struct inode *dir, umode_t *mode, *acl = f2fs_acl_clone(p, GFP_NOFS); if (!*acl) - return -ENOMEM; + goto no_mem; ret = f2fs_acl_create_masq(*acl, mode); - if (ret < 0) { - posix_acl_release(*acl); - return -ENOMEM; - } + if (ret < 0) + goto no_mem_clone; if (ret == 0) { posix_acl_release(*acl); @@ -378,6 +376,12 @@ no_acl: *default_acl = NULL; *acl = NULL; return 0; + +no_mem_clone: + posix_acl_release(*acl); +no_mem: + posix_acl_release(p); + return -ENOMEM; } int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage, diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 7f794b72b3b7..a5e17a2a0781 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -276,7 +276,7 @@ continue_unlock: if (!clear_page_dirty_for_io(page)) goto continue_unlock; - if (f2fs_write_meta_page(page, &wbc)) { + if (mapping->a_ops->writepage(page, &wbc)) { unlock_page(page); break; } @@ -464,20 +464,19 @@ static void recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) void recover_orphan_inodes(struct f2fs_sb_info *sbi) { - block_t start_blk, orphan_blkaddr, i, j; + block_t start_blk, orphan_blocks, i, j; if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG)) return; set_sbi_flag(sbi, SBI_POR_DOING); - start_blk = __start_cp_addr(sbi) + 1 + - le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload); - orphan_blkaddr = __start_sum_addr(sbi) - 1; + start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi); + orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi); - ra_meta_pages(sbi, start_blk, orphan_blkaddr, META_CP); + ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP); - for (i = 0; i < orphan_blkaddr; i++) { + for (i = 0; i < orphan_blocks; i++) { struct page *page = get_meta_page(sbi, start_blk + i); struct f2fs_orphan_block *orphan_blk; @@ -615,7 +614,7 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi) unsigned long blk_size = sbi->blocksize; unsigned long long cp1_version = 0, cp2_version = 0; unsigned long long cp_start_blk_no; - unsigned int cp_blks = 1 + le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload); + unsigned int cp_blks = 1 + __cp_payload(sbi); block_t cp_blk_no; int i; @@ -796,6 +795,7 @@ retry: * wribacking dentry pages in the freeing inode. */ f2fs_submit_merged_bio(sbi, DATA, WRITE); + cond_resched(); } goto retry; } @@ -884,7 +884,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) __u32 crc32 = 0; void *kaddr; int i; - int cp_payload_blks = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload); + int cp_payload_blks = __cp_payload(sbi); /* * This avoids to conduct wrong roll-forward operations and uses @@ -1048,17 +1048,18 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); unsigned long long ckpt_ver; - trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops"); - mutex_lock(&sbi->cp_mutex); if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) && - cpc->reason != CP_DISCARD && cpc->reason != CP_UMOUNT) + (cpc->reason == CP_FASTBOOT || cpc->reason == CP_SYNC)) goto out; if (unlikely(f2fs_cp_error(sbi))) goto out; if (f2fs_readonly(sbi->sb)) goto out; + + trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops"); + if (block_operations(sbi)) goto out; @@ -1085,6 +1086,10 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) unblock_operations(sbi); stat_inc_cp_count(sbi->stat_info); + + if (cpc->reason == CP_RECOVERY) + f2fs_msg(sbi->sb, KERN_NOTICE, + "checkpoint: version = %llx", ckpt_ver); out: mutex_unlock(&sbi->cp_mutex); trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint"); @@ -1103,14 +1108,9 @@ void init_ino_entry_info(struct f2fs_sb_info *sbi) im->ino_num = 0; } - /* - * considering 512 blocks in a segment 8 blocks are needed for cp - * and log segment summaries. Remaining blocks are used to keep - * orphan entries with the limitation one reserved segment - * for cp pack we can have max 1020*504 orphan entries - */ sbi->max_orphans = (sbi->blocks_per_seg - F2FS_CP_PACKS - - NR_CURSEG_TYPE) * F2FS_ORPHANS_PER_BLOCK; + NR_CURSEG_TYPE - __cp_payload(sbi)) * + F2FS_ORPHANS_PER_BLOCK; } int __init create_checkpoint_caches(void) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 985ed023a750..b91b0e10678e 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -12,12 +12,12 @@ #include <linux/f2fs_fs.h> #include <linux/buffer_head.h> #include <linux/mpage.h> -#include <linux/aio.h> #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/blkdev.h> #include <linux/bio.h> #include <linux/prefetch.h> +#include <linux/uio.h> #include "f2fs.h" #include "node.h" @@ -25,6 +25,9 @@ #include "trace.h" #include <trace/events/f2fs.h> +static struct kmem_cache *extent_tree_slab; +static struct kmem_cache *extent_node_slab; + static void f2fs_read_end_io(struct bio *bio, int err) { struct bio_vec *bvec; @@ -197,7 +200,7 @@ alloc_new: * ->node_page * update block addresses in the node page */ -static void __set_data_blkaddr(struct dnode_of_data *dn) +void set_data_blkaddr(struct dnode_of_data *dn) { struct f2fs_node *rn; __le32 *addr_array; @@ -226,7 +229,7 @@ int reserve_new_block(struct dnode_of_data *dn) trace_f2fs_reserve_new_block(dn->inode, dn->nid, dn->ofs_in_node); dn->data_blkaddr = NEW_ADDR; - __set_data_blkaddr(dn); + set_data_blkaddr(dn); mark_inode_dirty(dn->inode); sync_inode_page(dn); return 0; @@ -248,73 +251,62 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index) return err; } -static int check_extent_cache(struct inode *inode, pgoff_t pgofs, - struct buffer_head *bh_result) +static void f2fs_map_bh(struct super_block *sb, pgoff_t pgofs, + struct extent_info *ei, struct buffer_head *bh_result) +{ + unsigned int blkbits = sb->s_blocksize_bits; + size_t max_size = bh_result->b_size; + size_t mapped_size; + + clear_buffer_new(bh_result); + map_bh(bh_result, sb, ei->blk + pgofs - ei->fofs); + mapped_size = (ei->fofs + ei->len - pgofs) << blkbits; + bh_result->b_size = min(max_size, mapped_size); +} + +static bool lookup_extent_info(struct inode *inode, pgoff_t pgofs, + struct extent_info *ei) { struct f2fs_inode_info *fi = F2FS_I(inode); pgoff_t start_fofs, end_fofs; block_t start_blkaddr; - if (is_inode_flag_set(fi, FI_NO_EXTENT)) - return 0; - - read_lock(&fi->ext.ext_lock); + read_lock(&fi->ext_lock); if (fi->ext.len == 0) { - read_unlock(&fi->ext.ext_lock); - return 0; + read_unlock(&fi->ext_lock); + return false; } stat_inc_total_hit(inode->i_sb); start_fofs = fi->ext.fofs; end_fofs = fi->ext.fofs + fi->ext.len - 1; - start_blkaddr = fi->ext.blk_addr; + start_blkaddr = fi->ext.blk; if (pgofs >= start_fofs && pgofs <= end_fofs) { - unsigned int blkbits = inode->i_sb->s_blocksize_bits; - size_t count; - - set_buffer_new(bh_result); - map_bh(bh_result, inode->i_sb, - start_blkaddr + pgofs - start_fofs); - count = end_fofs - pgofs + 1; - if (count < (UINT_MAX >> blkbits)) - bh_result->b_size = (count << blkbits); - else - bh_result->b_size = UINT_MAX; - + *ei = fi->ext; stat_inc_read_hit(inode->i_sb); - read_unlock(&fi->ext.ext_lock); - return 1; + read_unlock(&fi->ext_lock); + return true; } - read_unlock(&fi->ext.ext_lock); - return 0; + read_unlock(&fi->ext_lock); + return false; } -void update_extent_cache(struct dnode_of_data *dn) +static bool update_extent_info(struct inode *inode, pgoff_t fofs, + block_t blkaddr) { - struct f2fs_inode_info *fi = F2FS_I(dn->inode); - pgoff_t fofs, start_fofs, end_fofs; + struct f2fs_inode_info *fi = F2FS_I(inode); + pgoff_t start_fofs, end_fofs; block_t start_blkaddr, end_blkaddr; int need_update = true; - f2fs_bug_on(F2FS_I_SB(dn->inode), dn->data_blkaddr == NEW_ADDR); - - /* Update the page address in the parent node */ - __set_data_blkaddr(dn); - - if (is_inode_flag_set(fi, FI_NO_EXTENT)) - return; - - fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) + - dn->ofs_in_node; - - write_lock(&fi->ext.ext_lock); + write_lock(&fi->ext_lock); start_fofs = fi->ext.fofs; end_fofs = fi->ext.fofs + fi->ext.len - 1; - start_blkaddr = fi->ext.blk_addr; - end_blkaddr = fi->ext.blk_addr + fi->ext.len - 1; + start_blkaddr = fi->ext.blk; + end_blkaddr = fi->ext.blk + fi->ext.len - 1; /* Drop and initialize the matched extent */ if (fi->ext.len == 1 && fofs == start_fofs) @@ -322,24 +314,24 @@ void update_extent_cache(struct dnode_of_data *dn) /* Initial extent */ if (fi->ext.len == 0) { - if (dn->data_blkaddr != NULL_ADDR) { + if (blkaddr != NULL_ADDR) { fi->ext.fofs = fofs; - fi->ext.blk_addr = dn->data_blkaddr; + fi->ext.blk = blkaddr; fi->ext.len = 1; } goto end_update; } /* Front merge */ - if (fofs == start_fofs - 1 && dn->data_blkaddr == start_blkaddr - 1) { + if (fofs == start_fofs - 1 && blkaddr == start_blkaddr - 1) { fi->ext.fofs--; - fi->ext.blk_addr--; + fi->ext.blk--; fi->ext.len++; goto end_update; } /* Back merge */ - if (fofs == end_fofs + 1 && dn->data_blkaddr == end_blkaddr + 1) { + if (fofs == end_fofs + 1 && blkaddr == end_blkaddr + 1) { fi->ext.len++; goto end_update; } @@ -351,8 +343,7 @@ void update_extent_cache(struct dnode_of_data *dn) fi->ext.len = fofs - start_fofs; } else { fi->ext.fofs = fofs + 1; - fi->ext.blk_addr = start_blkaddr + - fofs - start_fofs + 1; + fi->ext.blk = start_blkaddr + fofs - start_fofs + 1; fi->ext.len -= fofs - start_fofs + 1; } } else { @@ -366,27 +357,583 @@ void update_extent_cache(struct dnode_of_data *dn) need_update = true; } end_update: - write_unlock(&fi->ext.ext_lock); - if (need_update) - sync_inode_page(dn); + write_unlock(&fi->ext_lock); + return need_update; +} + +static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi, + struct extent_tree *et, struct extent_info *ei, + struct rb_node *parent, struct rb_node **p) +{ + struct extent_node *en; + + en = kmem_cache_alloc(extent_node_slab, GFP_ATOMIC); + if (!en) + return NULL; + + en->ei = *ei; + INIT_LIST_HEAD(&en->list); + + rb_link_node(&en->rb_node, parent, p); + rb_insert_color(&en->rb_node, &et->root); + et->count++; + atomic_inc(&sbi->total_ext_node); + return en; +} + +static void __detach_extent_node(struct f2fs_sb_info *sbi, + struct extent_tree *et, struct extent_node *en) +{ + rb_erase(&en->rb_node, &et->root); + et->count--; + atomic_dec(&sbi->total_ext_node); + + if (et->cached_en == en) + et->cached_en = NULL; +} + +static struct extent_tree *__find_extent_tree(struct f2fs_sb_info *sbi, + nid_t ino) +{ + struct extent_tree *et; + + down_read(&sbi->extent_tree_lock); + et = radix_tree_lookup(&sbi->extent_tree_root, ino); + if (!et) { + up_read(&sbi->extent_tree_lock); + return NULL; + } + atomic_inc(&et->refcount); + up_read(&sbi->extent_tree_lock); + + return et; +} + +static struct extent_tree *__grab_extent_tree(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct extent_tree *et; + nid_t ino = inode->i_ino; + + down_write(&sbi->extent_tree_lock); + et = radix_tree_lookup(&sbi->extent_tree_root, ino); + if (!et) { + et = f2fs_kmem_cache_alloc(extent_tree_slab, GFP_NOFS); + f2fs_radix_tree_insert(&sbi->extent_tree_root, ino, et); + memset(et, 0, sizeof(struct extent_tree)); + et->ino = ino; + et->root = RB_ROOT; + et->cached_en = NULL; + rwlock_init(&et->lock); + atomic_set(&et->refcount, 0); + et->count = 0; + sbi->total_ext_tree++; + } + atomic_inc(&et->refcount); + up_write(&sbi->extent_tree_lock); + + return et; +} + +static struct extent_node *__lookup_extent_tree(struct extent_tree *et, + unsigned int fofs) +{ + struct rb_node *node = et->root.rb_node; + struct extent_node *en; + + if (et->cached_en) { + struct extent_info *cei = &et->cached_en->ei; + + if (cei->fofs <= fofs && cei->fofs + cei->len > fofs) + return et->cached_en; + } + + while (node) { + en = rb_entry(node, struct extent_node, rb_node); + + if (fofs < en->ei.fofs) { + node = node->rb_left; + } else if (fofs >= en->ei.fofs + en->ei.len) { + node = node->rb_right; + } else { + et->cached_en = en; + return en; + } + } + return NULL; +} + +static struct extent_node *__try_back_merge(struct f2fs_sb_info *sbi, + struct extent_tree *et, struct extent_node *en) +{ + struct extent_node *prev; + struct rb_node *node; + + node = rb_prev(&en->rb_node); + if (!node) + return NULL; + + prev = rb_entry(node, struct extent_node, rb_node); + if (__is_back_mergeable(&en->ei, &prev->ei)) { + en->ei.fofs = prev->ei.fofs; + en->ei.blk = prev->ei.blk; + en->ei.len += prev->ei.len; + __detach_extent_node(sbi, et, prev); + return prev; + } + return NULL; +} + +static struct extent_node *__try_front_merge(struct f2fs_sb_info *sbi, + struct extent_tree *et, struct extent_node *en) +{ + struct extent_node *next; + struct rb_node *node; + + node = rb_next(&en->rb_node); + if (!node) + return NULL; + + next = rb_entry(node, struct extent_node, rb_node); + if (__is_front_mergeable(&en->ei, &next->ei)) { + en->ei.len += next->ei.len; + __detach_extent_node(sbi, et, next); + return next; + } + return NULL; +} + +static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi, + struct extent_tree *et, struct extent_info *ei, + struct extent_node **den) +{ + struct rb_node **p = &et->root.rb_node; + struct rb_node *parent = NULL; + struct extent_node *en; + + while (*p) { + parent = *p; + en = rb_entry(parent, struct extent_node, rb_node); + + if (ei->fofs < en->ei.fofs) { + if (__is_front_mergeable(ei, &en->ei)) { + f2fs_bug_on(sbi, !den); + en->ei.fofs = ei->fofs; + en->ei.blk = ei->blk; + en->ei.len += ei->len; + *den = __try_back_merge(sbi, et, en); + return en; + } + p = &(*p)->rb_left; + } else if (ei->fofs >= en->ei.fofs + en->ei.len) { + if (__is_back_mergeable(ei, &en->ei)) { + f2fs_bug_on(sbi, !den); + en->ei.len += ei->len; + *den = __try_front_merge(sbi, et, en); + return en; + } + p = &(*p)->rb_right; + } else { + f2fs_bug_on(sbi, 1); + } + } + + return __attach_extent_node(sbi, et, ei, parent, p); +} + +static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi, + struct extent_tree *et, bool free_all) +{ + struct rb_node *node, *next; + struct extent_node *en; + unsigned int count = et->count; + + node = rb_first(&et->root); + while (node) { + next = rb_next(node); + en = rb_entry(node, struct extent_node, rb_node); + + if (free_all) { + spin_lock(&sbi->extent_lock); + if (!list_empty(&en->list)) + list_del_init(&en->list); + spin_unlock(&sbi->extent_lock); + } + + if (free_all || list_empty(&en->list)) { + __detach_extent_node(sbi, et, en); + kmem_cache_free(extent_node_slab, en); + } + node = next; + } + + return count - et->count; +} + +static void f2fs_init_extent_tree(struct inode *inode, + struct f2fs_extent *i_ext) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct extent_tree *et; + struct extent_node *en; + struct extent_info ei; + + if (le32_to_cpu(i_ext->len) < F2FS_MIN_EXTENT_LEN) + return; + + et = __grab_extent_tree(inode); + + write_lock(&et->lock); + if (et->count) + goto out; + + set_extent_info(&ei, le32_to_cpu(i_ext->fofs), + le32_to_cpu(i_ext->blk), le32_to_cpu(i_ext->len)); + + en = __insert_extent_tree(sbi, et, &ei, NULL); + if (en) { + et->cached_en = en; + + spin_lock(&sbi->extent_lock); + list_add_tail(&en->list, &sbi->extent_list); + spin_unlock(&sbi->extent_lock); + } +out: + write_unlock(&et->lock); + atomic_dec(&et->refcount); +} + +static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs, + struct extent_info *ei) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct extent_tree *et; + struct extent_node *en; + + trace_f2fs_lookup_extent_tree_start(inode, pgofs); + + et = __find_extent_tree(sbi, inode->i_ino); + if (!et) + return false; + + read_lock(&et->lock); + en = __lookup_extent_tree(et, pgofs); + if (en) { + *ei = en->ei; + spin_lock(&sbi->extent_lock); + if (!list_empty(&en->list)) + list_move_tail(&en->list, &sbi->extent_list); + spin_unlock(&sbi->extent_lock); + stat_inc_read_hit(sbi->sb); + } + stat_inc_total_hit(sbi->sb); + read_unlock(&et->lock); + + trace_f2fs_lookup_extent_tree_end(inode, pgofs, en); + + atomic_dec(&et->refcount); + return en ? true : false; +} + +static void f2fs_update_extent_tree(struct inode *inode, pgoff_t fofs, + block_t blkaddr) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct extent_tree *et; + struct extent_node *en = NULL, *en1 = NULL, *en2 = NULL, *en3 = NULL; + struct extent_node *den = NULL; + struct extent_info ei, dei; + unsigned int endofs; + + trace_f2fs_update_extent_tree(inode, fofs, blkaddr); + + et = __grab_extent_tree(inode); + + write_lock(&et->lock); + + /* 1. lookup and remove existing extent info in cache */ + en = __lookup_extent_tree(et, fofs); + if (!en) + goto update_extent; + + dei = en->ei; + __detach_extent_node(sbi, et, en); + + /* 2. if extent can be split more, split and insert the left part */ + if (dei.len > 1) { + /* insert left part of split extent into cache */ + if (fofs - dei.fofs >= F2FS_MIN_EXTENT_LEN) { + set_extent_info(&ei, dei.fofs, dei.blk, + fofs - dei.fofs); + en1 = __insert_extent_tree(sbi, et, &ei, NULL); + } + + /* insert right part of split extent into cache */ + endofs = dei.fofs + dei.len - 1; + if (endofs - fofs >= F2FS_MIN_EXTENT_LEN) { + set_extent_info(&ei, fofs + 1, + fofs - dei.fofs + dei.blk, endofs - fofs); + en2 = __insert_extent_tree(sbi, et, &ei, NULL); + } + } + +update_extent: + /* 3. update extent in extent cache */ + if (blkaddr) { + set_extent_info(&ei, fofs, blkaddr, 1); + en3 = __insert_extent_tree(sbi, et, &ei, &den); + } + + /* 4. update in global extent list */ + spin_lock(&sbi->extent_lock); + if (en && !list_empty(&en->list)) + list_del(&en->list); + /* + * en1 and en2 split from en, they will become more and more smaller + * fragments after splitting several times. So if the length is smaller + * than F2FS_MIN_EXTENT_LEN, we will not add them into extent tree. + */ + if (en1) + list_add_tail(&en1->list, &sbi->extent_list); + if (en2) + list_add_tail(&en2->list, &sbi->extent_list); + if (en3) { + if (list_empty(&en3->list)) + list_add_tail(&en3->list, &sbi->extent_list); + else + list_move_tail(&en3->list, &sbi->extent_list); + } + if (den && !list_empty(&den->list)) + list_del(&den->list); + spin_unlock(&sbi->extent_lock); + + /* 5. release extent node */ + if (en) + kmem_cache_free(extent_node_slab, en); + if (den) + kmem_cache_free(extent_node_slab, den); + + write_unlock(&et->lock); + atomic_dec(&et->refcount); +} + +void f2fs_preserve_extent_tree(struct inode *inode) +{ + struct extent_tree *et; + struct extent_info *ext = &F2FS_I(inode)->ext; + bool sync = false; + + if (!test_opt(F2FS_I_SB(inode), EXTENT_CACHE)) + return; + + et = __find_extent_tree(F2FS_I_SB(inode), inode->i_ino); + if (!et) { + if (ext->len) { + ext->len = 0; + update_inode_page(inode); + } + return; + } + + read_lock(&et->lock); + if (et->count) { + struct extent_node *en; + + if (et->cached_en) { + en = et->cached_en; + } else { + struct rb_node *node = rb_first(&et->root); + + if (!node) + node = rb_last(&et->root); + en = rb_entry(node, struct extent_node, rb_node); + } + + if (__is_extent_same(ext, &en->ei)) + goto out; + + *ext = en->ei; + sync = true; + } else if (ext->len) { + ext->len = 0; + sync = true; + } +out: + read_unlock(&et->lock); + atomic_dec(&et->refcount); + + if (sync) + update_inode_page(inode); +} + +void f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink) +{ + struct extent_tree *treevec[EXT_TREE_VEC_SIZE]; + struct extent_node *en, *tmp; + unsigned long ino = F2FS_ROOT_INO(sbi); + struct radix_tree_iter iter; + void **slot; + unsigned int found; + unsigned int node_cnt = 0, tree_cnt = 0; + + if (!test_opt(sbi, EXTENT_CACHE)) + return; + + if (available_free_memory(sbi, EXTENT_CACHE)) + return; + + spin_lock(&sbi->extent_lock); + list_for_each_entry_safe(en, tmp, &sbi->extent_list, list) { + if (!nr_shrink--) + break; + list_del_init(&en->list); + } + spin_unlock(&sbi->extent_lock); + + down_read(&sbi->extent_tree_lock); + while ((found = radix_tree_gang_lookup(&sbi->extent_tree_root, + (void **)treevec, ino, EXT_TREE_VEC_SIZE))) { + unsigned i; + + ino = treevec[found - 1]->ino + 1; + for (i = 0; i < found; i++) { + struct extent_tree *et = treevec[i]; + + atomic_inc(&et->refcount); + write_lock(&et->lock); + node_cnt += __free_extent_tree(sbi, et, false); + write_unlock(&et->lock); + atomic_dec(&et->refcount); + } + } + up_read(&sbi->extent_tree_lock); + + down_write(&sbi->extent_tree_lock); + radix_tree_for_each_slot(slot, &sbi->extent_tree_root, &iter, + F2FS_ROOT_INO(sbi)) { + struct extent_tree *et = (struct extent_tree *)*slot; + + if (!atomic_read(&et->refcount) && !et->count) { + radix_tree_delete(&sbi->extent_tree_root, et->ino); + kmem_cache_free(extent_tree_slab, et); + sbi->total_ext_tree--; + tree_cnt++; + } + } + up_write(&sbi->extent_tree_lock); + + trace_f2fs_shrink_extent_tree(sbi, node_cnt, tree_cnt); +} + +void f2fs_destroy_extent_tree(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct extent_tree *et; + unsigned int node_cnt = 0; + + if (!test_opt(sbi, EXTENT_CACHE)) + return; + + et = __find_extent_tree(sbi, inode->i_ino); + if (!et) + goto out; + + /* free all extent info belong to this extent tree */ + write_lock(&et->lock); + node_cnt = __free_extent_tree(sbi, et, true); + write_unlock(&et->lock); + + atomic_dec(&et->refcount); + + /* try to find and delete extent tree entry in radix tree */ + down_write(&sbi->extent_tree_lock); + et = radix_tree_lookup(&sbi->extent_tree_root, inode->i_ino); + if (!et) { + up_write(&sbi->extent_tree_lock); + goto out; + } + f2fs_bug_on(sbi, atomic_read(&et->refcount) || et->count); + radix_tree_delete(&sbi->extent_tree_root, inode->i_ino); + kmem_cache_free(extent_tree_slab, et); + sbi->total_ext_tree--; + up_write(&sbi->extent_tree_lock); +out: + trace_f2fs_destroy_extent_tree(inode, node_cnt); return; } +void f2fs_init_extent_cache(struct inode *inode, struct f2fs_extent *i_ext) +{ + if (test_opt(F2FS_I_SB(inode), EXTENT_CACHE)) + f2fs_init_extent_tree(inode, i_ext); + + write_lock(&F2FS_I(inode)->ext_lock); + get_extent_info(&F2FS_I(inode)->ext, *i_ext); + write_unlock(&F2FS_I(inode)->ext_lock); +} + +static bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs, + struct extent_info *ei) +{ + if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT)) + return false; + + if (test_opt(F2FS_I_SB(inode), EXTENT_CACHE)) + return f2fs_lookup_extent_tree(inode, pgofs, ei); + + return lookup_extent_info(inode, pgofs, ei); +} + +void f2fs_update_extent_cache(struct dnode_of_data *dn) +{ + struct f2fs_inode_info *fi = F2FS_I(dn->inode); + pgoff_t fofs; + + f2fs_bug_on(F2FS_I_SB(dn->inode), dn->data_blkaddr == NEW_ADDR); + + if (is_inode_flag_set(fi, FI_NO_EXTENT)) + return; + + fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) + + dn->ofs_in_node; + + if (test_opt(F2FS_I_SB(dn->inode), EXTENT_CACHE)) + return f2fs_update_extent_tree(dn->inode, fofs, + dn->data_blkaddr); + + if (update_extent_info(dn->inode, fofs, dn->data_blkaddr)) + sync_inode_page(dn); +} + struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync) { struct address_space *mapping = inode->i_mapping; struct dnode_of_data dn; struct page *page; + struct extent_info ei; int err; struct f2fs_io_info fio = { .type = DATA, .rw = sync ? READ_SYNC : READA, }; + /* + * If sync is false, it needs to check its block allocation. + * This is need and triggered by two flows: + * gc and truncate_partial_data_page. + */ + if (!sync) + goto search; + page = find_get_page(mapping, index); if (page && PageUptodate(page)) return page; f2fs_put_page(page, 0); +search: + if (f2fs_lookup_extent_cache(inode, index, &ei)) { + dn.data_blkaddr = ei.blk + index - ei.fofs; + goto got_it; + } set_new_dnode(&dn, inode, NULL, NULL, 0); err = get_dnode_of_data(&dn, index, LOOKUP_NODE); @@ -401,6 +948,7 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync) if (unlikely(dn.data_blkaddr == NEW_ADDR)) return ERR_PTR(-EINVAL); +got_it: page = grab_cache_page(mapping, index); if (!page) return ERR_PTR(-ENOMEM); @@ -435,6 +983,7 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index) struct address_space *mapping = inode->i_mapping; struct dnode_of_data dn; struct page *page; + struct extent_info ei; int err; struct f2fs_io_info fio = { .type = DATA, @@ -445,6 +994,11 @@ repeat: if (!page) return ERR_PTR(-ENOMEM); + if (f2fs_lookup_extent_cache(inode, index, &ei)) { + dn.data_blkaddr = ei.blk + index - ei.fofs; + goto got_it; + } + set_new_dnode(&dn, inode, NULL, NULL, 0); err = get_dnode_of_data(&dn, index, LOOKUP_NODE); if (err) { @@ -458,6 +1012,7 @@ repeat: return ERR_PTR(-ENOENT); } +got_it: if (PageUptodate(page)) return page; @@ -569,19 +1124,26 @@ static int __allocate_data_block(struct dnode_of_data *dn) if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC))) return -EPERM; + + dn->data_blkaddr = datablock_addr(dn->node_page, dn->ofs_in_node); + if (dn->data_blkaddr == NEW_ADDR) + goto alloc; + if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1))) return -ENOSPC; +alloc: get_node_info(sbi, dn->nid, &ni); set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version); if (dn->ofs_in_node == 0 && dn->inode_page == dn->node_page) seg = CURSEG_DIRECT_IO; - allocate_data_block(sbi, NULL, NULL_ADDR, &dn->data_blkaddr, &sum, seg); + allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr, + &sum, seg); /* direct IO doesn't use extent cache to maximize the performance */ - __set_data_blkaddr(dn); + set_data_blkaddr(dn); /* update i_size */ fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) + @@ -615,7 +1177,10 @@ static void __allocate_data_blocks(struct inode *inode, loff_t offset, end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); while (dn.ofs_in_node < end_offset && len) { - if (dn.data_blkaddr == NULL_ADDR) { + block_t blkaddr; + + blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); + if (blkaddr == NULL_ADDR || blkaddr == NEW_ADDR) { if (__allocate_data_block(&dn)) goto sync_out; allocated = true; @@ -659,13 +1224,16 @@ static int __get_data_block(struct inode *inode, sector_t iblock, int mode = create ? ALLOC_NODE : LOOKUP_NODE_RA; pgoff_t pgofs, end_offset; int err = 0, ofs = 1; + struct extent_info ei; bool allocated = false; /* Get the page offset from the block offset(iblock) */ pgofs = (pgoff_t)(iblock >> (PAGE_CACHE_SHIFT - blkbits)); - if (check_extent_cache(inode, pgofs, bh_result)) + if (f2fs_lookup_extent_cache(inode, pgofs, &ei)) { + f2fs_map_bh(inode->i_sb, pgofs, &ei, bh_result); goto out; + } if (create) f2fs_lock_op(F2FS_I_SB(inode)); @@ -682,7 +1250,7 @@ static int __get_data_block(struct inode *inode, sector_t iblock, goto put_out; if (dn.data_blkaddr != NULL_ADDR) { - set_buffer_new(bh_result); + clear_buffer_new(bh_result); map_bh(bh_result, inode->i_sb, dn.data_blkaddr); } else if (create) { err = __allocate_data_block(&dn); @@ -727,6 +1295,7 @@ get_next: if (err) goto sync_out; allocated = true; + set_buffer_new(bh_result); blkaddr = dn.data_blkaddr; } /* Give more consecutive addresses for the readahead */ @@ -813,8 +1382,10 @@ int do_write_data_page(struct page *page, struct f2fs_io_info *fio) fio->blk_addr = dn.data_blkaddr; /* This page is already truncated */ - if (fio->blk_addr == NULL_ADDR) + if (fio->blk_addr == NULL_ADDR) { + ClearPageUptodate(page); goto out_writepage; + } set_page_writeback(page); @@ -827,10 +1398,15 @@ int do_write_data_page(struct page *page, struct f2fs_io_info *fio) need_inplace_update(inode))) { rewrite_data_page(page, fio); set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE); + trace_f2fs_do_write_data_page(page, IPU); } else { write_data_page(page, &dn, fio); - update_extent_cache(&dn); + set_data_blkaddr(&dn); + f2fs_update_extent_cache(&dn); + trace_f2fs_do_write_data_page(page, OPU); set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE); + if (page->index == 0) + set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN); } out_writepage: f2fs_put_dnode(&dn); @@ -909,6 +1485,8 @@ done: clear_cold_data(page); out: inode_dec_dirty_pages(inode); + if (err) + ClearPageUptodate(page); unlock_page(page); if (need_balance_fs) f2fs_balance_fs(sbi); @@ -935,7 +1513,6 @@ static int f2fs_write_data_pages(struct address_space *mapping, { struct inode *inode = mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - bool locked = false; int ret; long diff; @@ -950,15 +1527,13 @@ static int f2fs_write_data_pages(struct address_space *mapping, available_free_memory(sbi, DIRTY_DENTS)) goto skip_write; + /* during POR, we don't need to trigger writepage at all. */ + if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) + goto skip_write; + diff = nr_pages_to_write(sbi, DATA, wbc); - if (!S_ISDIR(inode->i_mode)) { - mutex_lock(&sbi->writepages); - locked = true; - } ret = write_cache_pages(mapping, wbc, __f2fs_writepage, mapping); - if (locked) - mutex_unlock(&sbi->writepages); f2fs_submit_merged_bio(sbi, DATA, WRITE); @@ -1118,12 +1693,12 @@ static int f2fs_write_end(struct file *file, return copied; } -static int check_direct_IO(struct inode *inode, int rw, - struct iov_iter *iter, loff_t offset) +static int check_direct_IO(struct inode *inode, struct iov_iter *iter, + loff_t offset) { unsigned blocksize_mask = inode->i_sb->s_blocksize - 1; - if (rw == READ) + if (iov_iter_rw(iter) == READ) return 0; if (offset & blocksize_mask) @@ -1135,8 +1710,8 @@ static int check_direct_IO(struct inode *inode, int rw, return 0; } -static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb, - struct iov_iter *iter, loff_t offset) +static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -1151,19 +1726,19 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb, return err; } - if (check_direct_IO(inode, rw, iter, offset)) + if (check_direct_IO(inode, iter, offset)) return 0; - trace_f2fs_direct_IO_enter(inode, offset, count, rw); + trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter)); - if (rw & WRITE) + if (iov_iter_rw(iter) == WRITE) __allocate_data_blocks(inode, offset, count); - err = blockdev_direct_IO(rw, iocb, inode, iter, offset, get_data_block); - if (err < 0 && (rw & WRITE)) + err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block); + if (err < 0 && iov_iter_rw(iter) == WRITE) f2fs_write_failed(mapping, offset + count); - trace_f2fs_direct_IO_exit(inode, offset, count, rw, err); + trace_f2fs_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), err); return err; } @@ -1236,6 +1811,37 @@ static sector_t f2fs_bmap(struct address_space *mapping, sector_t block) return generic_block_bmap(mapping, block, get_data_block); } +void init_extent_cache_info(struct f2fs_sb_info *sbi) +{ + INIT_RADIX_TREE(&sbi->extent_tree_root, GFP_NOIO); + init_rwsem(&sbi->extent_tree_lock); + INIT_LIST_HEAD(&sbi->extent_list); + spin_lock_init(&sbi->extent_lock); + sbi->total_ext_tree = 0; + atomic_set(&sbi->total_ext_node, 0); +} + +int __init create_extent_cache(void) +{ + extent_tree_slab = f2fs_kmem_cache_create("f2fs_extent_tree", + sizeof(struct extent_tree)); + if (!extent_tree_slab) + return -ENOMEM; + extent_node_slab = f2fs_kmem_cache_create("f2fs_extent_node", + sizeof(struct extent_node)); + if (!extent_node_slab) { + kmem_cache_destroy(extent_tree_slab); + return -ENOMEM; + } + return 0; +} + +void destroy_extent_cache(void) +{ + kmem_cache_destroy(extent_node_slab); + kmem_cache_destroy(extent_tree_slab); +} + const struct address_space_operations f2fs_dblock_aops = { .readpage = f2fs_read_data_page, .readpages = f2fs_read_data_pages, diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index e671373cc8ab..f5388f37217e 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -35,6 +35,8 @@ static void update_general_status(struct f2fs_sb_info *sbi) /* validation check of the segment numbers */ si->hit_ext = sbi->read_hit_ext; si->total_ext = sbi->total_hit_ext; + si->ext_tree = sbi->total_ext_tree; + si->ext_node = atomic_read(&sbi->total_ext_node); si->ndirty_node = get_pages(sbi, F2FS_DIRTY_NODES); si->ndirty_dent = get_pages(sbi, F2FS_DIRTY_DENTS); si->ndirty_dirs = sbi->n_dirty_dirs; @@ -185,6 +187,9 @@ get_cache: si->cache_mem += sbi->n_dirty_dirs * sizeof(struct inode_entry); for (i = 0; i <= UPDATE_INO; i++) si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry); + si->cache_mem += sbi->total_ext_tree * sizeof(struct extent_tree); + si->cache_mem += atomic_read(&sbi->total_ext_node) * + sizeof(struct extent_node); si->page_mem = 0; npages = NODE_MAPPING(sbi)->nrpages; @@ -260,13 +265,20 @@ static int stat_show(struct seq_file *s, void *v) seq_printf(s, "CP calls: %d\n", si->cp_count); seq_printf(s, "GC calls: %d (BG: %d)\n", si->call_count, si->bg_gc); - seq_printf(s, " - data segments : %d\n", si->data_segs); - seq_printf(s, " - node segments : %d\n", si->node_segs); - seq_printf(s, "Try to move %d blocks\n", si->tot_blks); - seq_printf(s, " - data blocks : %d\n", si->data_blks); - seq_printf(s, " - node blocks : %d\n", si->node_blks); + seq_printf(s, " - data segments : %d (%d)\n", + si->data_segs, si->bg_data_segs); + seq_printf(s, " - node segments : %d (%d)\n", + si->node_segs, si->bg_node_segs); + seq_printf(s, "Try to move %d blocks (BG: %d)\n", si->tot_blks, + si->bg_data_blks + si->bg_node_blks); + seq_printf(s, " - data blocks : %d (%d)\n", si->data_blks, + si->bg_data_blks); + seq_printf(s, " - node blocks : %d (%d)\n", si->node_blks, + si->bg_node_blks); seq_printf(s, "\nExtent Hit Ratio: %d / %d\n", si->hit_ext, si->total_ext); + seq_printf(s, "\nExtent Tree Count: %d\n", si->ext_tree); + seq_printf(s, "\nExtent Node Count: %d\n", si->ext_node); seq_puts(s, "\nBalancing F2FS Async:\n"); seq_printf(s, " - inmem: %4d, wb: %4d\n", si->inmem_pages, si->wb_pages); diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index b74097a7f6d9..3a3302ab7871 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -59,9 +59,8 @@ static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = { [S_IFLNK >> S_SHIFT] = F2FS_FT_SYMLINK, }; -void set_de_type(struct f2fs_dir_entry *de, struct inode *inode) +void set_de_type(struct f2fs_dir_entry *de, umode_t mode) { - umode_t mode = inode->i_mode; de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT]; } @@ -127,22 +126,19 @@ struct f2fs_dir_entry *find_target_dentry(struct qstr *name, int *max_slots, *max_slots = 0; while (bit_pos < d->max) { if (!test_bit_le(bit_pos, d->bitmap)) { - if (bit_pos == 0) - max_len = 1; - else if (!test_bit_le(bit_pos - 1, d->bitmap)) - max_len++; bit_pos++; + max_len++; continue; } + de = &d->dentry[bit_pos]; if (early_match_name(name->len, namehash, de) && !memcmp(d->filename[bit_pos], name->name, name->len)) goto found; - if (max_slots && *max_slots >= 0 && max_len > *max_slots) { + if (max_slots && max_len > *max_slots) *max_slots = max_len; - max_len = 0; - } + max_len = 0; /* remain bug on condition */ if (unlikely(!de->name_len)) @@ -219,14 +215,14 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir, unsigned int max_depth; unsigned int level; + *res_page = NULL; + if (f2fs_has_inline_dentry(dir)) return find_in_inline_dir(dir, child, res_page); if (npages == 0) return NULL; - *res_page = NULL; - name_hash = f2fs_dentry_hash(child); max_depth = F2FS_I(dir)->i_current_depth; @@ -285,7 +281,7 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de, lock_page(page); f2fs_wait_on_page_writeback(page, type); de->ino = cpu_to_le32(inode->i_ino); - set_de_type(de, inode); + set_de_type(de, inode->i_mode); f2fs_dentry_kunmap(dir, page); set_page_dirty(page); dir->i_mtime = dir->i_ctime = CURRENT_TIME; @@ -331,14 +327,14 @@ void do_make_empty_dir(struct inode *inode, struct inode *parent, de->hash_code = 0; de->ino = cpu_to_le32(inode->i_ino); memcpy(d->filename[0], ".", 1); - set_de_type(de, inode); + set_de_type(de, inode->i_mode); de = &d->dentry[1]; de->hash_code = 0; de->name_len = cpu_to_le16(2); de->ino = cpu_to_le32(parent->i_ino); memcpy(d->filename[1], "..", 2); - set_de_type(de, inode); + set_de_type(de, parent->i_mode); test_and_set_bit_le(0, (void *)d->bitmap); test_and_set_bit_le(1, (void *)d->bitmap); @@ -435,7 +431,7 @@ error: void update_parent_metadata(struct inode *dir, struct inode *inode, unsigned int current_depth) { - if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) { + if (inode && is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) { if (S_ISDIR(inode->i_mode)) { inc_nlink(dir); set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR); @@ -450,7 +446,7 @@ void update_parent_metadata(struct inode *dir, struct inode *inode, set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR); } - if (is_inode_flag_set(F2FS_I(inode), FI_INC_LINK)) + if (inode && is_inode_flag_set(F2FS_I(inode), FI_INC_LINK)) clear_inode_flag(F2FS_I(inode), FI_INC_LINK); } @@ -474,30 +470,47 @@ next: goto next; } +void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d, + const struct qstr *name, f2fs_hash_t name_hash, + unsigned int bit_pos) +{ + struct f2fs_dir_entry *de; + int slots = GET_DENTRY_SLOTS(name->len); + int i; + + de = &d->dentry[bit_pos]; + de->hash_code = name_hash; + de->name_len = cpu_to_le16(name->len); + memcpy(d->filename[bit_pos], name->name, name->len); + de->ino = cpu_to_le32(ino); + set_de_type(de, mode); + for (i = 0; i < slots; i++) + test_and_set_bit_le(bit_pos + i, (void *)d->bitmap); +} + /* * Caller should grab and release a rwsem by calling f2fs_lock_op() and * f2fs_unlock_op(). */ int __f2fs_add_link(struct inode *dir, const struct qstr *name, - struct inode *inode) + struct inode *inode, nid_t ino, umode_t mode) { unsigned int bit_pos; unsigned int level; unsigned int current_depth; unsigned long bidx, block; f2fs_hash_t dentry_hash; - struct f2fs_dir_entry *de; unsigned int nbucket, nblock; size_t namelen = name->len; struct page *dentry_page = NULL; struct f2fs_dentry_block *dentry_blk = NULL; + struct f2fs_dentry_ptr d; int slots = GET_DENTRY_SLOTS(namelen); - struct page *page; + struct page *page = NULL; int err = 0; - int i; if (f2fs_has_inline_dentry(dir)) { - err = f2fs_add_inline_entry(dir, name, inode); + err = f2fs_add_inline_entry(dir, name, inode, ino, mode); if (!err || err != -EAGAIN) return err; else @@ -547,30 +560,31 @@ start: add_dentry: f2fs_wait_on_page_writeback(dentry_page, DATA); - down_write(&F2FS_I(inode)->i_sem); - page = init_inode_metadata(inode, dir, name, NULL); - if (IS_ERR(page)) { - err = PTR_ERR(page); - goto fail; + if (inode) { + down_write(&F2FS_I(inode)->i_sem); + page = init_inode_metadata(inode, dir, name, NULL); + if (IS_ERR(page)) { + err = PTR_ERR(page); + goto fail; + } } - de = &dentry_blk->dentry[bit_pos]; - de->hash_code = dentry_hash; - de->name_len = cpu_to_le16(namelen); - memcpy(dentry_blk->filename[bit_pos], name->name, name->len); - de->ino = cpu_to_le32(inode->i_ino); - set_de_type(de, inode); - for (i = 0; i < slots; i++) - test_and_set_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap); + + make_dentry_ptr(&d, (void *)dentry_blk, 1); + f2fs_update_dentry(ino, mode, &d, name, dentry_hash, bit_pos); + set_page_dirty(dentry_page); - /* we don't need to mark_inode_dirty now */ - F2FS_I(inode)->i_pino = dir->i_ino; - update_inode(inode, page); - f2fs_put_page(page, 1); + if (inode) { + /* we don't need to mark_inode_dirty now */ + F2FS_I(inode)->i_pino = dir->i_ino; + update_inode(inode, page); + f2fs_put_page(page, 1); + } update_parent_metadata(dir, inode, current_depth); fail: - up_write(&F2FS_I(inode)->i_sem); + if (inode) + up_write(&F2FS_I(inode)->i_sem); if (is_inode_flag_set(F2FS_I(dir), FI_UPDATE_DIR)) { update_inode_page(dir); @@ -669,6 +683,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, if (bit_pos == NR_DENTRY_IN_BLOCK) { truncate_hole(dir, page->index, page->index + 1); clear_page_dirty_for_io(page); + ClearPagePrivate(page); ClearPageUptodate(page); inode_dec_dirty_pages(dir); } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 7fa3313ab0e2..c06a25e5cec3 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -50,6 +50,7 @@ #define F2FS_MOUNT_FLUSH_MERGE 0x00000400 #define F2FS_MOUNT_NOBARRIER 0x00000800 #define F2FS_MOUNT_FASTBOOT 0x00001000 +#define F2FS_MOUNT_EXTENT_CACHE 0x00002000 #define clear_opt(sbi, option) (sbi->mount_opt.opt &= ~F2FS_MOUNT_##option) #define set_opt(sbi, option) (sbi->mount_opt.opt |= F2FS_MOUNT_##option) @@ -102,6 +103,7 @@ enum { CP_UMOUNT, CP_FASTBOOT, CP_SYNC, + CP_RECOVERY, CP_DISCARD, }; @@ -216,6 +218,15 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size, #define F2FS_IOC_RELEASE_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 4) #define F2FS_IOC_ABORT_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 5) +/* + * should be same as XFS_IOC_GOINGDOWN. + * Flags for going down operation used by FS_IOC_GOINGDOWN + */ +#define F2FS_IOC_SHUTDOWN _IOR('X', 125, __u32) /* Shutdown */ +#define F2FS_GOING_DOWN_FULLSYNC 0x0 /* going down with full sync */ +#define F2FS_GOING_DOWN_METASYNC 0x1 /* going down with metadata */ +#define F2FS_GOING_DOWN_NOSYNC 0x2 /* going down */ + #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* * ioctl commands in 32 bit emulation @@ -273,14 +284,34 @@ enum { #define MAX_DIR_RA_PAGES 4 /* maximum ra pages of dir */ +/* vector size for gang look-up from extent cache that consists of radix tree */ +#define EXT_TREE_VEC_SIZE 64 + /* for in-memory extent cache entry */ -#define F2FS_MIN_EXTENT_LEN 16 /* minimum extent length */ +#define F2FS_MIN_EXTENT_LEN 64 /* minimum extent length */ + +/* number of extent info in extent cache we try to shrink */ +#define EXTENT_CACHE_SHRINK_NUMBER 128 struct extent_info { - rwlock_t ext_lock; /* rwlock for consistency */ - unsigned int fofs; /* start offset in a file */ - u32 blk_addr; /* start block address of the extent */ - unsigned int len; /* length of the extent */ + unsigned int fofs; /* start offset in a file */ + u32 blk; /* start block address of the extent */ + unsigned int len; /* length of the extent */ +}; + +struct extent_node { + struct rb_node rb_node; /* rb node located in rb-tree */ + struct list_head list; /* node in global extent list of sbi */ + struct extent_info ei; /* extent info */ +}; + +struct extent_tree { + nid_t ino; /* inode number */ + struct rb_root root; /* root of extent info rb-tree */ + struct extent_node *cached_en; /* recently accessed extent node */ + rwlock_t lock; /* protect extent info rb-tree */ + atomic_t refcount; /* reference count of rb-tree */ + unsigned int count; /* # of extent node in rb-tree*/ }; /* @@ -309,6 +340,7 @@ struct f2fs_inode_info { nid_t i_xattr_nid; /* node id that contains xattrs */ unsigned long long xattr_ver; /* cp version of xattr modification */ struct extent_info ext; /* in-memory extent cache entry */ + rwlock_t ext_lock; /* rwlock for single extent cache */ struct inode_entry *dirty_dir; /* the pointer of dirty dir */ struct radix_tree_root inmem_root; /* radix tree for inmem pages */ @@ -319,21 +351,51 @@ struct f2fs_inode_info { static inline void get_extent_info(struct extent_info *ext, struct f2fs_extent i_ext) { - write_lock(&ext->ext_lock); ext->fofs = le32_to_cpu(i_ext.fofs); - ext->blk_addr = le32_to_cpu(i_ext.blk_addr); + ext->blk = le32_to_cpu(i_ext.blk); ext->len = le32_to_cpu(i_ext.len); - write_unlock(&ext->ext_lock); } static inline void set_raw_extent(struct extent_info *ext, struct f2fs_extent *i_ext) { - read_lock(&ext->ext_lock); i_ext->fofs = cpu_to_le32(ext->fofs); - i_ext->blk_addr = cpu_to_le32(ext->blk_addr); + i_ext->blk = cpu_to_le32(ext->blk); i_ext->len = cpu_to_le32(ext->len); - read_unlock(&ext->ext_lock); +} + +static inline void set_extent_info(struct extent_info *ei, unsigned int fofs, + u32 blk, unsigned int len) +{ + ei->fofs = fofs; + ei->blk = blk; + ei->len = len; +} + +static inline bool __is_extent_same(struct extent_info *ei1, + struct extent_info *ei2) +{ + return (ei1->fofs == ei2->fofs && ei1->blk == ei2->blk && + ei1->len == ei2->len); +} + +static inline bool __is_extent_mergeable(struct extent_info *back, + struct extent_info *front) +{ + return (back->fofs + back->len == front->fofs && + back->blk + back->len == front->blk); +} + +static inline bool __is_back_mergeable(struct extent_info *cur, + struct extent_info *back) +{ + return __is_extent_mergeable(back, cur); +} + +static inline bool __is_front_mergeable(struct extent_info *cur, + struct extent_info *front) +{ + return __is_extent_mergeable(cur, front); } struct f2fs_nm_info { @@ -502,6 +564,10 @@ enum page_type { META, NR_PAGE_TYPE, META_FLUSH, + INMEM, /* the below types are used by tracepoints only. */ + INMEM_DROP, + IPU, + OPU, }; struct f2fs_io_info { @@ -559,7 +625,6 @@ struct f2fs_sb_info { struct mutex cp_mutex; /* checkpoint procedure lock */ struct rw_semaphore cp_rwsem; /* blocking FS operations */ struct rw_semaphore node_write; /* locking node writes */ - struct mutex writepages; /* mutex for writepages() */ wait_queue_head_t cp_wait; struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */ @@ -571,6 +636,14 @@ struct f2fs_sb_info { struct list_head dir_inode_list; /* dir inode list */ spinlock_t dir_inode_lock; /* for dir inode list lock */ + /* for extent tree cache */ + struct radix_tree_root extent_tree_root;/* cache extent cache entries */ + struct rw_semaphore extent_tree_lock; /* locking extent radix tree */ + struct list_head extent_list; /* lru list for shrinker */ + spinlock_t extent_lock; /* locking extent lru list */ + int total_ext_tree; /* extent tree count */ + atomic_t total_ext_node; /* extent info count */ + /* basic filesystem units */ unsigned int log_sectors_per_block; /* log2 sectors per block */ unsigned int log_blocksize; /* log2 block size */ @@ -920,12 +993,17 @@ static inline unsigned long __bitmap_size(struct f2fs_sb_info *sbi, int flag) return 0; } +static inline block_t __cp_payload(struct f2fs_sb_info *sbi) +{ + return le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload); +} + static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); int offset; - if (le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload) > 0) { + if (__cp_payload(sbi) > 0) { if (flag == NAT_BITMAP) return &ckpt->sit_nat_version_bitmap; else @@ -1166,8 +1244,10 @@ enum { FI_NEED_IPU, /* used for ipu per file */ FI_ATOMIC_FILE, /* indicate atomic file */ FI_VOLATILE_FILE, /* indicate volatile file */ + FI_FIRST_BLOCK_WRITTEN, /* indicate #0 data block was written */ FI_DROP_CACHE, /* drop dirty page cache */ FI_DATA_EXIST, /* indicate data exists */ + FI_INLINE_DOTS, /* indicate inline dot dentries */ }; static inline void set_inode_flag(struct f2fs_inode_info *fi, int flag) @@ -1204,6 +1284,8 @@ static inline void get_inline_info(struct f2fs_inode_info *fi, set_inode_flag(fi, FI_INLINE_DENTRY); if (ri->i_inline & F2FS_DATA_EXIST) set_inode_flag(fi, FI_DATA_EXIST); + if (ri->i_inline & F2FS_INLINE_DOTS) + set_inode_flag(fi, FI_INLINE_DOTS); } static inline void set_raw_inline(struct f2fs_inode_info *fi, @@ -1219,6 +1301,8 @@ static inline void set_raw_inline(struct f2fs_inode_info *fi, ri->i_inline |= F2FS_INLINE_DENTRY; if (is_inode_flag_set(fi, FI_DATA_EXIST)) ri->i_inline |= F2FS_DATA_EXIST; + if (is_inode_flag_set(fi, FI_INLINE_DOTS)) + ri->i_inline |= F2FS_INLINE_DOTS; } static inline int f2fs_has_inline_xattr(struct inode *inode) @@ -1264,6 +1348,11 @@ static inline int f2fs_exist_data(struct inode *inode) return is_inode_flag_set(F2FS_I(inode), FI_DATA_EXIST); } +static inline int f2fs_has_inline_dots(struct inode *inode) +{ + return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DOTS); +} + static inline bool f2fs_is_atomic_file(struct inode *inode) { return is_inode_flag_set(F2FS_I(inode), FI_ATOMIC_FILE); @@ -1274,6 +1363,11 @@ static inline bool f2fs_is_volatile_file(struct inode *inode) return is_inode_flag_set(F2FS_I(inode), FI_VOLATILE_FILE); } +static inline bool f2fs_is_first_block_written(struct inode *inode) +{ + return is_inode_flag_set(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN); +} + static inline bool f2fs_is_drop_cache(struct inode *inode) { return is_inode_flag_set(F2FS_I(inode), FI_DROP_CACHE); @@ -1290,12 +1384,6 @@ static inline int f2fs_has_inline_dentry(struct inode *inode) return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DENTRY); } -static inline void *inline_dentry_addr(struct page *page) -{ - struct f2fs_inode *ri = F2FS_INODE(page); - return (void *)&(ri->i_addr[1]); -} - static inline void f2fs_dentry_kunmap(struct inode *dir, struct page *page) { if (!f2fs_has_inline_dentry(dir)) @@ -1363,7 +1451,7 @@ struct dentry *f2fs_get_parent(struct dentry *child); * dir.c */ extern unsigned char f2fs_filetype_table[F2FS_FT_MAX]; -void set_de_type(struct f2fs_dir_entry *, struct inode *); +void set_de_type(struct f2fs_dir_entry *, umode_t); struct f2fs_dir_entry *find_target_dentry(struct qstr *, int *, struct f2fs_dentry_ptr *); bool f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *, @@ -1382,7 +1470,10 @@ ino_t f2fs_inode_by_name(struct inode *, struct qstr *); void f2fs_set_link(struct inode *, struct f2fs_dir_entry *, struct page *, struct inode *); int update_dent_inode(struct inode *, const struct qstr *); -int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *); +void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *, + const struct qstr *, f2fs_hash_t , unsigned int); +int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *, nid_t, + umode_t); void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *, struct inode *); int f2fs_do_tmpfile(struct inode *, struct inode *); @@ -1392,7 +1483,7 @@ bool f2fs_empty_dir(struct inode *); static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) { return __f2fs_add_link(dentry->d_parent->d_inode, &dentry->d_name, - inode); + inode, inode->i_ino, inode->i_mode); } /* @@ -1519,14 +1610,22 @@ int f2fs_submit_page_bio(struct f2fs_sb_info *, struct page *, struct f2fs_io_info *); void f2fs_submit_page_mbio(struct f2fs_sb_info *, struct page *, struct f2fs_io_info *); +void set_data_blkaddr(struct dnode_of_data *); int reserve_new_block(struct dnode_of_data *); int f2fs_reserve_block(struct dnode_of_data *, pgoff_t); -void update_extent_cache(struct dnode_of_data *); +void f2fs_shrink_extent_tree(struct f2fs_sb_info *, int); +void f2fs_destroy_extent_tree(struct inode *); +void f2fs_init_extent_cache(struct inode *, struct f2fs_extent *); +void f2fs_update_extent_cache(struct dnode_of_data *); +void f2fs_preserve_extent_tree(struct inode *); struct page *find_data_page(struct inode *, pgoff_t, bool); struct page *get_lock_data_page(struct inode *, pgoff_t); struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool); int do_write_data_page(struct page *, struct f2fs_io_info *); int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64); +void init_extent_cache_info(struct f2fs_sb_info *); +int __init create_extent_cache(void); +void destroy_extent_cache(void); void f2fs_invalidate_page(struct page *, unsigned int, unsigned int); int f2fs_release_page(struct page *, gfp_t); @@ -1554,7 +1653,7 @@ struct f2fs_stat_info { struct f2fs_sb_info *sbi; int all_area_segs, sit_area_segs, nat_area_segs, ssa_area_segs; int main_area_segs, main_area_sections, main_area_zones; - int hit_ext, total_ext; + int hit_ext, total_ext, ext_tree, ext_node; int ndirty_node, ndirty_dent, ndirty_dirs, ndirty_meta; int nats, dirty_nats, sits, dirty_sits, fnids; int total_count, utilization; @@ -1566,7 +1665,9 @@ struct f2fs_stat_info { int dirty_count, node_pages, meta_pages; int prefree_count, call_count, cp_count; int tot_segs, node_segs, data_segs, free_segs, free_secs; + int bg_node_segs, bg_data_segs; int tot_blks, data_blks, node_blks; + int bg_data_blks, bg_node_blks; int curseg[NR_CURSEG_TYPE]; int cursec[NR_CURSEG_TYPE]; int curzone[NR_CURSEG_TYPE]; @@ -1615,31 +1716,36 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) ((sbi)->block_count[(curseg)->alloc_type]++) #define stat_inc_inplace_blocks(sbi) \ (atomic_inc(&(sbi)->inplace_count)) -#define stat_inc_seg_count(sbi, type) \ +#define stat_inc_seg_count(sbi, type, gc_type) \ do { \ struct f2fs_stat_info *si = F2FS_STAT(sbi); \ (si)->tot_segs++; \ - if (type == SUM_TYPE_DATA) \ + if (type == SUM_TYPE_DATA) { \ si->data_segs++; \ - else \ + si->bg_data_segs += (gc_type == BG_GC) ? 1 : 0; \ + } else { \ si->node_segs++; \ + si->bg_node_segs += (gc_type == BG_GC) ? 1 : 0; \ + } \ } while (0) #define stat_inc_tot_blk_count(si, blks) \ (si->tot_blks += (blks)) -#define stat_inc_data_blk_count(sbi, blks) \ +#define stat_inc_data_blk_count(sbi, blks, gc_type) \ do { \ struct f2fs_stat_info *si = F2FS_STAT(sbi); \ stat_inc_tot_blk_count(si, blks); \ si->data_blks += (blks); \ + si->bg_data_blks += (gc_type == BG_GC) ? (blks) : 0; \ } while (0) -#define stat_inc_node_blk_count(sbi, blks) \ +#define stat_inc_node_blk_count(sbi, blks, gc_type) \ do { \ struct f2fs_stat_info *si = F2FS_STAT(sbi); \ stat_inc_tot_blk_count(si, blks); \ si->node_blks += (blks); \ + si->bg_node_blks += (gc_type == BG_GC) ? (blks) : 0; \ } while (0) int f2fs_build_stats(struct f2fs_sb_info *); @@ -1661,10 +1767,10 @@ void f2fs_destroy_root_stats(void); #define stat_inc_seg_type(sbi, curseg) #define stat_inc_block_count(sbi, curseg) #define stat_inc_inplace_blocks(sbi) -#define stat_inc_seg_count(si, type) +#define stat_inc_seg_count(sbi, type, gc_type) #define stat_inc_tot_blk_count(si, blks) -#define stat_inc_data_blk_count(si, blks) -#define stat_inc_node_blk_count(sbi, blks) +#define stat_inc_data_blk_count(sbi, blks, gc_type) +#define stat_inc_node_blk_count(sbi, blks, gc_type) static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; } static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { } @@ -1688,6 +1794,7 @@ extern struct kmem_cache *inode_entry_slab; */ bool f2fs_may_inline(struct inode *); void read_inline_data(struct page *, struct page *); +bool truncate_inline_inode(struct page *, u64); int f2fs_read_inline_data(struct inode *, struct page *); int f2fs_convert_inline_page(struct dnode_of_data *, struct page *); int f2fs_convert_inline_inode(struct inode *); @@ -1697,7 +1804,8 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *, struct qstr *, struct page **); struct f2fs_dir_entry *f2fs_parent_inline_dir(struct inode *, struct page **); int make_empty_inline_dir(struct inode *inode, struct inode *, struct page *); -int f2fs_add_inline_entry(struct inode *, const struct qstr *, struct inode *); +int f2fs_add_inline_entry(struct inode *, const struct qstr *, struct inode *, + nid_t, umode_t); void f2fs_delete_inline_entry(struct f2fs_dir_entry *, struct page *, struct inode *, struct inode *); bool f2fs_empty_inline_dir(struct inode *); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 98dac27bc3f7..a6f3f6186588 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -241,6 +241,8 @@ go_write: * will be used only for fsynced inodes after checkpoint. */ try_to_fix_pino(inode); + clear_inode_flag(fi, FI_APPEND_WRITE); + clear_inode_flag(fi, FI_UPDATE_WRITE); goto out; } sync_nodes: @@ -433,8 +435,12 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count) continue; dn->data_blkaddr = NULL_ADDR; - update_extent_cache(dn); + set_data_blkaddr(dn); + f2fs_update_extent_cache(dn); invalidate_blocks(sbi, blkaddr); + if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page)) + clear_inode_flag(F2FS_I(dn->inode), + FI_FIRST_BLOCK_WRITTEN); nr_free++; } if (nr_free) { @@ -454,15 +460,16 @@ void truncate_data_blocks(struct dnode_of_data *dn) truncate_data_blocks_range(dn, ADDRS_PER_BLOCK); } -static int truncate_partial_data_page(struct inode *inode, u64 from) +static int truncate_partial_data_page(struct inode *inode, u64 from, + bool force) { unsigned offset = from & (PAGE_CACHE_SIZE - 1); struct page *page; - if (!offset) + if (!offset && !force) return 0; - page = find_data_page(inode, from >> PAGE_CACHE_SHIFT, false); + page = find_data_page(inode, from >> PAGE_CACHE_SHIFT, force); if (IS_ERR(page)) return 0; @@ -473,7 +480,8 @@ static int truncate_partial_data_page(struct inode *inode, u64 from) f2fs_wait_on_page_writeback(page, DATA); zero_user(page, offset, PAGE_CACHE_SIZE - offset); - set_page_dirty(page); + if (!force) + set_page_dirty(page); out: f2fs_put_page(page, 1); return 0; @@ -487,6 +495,7 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock) pgoff_t free_from; int count = 0, err = 0; struct page *ipage; + bool truncate_page = false; trace_f2fs_truncate_blocks_enter(inode, from); @@ -502,7 +511,10 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock) } if (f2fs_has_inline_data(inode)) { + if (truncate_inline_inode(ipage, from)) + set_page_dirty(ipage); f2fs_put_page(ipage, 1); + truncate_page = true; goto out; } @@ -533,7 +545,7 @@ out: /* lastly zero out the first data page */ if (!err) - err = truncate_partial_data_page(inode, from); + err = truncate_partial_data_page(inode, from, truncate_page); trace_f2fs_truncate_blocks_exit(inode, err); return err; @@ -997,6 +1009,9 @@ static int f2fs_ioc_release_volatile_write(struct file *filp) if (!f2fs_is_volatile_file(inode)) return 0; + if (!f2fs_is_first_block_written(inode)) + return truncate_partial_data_page(inode, 0, true); + punch_hole(inode, 0, F2FS_BLKSIZE); return 0; } @@ -1029,6 +1044,41 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp) return ret; } +static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct super_block *sb = sbi->sb; + __u32 in; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (get_user(in, (__u32 __user *)arg)) + return -EFAULT; + + switch (in) { + case F2FS_GOING_DOWN_FULLSYNC: + sb = freeze_bdev(sb->s_bdev); + if (sb && !IS_ERR(sb)) { + f2fs_stop_checkpoint(sbi); + thaw_bdev(sb->s_bdev, sb); + } + break; + case F2FS_GOING_DOWN_METASYNC: + /* do checkpoint only */ + f2fs_sync_fs(sb, 1); + f2fs_stop_checkpoint(sbi); + break; + case F2FS_GOING_DOWN_NOSYNC: + f2fs_stop_checkpoint(sbi); + break; + default: + return -EINVAL; + } + return 0; +} + static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -1078,6 +1128,8 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_release_volatile_write(filp); case F2FS_IOC_ABORT_VOLATILE_WRITE: return f2fs_ioc_abort_volatile_write(filp); + case F2FS_IOC_SHUTDOWN: + return f2fs_ioc_shutdown(filp, arg); case FITRIM: return f2fs_ioc_fitrim(filp, arg); default: @@ -1104,8 +1156,6 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) const struct file_operations f2fs_file_operations = { .llseek = f2fs_llseek, - .read = new_sync_read, - .write = new_sync_write, .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, .open = generic_file_open, diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 76adbc3641f1..ed58211fe79b 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -435,7 +435,7 @@ next_step: set_page_dirty(node_page); } f2fs_put_page(node_page, 1); - stat_inc_node_blk_count(sbi, 1); + stat_inc_node_blk_count(sbi, 1, gc_type); } if (initial) { @@ -622,7 +622,7 @@ next_step: if (IS_ERR(data_page)) continue; move_data_page(inode, data_page, gc_type); - stat_inc_data_blk_count(sbi, 1); + stat_inc_data_blk_count(sbi, 1, gc_type); } } @@ -680,7 +680,7 @@ static void do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno, } blk_finish_plug(&plug); - stat_inc_seg_count(sbi, GET_SUM_TYPE((&sum->footer))); + stat_inc_seg_count(sbi, GET_SUM_TYPE((&sum->footer)), gc_type); stat_inc_call_count(sbi->stat_info); f2fs_put_page(sum_page, 1); diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 1484c00133cd..8140e4f0e538 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -21,7 +21,7 @@ bool f2fs_may_inline(struct inode *inode) if (f2fs_is_atomic_file(inode)) return false; - if (!S_ISREG(inode->i_mode)) + if (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode)) return false; if (i_size_read(inode) > MAX_INLINE_DATA) @@ -50,10 +50,19 @@ void read_inline_data(struct page *page, struct page *ipage) SetPageUptodate(page); } -static void truncate_inline_data(struct page *ipage) +bool truncate_inline_inode(struct page *ipage, u64 from) { + void *addr; + + if (from >= MAX_INLINE_DATA) + return false; + + addr = inline_data_addr(ipage); + f2fs_wait_on_page_writeback(ipage, NODE); - memset(inline_data_addr(ipage), 0, MAX_INLINE_DATA); + memset(addr + from, 0, MAX_INLINE_DATA - from); + + return true; } int f2fs_read_inline_data(struct inode *inode, struct page *page) @@ -122,7 +131,8 @@ no_update: set_page_writeback(page); fio.blk_addr = dn->data_blkaddr; write_data_page(page, dn, &fio); - update_extent_cache(dn); + set_data_blkaddr(dn); + f2fs_update_extent_cache(dn); f2fs_wait_on_page_writeback(page, DATA); if (dirty) inode_dec_dirty_pages(dn->inode); @@ -131,7 +141,7 @@ no_update: set_inode_flag(F2FS_I(dn->inode), FI_APPEND_WRITE); /* clear inline data and flag after data writeback */ - truncate_inline_data(dn->inode_page); + truncate_inline_inode(dn->inode_page, 0); clear_out: stat_dec_inline_inode(dn->inode); f2fs_clear_inline_inode(dn->inode); @@ -245,7 +255,7 @@ process_inline: if (f2fs_has_inline_data(inode)) { ipage = get_node_page(sbi, inode->i_ino); f2fs_bug_on(sbi, IS_ERR(ipage)); - truncate_inline_data(ipage); + truncate_inline_inode(ipage, 0); f2fs_clear_inline_inode(inode); update_inode(inode, ipage); f2fs_put_page(ipage, 1); @@ -363,7 +373,7 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage, set_page_dirty(page); /* clear inline dir and flag after data writeback */ - truncate_inline_data(ipage); + truncate_inline_inode(ipage, 0); stat_dec_inline_dir(dir); clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY); @@ -380,21 +390,18 @@ out: } int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name, - struct inode *inode) + struct inode *inode, nid_t ino, umode_t mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct page *ipage; unsigned int bit_pos; f2fs_hash_t name_hash; - struct f2fs_dir_entry *de; size_t namelen = name->len; struct f2fs_inline_dentry *dentry_blk = NULL; + struct f2fs_dentry_ptr d; int slots = GET_DENTRY_SLOTS(namelen); - struct page *page; + struct page *page = NULL; int err = 0; - int i; - - name_hash = f2fs_dentry_hash(name); ipage = get_node_page(sbi, dir->i_ino); if (IS_ERR(ipage)) @@ -410,32 +417,34 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name, goto out; } - down_write(&F2FS_I(inode)->i_sem); - page = init_inode_metadata(inode, dir, name, ipage); - if (IS_ERR(page)) { - err = PTR_ERR(page); - goto fail; + if (inode) { + down_write(&F2FS_I(inode)->i_sem); + page = init_inode_metadata(inode, dir, name, ipage); + if (IS_ERR(page)) { + err = PTR_ERR(page); + goto fail; + } } f2fs_wait_on_page_writeback(ipage, NODE); - de = &dentry_blk->dentry[bit_pos]; - de->hash_code = name_hash; - de->name_len = cpu_to_le16(namelen); - memcpy(dentry_blk->filename[bit_pos], name->name, name->len); - de->ino = cpu_to_le32(inode->i_ino); - set_de_type(de, inode); - for (i = 0; i < slots; i++) - test_and_set_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap); + + name_hash = f2fs_dentry_hash(name); + make_dentry_ptr(&d, (void *)dentry_blk, 2); + f2fs_update_dentry(ino, mode, &d, name, name_hash, bit_pos); + set_page_dirty(ipage); /* we don't need to mark_inode_dirty now */ - F2FS_I(inode)->i_pino = dir->i_ino; - update_inode(inode, page); - f2fs_put_page(page, 1); + if (inode) { + F2FS_I(inode)->i_pino = dir->i_ino; + update_inode(inode, page); + f2fs_put_page(page, 1); + } update_parent_metadata(dir, inode, 0); fail: - up_write(&F2FS_I(inode)->i_sem); + if (inode) + up_write(&F2FS_I(inode)->i_sem); if (is_inode_flag_set(F2FS_I(dir), FI_UPDATE_DIR)) { update_inode(dir, ipage); diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 2d002e3738a7..e622ec95409e 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -51,6 +51,15 @@ static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri) } } +static bool __written_first_block(struct f2fs_inode *ri) +{ + block_t addr = le32_to_cpu(ri->i_addr[0]); + + if (addr != NEW_ADDR && addr != NULL_ADDR) + return true; + return false; +} + static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri) { if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) { @@ -130,7 +139,8 @@ static int do_read_inode(struct inode *inode) fi->i_pino = le32_to_cpu(ri->i_pino); fi->i_dir_level = ri->i_dir_level; - get_extent_info(&fi->ext, ri->i_ext); + f2fs_init_extent_cache(inode, &ri->i_ext); + get_inline_info(fi, ri); /* check data exist */ @@ -140,6 +150,9 @@ static int do_read_inode(struct inode *inode) /* get rdev by using inline_info */ __get_inode_rdev(inode, ri); + if (__written_first_block(ri)) + set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN); + f2fs_put_page(node_page, 1); stat_inc_inline_inode(inode); @@ -220,7 +233,11 @@ void update_inode(struct inode *inode, struct page *node_page) ri->i_links = cpu_to_le32(inode->i_nlink); ri->i_size = cpu_to_le64(i_size_read(inode)); ri->i_blocks = cpu_to_le64(inode->i_blocks); + + read_lock(&F2FS_I(inode)->ext_lock); set_raw_extent(&F2FS_I(inode)->ext, &ri->i_ext); + read_unlock(&F2FS_I(inode)->ext_lock); + set_raw_inline(F2FS_I(inode), ri); ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec); @@ -328,6 +345,12 @@ void f2fs_evict_inode(struct inode *inode) no_delete: stat_dec_inline_dir(inode); stat_dec_inline_inode(inode); + + /* update extent info in inode */ + if (inode->i_nlink) + f2fs_preserve_extent_tree(inode); + f2fs_destroy_extent_tree(inode); + invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino); if (xnid) invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid); diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index e79639a9787a..407dde3d7a92 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -14,6 +14,7 @@ #include <linux/sched.h> #include <linux/ctype.h> #include <linux/dcache.h> +#include <linux/namei.h> #include "f2fs.h" #include "node.h" @@ -187,6 +188,44 @@ struct dentry *f2fs_get_parent(struct dentry *child) return d_obtain_alias(f2fs_iget(child->d_inode->i_sb, ino)); } +static int __recover_dot_dentries(struct inode *dir, nid_t pino) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + struct qstr dot = QSTR_INIT(".", 1); + struct qstr dotdot = QSTR_INIT("..", 2); + struct f2fs_dir_entry *de; + struct page *page; + int err = 0; + + f2fs_lock_op(sbi); + + de = f2fs_find_entry(dir, &dot, &page); + if (de) { + f2fs_dentry_kunmap(dir, page); + f2fs_put_page(page, 0); + } else { + err = __f2fs_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR); + if (err) + goto out; + } + + de = f2fs_find_entry(dir, &dotdot, &page); + if (de) { + f2fs_dentry_kunmap(dir, page); + f2fs_put_page(page, 0); + } else { + err = __f2fs_add_link(dir, &dotdot, NULL, pino, S_IFDIR); + } +out: + if (!err) { + clear_inode_flag(F2FS_I(dir), FI_INLINE_DOTS); + mark_inode_dirty(dir); + } + + f2fs_unlock_op(sbi); + return err; +} + static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { @@ -206,6 +245,16 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, inode = f2fs_iget(dir->i_sb, ino); if (IS_ERR(inode)) return ERR_CAST(inode); + + if (f2fs_has_inline_dots(inode)) { + int err; + + err = __recover_dot_dentries(inode, dir->i_ino); + if (err) { + iget_failed(inode); + return ERR_PTR(err); + } + } } return d_splice_alias(inode, dentry); @@ -247,6 +296,23 @@ fail: return err; } +static void *f2fs_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + struct page *page; + + page = page_follow_link_light(dentry, nd); + if (IS_ERR(page)) + return page; + + /* this is broken symlink case */ + if (*nd_get_link(nd) == 0) { + kunmap(page); + page_cache_release(page); + return ERR_PTR(-ENOENT); + } + return page; +} + static int f2fs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) { @@ -276,6 +342,17 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, d_instantiate(dentry, inode); unlock_new_inode(inode); + /* + * Let's flush symlink data in order to avoid broken symlink as much as + * possible. Nevertheless, fsyncing is the best way, but there is no + * way to get a file descriptor in order to flush that. + * + * Note that, it needs to do dir->fsync to make this recoverable. + * If the symlink path is stored into inline_data, there is no + * performance regression. + */ + filemap_write_and_wait_range(inode->i_mapping, 0, symlen - 1); + if (IS_DIRSYNC(dir)) f2fs_sync_fs(sbi->sb, 1); return err; @@ -693,6 +770,8 @@ static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) f2fs_unlock_op(sbi); alloc_nid_done(sbi, inode->i_ino); + + stat_inc_inline_inode(inode); d_tmpfile(dentry, inode); unlock_new_inode(inode); return 0; @@ -729,7 +808,7 @@ const struct inode_operations f2fs_dir_inode_operations = { const struct inode_operations f2fs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, + .follow_link = f2fs_follow_link, .put_link = page_put_link, .getattr = f2fs_getattr, .setattr = f2fs_setattr, diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 97bd9d3db882..8ab0cf1930bd 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -41,7 +41,9 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) /* only uses low memory */ avail_ram = val.totalram - val.totalhigh; - /* give 25%, 25%, 50%, 50% memory for each components respectively */ + /* + * give 25%, 25%, 50%, 50%, 50% memory for each components respectively + */ if (type == FREE_NIDS) { mem_size = (nm_i->fcnt * sizeof(struct free_nid)) >> PAGE_CACHE_SHIFT; @@ -62,6 +64,11 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) mem_size += (sbi->im[i].ino_num * sizeof(struct ino_entry)) >> PAGE_CACHE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); + } else if (type == EXTENT_CACHE) { + mem_size = (sbi->total_ext_tree * sizeof(struct extent_tree) + + atomic_read(&sbi->total_ext_node) * + sizeof(struct extent_node)) >> PAGE_CACHE_SHIFT; + res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); } else { if (sbi->sb->s_bdi->dirty_exceeded) return false; @@ -494,7 +501,7 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) /* if inline_data is set, should not report any block indices */ if (f2fs_has_inline_data(dn->inode) && index) { - err = -EINVAL; + err = -ENOENT; f2fs_put_page(npage[0], 1); goto release_out; } @@ -995,6 +1002,7 @@ static int read_node_page(struct page *page, int rw) get_node_info(sbi, page->index, &ni); if (unlikely(ni.blk_addr == NULL_ADDR)) { + ClearPageUptodate(page); f2fs_put_page(page, 1); return -ENOENT; } @@ -1306,6 +1314,7 @@ static int f2fs_write_node_page(struct page *page, /* This page is already truncated */ if (unlikely(ni.blk_addr == NULL_ADDR)) { + ClearPageUptodate(page); dec_page_count(sbi, F2FS_DIRTY_NODES); unlock_page(page); return 0; @@ -1821,6 +1830,7 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, struct f2fs_nat_block *nat_blk; struct nat_entry *ne, *cur; struct page *page = NULL; + struct f2fs_nm_info *nm_i = NM_I(sbi); /* * there are two steps to flush nat entries: @@ -1874,7 +1884,9 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, f2fs_bug_on(sbi, set->entry_cnt); + down_write(&nm_i->nat_tree_lock); radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set); + up_write(&nm_i->nat_tree_lock); kmem_cache_free(nat_entry_set_slab, set); } @@ -1902,6 +1914,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi) if (!__has_cursum_space(sum, nm_i->dirty_nat_cnt, NAT_JOURNAL)) remove_nats_in_journal(sbi); + down_write(&nm_i->nat_tree_lock); while ((found = __gang_lookup_nat_set(nm_i, set_idx, SETVEC_SIZE, setvec))) { unsigned idx; @@ -1910,6 +1923,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi) __adjust_nat_entry_set(setvec[idx], &sets, MAX_NAT_JENTRIES(sum)); } + up_write(&nm_i->nat_tree_lock); /* flush dirty nats in nat entry set */ list_for_each_entry_safe(set, tmp, &sets, set_list) diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index f405bbf2435a..c56026f1725c 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -120,6 +120,7 @@ enum mem_type { NAT_ENTRIES, /* indicates the cached nat entry */ DIRTY_DENTS, /* indicates dirty dentry pages */ INO_ENTRIES, /* indicates inode entries */ + EXTENT_CACHE, /* indicates extent cache */ BASE_CHECK, /* check kernel status */ }; diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 41afb9534bbd..8d8ea99f2156 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -93,10 +93,9 @@ static int recover_dentry(struct inode *inode, struct page *ipage) } retry: de = f2fs_find_entry(dir, &name, &page); - if (de && inode->i_ino == le32_to_cpu(de->ino)) { - clear_inode_flag(F2FS_I(inode), FI_INC_LINK); + if (de && inode->i_ino == le32_to_cpu(de->ino)) goto out_unmap_put; - } + if (de) { einode = f2fs_iget(inode->i_sb, le32_to_cpu(de->ino)); if (IS_ERR(einode)) { @@ -115,7 +114,7 @@ retry: iput(einode); goto retry; } - err = __f2fs_add_link(dir, &name, inode); + err = __f2fs_add_link(dir, &name, inode, inode->i_ino, inode->i_mode); if (err) goto out_err; @@ -187,11 +186,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head) goto next; entry = get_fsync_inode(head, ino_of_node(page)); - if (entry) { - if (IS_INODE(page) && is_dent_dnode(page)) - set_inode_flag(F2FS_I(entry->inode), - FI_INC_LINK); - } else { + if (!entry) { if (IS_INODE(page) && is_dent_dnode(page)) { err = recover_inode_page(sbi, page); if (err) @@ -212,8 +207,10 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head) if (IS_ERR(entry->inode)) { err = PTR_ERR(entry->inode); kmem_cache_free(fsync_entry_slab, entry); - if (err == -ENOENT) + if (err == -ENOENT) { + err = 0; goto next; + } break; } list_add_tail(&entry->list, head); @@ -256,6 +253,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, struct f2fs_summary_block *sum_node; struct f2fs_summary sum; struct page *sum_page, *node_page; + struct dnode_of_data tdn = *dn; nid_t ino, nid; struct inode *inode; unsigned int offset; @@ -283,17 +281,15 @@ got_it: /* Use the locked dnode page and inode */ nid = le32_to_cpu(sum.nid); if (dn->inode->i_ino == nid) { - struct dnode_of_data tdn = *dn; tdn.nid = nid; + if (!dn->inode_page_locked) + lock_page(dn->inode_page); tdn.node_page = dn->inode_page; tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node); - truncate_data_blocks_range(&tdn, 1); - return 0; + goto truncate_out; } else if (dn->nid == nid) { - struct dnode_of_data tdn = *dn; tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node); - truncate_data_blocks_range(&tdn, 1); - return 0; + goto truncate_out; } /* Get the node page */ @@ -317,18 +313,33 @@ got_it: bidx = start_bidx_of_node(offset, F2FS_I(inode)) + le16_to_cpu(sum.ofs_in_node); - if (ino != dn->inode->i_ino) { - truncate_hole(inode, bidx, bidx + 1); + /* + * if inode page is locked, unlock temporarily, but its reference + * count keeps alive. + */ + if (ino == dn->inode->i_ino && dn->inode_page_locked) + unlock_page(dn->inode_page); + + set_new_dnode(&tdn, inode, NULL, NULL, 0); + if (get_dnode_of_data(&tdn, bidx, LOOKUP_NODE)) + goto out; + + if (tdn.data_blkaddr == blkaddr) + truncate_data_blocks_range(&tdn, 1); + + f2fs_put_dnode(&tdn); +out: + if (ino != dn->inode->i_ino) iput(inode); - } else { - struct dnode_of_data tdn; - set_new_dnode(&tdn, inode, dn->inode_page, NULL, 0); - if (get_dnode_of_data(&tdn, bidx, LOOKUP_NODE)) - return 0; - if (tdn.data_blkaddr != NULL_ADDR) - truncate_data_blocks_range(&tdn, 1); - f2fs_put_page(tdn.node_page, 1); - } + else if (dn->inode_page_locked) + lock_page(dn->inode_page); + return 0; + +truncate_out: + if (datablock_addr(tdn.node_page, tdn.ofs_in_node) == blkaddr) + truncate_data_blocks_range(&tdn, 1); + if (dn->inode->i_ino == nid && !dn->inode_page_locked) + unlock_page(dn->inode_page); return 0; } @@ -384,7 +395,9 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, src = datablock_addr(dn.node_page, dn.ofs_in_node); dest = datablock_addr(page, dn.ofs_in_node); - if (src != dest && dest != NEW_ADDR && dest != NULL_ADDR) { + if (src != dest && dest != NEW_ADDR && dest != NULL_ADDR && + dest >= MAIN_BLKADDR(sbi) && dest < MAX_BLKADDR(sbi)) { + if (src == NULL_ADDR) { err = reserve_new_block(&dn); /* We should not get -ENOSPC */ @@ -401,14 +414,13 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, /* write dummy data page */ recover_data_page(sbi, NULL, &sum, src, dest); dn.data_blkaddr = dest; - update_extent_cache(&dn); + set_data_blkaddr(&dn); + f2fs_update_extent_cache(&dn); recovered++; } dn.ofs_in_node++; } - /* write node page in place */ - set_summary(&sum, dn.nid, 0, 0); if (IS_INODE(dn.node_page)) sync_inode_page(&dn); @@ -552,7 +564,7 @@ out: mutex_unlock(&sbi->cp_mutex); } else if (need_writecp) { struct cp_control cpc = { - .reason = CP_SYNC, + .reason = CP_RECOVERY, }; mutex_unlock(&sbi->cp_mutex); write_checkpoint(sbi, &cpc); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index daee4ab913da..f939660941bb 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -205,6 +205,8 @@ retry: list_add_tail(&new->list, &fi->inmem_pages); inc_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES); mutex_unlock(&fi->inmem_lock); + + trace_f2fs_register_inmem_page(page, INMEM); } void commit_inmem_pages(struct inode *inode, bool abort) @@ -238,11 +240,13 @@ void commit_inmem_pages(struct inode *inode, bool abort) f2fs_wait_on_page_writeback(cur->page, DATA); if (clear_page_dirty_for_io(cur->page)) inode_dec_dirty_pages(inode); + trace_f2fs_commit_inmem_page(cur->page, INMEM); do_write_data_page(cur->page, &fio); submit_bio = true; } f2fs_put_page(cur->page, 1); } else { + trace_f2fs_commit_inmem_page(cur->page, INMEM_DROP); put_page(cur->page); } radix_tree_delete(&fi->inmem_root, cur->page->index); @@ -277,6 +281,9 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi) void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) { + /* try to shrink extent cache when there is no enough memory */ + f2fs_shrink_extent_tree(sbi, EXTENT_CACHE_SHRINK_NUMBER); + /* check the # of cached NAT entries and prefree segments */ if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK) || excess_prefree_segs(sbi) || @@ -549,7 +556,7 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc) end = __find_rev_next_zero_bit(dmap, max_blocks, start + 1); - if (end - start < cpc->trim_minlen) + if (force && end - start < cpc->trim_minlen) continue; __add_discard_entry(sbi, cpc, start, end); @@ -1164,6 +1171,7 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, curseg = CURSEG_I(sbi, type); mutex_lock(&curseg->curseg_mutex); + mutex_lock(&sit_i->sentry_lock); /* direct_io'ed data is aligned to the segment for better performance */ if (direct_io && curseg->next_blkoff) @@ -1178,7 +1186,6 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, */ __add_sum_entry(sbi, type, sum); - mutex_lock(&sit_i->sentry_lock); __refresh_next_blkoff(sbi, curseg); stat_inc_block_count(sbi, curseg); @@ -1730,6 +1737,9 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) mutex_lock(&curseg->curseg_mutex); mutex_lock(&sit_i->sentry_lock); + if (!sit_i->dirty_sentries) + goto out; + /* * add and account sit entries of dirty bitmap in sit entry * set temporarily @@ -1744,9 +1754,6 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) if (!__has_cursum_space(sum, sit_i->dirty_sentries, SIT_JOURNAL)) remove_sits_in_journal(sbi); - if (!sit_i->dirty_sentries) - goto out; - /* * there are two steps to flush sit entries: * #1, flush sit entries to journal in current cold data summary block. diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 7fd35111cf62..85d7fa7514b2 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -336,7 +336,8 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno) clear_bit(segno, free_i->free_segmap); free_i->free_segments++; - next = find_next_bit(free_i->free_segmap, MAIN_SEGS(sbi), start_segno); + next = find_next_bit(free_i->free_segmap, + start_segno + sbi->segs_per_sec, start_segno); if (next >= start_segno + sbi->segs_per_sec) { clear_bit(secno, free_i->free_secmap); free_i->free_sections++; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index f2fe666a6ea9..160b88346b24 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -57,6 +57,8 @@ enum { Opt_flush_merge, Opt_nobarrier, Opt_fastboot, + Opt_extent_cache, + Opt_noinline_data, Opt_err, }; @@ -78,6 +80,8 @@ static match_table_t f2fs_tokens = { {Opt_flush_merge, "flush_merge"}, {Opt_nobarrier, "nobarrier"}, {Opt_fastboot, "fastboot"}, + {Opt_extent_cache, "extent_cache"}, + {Opt_noinline_data, "noinline_data"}, {Opt_err, NULL}, }; @@ -367,6 +371,12 @@ static int parse_options(struct super_block *sb, char *options) case Opt_fastboot: set_opt(sbi, FASTBOOT); break; + case Opt_extent_cache: + set_opt(sbi, EXTENT_CACHE); + break; + case Opt_noinline_data: + clear_opt(sbi, INLINE_DATA); + break; default: f2fs_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" or missing value", @@ -392,7 +402,7 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb) atomic_set(&fi->dirty_pages, 0); fi->i_current_depth = 1; fi->i_advise = 0; - rwlock_init(&fi->ext.ext_lock); + rwlock_init(&fi->ext_lock); init_rwsem(&fi->i_sem); INIT_RADIX_TREE(&fi->inmem_root, GFP_NOFS); INIT_LIST_HEAD(&fi->inmem_pages); @@ -591,6 +601,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",disable_ext_identify"); if (test_opt(sbi, INLINE_DATA)) seq_puts(seq, ",inline_data"); + else + seq_puts(seq, ",noinline_data"); if (test_opt(sbi, INLINE_DENTRY)) seq_puts(seq, ",inline_dentry"); if (!f2fs_readonly(sbi->sb) && test_opt(sbi, FLUSH_MERGE)) @@ -599,6 +611,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",nobarrier"); if (test_opt(sbi, FASTBOOT)) seq_puts(seq, ",fastboot"); + if (test_opt(sbi, EXTENT_CACHE)) + seq_puts(seq, ",extent_cache"); seq_printf(seq, ",active_logs=%u", sbi->active_logs); return 0; @@ -959,7 +973,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) struct buffer_head *raw_super_buf; struct inode *root; long err = -EINVAL; - bool retry = true; + bool retry = true, need_fsck = false; char *options = NULL; int i; @@ -984,6 +998,7 @@ try_onemore: sbi->active_logs = NR_CURSEG_TYPE; set_opt(sbi, BG_GC); + set_opt(sbi, INLINE_DATA); #ifdef CONFIG_F2FS_FS_XATTR set_opt(sbi, XATTR_USER); @@ -1020,7 +1035,6 @@ try_onemore: sbi->raw_super = raw_super; sbi->raw_super_buf = raw_super_buf; mutex_init(&sbi->gc_mutex); - mutex_init(&sbi->writepages); mutex_init(&sbi->cp_mutex); init_rwsem(&sbi->node_write); clear_sbi_flag(sbi, SBI_POR_DOING); @@ -1072,6 +1086,8 @@ try_onemore: INIT_LIST_HEAD(&sbi->dir_inode_list); spin_lock_init(&sbi->dir_inode_lock); + init_extent_cache_info(sbi); + init_ino_entry_info(sbi); /* setup f2fs internal modules */ @@ -1146,9 +1162,6 @@ try_onemore: if (err) goto free_proc; - if (!retry) - set_sbi_flag(sbi, SBI_NEED_FSCK); - /* recover fsynced data */ if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) { /* @@ -1160,8 +1173,13 @@ try_onemore: err = -EROFS; goto free_kobj; } + + if (need_fsck) + set_sbi_flag(sbi, SBI_NEED_FSCK); + err = recover_fsync_data(sbi); if (err) { + need_fsck = true; f2fs_msg(sb, KERN_ERR, "Cannot recover all fsync data errno=%ld", err); goto free_kobj; @@ -1212,7 +1230,7 @@ free_sbi: /* give only one another chance */ if (retry) { - retry = 0; + retry = false; shrink_dcache_sb(sb); goto try_onemore; } @@ -1278,10 +1296,13 @@ static int __init init_f2fs_fs(void) err = create_checkpoint_caches(); if (err) goto free_segment_manager_caches; + err = create_extent_cache(); + if (err) + goto free_checkpoint_caches; f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj); if (!f2fs_kset) { err = -ENOMEM; - goto free_checkpoint_caches; + goto free_extent_cache; } err = register_filesystem(&f2fs_fs_type); if (err) @@ -1292,6 +1313,8 @@ static int __init init_f2fs_fs(void) free_kset: kset_unregister(f2fs_kset); +free_extent_cache: + destroy_extent_cache(); free_checkpoint_caches: destroy_checkpoint_caches(); free_segment_manager_caches: @@ -1309,6 +1332,7 @@ static void __exit exit_f2fs_fs(void) remove_proc_entry("fs/f2fs", NULL); f2fs_destroy_root_stats(); unregister_filesystem(&f2fs_fs_type); + destroy_extent_cache(); destroy_checkpoint_caches(); destroy_segment_manager_caches(); destroy_node_manager_caches(); diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 5072bf9ae0ef..b0fd2f2d0716 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -135,7 +135,8 @@ static int f2fs_xattr_advise_get(struct dentry *dentry, const char *name, if (strcmp(name, "") != 0) return -EINVAL; - *((char *)buffer) = F2FS_I(inode)->i_advise; + if (buffer) + *((char *)buffer) = F2FS_I(inode)->i_advise; return sizeof(char); } @@ -152,6 +153,7 @@ static int f2fs_xattr_advise_set(struct dentry *dentry, const char *name, return -EINVAL; F2FS_I(inode)->i_advise |= *(char *)value; + mark_inode_dirty(inode); return 0; } diff --git a/fs/fat/cache.c b/fs/fat/cache.c index 91ad9e1c9441..93fc62232ec2 100644 --- a/fs/fat/cache.c +++ b/fs/fat/cache.c @@ -8,9 +8,7 @@ * May 1999. AV. Fixed the bogosity with FAT32 (read "FAT28"). Fscking lusers. */ -#include <linux/fs.h> #include <linux/slab.h> -#include <linux/buffer_head.h> #include "fat.h" /* this must be > 0. */ diff --git a/fs/fat/dir.c b/fs/fat/dir.c index c5d6bb939d19..4afc4d9d2e41 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -13,13 +13,9 @@ * Short name translation 1999, 2001 by Wolfram Pienkoss <wp@bszh.de> */ -#include <linux/module.h> #include <linux/slab.h> -#include <linux/time.h> -#include <linux/buffer_head.h> #include <linux/compat.h> #include <linux/uaccess.h> -#include <linux/kernel.h> #include "fat.h" /* diff --git a/fs/fat/fat.h b/fs/fat/fat.h index 64e295e8ff38..be5e15323bab 100644 --- a/fs/fat/fat.h +++ b/fs/fat/fat.h @@ -2,11 +2,8 @@ #define _FAT_H #include <linux/buffer_head.h> -#include <linux/string.h> #include <linux/nls.h> -#include <linux/fs.h> #include <linux/hash.h> -#include <linux/mutex.h> #include <linux/ratelimit.h> #include <linux/msdos_fs.h> @@ -66,7 +63,7 @@ struct msdos_sb_info { unsigned short sec_per_clus; /* sectors/cluster */ unsigned short cluster_bits; /* log2(cluster_size) */ unsigned int cluster_size; /* cluster size */ - unsigned char fats, fat_bits; /* number of FATs, FAT bits (12 or 16) */ + unsigned char fats, fat_bits; /* number of FATs, FAT bits (12,16 or 32) */ unsigned short fat_start; unsigned long fat_length; /* FAT start & length (sec.) */ unsigned long dir_start; diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index 260705c58062..8226557130a2 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -3,9 +3,6 @@ * Released under GPL v2. */ -#include <linux/module.h> -#include <linux/fs.h> -#include <linux/msdos_fs.h> #include <linux/blkdev.h> #include "fat.h" diff --git a/fs/fat/file.c b/fs/fat/file.c index 8429c68e3057..cf50d93565a2 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -10,10 +10,6 @@ #include <linux/module.h> #include <linux/compat.h> #include <linux/mount.h> -#include <linux/time.h> -#include <linux/buffer_head.h> -#include <linux/writeback.h> -#include <linux/backing-dev.h> #include <linux/blkdev.h> #include <linux/fsnotify.h> #include <linux/security.h> @@ -170,8 +166,6 @@ int fat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync) const struct file_operations fat_file_operations = { .llseek = generic_file_llseek, - .read = new_sync_read, - .write = new_sync_write, .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 497c7c5263c7..c06774658345 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -11,21 +11,12 @@ */ #include <linux/module.h> -#include <linux/init.h> -#include <linux/time.h> -#include <linux/slab.h> -#include <linux/seq_file.h> #include <linux/pagemap.h> #include <linux/mpage.h> -#include <linux/buffer_head.h> -#include <linux/mount.h> -#include <linux/aio.h> #include <linux/vfs.h> +#include <linux/seq_file.h> #include <linux/parser.h> #include <linux/uio.h> -#include <linux/writeback.h> -#include <linux/log2.h> -#include <linux/hash.h> #include <linux/blkdev.h> #include <asm/unaligned.h> #include "fat.h" @@ -246,8 +237,7 @@ static int fat_write_end(struct file *file, struct address_space *mapping, return err; } -static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, - struct iov_iter *iter, +static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; @@ -256,7 +246,7 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, size_t count = iov_iter_count(iter); ssize_t ret; - if (rw == WRITE) { + if (iov_iter_rw(iter) == WRITE) { /* * FIXME: blockdev_direct_IO() doesn't use ->write_begin(), * so we need to update the ->mmu_private to block boundary. @@ -275,8 +265,8 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, * FAT need to use the DIO_LOCKING for avoiding the race * condition of fat_get_block() and ->truncate(). */ - ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, fat_get_block); - if (ret < 0 && (rw & WRITE)) + ret = blockdev_direct_IO(iocb, inode, iter, offset, fat_get_block); + if (ret < 0 && iov_iter_rw(iter) == WRITE) fat_write_failed(mapping, offset + count); return ret; @@ -1280,8 +1270,7 @@ out: static int fat_read_root(struct inode *inode) { - struct super_block *sb = inode->i_sb; - struct msdos_sb_info *sbi = MSDOS_SB(sb); + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); int error; MSDOS_I(inode)->i_pos = MSDOS_ROOT_INO; diff --git a/fs/fat/misc.c b/fs/fat/misc.c index d8da2d2e30ae..c4589e981760 100644 --- a/fs/fat/misc.c +++ b/fs/fat/misc.c @@ -6,10 +6,6 @@ * and date_dos2unix for date==0 by Igor Zhbanov(bsg@uniyar.ac.ru) */ -#include <linux/module.h> -#include <linux/fs.h> -#include <linux/buffer_head.h> -#include <linux/time.h> #include "fat.h" /* diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c index a783b0e1272a..cc6a8541b668 100644 --- a/fs/fat/namei_msdos.c +++ b/fs/fat/namei_msdos.c @@ -7,8 +7,6 @@ */ #include <linux/module.h> -#include <linux/time.h> -#include <linux/buffer_head.h> #include "fat.h" /* Characters that are undesirable in an MS-DOS file name */ diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index b8b92c2f9683..7e0974eebd8e 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -16,10 +16,8 @@ */ #include <linux/module.h> -#include <linux/jiffies.h> #include <linux/ctype.h> #include <linux/slab.h> -#include <linux/buffer_head.h> #include <linux/namei.h> #include "fat.h" diff --git a/fs/file.c b/fs/file.c index ee738ea028fa..93c5f89c248b 100644 --- a/fs/file.c +++ b/fs/file.c @@ -638,8 +638,7 @@ static struct file *__fget(unsigned int fd, fmode_t mask) file = fcheck_files(files, fd); if (file) { /* File object ref couldn't be taken */ - if ((file->f_mode & mask) || - !atomic_long_inc_not_zero(&file->f_count)) + if ((file->f_mode & mask) || !get_file_rcu(file)) file = NULL; } rcu_read_unlock(); diff --git a/fs/file_table.c b/fs/file_table.c index 3f85411b03ce..294174dcc226 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -168,10 +168,10 @@ struct file *alloc_file(struct path *path, fmode_t mode, file->f_inode = path->dentry->d_inode; file->f_mapping = path->dentry->d_inode->i_mapping; if ((mode & FMODE_READ) && - likely(fop->read || fop->aio_read || fop->read_iter)) + likely(fop->read || fop->read_iter)) mode |= FMODE_CAN_READ; if ((mode & FMODE_WRITE) && - likely(fop->write || fop->aio_write || fop->write_iter)) + likely(fop->write || fop->write_iter)) mode |= FMODE_CAN_WRITE; file->f_mode = mode; file->f_op = fop; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index e907052eeadb..32a8bbd7a9ad 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -53,6 +53,18 @@ struct wb_writeback_work { struct completion *done; /* set if the caller waits */ }; +/* + * If an inode is constantly having its pages dirtied, but then the + * updates stop dirtytime_expire_interval seconds in the past, it's + * possible for the worst case time between when an inode has its + * timestamps updated and when they finally get written out to be two + * dirtytime_expire_intervals. We set the default to 12 hours (in + * seconds), which means most of the time inodes will have their + * timestamps written to disk after 12 hours, but in the worst case a + * few inodes might not their timestamps updated for 24 hours. + */ +unsigned int dirtytime_expire_interval = 12 * 60 * 60; + /** * writeback_in_progress - determine whether there is writeback in progress * @bdi: the device's backing_dev_info structure. @@ -275,8 +287,8 @@ static int move_expired_inodes(struct list_head *delaying_queue, if ((flags & EXPIRE_DIRTY_ATIME) == 0) older_than_this = work->older_than_this; - else if ((work->reason == WB_REASON_SYNC) == 0) { - expire_time = jiffies - (HZ * 86400); + else if (!work->for_sync) { + expire_time = jiffies - (dirtytime_expire_interval * HZ); older_than_this = &expire_time; } while (!list_empty(delaying_queue)) { @@ -458,6 +470,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, */ redirty_tail(inode, wb); } else if (inode->i_state & I_DIRTY_TIME) { + inode->dirtied_when = jiffies; list_move(&inode->i_wb_list, &wb->b_dirty_time); } else { /* The inode is clean. Remove from writeback lists. */ @@ -505,12 +518,17 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) spin_lock(&inode->i_lock); dirty = inode->i_state & I_DIRTY; - if (((dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) && - (inode->i_state & I_DIRTY_TIME)) || - (inode->i_state & I_DIRTY_TIME_EXPIRED)) { - dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED; - trace_writeback_lazytime(inode); - } + if (inode->i_state & I_DIRTY_TIME) { + if ((dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) || + unlikely(inode->i_state & I_DIRTY_TIME_EXPIRED) || + unlikely(time_after(jiffies, + (inode->dirtied_time_when + + dirtytime_expire_interval * HZ)))) { + dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED; + trace_writeback_lazytime(inode); + } + } else + inode->i_state &= ~I_DIRTY_TIME_EXPIRED; inode->i_state &= ~dirty; /* @@ -1131,6 +1149,56 @@ void wakeup_flusher_threads(long nr_pages, enum wb_reason reason) rcu_read_unlock(); } +/* + * Wake up bdi's periodically to make sure dirtytime inodes gets + * written back periodically. We deliberately do *not* check the + * b_dirtytime list in wb_has_dirty_io(), since this would cause the + * kernel to be constantly waking up once there are any dirtytime + * inodes on the system. So instead we define a separate delayed work + * function which gets called much more rarely. (By default, only + * once every 12 hours.) + * + * If there is any other write activity going on in the file system, + * this function won't be necessary. But if the only thing that has + * happened on the file system is a dirtytime inode caused by an atime + * update, we need this infrastructure below to make sure that inode + * eventually gets pushed out to disk. + */ +static void wakeup_dirtytime_writeback(struct work_struct *w); +static DECLARE_DELAYED_WORK(dirtytime_work, wakeup_dirtytime_writeback); + +static void wakeup_dirtytime_writeback(struct work_struct *w) +{ + struct backing_dev_info *bdi; + + rcu_read_lock(); + list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { + if (list_empty(&bdi->wb.b_dirty_time)) + continue; + bdi_wakeup_thread(bdi); + } + rcu_read_unlock(); + schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); +} + +static int __init start_dirtytime_writeback(void) +{ + schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); + return 0; +} +__initcall(start_dirtytime_writeback); + +int dirtytime_interval_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret; + + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (ret == 0 && write) + mod_delayed_work(system_wq, &dirtytime_work, 0); + return ret; +} + static noinline void block_dump___mark_inode_dirty(struct inode *inode) { if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) { @@ -1269,8 +1337,13 @@ void __mark_inode_dirty(struct inode *inode, int flags) } inode->dirtied_when = jiffies; - list_move(&inode->i_wb_list, dirtytime ? - &bdi->wb.b_dirty_time : &bdi->wb.b_dirty); + if (dirtytime) + inode->dirtied_time_when = jiffies; + if (inode->i_state & (I_DIRTY_INODE | I_DIRTY_PAGES)) + list_move(&inode->i_wb_list, &bdi->wb.b_dirty); + else + list_move(&inode->i_wb_list, + &bdi->wb.b_dirty_time); spin_unlock(&bdi->wb.list_lock); trace_writeback_dirty_inode_enqueue(inode); diff --git a/fs/fs_pin.c b/fs/fs_pin.c index b06c98796afb..611b5408f6ec 100644 --- a/fs/fs_pin.c +++ b/fs/fs_pin.c @@ -9,8 +9,8 @@ static DEFINE_SPINLOCK(pin_lock); void pin_remove(struct fs_pin *pin) { spin_lock(&pin_lock); - hlist_del(&pin->m_list); - hlist_del(&pin->s_list); + hlist_del_init(&pin->m_list); + hlist_del_init(&pin->s_list); spin_unlock(&pin_lock); spin_lock_irq(&pin->wait.lock); pin->done = 1; diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index 28d0c7abba1c..e5bbf748b698 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -38,7 +38,6 @@ #include <linux/device.h> #include <linux/file.h> #include <linux/fs.h> -#include <linux/aio.h> #include <linux/kdev_t.h> #include <linux/kthread.h> #include <linux/list.h> @@ -48,6 +47,7 @@ #include <linux/slab.h> #include <linux/stat.h> #include <linux/module.h> +#include <linux/uio.h> #include "fuse_i.h" @@ -88,32 +88,23 @@ static struct list_head *cuse_conntbl_head(dev_t devt) * FUSE file. */ -static ssize_t cuse_read(struct file *file, char __user *buf, size_t count, - loff_t *ppos) +static ssize_t cuse_read_iter(struct kiocb *kiocb, struct iov_iter *to) { + struct fuse_io_priv io = { .async = 0, .file = kiocb->ki_filp }; loff_t pos = 0; - struct iovec iov = { .iov_base = buf, .iov_len = count }; - struct fuse_io_priv io = { .async = 0, .file = file }; - struct iov_iter ii; - iov_iter_init(&ii, READ, &iov, 1, count); - return fuse_direct_io(&io, &ii, &pos, FUSE_DIO_CUSE); + return fuse_direct_io(&io, to, &pos, FUSE_DIO_CUSE); } -static ssize_t cuse_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) +static ssize_t cuse_write_iter(struct kiocb *kiocb, struct iov_iter *from) { + struct fuse_io_priv io = { .async = 0, .file = kiocb->ki_filp }; loff_t pos = 0; - struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = count }; - struct fuse_io_priv io = { .async = 0, .file = file }; - struct iov_iter ii; - iov_iter_init(&ii, WRITE, &iov, 1, count); - /* * No locking or generic_write_checks(), the server is * responsible for locking and sanity checks. */ - return fuse_direct_io(&io, &ii, &pos, + return fuse_direct_io(&io, from, &pos, FUSE_DIO_WRITE | FUSE_DIO_CUSE); } @@ -186,8 +177,8 @@ static long cuse_file_compat_ioctl(struct file *file, unsigned int cmd, static const struct file_operations cuse_frontend_fops = { .owner = THIS_MODULE, - .read = cuse_read, - .write = cuse_write, + .read_iter = cuse_read_iter, + .write_iter = cuse_write_iter, .open = cuse_open, .release = cuse_release, .unlocked_ioctl = cuse_file_ioctl, diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 39706c57ad3c..c8b68ab2e574 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -19,7 +19,6 @@ #include <linux/pipe_fs_i.h> #include <linux/swap.h> #include <linux/splice.h> -#include <linux/aio.h> MODULE_ALIAS_MISCDEV(FUSE_MINOR); MODULE_ALIAS("devname:fuse"); @@ -711,28 +710,26 @@ struct fuse_copy_state { struct fuse_conn *fc; int write; struct fuse_req *req; - const struct iovec *iov; + struct iov_iter *iter; struct pipe_buffer *pipebufs; struct pipe_buffer *currbuf; struct pipe_inode_info *pipe; unsigned long nr_segs; - unsigned long seglen; - unsigned long addr; struct page *pg; unsigned len; unsigned offset; unsigned move_pages:1; }; -static void fuse_copy_init(struct fuse_copy_state *cs, struct fuse_conn *fc, +static void fuse_copy_init(struct fuse_copy_state *cs, + struct fuse_conn *fc, int write, - const struct iovec *iov, unsigned long nr_segs) + struct iov_iter *iter) { memset(cs, 0, sizeof(*cs)); cs->fc = fc; cs->write = write; - cs->iov = iov; - cs->nr_segs = nr_segs; + cs->iter = iter; } /* Unmap and put previous page of userspace buffer */ @@ -800,22 +797,16 @@ static int fuse_copy_fill(struct fuse_copy_state *cs) cs->nr_segs++; } } else { - if (!cs->seglen) { - BUG_ON(!cs->nr_segs); - cs->seglen = cs->iov[0].iov_len; - cs->addr = (unsigned long) cs->iov[0].iov_base; - cs->iov++; - cs->nr_segs--; - } - err = get_user_pages_fast(cs->addr, 1, cs->write, &page); + size_t off; + err = iov_iter_get_pages(cs->iter, &page, PAGE_SIZE, 1, &off); if (err < 0) return err; - BUG_ON(err != 1); + BUG_ON(!err); + cs->len = err; + cs->offset = off; cs->pg = page; - cs->offset = cs->addr % PAGE_SIZE; - cs->len = min(PAGE_SIZE - cs->offset, cs->seglen); - cs->seglen -= cs->len; - cs->addr += cs->len; + cs->offset = off; + iov_iter_advance(cs->iter, err); } return lock_request(cs->fc, cs->req); @@ -1364,8 +1355,7 @@ static int fuse_dev_open(struct inode *inode, struct file *file) return 0; } -static ssize_t fuse_dev_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +static ssize_t fuse_dev_read(struct kiocb *iocb, struct iov_iter *to) { struct fuse_copy_state cs; struct file *file = iocb->ki_filp; @@ -1373,9 +1363,12 @@ static ssize_t fuse_dev_read(struct kiocb *iocb, const struct iovec *iov, if (!fc) return -EPERM; - fuse_copy_init(&cs, fc, 1, iov, nr_segs); + if (!iter_is_iovec(to)) + return -EINVAL; - return fuse_dev_do_read(fc, file, &cs, iov_length(iov, nr_segs)); + fuse_copy_init(&cs, fc, 1, to); + + return fuse_dev_do_read(fc, file, &cs, iov_iter_count(to)); } static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos, @@ -1395,7 +1388,7 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos, if (!bufs) return -ENOMEM; - fuse_copy_init(&cs, fc, 1, NULL, 0); + fuse_copy_init(&cs, fc, 1, NULL); cs.pipebufs = bufs; cs.pipe = pipe; ret = fuse_dev_do_read(fc, in, &cs, len); @@ -1971,17 +1964,19 @@ static ssize_t fuse_dev_do_write(struct fuse_conn *fc, return err; } -static ssize_t fuse_dev_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +static ssize_t fuse_dev_write(struct kiocb *iocb, struct iov_iter *from) { struct fuse_copy_state cs; struct fuse_conn *fc = fuse_get_conn(iocb->ki_filp); if (!fc) return -EPERM; - fuse_copy_init(&cs, fc, 0, iov, nr_segs); + if (!iter_is_iovec(from)) + return -EINVAL; + + fuse_copy_init(&cs, fc, 0, from); - return fuse_dev_do_write(fc, &cs, iov_length(iov, nr_segs)); + return fuse_dev_do_write(fc, &cs, iov_iter_count(from)); } static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, @@ -2044,8 +2039,9 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, } pipe_unlock(pipe); - fuse_copy_init(&cs, fc, 0, NULL, nbuf); + fuse_copy_init(&cs, fc, 0, NULL); cs.pipebufs = bufs; + cs.nr_segs = nbuf; cs.pipe = pipe; if (flags & SPLICE_F_MOVE) @@ -2233,11 +2229,9 @@ const struct file_operations fuse_dev_operations = { .owner = THIS_MODULE, .open = fuse_dev_open, .llseek = no_llseek, - .read = do_sync_read, - .aio_read = fuse_dev_read, + .read_iter = fuse_dev_read, .splice_read = fuse_dev_splice_read, - .write = do_sync_write, - .aio_write = fuse_dev_write, + .write_iter = fuse_dev_write, .splice_write = fuse_dev_splice_write, .poll = fuse_dev_poll, .release = fuse_dev_release, diff --git a/fs/fuse/file.c b/fs/fuse/file.c index c01ec3bdcfd8..5ef05b5c4cff 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -15,8 +15,8 @@ #include <linux/module.h> #include <linux/compat.h> #include <linux/swap.h> -#include <linux/aio.h> #include <linux/falloc.h> +#include <linux/uio.h> static const struct file_operations fuse_direct_io_file_operations; @@ -528,6 +528,17 @@ static void fuse_release_user_pages(struct fuse_req *req, int write) } } +static ssize_t fuse_get_res_by_io(struct fuse_io_priv *io) +{ + if (io->err) + return io->err; + + if (io->bytes >= 0 && io->write) + return -EIO; + + return io->bytes < 0 ? io->size : io->bytes; +} + /** * In case of short read, the caller sets 'pos' to the position of * actual end of fuse request in IO request. Otherwise, if bytes_requested @@ -546,6 +557,7 @@ static void fuse_release_user_pages(struct fuse_req *req, int write) */ static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos) { + bool is_sync = is_sync_kiocb(io->iocb); int left; spin_lock(&io->lock); @@ -555,30 +567,24 @@ static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos) io->bytes = pos; left = --io->reqs; + if (!left && is_sync) + complete(io->done); spin_unlock(&io->lock); - if (!left) { - long res; + if (!left && !is_sync) { + ssize_t res = fuse_get_res_by_io(io); - if (io->err) - res = io->err; - else if (io->bytes >= 0 && io->write) - res = -EIO; - else { - res = io->bytes < 0 ? io->size : io->bytes; - - if (!is_sync_kiocb(io->iocb)) { - struct inode *inode = file_inode(io->iocb->ki_filp); - struct fuse_conn *fc = get_fuse_conn(inode); - struct fuse_inode *fi = get_fuse_inode(inode); + if (res >= 0) { + struct inode *inode = file_inode(io->iocb->ki_filp); + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_inode *fi = get_fuse_inode(inode); - spin_lock(&fc->lock); - fi->attr_version = ++fc->attr_version; - spin_unlock(&fc->lock); - } + spin_lock(&fc->lock); + fi->attr_version = ++fc->attr_version; + spin_unlock(&fc->lock); } - aio_complete(io->iocb, res, 0); + io->iocb->ki_complete(io->iocb, res, 0); kfree(io); } } @@ -1139,13 +1145,11 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; - size_t count = iov_iter_count(from); ssize_t written = 0; ssize_t written_buffered = 0; struct inode *inode = mapping->host; ssize_t err; loff_t endbyte = 0; - loff_t pos = iocb->ki_pos; if (get_fuse_conn(inode)->writeback_cache) { /* Update size (EOF optimization) and mode (SUID clearing) */ @@ -1161,14 +1165,10 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from) /* We can write back this queue in page reclaim */ current->backing_dev_info = inode_to_bdi(inode); - err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); - if (err) + err = generic_write_checks(iocb, from); + if (err <= 0) goto out; - if (count == 0) - goto out; - - iov_iter_truncate(from, count); err = file_remove_suid(file); if (err) goto out; @@ -1177,7 +1177,8 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (err) goto out; - if (file->f_flags & O_DIRECT) { + if (iocb->ki_flags & IOCB_DIRECT) { + loff_t pos = iocb->ki_pos; written = generic_file_direct_write(iocb, from, pos); if (written < 0 || !iov_iter_count(from)) goto out; @@ -1203,9 +1204,9 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from) written += written_buffered; iocb->ki_pos = pos + written_buffered; } else { - written = fuse_perform_write(file, mapping, from, pos); + written = fuse_perform_write(file, mapping, from, iocb->ki_pos); if (written >= 0) - iocb->ki_pos = pos + written; + iocb->ki_pos += written; } out: current->backing_dev_info = NULL; @@ -1395,55 +1396,30 @@ static ssize_t __fuse_direct_read(struct fuse_io_priv *io, return res; } -static ssize_t fuse_direct_read(struct file *file, char __user *buf, - size_t count, loff_t *ppos) -{ - struct fuse_io_priv io = { .async = 0, .file = file }; - struct iovec iov = { .iov_base = buf, .iov_len = count }; - struct iov_iter ii; - iov_iter_init(&ii, READ, &iov, 1, count); - return __fuse_direct_read(&io, &ii, ppos); -} - -static ssize_t __fuse_direct_write(struct fuse_io_priv *io, - struct iov_iter *iter, - loff_t *ppos) +static ssize_t fuse_direct_read_iter(struct kiocb *iocb, struct iov_iter *to) { - struct file *file = io->file; - struct inode *inode = file_inode(file); - size_t count = iov_iter_count(iter); - ssize_t res; - - - res = generic_write_checks(file, ppos, &count, 0); - if (!res) { - iov_iter_truncate(iter, count); - res = fuse_direct_io(io, iter, ppos, FUSE_DIO_WRITE); - } - - fuse_invalidate_attr(inode); - - return res; + struct fuse_io_priv io = { .async = 0, .file = iocb->ki_filp }; + return __fuse_direct_read(&io, to, &iocb->ki_pos); } -static ssize_t fuse_direct_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) +static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from) { - struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = count }; + struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); - ssize_t res; struct fuse_io_priv io = { .async = 0, .file = file }; - struct iov_iter ii; - iov_iter_init(&ii, WRITE, &iov, 1, count); + ssize_t res; if (is_bad_inode(inode)) return -EIO; /* Don't allow parallel writes to the same file */ mutex_lock(&inode->i_mutex); - res = __fuse_direct_write(&io, &ii, ppos); + res = generic_write_checks(iocb, from); if (res > 0) - fuse_write_update_size(inode, *ppos); + res = fuse_direct_io(&io, from, &iocb->ki_pos, FUSE_DIO_WRITE); + fuse_invalidate_attr(inode); + if (res > 0) + fuse_write_update_size(inode, iocb->ki_pos); mutex_unlock(&inode->i_mutex); return res; @@ -2798,9 +2774,9 @@ static inline loff_t fuse_round_up(loff_t off) } static ssize_t -fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) { + DECLARE_COMPLETION_ONSTACK(wait); ssize_t ret = 0; struct file *file = iocb->ki_filp; struct fuse_file *ff = file->private_data; @@ -2815,15 +2791,15 @@ fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, inode = file->f_mapping->host; i_size = i_size_read(inode); - if ((rw == READ) && (offset > i_size)) + if ((iov_iter_rw(iter) == READ) && (offset > i_size)) return 0; /* optimization for short read */ - if (async_dio && rw != WRITE && offset + count > i_size) { + if (async_dio && iov_iter_rw(iter) != WRITE && offset + count > i_size) { if (offset >= i_size) return 0; - count = min_t(loff_t, count, fuse_round_up(i_size - offset)); - iov_iter_truncate(iter, count); + iov_iter_truncate(iter, fuse_round_up(i_size - offset)); + count = iov_iter_count(iter); } io = kmalloc(sizeof(struct fuse_io_priv), GFP_KERNEL); @@ -2834,7 +2810,7 @@ fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, io->bytes = -1; io->size = 0; io->offset = offset; - io->write = (rw == WRITE); + io->write = (iov_iter_rw(iter) == WRITE); io->err = 0; io->file = file; /* @@ -2849,13 +2825,19 @@ fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, * to wait on real async I/O requests, so we must submit this request * synchronously. */ - if (!is_sync_kiocb(iocb) && (offset + count > i_size) && rw == WRITE) + if (!is_sync_kiocb(iocb) && (offset + count > i_size) && + iov_iter_rw(iter) == WRITE) io->async = false; - if (rw == WRITE) - ret = __fuse_direct_write(io, iter, &pos); - else + if (io->async && is_sync_kiocb(iocb)) + io->done = &wait; + + if (iov_iter_rw(iter) == WRITE) { + ret = fuse_direct_io(io, iter, &pos, FUSE_DIO_WRITE); + fuse_invalidate_attr(inode); + } else { ret = __fuse_direct_read(io, iter, &pos); + } if (io->async) { fuse_aio_complete(io, ret < 0 ? ret : 0, -1); @@ -2864,12 +2846,13 @@ fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, if (!is_sync_kiocb(iocb)) return -EIOCBQUEUED; - ret = wait_on_sync_kiocb(iocb); - } else { - kfree(io); + wait_for_completion(&wait); + ret = fuse_get_res_by_io(io); } - if (rw == WRITE) { + kfree(io); + + if (iov_iter_rw(iter) == WRITE) { if (ret > 0) fuse_write_update_size(inode, pos); else if (ret < 0 && offset + count > i_size) @@ -2957,9 +2940,7 @@ out: static const struct file_operations fuse_file_operations = { .llseek = fuse_file_llseek, - .read = new_sync_read, .read_iter = fuse_file_read_iter, - .write = new_sync_write, .write_iter = fuse_file_write_iter, .mmap = fuse_file_mmap, .open = fuse_open, @@ -2977,8 +2958,8 @@ static const struct file_operations fuse_file_operations = { static const struct file_operations fuse_direct_io_file_operations = { .llseek = fuse_file_llseek, - .read = fuse_direct_read, - .write = fuse_direct_write, + .read_iter = fuse_direct_read_iter, + .write_iter = fuse_direct_write_iter, .mmap = fuse_direct_mmap, .open = fuse_open, .flush = fuse_flush, diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 1cdfb07c1376..7354dc142a50 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -263,6 +263,7 @@ struct fuse_io_priv { int err; struct kiocb *iocb; struct file *file; + struct completion *done; }; /** diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 7b3143064af1..1be3b061c05c 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -110,11 +110,7 @@ int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) error = __gfs2_xattr_set(inode, name, data, len, 0, GFS2_EATYPE_SYS); if (error) goto out; - - if (acl) - set_cached_acl(inode, type, acl); - else - forget_cached_acl(inode, type); + set_cached_acl(inode, type, acl); out: kfree(data); return error; diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 4ad4f94edebe..5551fea0afd7 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -20,7 +20,7 @@ #include <linux/swap.h> #include <linux/gfs2_ondisk.h> #include <linux/backing-dev.h> -#include <linux/aio.h> +#include <linux/uio.h> #include <trace/events/writeback.h> #include "gfs2.h" @@ -671,12 +671,12 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping, if (alloc_required) { struct gfs2_alloc_parms ap = { .aflags = 0, }; - error = gfs2_quota_lock_check(ip); + requested = data_blocks + ind_blocks; + ap.target = requested; + error = gfs2_quota_lock_check(ip, &ap); if (error) goto out_unlock; - requested = data_blocks + ind_blocks; - ap.target = requested; error = gfs2_inplace_reserve(ip, &ap); if (error) goto out_qunlock; @@ -1016,13 +1016,12 @@ out: /** * gfs2_ok_for_dio - check that dio is valid on this file * @ip: The inode - * @rw: READ or WRITE * @offset: The offset at which we are reading or writing * * Returns: 0 (to ignore the i/o request and thus fall back to buffered i/o) * 1 (to accept the i/o request) */ -static int gfs2_ok_for_dio(struct gfs2_inode *ip, int rw, loff_t offset) +static int gfs2_ok_for_dio(struct gfs2_inode *ip, loff_t offset) { /* * Should we return an error here? I can't see that O_DIRECT for @@ -1039,8 +1038,8 @@ static int gfs2_ok_for_dio(struct gfs2_inode *ip, int rw, loff_t offset) -static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb, - struct iov_iter *iter, loff_t offset) +static ssize_t gfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; @@ -1061,7 +1060,7 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb, rv = gfs2_glock_nq(&gh); if (rv) return rv; - rv = gfs2_ok_for_dio(ip, rw, offset); + rv = gfs2_ok_for_dio(ip, offset); if (rv != 1) goto out; /* dio not valid, fall back to buffered i/o */ @@ -1091,13 +1090,12 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb, rv = filemap_write_and_wait_range(mapping, lstart, end); if (rv) goto out; - if (rw == WRITE) + if (iov_iter_rw(iter) == WRITE) truncate_inode_pages_range(mapping, lstart, end); } - rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, - iter, offset, - gfs2_get_block_direct, NULL, NULL, 0); + rv = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, + offset, gfs2_get_block_direct, NULL, NULL, 0); out: gfs2_glock_dq(&gh); gfs2_holder_uninit(&gh); diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index f0b945ab853e..61296ecbd0e2 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1224,7 +1224,7 @@ static int do_grow(struct inode *inode, u64 size) if (gfs2_is_stuffed(ip) && (size > (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)))) { - error = gfs2_quota_lock_check(ip); + error = gfs2_quota_lock_check(ip, &ap); if (error) return error; diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 3e32bb8e2d7e..31892871ea87 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -25,7 +25,6 @@ #include <asm/uaccess.h> #include <linux/dlm.h> #include <linux/dlm_plock.h> -#include <linux/aio.h> #include <linux/delay.h> #include "gfs2.h" @@ -429,11 +428,11 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) if (ret) goto out_unlock; - ret = gfs2_quota_lock_check(ip); - if (ret) - goto out_unlock; gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks); ap.target = data_blocks + ind_blocks; + ret = gfs2_quota_lock_check(ip, &ap); + if (ret) + goto out_unlock; ret = gfs2_inplace_reserve(ip, &ap); if (ret) goto out_quota_unlock; @@ -710,7 +709,7 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from) gfs2_size_hint(file, iocb->ki_pos, iov_iter_count(from)); - if (file->f_flags & O_APPEND) { + if (iocb->ki_flags & IOCB_APPEND) { struct gfs2_holder gh; ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh); @@ -765,22 +764,30 @@ out: brelse(dibh); return error; } - -static void calc_max_reserv(struct gfs2_inode *ip, loff_t max, loff_t *len, - unsigned int *data_blocks, unsigned int *ind_blocks) +/** + * calc_max_reserv() - Reverse of write_calc_reserv. Given a number of + * blocks, determine how many bytes can be written. + * @ip: The inode in question. + * @len: Max cap of bytes. What we return in *len must be <= this. + * @data_blocks: Compute and return the number of data blocks needed + * @ind_blocks: Compute and return the number of indirect blocks needed + * @max_blocks: The total blocks available to work with. + * + * Returns: void, but @len, @data_blocks and @ind_blocks are filled in. + */ +static void calc_max_reserv(struct gfs2_inode *ip, loff_t *len, + unsigned int *data_blocks, unsigned int *ind_blocks, + unsigned int max_blocks) { + loff_t max = *len; const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - unsigned int max_blocks = ip->i_rgd->rd_free_clone; unsigned int tmp, max_data = max_blocks - 3 * (sdp->sd_max_height - 1); for (tmp = max_data; tmp > sdp->sd_diptrs;) { tmp = DIV_ROUND_UP(tmp, sdp->sd_inptrs); max_data -= tmp; } - /* This calculation isn't the exact reverse of gfs2_write_calc_reserve, - so it might end up with fewer data blocks */ - if (max_data <= *data_blocks) - return; + *data_blocks = max_data; *ind_blocks = max_blocks - max_data; *len = ((loff_t)max_data - 3) << sdp->sd_sb.sb_bsize_shift; @@ -797,7 +804,7 @@ static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_alloc_parms ap = { .aflags = 0, }; unsigned int data_blocks = 0, ind_blocks = 0, rblocks; - loff_t bytes, max_bytes; + loff_t bytes, max_bytes, max_blks = UINT_MAX; int error; const loff_t pos = offset; const loff_t count = len; @@ -819,6 +826,9 @@ static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t gfs2_size_hint(file, offset, len); + gfs2_write_calc_reserv(ip, PAGE_SIZE, &data_blocks, &ind_blocks); + ap.min_target = data_blocks + ind_blocks; + while (len > 0) { if (len < bytes) bytes = len; @@ -827,27 +837,41 @@ static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t offset += bytes; continue; } - error = gfs2_quota_lock_check(ip); + + /* We need to determine how many bytes we can actually + * fallocate without exceeding quota or going over the + * end of the fs. We start off optimistically by assuming + * we can write max_bytes */ + max_bytes = (len > max_chunk_size) ? max_chunk_size : len; + + /* Since max_bytes is most likely a theoretical max, we + * calculate a more realistic 'bytes' to serve as a good + * starting point for the number of bytes we may be able + * to write */ + gfs2_write_calc_reserv(ip, bytes, &data_blocks, &ind_blocks); + ap.target = data_blocks + ind_blocks; + + error = gfs2_quota_lock_check(ip, &ap); if (error) return error; -retry: - gfs2_write_calc_reserv(ip, bytes, &data_blocks, &ind_blocks); + /* ap.allowed tells us how many blocks quota will allow + * us to write. Check if this reduces max_blks */ + if (ap.allowed && ap.allowed < max_blks) + max_blks = ap.allowed; - ap.target = data_blocks + ind_blocks; error = gfs2_inplace_reserve(ip, &ap); - if (error) { - if (error == -ENOSPC && bytes > sdp->sd_sb.sb_bsize) { - bytes >>= 1; - bytes &= bsize_mask; - if (bytes == 0) - bytes = sdp->sd_sb.sb_bsize; - goto retry; - } + if (error) goto out_qunlock; - } - max_bytes = bytes; - calc_max_reserv(ip, (len > max_chunk_size)? max_chunk_size: len, - &max_bytes, &data_blocks, &ind_blocks); + + /* check if the selected rgrp limits our max_blks further */ + if (ap.allowed && ap.allowed < max_blks) + max_blks = ap.allowed; + + /* Almost done. Calculate bytes that can be written using + * max_blks. We also recompute max_bytes, data_blocks and + * ind_blocks */ + calc_max_reserv(ip, &max_bytes, &data_blocks, + &ind_blocks, max_blks); rblocks = RES_DINODE + ind_blocks + RES_STATFS + RES_QUOTA + RES_RG_HDR + gfs2_rg_blocks(ip, data_blocks + ind_blocks); @@ -931,6 +955,22 @@ out_uninit: return ret; } +static ssize_t gfs2_file_splice_write(struct pipe_inode_info *pipe, + struct file *out, loff_t *ppos, + size_t len, unsigned int flags) +{ + int error; + struct gfs2_inode *ip = GFS2_I(out->f_mapping->host); + + error = gfs2_rs_alloc(ip); + if (error) + return (ssize_t)error; + + gfs2_size_hint(out, *ppos, len); + + return iter_file_splice_write(pipe, out, ppos, len, flags); +} + #ifdef CONFIG_GFS2_FS_LOCKING_DLM /** @@ -1065,9 +1105,7 @@ static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl) const struct file_operations gfs2_file_fops = { .llseek = gfs2_llseek, - .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = new_sync_write, .write_iter = gfs2_file_write_iter, .unlocked_ioctl = gfs2_ioctl, .mmap = gfs2_mmap, @@ -1077,7 +1115,7 @@ const struct file_operations gfs2_file_fops = { .lock = gfs2_lock, .flock = gfs2_flock, .splice_read = generic_file_splice_read, - .splice_write = iter_file_splice_write, + .splice_write = gfs2_file_splice_write, .setlease = simple_nosetlease, .fallocate = gfs2_fallocate, }; @@ -1097,9 +1135,7 @@ const struct file_operations gfs2_dir_fops = { const struct file_operations gfs2_file_fops_nolock = { .llseek = gfs2_llseek, - .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = new_sync_write, .write_iter = gfs2_file_write_iter, .unlocked_ioctl = gfs2_ioctl, .mmap = gfs2_mmap, @@ -1107,7 +1143,7 @@ const struct file_operations gfs2_file_fops_nolock = { .release = gfs2_release, .fsync = gfs2_fsync, .splice_read = generic_file_splice_read, - .splice_write = iter_file_splice_write, + .splice_write = gfs2_file_splice_write, .setlease = generic_setlease, .fallocate = gfs2_fallocate, }; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index f42dffba056a..0fa8062f85a7 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -2047,34 +2047,41 @@ static const struct file_operations gfs2_sbstats_fops = { int gfs2_create_debugfs_file(struct gfs2_sbd *sdp) { - sdp->debugfs_dir = debugfs_create_dir(sdp->sd_table_name, gfs2_root); - if (!sdp->debugfs_dir) - return -ENOMEM; - sdp->debugfs_dentry_glocks = debugfs_create_file("glocks", - S_IFREG | S_IRUGO, - sdp->debugfs_dir, sdp, - &gfs2_glocks_fops); - if (!sdp->debugfs_dentry_glocks) + struct dentry *dent; + + dent = debugfs_create_dir(sdp->sd_table_name, gfs2_root); + if (IS_ERR_OR_NULL(dent)) + goto fail; + sdp->debugfs_dir = dent; + + dent = debugfs_create_file("glocks", + S_IFREG | S_IRUGO, + sdp->debugfs_dir, sdp, + &gfs2_glocks_fops); + if (IS_ERR_OR_NULL(dent)) goto fail; + sdp->debugfs_dentry_glocks = dent; - sdp->debugfs_dentry_glstats = debugfs_create_file("glstats", - S_IFREG | S_IRUGO, - sdp->debugfs_dir, sdp, - &gfs2_glstats_fops); - if (!sdp->debugfs_dentry_glstats) + dent = debugfs_create_file("glstats", + S_IFREG | S_IRUGO, + sdp->debugfs_dir, sdp, + &gfs2_glstats_fops); + if (IS_ERR_OR_NULL(dent)) goto fail; + sdp->debugfs_dentry_glstats = dent; - sdp->debugfs_dentry_sbstats = debugfs_create_file("sbstats", - S_IFREG | S_IRUGO, - sdp->debugfs_dir, sdp, - &gfs2_sbstats_fops); - if (!sdp->debugfs_dentry_sbstats) + dent = debugfs_create_file("sbstats", + S_IFREG | S_IRUGO, + sdp->debugfs_dir, sdp, + &gfs2_sbstats_fops); + if (IS_ERR_OR_NULL(dent)) goto fail; + sdp->debugfs_dentry_sbstats = dent; return 0; fail: gfs2_delete_debugfs_file(sdp); - return -ENOMEM; + return dent ? PTR_ERR(dent) : -ENOMEM; } void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp) @@ -2100,6 +2107,8 @@ void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp) int gfs2_register_debugfs(void) { gfs2_root = debugfs_create_dir("gfs2", NULL); + if (IS_ERR(gfs2_root)) + return PTR_ERR(gfs2_root); return gfs2_root ? 0 : -ENOMEM; } diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 7a2dbbc0d634..58b75abf6ab2 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -301,8 +301,10 @@ struct gfs2_blkreserv { * to the allocation code. */ struct gfs2_alloc_parms { - u32 target; + u64 target; + u32 min_target; u32 aflags; + u64 allowed; }; enum { diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 73c72253faac..08bc84d7e768 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -382,7 +382,7 @@ static int alloc_dinode(struct gfs2_inode *ip, u32 flags, unsigned *dblocks) struct gfs2_alloc_parms ap = { .target = *dblocks, .aflags = flags, }; int error; - error = gfs2_quota_lock_check(ip); + error = gfs2_quota_lock_check(ip, &ap); if (error) goto out; @@ -525,7 +525,7 @@ static int link_dinode(struct gfs2_inode *dip, const struct qstr *name, int error; if (da->nr_blocks) { - error = gfs2_quota_lock_check(dip); + error = gfs2_quota_lock_check(dip, &ap); if (error) goto fail_quota_locks; @@ -953,7 +953,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir, if (da.nr_blocks) { struct gfs2_alloc_parms ap = { .target = da.nr_blocks, }; - error = gfs2_quota_lock_check(dip); + error = gfs2_quota_lock_check(dip, &ap); if (error) goto out_gunlock; @@ -1470,7 +1470,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, if (da.nr_blocks) { struct gfs2_alloc_parms ap = { .target = da.nr_blocks, }; - error = gfs2_quota_lock_check(ndip); + error = gfs2_quota_lock_check(ndip, &ap); if (error) goto out_gunlock; @@ -1669,6 +1669,7 @@ static int setattr_chown(struct inode *inode, struct iattr *attr) kuid_t ouid, nuid; kgid_t ogid, ngid; int error; + struct gfs2_alloc_parms ap; ouid = inode->i_uid; ogid = inode->i_gid; @@ -1696,9 +1697,11 @@ static int setattr_chown(struct inode *inode, struct iattr *attr) if (error) goto out; + ap.target = gfs2_get_inode_blocks(&ip->i_inode); + if (!uid_eq(ouid, NO_UID_QUOTA_CHANGE) || !gid_eq(ogid, NO_GID_QUOTA_CHANGE)) { - error = gfs2_quota_check(ip, nuid, ngid); + error = gfs2_quota_check(ip, nuid, ngid, &ap); if (error) goto out_gunlock_q; } @@ -1713,9 +1716,8 @@ static int setattr_chown(struct inode *inode, struct iattr *attr) if (!uid_eq(ouid, NO_UID_QUOTA_CHANGE) || !gid_eq(ogid, NO_GID_QUOTA_CHANGE)) { - u64 blocks = gfs2_get_inode_blocks(&ip->i_inode); - gfs2_quota_change(ip, -blocks, ouid, ogid); - gfs2_quota_change(ip, blocks, nuid, ngid); + gfs2_quota_change(ip, -ap.target, ouid, ogid); + gfs2_quota_change(ip, ap.target, nuid, ngid); } out_end_trans: diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 3aa17d4d1cfc..e3065cb9ab08 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -923,6 +923,9 @@ restart: if (error) return error; + if (test_and_clear_bit(QDF_REFRESH, &qd->qd_flags)) + force_refresh = FORCE; + qd->qd_qb = *(struct gfs2_quota_lvb *)qd->qd_gl->gl_lksb.sb_lvbptr; if (force_refresh || qd->qd_qb.qb_magic != cpu_to_be32(GFS2_MAGIC)) { @@ -974,11 +977,8 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) sizeof(struct gfs2_quota_data *), sort_qd, NULL); for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) { - int force = NO_FORCE; qd = ip->i_res->rs_qa_qd[x]; - if (test_and_clear_bit(QDF_REFRESH, &qd->qd_flags)) - force = FORCE; - error = do_glock(qd, force, &ip->i_res->rs_qa_qd_ghs[x]); + error = do_glock(qd, NO_FORCE, &ip->i_res->rs_qa_qd_ghs[x]); if (error) break; } @@ -1094,14 +1094,33 @@ static int print_message(struct gfs2_quota_data *qd, char *type) return 0; } -int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) +/** + * gfs2_quota_check - check if allocating new blocks will exceed quota + * @ip: The inode for which this check is being performed + * @uid: The uid to check against + * @gid: The gid to check against + * @ap: The allocation parameters. ap->target contains the requested + * blocks. ap->min_target, if set, contains the minimum blks + * requested. + * + * Returns: 0 on success. + * min_req = ap->min_target ? ap->min_target : ap->target; + * quota must allow atleast min_req blks for success and + * ap->allowed is set to the number of blocks allowed + * + * -EDQUOT otherwise, quota violation. ap->allowed is set to number + * of blocks available. + */ +int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid, + struct gfs2_alloc_parms *ap) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_quota_data *qd; - s64 value; + s64 value, warn, limit; unsigned int x; int error = 0; + ap->allowed = UINT_MAX; /* Assume we are permitted a whole lot */ if (!test_bit(GIF_QD_LOCKED, &ip->i_flags)) return 0; @@ -1115,30 +1134,37 @@ int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) qid_eq(qd->qd_id, make_kqid_gid(gid)))) continue; + warn = (s64)be64_to_cpu(qd->qd_qb.qb_warn); + limit = (s64)be64_to_cpu(qd->qd_qb.qb_limit); value = (s64)be64_to_cpu(qd->qd_qb.qb_value); spin_lock(&qd_lock); value += qd->qd_change; spin_unlock(&qd_lock); - if (be64_to_cpu(qd->qd_qb.qb_limit) && (s64)be64_to_cpu(qd->qd_qb.qb_limit) < value) { - print_message(qd, "exceeded"); - quota_send_warning(qd->qd_id, - sdp->sd_vfs->s_dev, QUOTA_NL_BHARDWARN); - - error = -EDQUOT; - break; - } else if (be64_to_cpu(qd->qd_qb.qb_warn) && - (s64)be64_to_cpu(qd->qd_qb.qb_warn) < value && + if (limit > 0 && (limit - value) < ap->allowed) + ap->allowed = limit - value; + /* If we can't meet the target */ + if (limit && limit < (value + (s64)ap->target)) { + /* If no min_target specified or we don't meet + * min_target, return -EDQUOT */ + if (!ap->min_target || ap->min_target > ap->allowed) { + print_message(qd, "exceeded"); + quota_send_warning(qd->qd_id, + sdp->sd_vfs->s_dev, + QUOTA_NL_BHARDWARN); + error = -EDQUOT; + break; + } + } else if (warn && warn < value && time_after_eq(jiffies, qd->qd_last_warn + - gfs2_tune_get(sdp, - gt_quota_warn_period) * HZ)) { + gfs2_tune_get(sdp, gt_quota_warn_period) + * HZ)) { quota_send_warning(qd->qd_id, sdp->sd_vfs->s_dev, QUOTA_NL_BSOFTWARN); error = print_message(qd, "warning"); qd->qd_last_warn = jiffies; } } - return error; } @@ -1468,32 +1494,34 @@ int gfs2_quotad(void *data) return 0; } -static int gfs2_quota_get_xstate(struct super_block *sb, - struct fs_quota_stat *fqs) +static int gfs2_quota_get_state(struct super_block *sb, struct qc_state *state) { struct gfs2_sbd *sdp = sb->s_fs_info; - memset(fqs, 0, sizeof(struct fs_quota_stat)); - fqs->qs_version = FS_QSTAT_VERSION; + memset(state, 0, sizeof(*state)); switch (sdp->sd_args.ar_quota) { case GFS2_QUOTA_ON: - fqs->qs_flags |= (FS_QUOTA_UDQ_ENFD | FS_QUOTA_GDQ_ENFD); + state->s_state[USRQUOTA].flags |= QCI_LIMITS_ENFORCED; + state->s_state[GRPQUOTA].flags |= QCI_LIMITS_ENFORCED; /*FALLTHRU*/ case GFS2_QUOTA_ACCOUNT: - fqs->qs_flags |= (FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT); + state->s_state[USRQUOTA].flags |= QCI_ACCT_ENABLED | + QCI_SYSFILE; + state->s_state[GRPQUOTA].flags |= QCI_ACCT_ENABLED | + QCI_SYSFILE; break; case GFS2_QUOTA_OFF: break; } - if (sdp->sd_quota_inode) { - fqs->qs_uquota.qfs_ino = GFS2_I(sdp->sd_quota_inode)->i_no_addr; - fqs->qs_uquota.qfs_nblks = sdp->sd_quota_inode->i_blocks; + state->s_state[USRQUOTA].ino = + GFS2_I(sdp->sd_quota_inode)->i_no_addr; + state->s_state[USRQUOTA].blocks = sdp->sd_quota_inode->i_blocks; } - fqs->qs_uquota.qfs_nextents = 1; /* unsupported */ - fqs->qs_gquota = fqs->qs_uquota; /* its the same inode in both cases */ - fqs->qs_incoredqs = list_lru_count(&gfs2_qd_lru); + state->s_state[USRQUOTA].nextents = 1; /* unsupported */ + state->s_state[GRPQUOTA] = state->s_state[USRQUOTA]; + state->s_incoredqs = list_lru_count(&gfs2_qd_lru); return 0; } @@ -1638,7 +1666,7 @@ out_put: const struct quotactl_ops gfs2_quotactl_ops = { .quota_sync = gfs2_quota_sync, - .get_xstate = gfs2_quota_get_xstate, + .get_state = gfs2_quota_get_state, .get_dqblk = gfs2_get_dqblk, .set_dqblk = gfs2_set_dqblk, }; diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index 55d506eb3c4a..ad04b3acae2b 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -24,7 +24,8 @@ extern void gfs2_quota_unhold(struct gfs2_inode *ip); extern int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid); extern void gfs2_quota_unlock(struct gfs2_inode *ip); -extern int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid); +extern int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid, + struct gfs2_alloc_parms *ap); extern void gfs2_quota_change(struct gfs2_inode *ip, s64 change, kuid_t uid, kgid_t gid); @@ -37,7 +38,8 @@ extern int gfs2_quotad(void *data); extern void gfs2_wake_up_statfs(struct gfs2_sbd *sdp); -static inline int gfs2_quota_lock_check(struct gfs2_inode *ip) +static inline int gfs2_quota_lock_check(struct gfs2_inode *ip, + struct gfs2_alloc_parms *ap) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); int ret; @@ -48,7 +50,7 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip) return ret; if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON) return 0; - ret = gfs2_quota_check(ip, ip->i_inode.i_uid, ip->i_inode.i_gid); + ret = gfs2_quota_check(ip, ip->i_inode.i_uid, ip->i_inode.i_gid, ap); if (ret) gfs2_quota_unlock(ip); return ret; diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 9150207f365c..6af2396a317c 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -1946,10 +1946,18 @@ static inline int fast_to_acquire(struct gfs2_rgrpd *rgd) * @ip: the inode to reserve space for * @ap: the allocation parameters * - * Returns: errno + * We try our best to find an rgrp that has at least ap->target blocks + * available. After a couple of passes (loops == 2), the prospects of finding + * such an rgrp diminish. At this stage, we return the first rgrp that has + * atleast ap->min_target blocks available. Either way, we set ap->allowed to + * the number of blocks available in the chosen rgrp. + * + * Returns: 0 on success, + * -ENOMEM if a suitable rgrp can't be found + * errno otherwise */ -int gfs2_inplace_reserve(struct gfs2_inode *ip, const struct gfs2_alloc_parms *ap) +int gfs2_inplace_reserve(struct gfs2_inode *ip, struct gfs2_alloc_parms *ap) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_rgrpd *begin = NULL; @@ -2012,7 +2020,7 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, const struct gfs2_alloc_parms *a /* Skip unuseable resource groups */ if ((rs->rs_rbm.rgd->rd_flags & (GFS2_RGF_NOALLOC | GFS2_RDF_ERROR)) || - (ap->target > rs->rs_rbm.rgd->rd_extfail_pt)) + (loops == 0 && ap->target > rs->rs_rbm.rgd->rd_extfail_pt)) goto skip_rgrp; if (sdp->sd_args.ar_rgrplvb) @@ -2027,11 +2035,13 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, const struct gfs2_alloc_parms *a goto check_rgrp; /* If rgrp has enough free space, use it */ - if (rs->rs_rbm.rgd->rd_free_clone >= ap->target) { + if (rs->rs_rbm.rgd->rd_free_clone >= ap->target || + (loops == 2 && ap->min_target && + rs->rs_rbm.rgd->rd_free_clone >= ap->min_target)) { ip->i_rgd = rs->rs_rbm.rgd; + ap->allowed = ip->i_rgd->rd_free_clone; return 0; } - check_rgrp: /* Check for unlinked inodes which can be reclaimed */ if (rs->rs_rbm.rgd->rd_flags & GFS2_RDF_CHECK) diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h index b104f4af3afd..68972ecfbb01 100644 --- a/fs/gfs2/rgrp.h +++ b/fs/gfs2/rgrp.h @@ -41,7 +41,8 @@ extern void gfs2_rgrp_go_unlock(struct gfs2_holder *gh); extern struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip); #define GFS2_AF_ORLOV 1 -extern int gfs2_inplace_reserve(struct gfs2_inode *ip, const struct gfs2_alloc_parms *ap); +extern int gfs2_inplace_reserve(struct gfs2_inode *ip, + struct gfs2_alloc_parms *ap); extern void gfs2_inplace_release(struct gfs2_inode *ip); extern int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *n, diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index 0b81f783f787..fd260ce8869a 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -732,7 +732,7 @@ static int ea_alloc_skeleton(struct gfs2_inode *ip, struct gfs2_ea_request *er, if (error) return error; - error = gfs2_quota_lock_check(ip); + error = gfs2_quota_lock_check(ip, &ap); if (error) return error; diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c index 145566851e7a..36d1a6ae7655 100644 --- a/fs/hfs/dir.c +++ b/fs/hfs/dir.c @@ -197,7 +197,7 @@ static int hfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, inode = hfs_new_inode(dir, &dentry->d_name, mode); if (!inode) - return -ENOSPC; + return -ENOMEM; res = hfs_cat_create(inode->i_ino, dir, &dentry->d_name, inode); if (res) { @@ -226,7 +226,7 @@ static int hfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) inode = hfs_new_inode(dir, &dentry->d_name, S_IFDIR | mode); if (!inode) - return -ENOSPC; + return -ENOMEM; res = hfs_cat_create(inode->i_ino, dir, &dentry->d_name, inode); if (res) { diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index d0929bc81782..75fd5d873c19 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -14,7 +14,7 @@ #include <linux/pagemap.h> #include <linux/mpage.h> #include <linux/sched.h> -#include <linux/aio.h> +#include <linux/uio.h> #include "hfs_fs.h" #include "btree.h" @@ -124,8 +124,8 @@ static int hfs_releasepage(struct page *page, gfp_t mask) return res ? try_to_free_buffers(page) : 0; } -static ssize_t hfs_direct_IO(int rw, struct kiocb *iocb, - struct iov_iter *iter, loff_t offset) +static ssize_t hfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -133,13 +133,13 @@ static ssize_t hfs_direct_IO(int rw, struct kiocb *iocb, size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, hfs_get_block); + ret = blockdev_direct_IO(iocb, inode, iter, offset, hfs_get_block); /* * In case of error extending write may have instantiated a few * blocks outside i_size. Trim these off again. */ - if (unlikely((rw & WRITE) && ret < 0)) { + if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) { loff_t isize = i_size_read(inode); loff_t end = offset + count; @@ -674,9 +674,7 @@ static int hfs_file_fsync(struct file *filp, loff_t start, loff_t end, static const struct file_operations hfs_file_operations = { .llseek = generic_file_llseek, - .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = new_sync_write, .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .splice_read = generic_file_splice_read, diff --git a/fs/hfsplus/bfind.c b/fs/hfsplus/bfind.c index c1422d91cd36..528e38b5af7f 100644 --- a/fs/hfsplus/bfind.c +++ b/fs/hfsplus/bfind.c @@ -118,9 +118,7 @@ int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd, int b, e; int res; - if (!rec_found) - BUG(); - + BUG_ON(!rec_found); b = 0; e = bnode->num_recs - 1; res = -ENOENT; diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c index 6e560d56094b..754fdf8c6356 100644 --- a/fs/hfsplus/brec.c +++ b/fs/hfsplus/brec.c @@ -131,13 +131,16 @@ skip: hfs_bnode_write(node, entry, data_off + key_len, entry_len); hfs_bnode_dump(node); - if (new_node) { - /* update parent key if we inserted a key - * at the start of the first node - */ - if (!rec && new_node != node) - hfs_brec_update_parent(fd); + /* + * update parent key if we inserted a key + * at the start of the node and it is not the new node + */ + if (!rec && new_node != node) { + hfs_bnode_read_key(node, fd->search_key, data_off + size); + hfs_brec_update_parent(fd); + } + if (new_node) { hfs_bnode_put(fd->bnode); if (!new_node->parent) { hfs_btree_inc_height(tree); @@ -168,9 +171,6 @@ skip: goto again; } - if (!rec) - hfs_brec_update_parent(fd); - return 0; } @@ -370,6 +370,8 @@ again: if (IS_ERR(parent)) return PTR_ERR(parent); __hfs_brec_find(parent, fd, hfs_find_rec_by_key); + if (fd->record < 0) + return -ENOENT; hfs_bnode_dump(parent); rec = fd->record; diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c index 7892e6fddb66..022974ab6e3c 100644 --- a/fs/hfsplus/catalog.c +++ b/fs/hfsplus/catalog.c @@ -350,10 +350,11 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str) &fd.search_key->cat.name.unicode, off + 2, len); fd.search_key->key_len = cpu_to_be16(6 + len); - } else + } else { err = hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str); if (unlikely(err)) goto out; + } err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err) diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index f0235c1640af..3074609befc3 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -434,7 +434,7 @@ static int hfsplus_symlink(struct inode *dir, struct dentry *dentry, { struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb); struct inode *inode; - int res = -ENOSPC; + int res = -ENOMEM; mutex_lock(&sbi->vh_mutex); inode = hfsplus_new_inode(dir->i_sb, S_IFLNK | S_IRWXUGO); @@ -476,7 +476,7 @@ static int hfsplus_mknod(struct inode *dir, struct dentry *dentry, { struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb); struct inode *inode; - int res = -ENOSPC; + int res = -ENOMEM; mutex_lock(&sbi->vh_mutex); inode = hfsplus_new_inode(dir->i_sb, mode); diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 0cf786f2d046..b0afedbef12b 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -14,7 +14,7 @@ #include <linux/pagemap.h> #include <linux/mpage.h> #include <linux/sched.h> -#include <linux/aio.h> +#include <linux/uio.h> #include "hfsplus_fs.h" #include "hfsplus_raw.h" @@ -122,8 +122,8 @@ static int hfsplus_releasepage(struct page *page, gfp_t mask) return res ? try_to_free_buffers(page) : 0; } -static ssize_t hfsplus_direct_IO(int rw, struct kiocb *iocb, - struct iov_iter *iter, loff_t offset) +static ssize_t hfsplus_direct_IO(struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -131,14 +131,13 @@ static ssize_t hfsplus_direct_IO(int rw, struct kiocb *iocb, size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, - hfsplus_get_block); + ret = blockdev_direct_IO(iocb, inode, iter, offset, hfsplus_get_block); /* * In case of error extending write may have instantiated a few * blocks outside i_size. Trim these off again. */ - if (unlikely((rw & WRITE) && ret < 0)) { + if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) { loff_t isize = i_size_read(inode); loff_t end = offset + count; @@ -254,6 +253,12 @@ static int hfsplus_setattr(struct dentry *dentry, struct iattr *attr) if ((attr->ia_valid & ATTR_SIZE) && attr->ia_size != i_size_read(inode)) { inode_dio_wait(inode); + if (attr->ia_size > inode->i_size) { + error = generic_cont_expand_simple(inode, + attr->ia_size); + if (error) + return error; + } truncate_setsize(inode, attr->ia_size); hfsplus_file_truncate(inode); } @@ -341,9 +346,7 @@ static const struct inode_operations hfsplus_file_inode_operations = { static const struct file_operations hfsplus_file_operations = { .llseek = generic_file_llseek, - .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = new_sync_write, .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .splice_read = generic_file_splice_read, diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c index d3ff5cc317d7..8e98f5db6ad6 100644 --- a/fs/hfsplus/ioctl.c +++ b/fs/hfsplus/ioctl.c @@ -76,7 +76,7 @@ static int hfsplus_ioctl_setflags(struct file *file, int __user *user_flags) { struct inode *inode = file_inode(file); struct hfsplus_inode_info *hip = HFSPLUS_I(inode); - unsigned int flags; + unsigned int flags, new_fl = 0; int err = 0; err = mnt_want_write_file(file); @@ -110,14 +110,12 @@ static int hfsplus_ioctl_setflags(struct file *file, int __user *user_flags) } if (flags & FS_IMMUTABLE_FL) - inode->i_flags |= S_IMMUTABLE; - else - inode->i_flags &= ~S_IMMUTABLE; + new_fl |= S_IMMUTABLE; if (flags & FS_APPEND_FL) - inode->i_flags |= S_APPEND; - else - inode->i_flags &= ~S_APPEND; + new_fl |= S_APPEND; + + inode_set_flags(inode, new_fl, S_IMMUTABLE | S_APPEND); if (flags & FS_NODUMP_FL) hip->userflags |= HFSPLUS_FLG_NODUMP; diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c index d98094a9f476..89f262d8fcd8 100644 --- a/fs/hfsplus/xattr.c +++ b/fs/hfsplus/xattr.c @@ -44,7 +44,7 @@ static int strcmp_xattr_acl(const char *name) return -1; } -static inline int is_known_namespace(const char *name) +static bool is_known_namespace(const char *name) { if (strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN) && strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) && @@ -424,6 +424,28 @@ static int copy_name(char *buffer, const char *xattr_name, int name_len) return len; } +int hfsplus_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags, + const char *prefix, size_t prefixlen) +{ + char *xattr_name; + int res; + + if (!strcmp(name, "")) + return -EINVAL; + + xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1, + GFP_KERNEL); + if (!xattr_name) + return -ENOMEM; + strcpy(xattr_name, prefix); + strcpy(xattr_name + prefixlen, name); + res = __hfsplus_setxattr(dentry->d_inode, xattr_name, value, size, + flags); + kfree(xattr_name); + return res; +} + static ssize_t hfsplus_getxattr_finder_info(struct inode *inode, void *value, size_t size) { @@ -560,6 +582,30 @@ failed_getxattr_init: return res; } +ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, + void *value, size_t size, + const char *prefix, size_t prefixlen) +{ + int res; + char *xattr_name; + + if (!strcmp(name, "")) + return -EINVAL; + + xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1, + GFP_KERNEL); + if (!xattr_name) + return -ENOMEM; + + strcpy(xattr_name, prefix); + strcpy(xattr_name + prefixlen, name); + + res = __hfsplus_getxattr(dentry->d_inode, xattr_name, value, size); + kfree(xattr_name); + return res; + +} + static inline int can_list(const char *xattr_name) { if (!xattr_name) @@ -806,9 +852,6 @@ end_removexattr: static int hfsplus_osx_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t size, int type) { - char *xattr_name; - int res; - if (!strcmp(name, "")) return -EINVAL; @@ -818,24 +861,19 @@ static int hfsplus_osx_getxattr(struct dentry *dentry, const char *name, */ if (is_known_namespace(name)) return -EOPNOTSUPP; - xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN - + XATTR_MAC_OSX_PREFIX_LEN + 1, GFP_KERNEL); - if (!xattr_name) - return -ENOMEM; - strcpy(xattr_name, XATTR_MAC_OSX_PREFIX); - strcpy(xattr_name + XATTR_MAC_OSX_PREFIX_LEN, name); - res = hfsplus_getxattr(dentry, xattr_name, buffer, size); - kfree(xattr_name); - return res; + /* + * osx is the namespace we use to indicate an unprefixed + * attribute on the filesystem (like the ones that OS X + * creates), so we pass the name through unmodified (after + * ensuring it doesn't conflict with another namespace). + */ + return __hfsplus_getxattr(dentry->d_inode, name, buffer, size); } static int hfsplus_osx_setxattr(struct dentry *dentry, const char *name, const void *buffer, size_t size, int flags, int type) { - char *xattr_name; - int res; - if (!strcmp(name, "")) return -EINVAL; @@ -845,16 +883,14 @@ static int hfsplus_osx_setxattr(struct dentry *dentry, const char *name, */ if (is_known_namespace(name)) return -EOPNOTSUPP; - xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN - + XATTR_MAC_OSX_PREFIX_LEN + 1, GFP_KERNEL); - if (!xattr_name) - return -ENOMEM; - strcpy(xattr_name, XATTR_MAC_OSX_PREFIX); - strcpy(xattr_name + XATTR_MAC_OSX_PREFIX_LEN, name); - res = hfsplus_setxattr(dentry, xattr_name, buffer, size, flags); - kfree(xattr_name); - return res; + /* + * osx is the namespace we use to indicate an unprefixed + * attribute on the filesystem (like the ones that OS X + * creates), so we pass the name through unmodified (after + * ensuring it doesn't conflict with another namespace). + */ + return __hfsplus_setxattr(dentry->d_inode, name, buffer, size, flags); } static size_t hfsplus_osx_listxattr(struct dentry *dentry, char *list, diff --git a/fs/hfsplus/xattr.h b/fs/hfsplus/xattr.h index 288530cf80b5..f9b0955b3d28 100644 --- a/fs/hfsplus/xattr.h +++ b/fs/hfsplus/xattr.h @@ -21,22 +21,16 @@ extern const struct xattr_handler *hfsplus_xattr_handlers[]; int __hfsplus_setxattr(struct inode *inode, const char *name, const void *value, size_t size, int flags); -static inline int hfsplus_setxattr(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags) -{ - return __hfsplus_setxattr(dentry->d_inode, name, value, size, flags); -} +int hfsplus_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags, + const char *prefix, size_t prefixlen); ssize_t __hfsplus_getxattr(struct inode *inode, const char *name, - void *value, size_t size); - -static inline ssize_t hfsplus_getxattr(struct dentry *dentry, - const char *name, - void *value, - size_t size) -{ - return __hfsplus_getxattr(dentry->d_inode, name, value, size); -} + void *value, size_t size); + +ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, + void *value, size_t size, + const char *prefix, size_t prefixlen); ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size); diff --git a/fs/hfsplus/xattr_security.c b/fs/hfsplus/xattr_security.c index 6ec5e107691f..aacff00a9ff9 100644 --- a/fs/hfsplus/xattr_security.c +++ b/fs/hfsplus/xattr_security.c @@ -16,43 +16,17 @@ static int hfsplus_security_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t size, int type) { - char *xattr_name; - int res; - - if (!strcmp(name, "")) - return -EINVAL; - - xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1, - GFP_KERNEL); - if (!xattr_name) - return -ENOMEM; - strcpy(xattr_name, XATTR_SECURITY_PREFIX); - strcpy(xattr_name + XATTR_SECURITY_PREFIX_LEN, name); - - res = hfsplus_getxattr(dentry, xattr_name, buffer, size); - kfree(xattr_name); - return res; + return hfsplus_getxattr(dentry, name, buffer, size, + XATTR_SECURITY_PREFIX, + XATTR_SECURITY_PREFIX_LEN); } static int hfsplus_security_setxattr(struct dentry *dentry, const char *name, const void *buffer, size_t size, int flags, int type) { - char *xattr_name; - int res; - - if (!strcmp(name, "")) - return -EINVAL; - - xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1, - GFP_KERNEL); - if (!xattr_name) - return -ENOMEM; - strcpy(xattr_name, XATTR_SECURITY_PREFIX); - strcpy(xattr_name + XATTR_SECURITY_PREFIX_LEN, name); - - res = hfsplus_setxattr(dentry, xattr_name, buffer, size, flags); - kfree(xattr_name); - return res; + return hfsplus_setxattr(dentry, name, buffer, size, flags, + XATTR_SECURITY_PREFIX, + XATTR_SECURITY_PREFIX_LEN); } static size_t hfsplus_security_listxattr(struct dentry *dentry, char *list, diff --git a/fs/hfsplus/xattr_trusted.c b/fs/hfsplus/xattr_trusted.c index 3c5f27e4746a..bcf65089b7f7 100644 --- a/fs/hfsplus/xattr_trusted.c +++ b/fs/hfsplus/xattr_trusted.c @@ -14,43 +14,16 @@ static int hfsplus_trusted_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t size, int type) { - char *xattr_name; - int res; - - if (!strcmp(name, "")) - return -EINVAL; - - xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1, - GFP_KERNEL); - if (!xattr_name) - return -ENOMEM; - strcpy(xattr_name, XATTR_TRUSTED_PREFIX); - strcpy(xattr_name + XATTR_TRUSTED_PREFIX_LEN, name); - - res = hfsplus_getxattr(dentry, xattr_name, buffer, size); - kfree(xattr_name); - return res; + return hfsplus_getxattr(dentry, name, buffer, size, + XATTR_TRUSTED_PREFIX, + XATTR_TRUSTED_PREFIX_LEN); } static int hfsplus_trusted_setxattr(struct dentry *dentry, const char *name, const void *buffer, size_t size, int flags, int type) { - char *xattr_name; - int res; - - if (!strcmp(name, "")) - return -EINVAL; - - xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1, - GFP_KERNEL); - if (!xattr_name) - return -ENOMEM; - strcpy(xattr_name, XATTR_TRUSTED_PREFIX); - strcpy(xattr_name + XATTR_TRUSTED_PREFIX_LEN, name); - - res = hfsplus_setxattr(dentry, xattr_name, buffer, size, flags); - kfree(xattr_name); - return res; + return hfsplus_setxattr(dentry, name, buffer, size, flags, + XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN); } static size_t hfsplus_trusted_listxattr(struct dentry *dentry, char *list, diff --git a/fs/hfsplus/xattr_user.c b/fs/hfsplus/xattr_user.c index 2b625a538b64..5aa0e6dc4a1e 100644 --- a/fs/hfsplus/xattr_user.c +++ b/fs/hfsplus/xattr_user.c @@ -14,43 +14,16 @@ static int hfsplus_user_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t size, int type) { - char *xattr_name; - int res; - if (!strcmp(name, "")) - return -EINVAL; - - xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1, - GFP_KERNEL); - if (!xattr_name) - return -ENOMEM; - strcpy(xattr_name, XATTR_USER_PREFIX); - strcpy(xattr_name + XATTR_USER_PREFIX_LEN, name); - - res = hfsplus_getxattr(dentry, xattr_name, buffer, size); - kfree(xattr_name); - return res; + return hfsplus_getxattr(dentry, name, buffer, size, + XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN); } static int hfsplus_user_setxattr(struct dentry *dentry, const char *name, const void *buffer, size_t size, int flags, int type) { - char *xattr_name; - int res; - - if (!strcmp(name, "")) - return -EINVAL; - - xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1, - GFP_KERNEL); - if (!xattr_name) - return -ENOMEM; - strcpy(xattr_name, XATTR_USER_PREFIX); - strcpy(xattr_name + XATTR_USER_PREFIX_LEN, name); - - res = hfsplus_setxattr(dentry, xattr_name, buffer, size, flags); - kfree(xattr_name); - return res; + return hfsplus_setxattr(dentry, name, buffer, size, flags, + XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN); } static size_t hfsplus_user_listxattr(struct dentry *dentry, char *list, diff --git a/fs/hostfs/hostfs.h b/fs/hostfs/hostfs.h index 4fcd40d6f308..91e19f9dffe5 100644 --- a/fs/hostfs/hostfs.h +++ b/fs/hostfs/hostfs.h @@ -66,7 +66,8 @@ extern int stat_file(const char *path, struct hostfs_stat *p, int fd); extern int access_file(char *path, int r, int w, int x); extern int open_file(char *path, int r, int w, int append); extern void *open_dir(char *path, int *err_out); -extern char *read_dir(void *stream, unsigned long long *pos, +extern void seek_dir(void *stream, unsigned long long pos); +extern char *read_dir(void *stream, unsigned long long *pos_out, unsigned long long *ino_out, int *len_out, unsigned int *type_out); extern void close_file(void *stream); @@ -77,8 +78,7 @@ extern int write_file(int fd, unsigned long long *offset, const char *buf, int len); extern int lseek_file(int fd, long long offset, int whence); extern int fsync_file(int fd, int datasync); -extern int file_create(char *name, int ur, int uw, int ux, int gr, - int gw, int gx, int or, int ow, int ox); +extern int file_create(char *name, int mode); extern int set_attr(const char *file, struct hostfs_iattr *attrs, int fd); extern int make_symlink(const char *from, const char *to); extern int unlink_file(const char *file); diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index fd62cae0fdcb..b83a0343378b 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -24,6 +24,7 @@ struct hostfs_inode_info { int fd; fmode_t mode; struct inode vfs_inode; + struct mutex open_mutex; }; static inline struct hostfs_inode_info *HOSTFS_I(struct inode *inode) @@ -92,16 +93,22 @@ static char *__dentry_name(struct dentry *dentry, char *name) __putname(name); return NULL; } + + /* + * This function relies on the fact that dentry_path_raw() will place + * the path name at the end of the provided buffer. + */ + BUG_ON(p + strlen(p) + 1 != name + PATH_MAX); + strlcpy(name, root, PATH_MAX); if (len > p - name) { __putname(name); return NULL; } - if (p > name + len) { - char *s = name + len; - while ((*s++ = *p++) != '\0') - ; - } + + if (p > name + len) + strcpy(name + len, p); + return name; } @@ -135,21 +142,19 @@ static char *follow_link(char *link) int len, n; char *name, *resolved, *end; - len = 64; - while (1) { + name = __getname(); + if (!name) { n = -ENOMEM; - name = kmalloc(len, GFP_KERNEL); - if (name == NULL) - goto out; - - n = hostfs_do_readlink(link, name, len); - if (n < len) - break; - len *= 2; - kfree(name); + goto out_free; } + + n = hostfs_do_readlink(link, name, PATH_MAX); if (n < 0) goto out_free; + else if (n == PATH_MAX) { + n = -E2BIG; + goto out_free; + } if (*name == '/') return name; @@ -168,13 +173,12 @@ static char *follow_link(char *link) } sprintf(resolved, "%s%s", link, name); - kfree(name); + __putname(name); kfree(link); return resolved; out_free: - kfree(name); - out: + __putname(name); return ERR_PTR(n); } @@ -225,6 +229,7 @@ static struct inode *hostfs_alloc_inode(struct super_block *sb) hi->fd = -1; hi->mode = 0; inode_init_once(&hi->vfs_inode); + mutex_init(&hi->open_mutex); return &hi->vfs_inode; } @@ -257,6 +262,9 @@ static int hostfs_show_options(struct seq_file *seq, struct dentry *root) if (strlen(root_path) > offset) seq_printf(seq, ",%s", root_path + offset); + if (append) + seq_puts(seq, ",append"); + return 0; } @@ -284,6 +292,7 @@ static int hostfs_readdir(struct file *file, struct dir_context *ctx) if (dir == NULL) return -error; next = ctx->pos; + seek_dir(dir, next); while ((name = read_dir(dir, &next, &ino, &len, &type)) != NULL) { if (!dir_emit(ctx, name, len, ino, type)) break; @@ -293,13 +302,12 @@ static int hostfs_readdir(struct file *file, struct dir_context *ctx) return 0; } -static int hostfs_file_open(struct inode *ino, struct file *file) +static int hostfs_open(struct inode *ino, struct file *file) { - static DEFINE_MUTEX(open_mutex); char *name; - fmode_t mode = 0; + fmode_t mode; int err; - int r = 0, w = 0, fd; + int r, w, fd; mode = file->f_mode & (FMODE_READ | FMODE_WRITE); if ((mode & HOSTFS_I(ino)->mode) == mode) @@ -308,12 +316,12 @@ static int hostfs_file_open(struct inode *ino, struct file *file) mode |= HOSTFS_I(ino)->mode; retry: + r = w = 0; + if (mode & FMODE_READ) r = 1; if (mode & FMODE_WRITE) - w = 1; - if (w) - r = 1; + r = w = 1; name = dentry_name(file->f_path.dentry); if (name == NULL) @@ -324,15 +332,16 @@ retry: if (fd < 0) return fd; - mutex_lock(&open_mutex); + mutex_lock(&HOSTFS_I(ino)->open_mutex); /* somebody else had handled it first? */ if ((mode & HOSTFS_I(ino)->mode) == mode) { - mutex_unlock(&open_mutex); + mutex_unlock(&HOSTFS_I(ino)->open_mutex); + close_file(&fd); return 0; } if ((mode | HOSTFS_I(ino)->mode) != mode) { mode |= HOSTFS_I(ino)->mode; - mutex_unlock(&open_mutex); + mutex_unlock(&HOSTFS_I(ino)->open_mutex); close_file(&fd); goto retry; } @@ -342,12 +351,12 @@ retry: err = replace_file(fd, HOSTFS_I(ino)->fd); close_file(&fd); if (err < 0) { - mutex_unlock(&open_mutex); + mutex_unlock(&HOSTFS_I(ino)->open_mutex); return err; } } HOSTFS_I(ino)->mode = mode; - mutex_unlock(&open_mutex); + mutex_unlock(&HOSTFS_I(ino)->open_mutex); return 0; } @@ -378,13 +387,11 @@ static int hostfs_fsync(struct file *file, loff_t start, loff_t end, static const struct file_operations hostfs_file_fops = { .llseek = generic_file_llseek, - .read = new_sync_read, .splice_read = generic_file_splice_read, .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, - .write = new_sync_write, .mmap = generic_file_mmap, - .open = hostfs_file_open, + .open = hostfs_open, .release = hostfs_file_release, .fsync = hostfs_fsync, }; @@ -393,6 +400,8 @@ static const struct file_operations hostfs_dir_fops = { .llseek = generic_file_llseek, .iterate = hostfs_readdir, .read = generic_read_dir, + .open = hostfs_open, + .fsync = hostfs_fsync, }; static int hostfs_writepage(struct page *page, struct writeback_control *wbc) @@ -400,7 +409,7 @@ static int hostfs_writepage(struct page *page, struct writeback_control *wbc) struct address_space *mapping = page->mapping; struct inode *inode = mapping->host; char *buffer; - unsigned long long base; + loff_t base = page_offset(page); int count = PAGE_CACHE_SIZE; int end_index = inode->i_size >> PAGE_CACHE_SHIFT; int err; @@ -409,7 +418,6 @@ static int hostfs_writepage(struct page *page, struct writeback_control *wbc) count = inode->i_size & (PAGE_CACHE_SIZE-1); buffer = kmap(page); - base = ((unsigned long long) page->index) << PAGE_CACHE_SHIFT; err = write_file(HOSTFS_I(inode)->fd, &base, buffer, count); if (err != count) { @@ -434,26 +442,29 @@ static int hostfs_writepage(struct page *page, struct writeback_control *wbc) static int hostfs_readpage(struct file *file, struct page *page) { char *buffer; - long long start; - int err = 0; + loff_t start = page_offset(page); + int bytes_read, ret = 0; - start = (long long) page->index << PAGE_CACHE_SHIFT; buffer = kmap(page); - err = read_file(FILE_HOSTFS_I(file)->fd, &start, buffer, + bytes_read = read_file(FILE_HOSTFS_I(file)->fd, &start, buffer, PAGE_CACHE_SIZE); - if (err < 0) + if (bytes_read < 0) { + ClearPageUptodate(page); + SetPageError(page); + ret = bytes_read; goto out; + } - memset(&buffer[err], 0, PAGE_CACHE_SIZE - err); + memset(buffer + bytes_read, 0, PAGE_CACHE_SIZE - bytes_read); - flush_dcache_page(page); + ClearPageError(page); SetPageUptodate(page); - if (PageError(page)) ClearPageError(page); - err = 0; + out: + flush_dcache_page(page); kunmap(page); unlock_page(page); - return err; + return ret; } static int hostfs_write_begin(struct file *file, struct address_space *mapping, @@ -530,11 +541,13 @@ static int read_name(struct inode *ino, char *name) init_special_inode(ino, st.mode & S_IFMT, rdev); ino->i_op = &hostfs_iops; break; - - default: + case S_IFREG: ino->i_op = &hostfs_iops; ino->i_fop = &hostfs_file_fops; ino->i_mapping->a_ops = &hostfs_aops; + break; + default: + return -EIO; } ino->i_ino = st.ino; @@ -568,10 +581,7 @@ static int hostfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, if (name == NULL) goto out_put; - fd = file_create(name, - mode & S_IRUSR, mode & S_IWUSR, mode & S_IXUSR, - mode & S_IRGRP, mode & S_IWGRP, mode & S_IXGRP, - mode & S_IROTH, mode & S_IWOTH, mode & S_IXOTH); + fd = file_create(name, mode & S_IFMT); if (fd < 0) error = fd; else diff --git a/fs/hostfs/hostfs_user.c b/fs/hostfs/hostfs_user.c index 9765dab95cbd..9c1e0f019880 100644 --- a/fs/hostfs/hostfs_user.c +++ b/fs/hostfs/hostfs_user.c @@ -97,21 +97,27 @@ void *open_dir(char *path, int *err_out) return dir; } -char *read_dir(void *stream, unsigned long long *pos, +void seek_dir(void *stream, unsigned long long pos) +{ + DIR *dir = stream; + + seekdir(dir, pos); +} + +char *read_dir(void *stream, unsigned long long *pos_out, unsigned long long *ino_out, int *len_out, unsigned int *type_out) { DIR *dir = stream; struct dirent *ent; - seekdir(dir, *pos); ent = readdir(dir); if (ent == NULL) return NULL; *len_out = strlen(ent->d_name); *ino_out = ent->d_ino; *type_out = ent->d_type; - *pos = telldir(dir); + *pos_out = ent->d_off; return ent->d_name; } @@ -175,21 +181,10 @@ void close_dir(void *stream) closedir(stream); } -int file_create(char *name, int ur, int uw, int ux, int gr, - int gw, int gx, int or, int ow, int ox) +int file_create(char *name, int mode) { - int mode, fd; - - mode = 0; - mode |= ur ? S_IRUSR : 0; - mode |= uw ? S_IWUSR : 0; - mode |= ux ? S_IXUSR : 0; - mode |= gr ? S_IRGRP : 0; - mode |= gw ? S_IWGRP : 0; - mode |= gx ? S_IXGRP : 0; - mode |= or ? S_IROTH : 0; - mode |= ow ? S_IWOTH : 0; - mode |= ox ? S_IXOTH : 0; + int fd; + fd = open64(name, O_CREAT | O_RDWR, mode); if (fd < 0) return -errno; diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index 7f54e5f76cec..6d8cfe9b52d6 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -197,9 +197,7 @@ const struct address_space_operations hpfs_aops = { const struct file_operations hpfs_file_ops = { .llseek = generic_file_llseek, - .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = new_sync_write, .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .release = hpfs_file_release, diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index c274aca8e8dc..2640d88b0e63 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -34,6 +34,7 @@ #include <linux/security.h> #include <linux/magic.h> #include <linux/migrate.h> +#include <linux/uio.h> #include <asm/uaccess.h> @@ -47,9 +48,10 @@ struct hugetlbfs_config { kuid_t uid; kgid_t gid; umode_t mode; - long nr_blocks; + long max_hpages; long nr_inodes; struct hstate *hstate; + long min_hpages; }; struct hugetlbfs_inode_info { @@ -67,7 +69,7 @@ int sysctl_hugetlb_shm_group; enum { Opt_size, Opt_nr_inodes, Opt_mode, Opt_uid, Opt_gid, - Opt_pagesize, + Opt_pagesize, Opt_min_size, Opt_err, }; @@ -78,6 +80,7 @@ static const match_table_t tokens = { {Opt_uid, "uid=%u"}, {Opt_gid, "gid=%u"}, {Opt_pagesize, "pagesize=%s"}, + {Opt_min_size, "min_size=%s"}, {Opt_err, NULL}, }; @@ -179,42 +182,33 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, } #endif -static int +static size_t hugetlbfs_read_actor(struct page *page, unsigned long offset, - char __user *buf, unsigned long count, - unsigned long size) + struct iov_iter *to, unsigned long size) { - char *kaddr; - unsigned long left, copied = 0; + size_t copied = 0; int i, chunksize; - if (size > count) - size = count; - /* Find which 4k chunk and offset with in that chunk */ i = offset >> PAGE_CACHE_SHIFT; offset = offset & ~PAGE_CACHE_MASK; while (size) { + size_t n; chunksize = PAGE_CACHE_SIZE; if (offset) chunksize -= offset; if (chunksize > size) chunksize = size; - kaddr = kmap(&page[i]); - left = __copy_to_user(buf, kaddr + offset, chunksize); - kunmap(&page[i]); - if (left) { - copied += (chunksize - left); - break; - } + n = copy_page_to_iter(&page[i], offset, chunksize, to); + copied += n; + if (n != chunksize) + return copied; offset = 0; size -= chunksize; - buf += chunksize; - copied += chunksize; i++; } - return copied ? copied : -EFAULT; + return copied; } /* @@ -222,39 +216,34 @@ hugetlbfs_read_actor(struct page *page, unsigned long offset, * data. Its *very* similar to do_generic_mapping_read(), we can't use that * since it has PAGE_CACHE_SIZE assumptions. */ -static ssize_t hugetlbfs_read(struct file *filp, char __user *buf, - size_t len, loff_t *ppos) +static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to) { - struct hstate *h = hstate_file(filp); - struct address_space *mapping = filp->f_mapping; + struct file *file = iocb->ki_filp; + struct hstate *h = hstate_file(file); + struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; - unsigned long index = *ppos >> huge_page_shift(h); - unsigned long offset = *ppos & ~huge_page_mask(h); + unsigned long index = iocb->ki_pos >> huge_page_shift(h); + unsigned long offset = iocb->ki_pos & ~huge_page_mask(h); unsigned long end_index; loff_t isize; ssize_t retval = 0; - /* validate length */ - if (len == 0) - goto out; - - for (;;) { + while (iov_iter_count(to)) { struct page *page; - unsigned long nr, ret; - int ra; + size_t nr, copied; /* nr is the maximum number of bytes to copy from this page */ nr = huge_page_size(h); isize = i_size_read(inode); if (!isize) - goto out; + break; end_index = (isize - 1) >> huge_page_shift(h); - if (index >= end_index) { - if (index > end_index) - goto out; + if (index > end_index) + break; + if (index == end_index) { nr = ((isize - 1) & ~huge_page_mask(h)) + 1; if (nr <= offset) - goto out; + break; } nr = nr - offset; @@ -265,39 +254,27 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf, * We have a HOLE, zero out the user-buffer for the * length of the hole or request. */ - ret = len < nr ? len : nr; - if (clear_user(buf, ret)) - ra = -EFAULT; - else - ra = 0; + copied = iov_iter_zero(nr, to); } else { unlock_page(page); /* * We have the page, copy it to user space buffer. */ - ra = hugetlbfs_read_actor(page, offset, buf, len, nr); - ret = ra; + copied = hugetlbfs_read_actor(page, offset, to, nr); page_cache_release(page); } - if (ra < 0) { - if (retval == 0) - retval = ra; - goto out; + offset += copied; + retval += copied; + if (copied != nr && iov_iter_count(to)) { + if (!retval) + retval = -EFAULT; + break; } - - offset += ret; - retval += ret; - len -= ret; index += offset >> huge_page_shift(h); offset &= ~huge_page_mask(h); - - /* short read or no more work */ - if ((ret != nr) || (len == 0)) - break; } -out: - *ppos = ((loff_t)index << huge_page_shift(h)) + offset; + iocb->ki_pos = ((loff_t)index << huge_page_shift(h)) + offset; return retval; } @@ -319,7 +296,7 @@ static int hugetlbfs_write_end(struct file *file, struct address_space *mapping, static void truncate_huge_page(struct page *page) { - cancel_dirty_page(page, /* No IO accounting for huge pages? */0); + ClearPageDirty(page); ClearPageUptodate(page); delete_from_page_cache(page); } @@ -721,7 +698,7 @@ static void init_once(void *foo) } const struct file_operations hugetlbfs_file_operations = { - .read = hugetlbfs_read, + .read_iter = hugetlbfs_read_iter, .mmap = hugetlbfs_file_mmap, .fsync = noop_fsync, .get_unmapped_area = hugetlb_get_unmapped_area, @@ -754,14 +731,38 @@ static const struct super_operations hugetlbfs_ops = { .show_options = generic_show_options, }; +enum { NO_SIZE, SIZE_STD, SIZE_PERCENT }; + +/* + * Convert size option passed from command line to number of huge pages + * in the pool specified by hstate. Size option could be in bytes + * (val_type == SIZE_STD) or percentage of the pool (val_type == SIZE_PERCENT). + */ +static long long +hugetlbfs_size_to_hpages(struct hstate *h, unsigned long long size_opt, + int val_type) +{ + if (val_type == NO_SIZE) + return -1; + + if (val_type == SIZE_PERCENT) { + size_opt <<= huge_page_shift(h); + size_opt *= h->max_huge_pages; + do_div(size_opt, 100); + } + + size_opt >>= huge_page_shift(h); + return size_opt; +} + static int hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig) { char *p, *rest; substring_t args[MAX_OPT_ARGS]; int option; - unsigned long long size = 0; - enum { NO_SIZE, SIZE_STD, SIZE_PERCENT } setsize = NO_SIZE; + unsigned long long max_size_opt = 0, min_size_opt = 0; + int max_val_type = NO_SIZE, min_val_type = NO_SIZE; if (!options) return 0; @@ -799,10 +800,10 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig) /* memparse() will accept a K/M/G without a digit */ if (!isdigit(*args[0].from)) goto bad_val; - size = memparse(args[0].from, &rest); - setsize = SIZE_STD; + max_size_opt = memparse(args[0].from, &rest); + max_val_type = SIZE_STD; if (*rest == '%') - setsize = SIZE_PERCENT; + max_val_type = SIZE_PERCENT; break; } @@ -825,6 +826,17 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig) break; } + case Opt_min_size: { + /* memparse() will accept a K/M/G without a digit */ + if (!isdigit(*args[0].from)) + goto bad_val; + min_size_opt = memparse(args[0].from, &rest); + min_val_type = SIZE_STD; + if (*rest == '%') + min_val_type = SIZE_PERCENT; + break; + } + default: pr_err("Bad mount option: \"%s\"\n", p); return -EINVAL; @@ -832,15 +844,22 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig) } } - /* Do size after hstate is set up */ - if (setsize > NO_SIZE) { - struct hstate *h = pconfig->hstate; - if (setsize == SIZE_PERCENT) { - size <<= huge_page_shift(h); - size *= h->max_huge_pages; - do_div(size, 100); - } - pconfig->nr_blocks = (size >> huge_page_shift(h)); + /* + * Use huge page pool size (in hstate) to convert the size + * options to number of huge pages. If NO_SIZE, -1 is returned. + */ + pconfig->max_hpages = hugetlbfs_size_to_hpages(pconfig->hstate, + max_size_opt, max_val_type); + pconfig->min_hpages = hugetlbfs_size_to_hpages(pconfig->hstate, + min_size_opt, min_val_type); + + /* + * If max_size was specified, then min_size must be smaller + */ + if (max_val_type > NO_SIZE && + pconfig->min_hpages > pconfig->max_hpages) { + pr_err("minimum size can not be greater than maximum size\n"); + return -EINVAL; } return 0; @@ -859,12 +878,13 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent) save_mount_options(sb, data); - config.nr_blocks = -1; /* No limit on size by default */ + config.max_hpages = -1; /* No limit on size by default */ config.nr_inodes = -1; /* No limit on number of inodes by default */ config.uid = current_fsuid(); config.gid = current_fsgid(); config.mode = 0755; config.hstate = &default_hstate; + config.min_hpages = -1; /* No default minimum size */ ret = hugetlbfs_parse_options(data, &config); if (ret) return ret; @@ -878,8 +898,15 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent) sbinfo->max_inodes = config.nr_inodes; sbinfo->free_inodes = config.nr_inodes; sbinfo->spool = NULL; - if (config.nr_blocks != -1) { - sbinfo->spool = hugepage_new_subpool(config.nr_blocks); + /* + * Allocate and initialize subpool if maximum or minimum size is + * specified. Any needed reservations (for minimim size) are taken + * taken when the subpool is created. + */ + if (config.max_hpages != -1 || config.min_hpages != -1) { + sbinfo->spool = hugepage_new_subpool(config.hstate, + config.max_hpages, + config.min_hpages); if (!sbinfo->spool) goto out_free; } diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index 64989ca9ba90..f509f62e12f6 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -51,9 +51,7 @@ const struct file_operations jffs2_file_operations = { .llseek = generic_file_llseek, .open = generic_file_open, - .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = new_sync_write, .write_iter = generic_file_write_iter, .unlocked_ioctl=jffs2_ioctl, .mmap = generic_file_readonly_mmap, diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c index d72817ac51f6..2eac55379239 100644 --- a/fs/jffs2/xattr.c +++ b/fs/jffs2/xattr.c @@ -195,7 +195,7 @@ static int do_verify_xattr_datum(struct jffs2_sb_info *c, struct jffs2_xattr_dat /* unchecked xdatum is chained with c->xattr_unchecked */ list_del_init(&xd->xindex); - dbg_xattr("success on verfying xdatum (xid=%u, version=%u)\n", + dbg_xattr("success on verifying xdatum (xid=%u, version=%u)\n", xd->xid, xd->version); return 0; @@ -1266,7 +1266,6 @@ int jffs2_garbage_collect_xattr_ref(struct jffs2_sb_info *c, struct jffs2_xattr_ if (rc) { JFFS2_WARNING("%s: jffs2_reserve_space_gc() = %d, request = %u\n", __func__, rc, totlen); - rc = rc ? rc : -EBADFD; goto out; } rc = save_xattr_ref(c, ref); diff --git a/fs/jfs/file.c b/fs/jfs/file.c index 10815f8dfd8b..ae46788b9723 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -151,8 +151,6 @@ const struct inode_operations jfs_file_inode_operations = { const struct file_operations jfs_file_operations = { .open = jfs_open, .llseek = generic_file_llseek, - .write = new_sync_write, - .read = new_sync_read, .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index bd3df1ca3c9b..070dc4b33544 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -22,8 +22,8 @@ #include <linux/buffer_head.h> #include <linux/pagemap.h> #include <linux/quotaops.h> +#include <linux/uio.h> #include <linux/writeback.h> -#include <linux/aio.h> #include "jfs_incore.h" #include "jfs_inode.h" #include "jfs_filsys.h" @@ -330,8 +330,8 @@ static sector_t jfs_bmap(struct address_space *mapping, sector_t block) return generic_block_bmap(mapping, block, jfs_get_block); } -static ssize_t jfs_direct_IO(int rw, struct kiocb *iocb, - struct iov_iter *iter, loff_t offset) +static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -339,13 +339,13 @@ static ssize_t jfs_direct_IO(int rw, struct kiocb *iocb, size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, jfs_get_block); + ret = blockdev_direct_IO(iocb, inode, iter, offset, jfs_get_block); /* * In case of error extending write may have instantiated a few * blocks outside i_size. Trim these off again. */ - if (unlikely((rw & WRITE) && ret < 0)) { + if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) { loff_t isize = i_size_read(inode); loff_t end = offset + count; diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index 49ba7ff1bbb9..16a0922beb59 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -183,30 +183,23 @@ static inline void remove_metapage(struct page *page, struct metapage *mp) #endif -static void init_once(void *foo) -{ - struct metapage *mp = (struct metapage *)foo; - - mp->lid = 0; - mp->lsn = 0; - mp->flag = 0; - mp->data = NULL; - mp->clsn = 0; - mp->log = NULL; - set_bit(META_free, &mp->flag); - init_waitqueue_head(&mp->wait); -} - static inline struct metapage *alloc_metapage(gfp_t gfp_mask) { - return mempool_alloc(metapage_mempool, gfp_mask); + struct metapage *mp = mempool_alloc(metapage_mempool, gfp_mask); + + if (mp) { + mp->lid = 0; + mp->lsn = 0; + mp->data = NULL; + mp->clsn = 0; + mp->log = NULL; + init_waitqueue_head(&mp->wait); + } + return mp; } static inline void free_metapage(struct metapage *mp) { - mp->flag = 0; - set_bit(META_free, &mp->flag); - mempool_free(mp, metapage_mempool); } @@ -216,7 +209,7 @@ int __init metapage_init(void) * Allocate the metapage structures */ metapage_cache = kmem_cache_create("jfs_mp", sizeof(struct metapage), - 0, 0, init_once); + 0, 0, NULL); if (metapage_cache == NULL) return -ENOMEM; diff --git a/fs/jfs/jfs_metapage.h b/fs/jfs/jfs_metapage.h index a78beda85f68..337e9e51ac06 100644 --- a/fs/jfs/jfs_metapage.h +++ b/fs/jfs/jfs_metapage.h @@ -48,7 +48,6 @@ struct metapage { /* metapage flag */ #define META_locked 0 -#define META_free 1 #define META_dirty 2 #define META_sync 3 #define META_discard 4 diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 5d30c56ae075..4cd9798f4948 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -102,7 +102,7 @@ void jfs_error(struct super_block *sb, const char *fmt, ...) vaf.fmt = fmt; vaf.va = &args; - pr_err("ERROR: (device %s): %pf: %pV\n", + pr_err("ERROR: (device %s): %ps: %pV\n", sb->s_id, __builtin_return_address(0), &vaf); va_end(args); diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index 665ef5a05183..a563ddbc19e6 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -31,7 +31,7 @@ static struct hlist_head nlm_files[FILE_NRHASH]; static DEFINE_MUTEX(nlm_file_mutex); -#ifdef NFSD_DEBUG +#ifdef CONFIG_SUNRPC_DEBUG static inline void nlm_debug_print_fh(char *msg, struct nfs_fh *f) { u32 *fhp = (u32*)f->data; diff --git a/fs/locks.c b/fs/locks.c index 528fedfda15e..653faabb07f4 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -203,11 +203,11 @@ static struct kmem_cache *flctx_cache __read_mostly; static struct kmem_cache *filelock_cache __read_mostly; static struct file_lock_context * -locks_get_lock_context(struct inode *inode) +locks_get_lock_context(struct inode *inode, int type) { struct file_lock_context *new; - if (likely(inode->i_flctx)) + if (likely(inode->i_flctx) || type == F_UNLCK) goto out; new = kmem_cache_alloc(flctx_cache, GFP_KERNEL); @@ -223,14 +223,7 @@ locks_get_lock_context(struct inode *inode) * Assign the pointer if it's not already assigned. If it is, then * free the context we just allocated. */ - spin_lock(&inode->i_lock); - if (likely(!inode->i_flctx)) { - inode->i_flctx = new; - new = NULL; - } - spin_unlock(&inode->i_lock); - - if (new) + if (cmpxchg(&inode->i_flctx, NULL, new)) kmem_cache_free(flctx_cache, new); out: return inode->i_flctx; @@ -276,8 +269,10 @@ void locks_release_private(struct file_lock *fl) } if (fl->fl_lmops) { - if (fl->fl_lmops->lm_put_owner) - fl->fl_lmops->lm_put_owner(fl); + if (fl->fl_lmops->lm_put_owner) { + fl->fl_lmops->lm_put_owner(fl->fl_owner); + fl->fl_owner = NULL; + } fl->fl_lmops = NULL; } } @@ -333,7 +328,7 @@ void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) if (fl->fl_lmops) { if (fl->fl_lmops->lm_get_owner) - fl->fl_lmops->lm_get_owner(new, fl); + fl->fl_lmops->lm_get_owner(fl->fl_owner); } } EXPORT_SYMBOL(locks_copy_conflock); @@ -592,11 +587,15 @@ posix_owner_key(struct file_lock *fl) static void locks_insert_global_blocked(struct file_lock *waiter) { + lockdep_assert_held(&blocked_lock_lock); + hash_add(blocked_hash, &waiter->fl_link, posix_owner_key(waiter)); } static void locks_delete_global_blocked(struct file_lock *waiter) { + lockdep_assert_held(&blocked_lock_lock); + hash_del(&waiter->fl_link); } @@ -730,7 +729,7 @@ static int posix_locks_conflict(struct file_lock *caller_fl, struct file_lock *s /* POSIX locks owned by the same process do not conflict with * each other. */ - if (!IS_POSIX(sys_fl) || posix_same_owner(caller_fl, sys_fl)) + if (posix_same_owner(caller_fl, sys_fl)) return (0); /* Check whether they overlap */ @@ -748,7 +747,7 @@ static int flock_locks_conflict(struct file_lock *caller_fl, struct file_lock *s /* FLOCK locks referring to the same filp do not conflict with * each other. */ - if (!IS_FLOCK(sys_fl) || (caller_fl->fl_file == sys_fl->fl_file)) + if (caller_fl->fl_file == sys_fl->fl_file) return (0); if ((caller_fl->fl_type & LOCK_MAND) || (sys_fl->fl_type & LOCK_MAND)) return 0; @@ -838,6 +837,8 @@ static int posix_locks_deadlock(struct file_lock *caller_fl, { int i = 0; + lockdep_assert_held(&blocked_lock_lock); + /* * This deadlock detector can't reasonably detect deadlocks with * FL_OFDLCK locks, since they aren't owned by a process, per-se. @@ -871,9 +872,12 @@ static int flock_lock_file(struct file *filp, struct file_lock *request) bool found = false; LIST_HEAD(dispose); - ctx = locks_get_lock_context(inode); - if (!ctx) - return -ENOMEM; + ctx = locks_get_lock_context(inode, request->fl_type); + if (!ctx) { + if (request->fl_type != F_UNLCK) + return -ENOMEM; + return (request->fl_flags & FL_EXISTS) ? -ENOENT : 0; + } if (!(request->fl_flags & FL_ACCESS) && (request->fl_type != F_UNLCK)) { new_fl = locks_alloc_lock(); @@ -939,9 +943,9 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str bool added = false; LIST_HEAD(dispose); - ctx = locks_get_lock_context(inode); + ctx = locks_get_lock_context(inode, request->fl_type); if (!ctx) - return -ENOMEM; + return (request->fl_type == F_UNLCK) ? 0 : -ENOMEM; /* * We may need two file_lock structures for this operation, @@ -964,8 +968,6 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str */ if (request->fl_type != F_UNLCK) { list_for_each_entry(fl, &ctx->flc_posix, fl_list) { - if (!IS_POSIX(fl)) - continue; if (!posix_locks_conflict(request, fl)) continue; if (conflock) @@ -1388,9 +1390,8 @@ any_leases_conflict(struct inode *inode, struct file_lock *breaker) int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { int error = 0; - struct file_lock *new_fl; struct file_lock_context *ctx = inode->i_flctx; - struct file_lock *fl; + struct file_lock *new_fl, *fl, *tmp; unsigned long break_time; int want_write = (mode & O_ACCMODE) != O_RDONLY; LIST_HEAD(dispose); @@ -1420,7 +1421,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) break_time++; /* so that 0 means no break time */ } - list_for_each_entry(fl, &ctx->flc_lease, fl_list) { + list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) { if (!leases_conflict(fl, new_fl)) continue; if (want_write) { @@ -1606,7 +1607,8 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr lease = *flp; trace_generic_add_lease(inode, lease); - ctx = locks_get_lock_context(inode); + /* Note that arg is never F_UNLCK here */ + ctx = locks_get_lock_context(inode, arg); if (!ctx) return -ENOMEM; @@ -2556,15 +2558,10 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, : (fl->fl_type == F_WRLCK) ? "WRITE" : "READ "); } if (inode) { -#ifdef WE_CAN_BREAK_LSLK_NOW - seq_printf(f, "%d %s:%ld ", fl_pid, - inode->i_sb->s_id, inode->i_ino); -#else - /* userspace relies on this representation of dev_t ;-( */ + /* userspace relies on this representation of dev_t */ seq_printf(f, "%d %02x:%02x:%ld ", fl_pid, MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino); -#endif } else { seq_printf(f, "%d <none>:0 ", fl_pid); } @@ -2593,6 +2590,44 @@ static int locks_show(struct seq_file *f, void *v) return 0; } +static void __show_fd_locks(struct seq_file *f, + struct list_head *head, int *id, + struct file *filp, struct files_struct *files) +{ + struct file_lock *fl; + + list_for_each_entry(fl, head, fl_list) { + + if (filp != fl->fl_file) + continue; + if (fl->fl_owner != files && + fl->fl_owner != filp) + continue; + + (*id)++; + seq_puts(f, "lock:\t"); + lock_get_status(f, fl, *id, ""); + } +} + +void show_fd_locks(struct seq_file *f, + struct file *filp, struct files_struct *files) +{ + struct inode *inode = file_inode(filp); + struct file_lock_context *ctx; + int id = 0; + + ctx = inode->i_flctx; + if (!ctx) + return; + + spin_lock(&ctx->flc_lock); + __show_fd_locks(f, &ctx->flc_flock, &id, filp, files); + __show_fd_locks(f, &ctx->flc_posix, &id, filp, files); + __show_fd_locks(f, &ctx->flc_lease, &id, filp, files); + spin_unlock(&ctx->flc_lock); +} + static void *locks_start(struct seq_file *f, loff_t *pos) __acquires(&blocked_lock_lock) { diff --git a/fs/logfs/file.c b/fs/logfs/file.c index 8538752df2f6..b2c13f739ffa 100644 --- a/fs/logfs/file.c +++ b/fs/logfs/file.c @@ -271,8 +271,6 @@ const struct file_operations logfs_reg_fops = { .llseek = generic_file_llseek, .mmap = generic_file_readonly_mmap, .open = generic_file_open, - .read = new_sync_read, - .write = new_sync_write, }; const struct address_space_operations logfs_reg_aops = { diff --git a/fs/minix/file.c b/fs/minix/file.c index a967de085ac0..6d63e27ec961 100644 --- a/fs/minix/file.c +++ b/fs/minix/file.c @@ -14,9 +14,7 @@ */ const struct file_operations minix_file_operations = { .llseek = generic_file_llseek, - .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = new_sync_write, .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .fsync = generic_file_fsync, diff --git a/fs/namei.c b/fs/namei.c index c83145af4bfc..ffab2e06e147 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -119,15 +119,14 @@ * PATH_MAX includes the nul terminator --RR. */ -#define EMBEDDED_NAME_MAX (PATH_MAX - sizeof(struct filename)) +#define EMBEDDED_NAME_MAX (PATH_MAX - offsetof(struct filename, iname)) struct filename * getname_flags(const char __user *filename, int flags, int *empty) { - struct filename *result, *err; - int len; - long max; + struct filename *result; char *kname; + int len; result = audit_reusename(filename); if (result) @@ -136,22 +135,18 @@ getname_flags(const char __user *filename, int flags, int *empty) result = __getname(); if (unlikely(!result)) return ERR_PTR(-ENOMEM); - result->refcnt = 1; /* * First, try to embed the struct filename inside the names_cache * allocation */ - kname = (char *)result + sizeof(*result); + kname = (char *)result->iname; result->name = kname; - result->separate = false; - max = EMBEDDED_NAME_MAX; -recopy: - len = strncpy_from_user(kname, filename, max); + len = strncpy_from_user(kname, filename, EMBEDDED_NAME_MAX); if (unlikely(len < 0)) { - err = ERR_PTR(len); - goto error; + __putname(result); + return ERR_PTR(len); } /* @@ -160,43 +155,49 @@ recopy: * names_cache allocation for the pathname, and re-do the copy from * userland. */ - if (len == EMBEDDED_NAME_MAX && max == EMBEDDED_NAME_MAX) { + if (unlikely(len == EMBEDDED_NAME_MAX)) { + const size_t size = offsetof(struct filename, iname[1]); kname = (char *)result; - result = kzalloc(sizeof(*result), GFP_KERNEL); - if (!result) { - err = ERR_PTR(-ENOMEM); - result = (struct filename *)kname; - goto error; + /* + * size is chosen that way we to guarantee that + * result->iname[0] is within the same object and that + * kname can't be equal to result->iname, no matter what. + */ + result = kzalloc(size, GFP_KERNEL); + if (unlikely(!result)) { + __putname(kname); + return ERR_PTR(-ENOMEM); } result->name = kname; - result->separate = true; - result->refcnt = 1; - max = PATH_MAX; - goto recopy; + len = strncpy_from_user(kname, filename, PATH_MAX); + if (unlikely(len < 0)) { + __putname(kname); + kfree(result); + return ERR_PTR(len); + } + if (unlikely(len == PATH_MAX)) { + __putname(kname); + kfree(result); + return ERR_PTR(-ENAMETOOLONG); + } } + result->refcnt = 1; /* The empty path is special. */ if (unlikely(!len)) { if (empty) *empty = 1; - err = ERR_PTR(-ENOENT); - if (!(flags & LOOKUP_EMPTY)) - goto error; + if (!(flags & LOOKUP_EMPTY)) { + putname(result); + return ERR_PTR(-ENOENT); + } } - err = ERR_PTR(-ENAMETOOLONG); - if (unlikely(len >= PATH_MAX)) - goto error; - result->uptr = filename; result->aname = NULL; audit_getname(result); return result; - -error: - putname(result); - return err; } struct filename * @@ -216,8 +217,7 @@ getname_kernel(const char * filename) return ERR_PTR(-ENOMEM); if (len <= EMBEDDED_NAME_MAX) { - result->name = (char *)(result) + sizeof(*result); - result->separate = false; + result->name = (char *)result->iname; } else if (len <= PATH_MAX) { struct filename *tmp; @@ -227,7 +227,6 @@ getname_kernel(const char * filename) return ERR_PTR(-ENOMEM); } tmp->name = (char *)result; - tmp->separate = true; result = tmp; } else { __putname(result); @@ -249,7 +248,7 @@ void putname(struct filename *name) if (--name->refcnt > 0) return; - if (name->separate) { + if (name->name != name->iname) { __putname(name->name); kfree(name); } else @@ -1586,7 +1585,7 @@ static inline int walk_component(struct nameidata *nd, struct path *path, inode = path->dentry->d_inode; } err = -ENOENT; - if (!inode || d_is_negative(path->dentry)) + if (d_is_negative(path->dentry)) goto out_path_put; if (should_follow_link(path->dentry, follow)) { @@ -1851,10 +1850,11 @@ static int link_path_walk(const char *name, struct nameidata *nd) return err; } -static int path_init(int dfd, const char *name, unsigned int flags, +static int path_init(int dfd, const struct filename *name, unsigned int flags, struct nameidata *nd) { int retval = 0; + const char *s = name->name; nd->last_type = LAST_ROOT; /* if there are only slashes... */ nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT; @@ -1863,7 +1863,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, if (flags & LOOKUP_ROOT) { struct dentry *root = nd->root.dentry; struct inode *inode = root->d_inode; - if (*name) { + if (*s) { if (!d_can_lookup(root)) return -ENOTDIR; retval = inode_permission(inode, MAY_EXEC); @@ -1885,7 +1885,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, nd->root.mnt = NULL; nd->m_seq = read_seqbegin(&mount_lock); - if (*name=='/') { + if (*s == '/') { if (flags & LOOKUP_RCU) { rcu_read_lock(); nd->seq = set_root_rcu(nd); @@ -1919,7 +1919,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, dentry = f.file->f_path.dentry; - if (*name) { + if (*s) { if (!d_can_lookup(dentry)) { fdput(f); return -ENOTDIR; @@ -1949,7 +1949,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, return -ECHILD; done: current->total_link_count = 0; - return link_path_walk(name, nd); + return link_path_walk(s, nd); } static void path_cleanup(struct nameidata *nd) @@ -1972,7 +1972,7 @@ static inline int lookup_last(struct nameidata *nd, struct path *path) } /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */ -static int path_lookupat(int dfd, const char *name, +static int path_lookupat(int dfd, const struct filename *name, unsigned int flags, struct nameidata *nd) { struct path path; @@ -2027,31 +2027,17 @@ static int path_lookupat(int dfd, const char *name, static int filename_lookup(int dfd, struct filename *name, unsigned int flags, struct nameidata *nd) { - int retval = path_lookupat(dfd, name->name, flags | LOOKUP_RCU, nd); + int retval = path_lookupat(dfd, name, flags | LOOKUP_RCU, nd); if (unlikely(retval == -ECHILD)) - retval = path_lookupat(dfd, name->name, flags, nd); + retval = path_lookupat(dfd, name, flags, nd); if (unlikely(retval == -ESTALE)) - retval = path_lookupat(dfd, name->name, - flags | LOOKUP_REVAL, nd); + retval = path_lookupat(dfd, name, flags | LOOKUP_REVAL, nd); if (likely(!retval)) audit_inode(name, nd->path.dentry, flags & LOOKUP_PARENT); return retval; } -static int do_path_lookup(int dfd, const char *name, - unsigned int flags, struct nameidata *nd) -{ - struct filename *filename = getname_kernel(name); - int retval = PTR_ERR(filename); - - if (!IS_ERR(filename)) { - retval = filename_lookup(dfd, filename, flags, nd); - putname(filename); - } - return retval; -} - /* does lookup, returns the object with parent locked */ struct dentry *kern_path_locked(const char *name, struct path *path) { @@ -2089,9 +2075,15 @@ out: int kern_path(const char *name, unsigned int flags, struct path *path) { struct nameidata nd; - int res = do_path_lookup(AT_FDCWD, name, flags, &nd); - if (!res) - *path = nd.path; + struct filename *filename = getname_kernel(name); + int res = PTR_ERR(filename); + + if (!IS_ERR(filename)) { + res = filename_lookup(AT_FDCWD, filename, flags, &nd); + putname(filename); + if (!res) + *path = nd.path; + } return res; } EXPORT_SYMBOL(kern_path); @@ -2108,15 +2100,22 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, const char *name, unsigned int flags, struct path *path) { - struct nameidata nd; - int err; - nd.root.dentry = dentry; - nd.root.mnt = mnt; + struct filename *filename = getname_kernel(name); + int err = PTR_ERR(filename); + BUG_ON(flags & LOOKUP_PARENT); - /* the first argument of do_path_lookup() is ignored with LOOKUP_ROOT */ - err = do_path_lookup(AT_FDCWD, name, flags | LOOKUP_ROOT, &nd); - if (!err) - *path = nd.path; + + /* the first argument of filename_lookup() is ignored with LOOKUP_ROOT */ + if (!IS_ERR(filename)) { + struct nameidata nd; + nd.root.dentry = dentry; + nd.root.mnt = mnt; + err = filename_lookup(AT_FDCWD, filename, + flags | LOOKUP_ROOT, &nd); + if (!err) + *path = nd.path; + putname(filename); + } return err; } EXPORT_SYMBOL(vfs_path_lookup); @@ -2138,9 +2137,7 @@ static struct dentry *lookup_hash(struct nameidata *nd) * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should - * not be called by generic code. Also note that by using this function the - * nameidata argument is passed to the filesystem methods and a filesystem - * using this helper needs to be prepared for that. + * not be called by generic code. */ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) { @@ -2313,7 +2310,7 @@ mountpoint_last(struct nameidata *nd, struct path *path) mutex_unlock(&dir->d_inode->i_mutex); done: - if (!dentry->d_inode || d_is_negative(dentry)) { + if (d_is_negative(dentry)) { error = -ENOENT; dput(dentry); goto out; @@ -2341,7 +2338,8 @@ out: * Returns 0 and "path" will be valid on success; Returns error otherwise. */ static int -path_mountpoint(int dfd, const char *name, struct path *path, unsigned int flags) +path_mountpoint(int dfd, const struct filename *name, struct path *path, + unsigned int flags) { struct nameidata nd; int err; @@ -2370,20 +2368,20 @@ out: } static int -filename_mountpoint(int dfd, struct filename *s, struct path *path, +filename_mountpoint(int dfd, struct filename *name, struct path *path, unsigned int flags) { int error; - if (IS_ERR(s)) - return PTR_ERR(s); - error = path_mountpoint(dfd, s->name, path, flags | LOOKUP_RCU); + if (IS_ERR(name)) + return PTR_ERR(name); + error = path_mountpoint(dfd, name, path, flags | LOOKUP_RCU); if (unlikely(error == -ECHILD)) - error = path_mountpoint(dfd, s->name, path, flags); + error = path_mountpoint(dfd, name, path, flags); if (unlikely(error == -ESTALE)) - error = path_mountpoint(dfd, s->name, path, flags | LOOKUP_REVAL); + error = path_mountpoint(dfd, name, path, flags | LOOKUP_REVAL); if (likely(!error)) - audit_inode(s, path->dentry, 0); - putname(s); + audit_inode(name, path->dentry, 0); + putname(name); return error; } @@ -3040,7 +3038,7 @@ retry_lookup: finish_lookup: /* we _can_ be in RCU mode here */ error = -ENOENT; - if (!inode || d_is_negative(path->dentry)) { + if (d_is_negative(path->dentry)) { path_to_nameidata(path, nd); goto out; } @@ -3079,7 +3077,7 @@ finish_open: error = -ENOTDIR; if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry)) goto out; - if (!S_ISREG(nd->inode->i_mode)) + if (!d_is_reg(nd->path.dentry)) will_truncate = false; if (will_truncate) { @@ -3156,7 +3154,7 @@ static int do_tmpfile(int dfd, struct filename *pathname, static const struct qstr name = QSTR_INIT("/", 1); struct dentry *dentry, *child; struct inode *dir; - int error = path_lookupat(dfd, pathname->name, + int error = path_lookupat(dfd, pathname, flags | LOOKUP_DIRECTORY, nd); if (unlikely(error)) return error; @@ -3229,7 +3227,7 @@ static struct file *path_openat(int dfd, struct filename *pathname, goto out; } - error = path_init(dfd, pathname->name, flags, nd); + error = path_init(dfd, pathname, flags, nd); if (unlikely(error)) goto out; diff --git a/fs/namespace.c b/fs/namespace.c index 82ef1405260e..1f4f9dac6e5a 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -632,14 +632,17 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) */ struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry) { - struct mount *p, *res; - res = p = __lookup_mnt(mnt, dentry); + struct mount *p, *res = NULL; + p = __lookup_mnt(mnt, dentry); if (!p) goto out; + if (!(p->mnt.mnt_flags & MNT_UMOUNT)) + res = p; hlist_for_each_entry_continue(p, mnt_hash) { if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry) break; - res = p; + if (!(p->mnt.mnt_flags & MNT_UMOUNT)) + res = p; } out: return res; @@ -795,10 +798,8 @@ static void __touch_mnt_namespace(struct mnt_namespace *ns) /* * vfsmount lock must be held for write */ -static void detach_mnt(struct mount *mnt, struct path *old_path) +static void unhash_mnt(struct mount *mnt) { - old_path->dentry = mnt->mnt_mountpoint; - old_path->mnt = &mnt->mnt_parent->mnt; mnt->mnt_parent = mnt; mnt->mnt_mountpoint = mnt->mnt.mnt_root; list_del_init(&mnt->mnt_child); @@ -811,6 +812,26 @@ static void detach_mnt(struct mount *mnt, struct path *old_path) /* * vfsmount lock must be held for write */ +static void detach_mnt(struct mount *mnt, struct path *old_path) +{ + old_path->dentry = mnt->mnt_mountpoint; + old_path->mnt = &mnt->mnt_parent->mnt; + unhash_mnt(mnt); +} + +/* + * vfsmount lock must be held for write + */ +static void umount_mnt(struct mount *mnt) +{ + /* old mountpoint will be dropped when we can do that */ + mnt->mnt_ex_mountpoint = mnt->mnt_mountpoint; + unhash_mnt(mnt); +} + +/* + * vfsmount lock must be held for write + */ void mnt_set_mountpoint(struct mount *mnt, struct mountpoint *mp, struct mount *child_mnt) @@ -1078,6 +1099,13 @@ static void mntput_no_expire(struct mount *mnt) rcu_read_unlock(); list_del(&mnt->mnt_instance); + + if (unlikely(!list_empty(&mnt->mnt_mounts))) { + struct mount *p, *tmp; + list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts, mnt_child) { + umount_mnt(p); + } + } unlock_mount_hash(); if (likely(!(mnt->mnt.mnt_flags & MNT_INTERNAL))) { @@ -1298,17 +1326,15 @@ static HLIST_HEAD(unmounted); /* protected by namespace_sem */ static void namespace_unlock(void) { - struct hlist_head head = unmounted; + struct hlist_head head; - if (likely(hlist_empty(&head))) { - up_write(&namespace_sem); - return; - } + hlist_move_list(&unmounted, &head); - head.first->pprev = &head.first; - INIT_HLIST_HEAD(&unmounted); up_write(&namespace_sem); + if (likely(hlist_empty(&head))) + return; + synchronize_rcu(); group_pin_kill(&head); @@ -1319,49 +1345,63 @@ static inline void namespace_lock(void) down_write(&namespace_sem); } +enum umount_tree_flags { + UMOUNT_SYNC = 1, + UMOUNT_PROPAGATE = 2, + UMOUNT_CONNECTED = 4, +}; /* * mount_lock must be held * namespace_sem must be held for write - * how = 0 => just this tree, don't propagate - * how = 1 => propagate; we know that nobody else has reference to any victims - * how = 2 => lazy umount */ -void umount_tree(struct mount *mnt, int how) +static void umount_tree(struct mount *mnt, enum umount_tree_flags how) { - HLIST_HEAD(tmp_list); + LIST_HEAD(tmp_list); struct mount *p; + if (how & UMOUNT_PROPAGATE) + propagate_mount_unlock(mnt); + + /* Gather the mounts to umount */ for (p = mnt; p; p = next_mnt(p, mnt)) { - hlist_del_init_rcu(&p->mnt_hash); - hlist_add_head(&p->mnt_hash, &tmp_list); + p->mnt.mnt_flags |= MNT_UMOUNT; + list_move(&p->mnt_list, &tmp_list); } - hlist_for_each_entry(p, &tmp_list, mnt_hash) + /* Hide the mounts from mnt_mounts */ + list_for_each_entry(p, &tmp_list, mnt_list) { list_del_init(&p->mnt_child); + } - if (how) + /* Add propogated mounts to the tmp_list */ + if (how & UMOUNT_PROPAGATE) propagate_umount(&tmp_list); - while (!hlist_empty(&tmp_list)) { - p = hlist_entry(tmp_list.first, struct mount, mnt_hash); - hlist_del_init_rcu(&p->mnt_hash); + while (!list_empty(&tmp_list)) { + bool disconnect; + p = list_first_entry(&tmp_list, struct mount, mnt_list); list_del_init(&p->mnt_expire); list_del_init(&p->mnt_list); __touch_mnt_namespace(p->mnt_ns); p->mnt_ns = NULL; - if (how < 2) + if (how & UMOUNT_SYNC) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; - pin_insert_group(&p->mnt_umount, &p->mnt_parent->mnt, &unmounted); + disconnect = !(((how & UMOUNT_CONNECTED) && + mnt_has_parent(p) && + (p->mnt_parent->mnt.mnt_flags & MNT_UMOUNT)) || + IS_MNT_LOCKED_AND_LAZY(p)); + + pin_insert_group(&p->mnt_umount, &p->mnt_parent->mnt, + disconnect ? &unmounted : NULL); if (mnt_has_parent(p)) { - hlist_del_init(&p->mnt_mp_list); - put_mountpoint(p->mnt_mp); mnt_add_count(p->mnt_parent, -1); - /* old mountpoint will be dropped when we can do that */ - p->mnt_ex_mountpoint = p->mnt_mountpoint; - p->mnt_mountpoint = p->mnt.mnt_root; - p->mnt_parent = p; - p->mnt_mp = NULL; + if (!disconnect) { + /* Don't forget about p */ + list_add_tail(&p->mnt_child, &p->mnt_parent->mnt_mounts); + } else { + umount_mnt(p); + } } change_mnt_propagation(p, MS_PRIVATE); } @@ -1447,14 +1487,14 @@ static int do_umount(struct mount *mnt, int flags) if (flags & MNT_DETACH) { if (!list_empty(&mnt->mnt_list)) - umount_tree(mnt, 2); + umount_tree(mnt, UMOUNT_PROPAGATE); retval = 0; } else { shrink_submounts(mnt); retval = -EBUSY; if (!propagate_mount_busy(mnt, 2)) { if (!list_empty(&mnt->mnt_list)) - umount_tree(mnt, 1); + umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); retval = 0; } } @@ -1480,13 +1520,20 @@ void __detach_mounts(struct dentry *dentry) namespace_lock(); mp = lookup_mountpoint(dentry); - if (!mp) + if (IS_ERR_OR_NULL(mp)) goto out_unlock; lock_mount_hash(); while (!hlist_empty(&mp->m_list)) { mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list); - umount_tree(mnt, 2); + if (mnt->mnt.mnt_flags & MNT_UMOUNT) { + struct mount *p, *tmp; + list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts, mnt_child) { + hlist_add_head(&p->mnt_umount.s_list, &unmounted); + umount_mnt(p); + } + } + else umount_tree(mnt, UMOUNT_CONNECTED); } unlock_mount_hash(); put_mountpoint(mp); @@ -1648,7 +1695,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, out: if (res) { lock_mount_hash(); - umount_tree(res, 0); + umount_tree(res, UMOUNT_SYNC); unlock_mount_hash(); } return q; @@ -1660,8 +1707,11 @@ struct vfsmount *collect_mounts(struct path *path) { struct mount *tree; namespace_lock(); - tree = copy_tree(real_mount(path->mnt), path->dentry, - CL_COPY_ALL | CL_PRIVATE); + if (!check_mnt(real_mount(path->mnt))) + tree = ERR_PTR(-EINVAL); + else + tree = copy_tree(real_mount(path->mnt), path->dentry, + CL_COPY_ALL | CL_PRIVATE); namespace_unlock(); if (IS_ERR(tree)) return ERR_CAST(tree); @@ -1672,7 +1722,7 @@ void drop_collected_mounts(struct vfsmount *mnt) { namespace_lock(); lock_mount_hash(); - umount_tree(real_mount(mnt), 0); + umount_tree(real_mount(mnt), UMOUNT_SYNC); unlock_mount_hash(); namespace_unlock(); } @@ -1855,7 +1905,7 @@ static int attach_recursive_mnt(struct mount *source_mnt, out_cleanup_ids: while (!hlist_empty(&tree_list)) { child = hlist_entry(tree_list.first, struct mount, mnt_hash); - umount_tree(child, 0); + umount_tree(child, UMOUNT_SYNC); } unlock_mount_hash(); cleanup_group_ids(source_mnt, NULL); @@ -2035,7 +2085,7 @@ static int do_loopback(struct path *path, const char *old_name, err = graft_tree(mnt, parent, mp); if (err) { lock_mount_hash(); - umount_tree(mnt, 0); + umount_tree(mnt, UMOUNT_SYNC); unlock_mount_hash(); } out2: @@ -2406,7 +2456,7 @@ void mark_mounts_for_expiry(struct list_head *mounts) while (!list_empty(&graveyard)) { mnt = list_first_entry(&graveyard, struct mount, mnt_expire); touch_mnt_namespace(mnt->mnt_ns); - umount_tree(mnt, 1); + umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); } unlock_mount_hash(); namespace_unlock(); @@ -2477,7 +2527,7 @@ static void shrink_submounts(struct mount *mnt) m = list_first_entry(&graveyard, struct mount, mnt_expire); touch_mnt_namespace(m->mnt_ns); - umount_tree(m, 1); + umount_tree(m, UMOUNT_PROPAGATE|UMOUNT_SYNC); } } } diff --git a/fs/ncpfs/file.c b/fs/ncpfs/file.c index 1dd7007f974d..011324ce9df2 100644 --- a/fs/ncpfs/file.c +++ b/fs/ncpfs/file.c @@ -98,30 +98,24 @@ out: } static ssize_t -ncp_file_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) +ncp_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { + struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); size_t already_read = 0; - off_t pos; + off_t pos = iocb->ki_pos; size_t bufsize; int error; - void* freepage; + void *freepage; size_t freelen; ncp_dbg(1, "enter %pD2\n", file); - pos = *ppos; - - if ((ssize_t) count < 0) { - return -EINVAL; - } - if (!count) + if (!iov_iter_count(to)) return 0; if (pos > inode->i_sb->s_maxbytes) return 0; - if (pos + count > inode->i_sb->s_maxbytes) { - count = inode->i_sb->s_maxbytes - pos; - } + iov_iter_truncate(to, inode->i_sb->s_maxbytes - pos); error = ncp_make_open(inode, O_RDONLY); if (error) { @@ -138,31 +132,29 @@ ncp_file_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) goto outrel; error = 0; /* First read in as much as possible for each bufsize. */ - while (already_read < count) { + while (iov_iter_count(to)) { int read_this_time; - size_t to_read = min_t(unsigned int, + size_t to_read = min_t(size_t, bufsize - (pos % bufsize), - count - already_read); + iov_iter_count(to)); error = ncp_read_bounce(NCP_SERVER(inode), NCP_FINFO(inode)->file_handle, - pos, to_read, buf, &read_this_time, + pos, to_read, to, &read_this_time, freepage, freelen); if (error) { error = -EIO; /* NW errno -> Linux errno */ break; } pos += read_this_time; - buf += read_this_time; already_read += read_this_time; - if (read_this_time != to_read) { + if (read_this_time != to_read) break; - } } vfree(freepage); - *ppos = pos; + iocb->ki_pos = pos; file_accessed(file); @@ -173,42 +165,21 @@ outrel: } static ssize_t -ncp_file_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) +ncp_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { + struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); size_t already_written = 0; - off_t pos; size_t bufsize; int errno; - void* bouncebuffer; + void *bouncebuffer; + off_t pos; ncp_dbg(1, "enter %pD2\n", file); - if ((ssize_t) count < 0) - return -EINVAL; - pos = *ppos; - if (file->f_flags & O_APPEND) { - pos = i_size_read(inode); - } + errno = generic_write_checks(iocb, from); + if (errno <= 0) + return errno; - if (pos + count > MAX_NON_LFS && !(file->f_flags&O_LARGEFILE)) { - if (pos >= MAX_NON_LFS) { - return -EFBIG; - } - if (count > MAX_NON_LFS - (u32)pos) { - count = MAX_NON_LFS - (u32)pos; - } - } - if (pos >= inode->i_sb->s_maxbytes) { - if (count || pos > inode->i_sb->s_maxbytes) { - return -EFBIG; - } - } - if (pos + count > inode->i_sb->s_maxbytes) { - count = inode->i_sb->s_maxbytes - pos; - } - - if (!count) - return 0; errno = ncp_make_open(inode, O_WRONLY); if (errno) { ncp_dbg(1, "open failed, error=%d\n", errno); @@ -216,8 +187,6 @@ ncp_file_write(struct file *file, const char __user *buf, size_t count, loff_t * } bufsize = NCP_SERVER(inode)->buffer_size; - already_written = 0; - errno = file_update_time(file); if (errno) goto outrel; @@ -227,13 +196,14 @@ ncp_file_write(struct file *file, const char __user *buf, size_t count, loff_t * errno = -EIO; /* -ENOMEM */ goto outrel; } - while (already_written < count) { + pos = iocb->ki_pos; + while (iov_iter_count(from)) { int written_this_time; - size_t to_write = min_t(unsigned int, + size_t to_write = min_t(size_t, bufsize - (pos % bufsize), - count - already_written); + iov_iter_count(from)); - if (copy_from_user(bouncebuffer, buf, to_write)) { + if (copy_from_iter(bouncebuffer, to_write, from) != to_write) { errno = -EFAULT; break; } @@ -244,16 +214,14 @@ ncp_file_write(struct file *file, const char __user *buf, size_t count, loff_t * break; } pos += written_this_time; - buf += written_this_time; already_written += written_this_time; - if (written_this_time != to_write) { + if (written_this_time != to_write) break; - } } vfree(bouncebuffer); - *ppos = pos; + iocb->ki_pos = pos; if (pos > i_size_read(inode)) { mutex_lock(&inode->i_mutex); @@ -277,8 +245,8 @@ static int ncp_release(struct inode *inode, struct file *file) { const struct file_operations ncp_file_operations = { .llseek = generic_file_llseek, - .read = ncp_file_read, - .write = ncp_file_write, + .read_iter = ncp_file_read_iter, + .write_iter = ncp_file_write_iter, .unlocked_ioctl = ncp_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ncp_compat_ioctl, diff --git a/fs/ncpfs/ncplib_kernel.c b/fs/ncpfs/ncplib_kernel.c index 482387532f54..2b502a0d7941 100644 --- a/fs/ncpfs/ncplib_kernel.c +++ b/fs/ncpfs/ncplib_kernel.c @@ -1001,8 +1001,8 @@ out: */ int ncp_read_bounce(struct ncp_server *server, const char *file_id, - __u32 offset, __u16 to_read, char __user *target, int *bytes_read, - void* bounce, __u32 bufsize) + __u32 offset, __u16 to_read, struct iov_iter *to, + int *bytes_read, void *bounce, __u32 bufsize) { int result; @@ -1025,7 +1025,7 @@ ncp_read_bounce(struct ncp_server *server, const char *file_id, (offset & 1); *bytes_read = len; result = 0; - if (copy_to_user(target, source, len)) + if (copy_to_iter(source, len, to) != len) result = -EFAULT; } } diff --git a/fs/ncpfs/ncplib_kernel.h b/fs/ncpfs/ncplib_kernel.h index 250e443a07f3..5233fbc1747a 100644 --- a/fs/ncpfs/ncplib_kernel.h +++ b/fs/ncpfs/ncplib_kernel.h @@ -53,7 +53,7 @@ static inline int ncp_read_bounce_size(__u32 size) { return sizeof(struct ncp_reply_header) + 2 + 2 + size + 8; }; int ncp_read_bounce(struct ncp_server *, const char *, __u32, __u16, - char __user *, int *, void* bounce, __u32 bouncelen); + struct iov_iter *, int *, void *bounce, __u32 bouncelen); int ncp_read_kernel(struct ncp_server *, const char *, __u32, __u16, char *, int *); int ncp_write_kernel(struct ncp_server *, const char *, __u32, __u16, diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index c7abc10279af..f31fd0dd92c6 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -1,6 +1,6 @@ config NFS_FS tristate "NFS client support" - depends on INET && FILE_LOCKING + depends on INET && FILE_LOCKING && MULTIUSER select LOCKD select SUNRPC select NFS_ACL_SUPPORT if NFS_V3_ACL diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index e907c8cf732e..682f65fe09b5 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -240,7 +240,6 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq, /** * nfs_direct_IO - NFS address space operation for direct I/O - * @rw: direction (read or write) * @iocb: target I/O control block * @iov: array of vectors that define I/O buffer * @pos: offset in file to begin the operation @@ -251,7 +250,7 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq, * shunt off direct read and write requests before the VFS gets them, * so this method is only ever called for swap. */ -ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos) +ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos) { struct inode *inode = iocb->ki_filp->f_mapping->host; @@ -265,11 +264,11 @@ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t return -EINVAL; #else - VM_BUG_ON(iocb->ki_nbytes != PAGE_SIZE); + VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE); - if (rw == READ) + if (iov_iter_rw(iter) == READ) return nfs_file_direct_read(iocb, iter, pos); - return nfs_file_direct_write(iocb, iter, pos); + return nfs_file_direct_write(iocb, iter); #endif /* CONFIG_NFS_SWAP */ } @@ -393,7 +392,7 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq, bool write) long res = (long) dreq->error; if (!res) res = (long) dreq->count; - aio_complete(dreq->iocb, res, 0); + dreq->iocb->ki_complete(dreq->iocb, res, 0); } complete_all(&dreq->completion); @@ -960,8 +959,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, * Note that O_APPEND is not supported for NFS direct writes, as there * is no atomic O_APPEND write facility in the NFS protocol. */ -ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter, - loff_t pos) +ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) { ssize_t result = -EINVAL; struct file *file = iocb->ki_filp; @@ -969,25 +967,16 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter, struct inode *inode = mapping->host; struct nfs_direct_req *dreq; struct nfs_lock_context *l_ctx; - loff_t end; - size_t count = iov_iter_count(iter); - end = (pos + count - 1) >> PAGE_CACHE_SHIFT; - - nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES, count); + loff_t pos, end; dfprintk(FILE, "NFS: direct write(%pD2, %zd@%Ld)\n", - file, count, (long long) pos); + file, iov_iter_count(iter), (long long) iocb->ki_pos); - result = generic_write_checks(file, &pos, &count, 0); - if (result) - goto out; + nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES, + iov_iter_count(iter)); - result = -EINVAL; - if ((ssize_t) count < 0) - goto out; - result = 0; - if (!count) - goto out; + pos = iocb->ki_pos; + end = (pos + iov_iter_count(iter) - 1) >> PAGE_CACHE_SHIFT; mutex_lock(&inode->i_mutex); @@ -1002,7 +991,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter, goto out_unlock; } - task_io_account_write(count); + task_io_account_write(iov_iter_count(iter)); result = -ENOMEM; dreq = nfs_direct_req_alloc(); @@ -1010,7 +999,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter, goto out_unlock; dreq->inode = inode; - dreq->bytes_left = count; + dreq->bytes_left = iov_iter_count(iter); dreq->io_start = pos; dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp)); l_ctx = nfs_get_lock_context(dreq->ctx); @@ -1050,7 +1039,6 @@ out_release: nfs_direct_req_release(dreq); out_unlock: mutex_unlock(&inode->i_mutex); -out: return result; } diff --git a/fs/nfs/file.c b/fs/nfs/file.c index e679d24c39d3..c40e4363e746 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -26,7 +26,6 @@ #include <linux/nfs_mount.h> #include <linux/mm.h> #include <linux/pagemap.h> -#include <linux/aio.h> #include <linux/gfp.h> #include <linux/swap.h> @@ -171,7 +170,7 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to) struct inode *inode = file_inode(iocb->ki_filp); ssize_t result; - if (iocb->ki_filp->f_flags & O_DIRECT) + if (iocb->ki_flags & IOCB_DIRECT) return nfs_file_direct_read(iocb, to, iocb->ki_pos); dprintk("NFS: read(%pD2, %zu@%lu)\n", @@ -675,17 +674,20 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) unsigned long written = 0; ssize_t result; size_t count = iov_iter_count(from); - loff_t pos = iocb->ki_pos; result = nfs_key_timeout_notify(file, inode); if (result) return result; - if (file->f_flags & O_DIRECT) - return nfs_file_direct_write(iocb, from, pos); + if (iocb->ki_flags & IOCB_DIRECT) { + result = generic_write_checks(iocb, from); + if (result <= 0) + return result; + return nfs_file_direct_write(iocb, from); + } dprintk("NFS: write(%pD2, %zu@%Ld)\n", - file, count, (long long) pos); + file, count, (long long) iocb->ki_pos); result = -EBUSY; if (IS_SWAPFILE(inode)) @@ -693,7 +695,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) /* * O_APPEND implies that we must revalidate the file length. */ - if (file->f_flags & O_APPEND) { + if (iocb->ki_flags & IOCB_APPEND) { result = nfs_revalidate_file_size(inode, file); if (result) goto out; @@ -927,8 +929,6 @@ EXPORT_SYMBOL_GPL(nfs_flock); const struct file_operations nfs_file_operations = { .llseek = nfs_file_llseek, - .read = new_sync_read, - .write = new_sync_write, .read_iter = nfs_file_read, .write_iter = nfs_file_write, .mmap = nfs_file_mmap, diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 8b46389c4c5b..0181cde1d102 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -170,8 +170,6 @@ const struct file_operations nfs4_file_operations = { #else .llseek = nfs_file_llseek, #endif - .read = new_sync_read, - .write = new_sync_write, .read_iter = nfs_file_read, .write_iter = nfs_file_write, .mmap = nfs_file_mmap, diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 568ecf0a880f..b8f5c63f77b2 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -117,15 +117,15 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, static void nfs_readpage_release(struct nfs_page *req) { - struct inode *d_inode = req->wb_context->dentry->d_inode; + struct inode *inode = req->wb_context->dentry->d_inode; - dprintk("NFS: read done (%s/%llu %d@%lld)\n", d_inode->i_sb->s_id, - (unsigned long long)NFS_FILEID(d_inode), req->wb_bytes, + dprintk("NFS: read done (%s/%llu %d@%lld)\n", inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(inode), req->wb_bytes, (long long)req_offset(req)); if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) { if (PageUptodate(req->wb_page)) - nfs_readpage_to_fscache(d_inode, req->wb_page, 0); + nfs_readpage_to_fscache(inode, req->wb_page, 0); unlock_page(req->wb_page); } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 849ed784d6ac..759931088094 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1876,11 +1876,6 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page) * request from the inode / page_private pointer and * release it */ nfs_inode_remove_request(req); - /* - * In case nfs_inode_remove_request has marked the - * page as being dirty - */ - cancel_dirty_page(page, PAGE_CACHE_SIZE); nfs_unlock_and_release_request(req); } diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index 683bf718aead..a0b77fc1bd39 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -6,6 +6,7 @@ config NFSD select SUNRPC select EXPORTFS select NFS_ACL_SUPPORT if NFSD_V2_ACL + depends on MULTIUSER help Choose Y here if you want to allow other computers to access files residing on this system using Sun's Network File System @@ -107,7 +108,7 @@ config NFSD_V4_SECURITY_LABEL config NFSD_FAULT_INJECTION bool "NFS server manual fault injection" - depends on NFSD_V4 && DEBUG_KERNEL + depends on NFSD_V4 && DEBUG_KERNEL && DEBUG_FS help This option enables support for manually injecting faults into the NFS server. This is intended to be used for diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index cdbc78c72542..03d647bf195d 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -137,7 +137,7 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, seg->offset = iomap.offset; seg->length = iomap.length; - dprintk("GET: %lld:%lld %d\n", bex->foff, bex->len, bex->es); + dprintk("GET: 0x%llx:0x%llx %d\n", bex->foff, bex->len, bex->es); return 0; out_error: diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c index 9da89fddab33..9aa2796da90d 100644 --- a/fs/nfsd/blocklayoutxdr.c +++ b/fs/nfsd/blocklayoutxdr.c @@ -122,19 +122,19 @@ nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp, p = xdr_decode_hyper(p, &bex.foff); if (bex.foff & (block_size - 1)) { - dprintk("%s: unaligned offset %lld\n", + dprintk("%s: unaligned offset 0x%llx\n", __func__, bex.foff); goto fail; } p = xdr_decode_hyper(p, &bex.len); if (bex.len & (block_size - 1)) { - dprintk("%s: unaligned length %lld\n", + dprintk("%s: unaligned length 0x%llx\n", __func__, bex.foff); goto fail; } p = xdr_decode_hyper(p, &bex.soff); if (bex.soff & (block_size - 1)) { - dprintk("%s: unaligned disk offset %lld\n", + dprintk("%s: unaligned disk offset 0x%llx\n", __func__, bex.soff); goto fail; } diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index c3e3b6e55ae2..900c3ae94adc 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -691,8 +691,7 @@ static int svc_export_match(struct cache_head *a, struct cache_head *b) struct svc_export *orig = container_of(a, struct svc_export, h); struct svc_export *new = container_of(b, struct svc_export, h); return orig->ex_client == new->ex_client && - orig->ex_path.dentry == new->ex_path.dentry && - orig->ex_path.mnt == new->ex_path.mnt; + path_equal(&orig->ex_path, &new->ex_path); } static void svc_export_init(struct cache_head *cnew, struct cache_head *citem) @@ -1159,6 +1158,7 @@ static struct flags { { NFSEXP_NOSUBTREECHECK, {"no_subtree_check", ""}}, { NFSEXP_NOAUTHNLM, {"insecure_locks", ""}}, { NFSEXP_V4ROOT, {"v4root", ""}}, + { NFSEXP_PNFS, {"pnfs", ""}}, { 0, {"", ""}} }; diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c index 59fd76651781..eaf4605a4b9e 100644 --- a/fs/nfsd/nfs4acl.c +++ b/fs/nfsd/nfs4acl.c @@ -499,43 +499,13 @@ static inline void add_to_mask(struct posix_acl_state *state, struct posix_ace_s state->mask.allow |= astate->allow; } -/* - * Certain bits (SYNCHRONIZE, DELETE, WRITE_OWNER, READ/WRITE_NAMED_ATTRS, - * READ_ATTRIBUTES, READ_ACL) are currently unenforceable and don't translate - * to traditional read/write/execute permissions. - * - * It's problematic to reject acls that use certain mode bits, because it - * places the burden on users to learn the rules about which bits one - * particular server sets, without giving the user a lot of help--we return an - * error that could mean any number of different things. To make matters - * worse, the problematic bits might be introduced by some application that's - * automatically mapping from some other acl model. - * - * So wherever possible we accept anything, possibly erring on the side of - * denying more permissions than necessary. - * - * However we do reject *explicit* DENY's of a few bits representing - * permissions we could never deny: - */ - -static inline int check_deny(u32 mask, int isowner) -{ - if (mask & (NFS4_ACE_READ_ATTRIBUTES | NFS4_ACE_READ_ACL)) - return -EINVAL; - if (!isowner) - return 0; - if (mask & (NFS4_ACE_WRITE_ATTRIBUTES | NFS4_ACE_WRITE_ACL)) - return -EINVAL; - return 0; -} - static struct posix_acl * posix_state_to_acl(struct posix_acl_state *state, unsigned int flags) { struct posix_acl_entry *pace; struct posix_acl *pacl; int nace; - int i, error = 0; + int i; /* * ACLs with no ACEs are treated differently in the inheritable @@ -560,17 +530,11 @@ posix_state_to_acl(struct posix_acl_state *state, unsigned int flags) pace = pacl->a_entries; pace->e_tag = ACL_USER_OBJ; - error = check_deny(state->owner.deny, 1); - if (error) - goto out_err; low_mode_from_nfs4(state->owner.allow, &pace->e_perm, flags); for (i=0; i < state->users->n; i++) { pace++; pace->e_tag = ACL_USER; - error = check_deny(state->users->aces[i].perms.deny, 0); - if (error) - goto out_err; low_mode_from_nfs4(state->users->aces[i].perms.allow, &pace->e_perm, flags); pace->e_uid = state->users->aces[i].uid; @@ -579,18 +543,12 @@ posix_state_to_acl(struct posix_acl_state *state, unsigned int flags) pace++; pace->e_tag = ACL_GROUP_OBJ; - error = check_deny(state->group.deny, 0); - if (error) - goto out_err; low_mode_from_nfs4(state->group.allow, &pace->e_perm, flags); add_to_mask(state, &state->group); for (i=0; i < state->groups->n; i++) { pace++; pace->e_tag = ACL_GROUP; - error = check_deny(state->groups->aces[i].perms.deny, 0); - if (error) - goto out_err; low_mode_from_nfs4(state->groups->aces[i].perms.allow, &pace->e_perm, flags); pace->e_gid = state->groups->aces[i].gid; @@ -605,15 +563,9 @@ posix_state_to_acl(struct posix_acl_state *state, unsigned int flags) pace++; pace->e_tag = ACL_OTHER; - error = check_deny(state->other.deny, 0); - if (error) - goto out_err; low_mode_from_nfs4(state->other.allow, &pace->e_perm, flags); return pacl; -out_err: - posix_acl_release(pacl); - return ERR_PTR(error); } static inline void allow_bits(struct posix_ace_state *astate, u32 mask) diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 1028a0629543..6904213a4363 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -118,7 +118,7 @@ void nfsd4_setup_layout_type(struct svc_export *exp) { struct super_block *sb = exp->ex_path.mnt->mnt_sb; - if (exp->ex_flags & NFSEXP_NOPNFS) + if (!(exp->ex_flags & NFSEXP_PNFS)) return; if (sb->s_export_op->get_uuid && @@ -440,15 +440,14 @@ nfsd4_return_file_layout(struct nfs4_layout *lp, struct nfsd4_layout_seg *seg, list_move_tail(&lp->lo_perstate, reaplist); return; } - end = seg->offset; + lo->offset = layout_end(seg); } else { /* retain the whole layout segment on a split. */ if (layout_end(seg) < end) { dprintk("%s: split not supported\n", __func__); return; } - - lo->offset = layout_end(seg); + end = seg->offset; } layout_update_len(lo, end); @@ -513,6 +512,9 @@ nfsd4_return_client_layouts(struct svc_rqst *rqstp, spin_lock(&clp->cl_lock); list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt) { + if (ls->ls_layout_type != lrp->lr_layout_type) + continue; + if (lrp->lr_return_type == RETURN_FSID && !fh_fsid_match(&ls->ls_stid.sc_file->fi_fhandle, &cstate->current_fh.fh_handle)) @@ -587,6 +589,8 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls) rpc_ntop((struct sockaddr *)&clp->cl_addr, addr_str, sizeof(addr_str)); + trace_layout_recall_fail(&ls->ls_stid.sc_stateid); + printk(KERN_WARNING "nfsd: client %s failed to respond to layout recall. " " Fencing..\n", addr_str); diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index d30bea8d0277..4a8314f08a0e 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -470,7 +470,7 @@ out: fh_put(resfh); kfree(resfh); } - nfsd4_cleanup_open_state(cstate, open, status); + nfsd4_cleanup_open_state(cstate, open); nfsd4_bump_seqid(cstate, status); return status; } @@ -1030,6 +1030,8 @@ nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, dprintk("NFSD: nfsd4_fallocate: couldn't process stateid!\n"); return status; } + if (!file) + return nfserr_bad_stateid; status = nfsd4_vfs_fallocate(rqstp, &cstate->current_fh, file, fallocate->falloc_offset, @@ -1069,6 +1071,8 @@ nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, dprintk("NFSD: nfsd4_seek: couldn't process stateid!\n"); return status; } + if (!file) + return nfserr_bad_stateid; switch (seek->seek_whence) { case NFS4_CONTENT_DATA: @@ -1237,8 +1241,8 @@ nfsd4_getdeviceinfo(struct svc_rqst *rqstp, nfserr = ops->proc_getdeviceinfo(exp->ex_path.mnt->mnt_sb, gdp); gdp->gd_notify_types &= ops->notify_types; - exp_put(exp); out: + exp_put(exp); return nfserr; } @@ -1815,7 +1819,7 @@ static inline u32 nfsd4_getattr_rsize(struct svc_rqst *rqstp, bmap0 &= ~FATTR4_WORD0_FILEHANDLE; } if (bmap2 & FATTR4_WORD2_SECURITY_LABEL) { - ret += NFSD4_MAX_SEC_LABEL_LEN + 12; + ret += NFS4_MAXLABELLEN + 12; bmap2 &= ~FATTR4_WORD2_SECURITY_LABEL; } /* @@ -2282,13 +2286,13 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_func = (nfsd4op_func)nfsd4_allocate, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_ALLOCATE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_write_rsize, + .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, }, [OP_DEALLOCATE] = { .op_func = (nfsd4op_func)nfsd4_deallocate, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_DEALLOCATE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_write_rsize, + .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, }, [OP_SEEK] = { .op_func = (nfsd4op_func)nfsd4_seek, diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index d2f2c37dc2db..d42786ee39af 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1139,7 +1139,7 @@ hash_sessionid(struct nfs4_sessionid *sessionid) return sid->sequence % SESSION_HASH_SIZE; } -#ifdef NFSD_DEBUG +#ifdef CONFIG_SUNRPC_DEBUG static inline void dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid) { @@ -3221,7 +3221,7 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open, } else nfs4_free_openowner(&oo->oo_owner); spin_unlock(&clp->cl_lock); - return oo; + return ret; } static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, struct nfsd4_open *open) { @@ -4049,7 +4049,6 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf status = nfserr_bad_stateid; if (nfsd4_is_deleg_cur(open)) goto out; - status = nfserr_jukebox; } /* @@ -4118,7 +4117,7 @@ out: } void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate, - struct nfsd4_open *open, __be32 status) + struct nfsd4_open *open) { if (open->op_openowner) { struct nfs4_stateowner *so = &open->op_openowner->oo_owner; @@ -4932,20 +4931,22 @@ nfs4_transform_lock_offset(struct file_lock *lock) lock->fl_end = OFFSET_MAX; } -static void nfsd4_fl_get_owner(struct file_lock *dst, struct file_lock *src) +static fl_owner_t +nfsd4_fl_get_owner(fl_owner_t owner) { - struct nfs4_lockowner *lo = (struct nfs4_lockowner *)src->fl_owner; - dst->fl_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(&lo->lo_owner)); + struct nfs4_lockowner *lo = (struct nfs4_lockowner *)owner; + + nfs4_get_stateowner(&lo->lo_owner); + return owner; } -static void nfsd4_fl_put_owner(struct file_lock *fl) +static void +nfsd4_fl_put_owner(fl_owner_t owner) { - struct nfs4_lockowner *lo = (struct nfs4_lockowner *)fl->fl_owner; + struct nfs4_lockowner *lo = (struct nfs4_lockowner *)owner; - if (lo) { + if (lo) nfs4_put_stateowner(&lo->lo_owner); - fl->fl_owner = NULL; - } } static const struct lock_manager_operations nfsd_posix_mng_ops = { @@ -5062,7 +5063,7 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, } else nfs4_free_lockowner(&lo->lo_owner); spin_unlock(&clp->cl_lock); - return lo; + return ret; } static void diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index df5e66caf100..a45032ce7b80 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -424,7 +424,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, len += 4; dummy32 = be32_to_cpup(p++); READ_BUF(dummy32); - if (dummy32 > NFSD4_MAX_SEC_LABEL_LEN) + if (dummy32 > NFS4_MAXLABELLEN) return nfserr_badlabel; len += (XDR_QUADLEN(dummy32) << 2); READMEM(buf, dummy32); @@ -1562,7 +1562,11 @@ nfsd4_decode_layoutget(struct nfsd4_compoundargs *argp, p = xdr_decode_hyper(p, &lgp->lg_seg.offset); p = xdr_decode_hyper(p, &lgp->lg_seg.length); p = xdr_decode_hyper(p, &lgp->lg_minlength); - nfsd4_decode_stateid(argp, &lgp->lg_sid); + + status = nfsd4_decode_stateid(argp, &lgp->lg_sid); + if (status) + return status; + READ_BUF(4); lgp->lg_maxcount = be32_to_cpup(p++); @@ -1580,7 +1584,11 @@ nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp, p = xdr_decode_hyper(p, &lcp->lc_seg.offset); p = xdr_decode_hyper(p, &lcp->lc_seg.length); lcp->lc_reclaim = be32_to_cpup(p++); - nfsd4_decode_stateid(argp, &lcp->lc_sid); + + status = nfsd4_decode_stateid(argp, &lcp->lc_sid); + if (status) + return status; + READ_BUF(4); lcp->lc_newoffset = be32_to_cpup(p++); if (lcp->lc_newoffset) { @@ -1628,7 +1636,11 @@ nfsd4_decode_layoutreturn(struct nfsd4_compoundargs *argp, READ_BUF(16); p = xdr_decode_hyper(p, &lrp->lr_seg.offset); p = xdr_decode_hyper(p, &lrp->lr_seg.length); - nfsd4_decode_stateid(argp, &lrp->lr_sid); + + status = nfsd4_decode_stateid(argp, &lrp->lr_sid); + if (status) + return status; + READ_BUF(4); lrp->lrf_body_len = be32_to_cpup(p++); if (lrp->lrf_body_len > 0) { @@ -2008,7 +2020,7 @@ static __be32 nfsd4_encode_path(struct xdr_stream *xdr, * dentries/path components in an array. */ for (;;) { - if (cur.dentry == root->dentry && cur.mnt == root->mnt) + if (path_equal(&cur, root)) break; if (cur.dentry == cur.mnt->mnt_root) { if (follow_up(&cur)) @@ -3410,6 +3422,7 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, unsigned long maxcount; struct xdr_stream *xdr = &resp->xdr; struct file *file = read->rd_filp; + struct svc_fh *fhp = read->rd_fhp; int starting_len = xdr->buf->len; struct raparms *ra; __be32 *p; @@ -3433,12 +3446,15 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, maxcount = min_t(unsigned long, maxcount, (xdr->buf->buflen - xdr->buf->len)); maxcount = min_t(unsigned long, maxcount, read->rd_length); - if (!read->rd_filp) { + if (read->rd_filp) + err = nfsd_permission(resp->rqstp, fhp->fh_export, + fhp->fh_dentry, + NFSD_MAY_READ|NFSD_MAY_OWNER_OVERRIDE); + else err = nfsd_get_tmp_read_open(resp->rqstp, read->rd_fhp, &file, &ra); - if (err) - goto err_truncate; - } + if (err) + goto err_truncate; if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) err = nfsd4_encode_splice_read(resp, read, file, maxcount); @@ -4123,7 +4139,7 @@ nfsd4_encode_layoutreturn(struct nfsd4_compoundres *resp, __be32 nfserr, return nfserr_resource; *p++ = cpu_to_be32(lrp->lrs_present); if (lrp->lrs_present) - nfsd4_encode_stateid(xdr, &lrp->lr_sid); + return nfsd4_encode_stateid(xdr, &lrp->lr_sid); return nfs_ok; } #endif /* CONFIG_NFSD_PNFS */ diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 83a9694ec485..46ec934f5dee 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -165,13 +165,17 @@ int nfsd_reply_cache_init(void) { unsigned int hashsize; unsigned int i; + int status = 0; max_drc_entries = nfsd_cache_size_limit(); atomic_set(&num_drc_entries, 0); hashsize = nfsd_hashsize(max_drc_entries); maskbits = ilog2(hashsize); - register_shrinker(&nfsd_reply_cache_shrinker); + status = register_shrinker(&nfsd_reply_cache_shrinker); + if (status) + return status; + drc_slab = kmem_cache_create("nfsd_drc", sizeof(struct svc_cacherep), 0, 0, NULL); if (!drc_slab) diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index aa47d75ddb26..9690cb4dd588 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1250,15 +1250,15 @@ static int __init init_nfsd(void) int retval; printk(KERN_INFO "Installing knfsd (copyright (C) 1996 okir@monad.swb.de).\n"); - retval = register_cld_notifier(); - if (retval) - return retval; retval = register_pernet_subsys(&nfsd_net_ops); if (retval < 0) - goto out_unregister_notifier; - retval = nfsd4_init_slabs(); + return retval; + retval = register_cld_notifier(); if (retval) goto out_unregister_pernet; + retval = nfsd4_init_slabs(); + if (retval) + goto out_unregister_notifier; retval = nfsd4_init_pnfs(); if (retval) goto out_free_slabs; @@ -1290,10 +1290,10 @@ out_exit_pnfs: nfsd4_exit_pnfs(); out_free_slabs: nfsd4_free_slabs(); -out_unregister_pernet: - unregister_pernet_subsys(&nfsd_net_ops); out_unregister_notifier: unregister_cld_notifier(); +out_unregister_pernet: + unregister_pernet_subsys(&nfsd_net_ops); return retval; } @@ -1308,8 +1308,8 @@ static void __exit exit_nfsd(void) nfsd4_exit_pnfs(); nfsd_fault_inject_cleanup(); unregister_filesystem(&nfsd_fs_type); - unregister_pernet_subsys(&nfsd_net_ops); unregister_cld_notifier(); + unregister_pernet_subsys(&nfsd_net_ops); } MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>"); diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 565c4da1a9eb..cf980523898b 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -24,7 +24,7 @@ #include "export.h" #undef ifdebug -#ifdef NFSD_DEBUG +#ifdef CONFIG_SUNRPC_DEBUG # define ifdebug(flag) if (nfsd_debug & NFSDDBG_##flag) #else # define ifdebug(flag) if (0) diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 0bda93e58e1b..556ce2e47555 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -40,7 +40,6 @@ #include "state.h" #include "nfsd.h" -#define NFSD4_MAX_SEC_LABEL_LEN 2048 #define NFSD4_MAX_TAGLEN 128 #define XDR_LEN(n) (((n) + 3) & ~3) @@ -683,7 +682,7 @@ extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open); extern void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate); extern void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate, - struct nfsd4_open *open, __be32 status); + struct nfsd4_open *open); extern __be32 nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *, struct nfsd4_open_confirm *oc); extern __be32 nfsd4_close(struct svc_rqst *rqstp, diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index 741fd02e0444..8df0f3b7839b 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -405,13 +405,14 @@ nilfs_palloc_rest_groups_in_desc_block(const struct inode *inode, static int nilfs_palloc_count_desc_blocks(struct inode *inode, unsigned long *desc_blocks) { - unsigned long blknum; + __u64 blknum; int ret; ret = nilfs_bmap_last_key(NILFS_I(inode)->i_bmap, &blknum); if (likely(!ret)) *desc_blocks = DIV_ROUND_UP( - blknum, NILFS_MDT(inode)->mi_blocks_per_desc_block); + (unsigned long)blknum, + NILFS_MDT(inode)->mi_blocks_per_desc_block); return ret; } diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c index aadbd0b5e3e8..27f75bcbeb30 100644 --- a/fs/nilfs2/bmap.c +++ b/fs/nilfs2/bmap.c @@ -152,9 +152,7 @@ static int nilfs_bmap_do_insert(struct nilfs_bmap *bmap, __u64 key, __u64 ptr) * * %-EEXIST - A record associated with @key already exist. */ -int nilfs_bmap_insert(struct nilfs_bmap *bmap, - unsigned long key, - unsigned long rec) +int nilfs_bmap_insert(struct nilfs_bmap *bmap, __u64 key, unsigned long rec) { int ret; @@ -191,19 +189,47 @@ static int nilfs_bmap_do_delete(struct nilfs_bmap *bmap, __u64 key) return bmap->b_ops->bop_delete(bmap, key); } -int nilfs_bmap_last_key(struct nilfs_bmap *bmap, unsigned long *key) +/** + * nilfs_bmap_seek_key - seek a valid entry and return its key + * @bmap: bmap struct + * @start: start key number + * @keyp: place to store valid key + * + * Description: nilfs_bmap_seek_key() seeks a valid key on @bmap + * starting from @start, and stores it to @keyp if found. + * + * Return Value: On success, 0 is returned. On error, one of the following + * negative error codes is returned. + * + * %-EIO - I/O error. + * + * %-ENOMEM - Insufficient amount of memory available. + * + * %-ENOENT - No valid entry was found + */ +int nilfs_bmap_seek_key(struct nilfs_bmap *bmap, __u64 start, __u64 *keyp) { - __u64 lastkey; int ret; down_read(&bmap->b_sem); - ret = bmap->b_ops->bop_last_key(bmap, &lastkey); + ret = bmap->b_ops->bop_seek_key(bmap, start, keyp); + up_read(&bmap->b_sem); + + if (ret < 0) + ret = nilfs_bmap_convert_error(bmap, __func__, ret); + return ret; +} + +int nilfs_bmap_last_key(struct nilfs_bmap *bmap, __u64 *keyp) +{ + int ret; + + down_read(&bmap->b_sem); + ret = bmap->b_ops->bop_last_key(bmap, keyp); up_read(&bmap->b_sem); if (ret < 0) ret = nilfs_bmap_convert_error(bmap, __func__, ret); - else - *key = lastkey; return ret; } @@ -224,7 +250,7 @@ int nilfs_bmap_last_key(struct nilfs_bmap *bmap, unsigned long *key) * * %-ENOENT - A record associated with @key does not exist. */ -int nilfs_bmap_delete(struct nilfs_bmap *bmap, unsigned long key) +int nilfs_bmap_delete(struct nilfs_bmap *bmap, __u64 key) { int ret; @@ -235,7 +261,7 @@ int nilfs_bmap_delete(struct nilfs_bmap *bmap, unsigned long key) return nilfs_bmap_convert_error(bmap, __func__, ret); } -static int nilfs_bmap_do_truncate(struct nilfs_bmap *bmap, unsigned long key) +static int nilfs_bmap_do_truncate(struct nilfs_bmap *bmap, __u64 key) { __u64 lastkey; int ret; @@ -276,7 +302,7 @@ static int nilfs_bmap_do_truncate(struct nilfs_bmap *bmap, unsigned long key) * * %-ENOMEM - Insufficient amount of memory available. */ -int nilfs_bmap_truncate(struct nilfs_bmap *bmap, unsigned long key) +int nilfs_bmap_truncate(struct nilfs_bmap *bmap, __u64 key) { int ret; diff --git a/fs/nilfs2/bmap.h b/fs/nilfs2/bmap.h index b89e68076adc..bfa817ce40b3 100644 --- a/fs/nilfs2/bmap.h +++ b/fs/nilfs2/bmap.h @@ -76,8 +76,10 @@ struct nilfs_bmap_operations { union nilfs_binfo *); int (*bop_mark)(struct nilfs_bmap *, __u64, int); - /* The following functions are internal use only. */ + int (*bop_seek_key)(const struct nilfs_bmap *, __u64, __u64 *); int (*bop_last_key)(const struct nilfs_bmap *, __u64 *); + + /* The following functions are internal use only. */ int (*bop_check_insert)(const struct nilfs_bmap *, __u64); int (*bop_check_delete)(struct nilfs_bmap *, __u64); int (*bop_gather_data)(struct nilfs_bmap *, __u64 *, __u64 *, int); @@ -153,10 +155,11 @@ int nilfs_bmap_test_and_clear_dirty(struct nilfs_bmap *); int nilfs_bmap_read(struct nilfs_bmap *, struct nilfs_inode *); void nilfs_bmap_write(struct nilfs_bmap *, struct nilfs_inode *); int nilfs_bmap_lookup_contig(struct nilfs_bmap *, __u64, __u64 *, unsigned); -int nilfs_bmap_insert(struct nilfs_bmap *, unsigned long, unsigned long); -int nilfs_bmap_delete(struct nilfs_bmap *, unsigned long); -int nilfs_bmap_last_key(struct nilfs_bmap *, unsigned long *); -int nilfs_bmap_truncate(struct nilfs_bmap *, unsigned long); +int nilfs_bmap_insert(struct nilfs_bmap *bmap, __u64 key, unsigned long rec); +int nilfs_bmap_delete(struct nilfs_bmap *bmap, __u64 key); +int nilfs_bmap_seek_key(struct nilfs_bmap *bmap, __u64 start, __u64 *keyp); +int nilfs_bmap_last_key(struct nilfs_bmap *bmap, __u64 *keyp); +int nilfs_bmap_truncate(struct nilfs_bmap *bmap, __u64 key); void nilfs_bmap_clear(struct nilfs_bmap *); int nilfs_bmap_propagate(struct nilfs_bmap *, struct buffer_head *); void nilfs_bmap_lookup_dirty_buffers(struct nilfs_bmap *, struct list_head *); diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index ecdbae19a766..059f37137f9a 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -633,6 +633,44 @@ static int nilfs_btree_do_lookup_last(const struct nilfs_bmap *btree, return 0; } +/** + * nilfs_btree_get_next_key - get next valid key from btree path array + * @btree: bmap struct of btree + * @path: array of nilfs_btree_path struct + * @minlevel: start level + * @nextkey: place to store the next valid key + * + * Return Value: If a next key was found, 0 is returned. Otherwise, + * -ENOENT is returned. + */ +static int nilfs_btree_get_next_key(const struct nilfs_bmap *btree, + const struct nilfs_btree_path *path, + int minlevel, __u64 *nextkey) +{ + struct nilfs_btree_node *node; + int maxlevel = nilfs_btree_height(btree) - 1; + int index, next_adj, level; + + /* Next index is already set to bp_index for leaf nodes. */ + next_adj = 0; + for (level = minlevel; level <= maxlevel; level++) { + if (level == maxlevel) + node = nilfs_btree_get_root(btree); + else + node = nilfs_btree_get_nonroot_node(path, level); + + index = path[level].bp_index + next_adj; + if (index < nilfs_btree_node_get_nchildren(node)) { + /* Next key is in this node */ + *nextkey = nilfs_btree_node_get_key(node, index); + return 0; + } + /* For non-leaf nodes, next index is stored at bp_index + 1. */ + next_adj = 1; + } + return -ENOENT; +} + static int nilfs_btree_lookup(const struct nilfs_bmap *btree, __u64 key, int level, __u64 *ptrp) { @@ -1563,6 +1601,27 @@ out: return ret; } +static int nilfs_btree_seek_key(const struct nilfs_bmap *btree, __u64 start, + __u64 *keyp) +{ + struct nilfs_btree_path *path; + const int minlevel = NILFS_BTREE_LEVEL_NODE_MIN; + int ret; + + path = nilfs_btree_alloc_path(); + if (!path) + return -ENOMEM; + + ret = nilfs_btree_do_lookup(btree, path, start, NULL, minlevel, 0); + if (!ret) + *keyp = start; + else if (ret == -ENOENT) + ret = nilfs_btree_get_next_key(btree, path, minlevel, keyp); + + nilfs_btree_free_path(path); + return ret; +} + static int nilfs_btree_last_key(const struct nilfs_bmap *btree, __u64 *keyp) { struct nilfs_btree_path *path; @@ -2298,7 +2357,9 @@ static const struct nilfs_bmap_operations nilfs_btree_ops = { .bop_assign = nilfs_btree_assign, .bop_mark = nilfs_btree_mark, + .bop_seek_key = nilfs_btree_seek_key, .bop_last_key = nilfs_btree_last_key, + .bop_check_insert = NULL, .bop_check_delete = nilfs_btree_check_delete, .bop_gather_data = nilfs_btree_gather_data, @@ -2318,7 +2379,9 @@ static const struct nilfs_bmap_operations nilfs_btree_ops_gc = { .bop_assign = nilfs_btree_assign_gc, .bop_mark = NULL, + .bop_seek_key = NULL, .bop_last_key = NULL, + .bop_check_insert = NULL, .bop_check_delete = NULL, .bop_gather_data = NULL, diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c index 0d58075f34e2..b6596cab9e99 100644 --- a/fs/nilfs2/cpfile.c +++ b/fs/nilfs2/cpfile.c @@ -53,6 +53,13 @@ nilfs_cpfile_get_offset(const struct inode *cpfile, __u64 cno) return do_div(tcno, nilfs_cpfile_checkpoints_per_block(cpfile)); } +static __u64 nilfs_cpfile_first_checkpoint_in_block(const struct inode *cpfile, + unsigned long blkoff) +{ + return (__u64)nilfs_cpfile_checkpoints_per_block(cpfile) * blkoff + + 1 - NILFS_MDT(cpfile)->mi_first_entry_offset; +} + static unsigned long nilfs_cpfile_checkpoints_in_block(const struct inode *cpfile, __u64 curr, @@ -146,6 +153,44 @@ static inline int nilfs_cpfile_get_checkpoint_block(struct inode *cpfile, create, nilfs_cpfile_block_init, bhp); } +/** + * nilfs_cpfile_find_checkpoint_block - find and get a buffer on cpfile + * @cpfile: inode of cpfile + * @start_cno: start checkpoint number (inclusive) + * @end_cno: end checkpoint number (inclusive) + * @cnop: place to store the next checkpoint number + * @bhp: place to store a pointer to buffer_head struct + * + * Return Value: On success, it returns 0. On error, the following negative + * error code is returned. + * + * %-ENOMEM - Insufficient memory available. + * + * %-EIO - I/O error + * + * %-ENOENT - no block exists in the range. + */ +static int nilfs_cpfile_find_checkpoint_block(struct inode *cpfile, + __u64 start_cno, __u64 end_cno, + __u64 *cnop, + struct buffer_head **bhp) +{ + unsigned long start, end, blkoff; + int ret; + + if (unlikely(start_cno > end_cno)) + return -ENOENT; + + start = nilfs_cpfile_get_blkoff(cpfile, start_cno); + end = nilfs_cpfile_get_blkoff(cpfile, end_cno); + + ret = nilfs_mdt_find_block(cpfile, start, end, &blkoff, bhp); + if (!ret) + *cnop = (blkoff == start) ? start_cno : + nilfs_cpfile_first_checkpoint_in_block(cpfile, blkoff); + return ret; +} + static inline int nilfs_cpfile_delete_checkpoint_block(struct inode *cpfile, __u64 cno) { @@ -403,14 +448,15 @@ static ssize_t nilfs_cpfile_do_get_cpinfo(struct inode *cpfile, __u64 *cnop, return -ENOENT; /* checkpoint number 0 is invalid */ down_read(&NILFS_MDT(cpfile)->mi_sem); - for (n = 0; cno < cur_cno && n < nci; cno += ncps) { - ncps = nilfs_cpfile_checkpoints_in_block(cpfile, cno, cur_cno); - ret = nilfs_cpfile_get_checkpoint_block(cpfile, cno, 0, &bh); + for (n = 0; n < nci; cno += ncps) { + ret = nilfs_cpfile_find_checkpoint_block( + cpfile, cno, cur_cno - 1, &cno, &bh); if (ret < 0) { - if (ret != -ENOENT) - goto out; - continue; /* skip hole */ + if (likely(ret == -ENOENT)) + break; + goto out; } + ncps = nilfs_cpfile_checkpoints_in_block(cpfile, cno, cur_cno); kaddr = kmap_atomic(bh->b_page); cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, bh, kaddr); diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c index 82f4865e86dd..ebf89fd8ac1a 100644 --- a/fs/nilfs2/direct.c +++ b/fs/nilfs2/direct.c @@ -173,6 +173,21 @@ static int nilfs_direct_delete(struct nilfs_bmap *bmap, __u64 key) return ret; } +static int nilfs_direct_seek_key(const struct nilfs_bmap *direct, __u64 start, + __u64 *keyp) +{ + __u64 key; + + for (key = start; key <= NILFS_DIRECT_KEY_MAX; key++) { + if (nilfs_direct_get_ptr(direct, key) != + NILFS_BMAP_INVALID_PTR) { + *keyp = key; + return 0; + } + } + return -ENOENT; +} + static int nilfs_direct_last_key(const struct nilfs_bmap *direct, __u64 *keyp) { __u64 key, lastkey; @@ -355,7 +370,9 @@ static const struct nilfs_bmap_operations nilfs_direct_ops = { .bop_assign = nilfs_direct_assign, .bop_mark = NULL, + .bop_seek_key = nilfs_direct_seek_key, .bop_last_key = nilfs_direct_last_key, + .bop_check_insert = nilfs_direct_check_insert, .bop_check_delete = NULL, .bop_gather_data = nilfs_direct_gather_data, diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index a8c728acb7a8..54575e3cc1a2 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -143,8 +143,6 @@ static int nilfs_file_mmap(struct file *file, struct vm_area_struct *vma) */ const struct file_operations nilfs_file_operations = { .llseek = generic_file_llseek, - .read = new_sync_read, - .write = new_sync_write, .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, .unlocked_ioctl = nilfs_ioctl, diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 8b5969538f39..be936df4ba73 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -26,7 +26,7 @@ #include <linux/mpage.h> #include <linux/pagemap.h> #include <linux/writeback.h> -#include <linux/aio.h> +#include <linux/uio.h> #include "nilfs.h" #include "btnode.h" #include "segment.h" @@ -106,7 +106,7 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff, err = nilfs_transaction_begin(inode->i_sb, &ti, 1); if (unlikely(err)) goto out; - err = nilfs_bmap_insert(ii->i_bmap, (unsigned long)blkoff, + err = nilfs_bmap_insert(ii->i_bmap, blkoff, (unsigned long)bh_result); if (unlikely(err != 0)) { if (err == -EEXIST) { @@ -305,8 +305,7 @@ static int nilfs_write_end(struct file *file, struct address_space *mapping, } static ssize_t -nilfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +nilfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -314,18 +313,17 @@ nilfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, size_t count = iov_iter_count(iter); ssize_t size; - if (rw == WRITE) + if (iov_iter_rw(iter) == WRITE) return 0; /* Needs synchronization with the cleaner */ - size = blockdev_direct_IO(rw, iocb, inode, iter, offset, - nilfs_get_block); + size = blockdev_direct_IO(iocb, inode, iter, offset, nilfs_get_block); /* * In case of error extending write may have instantiated a few * blocks outside i_size. Trim these off again. */ - if (unlikely((rw & WRITE) && size < 0)) { + if (unlikely(iov_iter_rw(iter) == WRITE && size < 0)) { loff_t isize = i_size_read(inode); loff_t end = offset + count; @@ -443,21 +441,20 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) void nilfs_set_inode_flags(struct inode *inode) { unsigned int flags = NILFS_I(inode)->i_flags; + unsigned int new_fl = 0; - inode->i_flags &= ~(S_SYNC | S_APPEND | S_IMMUTABLE | S_NOATIME | - S_DIRSYNC); if (flags & FS_SYNC_FL) - inode->i_flags |= S_SYNC; + new_fl |= S_SYNC; if (flags & FS_APPEND_FL) - inode->i_flags |= S_APPEND; + new_fl |= S_APPEND; if (flags & FS_IMMUTABLE_FL) - inode->i_flags |= S_IMMUTABLE; + new_fl |= S_IMMUTABLE; if (flags & FS_NOATIME_FL) - inode->i_flags |= S_NOATIME; + new_fl |= S_NOATIME; if (flags & FS_DIRSYNC_FL) - inode->i_flags |= S_DIRSYNC; - mapping_set_gfp_mask(inode->i_mapping, - mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS); + new_fl |= S_DIRSYNC; + inode_set_flags(inode, new_fl, S_SYNC | S_APPEND | S_IMMUTABLE | + S_NOATIME | S_DIRSYNC); } int nilfs_read_inode_common(struct inode *inode, @@ -542,6 +539,8 @@ static int __nilfs_read_inode(struct super_block *sb, brelse(bh); up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem); nilfs_set_inode_flags(inode); + mapping_set_gfp_mask(inode->i_mapping, + mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS); return 0; failed_unmap: @@ -714,7 +713,7 @@ void nilfs_update_inode(struct inode *inode, struct buffer_head *ibh, int flags) static void nilfs_truncate_bmap(struct nilfs_inode_info *ii, unsigned long from) { - unsigned long b; + __u64 b; int ret; if (!test_bit(NILFS_I_BMAP, &ii->i_state)) @@ -729,7 +728,7 @@ repeat: if (b < from) return; - b -= min_t(unsigned long, NILFS_MAX_TRUNCATE_BLOCKS, b - from); + b -= min_t(__u64, NILFS_MAX_TRUNCATE_BLOCKS, b - from); ret = nilfs_bmap_truncate(ii->i_bmap, b); nilfs_relax_pressure_in_lock(ii->vfs_inode.i_sb); if (!ret || (ret == -ENOMEM && diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index 892cf5ffdb8e..dee34d990281 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -261,6 +261,60 @@ int nilfs_mdt_get_block(struct inode *inode, unsigned long blkoff, int create, } /** + * nilfs_mdt_find_block - find and get a buffer on meta data file. + * @inode: inode of the meta data file + * @start: start block offset (inclusive) + * @end: end block offset (inclusive) + * @blkoff: block offset + * @out_bh: place to store a pointer to buffer_head struct + * + * nilfs_mdt_find_block() looks up an existing block in range of + * [@start, @end] and stores pointer to a buffer head of the block to + * @out_bh, and block offset to @blkoff, respectively. @out_bh and + * @blkoff are substituted only when zero is returned. + * + * Return Value: On success, it returns 0. On error, the following negative + * error code is returned. + * + * %-ENOMEM - Insufficient memory available. + * + * %-EIO - I/O error + * + * %-ENOENT - no block was found in the range + */ +int nilfs_mdt_find_block(struct inode *inode, unsigned long start, + unsigned long end, unsigned long *blkoff, + struct buffer_head **out_bh) +{ + __u64 next; + int ret; + + if (unlikely(start > end)) + return -ENOENT; + + ret = nilfs_mdt_read_block(inode, start, true, out_bh); + if (!ret) { + *blkoff = start; + goto out; + } + if (unlikely(ret != -ENOENT || start == ULONG_MAX)) + goto out; + + ret = nilfs_bmap_seek_key(NILFS_I(inode)->i_bmap, start + 1, &next); + if (!ret) { + if (next <= end) { + ret = nilfs_mdt_read_block(inode, next, true, out_bh); + if (!ret) + *blkoff = next; + } else { + ret = -ENOENT; + } + } +out: + return ret; +} + +/** * nilfs_mdt_delete_block - make a hole on the meta data file. * @inode: inode of the meta data file * @block: block offset diff --git a/fs/nilfs2/mdt.h b/fs/nilfs2/mdt.h index ab172e8549c5..fe529a87a208 100644 --- a/fs/nilfs2/mdt.h +++ b/fs/nilfs2/mdt.h @@ -78,6 +78,9 @@ int nilfs_mdt_get_block(struct inode *, unsigned long, int, void (*init_block)(struct inode *, struct buffer_head *, void *), struct buffer_head **); +int nilfs_mdt_find_block(struct inode *inode, unsigned long start, + unsigned long end, unsigned long *blkoff, + struct buffer_head **out_bh); int nilfs_mdt_delete_block(struct inode *, unsigned long); int nilfs_mdt_forget_block(struct inode *, unsigned long); int nilfs_mdt_mark_block_dirty(struct inode *, unsigned long); @@ -111,7 +114,10 @@ static inline __u64 nilfs_mdt_cno(struct inode *inode) return ((struct the_nilfs *)inode->i_sb->s_fs_info)->ns_cno; } -#define nilfs_mdt_bgl_lock(inode, bg) \ - (&NILFS_MDT(inode)->mi_bgl->locks[(bg) & (NR_BG_LOCKS-1)].lock) +static inline spinlock_t * +nilfs_mdt_bgl_lock(struct inode *inode, unsigned int block_group) +{ + return bgl_lock_ptr(NILFS_MDT(inode)->mi_bgl, block_group); +} #endif /* _NILFS_MDT_H */ diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 700ecbcca55d..45d650addd56 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -89,18 +89,16 @@ struct buffer_head *nilfs_grab_buffer(struct inode *inode, void nilfs_forget_buffer(struct buffer_head *bh) { struct page *page = bh->b_page; + const unsigned long clear_bits = + (1 << BH_Uptodate | 1 << BH_Dirty | 1 << BH_Mapped | + 1 << BH_Async_Write | 1 << BH_NILFS_Volatile | + 1 << BH_NILFS_Checked | 1 << BH_NILFS_Redirected); lock_buffer(bh); - clear_buffer_nilfs_volatile(bh); - clear_buffer_nilfs_checked(bh); - clear_buffer_nilfs_redirected(bh); - clear_buffer_async_write(bh); - clear_buffer_dirty(bh); + set_mask_bits(&bh->b_state, clear_bits, 0); if (nilfs_page_buffers_clean(page)) __nilfs_clear_page_dirty(page); - clear_buffer_uptodate(bh); - clear_buffer_mapped(bh); bh->b_blocknr = -1; ClearPageUptodate(page); ClearPageMappedToDisk(page); @@ -421,6 +419,10 @@ void nilfs_clear_dirty_page(struct page *page, bool silent) if (page_has_buffers(page)) { struct buffer_head *bh, *head; + const unsigned long clear_bits = + (1 << BH_Uptodate | 1 << BH_Dirty | 1 << BH_Mapped | + 1 << BH_Async_Write | 1 << BH_NILFS_Volatile | + 1 << BH_NILFS_Checked | 1 << BH_NILFS_Redirected); bh = head = page_buffers(page); do { @@ -430,13 +432,7 @@ void nilfs_clear_dirty_page(struct page *page, bool silent) "discard block %llu, size %zu", (u64)bh->b_blocknr, bh->b_size); } - clear_buffer_async_write(bh); - clear_buffer_dirty(bh); - clear_buffer_nilfs_volatile(bh); - clear_buffer_nilfs_checked(bh); - clear_buffer_nilfs_redirected(bh); - clear_buffer_uptodate(bh); - clear_buffer_mapped(bh); + set_mask_bits(&bh->b_state, clear_bits, 0); unlock_buffer(bh); } while (bh = bh->b_this_page, bh != head); } diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 0c3f303baf32..c6abbad9b8e3 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -24,6 +24,7 @@ #include <linux/pagemap.h> #include <linux/buffer_head.h> #include <linux/writeback.h> +#include <linux/bitops.h> #include <linux/bio.h> #include <linux/completion.h> #include <linux/blkdev.h> @@ -1588,7 +1589,6 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) list_for_each_entry(bh, &segbuf->sb_segsum_buffers, b_assoc_buffers) { - set_buffer_async_write(bh); if (bh->b_page != bd_page) { if (bd_page) { lock_page(bd_page); @@ -1688,7 +1688,6 @@ static void nilfs_abort_logs(struct list_head *logs, int err) list_for_each_entry(segbuf, logs, sb_list) { list_for_each_entry(bh, &segbuf->sb_segsum_buffers, b_assoc_buffers) { - clear_buffer_async_write(bh); if (bh->b_page != bd_page) { if (bd_page) end_page_writeback(bd_page); @@ -1768,7 +1767,6 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci) b_assoc_buffers) { set_buffer_uptodate(bh); clear_buffer_dirty(bh); - clear_buffer_async_write(bh); if (bh->b_page != bd_page) { if (bd_page) end_page_writeback(bd_page); @@ -1788,12 +1786,13 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci) */ list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) { - set_buffer_uptodate(bh); - clear_buffer_dirty(bh); - clear_buffer_async_write(bh); - clear_buffer_delay(bh); - clear_buffer_nilfs_volatile(bh); - clear_buffer_nilfs_redirected(bh); + const unsigned long set_bits = (1 << BH_Uptodate); + const unsigned long clear_bits = + (1 << BH_Dirty | 1 << BH_Async_Write | + 1 << BH_Delay | 1 << BH_NILFS_Volatile | + 1 << BH_NILFS_Redirected); + + set_mask_bits(&bh->b_state, clear_bits, set_bits); if (bh == segbuf->sb_super_root) { if (bh->b_page != bd_page) { end_page_writeback(bd_page); diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 5bc2a1cf73c3..c1725f20a9d1 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1020,7 +1020,7 @@ int nilfs_checkpoint_is_mounted(struct super_block *sb, __u64 cno) struct dentry *dentry; int ret; - if (cno < 0 || cno > nilfs->ns_cno) + if (cno > nilfs->ns_cno) return false; if (cno >= nilfs_last_cno(nilfs)) diff --git a/fs/ntfs/Makefile b/fs/ntfs/Makefile index 36ae529511c4..2ff263e6d363 100644 --- a/fs/ntfs/Makefile +++ b/fs/ntfs/Makefile @@ -8,7 +8,7 @@ ntfs-y := aops.o attrib.o collate.o compress.o debug.o dir.o file.o \ ntfs-$(CONFIG_NTFS_RW) += bitmap.o lcnalloc.o logfile.o quota.o usnjrnl.o -ccflags-y := -DNTFS_VERSION=\"2.1.31\" +ccflags-y := -DNTFS_VERSION=\"2.1.32\" ccflags-$(CONFIG_NTFS_DEBUG) += -DDEBUG ccflags-$(CONFIG_NTFS_RW) += -DNTFS_RW diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 1da9b2d184dc..7bb487e663b4 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -1,7 +1,7 @@ /* * file.c - NTFS kernel file operations. Part of the Linux-NTFS project. * - * Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc. + * Copyright (c) 2001-2015 Anton Altaparmakov and Tuxera Inc. * * This program/include file is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as published @@ -28,7 +28,6 @@ #include <linux/swap.h> #include <linux/uio.h> #include <linux/writeback.h> -#include <linux/aio.h> #include <asm/page.h> #include <asm/uaccess.h> @@ -329,62 +328,166 @@ err_out: return err; } -/** - * ntfs_fault_in_pages_readable - - * - * Fault a number of userspace pages into pagetables. - * - * Unlike include/linux/pagemap.h::fault_in_pages_readable(), this one copes - * with more than two userspace pages as well as handling the single page case - * elegantly. - * - * If you find this difficult to understand, then think of the while loop being - * the following code, except that we do without the integer variable ret: - * - * do { - * ret = __get_user(c, uaddr); - * uaddr += PAGE_SIZE; - * } while (!ret && uaddr < end); - * - * Note, the final __get_user() may well run out-of-bounds of the user buffer, - * but _not_ out-of-bounds of the page the user buffer belongs to, and since - * this is only a read and not a write, and since it is still in the same page, - * it should not matter and this makes the code much simpler. - */ -static inline void ntfs_fault_in_pages_readable(const char __user *uaddr, - int bytes) -{ - const char __user *end; - volatile char c; - - /* Set @end to the first byte outside the last page we care about. */ - end = (const char __user*)PAGE_ALIGN((unsigned long)uaddr + bytes); - - while (!__get_user(c, uaddr) && (uaddr += PAGE_SIZE, uaddr < end)) - ; -} - -/** - * ntfs_fault_in_pages_readable_iovec - - * - * Same as ntfs_fault_in_pages_readable() but operates on an array of iovecs. - */ -static inline void ntfs_fault_in_pages_readable_iovec(const struct iovec *iov, - size_t iov_ofs, int bytes) +static ssize_t ntfs_prepare_file_for_write(struct kiocb *iocb, + struct iov_iter *from) { - do { - const char __user *buf; - unsigned len; + loff_t pos; + s64 end, ll; + ssize_t err; + unsigned long flags; + struct file *file = iocb->ki_filp; + struct inode *vi = file_inode(file); + ntfs_inode *base_ni, *ni = NTFS_I(vi); + ntfs_volume *vol = ni->vol; - buf = iov->iov_base + iov_ofs; - len = iov->iov_len - iov_ofs; - if (len > bytes) - len = bytes; - ntfs_fault_in_pages_readable(buf, len); - bytes -= len; - iov++; - iov_ofs = 0; - } while (bytes); + ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, pos " + "0x%llx, count 0x%zx.", vi->i_ino, + (unsigned)le32_to_cpu(ni->type), + (unsigned long long)iocb->ki_pos, + iov_iter_count(from)); + err = generic_write_checks(iocb, from); + if (unlikely(err <= 0)) + goto out; + /* + * All checks have passed. Before we start doing any writing we want + * to abort any totally illegal writes. + */ + BUG_ON(NInoMstProtected(ni)); + BUG_ON(ni->type != AT_DATA); + /* If file is encrypted, deny access, just like NT4. */ + if (NInoEncrypted(ni)) { + /* Only $DATA attributes can be encrypted. */ + /* + * Reminder for later: Encrypted files are _always_ + * non-resident so that the content can always be encrypted. + */ + ntfs_debug("Denying write access to encrypted file."); + err = -EACCES; + goto out; + } + if (NInoCompressed(ni)) { + /* Only unnamed $DATA attribute can be compressed. */ + BUG_ON(ni->name_len); + /* + * Reminder for later: If resident, the data is not actually + * compressed. Only on the switch to non-resident does + * compression kick in. This is in contrast to encrypted files + * (see above). + */ + ntfs_error(vi->i_sb, "Writing to compressed files is not " + "implemented yet. Sorry."); + err = -EOPNOTSUPP; + goto out; + } + base_ni = ni; + if (NInoAttr(ni)) + base_ni = ni->ext.base_ntfs_ino; + err = file_remove_suid(file); + if (unlikely(err)) + goto out; + /* + * Our ->update_time method always succeeds thus file_update_time() + * cannot fail either so there is no need to check the return code. + */ + file_update_time(file); + pos = iocb->ki_pos; + /* The first byte after the last cluster being written to. */ + end = (pos + iov_iter_count(from) + vol->cluster_size_mask) & + ~(u64)vol->cluster_size_mask; + /* + * If the write goes beyond the allocated size, extend the allocation + * to cover the whole of the write, rounded up to the nearest cluster. + */ + read_lock_irqsave(&ni->size_lock, flags); + ll = ni->allocated_size; + read_unlock_irqrestore(&ni->size_lock, flags); + if (end > ll) { + /* + * Extend the allocation without changing the data size. + * + * Note we ensure the allocation is big enough to at least + * write some data but we do not require the allocation to be + * complete, i.e. it may be partial. + */ + ll = ntfs_attr_extend_allocation(ni, end, -1, pos); + if (likely(ll >= 0)) { + BUG_ON(pos >= ll); + /* If the extension was partial truncate the write. */ + if (end > ll) { + ntfs_debug("Truncating write to inode 0x%lx, " + "attribute type 0x%x, because " + "the allocation was only " + "partially extended.", + vi->i_ino, (unsigned) + le32_to_cpu(ni->type)); + iov_iter_truncate(from, ll - pos); + } + } else { + err = ll; + read_lock_irqsave(&ni->size_lock, flags); + ll = ni->allocated_size; + read_unlock_irqrestore(&ni->size_lock, flags); + /* Perform a partial write if possible or fail. */ + if (pos < ll) { + ntfs_debug("Truncating write to inode 0x%lx " + "attribute type 0x%x, because " + "extending the allocation " + "failed (error %d).", + vi->i_ino, (unsigned) + le32_to_cpu(ni->type), + (int)-err); + iov_iter_truncate(from, ll - pos); + } else { + if (err != -ENOSPC) + ntfs_error(vi->i_sb, "Cannot perform " + "write to inode " + "0x%lx, attribute " + "type 0x%x, because " + "extending the " + "allocation failed " + "(error %ld).", + vi->i_ino, (unsigned) + le32_to_cpu(ni->type), + (long)-err); + else + ntfs_debug("Cannot perform write to " + "inode 0x%lx, " + "attribute type 0x%x, " + "because there is not " + "space left.", + vi->i_ino, (unsigned) + le32_to_cpu(ni->type)); + goto out; + } + } + } + /* + * If the write starts beyond the initialized size, extend it up to the + * beginning of the write and initialize all non-sparse space between + * the old initialized size and the new one. This automatically also + * increments the vfs inode->i_size to keep it above or equal to the + * initialized_size. + */ + read_lock_irqsave(&ni->size_lock, flags); + ll = ni->initialized_size; + read_unlock_irqrestore(&ni->size_lock, flags); + if (pos > ll) { + /* + * Wait for ongoing direct i/o to complete before proceeding. + * New direct i/o cannot start as we hold i_mutex. + */ + inode_dio_wait(vi); + err = ntfs_attr_extend_initialized(ni, pos); + if (unlikely(err < 0)) + ntfs_error(vi->i_sb, "Cannot perform write to inode " + "0x%lx, attribute type 0x%x, because " + "extending the initialized size " + "failed (error %d).", vi->i_ino, + (unsigned)le32_to_cpu(ni->type), + (int)-err); + } +out: + return err; } /** @@ -421,8 +524,8 @@ static inline int __ntfs_grab_cache_pages(struct address_space *mapping, goto err_out; } } - err = add_to_page_cache_lru(*cached_page, mapping, index, - GFP_KERNEL); + err = add_to_page_cache_lru(*cached_page, mapping, + index, GFP_KERNEL); if (unlikely(err)) { if (err == -EEXIST) continue; @@ -1268,180 +1371,6 @@ rl_not_mapped_enoent: return err; } -/* - * Copy as much as we can into the pages and return the number of bytes which - * were successfully copied. If a fault is encountered then clear the pages - * out to (ofs + bytes) and return the number of bytes which were copied. - */ -static inline size_t ntfs_copy_from_user(struct page **pages, - unsigned nr_pages, unsigned ofs, const char __user *buf, - size_t bytes) -{ - struct page **last_page = pages + nr_pages; - char *addr; - size_t total = 0; - unsigned len; - int left; - - do { - len = PAGE_CACHE_SIZE - ofs; - if (len > bytes) - len = bytes; - addr = kmap_atomic(*pages); - left = __copy_from_user_inatomic(addr + ofs, buf, len); - kunmap_atomic(addr); - if (unlikely(left)) { - /* Do it the slow way. */ - addr = kmap(*pages); - left = __copy_from_user(addr + ofs, buf, len); - kunmap(*pages); - if (unlikely(left)) - goto err_out; - } - total += len; - bytes -= len; - if (!bytes) - break; - buf += len; - ofs = 0; - } while (++pages < last_page); -out: - return total; -err_out: - total += len - left; - /* Zero the rest of the target like __copy_from_user(). */ - while (++pages < last_page) { - bytes -= len; - if (!bytes) - break; - len = PAGE_CACHE_SIZE; - if (len > bytes) - len = bytes; - zero_user(*pages, 0, len); - } - goto out; -} - -static size_t __ntfs_copy_from_user_iovec_inatomic(char *vaddr, - const struct iovec *iov, size_t iov_ofs, size_t bytes) -{ - size_t total = 0; - - while (1) { - const char __user *buf = iov->iov_base + iov_ofs; - unsigned len; - size_t left; - - len = iov->iov_len - iov_ofs; - if (len > bytes) - len = bytes; - left = __copy_from_user_inatomic(vaddr, buf, len); - total += len; - bytes -= len; - vaddr += len; - if (unlikely(left)) { - total -= left; - break; - } - if (!bytes) - break; - iov++; - iov_ofs = 0; - } - return total; -} - -static inline void ntfs_set_next_iovec(const struct iovec **iovp, - size_t *iov_ofsp, size_t bytes) -{ - const struct iovec *iov = *iovp; - size_t iov_ofs = *iov_ofsp; - - while (bytes) { - unsigned len; - - len = iov->iov_len - iov_ofs; - if (len > bytes) - len = bytes; - bytes -= len; - iov_ofs += len; - if (iov->iov_len == iov_ofs) { - iov++; - iov_ofs = 0; - } - } - *iovp = iov; - *iov_ofsp = iov_ofs; -} - -/* - * This has the same side-effects and return value as ntfs_copy_from_user(). - * The difference is that on a fault we need to memset the remainder of the - * pages (out to offset + bytes), to emulate ntfs_copy_from_user()'s - * single-segment behaviour. - * - * We call the same helper (__ntfs_copy_from_user_iovec_inatomic()) both when - * atomic and when not atomic. This is ok because it calls - * __copy_from_user_inatomic() and it is ok to call this when non-atomic. In - * fact, the only difference between __copy_from_user_inatomic() and - * __copy_from_user() is that the latter calls might_sleep() and the former - * should not zero the tail of the buffer on error. And on many architectures - * __copy_from_user_inatomic() is just defined to __copy_from_user() so it - * makes no difference at all on those architectures. - */ -static inline size_t ntfs_copy_from_user_iovec(struct page **pages, - unsigned nr_pages, unsigned ofs, const struct iovec **iov, - size_t *iov_ofs, size_t bytes) -{ - struct page **last_page = pages + nr_pages; - char *addr; - size_t copied, len, total = 0; - - do { - len = PAGE_CACHE_SIZE - ofs; - if (len > bytes) - len = bytes; - addr = kmap_atomic(*pages); - copied = __ntfs_copy_from_user_iovec_inatomic(addr + ofs, - *iov, *iov_ofs, len); - kunmap_atomic(addr); - if (unlikely(copied != len)) { - /* Do it the slow way. */ - addr = kmap(*pages); - copied = __ntfs_copy_from_user_iovec_inatomic(addr + - ofs, *iov, *iov_ofs, len); - if (unlikely(copied != len)) - goto err_out; - kunmap(*pages); - } - total += len; - ntfs_set_next_iovec(iov, iov_ofs, len); - bytes -= len; - if (!bytes) - break; - ofs = 0; - } while (++pages < last_page); -out: - return total; -err_out: - BUG_ON(copied > len); - /* Zero the rest of the target like __copy_from_user(). */ - memset(addr + ofs + copied, 0, len - copied); - kunmap(*pages); - total += copied; - ntfs_set_next_iovec(iov, iov_ofs, copied); - while (++pages < last_page) { - bytes -= len; - if (!bytes) - break; - len = PAGE_CACHE_SIZE; - if (len > bytes) - len = bytes; - zero_user(*pages, 0, len); - } - goto out; -} - static inline void ntfs_flush_dcache_pages(struct page **pages, unsigned nr_pages) { @@ -1762,86 +1691,83 @@ err_out: return err; } -static void ntfs_write_failed(struct address_space *mapping, loff_t to) +/* + * Copy as much as we can into the pages and return the number of bytes which + * were successfully copied. If a fault is encountered then clear the pages + * out to (ofs + bytes) and return the number of bytes which were copied. + */ +static size_t ntfs_copy_from_user_iter(struct page **pages, unsigned nr_pages, + unsigned ofs, struct iov_iter *i, size_t bytes) { - struct inode *inode = mapping->host; + struct page **last_page = pages + nr_pages; + size_t total = 0; + struct iov_iter data = *i; + unsigned len, copied; - if (to > inode->i_size) { - truncate_pagecache(inode, inode->i_size); - ntfs_truncate_vfs(inode); - } + do { + len = PAGE_CACHE_SIZE - ofs; + if (len > bytes) + len = bytes; + copied = iov_iter_copy_from_user_atomic(*pages, &data, ofs, + len); + total += copied; + bytes -= copied; + if (!bytes) + break; + iov_iter_advance(&data, copied); + if (copied < len) + goto err; + ofs = 0; + } while (++pages < last_page); +out: + return total; +err: + /* Zero the rest of the target like __copy_from_user(). */ + len = PAGE_CACHE_SIZE - copied; + do { + if (len > bytes) + len = bytes; + zero_user(*pages, copied, len); + bytes -= len; + copied = 0; + len = PAGE_CACHE_SIZE; + } while (++pages < last_page); + goto out; } /** - * ntfs_file_buffered_write - - * - * Locking: The vfs is holding ->i_mutex on the inode. + * ntfs_perform_write - perform buffered write to a file + * @file: file to write to + * @i: iov_iter with data to write + * @pos: byte offset in file at which to begin writing to */ -static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, - const struct iovec *iov, unsigned long nr_segs, - loff_t pos, loff_t *ppos, size_t count) +static ssize_t ntfs_perform_write(struct file *file, struct iov_iter *i, + loff_t pos) { - struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *vi = mapping->host; ntfs_inode *ni = NTFS_I(vi); ntfs_volume *vol = ni->vol; struct page *pages[NTFS_MAX_PAGES_PER_CLUSTER]; struct page *cached_page = NULL; - char __user *buf = NULL; - s64 end, ll; VCN last_vcn; LCN lcn; - unsigned long flags; - size_t bytes, iov_ofs = 0; /* Offset in the current iovec. */ - ssize_t status, written; + size_t bytes; + ssize_t status, written = 0; unsigned nr_pages; - int err; - ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, " - "pos 0x%llx, count 0x%lx.", - vi->i_ino, (unsigned)le32_to_cpu(ni->type), - (unsigned long long)pos, (unsigned long)count); - if (unlikely(!count)) - return 0; - BUG_ON(NInoMstProtected(ni)); - /* - * If the attribute is not an index root and it is encrypted or - * compressed, we cannot write to it yet. Note we need to check for - * AT_INDEX_ALLOCATION since this is the type of both directory and - * index inodes. - */ - if (ni->type != AT_INDEX_ALLOCATION) { - /* If file is encrypted, deny access, just like NT4. */ - if (NInoEncrypted(ni)) { - /* - * Reminder for later: Encrypted files are _always_ - * non-resident so that the content can always be - * encrypted. - */ - ntfs_debug("Denying write access to encrypted file."); - return -EACCES; - } - if (NInoCompressed(ni)) { - /* Only unnamed $DATA attribute can be compressed. */ - BUG_ON(ni->type != AT_DATA); - BUG_ON(ni->name_len); - /* - * Reminder for later: If resident, the data is not - * actually compressed. Only on the switch to non- - * resident does compression kick in. This is in - * contrast to encrypted files (see above). - */ - ntfs_error(vi->i_sb, "Writing to compressed files is " - "not implemented yet. Sorry."); - return -EOPNOTSUPP; - } - } + ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, pos " + "0x%llx, count 0x%lx.", vi->i_ino, + (unsigned)le32_to_cpu(ni->type), + (unsigned long long)pos, + (unsigned long)iov_iter_count(i)); /* * If a previous ntfs_truncate() failed, repeat it and abort if it * fails again. */ if (unlikely(NInoTruncateFailed(ni))) { + int err; + inode_dio_wait(vi); err = ntfs_truncate(vi); if (err || NInoTruncateFailed(ni)) { @@ -1855,81 +1781,6 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, return err; } } - /* The first byte after the write. */ - end = pos + count; - /* - * If the write goes beyond the allocated size, extend the allocation - * to cover the whole of the write, rounded up to the nearest cluster. - */ - read_lock_irqsave(&ni->size_lock, flags); - ll = ni->allocated_size; - read_unlock_irqrestore(&ni->size_lock, flags); - if (end > ll) { - /* Extend the allocation without changing the data size. */ - ll = ntfs_attr_extend_allocation(ni, end, -1, pos); - if (likely(ll >= 0)) { - BUG_ON(pos >= ll); - /* If the extension was partial truncate the write. */ - if (end > ll) { - ntfs_debug("Truncating write to inode 0x%lx, " - "attribute type 0x%x, because " - "the allocation was only " - "partially extended.", - vi->i_ino, (unsigned) - le32_to_cpu(ni->type)); - end = ll; - count = ll - pos; - } - } else { - err = ll; - read_lock_irqsave(&ni->size_lock, flags); - ll = ni->allocated_size; - read_unlock_irqrestore(&ni->size_lock, flags); - /* Perform a partial write if possible or fail. */ - if (pos < ll) { - ntfs_debug("Truncating write to inode 0x%lx, " - "attribute type 0x%x, because " - "extending the allocation " - "failed (error code %i).", - vi->i_ino, (unsigned) - le32_to_cpu(ni->type), err); - end = ll; - count = ll - pos; - } else { - ntfs_error(vol->sb, "Cannot perform write to " - "inode 0x%lx, attribute type " - "0x%x, because extending the " - "allocation failed (error " - "code %i).", vi->i_ino, - (unsigned) - le32_to_cpu(ni->type), err); - return err; - } - } - } - written = 0; - /* - * If the write starts beyond the initialized size, extend it up to the - * beginning of the write and initialize all non-sparse space between - * the old initialized size and the new one. This automatically also - * increments the vfs inode->i_size to keep it above or equal to the - * initialized_size. - */ - read_lock_irqsave(&ni->size_lock, flags); - ll = ni->initialized_size; - read_unlock_irqrestore(&ni->size_lock, flags); - if (pos > ll) { - err = ntfs_attr_extend_initialized(ni, pos); - if (err < 0) { - ntfs_error(vol->sb, "Cannot perform write to inode " - "0x%lx, attribute type 0x%x, because " - "extending the initialized size " - "failed (error code %i).", vi->i_ino, - (unsigned)le32_to_cpu(ni->type), err); - status = err; - goto err_out; - } - } /* * Determine the number of pages per cluster for non-resident * attributes. @@ -1937,10 +1788,7 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, nr_pages = 1; if (vol->cluster_size > PAGE_CACHE_SIZE && NInoNonResident(ni)) nr_pages = vol->cluster_size >> PAGE_CACHE_SHIFT; - /* Finally, perform the actual write. */ last_vcn = -1; - if (likely(nr_segs == 1)) - buf = iov->iov_base; do { VCN vcn; pgoff_t idx, start_idx; @@ -1965,10 +1813,10 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, vol->cluster_size_bits, false); up_read(&ni->runlist.lock); if (unlikely(lcn < LCN_HOLE)) { - status = -EIO; if (lcn == LCN_ENOMEM) status = -ENOMEM; - else + else { + status = -EIO; ntfs_error(vol->sb, "Cannot " "perform write to " "inode 0x%lx, " @@ -1977,6 +1825,7 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, "is corrupt.", vi->i_ino, (unsigned) le32_to_cpu(ni->type)); + } break; } if (lcn == LCN_HOLE) { @@ -1989,8 +1838,9 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, } } } - if (bytes > count) - bytes = count; + if (bytes > iov_iter_count(i)) + bytes = iov_iter_count(i); +again: /* * Bring in the user page(s) that we will copy from _first_. * Otherwise there is a nasty deadlock on copying from the same @@ -1999,10 +1849,10 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, * pages being swapped out between us bringing them into memory * and doing the actual copying. */ - if (likely(nr_segs == 1)) - ntfs_fault_in_pages_readable(buf, bytes); - else - ntfs_fault_in_pages_readable_iovec(iov, iov_ofs, bytes); + if (unlikely(iov_iter_fault_in_multipages_readable(i, bytes))) { + status = -EFAULT; + break; + } /* Get and lock @do_pages starting at index @start_idx. */ status = __ntfs_grab_cache_pages(mapping, start_idx, do_pages, pages, &cached_page); @@ -2018,56 +1868,57 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, status = ntfs_prepare_pages_for_non_resident_write( pages, do_pages, pos, bytes); if (unlikely(status)) { - loff_t i_size; - do { unlock_page(pages[--do_pages]); page_cache_release(pages[do_pages]); } while (do_pages); - /* - * The write preparation may have instantiated - * allocated space outside i_size. Trim this - * off again. We can ignore any errors in this - * case as we will just be waisting a bit of - * allocated space, which is not a disaster. - */ - i_size = i_size_read(vi); - if (pos + bytes > i_size) { - ntfs_write_failed(mapping, pos + bytes); - } break; } } u = (pos >> PAGE_CACHE_SHIFT) - pages[0]->index; - if (likely(nr_segs == 1)) { - copied = ntfs_copy_from_user(pages + u, do_pages - u, - ofs, buf, bytes); - buf += copied; - } else - copied = ntfs_copy_from_user_iovec(pages + u, - do_pages - u, ofs, &iov, &iov_ofs, - bytes); + copied = ntfs_copy_from_user_iter(pages + u, do_pages - u, ofs, + i, bytes); ntfs_flush_dcache_pages(pages + u, do_pages - u); - status = ntfs_commit_pages_after_write(pages, do_pages, pos, - bytes); - if (likely(!status)) { - written += copied; - count -= copied; - pos += copied; - if (unlikely(copied != bytes)) - status = -EFAULT; + status = 0; + if (likely(copied == bytes)) { + status = ntfs_commit_pages_after_write(pages, do_pages, + pos, bytes); + if (!status) + status = bytes; } do { unlock_page(pages[--do_pages]); page_cache_release(pages[do_pages]); } while (do_pages); - if (unlikely(status)) + if (unlikely(status < 0)) break; - balance_dirty_pages_ratelimited(mapping); + copied = status; cond_resched(); - } while (count); -err_out: - *ppos = pos; + if (unlikely(!copied)) { + size_t sc; + + /* + * We failed to copy anything. Fall back to single + * segment length write. + * + * This is needed to avoid possible livelock in the + * case that all segments in the iov cannot be copied + * at once without a pagefault. + */ + sc = iov_iter_single_seg_count(i); + if (bytes > sc) + bytes = sc; + goto again; + } + iov_iter_advance(i, copied); + pos += copied; + written += copied; + balance_dirty_pages_ratelimited(mapping); + if (fatal_signal_pending(current)) { + status = -EINTR; + break; + } + } while (iov_iter_count(i)); if (cached_page) page_cache_release(cached_page); ntfs_debug("Done. Returning %s (written 0x%lx, status %li).", @@ -2077,63 +1928,36 @@ err_out: } /** - * ntfs_file_aio_write_nolock - + * ntfs_file_write_iter - simple wrapper for ntfs_file_write_iter_nolock() + * @iocb: IO state structure + * @from: iov_iter with data to write + * + * Basically the same as generic_file_write_iter() except that it ends up + * up calling ntfs_perform_write() instead of generic_perform_write() and that + * O_DIRECT is not implemented. */ -static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb, - const struct iovec *iov, unsigned long nr_segs, loff_t *ppos) +static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - loff_t pos; - size_t count; /* after file limit checks */ - ssize_t written, err; + struct inode *vi = file_inode(file); + ssize_t written = 0; + ssize_t err; - count = iov_length(iov, nr_segs); - pos = *ppos; + mutex_lock(&vi->i_mutex); /* We can write back this queue in page reclaim. */ - current->backing_dev_info = inode_to_bdi(inode); - written = 0; - err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); - if (err) - goto out; - if (!count) - goto out; - err = file_remove_suid(file); - if (err) - goto out; - err = file_update_time(file); - if (err) - goto out; - written = ntfs_file_buffered_write(iocb, iov, nr_segs, pos, ppos, - count); -out: + current->backing_dev_info = inode_to_bdi(vi); + err = ntfs_prepare_file_for_write(iocb, from); + if (iov_iter_count(from) && !err) + written = ntfs_perform_write(file, from, iocb->ki_pos); current->backing_dev_info = NULL; - return written ? written : err; -} - -/** - * ntfs_file_aio_write - - */ -static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) -{ - struct file *file = iocb->ki_filp; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - ssize_t ret; - - BUG_ON(iocb->ki_pos != pos); - - mutex_lock(&inode->i_mutex); - ret = ntfs_file_aio_write_nolock(iocb, iov, nr_segs, &iocb->ki_pos); - mutex_unlock(&inode->i_mutex); - if (ret > 0) { - int err = generic_write_sync(file, iocb->ki_pos - ret, ret); + mutex_unlock(&vi->i_mutex); + if (likely(written > 0)) { + err = generic_write_sync(file, iocb->ki_pos, written); if (err < 0) - ret = err; + written = 0; } - return ret; + iocb->ki_pos += written; + return written ? written : err; } /** @@ -2197,37 +2021,15 @@ static int ntfs_file_fsync(struct file *filp, loff_t start, loff_t end, #endif /* NTFS_RW */ const struct file_operations ntfs_file_ops = { - .llseek = generic_file_llseek, /* Seek inside file. */ - .read = new_sync_read, /* Read from file. */ - .read_iter = generic_file_read_iter, /* Async read from file. */ + .llseek = generic_file_llseek, + .read_iter = generic_file_read_iter, #ifdef NTFS_RW - .write = do_sync_write, /* Write to file. */ - .aio_write = ntfs_file_aio_write, /* Async write to file. */ - /*.release = ,*/ /* Last file is closed. See - fs/ext2/file.c:: - ext2_release_file() for - how to use this to discard - preallocated space for - write opened files. */ - .fsync = ntfs_file_fsync, /* Sync a file to disk. */ - /*.aio_fsync = ,*/ /* Sync all outstanding async - i/o operations on a - kiocb. */ + .write_iter = ntfs_file_write_iter, + .fsync = ntfs_file_fsync, #endif /* NTFS_RW */ - /*.ioctl = ,*/ /* Perform function on the - mounted filesystem. */ - .mmap = generic_file_mmap, /* Mmap file. */ - .open = ntfs_file_open, /* Open file. */ - .splice_read = generic_file_splice_read /* Zero-copy data send with - the data source being on - the ntfs partition. We do - not need to care about the - data destination. */ - /*.sendpage = ,*/ /* Zero-copy data send with - the data destination being - on the ntfs partition. We - do not need to care about - the data source. */ + .mmap = generic_file_mmap, + .open = ntfs_file_open, + .splice_read = generic_file_splice_read, }; const struct inode_operations ntfs_file_inode_ops = { diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index 898b9949d363..1d0c21df0d80 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -28,7 +28,6 @@ #include <linux/quotaops.h> #include <linux/slab.h> #include <linux/log2.h> -#include <linux/aio.h> #include "aops.h" #include "attrib.h" diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 044158bd22be..2d7f76e52c37 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -3370,7 +3370,7 @@ static int ocfs2_merge_rec_right(struct ocfs2_path *left_path, ret = ocfs2_get_right_path(et, left_path, &right_path); if (ret) { mlog_errno(ret); - goto out; + return ret; } right_el = path_leaf_el(right_path); @@ -3453,8 +3453,7 @@ static int ocfs2_merge_rec_right(struct ocfs2_path *left_path, subtree_index); } out: - if (right_path) - ocfs2_free_path(right_path); + ocfs2_free_path(right_path); return ret; } @@ -3536,7 +3535,7 @@ static int ocfs2_merge_rec_left(struct ocfs2_path *right_path, ret = ocfs2_get_left_path(et, right_path, &left_path); if (ret) { mlog_errno(ret); - goto out; + return ret; } left_el = path_leaf_el(left_path); @@ -3647,8 +3646,7 @@ static int ocfs2_merge_rec_left(struct ocfs2_path *right_path, right_path, subtree_index); } out: - if (left_path) - ocfs2_free_path(left_path); + ocfs2_free_path(left_path); return ret; } @@ -4334,17 +4332,17 @@ ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et, } else if (path->p_tree_depth > 0) { status = ocfs2_find_cpos_for_left_leaf(sb, path, &left_cpos); if (status) - goto out; + goto exit; if (left_cpos != 0) { left_path = ocfs2_new_path_from_path(path); if (!left_path) - goto out; + goto exit; status = ocfs2_find_path(et->et_ci, left_path, left_cpos); if (status) - goto out; + goto free_left_path; new_el = path_leaf_el(left_path); @@ -4361,7 +4359,7 @@ ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et, le16_to_cpu(new_el->l_next_free_rec), le16_to_cpu(new_el->l_count)); status = -EINVAL; - goto out; + goto free_left_path; } rec = &new_el->l_recs[ le16_to_cpu(new_el->l_next_free_rec) - 1]; @@ -4388,18 +4386,18 @@ ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et, path->p_tree_depth > 0) { status = ocfs2_find_cpos_for_right_leaf(sb, path, &right_cpos); if (status) - goto out; + goto free_left_path; if (right_cpos == 0) - goto out; + goto free_left_path; right_path = ocfs2_new_path_from_path(path); if (!right_path) - goto out; + goto free_left_path; status = ocfs2_find_path(et->et_ci, right_path, right_cpos); if (status) - goto out; + goto free_right_path; new_el = path_leaf_el(right_path); rec = &new_el->l_recs[0]; @@ -4413,7 +4411,7 @@ ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et, (unsigned long long)le64_to_cpu(eb->h_blkno), le16_to_cpu(new_el->l_next_free_rec)); status = -EINVAL; - goto out; + goto free_right_path; } rec = &new_el->l_recs[1]; } @@ -4430,12 +4428,11 @@ ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et, ret = contig_type; } -out: - if (left_path) - ocfs2_free_path(left_path); - if (right_path) - ocfs2_free_path(right_path); - +free_right_path: + ocfs2_free_path(right_path); +free_left_path: + ocfs2_free_path(left_path); +exit: return ret; } @@ -6858,13 +6855,13 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, if (pages == NULL) { ret = -ENOMEM; mlog_errno(ret); - goto out; + return ret; } ret = ocfs2_reserve_clusters(osb, 1, &data_ac); if (ret) { mlog_errno(ret); - goto out; + goto free_pages; } } @@ -6996,9 +6993,8 @@ out_commit: out: if (data_ac) ocfs2_free_alloc_context(data_ac); - if (pages) - kfree(pages); - +free_pages: + kfree(pages); return ret; } diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 44db1808cdb5..f906a250da6a 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -29,6 +29,7 @@ #include <linux/mpage.h> #include <linux/quotaops.h> #include <linux/blkdev.h> +#include <linux/uio.h> #include <cluster/masklog.h> @@ -663,6 +664,117 @@ static int ocfs2_is_overwrite(struct ocfs2_super *osb, return 0; } +static int ocfs2_direct_IO_zero_extend(struct ocfs2_super *osb, + struct inode *inode, loff_t offset, + u64 zero_len, int cluster_align) +{ + u32 p_cpos = 0; + u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, i_size_read(inode)); + unsigned int num_clusters = 0; + unsigned int ext_flags = 0; + int ret = 0; + + if (offset <= i_size_read(inode) || cluster_align) + return 0; + + ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos, &num_clusters, + &ext_flags); + if (ret < 0) { + mlog_errno(ret); + return ret; + } + + if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) { + u64 s = i_size_read(inode); + sector_t sector = (p_cpos << (osb->s_clustersize_bits - 9)) + + (do_div(s, osb->s_clustersize) >> 9); + + ret = blkdev_issue_zeroout(osb->sb->s_bdev, sector, + zero_len >> 9, GFP_NOFS, false); + if (ret < 0) + mlog_errno(ret); + } + + return ret; +} + +static int ocfs2_direct_IO_extend_no_holes(struct ocfs2_super *osb, + struct inode *inode, loff_t offset) +{ + u64 zero_start, zero_len, total_zero_len; + u32 p_cpos = 0, clusters_to_add; + u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, i_size_read(inode)); + unsigned int num_clusters = 0; + unsigned int ext_flags = 0; + u32 size_div, offset_div; + int ret = 0; + + { + u64 o = offset; + u64 s = i_size_read(inode); + + offset_div = do_div(o, osb->s_clustersize); + size_div = do_div(s, osb->s_clustersize); + } + + if (offset <= i_size_read(inode)) + return 0; + + clusters_to_add = ocfs2_bytes_to_clusters(inode->i_sb, offset) - + ocfs2_bytes_to_clusters(inode->i_sb, i_size_read(inode)); + total_zero_len = offset - i_size_read(inode); + if (clusters_to_add) + total_zero_len -= offset_div; + + /* Allocate clusters to fill out holes, and this is only needed + * when we add more than one clusters. Otherwise the cluster will + * be allocated during direct IO */ + if (clusters_to_add > 1) { + ret = ocfs2_extend_allocation(inode, + OCFS2_I(inode)->ip_clusters, + clusters_to_add - 1, 0); + if (ret) { + mlog_errno(ret); + goto out; + } + } + + while (total_zero_len) { + ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos, &num_clusters, + &ext_flags); + if (ret < 0) { + mlog_errno(ret); + goto out; + } + + zero_start = ocfs2_clusters_to_bytes(osb->sb, p_cpos) + + size_div; + zero_len = ocfs2_clusters_to_bytes(osb->sb, num_clusters) - + size_div; + zero_len = min(total_zero_len, zero_len); + + if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) { + ret = blkdev_issue_zeroout(osb->sb->s_bdev, + zero_start >> 9, zero_len >> 9, + GFP_NOFS, false); + if (ret < 0) { + mlog_errno(ret); + goto out; + } + } + + total_zero_len -= zero_len; + v_cpos += ocfs2_bytes_to_clusters(osb->sb, zero_len + size_div); + + /* Only at first iteration can be cluster not aligned. + * So set size_div to 0 for the rest */ + size_div = 0; + } + +out: + return ret; +} + static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) @@ -677,8 +789,8 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb, struct buffer_head *di_bh = NULL; size_t count = iter->count; journal_t *journal = osb->journal->j_journal; - u32 zero_len; - int cluster_align; + u64 zero_len_head, zero_len_tail; + int cluster_align_head, cluster_align_tail; loff_t final_size = offset + count; int append_write = offset >= i_size_read(inode) ? 1 : 0; unsigned int num_clusters = 0; @@ -686,9 +798,16 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb, { u64 o = offset; + u64 s = i_size_read(inode); + + zero_len_head = do_div(o, 1 << osb->s_clustersize_bits); + cluster_align_head = !zero_len_head; - zero_len = do_div(o, 1 << osb->s_clustersize_bits); - cluster_align = !zero_len; + zero_len_tail = osb->s_clustersize - + do_div(s, osb->s_clustersize); + if ((offset - i_size_read(inode)) < zero_len_tail) + zero_len_tail = offset - i_size_read(inode); + cluster_align_tail = !zero_len_tail; } /* @@ -706,21 +825,23 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb, } if (append_write) { - ret = ocfs2_inode_lock(inode, &di_bh, 1); + ret = ocfs2_inode_lock(inode, NULL, 1); if (ret < 0) { mlog_errno(ret); goto clean_orphan; } + /* zeroing out the previously allocated cluster tail + * that but not zeroed */ if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) - ret = ocfs2_zero_extend(inode, di_bh, offset); + ret = ocfs2_direct_IO_zero_extend(osb, inode, offset, + zero_len_tail, cluster_align_tail); else - ret = ocfs2_extend_no_holes(inode, di_bh, offset, + ret = ocfs2_direct_IO_extend_no_holes(osb, inode, offset); if (ret < 0) { mlog_errno(ret); ocfs2_inode_unlock(inode, 1); - brelse(di_bh); goto clean_orphan; } @@ -728,19 +849,15 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb, if (is_overwrite < 0) { mlog_errno(is_overwrite); ocfs2_inode_unlock(inode, 1); - brelse(di_bh); goto clean_orphan; } ocfs2_inode_unlock(inode, 1); - brelse(di_bh); - di_bh = NULL; } - written = __blockdev_direct_IO(WRITE, iocb, inode, inode->i_sb->s_bdev, - iter, offset, - ocfs2_direct_IO_get_blocks, - ocfs2_dio_end_io, NULL, 0); + written = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, + offset, ocfs2_direct_IO_get_blocks, + ocfs2_dio_end_io, NULL, 0); if (unlikely(written < 0)) { loff_t i_size = i_size_read(inode); @@ -771,15 +888,23 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb, if (ret < 0) mlog_errno(ret); } - } else if (written < 0 && append_write && !is_overwrite && - !cluster_align) { + } else if (written > 0 && append_write && !is_overwrite && + !cluster_align_head) { + /* zeroing out the allocated cluster head */ u32 p_cpos = 0; u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset); + ret = ocfs2_inode_lock(inode, NULL, 0); + if (ret < 0) { + mlog_errno(ret); + goto clean_orphan; + } + ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos, &num_clusters, &ext_flags); if (ret < 0) { mlog_errno(ret); + ocfs2_inode_unlock(inode, 0); goto clean_orphan; } @@ -787,9 +912,11 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb, ret = blkdev_issue_zeroout(osb->sb->s_bdev, p_cpos << (osb->s_clustersize_bits - 9), - zero_len >> 9, GFP_KERNEL, false); + zero_len_head >> 9, GFP_NOFS, false); if (ret < 0) mlog_errno(ret); + + ocfs2_inode_unlock(inode, 0); } clean_orphan: @@ -818,9 +945,7 @@ out: return ret; } -static ssize_t ocfs2_direct_IO(int rw, - struct kiocb *iocb, - struct iov_iter *iter, +static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; @@ -842,12 +967,11 @@ static ssize_t ocfs2_direct_IO(int rw, if (i_size_read(inode) <= offset && !full_coherency) return 0; - if (rw == READ) - return __blockdev_direct_IO(rw, iocb, inode, - inode->i_sb->s_bdev, - iter, offset, - ocfs2_direct_IO_get_blocks, - ocfs2_dio_end_io, NULL, 0); + if (iov_iter_rw(iter) == READ) + return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, + iter, offset, + ocfs2_direct_IO_get_blocks, + ocfs2_dio_end_io, NULL, 0); else return ocfs2_direct_IO_write(iocb, iter, offset); } diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h index 6cae155d54df..dd59599b022d 100644 --- a/fs/ocfs2/aops.h +++ b/fs/ocfs2/aops.h @@ -22,7 +22,7 @@ #ifndef OCFS2_AOPS_H #define OCFS2_AOPS_H -#include <linux/aio.h> +#include <linux/fs.h> handle_t *ocfs2_start_walk_page_trans(struct inode *inode, struct page *page, diff --git a/fs/ocfs2/cluster/masklog.h b/fs/ocfs2/cluster/masklog.h index 2260fb9e6508..7fdc25a4d8c0 100644 --- a/fs/ocfs2/cluster/masklog.h +++ b/fs/ocfs2/cluster/masklog.h @@ -196,13 +196,14 @@ extern struct mlog_bits mlog_and_bits, mlog_not_bits; } \ } while (0) -#define mlog_errno(st) do { \ +#define mlog_errno(st) ({ \ int _st = (st); \ if (_st != -ERESTARTSYS && _st != -EINTR && \ _st != AOP_TRUNCATED_PAGE && _st != -ENOSPC && \ _st != -EDQUOT) \ mlog(ML_ERROR, "status = %lld\n", (long long)_st); \ -} while (0) + _st; \ +}) #define mlog_bug_on_msg(cond, fmt, args...) do { \ if (cond) { \ diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index b08050bd3f2e..ccd4dcfc3645 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -18,7 +18,7 @@ * * linux/fs/minix/dir.c * - * Copyright (C) 1991, 1992 Linux Torvalds + * Copyright (C) 1991, 1992 Linus Torvalds * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public @@ -2047,22 +2047,19 @@ int ocfs2_check_dir_for_entry(struct inode *dir, const char *name, int namelen) { - int ret; + int ret = 0; struct ocfs2_dir_lookup_result lookup = { NULL, }; trace_ocfs2_check_dir_for_entry( (unsigned long long)OCFS2_I(dir)->ip_blkno, namelen, name); - ret = -EEXIST; - if (ocfs2_find_entry(name, namelen, dir, &lookup) == 0) - goto bail; + if (ocfs2_find_entry(name, namelen, dir, &lookup) == 0) { + ret = -EEXIST; + mlog_errno(ret); + } - ret = 0; -bail: ocfs2_free_dir_lookup_result(&lookup); - if (ret) - mlog_errno(ret); return ret; } diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 11849a44dc5a..8b23aa2f52dd 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -1391,6 +1391,11 @@ static int __ocfs2_cluster_lock(struct ocfs2_super *osb, int noqueue_attempted = 0; int dlm_locked = 0; + if (!(lockres->l_flags & OCFS2_LOCK_INITIALIZED)) { + mlog_errno(-EINVAL); + return -EINVAL; + } + ocfs2_init_mask_waiter(&mw); if (lockres->l_ops->flags & LOCK_TYPE_USES_LVB) diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c index 29651167190d..540dc4bdd042 100644 --- a/fs/ocfs2/export.c +++ b/fs/ocfs2/export.c @@ -82,7 +82,6 @@ static struct dentry *ocfs2_get_dentry(struct super_block *sb, } status = ocfs2_test_inode_bit(osb, blkno, &set); - trace_ocfs2_get_dentry_test_bit(status, set); if (status < 0) { if (status == -EINVAL) { /* @@ -96,6 +95,7 @@ static struct dentry *ocfs2_get_dentry(struct super_block *sb, goto unlock_nfs_sync; } + trace_ocfs2_get_dentry_test_bit(status, set); /* If the inode allocator bit is clear, this inode must be stale */ if (!set) { status = -ESTALE; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 46e0d4e857c7..913fc250d85a 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2106,7 +2106,7 @@ out: } static int ocfs2_prepare_inode_for_write(struct file *file, - loff_t *ppos, + loff_t pos, size_t count, int appending, int *direct_io, @@ -2115,7 +2115,7 @@ static int ocfs2_prepare_inode_for_write(struct file *file, int ret = 0, meta_level = 0; struct dentry *dentry = file->f_path.dentry; struct inode *inode = dentry->d_inode; - loff_t saved_pos = 0, end; + loff_t end; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); int full_coherency = !(osb->s_mount_opt & OCFS2_MOUNT_COHERENCY_BUFFERED); @@ -2155,23 +2155,16 @@ static int ocfs2_prepare_inode_for_write(struct file *file, } } - /* work on a copy of ppos until we're sure that we won't have - * to recalculate it due to relocking. */ - if (appending) - saved_pos = i_size_read(inode); - else - saved_pos = *ppos; - - end = saved_pos + count; + end = pos + count; - ret = ocfs2_check_range_for_refcount(inode, saved_pos, count); + ret = ocfs2_check_range_for_refcount(inode, pos, count); if (ret == 1) { ocfs2_inode_unlock(inode, meta_level); meta_level = -1; ret = ocfs2_prepare_inode_for_refcount(inode, file, - saved_pos, + pos, count, &meta_level); if (has_refcount) @@ -2227,7 +2220,7 @@ static int ocfs2_prepare_inode_for_write(struct file *file, * caller will have to retake some cluster * locks and initiate the io as buffered. */ - ret = ocfs2_check_range_for_holes(inode, saved_pos, count); + ret = ocfs2_check_range_for_holes(inode, pos, count); if (ret == 1) { /* * Fallback to old way if the feature bit is not set. @@ -2242,12 +2235,9 @@ static int ocfs2_prepare_inode_for_write(struct file *file, break; } - if (appending) - *ppos = saved_pos; - out_unlock: trace_ocfs2_prepare_inode_for_write(OCFS2_I(inode)->ip_blkno, - saved_pos, appending, count, + pos, appending, count, direct_io, has_refcount); if (meta_level >= 0) @@ -2260,19 +2250,20 @@ out: static ssize_t ocfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { - int ret, direct_io, appending, rw_level, have_alloc_sem = 0; + int direct_io, appending, rw_level, have_alloc_sem = 0; int can_do_direct, has_refcount = 0; ssize_t written = 0; - size_t count = iov_iter_count(from); - loff_t old_size, *ppos = &iocb->ki_pos; + ssize_t ret; + size_t count = iov_iter_count(from), orig_count; + loff_t old_size; u32 old_clusters; struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); - struct address_space *mapping = file->f_mapping; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); int full_coherency = !(osb->s_mount_opt & OCFS2_MOUNT_COHERENCY_BUFFERED); int unaligned_dio = 0; + int dropped_dio = 0; trace_ocfs2_file_aio_write(inode, file, file->f_path.dentry, (unsigned long long)OCFS2_I(inode)->ip_blkno, @@ -2280,11 +2271,11 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb, file->f_path.dentry->d_name.name, (unsigned int)from->nr_segs); /* GRRRRR */ - if (iocb->ki_nbytes == 0) + if (count == 0) return 0; - appending = file->f_flags & O_APPEND ? 1 : 0; - direct_io = file->f_flags & O_DIRECT ? 1 : 0; + appending = iocb->ki_flags & IOCB_APPEND ? 1 : 0; + direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0; mutex_lock(&inode->i_mutex); @@ -2329,9 +2320,17 @@ relock: ocfs2_inode_unlock(inode, 1); } + orig_count = iov_iter_count(from); + ret = generic_write_checks(iocb, from); + if (ret <= 0) { + if (ret) + mlog_errno(ret); + goto out; + } + count = ret; + can_do_direct = direct_io; - ret = ocfs2_prepare_inode_for_write(file, ppos, - iocb->ki_nbytes, appending, + ret = ocfs2_prepare_inode_for_write(file, iocb->ki_pos, count, appending, &can_do_direct, &has_refcount); if (ret < 0) { mlog_errno(ret); @@ -2339,8 +2338,7 @@ relock: } if (direct_io && !is_sync_kiocb(iocb)) - unaligned_dio = ocfs2_is_io_unaligned(inode, iocb->ki_nbytes, - *ppos); + unaligned_dio = ocfs2_is_io_unaligned(inode, count, iocb->ki_pos); /* * We can't complete the direct I/O as requested, fall back to @@ -2353,6 +2351,9 @@ relock: rw_level = -1; direct_io = 0; + iocb->ki_flags &= ~IOCB_DIRECT; + iov_iter_reexpand(from, orig_count); + dropped_dio = 1; goto relock; } @@ -2376,74 +2377,18 @@ relock: /* communicate with ocfs2_dio_end_io */ ocfs2_iocb_set_rw_locked(iocb, rw_level); - ret = generic_write_checks(file, ppos, &count, - S_ISBLK(inode->i_mode)); - if (ret) - goto out_dio; - - iov_iter_truncate(from, count); - if (direct_io) { - loff_t endbyte; - ssize_t written_buffered; - written = generic_file_direct_write(iocb, from, *ppos); - if (written < 0 || written == count) { - ret = written; - goto out_dio; - } - - /* - * for completing the rest of the request. - */ - *ppos += written; - count -= written; - written_buffered = generic_perform_write(file, from, *ppos); - /* - * If generic_file_buffered_write() returned a synchronous error - * then we want to return the number of bytes which were - * direct-written, or the error code if that was zero. Note - * that this differs from normal direct-io semantics, which - * will return -EFOO even if some bytes were written. - */ - if (written_buffered < 0) { - ret = written_buffered; - goto out_dio; - } - - iocb->ki_pos = *ppos + written_buffered; - /* We need to ensure that the page cache pages are written to - * disk and invalidated to preserve the expected O_DIRECT - * semantics. - */ - endbyte = *ppos + written_buffered - 1; - ret = filemap_write_and_wait_range(file->f_mapping, *ppos, - endbyte); - if (ret == 0) { - written += written_buffered; - invalidate_mapping_pages(mapping, - *ppos >> PAGE_CACHE_SHIFT, - endbyte >> PAGE_CACHE_SHIFT); - } else { - /* - * We don't know how much we wrote, so just return - * the number of bytes which were direct-written - */ - } - } else { - current->backing_dev_info = inode_to_bdi(inode); - written = generic_perform_write(file, from, *ppos); - if (likely(written >= 0)) - iocb->ki_pos = *ppos + written; - current->backing_dev_info = NULL; - } - -out_dio: + written = __generic_file_write_iter(iocb, from); /* buffered aio wouldn't have proper lock coverage today */ - BUG_ON(ret == -EIOCBQUEUED && !(file->f_flags & O_DIRECT)); + BUG_ON(written == -EIOCBQUEUED && !(iocb->ki_flags & IOCB_DIRECT)); + + if (unlikely(written <= 0)) + goto no_sync; - if (((file->f_flags & O_DSYNC) && !direct_io) || IS_SYNC(inode) || - ((file->f_flags & O_DIRECT) && !direct_io)) { - ret = filemap_fdatawrite_range(file->f_mapping, *ppos, - *ppos + count - 1); + if (((file->f_flags & O_DSYNC) && !direct_io) || + IS_SYNC(inode) || dropped_dio) { + ret = filemap_fdatawrite_range(file->f_mapping, + iocb->ki_pos - written, + iocb->ki_pos - 1); if (ret < 0) written = ret; @@ -2454,10 +2399,12 @@ out_dio: } if (!ret) - ret = filemap_fdatawait_range(file->f_mapping, *ppos, - *ppos + count - 1); + ret = filemap_fdatawait_range(file->f_mapping, + iocb->ki_pos - written, + iocb->ki_pos - 1); } +no_sync: /* * deep in g_f_a_w_n()->ocfs2_direct_IO we pass in a ocfs2_dio_end_io * function pointer which is called when o_direct io completes so that @@ -2549,7 +2496,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb, * buffered reads protect themselves in ->readpage(). O_DIRECT reads * need locks to protect pending reads from racing with truncate. */ - if (filp->f_flags & O_DIRECT) { + if (iocb->ki_flags & IOCB_DIRECT) { have_alloc_sem = 1; ocfs2_iocb_set_sem_locked(iocb); @@ -2583,7 +2530,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb, trace_generic_file_aio_read_ret(ret); /* buffered aio wouldn't have proper lock coverage today */ - BUG_ON(ret == -EIOCBQUEUED && !(filp->f_flags & O_DIRECT)); + BUG_ON(ret == -EIOCBQUEUED && !(iocb->ki_flags & IOCB_DIRECT)); /* see ocfs2_file_write_iter */ if (ret == -EIOCBQUEUED || !ocfs2_iocb_is_rw_locked(iocb)) { @@ -2678,8 +2625,6 @@ const struct inode_operations ocfs2_special_file_iops = { */ const struct file_operations ocfs2_fops = { .llseek = ocfs2_file_llseek, - .read = new_sync_read, - .write = new_sync_write, .mmap = ocfs2_mmap, .fsync = ocfs2_sync_file, .release = ocfs2_file_release, @@ -2726,8 +2671,6 @@ const struct file_operations ocfs2_dops = { */ const struct file_operations ocfs2_fops_no_plocks = { .llseek = ocfs2_file_llseek, - .read = new_sync_read, - .write = new_sync_write, .mmap = ocfs2_mmap, .fsync = ocfs2_sync_file, .release = ocfs2_file_release, diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 3025c0da6b8a..be71ca0937f7 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -624,7 +624,7 @@ static int ocfs2_remove_inode(struct inode *inode, ocfs2_get_system_file_inode(osb, INODE_ALLOC_SYSTEM_INODE, le16_to_cpu(di->i_suballoc_slot)); if (!inode_alloc_inode) { - status = -EEXIST; + status = -ENOENT; mlog_errno(status); goto bail; } @@ -742,7 +742,7 @@ static int ocfs2_wipe_inode(struct inode *inode, ORPHAN_DIR_SYSTEM_INODE, orphaned_slot); if (!orphan_dir_inode) { - status = -EEXIST; + status = -ENOENT; mlog_errno(status); goto bail; } diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 044013455621..857bbbcd39f3 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -666,7 +666,7 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb, if (le32_to_cpu(alloc->id1.bitmap1.i_used) != ocfs2_local_alloc_count_bits(alloc)) { ocfs2_error(osb->sb, "local alloc inode %llu says it has " - "%u free bits, but a count shows %u", + "%u used bits, but a count shows %u", (unsigned long long)le64_to_cpu(alloc->i_blkno), le32_to_cpu(alloc->id1.bitmap1.i_used), ocfs2_local_alloc_count_bits(alloc)); @@ -839,7 +839,7 @@ static int ocfs2_local_alloc_find_clear_bits(struct ocfs2_super *osb, u32 *numbits, struct ocfs2_alloc_reservation *resv) { - int numfound, bitoff, left, startoff, lastzero; + int numfound = 0, bitoff, left, startoff, lastzero; int local_resv = 0; struct ocfs2_alloc_reservation r; void *bitmap = NULL; diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index b5c3a5ea3ee6..09f90cbf0e24 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -2322,10 +2322,10 @@ int ocfs2_orphan_del(struct ocfs2_super *osb, trace_ocfs2_orphan_del( (unsigned long long)OCFS2_I(orphan_dir_inode)->ip_blkno, - name, namelen); + name, strlen(name)); /* find it's spot in the orphan directory */ - status = ocfs2_find_entry(name, namelen, orphan_dir_inode, + status = ocfs2_find_entry(name, strlen(name), orphan_dir_inode, &lookup); if (status) { mlog_errno(status); @@ -2808,7 +2808,7 @@ int ocfs2_mv_orphaned_inode_to_new(struct inode *dir, ORPHAN_DIR_SYSTEM_INODE, osb->slot_num); if (!orphan_dir_inode) { - status = -EEXIST; + status = -ENOENT; mlog_errno(status); goto leave; } diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index ee541f92dab4..df3a500789c7 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4276,7 +4276,7 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir, error = posix_acl_create(dir, &mode, &default_acl, &acl); if (error) { mlog_errno(error); - goto out; + return error; } error = ocfs2_create_inode_in_orphan(dir, mode, diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c index d5493e361a38..e78a203d44c8 100644 --- a/fs/ocfs2/slot_map.c +++ b/fs/ocfs2/slot_map.c @@ -427,7 +427,7 @@ int ocfs2_init_slot_info(struct ocfs2_super *osb) if (!si) { status = -ENOMEM; mlog_errno(status); - goto bail; + return status; } si->si_extended = ocfs2_uses_extended_slot_map(osb); @@ -452,7 +452,7 @@ int ocfs2_init_slot_info(struct ocfs2_super *osb) osb->slot_info = (struct ocfs2_slot_info *)si; bail: - if (status < 0 && si) + if (status < 0) __ocfs2_free_slot_info(si); return status; diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c index 1724d43d3da1..220cae7bbdbc 100644 --- a/fs/ocfs2/stack_o2cb.c +++ b/fs/ocfs2/stack_o2cb.c @@ -295,7 +295,7 @@ static int o2cb_cluster_check(void) set_bit(node_num, netmap); if (!memcmp(hbmap, netmap, sizeof(hbmap))) return 0; - if (i < O2CB_MAP_STABILIZE_COUNT) + if (i < O2CB_MAP_STABILIZE_COUNT - 1) msleep(1000); } diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c index 720aa389e0ea..2768eb1da2b8 100644 --- a/fs/ocfs2/stack_user.c +++ b/fs/ocfs2/stack_user.c @@ -1004,10 +1004,8 @@ static int user_cluster_connect(struct ocfs2_cluster_connection *conn) BUG_ON(conn == NULL); lc = kzalloc(sizeof(struct ocfs2_live_connection), GFP_KERNEL); - if (!lc) { - rc = -ENOMEM; - goto out; - } + if (!lc) + return -ENOMEM; init_waitqueue_head(&lc->oc_wait); init_completion(&lc->oc_sync_wait); @@ -1063,7 +1061,7 @@ static int user_cluster_connect(struct ocfs2_cluster_connection *conn) } out: - if (rc && lc) + if (rc) kfree(lc); return rc; } diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 0cb889a17ae1..4479029630bb 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -2499,6 +2499,8 @@ static int _ocfs2_free_suballoc_bits(handle_t *handle, alloc_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); + ocfs2_block_group_set_bits(handle, alloc_inode, group, group_bh, + start_bit, count); goto bail; } diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 26675185b886..403c5660b306 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -2069,6 +2069,8 @@ static int ocfs2_initialize_super(struct super_block *sb, cbits = le32_to_cpu(di->id2.i_super.s_clustersize_bits); bbits = le32_to_cpu(di->id2.i_super.s_blocksize_bits); sb->s_maxbytes = ocfs2_max_file_offset(bbits, cbits); + memcpy(sb->s_uuid, di->id2.i_super.s_uuid, + sizeof(di->id2.i_super.s_uuid)); osb->osb_dx_mask = (1 << (cbits - bbits)) - 1; @@ -2333,7 +2335,7 @@ static int ocfs2_initialize_super(struct super_block *sb, mlog_errno(status); goto bail; } - cleancache_init_shared_fs((char *)&di->id2.i_super.s_uuid, sb); + cleancache_init_shared_fs(sb); bail: return status; @@ -2563,22 +2565,22 @@ static void ocfs2_handle_error(struct super_block *sb) ocfs2_set_ro_flag(osb, 0); } -static char error_buf[1024]; - -void __ocfs2_error(struct super_block *sb, - const char *function, - const char *fmt, ...) +void __ocfs2_error(struct super_block *sb, const char *function, + const char *fmt, ...) { + struct va_format vaf; va_list args; va_start(args, fmt); - vsnprintf(error_buf, sizeof(error_buf), fmt, args); - va_end(args); + vaf.fmt = fmt; + vaf.va = &args; /* Not using mlog here because we want to show the actual * function the error came from. */ - printk(KERN_CRIT "OCFS2: ERROR (device %s): %s: %s\n", - sb->s_id, function, error_buf); + printk(KERN_CRIT "OCFS2: ERROR (device %s): %s: %pV\n", + sb->s_id, function, &vaf); + + va_end(args); ocfs2_handle_error(sb); } @@ -2586,18 +2588,21 @@ void __ocfs2_error(struct super_block *sb, /* Handle critical errors. This is intentionally more drastic than * ocfs2_handle_error, so we only use for things like journal errors, * etc. */ -void __ocfs2_abort(struct super_block* sb, - const char *function, +void __ocfs2_abort(struct super_block *sb, const char *function, const char *fmt, ...) { + struct va_format vaf; va_list args; va_start(args, fmt); - vsnprintf(error_buf, sizeof(error_buf), fmt, args); - va_end(args); - printk(KERN_CRIT "OCFS2: abort (device %s): %s: %s\n", - sb->s_id, function, error_buf); + vaf.fmt = fmt; + vaf.va = &args; + + printk(KERN_CRIT "OCFS2: abort (device %s): %s: %pV\n", + sb->s_id, function, &vaf); + + va_end(args); /* We don't have the cluster support yet to go straight to * hard readonly in here. Until then, we want to keep diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 85b190dc132f..4ca7533be479 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -1238,6 +1238,10 @@ static int ocfs2_xattr_block_get(struct inode *inode, i, &block_off, &name_offset); + if (ret) { + mlog_errno(ret); + goto cleanup; + } xs->base = bucket_block(xs->bucket, block_off); } if (ocfs2_xattr_is_local(xs->here)) { @@ -5665,6 +5669,10 @@ static int ocfs2_delete_xattr_in_bucket(struct inode *inode, ret = ocfs2_get_xattr_tree_value_root(inode->i_sb, bucket, i, &xv, NULL); + if (ret) { + mlog_errno(ret); + break; + } ret = ocfs2_lock_xattr_remove_allocators(inode, xv, args->ref_ci, diff --git a/fs/omfs/file.c b/fs/omfs/file.c index 902e88527fce..f993be7f2156 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -337,8 +337,6 @@ static sector_t omfs_bmap(struct address_space *mapping, sector_t block) const struct file_operations omfs_file_operations = { .llseek = generic_file_llseek, - .read = new_sync_read, - .write = new_sync_write, .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, diff --git a/fs/open.c b/fs/open.c index 33f9cbf2610b..98e5a52dc68c 100644 --- a/fs/open.c +++ b/fs/open.c @@ -231,8 +231,7 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) return -EINVAL; /* Return error if mode is not supported */ - if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | - FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE)) + if (mode & ~FALLOC_FL_SUPPORTED_MASK) return -EOPNOTSUPP; /* Punch hole and zero range are mutually exclusive */ @@ -250,6 +249,11 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) (mode & ~FALLOC_FL_COLLAPSE_RANGE)) return -EINVAL; + /* Insert range should only be used exclusively. */ + if ((mode & FALLOC_FL_INSERT_RANGE) && + (mode & ~FALLOC_FL_INSERT_RANGE)) + return -EINVAL; + if (!(file->f_mode & FMODE_WRITE)) return -EBADF; @@ -570,6 +574,7 @@ static int chown_common(struct path *path, uid_t user, gid_t group) uid = make_kuid(current_user_ns(), user); gid = make_kgid(current_user_ns(), group); +retry_deleg: newattrs.ia_valid = ATTR_CTIME; if (user != (uid_t) -1) { if (!uid_valid(uid)) @@ -586,7 +591,6 @@ static int chown_common(struct path *path, uid_t user, gid_t group) if (!S_ISDIR(inode->i_mode)) newattrs.ia_valid |= ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV; -retry_deleg: mutex_lock(&inode->i_mutex); error = security_path_chown(path, uid, gid); if (!error) @@ -734,10 +738,10 @@ static int do_dentry_open(struct file *f, if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_inc(inode); if ((f->f_mode & FMODE_READ) && - likely(f->f_op->read || f->f_op->aio_read || f->f_op->read_iter)) + likely(f->f_op->read || f->f_op->read_iter)) f->f_mode |= FMODE_CAN_READ; if ((f->f_mode & FMODE_WRITE) && - likely(f->f_op->write || f->f_op->aio_write || f->f_op->write_iter)) + likely(f->f_op->write || f->f_op->write_iter)) f->f_mode |= FMODE_CAN_WRITE; f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC); @@ -988,9 +992,6 @@ struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt, return ERR_PTR(err); if (flags & O_CREAT) return ERR_PTR(-EINVAL); - if (!filename && (flags & O_DIRECTORY)) - if (!dentry->d_inode->i_op->lookup) - return ERR_PTR(-ENOTDIR); return do_file_open_root(dentry, mnt, filename, &op); } EXPORT_SYMBOL(file_open_root); diff --git a/fs/pipe.c b/fs/pipe.c index 21981e58e2a6..822da5b7cff0 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -21,7 +21,6 @@ #include <linux/audit.h> #include <linux/syscalls.h> #include <linux/fcntl.h> -#include <linux/aio.h> #include <asm/uaccess.h> #include <asm/ioctls.h> @@ -947,9 +946,7 @@ err: const struct file_operations pipefifo_fops = { .open = fifo_open, .llseek = no_llseek, - .read = new_sync_read, .read_iter = pipe_read, - .write = new_sync_write, .write_iter = pipe_write, .poll = pipe_poll, .unlocked_ioctl = pipe_ioctl, diff --git a/fs/pnode.c b/fs/pnode.c index 260ac8f898a4..6367e1e435c6 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -362,6 +362,46 @@ int propagate_mount_busy(struct mount *mnt, int refcnt) } /* + * Clear MNT_LOCKED when it can be shown to be safe. + * + * mount_lock lock must be held for write + */ +void propagate_mount_unlock(struct mount *mnt) +{ + struct mount *parent = mnt->mnt_parent; + struct mount *m, *child; + + BUG_ON(parent == mnt); + + for (m = propagation_next(parent, parent); m; + m = propagation_next(m, parent)) { + child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint); + if (child) + child->mnt.mnt_flags &= ~MNT_LOCKED; + } +} + +/* + * Mark all mounts that the MNT_LOCKED logic will allow to be unmounted. + */ +static void mark_umount_candidates(struct mount *mnt) +{ + struct mount *parent = mnt->mnt_parent; + struct mount *m; + + BUG_ON(parent == mnt); + + for (m = propagation_next(parent, parent); m; + m = propagation_next(m, parent)) { + struct mount *child = __lookup_mnt_last(&m->mnt, + mnt->mnt_mountpoint); + if (child && (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m))) { + SET_MNT_MARK(child); + } + } +} + +/* * NOTE: unmounting 'mnt' naturally propagates to all other mounts its * parent propagates to. */ @@ -378,13 +418,16 @@ static void __propagate_umount(struct mount *mnt) struct mount *child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint); /* - * umount the child only if the child has no - * other children + * umount the child only if the child has no children + * and the child is marked safe to unmount. */ - if (child && list_empty(&child->mnt_mounts)) { + if (!child || !IS_MNT_MARKED(child)) + continue; + CLEAR_MNT_MARK(child); + if (list_empty(&child->mnt_mounts)) { list_del_init(&child->mnt_child); - hlist_del_init_rcu(&child->mnt_hash); - hlist_add_before_rcu(&child->mnt_hash, &mnt->mnt_hash); + child->mnt.mnt_flags |= MNT_UMOUNT; + list_move_tail(&child->mnt_list, &mnt->mnt_list); } } } @@ -396,11 +439,14 @@ static void __propagate_umount(struct mount *mnt) * * vfsmount lock must be held for write */ -int propagate_umount(struct hlist_head *list) +int propagate_umount(struct list_head *list) { struct mount *mnt; - hlist_for_each_entry(mnt, list, mnt_hash) + list_for_each_entry_reverse(mnt, list, mnt_list) + mark_umount_candidates(mnt); + + list_for_each_entry(mnt, list, mnt_list) __propagate_umount(mnt); return 0; } diff --git a/fs/pnode.h b/fs/pnode.h index 4a246358b031..7114ce6e6b9e 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -19,6 +19,9 @@ #define IS_MNT_MARKED(m) ((m)->mnt.mnt_flags & MNT_MARKED) #define SET_MNT_MARK(m) ((m)->mnt.mnt_flags |= MNT_MARKED) #define CLEAR_MNT_MARK(m) ((m)->mnt.mnt_flags &= ~MNT_MARKED) +#define IS_MNT_LOCKED(m) ((m)->mnt.mnt_flags & MNT_LOCKED) +#define IS_MNT_LOCKED_AND_LAZY(m) \ + (((m)->mnt.mnt_flags & (MNT_LOCKED|MNT_SYNC_UMOUNT)) == MNT_LOCKED) #define CL_EXPIRE 0x01 #define CL_SLAVE 0x02 @@ -40,14 +43,14 @@ static inline void set_mnt_shared(struct mount *mnt) void change_mnt_propagation(struct mount *, int); int propagate_mnt(struct mount *, struct mountpoint *, struct mount *, struct hlist_head *); -int propagate_umount(struct hlist_head *); +int propagate_umount(struct list_head *); int propagate_mount_busy(struct mount *, int); +void propagate_mount_unlock(struct mount *); void mnt_release_group_id(struct mount *); int get_dominating_id(struct mount *mnt, const struct path *root); unsigned int mnt_get_count(struct mount *mnt); void mnt_set_mountpoint(struct mount *, struct mountpoint *, struct mount *); -void umount_tree(struct mount *, int); struct mount *copy_tree(struct mount *, struct dentry *, int); bool is_path_reachable(struct mount *, struct dentry *, const struct path *root); diff --git a/fs/proc/array.c b/fs/proc/array.c index 1295a00ca316..fd02a9ebfc30 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -99,8 +99,8 @@ static inline void task_name(struct seq_file *m, struct task_struct *p) buf = m->buf + m->count; /* Ignore error for now */ - string_escape_str(tcomm, &buf, m->size - m->count, - ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\"); + buf += string_escape_str(tcomm, buf, m->size - m->count, + ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\"); m->count = buf - m->buf; seq_putc(m, '\n'); @@ -188,6 +188,24 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns, from_kgid_munged(user_ns, GROUP_AT(group_info, g))); put_cred(cred); +#ifdef CONFIG_PID_NS + seq_puts(m, "\nNStgid:"); + for (g = ns->level; g <= pid->level; g++) + seq_printf(m, "\t%d", + task_tgid_nr_ns(p, pid->numbers[g].ns)); + seq_puts(m, "\nNSpid:"); + for (g = ns->level; g <= pid->level; g++) + seq_printf(m, "\t%d", + task_pid_nr_ns(p, pid->numbers[g].ns)); + seq_puts(m, "\nNSpgid:"); + for (g = ns->level; g <= pid->level; g++) + seq_printf(m, "\t%d", + task_pgrp_nr_ns(p, pid->numbers[g].ns)); + seq_puts(m, "\nNSsid:"); + for (g = ns->level; g <= pid->level; g++) + seq_printf(m, "\t%d", + task_session_nr_ns(p, pid->numbers[g].ns)); +#endif seq_putc(m, '\n'); } @@ -614,7 +632,9 @@ static int children_seq_show(struct seq_file *seq, void *v) pid_t pid; pid = pid_nr_ns(v, inode->i_sb->s_fs_info); - return seq_printf(seq, "%d ", pid); + seq_printf(seq, "%d ", pid); + + return 0; } static void *children_seq_start(struct seq_file *seq, loff_t *pos) diff --git a/fs/proc/base.c b/fs/proc/base.c index 3f3d7aeb0712..7a3b82f986dd 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -238,13 +238,15 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, wchan = get_wchan(task); - if (lookup_symbol_name(wchan, symname) < 0) + if (lookup_symbol_name(wchan, symname) < 0) { if (!ptrace_may_access(task, PTRACE_MODE_READ)) return 0; - else - return seq_printf(m, "%lu", wchan); - else - return seq_printf(m, "%s", symname); + seq_printf(m, "%lu", wchan); + } else { + seq_printf(m, "%s", symname); + } + + return 0; } #endif /* CONFIG_KALLSYMS */ @@ -309,10 +311,12 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { - return seq_printf(m, "%llu %llu %lu\n", - (unsigned long long)task->se.sum_exec_runtime, - (unsigned long long)task->sched_info.run_delay, - task->sched_info.pcount); + seq_printf(m, "%llu %llu %lu\n", + (unsigned long long)task->se.sum_exec_runtime, + (unsigned long long)task->sched_info.run_delay, + task->sched_info.pcount); + + return 0; } #endif @@ -387,7 +391,9 @@ static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns, points = oom_badness(task, NULL, NULL, totalpages) * 1000 / totalpages; read_unlock(&tasklist_lock); - return seq_printf(m, "%lu\n", points); + seq_printf(m, "%lu\n", points); + + return 0; } struct limit_names { @@ -432,15 +438,15 @@ static int proc_pid_limits(struct seq_file *m, struct pid_namespace *ns, * print the file header */ seq_printf(m, "%-25s %-20s %-20s %-10s\n", - "Limit", "Soft Limit", "Hard Limit", "Units"); + "Limit", "Soft Limit", "Hard Limit", "Units"); for (i = 0; i < RLIM_NLIMITS; i++) { if (rlim[i].rlim_cur == RLIM_INFINITY) seq_printf(m, "%-25s %-20s ", - lnames[i].name, "unlimited"); + lnames[i].name, "unlimited"); else seq_printf(m, "%-25s %-20lu ", - lnames[i].name, rlim[i].rlim_cur); + lnames[i].name, rlim[i].rlim_cur); if (rlim[i].rlim_max == RLIM_INFINITY) seq_printf(m, "%-20s ", "unlimited"); @@ -462,7 +468,9 @@ static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns, { long nr; unsigned long args[6], sp, pc; - int res = lock_trace(task); + int res; + + res = lock_trace(task); if (res) return res; @@ -477,7 +485,8 @@ static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns, args[0], args[1], args[2], args[3], args[4], args[5], sp, pc); unlock_trace(task); - return res; + + return 0; } #endif /* CONFIG_HAVE_ARCH_TRACEHOOK */ @@ -2002,12 +2011,13 @@ static int show_timer(struct seq_file *m, void *v) notify = timer->it_sigev_notify; seq_printf(m, "ID: %d\n", timer->it_id); - seq_printf(m, "signal: %d/%p\n", timer->sigq->info.si_signo, - timer->sigq->info.si_value.sival_ptr); + seq_printf(m, "signal: %d/%p\n", + timer->sigq->info.si_signo, + timer->sigq->info.si_value.sival_ptr); seq_printf(m, "notify: %s/%s.%d\n", - nstr[notify & ~SIGEV_THREAD_ID], - (notify & SIGEV_THREAD_ID) ? "tid" : "pid", - pid_nr_ns(timer->it_pid, tp->ns)); + nstr[notify & ~SIGEV_THREAD_ID], + (notify & SIGEV_THREAD_ID) ? "tid" : "pid", + pid_nr_ns(timer->it_pid, tp->ns)); seq_printf(m, "ClockID: %d\n", timer->it_clock); return 0; @@ -2352,21 +2362,23 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh unlock_task_sighand(task, &flags); } - result = seq_printf(m, - "rchar: %llu\n" - "wchar: %llu\n" - "syscr: %llu\n" - "syscw: %llu\n" - "read_bytes: %llu\n" - "write_bytes: %llu\n" - "cancelled_write_bytes: %llu\n", - (unsigned long long)acct.rchar, - (unsigned long long)acct.wchar, - (unsigned long long)acct.syscr, - (unsigned long long)acct.syscw, - (unsigned long long)acct.read_bytes, - (unsigned long long)acct.write_bytes, - (unsigned long long)acct.cancelled_write_bytes); + seq_printf(m, + "rchar: %llu\n" + "wchar: %llu\n" + "syscr: %llu\n" + "syscw: %llu\n" + "read_bytes: %llu\n" + "write_bytes: %llu\n" + "cancelled_write_bytes: %llu\n", + (unsigned long long)acct.rchar, + (unsigned long long)acct.wchar, + (unsigned long long)acct.syscr, + (unsigned long long)acct.syscw, + (unsigned long long)acct.read_bytes, + (unsigned long long)acct.write_bytes, + (unsigned long long)acct.cancelled_write_bytes); + result = 0; + out_unlock: mutex_unlock(&task->signal->cred_guard_mutex); return result; diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 8e5ad83b629a..af84ad04df77 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -8,6 +8,7 @@ #include <linux/security.h> #include <linux/file.h> #include <linux/seq_file.h> +#include <linux/fs.h> #include <linux/proc_fs.h> @@ -48,17 +49,23 @@ static int seq_show(struct seq_file *m, void *v) put_files_struct(files); } - if (!ret) { - seq_printf(m, "pos:\t%lli\nflags:\t0%o\nmnt_id:\t%i\n", - (long long)file->f_pos, f_flags, - real_mount(file->f_path.mnt)->mnt_id); - if (file->f_op->show_fdinfo) - file->f_op->show_fdinfo(m, file); - ret = seq_has_overflowed(m); - fput(file); - } + if (ret) + return ret; - return ret; + seq_printf(m, "pos:\t%lli\nflags:\t0%o\nmnt_id:\t%i\n", + (long long)file->f_pos, f_flags, + real_mount(file->f_path.mnt)->mnt_id); + + show_fd_locks(m, file, files); + if (seq_has_overflowed(m)) + goto out; + + if (file->f_op->show_fdinfo) + file->f_op->show_fdinfo(m, file); + +out: + fput(file); + return 0; } static int seq_fdinfo_open(struct inode *inode, struct file *file) diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index b32ce53d24ee..56e1ffda4d89 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -364,6 +364,9 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count, case PSTORE_TYPE_PMSG: scnprintf(name, sizeof(name), "pmsg-%s-%lld", psname, id); break; + case PSTORE_TYPE_PPC_OPAL: + sprintf(name, "powerpc-opal-%s-%lld", psname, id); + break; case PSTORE_TYPE_UNKNOWN: scnprintf(name, sizeof(name), "unknown-%s-%lld", psname, id); break; diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 39d1373128e9..44a549beeafa 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -539,6 +539,9 @@ static int ramoops_probe(struct platform_device *pdev) mem_address = pdata->mem_address; record_size = pdata->record_size; dump_oops = pdata->dump_oops; + ramoops_console_size = pdata->console_size; + ramoops_pmsg_size = pdata->pmsg_size; + ramoops_ftrace_size = pdata->ftrace_size; pr_info("attached 0x%lx@0x%llx, ecc: %d/%d\n", cxt->size, (unsigned long long)cxt->phys_addr, diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 0ccd4ba3a246..ecc25cf0ee6e 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -900,14 +900,17 @@ static inline struct dquot **i_dquot(struct inode *inode) static int dqinit_needed(struct inode *inode, int type) { + struct dquot * const *dquots; int cnt; if (IS_NOQUOTA(inode)) return 0; + + dquots = i_dquot(inode); if (type != -1) - return !i_dquot(inode)[type]; + return !dquots[type]; for (cnt = 0; cnt < MAXQUOTAS; cnt++) - if (!i_dquot(inode)[cnt]) + if (!dquots[cnt]) return 1; return 0; } @@ -970,12 +973,13 @@ static void add_dquot_ref(struct super_block *sb, int type) static void remove_inode_dquot_ref(struct inode *inode, int type, struct list_head *tofree_head) { - struct dquot *dquot = i_dquot(inode)[type]; + struct dquot **dquots = i_dquot(inode); + struct dquot *dquot = dquots[type]; - i_dquot(inode)[type] = NULL; if (!dquot) return; + dquots[type] = NULL; if (list_empty(&dquot->dq_free)) { /* * The inode still has reference to dquot so it can't be in the @@ -1159,8 +1163,8 @@ static int need_print_warning(struct dquot_warn *warn) return uid_eq(current_fsuid(), warn->w_dq_id.uid); case GRPQUOTA: return in_group_p(warn->w_dq_id.gid); - case PRJQUOTA: /* Never taken... Just make gcc happy */ - return 0; + case PRJQUOTA: + return 1; } return 0; } @@ -1389,16 +1393,21 @@ static int dquot_active(const struct inode *inode) static void __dquot_initialize(struct inode *inode, int type) { int cnt, init_needed = 0; - struct dquot *got[MAXQUOTAS]; + struct dquot **dquots, *got[MAXQUOTAS]; struct super_block *sb = inode->i_sb; qsize_t rsv; if (!dquot_active(inode)) return; + dquots = i_dquot(inode); + /* First get references to structures we might need. */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { struct kqid qid; + kprojid_t projid; + int rc; + got[cnt] = NULL; if (type != -1 && cnt != type) continue; @@ -1407,8 +1416,12 @@ static void __dquot_initialize(struct inode *inode, int type) * we check it without locking here to avoid unnecessary * dqget()/dqput() calls. */ - if (i_dquot(inode)[cnt]) + if (dquots[cnt]) + continue; + + if (!sb_has_quota_active(sb, cnt)) continue; + init_needed = 1; switch (cnt) { @@ -1418,6 +1431,12 @@ static void __dquot_initialize(struct inode *inode, int type) case GRPQUOTA: qid = make_kqid_gid(inode->i_gid); break; + case PRJQUOTA: + rc = inode->i_sb->dq_op->get_projid(inode, &projid); + if (rc) + continue; + qid = make_kqid_projid(projid); + break; } got[cnt] = dqget(sb, qid); } @@ -1438,8 +1457,8 @@ static void __dquot_initialize(struct inode *inode, int type) /* We could race with quotaon or dqget() could have failed */ if (!got[cnt]) continue; - if (!i_dquot(inode)[cnt]) { - i_dquot(inode)[cnt] = got[cnt]; + if (!dquots[cnt]) { + dquots[cnt] = got[cnt]; got[cnt] = NULL; /* * Make quota reservation system happy if someone @@ -1447,7 +1466,7 @@ static void __dquot_initialize(struct inode *inode, int type) */ rsv = inode_get_rsv_space(inode); if (unlikely(rsv)) - dquot_resv_space(i_dquot(inode)[cnt], rsv); + dquot_resv_space(dquots[cnt], rsv); } } out_err: @@ -1473,12 +1492,13 @@ EXPORT_SYMBOL(dquot_initialize); static void __dquot_drop(struct inode *inode) { int cnt; + struct dquot **dquots = i_dquot(inode); struct dquot *put[MAXQUOTAS]; spin_lock(&dq_data_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - put[cnt] = i_dquot(inode)[cnt]; - i_dquot(inode)[cnt] = NULL; + put[cnt] = dquots[cnt]; + dquots[cnt] = NULL; } spin_unlock(&dq_data_lock); dqput_all(put); @@ -1486,6 +1506,7 @@ static void __dquot_drop(struct inode *inode) void dquot_drop(struct inode *inode) { + struct dquot * const *dquots; int cnt; if (IS_NOQUOTA(inode)) @@ -1498,8 +1519,9 @@ void dquot_drop(struct inode *inode) * must assure that nobody can come after the DQUOT_DROP and * add quota pointers back anyway. */ + dquots = i_dquot(inode); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (i_dquot(inode)[cnt]) + if (dquots[cnt]) break; } @@ -1600,8 +1622,8 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) { int cnt, ret = 0, index; struct dquot_warn warn[MAXQUOTAS]; - struct dquot **dquots = i_dquot(inode); int reserve = flags & DQUOT_SPACE_RESERVE; + struct dquot **dquots; if (!dquot_active(inode)) { inode_incr_space(inode, number, reserve); @@ -1611,6 +1633,7 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) for (cnt = 0; cnt < MAXQUOTAS; cnt++) warn[cnt].w_type = QUOTA_NL_NOWARN; + dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); spin_lock(&dq_data_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { @@ -1652,13 +1675,14 @@ int dquot_alloc_inode(struct inode *inode) { int cnt, ret = 0, index; struct dquot_warn warn[MAXQUOTAS]; - struct dquot * const *dquots = i_dquot(inode); + struct dquot * const *dquots; if (!dquot_active(inode)) return 0; for (cnt = 0; cnt < MAXQUOTAS; cnt++) warn[cnt].w_type = QUOTA_NL_NOWARN; + dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); spin_lock(&dq_data_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { @@ -1690,6 +1714,7 @@ EXPORT_SYMBOL(dquot_alloc_inode); */ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) { + struct dquot **dquots; int cnt, index; if (!dquot_active(inode)) { @@ -1697,18 +1722,18 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) return 0; } + dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); spin_lock(&dq_data_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (i_dquot(inode)[cnt]) - dquot_claim_reserved_space(i_dquot(inode)[cnt], - number); + if (dquots[cnt]) + dquot_claim_reserved_space(dquots[cnt], number); } /* Update inode bytes */ inode_claim_rsv_space(inode, number); spin_unlock(&dq_data_lock); - mark_all_dquot_dirty(i_dquot(inode)); + mark_all_dquot_dirty(dquots); srcu_read_unlock(&dquot_srcu, index); return 0; } @@ -1719,6 +1744,7 @@ EXPORT_SYMBOL(dquot_claim_space_nodirty); */ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) { + struct dquot **dquots; int cnt, index; if (!dquot_active(inode)) { @@ -1726,18 +1752,18 @@ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) return; } + dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); spin_lock(&dq_data_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (i_dquot(inode)[cnt]) - dquot_reclaim_reserved_space(i_dquot(inode)[cnt], - number); + if (dquots[cnt]) + dquot_reclaim_reserved_space(dquots[cnt], number); } /* Update inode bytes */ inode_reclaim_rsv_space(inode, number); spin_unlock(&dq_data_lock); - mark_all_dquot_dirty(i_dquot(inode)); + mark_all_dquot_dirty(dquots); srcu_read_unlock(&dquot_srcu, index); return; } @@ -1750,7 +1776,7 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) { unsigned int cnt; struct dquot_warn warn[MAXQUOTAS]; - struct dquot **dquots = i_dquot(inode); + struct dquot **dquots; int reserve = flags & DQUOT_SPACE_RESERVE, index; if (!dquot_active(inode)) { @@ -1758,6 +1784,7 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) return; } + dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); spin_lock(&dq_data_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { @@ -1793,12 +1820,13 @@ void dquot_free_inode(struct inode *inode) { unsigned int cnt; struct dquot_warn warn[MAXQUOTAS]; - struct dquot * const *dquots = i_dquot(inode); + struct dquot * const *dquots; int index; if (!dquot_active(inode)) return; + dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); spin_lock(&dq_data_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { @@ -2161,7 +2189,8 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, error = -EROFS; goto out_fmt; } - if (!sb->s_op->quota_write || !sb->s_op->quota_read) { + if (!sb->s_op->quota_write || !sb->s_op->quota_read || + (type == PRJQUOTA && sb->dq_op->get_projid == NULL)) { error = -EINVAL; goto out_fmt; } @@ -2614,55 +2643,73 @@ out: EXPORT_SYMBOL(dquot_set_dqblk); /* Generic routine for getting common part of quota file information */ -int dquot_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii) +int dquot_get_state(struct super_block *sb, struct qc_state *state) { struct mem_dqinfo *mi; + struct qc_type_state *tstate; + struct quota_info *dqopt = sb_dqopt(sb); + int type; mutex_lock(&sb_dqopt(sb)->dqonoff_mutex); - if (!sb_has_quota_active(sb, type)) { - mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex); - return -ESRCH; + memset(state, 0, sizeof(*state)); + for (type = 0; type < MAXQUOTAS; type++) { + if (!sb_has_quota_active(sb, type)) + continue; + tstate = state->s_state + type; + mi = sb_dqopt(sb)->info + type; + tstate->flags = QCI_ACCT_ENABLED; + spin_lock(&dq_data_lock); + if (mi->dqi_flags & DQF_SYS_FILE) + tstate->flags |= QCI_SYSFILE; + if (mi->dqi_flags & DQF_ROOT_SQUASH) + tstate->flags |= QCI_ROOT_SQUASH; + if (sb_has_quota_limits_enabled(sb, type)) + tstate->flags |= QCI_LIMITS_ENFORCED; + tstate->spc_timelimit = mi->dqi_bgrace; + tstate->ino_timelimit = mi->dqi_igrace; + tstate->ino = dqopt->files[type]->i_ino; + tstate->blocks = dqopt->files[type]->i_blocks; + tstate->nextents = 1; /* We don't know... */ + spin_unlock(&dq_data_lock); } - mi = sb_dqopt(sb)->info + type; - spin_lock(&dq_data_lock); - ii->dqi_bgrace = mi->dqi_bgrace; - ii->dqi_igrace = mi->dqi_igrace; - ii->dqi_flags = mi->dqi_flags & DQF_GETINFO_MASK; - ii->dqi_valid = IIF_ALL; - spin_unlock(&dq_data_lock); mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex); return 0; } -EXPORT_SYMBOL(dquot_get_dqinfo); +EXPORT_SYMBOL(dquot_get_state); /* Generic routine for setting common part of quota file information */ -int dquot_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii) +int dquot_set_dqinfo(struct super_block *sb, int type, struct qc_info *ii) { struct mem_dqinfo *mi; int err = 0; + if ((ii->i_fieldmask & QC_WARNS_MASK) || + (ii->i_fieldmask & QC_RT_SPC_TIMER)) + return -EINVAL; mutex_lock(&sb_dqopt(sb)->dqonoff_mutex); if (!sb_has_quota_active(sb, type)) { err = -ESRCH; goto out; } mi = sb_dqopt(sb)->info + type; - if (ii->dqi_valid & IIF_FLAGS) { - if (ii->dqi_flags & ~DQF_SETINFO_MASK || - (ii->dqi_flags & DQF_ROOT_SQUASH && + if (ii->i_fieldmask & QC_FLAGS) { + if ((ii->i_flags & QCI_ROOT_SQUASH && mi->dqi_format->qf_fmt_id != QFMT_VFS_OLD)) { err = -EINVAL; goto out; } } spin_lock(&dq_data_lock); - if (ii->dqi_valid & IIF_BGRACE) - mi->dqi_bgrace = ii->dqi_bgrace; - if (ii->dqi_valid & IIF_IGRACE) - mi->dqi_igrace = ii->dqi_igrace; - if (ii->dqi_valid & IIF_FLAGS) - mi->dqi_flags = (mi->dqi_flags & ~DQF_SETINFO_MASK) | - (ii->dqi_flags & DQF_SETINFO_MASK); + if (ii->i_fieldmask & QC_SPC_TIMER) + mi->dqi_bgrace = ii->i_spc_timelimit; + if (ii->i_fieldmask & QC_INO_TIMER) + mi->dqi_igrace = ii->i_ino_timelimit; + if (ii->i_fieldmask & QC_FLAGS) { + if (ii->i_flags & QCI_ROOT_SQUASH) + mi->dqi_flags |= DQF_ROOT_SQUASH; + else + mi->dqi_flags &= ~DQF_ROOT_SQUASH; + } spin_unlock(&dq_data_lock); mark_info_dirty(sb, type); /* Force write to disk */ @@ -2677,7 +2724,7 @@ const struct quotactl_ops dquot_quotactl_ops = { .quota_on = dquot_quota_on, .quota_off = dquot_quota_off, .quota_sync = dquot_quota_sync, - .get_info = dquot_get_dqinfo, + .get_state = dquot_get_state, .set_info = dquot_set_dqinfo, .get_dqblk = dquot_get_dqblk, .set_dqblk = dquot_set_dqblk @@ -2688,7 +2735,7 @@ const struct quotactl_ops dquot_quotactl_sysfile_ops = { .quota_enable = dquot_quota_enable, .quota_disable = dquot_quota_disable, .quota_sync = dquot_quota_sync, - .get_info = dquot_get_dqinfo, + .get_state = dquot_get_state, .set_info = dquot_set_dqinfo, .get_dqblk = dquot_get_dqblk, .set_dqblk = dquot_set_dqblk diff --git a/fs/quota/quota.c b/fs/quota/quota.c index d14a799c7785..86ded7375c21 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -118,13 +118,30 @@ static int quota_getfmt(struct super_block *sb, int type, void __user *addr) static int quota_getinfo(struct super_block *sb, int type, void __user *addr) { - struct if_dqinfo info; + struct qc_state state; + struct qc_type_state *tstate; + struct if_dqinfo uinfo; int ret; - if (!sb->s_qcop->get_info) + /* This checks whether qc_state has enough entries... */ + BUILD_BUG_ON(MAXQUOTAS > XQM_MAXQUOTAS); + if (!sb->s_qcop->get_state) return -ENOSYS; - ret = sb->s_qcop->get_info(sb, type, &info); - if (!ret && copy_to_user(addr, &info, sizeof(info))) + ret = sb->s_qcop->get_state(sb, &state); + if (ret) + return ret; + tstate = state.s_state + type; + if (!(tstate->flags & QCI_ACCT_ENABLED)) + return -ESRCH; + memset(&uinfo, 0, sizeof(uinfo)); + uinfo.dqi_bgrace = tstate->spc_timelimit; + uinfo.dqi_igrace = tstate->ino_timelimit; + if (tstate->flags & QCI_SYSFILE) + uinfo.dqi_flags |= DQF_SYS_FILE; + if (tstate->flags & QCI_ROOT_SQUASH) + uinfo.dqi_flags |= DQF_ROOT_SQUASH; + uinfo.dqi_valid = IIF_ALL; + if (!ret && copy_to_user(addr, &uinfo, sizeof(uinfo))) return -EFAULT; return ret; } @@ -132,12 +149,31 @@ static int quota_getinfo(struct super_block *sb, int type, void __user *addr) static int quota_setinfo(struct super_block *sb, int type, void __user *addr) { struct if_dqinfo info; + struct qc_info qinfo; if (copy_from_user(&info, addr, sizeof(info))) return -EFAULT; if (!sb->s_qcop->set_info) return -ENOSYS; - return sb->s_qcop->set_info(sb, type, &info); + if (info.dqi_valid & ~(IIF_FLAGS | IIF_BGRACE | IIF_IGRACE)) + return -EINVAL; + memset(&qinfo, 0, sizeof(qinfo)); + if (info.dqi_valid & IIF_FLAGS) { + if (info.dqi_flags & ~DQF_SETINFO_MASK) + return -EINVAL; + if (info.dqi_flags & DQF_ROOT_SQUASH) + qinfo.i_flags |= QCI_ROOT_SQUASH; + qinfo.i_fieldmask |= QC_FLAGS; + } + if (info.dqi_valid & IIF_BGRACE) { + qinfo.i_spc_timelimit = info.dqi_bgrace; + qinfo.i_fieldmask |= QC_SPC_TIMER; + } + if (info.dqi_valid & IIF_IGRACE) { + qinfo.i_ino_timelimit = info.dqi_igrace; + qinfo.i_fieldmask |= QC_INO_TIMER; + } + return sb->s_qcop->set_info(sb, type, &qinfo); } static inline qsize_t qbtos(qsize_t blocks) @@ -252,25 +288,149 @@ static int quota_disable(struct super_block *sb, void __user *addr) return sb->s_qcop->quota_disable(sb, flags); } +static int quota_state_to_flags(struct qc_state *state) +{ + int flags = 0; + + if (state->s_state[USRQUOTA].flags & QCI_ACCT_ENABLED) + flags |= FS_QUOTA_UDQ_ACCT; + if (state->s_state[USRQUOTA].flags & QCI_LIMITS_ENFORCED) + flags |= FS_QUOTA_UDQ_ENFD; + if (state->s_state[GRPQUOTA].flags & QCI_ACCT_ENABLED) + flags |= FS_QUOTA_GDQ_ACCT; + if (state->s_state[GRPQUOTA].flags & QCI_LIMITS_ENFORCED) + flags |= FS_QUOTA_GDQ_ENFD; + if (state->s_state[PRJQUOTA].flags & QCI_ACCT_ENABLED) + flags |= FS_QUOTA_PDQ_ACCT; + if (state->s_state[PRJQUOTA].flags & QCI_LIMITS_ENFORCED) + flags |= FS_QUOTA_PDQ_ENFD; + return flags; +} + +static int quota_getstate(struct super_block *sb, struct fs_quota_stat *fqs) +{ + int type; + struct qc_state state; + int ret; + + ret = sb->s_qcop->get_state(sb, &state); + if (ret < 0) + return ret; + + memset(fqs, 0, sizeof(*fqs)); + fqs->qs_version = FS_QSTAT_VERSION; + fqs->qs_flags = quota_state_to_flags(&state); + /* No quota enabled? */ + if (!fqs->qs_flags) + return -ENOSYS; + fqs->qs_incoredqs = state.s_incoredqs; + /* + * GETXSTATE quotactl has space for just one set of time limits so + * report them for the first enabled quota type + */ + for (type = 0; type < XQM_MAXQUOTAS; type++) + if (state.s_state[type].flags & QCI_ACCT_ENABLED) + break; + BUG_ON(type == XQM_MAXQUOTAS); + fqs->qs_btimelimit = state.s_state[type].spc_timelimit; + fqs->qs_itimelimit = state.s_state[type].ino_timelimit; + fqs->qs_rtbtimelimit = state.s_state[type].rt_spc_timelimit; + fqs->qs_bwarnlimit = state.s_state[type].spc_warnlimit; + fqs->qs_iwarnlimit = state.s_state[type].ino_warnlimit; + if (state.s_state[USRQUOTA].flags & QCI_ACCT_ENABLED) { + fqs->qs_uquota.qfs_ino = state.s_state[USRQUOTA].ino; + fqs->qs_uquota.qfs_nblks = state.s_state[USRQUOTA].blocks; + fqs->qs_uquota.qfs_nextents = state.s_state[USRQUOTA].nextents; + } + if (state.s_state[GRPQUOTA].flags & QCI_ACCT_ENABLED) { + fqs->qs_gquota.qfs_ino = state.s_state[GRPQUOTA].ino; + fqs->qs_gquota.qfs_nblks = state.s_state[GRPQUOTA].blocks; + fqs->qs_gquota.qfs_nextents = state.s_state[GRPQUOTA].nextents; + } + if (state.s_state[PRJQUOTA].flags & QCI_ACCT_ENABLED) { + /* + * Q_XGETQSTAT doesn't have room for both group and project + * quotas. So, allow the project quota values to be copied out + * only if there is no group quota information available. + */ + if (!(state.s_state[GRPQUOTA].flags & QCI_ACCT_ENABLED)) { + fqs->qs_gquota.qfs_ino = state.s_state[PRJQUOTA].ino; + fqs->qs_gquota.qfs_nblks = + state.s_state[PRJQUOTA].blocks; + fqs->qs_gquota.qfs_nextents = + state.s_state[PRJQUOTA].nextents; + } + } + return 0; +} + static int quota_getxstate(struct super_block *sb, void __user *addr) { struct fs_quota_stat fqs; int ret; - if (!sb->s_qcop->get_xstate) + if (!sb->s_qcop->get_state) return -ENOSYS; - ret = sb->s_qcop->get_xstate(sb, &fqs); + ret = quota_getstate(sb, &fqs); if (!ret && copy_to_user(addr, &fqs, sizeof(fqs))) return -EFAULT; return ret; } +static int quota_getstatev(struct super_block *sb, struct fs_quota_statv *fqs) +{ + int type; + struct qc_state state; + int ret; + + ret = sb->s_qcop->get_state(sb, &state); + if (ret < 0) + return ret; + + memset(fqs, 0, sizeof(*fqs)); + fqs->qs_version = FS_QSTAT_VERSION; + fqs->qs_flags = quota_state_to_flags(&state); + /* No quota enabled? */ + if (!fqs->qs_flags) + return -ENOSYS; + fqs->qs_incoredqs = state.s_incoredqs; + /* + * GETXSTATV quotactl has space for just one set of time limits so + * report them for the first enabled quota type + */ + for (type = 0; type < XQM_MAXQUOTAS; type++) + if (state.s_state[type].flags & QCI_ACCT_ENABLED) + break; + BUG_ON(type == XQM_MAXQUOTAS); + fqs->qs_btimelimit = state.s_state[type].spc_timelimit; + fqs->qs_itimelimit = state.s_state[type].ino_timelimit; + fqs->qs_rtbtimelimit = state.s_state[type].rt_spc_timelimit; + fqs->qs_bwarnlimit = state.s_state[type].spc_warnlimit; + fqs->qs_iwarnlimit = state.s_state[type].ino_warnlimit; + if (state.s_state[USRQUOTA].flags & QCI_ACCT_ENABLED) { + fqs->qs_uquota.qfs_ino = state.s_state[USRQUOTA].ino; + fqs->qs_uquota.qfs_nblks = state.s_state[USRQUOTA].blocks; + fqs->qs_uquota.qfs_nextents = state.s_state[USRQUOTA].nextents; + } + if (state.s_state[GRPQUOTA].flags & QCI_ACCT_ENABLED) { + fqs->qs_gquota.qfs_ino = state.s_state[GRPQUOTA].ino; + fqs->qs_gquota.qfs_nblks = state.s_state[GRPQUOTA].blocks; + fqs->qs_gquota.qfs_nextents = state.s_state[GRPQUOTA].nextents; + } + if (state.s_state[PRJQUOTA].flags & QCI_ACCT_ENABLED) { + fqs->qs_pquota.qfs_ino = state.s_state[PRJQUOTA].ino; + fqs->qs_pquota.qfs_nblks = state.s_state[PRJQUOTA].blocks; + fqs->qs_pquota.qfs_nextents = state.s_state[PRJQUOTA].nextents; + } + return 0; +} + static int quota_getxstatev(struct super_block *sb, void __user *addr) { struct fs_quota_statv fqs; int ret; - if (!sb->s_qcop->get_xstatev) + if (!sb->s_qcop->get_state) return -ENOSYS; memset(&fqs, 0, sizeof(fqs)); @@ -284,7 +444,7 @@ static int quota_getxstatev(struct super_block *sb, void __user *addr) default: return -EINVAL; } - ret = sb->s_qcop->get_xstatev(sb, &fqs); + ret = quota_getstatev(sb, &fqs); if (!ret && copy_to_user(addr, &fqs, sizeof(fqs))) return -EFAULT; return ret; @@ -357,6 +517,30 @@ static void copy_from_xfs_dqblk(struct qc_dqblk *dst, struct fs_disk_quota *src) dst->d_fieldmask |= QC_RT_SPACE; } +static void copy_qcinfo_from_xfs_dqblk(struct qc_info *dst, + struct fs_disk_quota *src) +{ + memset(dst, 0, sizeof(*dst)); + dst->i_spc_timelimit = src->d_btimer; + dst->i_ino_timelimit = src->d_itimer; + dst->i_rt_spc_timelimit = src->d_rtbtimer; + dst->i_ino_warnlimit = src->d_iwarns; + dst->i_spc_warnlimit = src->d_bwarns; + dst->i_rt_spc_warnlimit = src->d_rtbwarns; + if (src->d_fieldmask & FS_DQ_BWARNS) + dst->i_fieldmask |= QC_SPC_WARNS; + if (src->d_fieldmask & FS_DQ_IWARNS) + dst->i_fieldmask |= QC_INO_WARNS; + if (src->d_fieldmask & FS_DQ_RTBWARNS) + dst->i_fieldmask |= QC_RT_SPC_WARNS; + if (src->d_fieldmask & FS_DQ_BTIMER) + dst->i_fieldmask |= QC_SPC_TIMER; + if (src->d_fieldmask & FS_DQ_ITIMER) + dst->i_fieldmask |= QC_INO_TIMER; + if (src->d_fieldmask & FS_DQ_RTBTIMER) + dst->i_fieldmask |= QC_RT_SPC_TIMER; +} + static int quota_setxquota(struct super_block *sb, int type, qid_t id, void __user *addr) { @@ -371,6 +555,21 @@ static int quota_setxquota(struct super_block *sb, int type, qid_t id, qid = make_kqid(current_user_ns(), type, id); if (!qid_valid(qid)) return -EINVAL; + /* Are we actually setting timer / warning limits for all users? */ + if (from_kqid(&init_user_ns, qid) == 0 && + fdq.d_fieldmask & (FS_DQ_WARNS_MASK | FS_DQ_TIMER_MASK)) { + struct qc_info qinfo; + int ret; + + if (!sb->s_qcop->set_info) + return -EINVAL; + copy_qcinfo_from_xfs_dqblk(&qinfo, &fdq); + ret = sb->s_qcop->set_info(sb, type, &qinfo); + if (ret) + return ret; + /* These are already done */ + fdq.d_fieldmask &= ~(FS_DQ_WARNS_MASK | FS_DQ_TIMER_MASK); + } copy_from_xfs_dqblk(&qdq, &fdq); return sb->s_qcop->set_dqblk(sb, qid, &qdq); } diff --git a/fs/quota/quota_tree.c b/fs/quota/quota_tree.c index d65877fbe8f4..58efb83dec1c 100644 --- a/fs/quota/quota_tree.c +++ b/fs/quota/quota_tree.c @@ -349,6 +349,13 @@ static inline int dq_insert_tree(struct qtree_mem_dqinfo *info, struct dquot *dquot) { int tmp = QT_TREEOFF; + +#ifdef __QUOTA_QT_PARANOIA + if (info->dqi_blocks <= QT_TREEOFF) { + quota_error(dquot->dq_sb, "Quota tree root isn't allocated!"); + return -EIO; + } +#endif return do_insert_tree(info, dquot, &tmp, 0); } diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c index 9cb10d7197f7..2aa012a68e90 100644 --- a/fs/quota/quota_v2.c +++ b/fs/quota/quota_v2.c @@ -117,12 +117,16 @@ static int v2_read_file_info(struct super_block *sb, int type) qinfo = info->dqi_priv; if (version == 0) { /* limits are stored as unsigned 32-bit data */ - info->dqi_max_spc_limit = 0xffffffffULL << QUOTABLOCK_BITS; + info->dqi_max_spc_limit = 0xffffffffLL << QUOTABLOCK_BITS; info->dqi_max_ino_limit = 0xffffffff; } else { - /* used space is stored as unsigned 64-bit value in bytes */ - info->dqi_max_spc_limit = 0xffffffffffffffffULL; /* 2^64-1 */ - info->dqi_max_ino_limit = 0xffffffffffffffffULL; + /* + * Used space is stored as unsigned 64-bit value in bytes but + * quota core supports only signed 64-bit values so use that + * as a limit + */ + info->dqi_max_spc_limit = 0x7fffffffffffffffLL; /* 2^63-1 */ + info->dqi_max_ino_limit = 0x7fffffffffffffffLL; } info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace); info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace); diff --git a/fs/quota/quotaio_v2.h b/fs/quota/quotaio_v2.h index f1966b42c2fd..4e95430093d9 100644 --- a/fs/quota/quotaio_v2.h +++ b/fs/quota/quotaio_v2.h @@ -13,12 +13,14 @@ */ #define V2_INITQMAGICS {\ 0xd9c01f11, /* USRQUOTA */\ - 0xd9c01927 /* GRPQUOTA */\ + 0xd9c01927, /* GRPQUOTA */\ + 0xd9c03f14, /* PRJQUOTA */\ } #define V2_INITQVERSIONS {\ 1, /* USRQUOTA */\ - 1 /* GRPQUOTA */\ + 1, /* GRPQUOTA */\ + 1, /* PRJQUOTA */\ } /* First generic header */ diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c index 4f56de822d2f..183a212694bf 100644 --- a/fs/ramfs/file-mmu.c +++ b/fs/ramfs/file-mmu.c @@ -31,9 +31,7 @@ #include "internal.h" const struct file_operations ramfs_file_operations = { - .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = new_sync_write, .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .fsync = noop_fsync, diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index f6ab41b39612..0b38befa69f3 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -44,9 +44,7 @@ const struct file_operations ramfs_file_operations = { .mmap_capabilities = ramfs_mmap_capabilities, .mmap = ramfs_nommu_mmap, .get_unmapped_area = ramfs_nommu_get_unmapped_area, - .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = new_sync_write, .write_iter = generic_file_write_iter, .fsync = noop_fsync, .splice_read = generic_file_splice_read, diff --git a/fs/read_write.c b/fs/read_write.c index 8e1b68786d66..819ef3faf1bb 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -9,7 +9,6 @@ #include <linux/fcntl.h> #include <linux/file.h> #include <linux/uio.h> -#include <linux/aio.h> #include <linux/fsnotify.h> #include <linux/security.h> #include <linux/export.h> @@ -23,13 +22,10 @@ #include <asm/unistd.h> typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *); -typedef ssize_t (*iov_fn_t)(struct kiocb *, const struct iovec *, - unsigned long, loff_t); typedef ssize_t (*iter_fn_t)(struct kiocb *, struct iov_iter *); const struct file_operations generic_ro_fops = { .llseek = generic_file_llseek, - .read = new_sync_read, .read_iter = generic_file_read_iter, .mmap = generic_file_readonly_mmap, .splice_read = generic_file_splice_read, @@ -343,13 +339,10 @@ ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos) init_sync_kiocb(&kiocb, file); kiocb.ki_pos = *ppos; - kiocb.ki_nbytes = iov_iter_count(iter); iter->type |= READ; ret = file->f_op->read_iter(&kiocb, iter); - if (ret == -EIOCBQUEUED) - ret = wait_on_sync_kiocb(&kiocb); - + BUG_ON(ret == -EIOCBQUEUED); if (ret > 0) *ppos = kiocb.ki_pos; return ret; @@ -366,13 +359,10 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos) init_sync_kiocb(&kiocb, file); kiocb.ki_pos = *ppos; - kiocb.ki_nbytes = iov_iter_count(iter); iter->type |= WRITE; ret = file->f_op->write_iter(&kiocb, iter); - if (ret == -EIOCBQUEUED) - ret = wait_on_sync_kiocb(&kiocb); - + BUG_ON(ret == -EIOCBQUEUED); if (ret > 0) *ppos = kiocb.ki_pos; return ret; @@ -418,26 +408,7 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t return count > MAX_RW_COUNT ? MAX_RW_COUNT : count; } -ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) -{ - struct iovec iov = { .iov_base = buf, .iov_len = len }; - struct kiocb kiocb; - ssize_t ret; - - init_sync_kiocb(&kiocb, filp); - kiocb.ki_pos = *ppos; - kiocb.ki_nbytes = len; - - ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); - *ppos = kiocb.ki_pos; - return ret; -} - -EXPORT_SYMBOL(do_sync_read); - -ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) +static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) { struct iovec iov = { .iov_base = buf, .iov_len = len }; struct kiocb kiocb; @@ -446,34 +417,25 @@ ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *p init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; - kiocb.ki_nbytes = len; iov_iter_init(&iter, READ, &iov, 1, len); ret = filp->f_op->read_iter(&kiocb, &iter); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); + BUG_ON(ret == -EIOCBQUEUED); *ppos = kiocb.ki_pos; return ret; } -EXPORT_SYMBOL(new_sync_read); - ssize_t __vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { - ssize_t ret; - if (file->f_op->read) - ret = file->f_op->read(file, buf, count, pos); - else if (file->f_op->aio_read) - ret = do_sync_read(file, buf, count, pos); + return file->f_op->read(file, buf, count, pos); else if (file->f_op->read_iter) - ret = new_sync_read(file, buf, count, pos); + return new_sync_read(file, buf, count, pos); else - ret = -EINVAL; - - return ret; + return -EINVAL; } +EXPORT_SYMBOL(__vfs_read); ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { @@ -502,26 +464,7 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) EXPORT_SYMBOL(vfs_read); -ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos) -{ - struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len }; - struct kiocb kiocb; - ssize_t ret; - - init_sync_kiocb(&kiocb, filp); - kiocb.ki_pos = *ppos; - kiocb.ki_nbytes = len; - - ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); - *ppos = kiocb.ki_pos; - return ret; -} - -EXPORT_SYMBOL(do_sync_write); - -ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos) +static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos) { struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len }; struct kiocb kiocb; @@ -530,17 +473,26 @@ ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, lo init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; - kiocb.ki_nbytes = len; iov_iter_init(&iter, WRITE, &iov, 1, len); ret = filp->f_op->write_iter(&kiocb, &iter); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); - *ppos = kiocb.ki_pos; + BUG_ON(ret == -EIOCBQUEUED); + if (ret > 0) + *ppos = kiocb.ki_pos; return ret; } -EXPORT_SYMBOL(new_sync_write); +ssize_t __vfs_write(struct file *file, const char __user *p, size_t count, + loff_t *pos) +{ + if (file->f_op->write) + return file->f_op->write(file, p, count, pos); + else if (file->f_op->write_iter) + return new_sync_write(file, p, count, pos); + else + return -EINVAL; +} +EXPORT_SYMBOL(__vfs_write); ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t *pos) { @@ -556,12 +508,7 @@ ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t p = (__force const char __user *)buf; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; - if (file->f_op->write) - ret = file->f_op->write(file, p, count, pos); - else if (file->f_op->aio_write) - ret = do_sync_write(file, p, count, pos); - else - ret = new_sync_write(file, p, count, pos); + ret = __vfs_write(file, p, count, pos); set_fs(old_fs); if (ret > 0) { fsnotify_modify(file); @@ -588,12 +535,7 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ if (ret >= 0) { count = ret; file_start_write(file); - if (file->f_op->write) - ret = file->f_op->write(file, buf, count, pos); - else if (file->f_op->aio_write) - ret = do_sync_write(file, buf, count, pos); - else - ret = new_sync_write(file, buf, count, pos); + ret = __vfs_write(file, buf, count, pos); if (ret > 0) { fsnotify_modify(file); add_wchar(current, ret); @@ -710,60 +652,32 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to) } EXPORT_SYMBOL(iov_shorten); -static ssize_t do_iter_readv_writev(struct file *filp, int rw, const struct iovec *iov, - unsigned long nr_segs, size_t len, loff_t *ppos, iter_fn_t fn) -{ - struct kiocb kiocb; - struct iov_iter iter; - ssize_t ret; - - init_sync_kiocb(&kiocb, filp); - kiocb.ki_pos = *ppos; - kiocb.ki_nbytes = len; - - iov_iter_init(&iter, rw, iov, nr_segs, len); - ret = fn(&kiocb, &iter); - if (ret == -EIOCBQUEUED) - ret = wait_on_sync_kiocb(&kiocb); - *ppos = kiocb.ki_pos; - return ret; -} - -static ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov, - unsigned long nr_segs, size_t len, loff_t *ppos, iov_fn_t fn) +static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, + loff_t *ppos, iter_fn_t fn) { struct kiocb kiocb; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; - kiocb.ki_nbytes = len; - ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos); - if (ret == -EIOCBQUEUED) - ret = wait_on_sync_kiocb(&kiocb); + ret = fn(&kiocb, iter); + BUG_ON(ret == -EIOCBQUEUED); *ppos = kiocb.ki_pos; return ret; } /* Do it by hand, with file-ops */ -static ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov, - unsigned long nr_segs, loff_t *ppos, io_fn_t fn) +static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, + loff_t *ppos, io_fn_t fn) { - struct iovec *vector = iov; ssize_t ret = 0; - while (nr_segs > 0) { - void __user *base; - size_t len; + while (iov_iter_count(iter)) { + struct iovec iovec = iov_iter_iovec(iter); ssize_t nr; - base = vector->iov_base; - len = vector->iov_len; - vector++; - nr_segs--; - - nr = fn(filp, base, len, ppos); + nr = fn(filp, iovec.iov_base, iovec.iov_len, ppos); if (nr < 0) { if (!ret) @@ -771,8 +685,9 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov, break; } ret += nr; - if (nr != len) + if (nr != iovec.iov_len) break; + iov_iter_advance(iter, nr); } return ret; @@ -863,48 +778,42 @@ static ssize_t do_readv_writev(int type, struct file *file, size_t tot_len; struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; + struct iov_iter iter; ssize_t ret; io_fn_t fn; - iov_fn_t fnv; iter_fn_t iter_fn; - ret = rw_copy_check_uvector(type, uvector, nr_segs, - ARRAY_SIZE(iovstack), iovstack, &iov); - if (ret <= 0) - goto out; + ret = import_iovec(type, uvector, nr_segs, + ARRAY_SIZE(iovstack), &iov, &iter); + if (ret < 0) + return ret; - tot_len = ret; + tot_len = iov_iter_count(&iter); + if (!tot_len) + goto out; ret = rw_verify_area(type, file, pos, tot_len); if (ret < 0) goto out; - fnv = NULL; if (type == READ) { fn = file->f_op->read; - fnv = file->f_op->aio_read; iter_fn = file->f_op->read_iter; } else { fn = (io_fn_t)file->f_op->write; - fnv = file->f_op->aio_write; iter_fn = file->f_op->write_iter; file_start_write(file); } if (iter_fn) - ret = do_iter_readv_writev(file, type, iov, nr_segs, tot_len, - pos, iter_fn); - else if (fnv) - ret = do_sync_readv_writev(file, iov, nr_segs, tot_len, - pos, fnv); + ret = do_iter_readv_writev(file, &iter, pos, iter_fn); else - ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn); + ret = do_loop_readv_writev(file, &iter, pos, fn); if (type != READ) file_end_write(file); out: - if (iov != iovstack) - kfree(iov); + kfree(iov); if ((ret + (type == READ)) > 0) { if (type == READ) fsnotify_access(file); @@ -1043,48 +952,42 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, compat_ssize_t tot_len; struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; + struct iov_iter iter; ssize_t ret; io_fn_t fn; - iov_fn_t fnv; iter_fn_t iter_fn; - ret = compat_rw_copy_check_uvector(type, uvector, nr_segs, - UIO_FASTIOV, iovstack, &iov); - if (ret <= 0) - goto out; + ret = compat_import_iovec(type, uvector, nr_segs, + UIO_FASTIOV, &iov, &iter); + if (ret < 0) + return ret; - tot_len = ret; + tot_len = iov_iter_count(&iter); + if (!tot_len) + goto out; ret = rw_verify_area(type, file, pos, tot_len); if (ret < 0) goto out; - fnv = NULL; if (type == READ) { fn = file->f_op->read; - fnv = file->f_op->aio_read; iter_fn = file->f_op->read_iter; } else { fn = (io_fn_t)file->f_op->write; - fnv = file->f_op->aio_write; iter_fn = file->f_op->write_iter; file_start_write(file); } if (iter_fn) - ret = do_iter_readv_writev(file, type, iov, nr_segs, tot_len, - pos, iter_fn); - else if (fnv) - ret = do_sync_readv_writev(file, iov, nr_segs, tot_len, - pos, fnv); + ret = do_iter_readv_writev(file, &iter, pos, iter_fn); else - ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn); + ret = do_loop_readv_writev(file, &iter, pos, fn); if (type != READ) file_end_write(file); out: - if (iov != iovstack) - kfree(iov); + kfree(iov); if ((ret + (type == READ)) > 0) { if (type == READ) fsnotify_access(file); diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 751dd3f4346b..96a1bcf33db4 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -243,8 +243,6 @@ drop_write_lock: } const struct file_operations reiserfs_file_operations = { - .read = new_sync_read, - .write = new_sync_write, .unlocked_ioctl = reiserfs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = reiserfs_compat_ioctl, diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index e72401e1f995..742242b60972 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -18,7 +18,7 @@ #include <linux/writeback.h> #include <linux/quotaops.h> #include <linux/swap.h> -#include <linux/aio.h> +#include <linux/uio.h> int reiserfs_commit_write(struct file *f, struct page *page, unsigned from, unsigned to); @@ -3278,22 +3278,22 @@ static int reiserfs_releasepage(struct page *page, gfp_t unused_gfp_flags) * We thank Mingming Cao for helping us understand in great detail what * to do in this section of the code. */ -static ssize_t reiserfs_direct_IO(int rw, struct kiocb *iocb, - struct iov_iter *iter, loff_t offset) +static ssize_t reiserfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, + ret = blockdev_direct_IO(iocb, inode, iter, offset, reiserfs_get_blocks_direct_io); /* * In case of error extending write may have instantiated a few * blocks outside i_size. Trim these off again. */ - if (unlikely((rw & WRITE) && ret < 0)) { + if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) { loff_t isize = i_size_read(inode); loff_t end = offset + count; diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index bb79cddf0a1f..2adcde137c3f 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -910,7 +910,6 @@ do { \ if (!(cond)) \ reiserfs_panic(NULL, "assertion failure", "(" #cond ") at " \ __FILE__ ":%i:%s: " format "\n", \ - in_interrupt() ? -1 : task_pid_nr(current), \ __LINE__, __func__ , ##args); \ } while (0) diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 71fbbe3e2dab..68b5f182984e 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -805,7 +805,7 @@ static const struct quotactl_ops reiserfs_qctl_operations = { .quota_on = reiserfs_quota_on, .quota_off = dquot_quota_off, .quota_sync = dquot_quota_sync, - .get_info = dquot_get_dqinfo, + .get_state = dquot_get_state, .set_info = dquot_set_dqinfo, .get_dqblk = dquot_get_dqblk, .set_dqblk = dquot_set_dqblk, diff --git a/fs/romfs/mmap-nommu.c b/fs/romfs/mmap-nommu.c index 7da9e2153953..1118a0dc6b45 100644 --- a/fs/romfs/mmap-nommu.c +++ b/fs/romfs/mmap-nommu.c @@ -81,7 +81,6 @@ static unsigned romfs_mmap_capabilities(struct file *file) const struct file_operations romfs_ro_fops = { .llseek = generic_file_llseek, - .read = new_sync_read, .read_iter = generic_file_read_iter, .splice_read = generic_file_splice_read, .mmap = romfs_mmap, diff --git a/fs/splice.c b/fs/splice.c index 7968da96bebb..476024bb6546 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -32,7 +32,6 @@ #include <linux/gfp.h> #include <linux/socket.h> #include <linux/compat.h> -#include <linux/aio.h> #include "internal.h" /* @@ -524,6 +523,9 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos, loff_t isize, left; int ret; + if (IS_DAX(in->f_mapping->host)) + return default_file_splice_read(in, ppos, pipe, len, flags); + isize = i_size_read(in->f_mapping->host); if (unlikely(*ppos >= isize)) return 0; @@ -1534,34 +1536,29 @@ static long vmsplice_to_user(struct file *file, const struct iovec __user *uiov, struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; - ssize_t count; pipe = get_pipe_info(file); if (!pipe) return -EBADF; - ret = rw_copy_check_uvector(READ, uiov, nr_segs, - ARRAY_SIZE(iovstack), iovstack, &iov); - if (ret <= 0) - goto out; - - count = ret; - iov_iter_init(&iter, READ, iov, nr_segs, count); + ret = import_iovec(READ, uiov, nr_segs, + ARRAY_SIZE(iovstack), &iov, &iter); + if (ret < 0) + return ret; + sd.total_len = iov_iter_count(&iter); sd.len = 0; - sd.total_len = count; sd.flags = flags; sd.u.data = &iter; sd.pos = 0; - pipe_lock(pipe); - ret = __splice_from_pipe(pipe, &sd, pipe_to_user); - pipe_unlock(pipe); - -out: - if (iov != iovstack) - kfree(iov); + if (sd.total_len) { + pipe_lock(pipe); + ret = __splice_from_pipe(pipe, &sd, pipe_to_user); + pipe_unlock(pipe); + } + kfree(iov); return ret; } diff --git a/fs/stat.c b/fs/stat.c index ae0c3cef9927..19636af5e75c 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -66,7 +66,7 @@ int vfs_getattr(struct path *path, struct kstat *stat) { int retval; - retval = security_inode_getattr(path->mnt, path->dentry); + retval = security_inode_getattr(path); if (retval) return retval; return vfs_getattr_nosec(path, stat); diff --git a/fs/super.c b/fs/super.c index 2b7dc90ccdbb..928c20f47af9 100644 --- a/fs/super.c +++ b/fs/super.c @@ -224,7 +224,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags) s->s_maxbytes = MAX_NON_LFS; s->s_op = &default_op; s->s_time_gran = 1000000000; - s->cleancache_poolid = -1; + s->cleancache_poolid = CLEANCACHE_NO_POOL; s->s_shrink.seeks = DEFAULT_SEEKS; s->s_shrink.scan_objects = super_cache_scan; diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index 2554d8835b48..b400c04371f0 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -41,7 +41,7 @@ static int create_files(struct kernfs_node *parent, struct kobject *kobj, if (grp->attrs) { for (i = 0, attr = grp->attrs; *attr && !error; i++, attr++) { - umode_t mode = 0; + umode_t mode = (*attr)->mode; /* * In update mode, we're changing the permissions or @@ -55,9 +55,14 @@ static int create_files(struct kernfs_node *parent, struct kobject *kobj, if (!mode) continue; } + + WARN(mode & ~(SYSFS_PREALLOC | 0664), + "Attribute %s: Invalid permissions 0%o\n", + (*attr)->name, mode); + + mode &= SYSFS_PREALLOC | 0664; error = sysfs_add_file_mode_ns(parent, *attr, false, - (*attr)->mode | mode, - NULL); + mode, NULL); if (unlikely(error)) break; } diff --git a/fs/sysv/file.c b/fs/sysv/file.c index b00811c75b24..a48e30410ad1 100644 --- a/fs/sysv/file.c +++ b/fs/sysv/file.c @@ -21,9 +21,7 @@ */ const struct file_operations sysv_file_operations = { .llseek = generic_file_llseek, - .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = new_sync_write, .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .fsync = generic_file_fsync, diff --git a/fs/tracefs/Makefile b/fs/tracefs/Makefile new file mode 100644 index 000000000000..82fa35b656c4 --- /dev/null +++ b/fs/tracefs/Makefile @@ -0,0 +1,4 @@ +tracefs-objs := inode.o + +obj-$(CONFIG_TRACING) += tracefs.o + diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c new file mode 100644 index 000000000000..d92bdf3b079a --- /dev/null +++ b/fs/tracefs/inode.c @@ -0,0 +1,650 @@ +/* + * inode.c - part of tracefs, a pseudo file system for activating tracing + * + * Based on debugfs by: Greg Kroah-Hartman <greg@kroah.com> + * + * Copyright (C) 2014 Red Hat Inc, author: Steven Rostedt <srostedt@redhat.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version + * 2 as published by the Free Software Foundation. + * + * tracefs is the file system that is used by the tracing infrastructure. + * + */ + +#include <linux/module.h> +#include <linux/fs.h> +#include <linux/mount.h> +#include <linux/kobject.h> +#include <linux/namei.h> +#include <linux/tracefs.h> +#include <linux/fsnotify.h> +#include <linux/seq_file.h> +#include <linux/parser.h> +#include <linux/magic.h> +#include <linux/slab.h> + +#define TRACEFS_DEFAULT_MODE 0700 + +static struct vfsmount *tracefs_mount; +static int tracefs_mount_count; +static bool tracefs_registered; + +static ssize_t default_read_file(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + return 0; +} + +static ssize_t default_write_file(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + return count; +} + +static const struct file_operations tracefs_file_operations = { + .read = default_read_file, + .write = default_write_file, + .open = simple_open, + .llseek = noop_llseek, +}; + +static struct tracefs_dir_ops { + int (*mkdir)(const char *name); + int (*rmdir)(const char *name); +} tracefs_ops; + +static char *get_dname(struct dentry *dentry) +{ + const char *dname; + char *name; + int len = dentry->d_name.len; + + dname = dentry->d_name.name; + name = kmalloc(len + 1, GFP_KERNEL); + if (!name) + return NULL; + memcpy(name, dname, len); + name[len] = 0; + return name; +} + +static int tracefs_syscall_mkdir(struct inode *inode, struct dentry *dentry, umode_t mode) +{ + char *name; + int ret; + + name = get_dname(dentry); + if (!name) + return -ENOMEM; + + /* + * The mkdir call can call the generic functions that create + * the files within the tracefs system. It is up to the individual + * mkdir routine to handle races. + */ + mutex_unlock(&inode->i_mutex); + ret = tracefs_ops.mkdir(name); + mutex_lock(&inode->i_mutex); + + kfree(name); + + return ret; +} + +static int tracefs_syscall_rmdir(struct inode *inode, struct dentry *dentry) +{ + char *name; + int ret; + + name = get_dname(dentry); + if (!name) + return -ENOMEM; + + /* + * The rmdir call can call the generic functions that create + * the files within the tracefs system. It is up to the individual + * rmdir routine to handle races. + * This time we need to unlock not only the parent (inode) but + * also the directory that is being deleted. + */ + mutex_unlock(&inode->i_mutex); + mutex_unlock(&dentry->d_inode->i_mutex); + + ret = tracefs_ops.rmdir(name); + + mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT); + mutex_lock(&dentry->d_inode->i_mutex); + + kfree(name); + + return ret; +} + +static const struct inode_operations tracefs_dir_inode_operations = { + .lookup = simple_lookup, + .mkdir = tracefs_syscall_mkdir, + .rmdir = tracefs_syscall_rmdir, +}; + +static struct inode *tracefs_get_inode(struct super_block *sb) +{ + struct inode *inode = new_inode(sb); + if (inode) { + inode->i_ino = get_next_ino(); + inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; + } + return inode; +} + +struct tracefs_mount_opts { + kuid_t uid; + kgid_t gid; + umode_t mode; +}; + +enum { + Opt_uid, + Opt_gid, + Opt_mode, + Opt_err +}; + +static const match_table_t tokens = { + {Opt_uid, "uid=%u"}, + {Opt_gid, "gid=%u"}, + {Opt_mode, "mode=%o"}, + {Opt_err, NULL} +}; + +struct tracefs_fs_info { + struct tracefs_mount_opts mount_opts; +}; + +static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts) +{ + substring_t args[MAX_OPT_ARGS]; + int option; + int token; + kuid_t uid; + kgid_t gid; + char *p; + + opts->mode = TRACEFS_DEFAULT_MODE; + + while ((p = strsep(&data, ",")) != NULL) { + if (!*p) + continue; + + token = match_token(p, tokens, args); + switch (token) { + case Opt_uid: + if (match_int(&args[0], &option)) + return -EINVAL; + uid = make_kuid(current_user_ns(), option); + if (!uid_valid(uid)) + return -EINVAL; + opts->uid = uid; + break; + case Opt_gid: + if (match_int(&args[0], &option)) + return -EINVAL; + gid = make_kgid(current_user_ns(), option); + if (!gid_valid(gid)) + return -EINVAL; + opts->gid = gid; + break; + case Opt_mode: + if (match_octal(&args[0], &option)) + return -EINVAL; + opts->mode = option & S_IALLUGO; + break; + /* + * We might like to report bad mount options here; + * but traditionally tracefs has ignored all mount options + */ + } + } + + return 0; +} + +static int tracefs_apply_options(struct super_block *sb) +{ + struct tracefs_fs_info *fsi = sb->s_fs_info; + struct inode *inode = sb->s_root->d_inode; + struct tracefs_mount_opts *opts = &fsi->mount_opts; + + inode->i_mode &= ~S_IALLUGO; + inode->i_mode |= opts->mode; + + inode->i_uid = opts->uid; + inode->i_gid = opts->gid; + + return 0; +} + +static int tracefs_remount(struct super_block *sb, int *flags, char *data) +{ + int err; + struct tracefs_fs_info *fsi = sb->s_fs_info; + + sync_filesystem(sb); + err = tracefs_parse_options(data, &fsi->mount_opts); + if (err) + goto fail; + + tracefs_apply_options(sb); + +fail: + return err; +} + +static int tracefs_show_options(struct seq_file *m, struct dentry *root) +{ + struct tracefs_fs_info *fsi = root->d_sb->s_fs_info; + struct tracefs_mount_opts *opts = &fsi->mount_opts; + + if (!uid_eq(opts->uid, GLOBAL_ROOT_UID)) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, opts->uid)); + if (!gid_eq(opts->gid, GLOBAL_ROOT_GID)) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, opts->gid)); + if (opts->mode != TRACEFS_DEFAULT_MODE) + seq_printf(m, ",mode=%o", opts->mode); + + return 0; +} + +static const struct super_operations tracefs_super_operations = { + .statfs = simple_statfs, + .remount_fs = tracefs_remount, + .show_options = tracefs_show_options, +}; + +static int trace_fill_super(struct super_block *sb, void *data, int silent) +{ + static struct tree_descr trace_files[] = {{""}}; + struct tracefs_fs_info *fsi; + int err; + + save_mount_options(sb, data); + + fsi = kzalloc(sizeof(struct tracefs_fs_info), GFP_KERNEL); + sb->s_fs_info = fsi; + if (!fsi) { + err = -ENOMEM; + goto fail; + } + + err = tracefs_parse_options(data, &fsi->mount_opts); + if (err) + goto fail; + + err = simple_fill_super(sb, TRACEFS_MAGIC, trace_files); + if (err) + goto fail; + + sb->s_op = &tracefs_super_operations; + + tracefs_apply_options(sb); + + return 0; + +fail: + kfree(fsi); + sb->s_fs_info = NULL; + return err; +} + +static struct dentry *trace_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, + void *data) +{ + return mount_single(fs_type, flags, data, trace_fill_super); +} + +static struct file_system_type trace_fs_type = { + .owner = THIS_MODULE, + .name = "tracefs", + .mount = trace_mount, + .kill_sb = kill_litter_super, +}; +MODULE_ALIAS_FS("tracefs"); + +static struct dentry *start_creating(const char *name, struct dentry *parent) +{ + struct dentry *dentry; + int error; + + pr_debug("tracefs: creating file '%s'\n",name); + + error = simple_pin_fs(&trace_fs_type, &tracefs_mount, + &tracefs_mount_count); + if (error) + return ERR_PTR(error); + + /* If the parent is not specified, we create it in the root. + * We need the root dentry to do this, which is in the super + * block. A pointer to that is in the struct vfsmount that we + * have around. + */ + if (!parent) + parent = tracefs_mount->mnt_root; + + mutex_lock(&parent->d_inode->i_mutex); + dentry = lookup_one_len(name, parent, strlen(name)); + if (!IS_ERR(dentry) && dentry->d_inode) { + dput(dentry); + dentry = ERR_PTR(-EEXIST); + } + if (IS_ERR(dentry)) + mutex_unlock(&parent->d_inode->i_mutex); + return dentry; +} + +static struct dentry *failed_creating(struct dentry *dentry) +{ + mutex_unlock(&dentry->d_parent->d_inode->i_mutex); + dput(dentry); + simple_release_fs(&tracefs_mount, &tracefs_mount_count); + return NULL; +} + +static struct dentry *end_creating(struct dentry *dentry) +{ + mutex_unlock(&dentry->d_parent->d_inode->i_mutex); + return dentry; +} + +/** + * tracefs_create_file - create a file in the tracefs filesystem + * @name: a pointer to a string containing the name of the file to create. + * @mode: the permission that the file should have. + * @parent: a pointer to the parent dentry for this file. This should be a + * directory dentry if set. If this parameter is NULL, then the + * file will be created in the root of the tracefs filesystem. + * @data: a pointer to something that the caller will want to get to later + * on. The inode.i_private pointer will point to this value on + * the open() call. + * @fops: a pointer to a struct file_operations that should be used for + * this file. + * + * This is the basic "create a file" function for tracefs. It allows for a + * wide range of flexibility in creating a file, or a directory (if you want + * to create a directory, the tracefs_create_dir() function is + * recommended to be used instead.) + * + * This function will return a pointer to a dentry if it succeeds. This + * pointer must be passed to the tracefs_remove() function when the file is + * to be removed (no automatic cleanup happens if your module is unloaded, + * you are responsible here.) If an error occurs, %NULL will be returned. + * + * If tracefs is not enabled in the kernel, the value -%ENODEV will be + * returned. + */ +struct dentry *tracefs_create_file(const char *name, umode_t mode, + struct dentry *parent, void *data, + const struct file_operations *fops) +{ + struct dentry *dentry; + struct inode *inode; + + if (!(mode & S_IFMT)) + mode |= S_IFREG; + BUG_ON(!S_ISREG(mode)); + dentry = start_creating(name, parent); + + if (IS_ERR(dentry)) + return NULL; + + inode = tracefs_get_inode(dentry->d_sb); + if (unlikely(!inode)) + return failed_creating(dentry); + + inode->i_mode = mode; + inode->i_fop = fops ? fops : &tracefs_file_operations; + inode->i_private = data; + d_instantiate(dentry, inode); + fsnotify_create(dentry->d_parent->d_inode, dentry); + return end_creating(dentry); +} + +static struct dentry *__create_dir(const char *name, struct dentry *parent, + const struct inode_operations *ops) +{ + struct dentry *dentry = start_creating(name, parent); + struct inode *inode; + + if (IS_ERR(dentry)) + return NULL; + + inode = tracefs_get_inode(dentry->d_sb); + if (unlikely(!inode)) + return failed_creating(dentry); + + inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; + inode->i_op = ops; + inode->i_fop = &simple_dir_operations; + + /* directory inodes start off with i_nlink == 2 (for "." entry) */ + inc_nlink(inode); + d_instantiate(dentry, inode); + inc_nlink(dentry->d_parent->d_inode); + fsnotify_mkdir(dentry->d_parent->d_inode, dentry); + return end_creating(dentry); +} + +/** + * tracefs_create_dir - create a directory in the tracefs filesystem + * @name: a pointer to a string containing the name of the directory to + * create. + * @parent: a pointer to the parent dentry for this file. This should be a + * directory dentry if set. If this parameter is NULL, then the + * directory will be created in the root of the tracefs filesystem. + * + * This function creates a directory in tracefs with the given name. + * + * This function will return a pointer to a dentry if it succeeds. This + * pointer must be passed to the tracefs_remove() function when the file is + * to be removed. If an error occurs, %NULL will be returned. + * + * If tracing is not enabled in the kernel, the value -%ENODEV will be + * returned. + */ +struct dentry *tracefs_create_dir(const char *name, struct dentry *parent) +{ + return __create_dir(name, parent, &simple_dir_inode_operations); +} + +/** + * tracefs_create_instance_dir - create the tracing instances directory + * @name: The name of the instances directory to create + * @parent: The parent directory that the instances directory will exist + * @mkdir: The function to call when a mkdir is performed. + * @rmdir: The function to call when a rmdir is performed. + * + * Only one instances directory is allowed. + * + * The instances directory is special as it allows for mkdir and rmdir to + * to be done by userspace. When a mkdir or rmdir is performed, the inode + * locks are released and the methhods passed in (@mkdir and @rmdir) are + * called without locks and with the name of the directory being created + * within the instances directory. + * + * Returns the dentry of the instances directory. + */ +struct dentry *tracefs_create_instance_dir(const char *name, struct dentry *parent, + int (*mkdir)(const char *name), + int (*rmdir)(const char *name)) +{ + struct dentry *dentry; + + /* Only allow one instance of the instances directory. */ + if (WARN_ON(tracefs_ops.mkdir || tracefs_ops.rmdir)) + return NULL; + + dentry = __create_dir(name, parent, &tracefs_dir_inode_operations); + if (!dentry) + return NULL; + + tracefs_ops.mkdir = mkdir; + tracefs_ops.rmdir = rmdir; + + return dentry; +} + +static inline int tracefs_positive(struct dentry *dentry) +{ + return dentry->d_inode && !d_unhashed(dentry); +} + +static int __tracefs_remove(struct dentry *dentry, struct dentry *parent) +{ + int ret = 0; + + if (tracefs_positive(dentry)) { + if (dentry->d_inode) { + dget(dentry); + switch (dentry->d_inode->i_mode & S_IFMT) { + case S_IFDIR: + ret = simple_rmdir(parent->d_inode, dentry); + break; + default: + simple_unlink(parent->d_inode, dentry); + break; + } + if (!ret) + d_delete(dentry); + dput(dentry); + } + } + return ret; +} + +/** + * tracefs_remove - removes a file or directory from the tracefs filesystem + * @dentry: a pointer to a the dentry of the file or directory to be + * removed. + * + * This function removes a file or directory in tracefs that was previously + * created with a call to another tracefs function (like + * tracefs_create_file() or variants thereof.) + */ +void tracefs_remove(struct dentry *dentry) +{ + struct dentry *parent; + int ret; + + if (IS_ERR_OR_NULL(dentry)) + return; + + parent = dentry->d_parent; + if (!parent || !parent->d_inode) + return; + + mutex_lock(&parent->d_inode->i_mutex); + ret = __tracefs_remove(dentry, parent); + mutex_unlock(&parent->d_inode->i_mutex); + if (!ret) + simple_release_fs(&tracefs_mount, &tracefs_mount_count); +} + +/** + * tracefs_remove_recursive - recursively removes a directory + * @dentry: a pointer to a the dentry of the directory to be removed. + * + * This function recursively removes a directory tree in tracefs that + * was previously created with a call to another tracefs function + * (like tracefs_create_file() or variants thereof.) + */ +void tracefs_remove_recursive(struct dentry *dentry) +{ + struct dentry *child, *parent; + + if (IS_ERR_OR_NULL(dentry)) + return; + + parent = dentry->d_parent; + if (!parent || !parent->d_inode) + return; + + parent = dentry; + down: + mutex_lock(&parent->d_inode->i_mutex); + loop: + /* + * The parent->d_subdirs is protected by the d_lock. Outside that + * lock, the child can be unlinked and set to be freed which can + * use the d_u.d_child as the rcu head and corrupt this list. + */ + spin_lock(&parent->d_lock); + list_for_each_entry(child, &parent->d_subdirs, d_child) { + if (!tracefs_positive(child)) + continue; + + /* perhaps simple_empty(child) makes more sense */ + if (!list_empty(&child->d_subdirs)) { + spin_unlock(&parent->d_lock); + mutex_unlock(&parent->d_inode->i_mutex); + parent = child; + goto down; + } + + spin_unlock(&parent->d_lock); + + if (!__tracefs_remove(child, parent)) + simple_release_fs(&tracefs_mount, &tracefs_mount_count); + + /* + * The parent->d_lock protects agaist child from unlinking + * from d_subdirs. When releasing the parent->d_lock we can + * no longer trust that the next pointer is valid. + * Restart the loop. We'll skip this one with the + * tracefs_positive() check. + */ + goto loop; + } + spin_unlock(&parent->d_lock); + + mutex_unlock(&parent->d_inode->i_mutex); + child = parent; + parent = parent->d_parent; + mutex_lock(&parent->d_inode->i_mutex); + + if (child != dentry) + /* go up */ + goto loop; + + if (!__tracefs_remove(child, parent)) + simple_release_fs(&tracefs_mount, &tracefs_mount_count); + mutex_unlock(&parent->d_inode->i_mutex); +} + +/** + * tracefs_initialized - Tells whether tracefs has been registered + */ +bool tracefs_initialized(void) +{ + return tracefs_registered; +} + +static struct kobject *trace_kobj; + +static int __init tracefs_init(void) +{ + int retval; + + trace_kobj = kobject_create_and_add("tracing", kernel_kobj); + if (!trace_kobj) + return -EINVAL; + + retval = register_filesystem(&trace_fs_type); + if (!retval) + tracefs_registered = true; + + return retval; +} +core_initcall(tracefs_init); diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c index eb997e9c4ab0..11a11b32a2a9 100644 --- a/fs/ubifs/budget.c +++ b/fs/ubifs/budget.c @@ -509,7 +509,7 @@ again: c->bi.nospace_rp = 1; smp_wmb(); } else - ubifs_err("cannot budget space, error %d", err); + ubifs_err(c, "cannot budget space, error %d", err); return err; } diff --git a/fs/ubifs/commit.c b/fs/ubifs/commit.c index 26b69b2d4a45..63f56619991d 100644 --- a/fs/ubifs/commit.c +++ b/fs/ubifs/commit.c @@ -225,7 +225,7 @@ out_cancel: out_up: up_write(&c->commit_sem); out: - ubifs_err("commit failed, error %d", err); + ubifs_err(c, "commit failed, error %d", err); spin_lock(&c->cs_lock); c->cmt_state = COMMIT_BROKEN; wake_up(&c->cmt_wq); @@ -289,7 +289,7 @@ int ubifs_bg_thread(void *info) int err; struct ubifs_info *c = info; - ubifs_msg("background thread \"%s\" started, PID %d", + ubifs_msg(c, "background thread \"%s\" started, PID %d", c->bgt_name, current->pid); set_freezable(); @@ -324,7 +324,7 @@ int ubifs_bg_thread(void *info) cond_resched(); } - ubifs_msg("background thread \"%s\" stops", c->bgt_name); + ubifs_msg(c, "background thread \"%s\" stops", c->bgt_name); return 0; } @@ -712,13 +712,13 @@ out: return 0; out_dump: - ubifs_err("dumping index node (iip=%d)", i->iip); + ubifs_err(c, "dumping index node (iip=%d)", i->iip); ubifs_dump_node(c, idx); list_del(&i->list); kfree(i); if (!list_empty(&list)) { i = list_entry(list.prev, struct idx_node, list); - ubifs_err("dumping parent index node"); + ubifs_err(c, "dumping parent index node"); ubifs_dump_node(c, &i->idx); } out_free: @@ -727,7 +727,7 @@ out_free: list_del(&i->list); kfree(i); } - ubifs_err("failed, error %d", err); + ubifs_err(c, "failed, error %d", err); if (err > 0) err = -EINVAL; return err; diff --git a/fs/ubifs/compress.c b/fs/ubifs/compress.c index 2bfa0953335d..565cb56d7225 100644 --- a/fs/ubifs/compress.c +++ b/fs/ubifs/compress.c @@ -92,8 +92,8 @@ struct ubifs_compressor *ubifs_compressors[UBIFS_COMPR_TYPES_CNT]; * Note, if the input buffer was not compressed, it is copied to the output * buffer and %UBIFS_COMPR_NONE is returned in @compr_type. */ -void ubifs_compress(const void *in_buf, int in_len, void *out_buf, int *out_len, - int *compr_type) +void ubifs_compress(const struct ubifs_info *c, const void *in_buf, + int in_len, void *out_buf, int *out_len, int *compr_type) { int err; struct ubifs_compressor *compr = ubifs_compressors[*compr_type]; @@ -112,9 +112,9 @@ void ubifs_compress(const void *in_buf, int in_len, void *out_buf, int *out_len, if (compr->comp_mutex) mutex_unlock(compr->comp_mutex); if (unlikely(err)) { - ubifs_warn("cannot compress %d bytes, compressor %s, error %d, leave data uncompressed", + ubifs_warn(c, "cannot compress %d bytes, compressor %s, error %d, leave data uncompressed", in_len, compr->name, err); - goto no_compr; + goto no_compr; } /* @@ -144,21 +144,21 @@ no_compr: * The length of the uncompressed data is returned in @out_len. This functions * returns %0 on success or a negative error code on failure. */ -int ubifs_decompress(const void *in_buf, int in_len, void *out_buf, - int *out_len, int compr_type) +int ubifs_decompress(const struct ubifs_info *c, const void *in_buf, + int in_len, void *out_buf, int *out_len, int compr_type) { int err; struct ubifs_compressor *compr; if (unlikely(compr_type < 0 || compr_type >= UBIFS_COMPR_TYPES_CNT)) { - ubifs_err("invalid compression type %d", compr_type); + ubifs_err(c, "invalid compression type %d", compr_type); return -EINVAL; } compr = ubifs_compressors[compr_type]; if (unlikely(!compr->capi_name)) { - ubifs_err("%s compression is not compiled in", compr->name); + ubifs_err(c, "%s compression is not compiled in", compr->name); return -EINVAL; } @@ -175,7 +175,7 @@ int ubifs_decompress(const void *in_buf, int in_len, void *out_buf, if (compr->decomp_mutex) mutex_unlock(compr->decomp_mutex); if (err) - ubifs_err("cannot decompress %d bytes, compressor %s, error %d", + ubifs_err(c, "cannot decompress %d bytes, compressor %s, error %d", in_len, compr->name, err); return err; @@ -193,8 +193,8 @@ static int __init compr_init(struct ubifs_compressor *compr) if (compr->capi_name) { compr->cc = crypto_alloc_comp(compr->capi_name, 0, 0); if (IS_ERR(compr->cc)) { - ubifs_err("cannot initialize compressor %s, error %ld", - compr->name, PTR_ERR(compr->cc)); + pr_err("UBIFS error (pid %d): cannot initialize compressor %s, error %ld", + current->pid, compr->name, PTR_ERR(compr->cc)); return PTR_ERR(compr->cc); } } diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index 4cfb3e82c56f..4c46a9865fa7 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -746,7 +746,7 @@ void ubifs_dump_lprops(struct ubifs_info *c) for (lnum = c->main_first; lnum < c->leb_cnt; lnum++) { err = ubifs_read_one_lp(c, lnum, &lp); if (err) { - ubifs_err("cannot read lprops for LEB %d", lnum); + ubifs_err(c, "cannot read lprops for LEB %d", lnum); continue; } @@ -819,13 +819,13 @@ void ubifs_dump_leb(const struct ubifs_info *c, int lnum) buf = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL); if (!buf) { - ubifs_err("cannot allocate memory for dumping LEB %d", lnum); + ubifs_err(c, "cannot allocate memory for dumping LEB %d", lnum); return; } sleb = ubifs_scan(c, lnum, 0, buf, 0); if (IS_ERR(sleb)) { - ubifs_err("scan error %d", (int)PTR_ERR(sleb)); + ubifs_err(c, "scan error %d", (int)PTR_ERR(sleb)); goto out; } @@ -1032,7 +1032,7 @@ int dbg_check_space_info(struct ubifs_info *c) spin_unlock(&c->space_lock); if (free != d->saved_free) { - ubifs_err("free space changed from %lld to %lld", + ubifs_err(c, "free space changed from %lld to %lld", d->saved_free, free); goto out; } @@ -1040,15 +1040,15 @@ int dbg_check_space_info(struct ubifs_info *c) return 0; out: - ubifs_msg("saved lprops statistics dump"); + ubifs_msg(c, "saved lprops statistics dump"); ubifs_dump_lstats(&d->saved_lst); - ubifs_msg("saved budgeting info dump"); + ubifs_msg(c, "saved budgeting info dump"); ubifs_dump_budg(c, &d->saved_bi); - ubifs_msg("saved idx_gc_cnt %d", d->saved_idx_gc_cnt); - ubifs_msg("current lprops statistics dump"); + ubifs_msg(c, "saved idx_gc_cnt %d", d->saved_idx_gc_cnt); + ubifs_msg(c, "current lprops statistics dump"); ubifs_get_lp_stats(c, &lst); ubifs_dump_lstats(&lst); - ubifs_msg("current budgeting info dump"); + ubifs_msg(c, "current budgeting info dump"); ubifs_dump_budg(c, &c->bi); dump_stack(); return -EINVAL; @@ -1077,9 +1077,9 @@ int dbg_check_synced_i_size(const struct ubifs_info *c, struct inode *inode) mutex_lock(&ui->ui_mutex); spin_lock(&ui->ui_lock); if (ui->ui_size != ui->synced_i_size && !ui->dirty) { - ubifs_err("ui_size is %lld, synced_i_size is %lld, but inode is clean", + ubifs_err(c, "ui_size is %lld, synced_i_size is %lld, but inode is clean", ui->ui_size, ui->synced_i_size); - ubifs_err("i_ino %lu, i_mode %#x, i_size %lld", inode->i_ino, + ubifs_err(c, "i_ino %lu, i_mode %#x, i_size %lld", inode->i_ino, inode->i_mode, i_size_read(inode)); dump_stack(); err = -EINVAL; @@ -1140,7 +1140,7 @@ int dbg_check_dir(struct ubifs_info *c, const struct inode *dir) kfree(pdent); if (i_size_read(dir) != size) { - ubifs_err("directory inode %lu has size %llu, but calculated size is %llu", + ubifs_err(c, "directory inode %lu has size %llu, but calculated size is %llu", dir->i_ino, (unsigned long long)i_size_read(dir), (unsigned long long)size); ubifs_dump_inode(c, dir); @@ -1148,7 +1148,7 @@ int dbg_check_dir(struct ubifs_info *c, const struct inode *dir) return -EINVAL; } if (dir->i_nlink != nlink) { - ubifs_err("directory inode %lu has nlink %u, but calculated nlink is %u", + ubifs_err(c, "directory inode %lu has nlink %u, but calculated nlink is %u", dir->i_ino, dir->i_nlink, nlink); ubifs_dump_inode(c, dir); dump_stack(); @@ -1207,10 +1207,10 @@ static int dbg_check_key_order(struct ubifs_info *c, struct ubifs_zbranch *zbr1, err = 1; key_read(c, &dent1->key, &key); if (keys_cmp(c, &zbr1->key, &key)) { - ubifs_err("1st entry at %d:%d has key %s", zbr1->lnum, + ubifs_err(c, "1st entry at %d:%d has key %s", zbr1->lnum, zbr1->offs, dbg_snprintf_key(c, &key, key_buf, DBG_KEY_BUF_LEN)); - ubifs_err("but it should have key %s according to tnc", + ubifs_err(c, "but it should have key %s according to tnc", dbg_snprintf_key(c, &zbr1->key, key_buf, DBG_KEY_BUF_LEN)); ubifs_dump_node(c, dent1); @@ -1219,10 +1219,10 @@ static int dbg_check_key_order(struct ubifs_info *c, struct ubifs_zbranch *zbr1, key_read(c, &dent2->key, &key); if (keys_cmp(c, &zbr2->key, &key)) { - ubifs_err("2nd entry at %d:%d has key %s", zbr1->lnum, + ubifs_err(c, "2nd entry at %d:%d has key %s", zbr1->lnum, zbr1->offs, dbg_snprintf_key(c, &key, key_buf, DBG_KEY_BUF_LEN)); - ubifs_err("but it should have key %s according to tnc", + ubifs_err(c, "but it should have key %s according to tnc", dbg_snprintf_key(c, &zbr2->key, key_buf, DBG_KEY_BUF_LEN)); ubifs_dump_node(c, dent2); @@ -1238,14 +1238,14 @@ static int dbg_check_key_order(struct ubifs_info *c, struct ubifs_zbranch *zbr1, goto out_free; } if (cmp == 0 && nlen1 == nlen2) - ubifs_err("2 xent/dent nodes with the same name"); + ubifs_err(c, "2 xent/dent nodes with the same name"); else - ubifs_err("bad order of colliding key %s", + ubifs_err(c, "bad order of colliding key %s", dbg_snprintf_key(c, &key, key_buf, DBG_KEY_BUF_LEN)); - ubifs_msg("first node at %d:%d\n", zbr1->lnum, zbr1->offs); + ubifs_msg(c, "first node at %d:%d\n", zbr1->lnum, zbr1->offs); ubifs_dump_node(c, dent1); - ubifs_msg("second node at %d:%d\n", zbr2->lnum, zbr2->offs); + ubifs_msg(c, "second node at %d:%d\n", zbr2->lnum, zbr2->offs); ubifs_dump_node(c, dent2); out_free: @@ -1447,11 +1447,11 @@ static int dbg_check_znode(struct ubifs_info *c, struct ubifs_zbranch *zbr) return 0; out: - ubifs_err("failed, error %d", err); - ubifs_msg("dump of the znode"); + ubifs_err(c, "failed, error %d", err); + ubifs_msg(c, "dump of the znode"); ubifs_dump_znode(c, znode); if (zp) { - ubifs_msg("dump of the parent znode"); + ubifs_msg(c, "dump of the parent znode"); ubifs_dump_znode(c, zp); } dump_stack(); @@ -1518,9 +1518,9 @@ int dbg_check_tnc(struct ubifs_info *c, int extra) if (err < 0) return err; if (err) { - ubifs_msg("first znode"); + ubifs_msg(c, "first znode"); ubifs_dump_znode(c, prev); - ubifs_msg("second znode"); + ubifs_msg(c, "second znode"); ubifs_dump_znode(c, znode); return -EINVAL; } @@ -1529,13 +1529,13 @@ int dbg_check_tnc(struct ubifs_info *c, int extra) if (extra) { if (clean_cnt != atomic_long_read(&c->clean_zn_cnt)) { - ubifs_err("incorrect clean_zn_cnt %ld, calculated %ld", + ubifs_err(c, "incorrect clean_zn_cnt %ld, calculated %ld", atomic_long_read(&c->clean_zn_cnt), clean_cnt); return -EINVAL; } if (dirty_cnt != atomic_long_read(&c->dirty_zn_cnt)) { - ubifs_err("incorrect dirty_zn_cnt %ld, calculated %ld", + ubifs_err(c, "incorrect dirty_zn_cnt %ld, calculated %ld", atomic_long_read(&c->dirty_zn_cnt), dirty_cnt); return -EINVAL; @@ -1608,7 +1608,7 @@ int dbg_walk_index(struct ubifs_info *c, dbg_leaf_callback leaf_cb, if (znode_cb) { err = znode_cb(c, znode, priv); if (err) { - ubifs_err("znode checking function returned error %d", + ubifs_err(c, "znode checking function returned error %d", err); ubifs_dump_znode(c, znode); goto out_dump; @@ -1619,7 +1619,7 @@ int dbg_walk_index(struct ubifs_info *c, dbg_leaf_callback leaf_cb, zbr = &znode->zbranch[idx]; err = leaf_cb(c, zbr, priv); if (err) { - ubifs_err("leaf checking function returned error %d, for leaf at LEB %d:%d", + ubifs_err(c, "leaf checking function returned error %d, for leaf at LEB %d:%d", err, zbr->lnum, zbr->offs); goto out_dump; } @@ -1675,7 +1675,7 @@ out_dump: zbr = &znode->parent->zbranch[znode->iip]; else zbr = &c->zroot; - ubifs_msg("dump of znode at LEB %d:%d", zbr->lnum, zbr->offs); + ubifs_msg(c, "dump of znode at LEB %d:%d", zbr->lnum, zbr->offs); ubifs_dump_znode(c, znode); out_unlock: mutex_unlock(&c->tnc_mutex); @@ -1722,12 +1722,12 @@ int dbg_check_idx_size(struct ubifs_info *c, long long idx_size) err = dbg_walk_index(c, NULL, add_size, &calc); if (err) { - ubifs_err("error %d while walking the index", err); + ubifs_err(c, "error %d while walking the index", err); return err; } if (calc != idx_size) { - ubifs_err("index size check failed: calculated size is %lld, should be %lld", + ubifs_err(c, "index size check failed: calculated size is %lld, should be %lld", calc, idx_size); dump_stack(); return -EINVAL; @@ -1814,7 +1814,7 @@ static struct fsck_inode *add_inode(struct ubifs_info *c, } if (inum > c->highest_inum) { - ubifs_err("too high inode number, max. is %lu", + ubifs_err(c, "too high inode number, max. is %lu", (unsigned long)c->highest_inum); return ERR_PTR(-EINVAL); } @@ -1921,17 +1921,17 @@ static struct fsck_inode *read_add_inode(struct ubifs_info *c, ino_key_init(c, &key, inum); err = ubifs_lookup_level0(c, &key, &znode, &n); if (!err) { - ubifs_err("inode %lu not found in index", (unsigned long)inum); + ubifs_err(c, "inode %lu not found in index", (unsigned long)inum); return ERR_PTR(-ENOENT); } else if (err < 0) { - ubifs_err("error %d while looking up inode %lu", + ubifs_err(c, "error %d while looking up inode %lu", err, (unsigned long)inum); return ERR_PTR(err); } zbr = &znode->zbranch[n]; if (zbr->len < UBIFS_INO_NODE_SZ) { - ubifs_err("bad node %lu node length %d", + ubifs_err(c, "bad node %lu node length %d", (unsigned long)inum, zbr->len); return ERR_PTR(-EINVAL); } @@ -1942,7 +1942,7 @@ static struct fsck_inode *read_add_inode(struct ubifs_info *c, err = ubifs_tnc_read_node(c, zbr, ino); if (err) { - ubifs_err("cannot read inode node at LEB %d:%d, error %d", + ubifs_err(c, "cannot read inode node at LEB %d:%d, error %d", zbr->lnum, zbr->offs, err); kfree(ino); return ERR_PTR(err); @@ -1951,7 +1951,7 @@ static struct fsck_inode *read_add_inode(struct ubifs_info *c, fscki = add_inode(c, fsckd, ino); kfree(ino); if (IS_ERR(fscki)) { - ubifs_err("error %ld while adding inode %lu node", + ubifs_err(c, "error %ld while adding inode %lu node", PTR_ERR(fscki), (unsigned long)inum); return fscki; } @@ -1985,7 +1985,7 @@ static int check_leaf(struct ubifs_info *c, struct ubifs_zbranch *zbr, struct fsck_inode *fscki; if (zbr->len < UBIFS_CH_SZ) { - ubifs_err("bad leaf length %d (LEB %d:%d)", + ubifs_err(c, "bad leaf length %d (LEB %d:%d)", zbr->len, zbr->lnum, zbr->offs); return -EINVAL; } @@ -1996,7 +1996,7 @@ static int check_leaf(struct ubifs_info *c, struct ubifs_zbranch *zbr, err = ubifs_tnc_read_node(c, zbr, node); if (err) { - ubifs_err("cannot read leaf node at LEB %d:%d, error %d", + ubifs_err(c, "cannot read leaf node at LEB %d:%d, error %d", zbr->lnum, zbr->offs, err); goto out_free; } @@ -2006,7 +2006,7 @@ static int check_leaf(struct ubifs_info *c, struct ubifs_zbranch *zbr, fscki = add_inode(c, priv, node); if (IS_ERR(fscki)) { err = PTR_ERR(fscki); - ubifs_err("error %d while adding inode node", err); + ubifs_err(c, "error %d while adding inode node", err); goto out_dump; } goto out; @@ -2014,7 +2014,7 @@ static int check_leaf(struct ubifs_info *c, struct ubifs_zbranch *zbr, if (type != UBIFS_DENT_KEY && type != UBIFS_XENT_KEY && type != UBIFS_DATA_KEY) { - ubifs_err("unexpected node type %d at LEB %d:%d", + ubifs_err(c, "unexpected node type %d at LEB %d:%d", type, zbr->lnum, zbr->offs); err = -EINVAL; goto out_free; @@ -2022,7 +2022,7 @@ static int check_leaf(struct ubifs_info *c, struct ubifs_zbranch *zbr, ch = node; if (le64_to_cpu(ch->sqnum) > c->max_sqnum) { - ubifs_err("too high sequence number, max. is %llu", + ubifs_err(c, "too high sequence number, max. is %llu", c->max_sqnum); err = -EINVAL; goto out_dump; @@ -2042,7 +2042,7 @@ static int check_leaf(struct ubifs_info *c, struct ubifs_zbranch *zbr, fscki = read_add_inode(c, priv, inum); if (IS_ERR(fscki)) { err = PTR_ERR(fscki); - ubifs_err("error %d while processing data node and trying to find inode node %lu", + ubifs_err(c, "error %d while processing data node and trying to find inode node %lu", err, (unsigned long)inum); goto out_dump; } @@ -2052,7 +2052,7 @@ static int check_leaf(struct ubifs_info *c, struct ubifs_zbranch *zbr, blk_offs <<= UBIFS_BLOCK_SHIFT; blk_offs += le32_to_cpu(dn->size); if (blk_offs > fscki->size) { - ubifs_err("data node at LEB %d:%d is not within inode size %lld", + ubifs_err(c, "data node at LEB %d:%d is not within inode size %lld", zbr->lnum, zbr->offs, fscki->size); err = -EINVAL; goto out_dump; @@ -2076,7 +2076,7 @@ static int check_leaf(struct ubifs_info *c, struct ubifs_zbranch *zbr, fscki = read_add_inode(c, priv, inum); if (IS_ERR(fscki)) { err = PTR_ERR(fscki); - ubifs_err("error %d while processing entry node and trying to find inode node %lu", + ubifs_err(c, "error %d while processing entry node and trying to find inode node %lu", err, (unsigned long)inum); goto out_dump; } @@ -2088,7 +2088,7 @@ static int check_leaf(struct ubifs_info *c, struct ubifs_zbranch *zbr, fscki1 = read_add_inode(c, priv, inum); if (IS_ERR(fscki1)) { err = PTR_ERR(fscki1); - ubifs_err("error %d while processing entry node and trying to find parent inode node %lu", + ubifs_err(c, "error %d while processing entry node and trying to find parent inode node %lu", err, (unsigned long)inum); goto out_dump; } @@ -2111,7 +2111,7 @@ out: return 0; out_dump: - ubifs_msg("dump of node at LEB %d:%d", zbr->lnum, zbr->offs); + ubifs_msg(c, "dump of node at LEB %d:%d", zbr->lnum, zbr->offs); ubifs_dump_node(c, node); out_free: kfree(node); @@ -2162,52 +2162,52 @@ static int check_inodes(struct ubifs_info *c, struct fsck_data *fsckd) */ if (fscki->inum != UBIFS_ROOT_INO && fscki->references != 1) { - ubifs_err("directory inode %lu has %d direntries which refer it, but should be 1", + ubifs_err(c, "directory inode %lu has %d direntries which refer it, but should be 1", (unsigned long)fscki->inum, fscki->references); goto out_dump; } if (fscki->inum == UBIFS_ROOT_INO && fscki->references != 0) { - ubifs_err("root inode %lu has non-zero (%d) direntries which refer it", + ubifs_err(c, "root inode %lu has non-zero (%d) direntries which refer it", (unsigned long)fscki->inum, fscki->references); goto out_dump; } if (fscki->calc_sz != fscki->size) { - ubifs_err("directory inode %lu size is %lld, but calculated size is %lld", + ubifs_err(c, "directory inode %lu size is %lld, but calculated size is %lld", (unsigned long)fscki->inum, fscki->size, fscki->calc_sz); goto out_dump; } if (fscki->calc_cnt != fscki->nlink) { - ubifs_err("directory inode %lu nlink is %d, but calculated nlink is %d", + ubifs_err(c, "directory inode %lu nlink is %d, but calculated nlink is %d", (unsigned long)fscki->inum, fscki->nlink, fscki->calc_cnt); goto out_dump; } } else { if (fscki->references != fscki->nlink) { - ubifs_err("inode %lu nlink is %d, but calculated nlink is %d", + ubifs_err(c, "inode %lu nlink is %d, but calculated nlink is %d", (unsigned long)fscki->inum, fscki->nlink, fscki->references); goto out_dump; } } if (fscki->xattr_sz != fscki->calc_xsz) { - ubifs_err("inode %lu has xattr size %u, but calculated size is %lld", + ubifs_err(c, "inode %lu has xattr size %u, but calculated size is %lld", (unsigned long)fscki->inum, fscki->xattr_sz, fscki->calc_xsz); goto out_dump; } if (fscki->xattr_cnt != fscki->calc_xcnt) { - ubifs_err("inode %lu has %u xattrs, but calculated count is %lld", + ubifs_err(c, "inode %lu has %u xattrs, but calculated count is %lld", (unsigned long)fscki->inum, fscki->xattr_cnt, fscki->calc_xcnt); goto out_dump; } if (fscki->xattr_nms != fscki->calc_xnms) { - ubifs_err("inode %lu has xattr names' size %u, but calculated names' size is %lld", + ubifs_err(c, "inode %lu has xattr names' size %u, but calculated names' size is %lld", (unsigned long)fscki->inum, fscki->xattr_nms, fscki->calc_xnms); goto out_dump; @@ -2221,11 +2221,11 @@ out_dump: ino_key_init(c, &key, fscki->inum); err = ubifs_lookup_level0(c, &key, &znode, &n); if (!err) { - ubifs_err("inode %lu not found in index", + ubifs_err(c, "inode %lu not found in index", (unsigned long)fscki->inum); return -ENOENT; } else if (err < 0) { - ubifs_err("error %d while looking up inode %lu", + ubifs_err(c, "error %d while looking up inode %lu", err, (unsigned long)fscki->inum); return err; } @@ -2237,13 +2237,13 @@ out_dump: err = ubifs_tnc_read_node(c, zbr, ino); if (err) { - ubifs_err("cannot read inode node at LEB %d:%d, error %d", + ubifs_err(c, "cannot read inode node at LEB %d:%d, error %d", zbr->lnum, zbr->offs, err); kfree(ino); return err; } - ubifs_msg("dump of the inode %lu sitting in LEB %d:%d", + ubifs_msg(c, "dump of the inode %lu sitting in LEB %d:%d", (unsigned long)fscki->inum, zbr->lnum, zbr->offs); ubifs_dump_node(c, ino); kfree(ino); @@ -2284,7 +2284,7 @@ int dbg_check_filesystem(struct ubifs_info *c) return 0; out_free: - ubifs_err("file-system check failed with error %d", err); + ubifs_err(c, "file-system check failed with error %d", err); dump_stack(); free_inodes(&fsckd); return err; @@ -2315,12 +2315,12 @@ int dbg_check_data_nodes_order(struct ubifs_info *c, struct list_head *head) sb = container_of(cur->next, struct ubifs_scan_node, list); if (sa->type != UBIFS_DATA_NODE) { - ubifs_err("bad node type %d", sa->type); + ubifs_err(c, "bad node type %d", sa->type); ubifs_dump_node(c, sa->node); return -EINVAL; } if (sb->type != UBIFS_DATA_NODE) { - ubifs_err("bad node type %d", sb->type); + ubifs_err(c, "bad node type %d", sb->type); ubifs_dump_node(c, sb->node); return -EINVAL; } @@ -2331,7 +2331,7 @@ int dbg_check_data_nodes_order(struct ubifs_info *c, struct list_head *head) if (inuma < inumb) continue; if (inuma > inumb) { - ubifs_err("larger inum %lu goes before inum %lu", + ubifs_err(c, "larger inum %lu goes before inum %lu", (unsigned long)inuma, (unsigned long)inumb); goto error_dump; } @@ -2340,11 +2340,11 @@ int dbg_check_data_nodes_order(struct ubifs_info *c, struct list_head *head) blkb = key_block(c, &sb->key); if (blka > blkb) { - ubifs_err("larger block %u goes before %u", blka, blkb); + ubifs_err(c, "larger block %u goes before %u", blka, blkb); goto error_dump; } if (blka == blkb) { - ubifs_err("two data nodes for the same block"); + ubifs_err(c, "two data nodes for the same block"); goto error_dump; } } @@ -2383,19 +2383,19 @@ int dbg_check_nondata_nodes_order(struct ubifs_info *c, struct list_head *head) if (sa->type != UBIFS_INO_NODE && sa->type != UBIFS_DENT_NODE && sa->type != UBIFS_XENT_NODE) { - ubifs_err("bad node type %d", sa->type); + ubifs_err(c, "bad node type %d", sa->type); ubifs_dump_node(c, sa->node); return -EINVAL; } if (sa->type != UBIFS_INO_NODE && sa->type != UBIFS_DENT_NODE && sa->type != UBIFS_XENT_NODE) { - ubifs_err("bad node type %d", sb->type); + ubifs_err(c, "bad node type %d", sb->type); ubifs_dump_node(c, sb->node); return -EINVAL; } if (sa->type != UBIFS_INO_NODE && sb->type == UBIFS_INO_NODE) { - ubifs_err("non-inode node goes before inode node"); + ubifs_err(c, "non-inode node goes before inode node"); goto error_dump; } @@ -2405,7 +2405,7 @@ int dbg_check_nondata_nodes_order(struct ubifs_info *c, struct list_head *head) if (sa->type == UBIFS_INO_NODE && sb->type == UBIFS_INO_NODE) { /* Inode nodes are sorted in descending size order */ if (sa->len < sb->len) { - ubifs_err("smaller inode node goes first"); + ubifs_err(c, "smaller inode node goes first"); goto error_dump; } continue; @@ -2421,7 +2421,7 @@ int dbg_check_nondata_nodes_order(struct ubifs_info *c, struct list_head *head) if (inuma < inumb) continue; if (inuma > inumb) { - ubifs_err("larger inum %lu goes before inum %lu", + ubifs_err(c, "larger inum %lu goes before inum %lu", (unsigned long)inuma, (unsigned long)inumb); goto error_dump; } @@ -2430,7 +2430,7 @@ int dbg_check_nondata_nodes_order(struct ubifs_info *c, struct list_head *head) hashb = key_block(c, &sb->key); if (hasha > hashb) { - ubifs_err("larger hash %u goes before %u", + ubifs_err(c, "larger hash %u goes before %u", hasha, hashb); goto error_dump; } @@ -2439,9 +2439,9 @@ int dbg_check_nondata_nodes_order(struct ubifs_info *c, struct list_head *head) return 0; error_dump: - ubifs_msg("dumping first node"); + ubifs_msg(c, "dumping first node"); ubifs_dump_node(c, sa->node); - ubifs_msg("dumping second node"); + ubifs_msg(c, "dumping second node"); ubifs_dump_node(c, sb->node); return -EINVAL; return 0; @@ -2470,13 +2470,13 @@ static int power_cut_emulated(struct ubifs_info *c, int lnum, int write) delay = prandom_u32() % 60000; d->pc_timeout = jiffies; d->pc_timeout += msecs_to_jiffies(delay); - ubifs_warn("failing after %lums", delay); + ubifs_warn(c, "failing after %lums", delay); } else { d->pc_delay = 2; delay = prandom_u32() % 10000; /* Fail within 10000 operations */ d->pc_cnt_max = delay; - ubifs_warn("failing after %lu calls", delay); + ubifs_warn(c, "failing after %lu calls", delay); } } @@ -2494,55 +2494,55 @@ static int power_cut_emulated(struct ubifs_info *c, int lnum, int write) return 0; if (chance(19, 20)) return 0; - ubifs_warn("failing in super block LEB %d", lnum); + ubifs_warn(c, "failing in super block LEB %d", lnum); } else if (lnum == UBIFS_MST_LNUM || lnum == UBIFS_MST_LNUM + 1) { if (chance(19, 20)) return 0; - ubifs_warn("failing in master LEB %d", lnum); + ubifs_warn(c, "failing in master LEB %d", lnum); } else if (lnum >= UBIFS_LOG_LNUM && lnum <= c->log_last) { if (write && chance(99, 100)) return 0; if (chance(399, 400)) return 0; - ubifs_warn("failing in log LEB %d", lnum); + ubifs_warn(c, "failing in log LEB %d", lnum); } else if (lnum >= c->lpt_first && lnum <= c->lpt_last) { if (write && chance(7, 8)) return 0; if (chance(19, 20)) return 0; - ubifs_warn("failing in LPT LEB %d", lnum); + ubifs_warn(c, "failing in LPT LEB %d", lnum); } else if (lnum >= c->orph_first && lnum <= c->orph_last) { if (write && chance(1, 2)) return 0; if (chance(9, 10)) return 0; - ubifs_warn("failing in orphan LEB %d", lnum); + ubifs_warn(c, "failing in orphan LEB %d", lnum); } else if (lnum == c->ihead_lnum) { if (chance(99, 100)) return 0; - ubifs_warn("failing in index head LEB %d", lnum); + ubifs_warn(c, "failing in index head LEB %d", lnum); } else if (c->jheads && lnum == c->jheads[GCHD].wbuf.lnum) { if (chance(9, 10)) return 0; - ubifs_warn("failing in GC head LEB %d", lnum); + ubifs_warn(c, "failing in GC head LEB %d", lnum); } else if (write && !RB_EMPTY_ROOT(&c->buds) && !ubifs_search_bud(c, lnum)) { if (chance(19, 20)) return 0; - ubifs_warn("failing in non-bud LEB %d", lnum); + ubifs_warn(c, "failing in non-bud LEB %d", lnum); } else if (c->cmt_state == COMMIT_RUNNING_BACKGROUND || c->cmt_state == COMMIT_RUNNING_REQUIRED) { if (chance(999, 1000)) return 0; - ubifs_warn("failing in bud LEB %d commit running", lnum); + ubifs_warn(c, "failing in bud LEB %d commit running", lnum); } else { if (chance(9999, 10000)) return 0; - ubifs_warn("failing in bud LEB %d commit not running", lnum); + ubifs_warn(c, "failing in bud LEB %d commit not running", lnum); } d->pc_happened = 1; - ubifs_warn("========== Power cut emulated =========="); + ubifs_warn(c, "========== Power cut emulated =========="); dump_stack(); return 1; } @@ -2557,7 +2557,7 @@ static int corrupt_data(const struct ubifs_info *c, const void *buf, /* Corruption span max to end of write unit */ to = min(len, ALIGN(from + 1, c->max_write_size)); - ubifs_warn("filled bytes %u-%u with %s", from, to - 1, + ubifs_warn(c, "filled bytes %u-%u with %s", from, to - 1, ffs ? "0xFFs" : "random data"); if (ffs) @@ -2579,7 +2579,7 @@ int dbg_leb_write(struct ubifs_info *c, int lnum, const void *buf, failing = power_cut_emulated(c, lnum, 1); if (failing) { len = corrupt_data(c, buf, len); - ubifs_warn("actually write %d bytes to LEB %d:%d (the buffer was corrupted)", + ubifs_warn(c, "actually write %d bytes to LEB %d:%d (the buffer was corrupted)", len, lnum, offs); } err = ubi_leb_write(c->ubi, lnum, buf, offs, len); @@ -2909,7 +2909,7 @@ out_remove: debugfs_remove_recursive(d->dfs_dir); out: err = dent ? PTR_ERR(dent) : -ENODEV; - ubifs_err("cannot create \"%s\" debugfs file or directory, error %d\n", + ubifs_err(c, "cannot create \"%s\" debugfs file or directory, error %d\n", fname, err); return err; } @@ -3063,8 +3063,8 @@ out_remove: debugfs_remove_recursive(dfs_rootdir); out: err = dent ? PTR_ERR(dent) : -ENODEV; - ubifs_err("cannot create \"%s\" debugfs file or directory, error %d\n", - fname, err); + pr_err("UBIFS error (pid %d): cannot create \"%s\" debugfs file or directory, error %d\n", + current->pid, fname, err); return err; } diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 0fa6c803992e..02d1ee778df0 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -146,12 +146,12 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, const struct inode *dir, if (c->highest_inum >= INUM_WARN_WATERMARK) { if (c->highest_inum >= INUM_WATERMARK) { spin_unlock(&c->cnt_lock); - ubifs_err("out of inode numbers"); + ubifs_err(c, "out of inode numbers"); make_bad_inode(inode); iput(inode); return ERR_PTR(-EINVAL); } - ubifs_warn("running out of inode numbers (current %lu, max %d)", + ubifs_warn(c, "running out of inode numbers (current %lu, max %u)", (unsigned long)c->highest_inum, INUM_WATERMARK); } @@ -222,7 +222,7 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry, * checking. */ err = PTR_ERR(inode); - ubifs_err("dead directory entry '%pd', error %d", + ubifs_err(c, "dead directory entry '%pd', error %d", dentry, err); ubifs_ro_mode(c, err); goto out; @@ -272,7 +272,7 @@ static int ubifs_create(struct inode *dir, struct dentry *dentry, umode_t mode, err = ubifs_init_security(dir, inode, &dentry->d_name); if (err) - goto out_cancel; + goto out_inode; mutex_lock(&dir_ui->ui_mutex); dir->i_size += sz_change; @@ -292,11 +292,12 @@ out_cancel: dir->i_size -= sz_change; dir_ui->ui_size = dir->i_size; mutex_unlock(&dir_ui->ui_mutex); +out_inode: make_bad_inode(inode); iput(inode); out_budg: ubifs_release_budget(c, &req); - ubifs_err("cannot create regular file, error %d", err); + ubifs_err(c, "cannot create regular file, error %d", err); return err; } @@ -449,7 +450,7 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx) out: if (err != -ENOENT) { - ubifs_err("cannot find next direntry, error %d", err); + ubifs_err(c, "cannot find next direntry, error %d", err); return err; } @@ -732,7 +733,7 @@ static int ubifs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) err = ubifs_init_security(dir, inode, &dentry->d_name); if (err) - goto out_cancel; + goto out_inode; mutex_lock(&dir_ui->ui_mutex); insert_inode_hash(inode); @@ -743,7 +744,7 @@ static int ubifs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) dir->i_mtime = dir->i_ctime = inode->i_ctime; err = ubifs_jnl_update(c, dir, &dentry->d_name, inode, 0, 0); if (err) { - ubifs_err("cannot create directory, error %d", err); + ubifs_err(c, "cannot create directory, error %d", err); goto out_cancel; } mutex_unlock(&dir_ui->ui_mutex); @@ -757,6 +758,7 @@ out_cancel: dir_ui->ui_size = dir->i_size; drop_nlink(dir); mutex_unlock(&dir_ui->ui_mutex); +out_inode: make_bad_inode(inode); iput(inode); out_budg: @@ -816,7 +818,7 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry, err = ubifs_init_security(dir, inode, &dentry->d_name); if (err) - goto out_cancel; + goto out_inode; mutex_lock(&dir_ui->ui_mutex); dir->i_size += sz_change; @@ -836,6 +838,7 @@ out_cancel: dir->i_size -= sz_change; dir_ui->ui_size = dir->i_size; mutex_unlock(&dir_ui->ui_mutex); +out_inode: make_bad_inode(inode); iput(inode); out_budg: @@ -896,7 +899,7 @@ static int ubifs_symlink(struct inode *dir, struct dentry *dentry, err = ubifs_init_security(dir, inode, &dentry->d_name); if (err) - goto out_cancel; + goto out_inode; mutex_lock(&dir_ui->ui_mutex); dir->i_size += sz_change; diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index e627c0acf626..3ba3fef64e9e 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -50,7 +50,6 @@ */ #include "ubifs.h" -#include <linux/aio.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/slab.h> @@ -80,7 +79,7 @@ static int read_block(struct inode *inode, void *addr, unsigned int block, dlen = le32_to_cpu(dn->ch.len) - UBIFS_DATA_NODE_SZ; out_len = UBIFS_BLOCK_SIZE; - err = ubifs_decompress(&dn->data, dlen, addr, &out_len, + err = ubifs_decompress(c, &dn->data, dlen, addr, &out_len, le16_to_cpu(dn->compr_type)); if (err || len != out_len) goto dump; @@ -96,7 +95,7 @@ static int read_block(struct inode *inode, void *addr, unsigned int block, return 0; dump: - ubifs_err("bad data node (block %u, inode %lu)", + ubifs_err(c, "bad data node (block %u, inode %lu)", block, inode->i_ino); ubifs_dump_node(c, dn); return -EINVAL; @@ -161,13 +160,14 @@ static int do_readpage(struct page *page) addr += UBIFS_BLOCK_SIZE; } if (err) { + struct ubifs_info *c = inode->i_sb->s_fs_info; if (err == -ENOENT) { /* Not found, so it must be a hole */ SetPageChecked(page); dbg_gen("hole"); goto out_free; } - ubifs_err("cannot read page %lu of inode %lu, error %d", + ubifs_err(c, "cannot read page %lu of inode %lu, error %d", page->index, inode->i_ino, err); goto error; } @@ -650,7 +650,7 @@ static int populate_page(struct ubifs_info *c, struct page *page, dlen = le32_to_cpu(dn->ch.len) - UBIFS_DATA_NODE_SZ; out_len = UBIFS_BLOCK_SIZE; - err = ubifs_decompress(&dn->data, dlen, addr, &out_len, + err = ubifs_decompress(c, &dn->data, dlen, addr, &out_len, le16_to_cpu(dn->compr_type)); if (err || len != out_len) goto out_err; @@ -698,7 +698,7 @@ out_err: SetPageError(page); flush_dcache_page(page); kunmap(page); - ubifs_err("bad data node (block %u, inode %lu)", + ubifs_err(c, "bad data node (block %u, inode %lu)", page_block, inode->i_ino); return -EINVAL; } @@ -802,7 +802,7 @@ out_free: return ret; out_warn: - ubifs_warn("ignoring error %d and skipping bulk-read", err); + ubifs_warn(c, "ignoring error %d and skipping bulk-read", err); goto out_free; out_bu_off: @@ -930,7 +930,7 @@ static int do_writepage(struct page *page, int len) } if (err) { SetPageError(page); - ubifs_err("cannot write page %lu of inode %lu, error %d", + ubifs_err(c, "cannot write page %lu of inode %lu, error %d", page->index, inode->i_ino, err); ubifs_ro_mode(c, err); } @@ -1485,7 +1485,7 @@ static int ubifs_vm_page_mkwrite(struct vm_area_struct *vma, err = ubifs_budget_space(c, &req); if (unlikely(err)) { if (err == -ENOSPC) - ubifs_warn("out of space for mmapped file (inode number %lu)", + ubifs_warn(c, "out of space for mmapped file (inode number %lu)", inode->i_ino); return VM_FAULT_SIGBUS; } @@ -1581,8 +1581,6 @@ const struct inode_operations ubifs_symlink_inode_operations = { const struct file_operations ubifs_file_operations = { .llseek = generic_file_llseek, - .read = new_sync_read, - .write = new_sync_write, .read_iter = generic_file_read_iter, .write_iter = ubifs_write_iter, .mmap = ubifs_file_mmap, diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c index fb08b0c514b6..97be41215332 100644 --- a/fs/ubifs/io.c +++ b/fs/ubifs/io.c @@ -85,7 +85,7 @@ void ubifs_ro_mode(struct ubifs_info *c, int err) c->ro_error = 1; c->no_chk_data_crc = 0; c->vfs_sb->s_flags |= MS_RDONLY; - ubifs_warn("switched to read-only mode, error %d", err); + ubifs_warn(c, "switched to read-only mode, error %d", err); dump_stack(); } } @@ -107,7 +107,7 @@ int ubifs_leb_read(const struct ubifs_info *c, int lnum, void *buf, int offs, * @even_ebadmsg is true. */ if (err && (err != -EBADMSG || even_ebadmsg)) { - ubifs_err("reading %d bytes from LEB %d:%d failed, error %d", + ubifs_err(c, "reading %d bytes from LEB %d:%d failed, error %d", len, lnum, offs, err); dump_stack(); } @@ -127,7 +127,7 @@ int ubifs_leb_write(struct ubifs_info *c, int lnum, const void *buf, int offs, else err = dbg_leb_write(c, lnum, buf, offs, len); if (err) { - ubifs_err("writing %d bytes to LEB %d:%d failed, error %d", + ubifs_err(c, "writing %d bytes to LEB %d:%d failed, error %d", len, lnum, offs, err); ubifs_ro_mode(c, err); dump_stack(); @@ -147,7 +147,7 @@ int ubifs_leb_change(struct ubifs_info *c, int lnum, const void *buf, int len) else err = dbg_leb_change(c, lnum, buf, len); if (err) { - ubifs_err("changing %d bytes in LEB %d failed, error %d", + ubifs_err(c, "changing %d bytes in LEB %d failed, error %d", len, lnum, err); ubifs_ro_mode(c, err); dump_stack(); @@ -167,7 +167,7 @@ int ubifs_leb_unmap(struct ubifs_info *c, int lnum) else err = dbg_leb_unmap(c, lnum); if (err) { - ubifs_err("unmap LEB %d failed, error %d", lnum, err); + ubifs_err(c, "unmap LEB %d failed, error %d", lnum, err); ubifs_ro_mode(c, err); dump_stack(); } @@ -186,7 +186,7 @@ int ubifs_leb_map(struct ubifs_info *c, int lnum) else err = dbg_leb_map(c, lnum); if (err) { - ubifs_err("mapping LEB %d failed, error %d", lnum, err); + ubifs_err(c, "mapping LEB %d failed, error %d", lnum, err); ubifs_ro_mode(c, err); dump_stack(); } @@ -199,7 +199,7 @@ int ubifs_is_mapped(const struct ubifs_info *c, int lnum) err = ubi_is_mapped(c->ubi, lnum); if (err < 0) { - ubifs_err("ubi_is_mapped failed for LEB %d, error %d", + ubifs_err(c, "ubi_is_mapped failed for LEB %d, error %d", lnum, err); dump_stack(); } @@ -247,7 +247,7 @@ int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum, magic = le32_to_cpu(ch->magic); if (magic != UBIFS_NODE_MAGIC) { if (!quiet) - ubifs_err("bad magic %#08x, expected %#08x", + ubifs_err(c, "bad magic %#08x, expected %#08x", magic, UBIFS_NODE_MAGIC); err = -EUCLEAN; goto out; @@ -256,7 +256,7 @@ int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum, type = ch->node_type; if (type < 0 || type >= UBIFS_NODE_TYPES_CNT) { if (!quiet) - ubifs_err("bad node type %d", type); + ubifs_err(c, "bad node type %d", type); goto out; } @@ -279,7 +279,7 @@ int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum, node_crc = le32_to_cpu(ch->crc); if (crc != node_crc) { if (!quiet) - ubifs_err("bad CRC: calculated %#08x, read %#08x", + ubifs_err(c, "bad CRC: calculated %#08x, read %#08x", crc, node_crc); err = -EUCLEAN; goto out; @@ -289,10 +289,10 @@ int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum, out_len: if (!quiet) - ubifs_err("bad node length %d", node_len); + ubifs_err(c, "bad node length %d", node_len); out: if (!quiet) { - ubifs_err("bad node at LEB %d:%d", lnum, offs); + ubifs_err(c, "bad node at LEB %d:%d", lnum, offs); ubifs_dump_node(c, buf); dump_stack(); } @@ -355,11 +355,11 @@ static unsigned long long next_sqnum(struct ubifs_info *c) if (unlikely(sqnum >= SQNUM_WARN_WATERMARK)) { if (sqnum >= SQNUM_WATERMARK) { - ubifs_err("sequence number overflow %llu, end of life", + ubifs_err(c, "sequence number overflow %llu, end of life", sqnum); ubifs_ro_mode(c, -EINVAL); } - ubifs_warn("running out of sequence numbers, end of life soon"); + ubifs_warn(c, "running out of sequence numbers, end of life soon"); } return sqnum; @@ -636,7 +636,7 @@ int ubifs_bg_wbufs_sync(struct ubifs_info *c) err = ubifs_wbuf_sync_nolock(wbuf); mutex_unlock(&wbuf->io_mutex); if (err) { - ubifs_err("cannot sync write-buffer, error %d", err); + ubifs_err(c, "cannot sync write-buffer, error %d", err); ubifs_ro_mode(c, err); goto out_timers; } @@ -833,7 +833,7 @@ exit: return 0; out: - ubifs_err("cannot write %d bytes to LEB %d:%d, error %d", + ubifs_err(c, "cannot write %d bytes to LEB %d:%d, error %d", len, wbuf->lnum, wbuf->offs, err); ubifs_dump_node(c, buf); dump_stack(); @@ -932,27 +932,27 @@ int ubifs_read_node_wbuf(struct ubifs_wbuf *wbuf, void *buf, int type, int len, } if (type != ch->node_type) { - ubifs_err("bad node type (%d but expected %d)", + ubifs_err(c, "bad node type (%d but expected %d)", ch->node_type, type); goto out; } err = ubifs_check_node(c, buf, lnum, offs, 0, 0); if (err) { - ubifs_err("expected node type %d", type); + ubifs_err(c, "expected node type %d", type); return err; } rlen = le32_to_cpu(ch->len); if (rlen != len) { - ubifs_err("bad node length %d, expected %d", rlen, len); + ubifs_err(c, "bad node length %d, expected %d", rlen, len); goto out; } return 0; out: - ubifs_err("bad node at LEB %d:%d", lnum, offs); + ubifs_err(c, "bad node at LEB %d:%d", lnum, offs); ubifs_dump_node(c, buf); dump_stack(); return -EINVAL; diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c index 648b143606cc..3c7b29de0ca7 100644 --- a/fs/ubifs/ioctl.c +++ b/fs/ubifs/ioctl.c @@ -138,7 +138,7 @@ static int setflags(struct inode *inode, int flags) return err; out_unlock: - ubifs_err("can't modify inode %lu attributes", inode->i_ino); + ubifs_err(c, "can't modify inode %lu attributes", inode->i_ino); mutex_unlock(&ui->ui_mutex); ubifs_release_budget(c, &req); return err; diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index f6ac3f29323c..90ae1a8439d9 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -363,11 +363,11 @@ again: * This should not happen unless the journal size limitations * are too tough. */ - ubifs_err("stuck in space allocation"); + ubifs_err(c, "stuck in space allocation"); err = -ENOSPC; goto out; } else if (cmt_retries > 32) - ubifs_warn("too many space allocation re-tries (%d)", + ubifs_warn(c, "too many space allocation re-tries (%d)", cmt_retries); dbg_jnl("-EAGAIN, commit and retry (retried %d times)", @@ -380,7 +380,7 @@ again: goto again; out: - ubifs_err("cannot reserve %d bytes in jhead %d, error %d", + ubifs_err(c, "cannot reserve %d bytes in jhead %d, error %d", len, jhead, err); if (err == -ENOSPC) { /* This are some budgeting problems, print useful information */ @@ -731,7 +731,7 @@ int ubifs_jnl_write_data(struct ubifs_info *c, const struct inode *inode, compr_type = ui->compr_type; out_len = dlen - UBIFS_DATA_NODE_SZ; - ubifs_compress(buf, len, &data->data, &out_len, &compr_type); + ubifs_compress(c, buf, len, &data->data, &out_len, &compr_type); ubifs_assert(out_len <= UBIFS_BLOCK_SIZE); dlen = UBIFS_DATA_NODE_SZ + out_len; @@ -1100,7 +1100,8 @@ out_free: * This function is used when an inode is truncated and the last data node of * the inode has to be re-compressed and re-written. */ -static int recomp_data_node(struct ubifs_data_node *dn, int *new_len) +static int recomp_data_node(const struct ubifs_info *c, + struct ubifs_data_node *dn, int *new_len) { void *buf; int err, len, compr_type, out_len; @@ -1112,11 +1113,11 @@ static int recomp_data_node(struct ubifs_data_node *dn, int *new_len) len = le32_to_cpu(dn->ch.len) - UBIFS_DATA_NODE_SZ; compr_type = le16_to_cpu(dn->compr_type); - err = ubifs_decompress(&dn->data, len, buf, &out_len, compr_type); + err = ubifs_decompress(c, &dn->data, len, buf, &out_len, compr_type); if (err) goto out; - ubifs_compress(buf, *new_len, &dn->data, &out_len, &compr_type); + ubifs_compress(c, buf, *new_len, &dn->data, &out_len, &compr_type); ubifs_assert(out_len <= UBIFS_BLOCK_SIZE); dn->compr_type = cpu_to_le16(compr_type); dn->size = cpu_to_le32(*new_len); @@ -1191,7 +1192,7 @@ int ubifs_jnl_truncate(struct ubifs_info *c, const struct inode *inode, int compr_type = le16_to_cpu(dn->compr_type); if (compr_type != UBIFS_COMPR_NONE) { - err = recomp_data_node(dn, &dlen); + err = recomp_data_node(c, dn, &dlen); if (err) goto out_free; } else { diff --git a/fs/ubifs/log.c b/fs/ubifs/log.c index c14628fbeee2..8c795e6392b1 100644 --- a/fs/ubifs/log.c +++ b/fs/ubifs/log.c @@ -696,7 +696,7 @@ int ubifs_consolidate_log(struct ubifs_info *c) destroy_done_tree(&done_tree); vfree(buf); if (write_lnum == c->lhead_lnum) { - ubifs_err("log is too full"); + ubifs_err(c, "log is too full"); return -EINVAL; } /* Unmap remaining LEBs */ @@ -743,7 +743,7 @@ static int dbg_check_bud_bytes(struct ubifs_info *c) bud_bytes += c->leb_size - bud->start; if (c->bud_bytes != bud_bytes) { - ubifs_err("bad bud_bytes %lld, calculated %lld", + ubifs_err(c, "bad bud_bytes %lld, calculated %lld", c->bud_bytes, bud_bytes); err = -EINVAL; } diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c index 46190a7c42a6..a0011aa3a779 100644 --- a/fs/ubifs/lprops.c +++ b/fs/ubifs/lprops.c @@ -682,7 +682,7 @@ int ubifs_change_one_lp(struct ubifs_info *c, int lnum, int free, int dirty, out: ubifs_release_lprops(c); if (err) - ubifs_err("cannot change properties of LEB %d, error %d", + ubifs_err(c, "cannot change properties of LEB %d, error %d", lnum, err); return err; } @@ -721,7 +721,7 @@ int ubifs_update_one_lp(struct ubifs_info *c, int lnum, int free, int dirty, out: ubifs_release_lprops(c); if (err) - ubifs_err("cannot update properties of LEB %d, error %d", + ubifs_err(c, "cannot update properties of LEB %d, error %d", lnum, err); return err; } @@ -746,7 +746,7 @@ int ubifs_read_one_lp(struct ubifs_info *c, int lnum, struct ubifs_lprops *lp) lpp = ubifs_lpt_lookup(c, lnum); if (IS_ERR(lpp)) { err = PTR_ERR(lpp); - ubifs_err("cannot read properties of LEB %d, error %d", + ubifs_err(c, "cannot read properties of LEB %d, error %d", lnum, err); goto out; } @@ -873,13 +873,13 @@ int dbg_check_cats(struct ubifs_info *c) list_for_each_entry(lprops, &c->empty_list, list) { if (lprops->free != c->leb_size) { - ubifs_err("non-empty LEB %d on empty list (free %d dirty %d flags %d)", + ubifs_err(c, "non-empty LEB %d on empty list (free %d dirty %d flags %d)", lprops->lnum, lprops->free, lprops->dirty, lprops->flags); return -EINVAL; } if (lprops->flags & LPROPS_TAKEN) { - ubifs_err("taken LEB %d on empty list (free %d dirty %d flags %d)", + ubifs_err(c, "taken LEB %d on empty list (free %d dirty %d flags %d)", lprops->lnum, lprops->free, lprops->dirty, lprops->flags); return -EINVAL; @@ -889,13 +889,13 @@ int dbg_check_cats(struct ubifs_info *c) i = 0; list_for_each_entry(lprops, &c->freeable_list, list) { if (lprops->free + lprops->dirty != c->leb_size) { - ubifs_err("non-freeable LEB %d on freeable list (free %d dirty %d flags %d)", + ubifs_err(c, "non-freeable LEB %d on freeable list (free %d dirty %d flags %d)", lprops->lnum, lprops->free, lprops->dirty, lprops->flags); return -EINVAL; } if (lprops->flags & LPROPS_TAKEN) { - ubifs_err("taken LEB %d on freeable list (free %d dirty %d flags %d)", + ubifs_err(c, "taken LEB %d on freeable list (free %d dirty %d flags %d)", lprops->lnum, lprops->free, lprops->dirty, lprops->flags); return -EINVAL; @@ -903,7 +903,7 @@ int dbg_check_cats(struct ubifs_info *c) i += 1; } if (i != c->freeable_cnt) { - ubifs_err("freeable list count %d expected %d", i, + ubifs_err(c, "freeable list count %d expected %d", i, c->freeable_cnt); return -EINVAL; } @@ -912,26 +912,26 @@ int dbg_check_cats(struct ubifs_info *c) list_for_each(pos, &c->idx_gc) i += 1; if (i != c->idx_gc_cnt) { - ubifs_err("idx_gc list count %d expected %d", i, + ubifs_err(c, "idx_gc list count %d expected %d", i, c->idx_gc_cnt); return -EINVAL; } list_for_each_entry(lprops, &c->frdi_idx_list, list) { if (lprops->free + lprops->dirty != c->leb_size) { - ubifs_err("non-freeable LEB %d on frdi_idx list (free %d dirty %d flags %d)", + ubifs_err(c, "non-freeable LEB %d on frdi_idx list (free %d dirty %d flags %d)", lprops->lnum, lprops->free, lprops->dirty, lprops->flags); return -EINVAL; } if (lprops->flags & LPROPS_TAKEN) { - ubifs_err("taken LEB %d on frdi_idx list (free %d dirty %d flags %d)", + ubifs_err(c, "taken LEB %d on frdi_idx list (free %d dirty %d flags %d)", lprops->lnum, lprops->free, lprops->dirty, lprops->flags); return -EINVAL; } if (!(lprops->flags & LPROPS_INDEX)) { - ubifs_err("non-index LEB %d on frdi_idx list (free %d dirty %d flags %d)", + ubifs_err(c, "non-index LEB %d on frdi_idx list (free %d dirty %d flags %d)", lprops->lnum, lprops->free, lprops->dirty, lprops->flags); return -EINVAL; @@ -944,15 +944,15 @@ int dbg_check_cats(struct ubifs_info *c) for (i = 0; i < heap->cnt; i++) { lprops = heap->arr[i]; if (!lprops) { - ubifs_err("null ptr in LPT heap cat %d", cat); + ubifs_err(c, "null ptr in LPT heap cat %d", cat); return -EINVAL; } if (lprops->hpos != i) { - ubifs_err("bad ptr in LPT heap cat %d", cat); + ubifs_err(c, "bad ptr in LPT heap cat %d", cat); return -EINVAL; } if (lprops->flags & LPROPS_TAKEN) { - ubifs_err("taken LEB in LPT heap cat %d", cat); + ubifs_err(c, "taken LEB in LPT heap cat %d", cat); return -EINVAL; } } @@ -988,7 +988,7 @@ void dbg_check_heap(struct ubifs_info *c, struct ubifs_lpt_heap *heap, int cat, goto out; } if (lprops != lp) { - ubifs_err("lprops %zx lp %zx lprops->lnum %d lp->lnum %d", + ubifs_err(c, "lprops %zx lp %zx lprops->lnum %d lp->lnum %d", (size_t)lprops, (size_t)lp, lprops->lnum, lp->lnum); err = 4; @@ -1008,7 +1008,7 @@ void dbg_check_heap(struct ubifs_info *c, struct ubifs_lpt_heap *heap, int cat, } out: if (err) { - ubifs_err("failed cat %d hpos %d err %d", cat, i, err); + ubifs_err(c, "failed cat %d hpos %d err %d", cat, i, err); dump_stack(); ubifs_dump_heap(c, heap, cat); } @@ -1039,7 +1039,7 @@ static int scan_check_cb(struct ubifs_info *c, if (cat != LPROPS_UNCAT) { cat = ubifs_categorize_lprops(c, lp); if (cat != (lp->flags & LPROPS_CAT_MASK)) { - ubifs_err("bad LEB category %d expected %d", + ubifs_err(c, "bad LEB category %d expected %d", (lp->flags & LPROPS_CAT_MASK), cat); return -EINVAL; } @@ -1074,7 +1074,7 @@ static int scan_check_cb(struct ubifs_info *c, } } if (!found) { - ubifs_err("bad LPT list (category %d)", cat); + ubifs_err(c, "bad LPT list (category %d)", cat); return -EINVAL; } } @@ -1086,7 +1086,7 @@ static int scan_check_cb(struct ubifs_info *c, if ((lp->hpos != -1 && heap->arr[lp->hpos]->lnum != lnum) || lp != heap->arr[lp->hpos]) { - ubifs_err("bad LPT heap (category %d)", cat); + ubifs_err(c, "bad LPT heap (category %d)", cat); return -EINVAL; } } @@ -1133,7 +1133,7 @@ static int scan_check_cb(struct ubifs_info *c, is_idx = (snod->type == UBIFS_IDX_NODE) ? 1 : 0; if (is_idx && snod->type != UBIFS_IDX_NODE) { - ubifs_err("indexing node in data LEB %d:%d", + ubifs_err(c, "indexing node in data LEB %d:%d", lnum, snod->offs); goto out_destroy; } @@ -1159,7 +1159,7 @@ static int scan_check_cb(struct ubifs_info *c, if (free > c->leb_size || free < 0 || dirty > c->leb_size || dirty < 0) { - ubifs_err("bad calculated accounting for LEB %d: free %d, dirty %d", + ubifs_err(c, "bad calculated accounting for LEB %d: free %d, dirty %d", lnum, free, dirty); goto out_destroy; } @@ -1206,13 +1206,13 @@ static int scan_check_cb(struct ubifs_info *c, /* Free but not unmapped LEB, it's fine */ is_idx = 0; else { - ubifs_err("indexing node without indexing flag"); + ubifs_err(c, "indexing node without indexing flag"); goto out_print; } } if (!is_idx && (lp->flags & LPROPS_INDEX)) { - ubifs_err("data node with indexing flag"); + ubifs_err(c, "data node with indexing flag"); goto out_print; } @@ -1241,7 +1241,7 @@ static int scan_check_cb(struct ubifs_info *c, return LPT_SCAN_CONTINUE; out_print: - ubifs_err("bad accounting of LEB %d: free %d, dirty %d flags %#x, should be free %d, dirty %d", + ubifs_err(c, "bad accounting of LEB %d: free %d, dirty %d flags %#x, should be free %d, dirty %d", lnum, lp->free, lp->dirty, lp->flags, free, dirty); ubifs_dump_leb(c, lnum); out_destroy: @@ -1293,11 +1293,11 @@ int dbg_check_lprops(struct ubifs_info *c) lst.total_free != c->lst.total_free || lst.total_dirty != c->lst.total_dirty || lst.total_used != c->lst.total_used) { - ubifs_err("bad overall accounting"); - ubifs_err("calculated: empty_lebs %d, idx_lebs %d, total_free %lld, total_dirty %lld, total_used %lld", + ubifs_err(c, "bad overall accounting"); + ubifs_err(c, "calculated: empty_lebs %d, idx_lebs %d, total_free %lld, total_dirty %lld, total_used %lld", lst.empty_lebs, lst.idx_lebs, lst.total_free, lst.total_dirty, lst.total_used); - ubifs_err("read from lprops: empty_lebs %d, idx_lebs %d, total_free %lld, total_dirty %lld, total_used %lld", + ubifs_err(c, "read from lprops: empty_lebs %d, idx_lebs %d, total_free %lld, total_dirty %lld, total_used %lld", c->lst.empty_lebs, c->lst.idx_lebs, c->lst.total_free, c->lst.total_dirty, c->lst.total_used); err = -EINVAL; @@ -1306,10 +1306,10 @@ int dbg_check_lprops(struct ubifs_info *c) if (lst.total_dead != c->lst.total_dead || lst.total_dark != c->lst.total_dark) { - ubifs_err("bad dead/dark space accounting"); - ubifs_err("calculated: total_dead %lld, total_dark %lld", + ubifs_err(c, "bad dead/dark space accounting"); + ubifs_err(c, "calculated: total_dead %lld, total_dark %lld", lst.total_dead, lst.total_dark); - ubifs_err("read from lprops: total_dead %lld, total_dark %lld", + ubifs_err(c, "read from lprops: total_dead %lld, total_dark %lld", c->lst.total_dead, c->lst.total_dark); err = -EINVAL; goto out; diff --git a/fs/ubifs/lpt.c b/fs/ubifs/lpt.c index 421bd0a80424..dc9f27e9d61b 100644 --- a/fs/ubifs/lpt.c +++ b/fs/ubifs/lpt.c @@ -145,13 +145,13 @@ int ubifs_calc_lpt_geom(struct ubifs_info *c) sz = c->lpt_sz * 2; /* Must have at least 2 times the size */ lebs_needed = div_u64(sz + c->leb_size - 1, c->leb_size); if (lebs_needed > c->lpt_lebs) { - ubifs_err("too few LPT LEBs"); + ubifs_err(c, "too few LPT LEBs"); return -EINVAL; } /* Verify that ltab fits in a single LEB (since ltab is a single node */ if (c->ltab_sz > c->leb_size) { - ubifs_err("LPT ltab too big"); + ubifs_err(c, "LPT ltab too big"); return -EINVAL; } @@ -213,7 +213,7 @@ static int calc_dflt_lpt_geom(struct ubifs_info *c, int *main_lebs, continue; } if (c->ltab_sz > c->leb_size) { - ubifs_err("LPT ltab too big"); + ubifs_err(c, "LPT ltab too big"); return -EINVAL; } *main_lebs = c->main_lebs; @@ -911,7 +911,7 @@ static void replace_cats(struct ubifs_info *c, struct ubifs_pnode *old_pnode, * * This function returns %0 on success and a negative error code on failure. */ -static int check_lpt_crc(void *buf, int len) +static int check_lpt_crc(const struct ubifs_info *c, void *buf, int len) { int pos = 0; uint8_t *addr = buf; @@ -921,8 +921,8 @@ static int check_lpt_crc(void *buf, int len) calc_crc = crc16(-1, buf + UBIFS_LPT_CRC_BYTES, len - UBIFS_LPT_CRC_BYTES); if (crc != calc_crc) { - ubifs_err("invalid crc in LPT node: crc %hx calc %hx", crc, - calc_crc); + ubifs_err(c, "invalid crc in LPT node: crc %hx calc %hx", + crc, calc_crc); dump_stack(); return -EINVAL; } @@ -938,14 +938,15 @@ static int check_lpt_crc(void *buf, int len) * * This function returns %0 on success and a negative error code on failure. */ -static int check_lpt_type(uint8_t **addr, int *pos, int type) +static int check_lpt_type(const struct ubifs_info *c, uint8_t **addr, + int *pos, int type) { int node_type; node_type = ubifs_unpack_bits(addr, pos, UBIFS_LPT_TYPE_BITS); if (node_type != type) { - ubifs_err("invalid type (%d) in LPT node type %d", node_type, - type); + ubifs_err(c, "invalid type (%d) in LPT node type %d", + node_type, type); dump_stack(); return -EINVAL; } @@ -966,7 +967,7 @@ static int unpack_pnode(const struct ubifs_info *c, void *buf, uint8_t *addr = buf + UBIFS_LPT_CRC_BYTES; int i, pos = 0, err; - err = check_lpt_type(&addr, &pos, UBIFS_LPT_PNODE); + err = check_lpt_type(c, &addr, &pos, UBIFS_LPT_PNODE); if (err) return err; if (c->big_lpt) @@ -985,7 +986,7 @@ static int unpack_pnode(const struct ubifs_info *c, void *buf, lprops->flags = 0; lprops->flags |= ubifs_categorize_lprops(c, lprops); } - err = check_lpt_crc(buf, c->pnode_sz); + err = check_lpt_crc(c, buf, c->pnode_sz); return err; } @@ -1003,7 +1004,7 @@ int ubifs_unpack_nnode(const struct ubifs_info *c, void *buf, uint8_t *addr = buf + UBIFS_LPT_CRC_BYTES; int i, pos = 0, err; - err = check_lpt_type(&addr, &pos, UBIFS_LPT_NNODE); + err = check_lpt_type(c, &addr, &pos, UBIFS_LPT_NNODE); if (err) return err; if (c->big_lpt) @@ -1019,7 +1020,7 @@ int ubifs_unpack_nnode(const struct ubifs_info *c, void *buf, nnode->nbranch[i].offs = ubifs_unpack_bits(&addr, &pos, c->lpt_offs_bits); } - err = check_lpt_crc(buf, c->nnode_sz); + err = check_lpt_crc(c, buf, c->nnode_sz); return err; } @@ -1035,7 +1036,7 @@ static int unpack_ltab(const struct ubifs_info *c, void *buf) uint8_t *addr = buf + UBIFS_LPT_CRC_BYTES; int i, pos = 0, err; - err = check_lpt_type(&addr, &pos, UBIFS_LPT_LTAB); + err = check_lpt_type(c, &addr, &pos, UBIFS_LPT_LTAB); if (err) return err; for (i = 0; i < c->lpt_lebs; i++) { @@ -1051,7 +1052,7 @@ static int unpack_ltab(const struct ubifs_info *c, void *buf) c->ltab[i].tgc = 0; c->ltab[i].cmt = 0; } - err = check_lpt_crc(buf, c->ltab_sz); + err = check_lpt_crc(c, buf, c->ltab_sz); return err; } @@ -1067,7 +1068,7 @@ static int unpack_lsave(const struct ubifs_info *c, void *buf) uint8_t *addr = buf + UBIFS_LPT_CRC_BYTES; int i, pos = 0, err; - err = check_lpt_type(&addr, &pos, UBIFS_LPT_LSAVE); + err = check_lpt_type(c, &addr, &pos, UBIFS_LPT_LSAVE); if (err) return err; for (i = 0; i < c->lsave_cnt; i++) { @@ -1077,7 +1078,7 @@ static int unpack_lsave(const struct ubifs_info *c, void *buf) return -EINVAL; c->lsave[i] = lnum; } - err = check_lpt_crc(buf, c->lsave_sz); + err = check_lpt_crc(c, buf, c->lsave_sz); return err; } @@ -1243,7 +1244,7 @@ int ubifs_read_nnode(struct ubifs_info *c, struct ubifs_nnode *parent, int iip) return 0; out: - ubifs_err("error %d reading nnode at %d:%d", err, lnum, offs); + ubifs_err(c, "error %d reading nnode at %d:%d", err, lnum, offs); dump_stack(); kfree(nnode); return err; @@ -1308,10 +1309,10 @@ static int read_pnode(struct ubifs_info *c, struct ubifs_nnode *parent, int iip) return 0; out: - ubifs_err("error %d reading pnode at %d:%d", err, lnum, offs); + ubifs_err(c, "error %d reading pnode at %d:%d", err, lnum, offs); ubifs_dump_pnode(c, pnode, parent, iip); dump_stack(); - ubifs_err("calc num: %d", calc_pnode_num_from_parent(c, parent, iip)); + ubifs_err(c, "calc num: %d", calc_pnode_num_from_parent(c, parent, iip)); kfree(pnode); return err; } @@ -2095,7 +2096,7 @@ static int dbg_chk_pnode(struct ubifs_info *c, struct ubifs_pnode *pnode, int i; if (pnode->num != col) { - ubifs_err("pnode num %d expected %d parent num %d iip %d", + ubifs_err(c, "pnode num %d expected %d parent num %d iip %d", pnode->num, col, pnode->parent->num, pnode->iip); return -EINVAL; } @@ -2110,13 +2111,13 @@ static int dbg_chk_pnode(struct ubifs_info *c, struct ubifs_pnode *pnode, if (lnum >= c->leb_cnt) continue; if (lprops->lnum != lnum) { - ubifs_err("bad LEB number %d expected %d", + ubifs_err(c, "bad LEB number %d expected %d", lprops->lnum, lnum); return -EINVAL; } if (lprops->flags & LPROPS_TAKEN) { if (cat != LPROPS_UNCAT) { - ubifs_err("LEB %d taken but not uncat %d", + ubifs_err(c, "LEB %d taken but not uncat %d", lprops->lnum, cat); return -EINVAL; } @@ -2129,7 +2130,7 @@ static int dbg_chk_pnode(struct ubifs_info *c, struct ubifs_pnode *pnode, case LPROPS_FRDI_IDX: break; default: - ubifs_err("LEB %d index but cat %d", + ubifs_err(c, "LEB %d index but cat %d", lprops->lnum, cat); return -EINVAL; } @@ -2142,7 +2143,7 @@ static int dbg_chk_pnode(struct ubifs_info *c, struct ubifs_pnode *pnode, case LPROPS_FREEABLE: break; default: - ubifs_err("LEB %d not index but cat %d", + ubifs_err(c, "LEB %d not index but cat %d", lprops->lnum, cat); return -EINVAL; } @@ -2183,14 +2184,14 @@ static int dbg_chk_pnode(struct ubifs_info *c, struct ubifs_pnode *pnode, break; } if (!found) { - ubifs_err("LEB %d cat %d not found in cat heap/list", + ubifs_err(c, "LEB %d cat %d not found in cat heap/list", lprops->lnum, cat); return -EINVAL; } switch (cat) { case LPROPS_EMPTY: if (lprops->free != c->leb_size) { - ubifs_err("LEB %d cat %d free %d dirty %d", + ubifs_err(c, "LEB %d cat %d free %d dirty %d", lprops->lnum, cat, lprops->free, lprops->dirty); return -EINVAL; @@ -2199,7 +2200,7 @@ static int dbg_chk_pnode(struct ubifs_info *c, struct ubifs_pnode *pnode, case LPROPS_FREEABLE: case LPROPS_FRDI_IDX: if (lprops->free + lprops->dirty != c->leb_size) { - ubifs_err("LEB %d cat %d free %d dirty %d", + ubifs_err(c, "LEB %d cat %d free %d dirty %d", lprops->lnum, cat, lprops->free, lprops->dirty); return -EINVAL; @@ -2236,7 +2237,7 @@ int dbg_check_lpt_nodes(struct ubifs_info *c, struct ubifs_cnode *cnode, /* cnode is a nnode */ num = calc_nnode_num(row, col); if (cnode->num != num) { - ubifs_err("nnode num %d expected %d parent num %d iip %d", + ubifs_err(c, "nnode num %d expected %d parent num %d iip %d", cnode->num, num, (nnode ? nnode->num : 0), cnode->iip); return -EINVAL; diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c index d9c02928e992..ce89bdc3eb02 100644 --- a/fs/ubifs/lpt_commit.c +++ b/fs/ubifs/lpt_commit.c @@ -319,7 +319,7 @@ static int layout_cnodes(struct ubifs_info *c) return 0; no_space: - ubifs_err("LPT out of space at LEB %d:%d needing %d, done_ltab %d, done_lsave %d", + ubifs_err(c, "LPT out of space at LEB %d:%d needing %d, done_ltab %d, done_lsave %d", lnum, offs, len, done_ltab, done_lsave); ubifs_dump_lpt_info(c); ubifs_dump_lpt_lebs(c); @@ -543,7 +543,7 @@ static int write_cnodes(struct ubifs_info *c) return 0; no_space: - ubifs_err("LPT out of space mismatch at LEB %d:%d needing %d, done_ltab %d, done_lsave %d", + ubifs_err(c, "LPT out of space mismatch at LEB %d:%d needing %d, done_ltab %d, done_lsave %d", lnum, offs, len, done_ltab, done_lsave); ubifs_dump_lpt_info(c); ubifs_dump_lpt_lebs(c); @@ -1638,7 +1638,7 @@ static int dbg_check_ltab_lnum(struct ubifs_info *c, int lnum) buf = p = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL); if (!buf) { - ubifs_err("cannot allocate memory for ltab checking"); + ubifs_err(c, "cannot allocate memory for ltab checking"); return 0; } @@ -1660,18 +1660,18 @@ static int dbg_check_ltab_lnum(struct ubifs_info *c, int lnum) continue; } if (!dbg_is_all_ff(p, len)) { - ubifs_err("invalid empty space in LEB %d at %d", + ubifs_err(c, "invalid empty space in LEB %d at %d", lnum, c->leb_size - len); err = -EINVAL; } i = lnum - c->lpt_first; if (len != c->ltab[i].free) { - ubifs_err("invalid free space in LEB %d (free %d, expected %d)", + ubifs_err(c, "invalid free space in LEB %d (free %d, expected %d)", lnum, len, c->ltab[i].free); err = -EINVAL; } if (dirty != c->ltab[i].dirty) { - ubifs_err("invalid dirty space in LEB %d (dirty %d, expected %d)", + ubifs_err(c, "invalid dirty space in LEB %d (dirty %d, expected %d)", lnum, dirty, c->ltab[i].dirty); err = -EINVAL; } @@ -1725,7 +1725,7 @@ int dbg_check_ltab(struct ubifs_info *c) for (lnum = c->lpt_first; lnum <= c->lpt_last; lnum++) { err = dbg_check_ltab_lnum(c, lnum); if (err) { - ubifs_err("failed at LEB %d", lnum); + ubifs_err(c, "failed at LEB %d", lnum); return err; } } @@ -1757,7 +1757,7 @@ int dbg_chk_lpt_free_spc(struct ubifs_info *c) free += c->leb_size; } if (free < c->lpt_sz) { - ubifs_err("LPT space error: free %lld lpt_sz %lld", + ubifs_err(c, "LPT space error: free %lld lpt_sz %lld", free, c->lpt_sz); ubifs_dump_lpt_info(c); ubifs_dump_lpt_lebs(c); @@ -1797,12 +1797,12 @@ int dbg_chk_lpt_sz(struct ubifs_info *c, int action, int len) d->chk_lpt_lebs = 0; d->chk_lpt_wastage = 0; if (c->dirty_pn_cnt > c->pnode_cnt) { - ubifs_err("dirty pnodes %d exceed max %d", + ubifs_err(c, "dirty pnodes %d exceed max %d", c->dirty_pn_cnt, c->pnode_cnt); err = -EINVAL; } if (c->dirty_nn_cnt > c->nnode_cnt) { - ubifs_err("dirty nnodes %d exceed max %d", + ubifs_err(c, "dirty nnodes %d exceed max %d", c->dirty_nn_cnt, c->nnode_cnt); err = -EINVAL; } @@ -1820,22 +1820,22 @@ int dbg_chk_lpt_sz(struct ubifs_info *c, int action, int len) chk_lpt_sz *= d->chk_lpt_lebs; chk_lpt_sz += len - c->nhead_offs; if (d->chk_lpt_sz != chk_lpt_sz) { - ubifs_err("LPT wrote %lld but space used was %lld", + ubifs_err(c, "LPT wrote %lld but space used was %lld", d->chk_lpt_sz, chk_lpt_sz); err = -EINVAL; } if (d->chk_lpt_sz > c->lpt_sz) { - ubifs_err("LPT wrote %lld but lpt_sz is %lld", + ubifs_err(c, "LPT wrote %lld but lpt_sz is %lld", d->chk_lpt_sz, c->lpt_sz); err = -EINVAL; } if (d->chk_lpt_sz2 && d->chk_lpt_sz != d->chk_lpt_sz2) { - ubifs_err("LPT layout size %lld but wrote %lld", + ubifs_err(c, "LPT layout size %lld but wrote %lld", d->chk_lpt_sz, d->chk_lpt_sz2); err = -EINVAL; } if (d->chk_lpt_sz2 && d->new_nhead_offs != len) { - ubifs_err("LPT new nhead offs: expected %d was %d", + ubifs_err(c, "LPT new nhead offs: expected %d was %d", d->new_nhead_offs, len); err = -EINVAL; } @@ -1845,7 +1845,7 @@ int dbg_chk_lpt_sz(struct ubifs_info *c, int action, int len) if (c->big_lpt) lpt_sz += c->lsave_sz; if (d->chk_lpt_sz - d->chk_lpt_wastage > lpt_sz) { - ubifs_err("LPT chk_lpt_sz %lld + waste %lld exceeds %lld", + ubifs_err(c, "LPT chk_lpt_sz %lld + waste %lld exceeds %lld", d->chk_lpt_sz, d->chk_lpt_wastage, lpt_sz); err = -EINVAL; } @@ -1887,7 +1887,7 @@ static void dump_lpt_leb(const struct ubifs_info *c, int lnum) pr_err("(pid %d) start dumping LEB %d\n", current->pid, lnum); buf = p = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL); if (!buf) { - ubifs_err("cannot allocate memory to dump LPT"); + ubifs_err(c, "cannot allocate memory to dump LPT"); return; } @@ -1962,7 +1962,7 @@ static void dump_lpt_leb(const struct ubifs_info *c, int lnum) pr_err("LEB %d:%d, lsave len\n", lnum, offs); break; default: - ubifs_err("LPT node type %d not recognized", node_type); + ubifs_err(c, "LPT node type %d not recognized", node_type); goto out; } diff --git a/fs/ubifs/master.c b/fs/ubifs/master.c index 1a4bb9e8b3b8..c6a5e39e2ba5 100644 --- a/fs/ubifs/master.c +++ b/fs/ubifs/master.c @@ -82,7 +82,7 @@ out: return -EUCLEAN; out_dump: - ubifs_err("unexpected node type %d master LEB %d:%d", + ubifs_err(c, "unexpected node type %d master LEB %d:%d", snod->type, lnum, snod->offs); ubifs_scan_destroy(sleb); return -EINVAL; @@ -240,7 +240,7 @@ static int validate_master(const struct ubifs_info *c) return 0; out: - ubifs_err("bad master node at offset %d error %d", c->mst_offs, err); + ubifs_err(c, "bad master node at offset %d error %d", c->mst_offs, err); ubifs_dump_node(c, c->mst_node); return -EINVAL; } @@ -316,7 +316,7 @@ int ubifs_read_master(struct ubifs_info *c) if (c->leb_cnt < old_leb_cnt || c->leb_cnt < UBIFS_MIN_LEB_CNT) { - ubifs_err("bad leb_cnt on master node"); + ubifs_err(c, "bad leb_cnt on master node"); ubifs_dump_node(c, c->mst_node); return -EINVAL; } diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c index 4409f486ecef..caf2d123e9ee 100644 --- a/fs/ubifs/orphan.c +++ b/fs/ubifs/orphan.c @@ -88,7 +88,7 @@ int ubifs_add_orphan(struct ubifs_info *c, ino_t inum) else if (inum > o->inum) p = &(*p)->rb_right; else { - ubifs_err("orphaned twice"); + ubifs_err(c, "orphaned twice"); spin_unlock(&c->orphan_lock); kfree(orphan); return 0; @@ -155,7 +155,7 @@ void ubifs_delete_orphan(struct ubifs_info *c, ino_t inum) } } spin_unlock(&c->orphan_lock); - ubifs_err("missing orphan ino %lu", (unsigned long)inum); + ubifs_err(c, "missing orphan ino %lu", (unsigned long)inum); dump_stack(); } @@ -287,7 +287,7 @@ static int write_orph_node(struct ubifs_info *c, int atomic) * We limit the number of orphans so that this should * never happen. */ - ubifs_err("out of space in orphan area"); + ubifs_err(c, "out of space in orphan area"); return -EINVAL; } } @@ -397,7 +397,7 @@ static int consolidate(struct ubifs_info *c) * We limit the number of orphans so that this should * never happen. */ - ubifs_err("out of space in orphan area"); + ubifs_err(c, "out of space in orphan area"); err = -EINVAL; } spin_unlock(&c->orphan_lock); @@ -569,7 +569,7 @@ static int do_kill_orphans(struct ubifs_info *c, struct ubifs_scan_leb *sleb, list_for_each_entry(snod, &sleb->nodes, list) { if (snod->type != UBIFS_ORPH_NODE) { - ubifs_err("invalid node type %d in orphan area at %d:%d", + ubifs_err(c, "invalid node type %d in orphan area at %d:%d", snod->type, sleb->lnum, snod->offs); ubifs_dump_node(c, snod->node); return -EINVAL; @@ -596,7 +596,7 @@ static int do_kill_orphans(struct ubifs_info *c, struct ubifs_scan_leb *sleb, * number. That makes this orphan node, out of date. */ if (!first) { - ubifs_err("out of order commit number %llu in orphan node at %d:%d", + ubifs_err(c, "out of order commit number %llu in orphan node at %d:%d", cmt_no, sleb->lnum, snod->offs); ubifs_dump_node(c, snod->node); return -EINVAL; @@ -831,20 +831,20 @@ static int dbg_orphan_check(struct ubifs_info *c, struct ubifs_zbranch *zbr, if (inum != ci->last_ino) { /* Lowest node type is the inode node, so it comes first */ if (key_type(c, &zbr->key) != UBIFS_INO_KEY) - ubifs_err("found orphan node ino %lu, type %d", + ubifs_err(c, "found orphan node ino %lu, type %d", (unsigned long)inum, key_type(c, &zbr->key)); ci->last_ino = inum; ci->tot_inos += 1; err = ubifs_tnc_read_node(c, zbr, ci->node); if (err) { - ubifs_err("node read failed, error %d", err); + ubifs_err(c, "node read failed, error %d", err); return err; } if (ci->node->nlink == 0) /* Must be recorded as an orphan */ if (!dbg_find_check_orphan(&ci->root, inum) && !dbg_find_orphan(c, inum)) { - ubifs_err("missing orphan, ino %lu", + ubifs_err(c, "missing orphan, ino %lu", (unsigned long)inum); ci->missing += 1; } @@ -887,7 +887,7 @@ static int dbg_scan_orphans(struct ubifs_info *c, struct check_info *ci) buf = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL); if (!buf) { - ubifs_err("cannot allocate memory to check orphans"); + ubifs_err(c, "cannot allocate memory to check orphans"); return 0; } @@ -925,7 +925,7 @@ static int dbg_check_orphans(struct ubifs_info *c) ci.root = RB_ROOT; ci.node = kmalloc(UBIFS_MAX_INO_NODE_SZ, GFP_NOFS); if (!ci.node) { - ubifs_err("out of memory"); + ubifs_err(c, "out of memory"); return -ENOMEM; } @@ -935,12 +935,12 @@ static int dbg_check_orphans(struct ubifs_info *c) err = dbg_walk_index(c, &dbg_orphan_check, NULL, &ci); if (err) { - ubifs_err("cannot scan TNC, error %d", err); + ubifs_err(c, "cannot scan TNC, error %d", err); goto out; } if (ci.missing) { - ubifs_err("%lu missing orphan(s)", ci.missing); + ubifs_err(c, "%lu missing orphan(s)", ci.missing); err = -EINVAL; goto out; } diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c index c640938f62f0..695fc71d5244 100644 --- a/fs/ubifs/recovery.c +++ b/fs/ubifs/recovery.c @@ -305,7 +305,7 @@ int ubifs_recover_master_node(struct ubifs_info *c) mst = mst2; } - ubifs_msg("recovered master node from LEB %d", + ubifs_msg(c, "recovered master node from LEB %d", (mst == mst1 ? UBIFS_MST_LNUM : UBIFS_MST_LNUM + 1)); memcpy(c->mst_node, mst, UBIFS_MST_NODE_SZ); @@ -360,13 +360,13 @@ int ubifs_recover_master_node(struct ubifs_info *c) out_err: err = -EINVAL; out_free: - ubifs_err("failed to recover master node"); + ubifs_err(c, "failed to recover master node"); if (mst1) { - ubifs_err("dumping first master node"); + ubifs_err(c, "dumping first master node"); ubifs_dump_node(c, mst1); } if (mst2) { - ubifs_err("dumping second master node"); + ubifs_err(c, "dumping second master node"); ubifs_dump_node(c, mst2); } vfree(buf2); @@ -682,7 +682,7 @@ struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum, ret, lnum, offs); break; } else { - ubifs_err("unexpected return value %d", ret); + ubifs_err(c, "unexpected return value %d", ret); err = -EINVAL; goto error; } @@ -702,7 +702,7 @@ struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum, * See header comment for this file for more * explanations about the reasons we have this check. */ - ubifs_err("corrupt empty space LEB %d:%d, corruption starts at %d", + ubifs_err(c, "corrupt empty space LEB %d:%d, corruption starts at %d", lnum, offs, corruption); /* Make sure we dump interesting non-0xFF data */ offs += corruption; @@ -788,13 +788,13 @@ struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum, corrupted_rescan: /* Re-scan the corrupted data with verbose messages */ - ubifs_err("corruption %d", ret); + ubifs_err(c, "corruption %d", ret); ubifs_scan_a_node(c, buf, len, lnum, offs, 1); corrupted: ubifs_scanned_corruption(c, lnum, offs, buf); err = -EUCLEAN; error: - ubifs_err("LEB %d scanning failed", lnum); + ubifs_err(c, "LEB %d scanning failed", lnum); ubifs_scan_destroy(sleb); return ERR_PTR(err); } @@ -826,15 +826,15 @@ static int get_cs_sqnum(struct ubifs_info *c, int lnum, int offs, goto out_free; ret = ubifs_scan_a_node(c, cs_node, UBIFS_CS_NODE_SZ, lnum, offs, 0); if (ret != SCANNED_A_NODE) { - ubifs_err("Not a valid node"); + ubifs_err(c, "Not a valid node"); goto out_err; } if (cs_node->ch.node_type != UBIFS_CS_NODE) { - ubifs_err("Node a CS node, type is %d", cs_node->ch.node_type); + ubifs_err(c, "Node a CS node, type is %d", cs_node->ch.node_type); goto out_err; } if (le64_to_cpu(cs_node->cmt_no) != c->cmt_no) { - ubifs_err("CS node cmt_no %llu != current cmt_no %llu", + ubifs_err(c, "CS node cmt_no %llu != current cmt_no %llu", (unsigned long long)le64_to_cpu(cs_node->cmt_no), c->cmt_no); goto out_err; @@ -847,7 +847,7 @@ static int get_cs_sqnum(struct ubifs_info *c, int lnum, int offs, out_err: err = -EINVAL; out_free: - ubifs_err("failed to get CS sqnum"); + ubifs_err(c, "failed to get CS sqnum"); kfree(cs_node); return err; } @@ -899,7 +899,7 @@ struct ubifs_scan_leb *ubifs_recover_log_leb(struct ubifs_info *c, int lnum, } } if (snod->sqnum > cs_sqnum) { - ubifs_err("unrecoverable log corruption in LEB %d", + ubifs_err(c, "unrecoverable log corruption in LEB %d", lnum); ubifs_scan_destroy(sleb); return ERR_PTR(-EUCLEAN); @@ -975,11 +975,8 @@ int ubifs_recover_inl_heads(struct ubifs_info *c, void *sbuf) return err; dbg_rcvry("checking LPT head at %d:%d", c->nhead_lnum, c->nhead_offs); - err = recover_head(c, c->nhead_lnum, c->nhead_offs, sbuf); - if (err) - return err; - return 0; + return recover_head(c, c->nhead_lnum, c->nhead_offs, sbuf); } /** @@ -1004,10 +1001,7 @@ static int clean_an_unclean_leb(struct ubifs_info *c, if (len == 0) { /* Nothing to read, just unmap it */ - err = ubifs_leb_unmap(c, lnum); - if (err) - return err; - return 0; + return ubifs_leb_unmap(c, lnum); } err = ubifs_leb_read(c, lnum, buf, offs, len, 0); @@ -1043,7 +1037,7 @@ static int clean_an_unclean_leb(struct ubifs_info *c, } if (ret == SCANNED_EMPTY_SPACE) { - ubifs_err("unexpected empty space at %d:%d", + ubifs_err(c, "unexpected empty space at %d:%d", lnum, offs); return -EUCLEAN; } @@ -1137,7 +1131,7 @@ static int grab_empty_leb(struct ubifs_info *c) */ lnum = ubifs_find_free_leb_for_idx(c); if (lnum < 0) { - ubifs_err("could not find an empty LEB"); + ubifs_err(c, "could not find an empty LEB"); ubifs_dump_lprops(c); ubifs_dump_budg(c, &c->bi); return lnum; @@ -1217,7 +1211,7 @@ int ubifs_rcvry_gc_commit(struct ubifs_info *c) } mutex_unlock(&wbuf->io_mutex); if (err < 0) { - ubifs_err("GC failed, error %d", err); + ubifs_err(c, "GC failed, error %d", err); if (err == -EAGAIN) err = -EINVAL; return err; @@ -1464,7 +1458,7 @@ static int fix_size_in_place(struct ubifs_info *c, struct size_entry *e) return 0; out: - ubifs_warn("inode %lu failed to fix size %lld -> %lld error %d", + ubifs_warn(c, "inode %lu failed to fix size %lld -> %lld error %d", (unsigned long)e->inum, e->i_size, e->d_size, err); return err; } diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c index 9b40a1c5e160..3ca4540130b5 100644 --- a/fs/ubifs/replay.c +++ b/fs/ubifs/replay.c @@ -458,13 +458,13 @@ int ubifs_validate_entry(struct ubifs_info *c, nlen > UBIFS_MAX_NLEN || dent->name[nlen] != 0 || strnlen(dent->name, nlen) != nlen || le64_to_cpu(dent->inum) > MAX_INUM) { - ubifs_err("bad %s node", key_type == UBIFS_DENT_KEY ? + ubifs_err(c, "bad %s node", key_type == UBIFS_DENT_KEY ? "directory entry" : "extended attribute entry"); return -EINVAL; } if (key_type != UBIFS_DENT_KEY && key_type != UBIFS_XENT_KEY) { - ubifs_err("bad key type %d", key_type); + ubifs_err(c, "bad key type %d", key_type); return -EINVAL; } @@ -589,7 +589,7 @@ static int replay_bud(struct ubifs_info *c, struct bud_entry *b) cond_resched(); if (snod->sqnum >= SQNUM_WATERMARK) { - ubifs_err("file system's life ended"); + ubifs_err(c, "file system's life ended"); goto out_dump; } @@ -647,7 +647,7 @@ static int replay_bud(struct ubifs_info *c, struct bud_entry *b) if (old_size < 0 || old_size > c->max_inode_sz || new_size < 0 || new_size > c->max_inode_sz || old_size <= new_size) { - ubifs_err("bad truncation node"); + ubifs_err(c, "bad truncation node"); goto out_dump; } @@ -662,7 +662,7 @@ static int replay_bud(struct ubifs_info *c, struct bud_entry *b) break; } default: - ubifs_err("unexpected node type %d in bud LEB %d:%d", + ubifs_err(c, "unexpected node type %d in bud LEB %d:%d", snod->type, lnum, snod->offs); err = -EINVAL; goto out_dump; @@ -685,7 +685,7 @@ out: return err; out_dump: - ubifs_err("bad node is at LEB %d:%d", lnum, snod->offs); + ubifs_err(c, "bad node is at LEB %d:%d", lnum, snod->offs); ubifs_dump_node(c, snod->node); ubifs_scan_destroy(sleb); return -EINVAL; @@ -805,7 +805,7 @@ static int validate_ref(struct ubifs_info *c, const struct ubifs_ref_node *ref) if (bud) { if (bud->jhead == jhead && bud->start <= offs) return 1; - ubifs_err("bud at LEB %d:%d was already referred", lnum, offs); + ubifs_err(c, "bud at LEB %d:%d was already referred", lnum, offs); return -EINVAL; } @@ -861,12 +861,12 @@ static int replay_log_leb(struct ubifs_info *c, int lnum, int offs, void *sbuf) * numbers. */ if (snod->type != UBIFS_CS_NODE) { - ubifs_err("first log node at LEB %d:%d is not CS node", + ubifs_err(c, "first log node at LEB %d:%d is not CS node", lnum, offs); goto out_dump; } if (le64_to_cpu(node->cmt_no) != c->cmt_no) { - ubifs_err("first CS node at LEB %d:%d has wrong commit number %llu expected %llu", + ubifs_err(c, "first CS node at LEB %d:%d has wrong commit number %llu expected %llu", lnum, offs, (unsigned long long)le64_to_cpu(node->cmt_no), c->cmt_no); @@ -891,7 +891,7 @@ static int replay_log_leb(struct ubifs_info *c, int lnum, int offs, void *sbuf) /* Make sure the first node sits at offset zero of the LEB */ if (snod->offs != 0) { - ubifs_err("first node is not at zero offset"); + ubifs_err(c, "first node is not at zero offset"); goto out_dump; } @@ -899,12 +899,12 @@ static int replay_log_leb(struct ubifs_info *c, int lnum, int offs, void *sbuf) cond_resched(); if (snod->sqnum >= SQNUM_WATERMARK) { - ubifs_err("file system's life ended"); + ubifs_err(c, "file system's life ended"); goto out_dump; } if (snod->sqnum < c->cs_sqnum) { - ubifs_err("bad sqnum %llu, commit sqnum %llu", + ubifs_err(c, "bad sqnum %llu, commit sqnum %llu", snod->sqnum, c->cs_sqnum); goto out_dump; } @@ -934,12 +934,12 @@ static int replay_log_leb(struct ubifs_info *c, int lnum, int offs, void *sbuf) case UBIFS_CS_NODE: /* Make sure it sits at the beginning of LEB */ if (snod->offs != 0) { - ubifs_err("unexpected node in log"); + ubifs_err(c, "unexpected node in log"); goto out_dump; } break; default: - ubifs_err("unexpected node in log"); + ubifs_err(c, "unexpected node in log"); goto out_dump; } } @@ -955,7 +955,7 @@ out: return err; out_dump: - ubifs_err("log error detected while replaying the log at LEB %d:%d", + ubifs_err(c, "log error detected while replaying the log at LEB %d:%d", lnum, offs + snod->offs); ubifs_dump_node(c, snod->node); ubifs_scan_destroy(sleb); @@ -1017,7 +1017,7 @@ int ubifs_replay_journal(struct ubifs_info *c) return free; /* Error code */ if (c->ihead_offs != c->leb_size - free) { - ubifs_err("bad index head LEB %d:%d", c->ihead_lnum, + ubifs_err(c, "bad index head LEB %d:%d", c->ihead_lnum, c->ihead_offs); return -EINVAL; } @@ -1040,7 +1040,7 @@ int ubifs_replay_journal(struct ubifs_info *c) * someting went wrong and we cannot proceed mounting * the file-system. */ - ubifs_err("no UBIFS nodes found at the log head LEB %d:%d, possibly corrupted", + ubifs_err(c, "no UBIFS nodes found at the log head LEB %d:%d, possibly corrupted", lnum, 0); err = -EINVAL; } diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c index 79c6dbbc0e04..f4fbc7b6b794 100644 --- a/fs/ubifs/sb.c +++ b/fs/ubifs/sb.c @@ -335,7 +335,7 @@ static int create_default_filesystem(struct ubifs_info *c) if (err) return err; - ubifs_msg("default file-system created"); + ubifs_msg(c, "default file-system created"); return 0; } @@ -365,13 +365,13 @@ static int validate_sb(struct ubifs_info *c, struct ubifs_sb_node *sup) } if (le32_to_cpu(sup->min_io_size) != c->min_io_size) { - ubifs_err("min. I/O unit mismatch: %d in superblock, %d real", + ubifs_err(c, "min. I/O unit mismatch: %d in superblock, %d real", le32_to_cpu(sup->min_io_size), c->min_io_size); goto failed; } if (le32_to_cpu(sup->leb_size) != c->leb_size) { - ubifs_err("LEB size mismatch: %d in superblock, %d real", + ubifs_err(c, "LEB size mismatch: %d in superblock, %d real", le32_to_cpu(sup->leb_size), c->leb_size); goto failed; } @@ -393,33 +393,33 @@ static int validate_sb(struct ubifs_info *c, struct ubifs_sb_node *sup) min_leb_cnt += c->lpt_lebs + c->orph_lebs + c->jhead_cnt + 6; if (c->leb_cnt < min_leb_cnt || c->leb_cnt > c->vi.size) { - ubifs_err("bad LEB count: %d in superblock, %d on UBI volume, %d minimum required", + ubifs_err(c, "bad LEB count: %d in superblock, %d on UBI volume, %d minimum required", c->leb_cnt, c->vi.size, min_leb_cnt); goto failed; } if (c->max_leb_cnt < c->leb_cnt) { - ubifs_err("max. LEB count %d less than LEB count %d", + ubifs_err(c, "max. LEB count %d less than LEB count %d", c->max_leb_cnt, c->leb_cnt); goto failed; } if (c->main_lebs < UBIFS_MIN_MAIN_LEBS) { - ubifs_err("too few main LEBs count %d, must be at least %d", + ubifs_err(c, "too few main LEBs count %d, must be at least %d", c->main_lebs, UBIFS_MIN_MAIN_LEBS); goto failed; } max_bytes = (long long)c->leb_size * UBIFS_MIN_BUD_LEBS; if (c->max_bud_bytes < max_bytes) { - ubifs_err("too small journal (%lld bytes), must be at least %lld bytes", + ubifs_err(c, "too small journal (%lld bytes), must be at least %lld bytes", c->max_bud_bytes, max_bytes); goto failed; } max_bytes = (long long)c->leb_size * c->main_lebs; if (c->max_bud_bytes > max_bytes) { - ubifs_err("too large journal size (%lld bytes), only %lld bytes available in the main area", + ubifs_err(c, "too large journal size (%lld bytes), only %lld bytes available in the main area", c->max_bud_bytes, max_bytes); goto failed; } @@ -468,7 +468,7 @@ static int validate_sb(struct ubifs_info *c, struct ubifs_sb_node *sup) return 0; failed: - ubifs_err("bad superblock, error %d", err); + ubifs_err(c, "bad superblock, error %d", err); ubifs_dump_node(c, sup); return -EINVAL; } @@ -549,12 +549,12 @@ int ubifs_read_superblock(struct ubifs_info *c) ubifs_assert(!c->ro_media || c->ro_mount); if (!c->ro_mount || c->ro_compat_version > UBIFS_RO_COMPAT_VERSION) { - ubifs_err("on-flash format version is w%d/r%d, but software only supports up to version w%d/r%d", + ubifs_err(c, "on-flash format version is w%d/r%d, but software only supports up to version w%d/r%d", c->fmt_version, c->ro_compat_version, UBIFS_FORMAT_VERSION, UBIFS_RO_COMPAT_VERSION); if (c->ro_compat_version <= UBIFS_RO_COMPAT_VERSION) { - ubifs_msg("only R/O mounting is possible"); + ubifs_msg(c, "only R/O mounting is possible"); err = -EROFS; } else err = -EINVAL; @@ -570,7 +570,7 @@ int ubifs_read_superblock(struct ubifs_info *c) } if (c->fmt_version < 3) { - ubifs_err("on-flash format version %d is not supported", + ubifs_err(c, "on-flash format version %d is not supported", c->fmt_version); err = -EINVAL; goto out; @@ -595,7 +595,7 @@ int ubifs_read_superblock(struct ubifs_info *c) c->key_len = UBIFS_SK_LEN; break; default: - ubifs_err("unsupported key format"); + ubifs_err(c, "unsupported key format"); err = -EINVAL; goto out; } @@ -785,7 +785,7 @@ int ubifs_fixup_free_space(struct ubifs_info *c) ubifs_assert(c->space_fixup); ubifs_assert(!c->ro_mount); - ubifs_msg("start fixing up free space"); + ubifs_msg(c, "start fixing up free space"); err = fixup_free_space(c); if (err) @@ -804,6 +804,6 @@ int ubifs_fixup_free_space(struct ubifs_info *c) if (err) return err; - ubifs_msg("free space fixup complete"); + ubifs_msg(c, "free space fixup complete"); return err; } diff --git a/fs/ubifs/scan.c b/fs/ubifs/scan.c index 89adbc4d08ac..aab87340d3de 100644 --- a/fs/ubifs/scan.c +++ b/fs/ubifs/scan.c @@ -100,7 +100,7 @@ int ubifs_scan_a_node(const struct ubifs_info *c, void *buf, int len, int lnum, if (pad_len < 0 || offs + node_len + pad_len > c->leb_size) { if (!quiet) { - ubifs_err("bad pad node at LEB %d:%d", + ubifs_err(c, "bad pad node at LEB %d:%d", lnum, offs); ubifs_dump_node(c, pad); } @@ -110,7 +110,7 @@ int ubifs_scan_a_node(const struct ubifs_info *c, void *buf, int len, int lnum, /* Make the node pads to 8-byte boundary */ if ((node_len + pad_len) & 7) { if (!quiet) - ubifs_err("bad padding length %d - %d", + ubifs_err(c, "bad padding length %d - %d", offs, offs + node_len + pad_len); return SCANNED_A_BAD_PAD_NODE; } @@ -152,7 +152,7 @@ struct ubifs_scan_leb *ubifs_start_scan(const struct ubifs_info *c, int lnum, err = ubifs_leb_read(c, lnum, sbuf + offs, offs, c->leb_size - offs, 0); if (err && err != -EBADMSG) { - ubifs_err("cannot read %d bytes from LEB %d:%d, error %d", + ubifs_err(c, "cannot read %d bytes from LEB %d:%d, error %d", c->leb_size - offs, lnum, offs, err); kfree(sleb); return ERR_PTR(err); @@ -240,11 +240,11 @@ void ubifs_scanned_corruption(const struct ubifs_info *c, int lnum, int offs, { int len; - ubifs_err("corruption at LEB %d:%d", lnum, offs); + ubifs_err(c, "corruption at LEB %d:%d", lnum, offs); len = c->leb_size - offs; if (len > 8192) len = 8192; - ubifs_err("first %d bytes from LEB %d:%d", len, lnum, offs); + ubifs_err(c, "first %d bytes from LEB %d:%d", len, lnum, offs); print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_OFFSET, 32, 4, buf, len, 1); } @@ -299,16 +299,16 @@ struct ubifs_scan_leb *ubifs_scan(const struct ubifs_info *c, int lnum, switch (ret) { case SCANNED_GARBAGE: - ubifs_err("garbage"); + ubifs_err(c, "garbage"); goto corrupted; case SCANNED_A_NODE: break; case SCANNED_A_CORRUPT_NODE: case SCANNED_A_BAD_PAD_NODE: - ubifs_err("bad node"); + ubifs_err(c, "bad node"); goto corrupted; default: - ubifs_err("unknown"); + ubifs_err(c, "unknown"); err = -EINVAL; goto error; } @@ -325,7 +325,7 @@ struct ubifs_scan_leb *ubifs_scan(const struct ubifs_info *c, int lnum, if (offs % c->min_io_size) { if (!quiet) - ubifs_err("empty space starts at non-aligned offset %d", + ubifs_err(c, "empty space starts at non-aligned offset %d", offs); goto corrupted; } @@ -338,7 +338,7 @@ struct ubifs_scan_leb *ubifs_scan(const struct ubifs_info *c, int lnum, for (; len; offs++, buf++, len--) if (*(uint8_t *)buf != 0xff) { if (!quiet) - ubifs_err("corrupt empty space at LEB %d:%d", + ubifs_err(c, "corrupt empty space at LEB %d:%d", lnum, offs); goto corrupted; } @@ -348,14 +348,14 @@ struct ubifs_scan_leb *ubifs_scan(const struct ubifs_info *c, int lnum, corrupted: if (!quiet) { ubifs_scanned_corruption(c, lnum, offs, buf); - ubifs_err("LEB %d scanning failed", lnum); + ubifs_err(c, "LEB %d scanning failed", lnum); } err = -EUCLEAN; ubifs_scan_destroy(sleb); return ERR_PTR(err); error: - ubifs_err("LEB %d scanning failed, error %d", lnum, err); + ubifs_err(c, "LEB %d scanning failed, error %d", lnum, err); ubifs_scan_destroy(sleb); return ERR_PTR(err); } diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 93e946561c5c..75e6f04bb795 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -70,13 +70,13 @@ static int validate_inode(struct ubifs_info *c, const struct inode *inode) const struct ubifs_inode *ui = ubifs_inode(inode); if (inode->i_size > c->max_inode_sz) { - ubifs_err("inode is too large (%lld)", + ubifs_err(c, "inode is too large (%lld)", (long long)inode->i_size); return 1; } if (ui->compr_type >= UBIFS_COMPR_TYPES_CNT) { - ubifs_err("unknown compression type %d", ui->compr_type); + ubifs_err(c, "unknown compression type %d", ui->compr_type); return 2; } @@ -90,7 +90,7 @@ static int validate_inode(struct ubifs_info *c, const struct inode *inode) return 5; if (!ubifs_compr_present(ui->compr_type)) { - ubifs_warn("inode %lu uses '%s' compression, but it was not compiled in", + ubifs_warn(c, "inode %lu uses '%s' compression, but it was not compiled in", inode->i_ino, ubifs_compr_name(ui->compr_type)); } @@ -242,14 +242,14 @@ struct inode *ubifs_iget(struct super_block *sb, unsigned long inum) return inode; out_invalid: - ubifs_err("inode %lu validation failed, error %d", inode->i_ino, err); + ubifs_err(c, "inode %lu validation failed, error %d", inode->i_ino, err); ubifs_dump_node(c, ino); ubifs_dump_inode(c, inode); err = -EINVAL; out_ino: kfree(ino); out: - ubifs_err("failed to read inode %lu, error %d", inode->i_ino, err); + ubifs_err(c, "failed to read inode %lu, error %d", inode->i_ino, err); iget_failed(inode); return ERR_PTR(err); } @@ -319,7 +319,7 @@ static int ubifs_write_inode(struct inode *inode, struct writeback_control *wbc) if (inode->i_nlink) { err = ubifs_jnl_write_inode(c, inode); if (err) - ubifs_err("can't write inode %lu, error %d", + ubifs_err(c, "can't write inode %lu, error %d", inode->i_ino, err); else err = dbg_check_inode_size(c, inode, ui->ui_size); @@ -363,7 +363,7 @@ static void ubifs_evict_inode(struct inode *inode) * Worst case we have a lost orphan inode wasting space, so a * simple error message is OK here. */ - ubifs_err("can't delete inode %lu, error %d", + ubifs_err(c, "can't delete inode %lu, error %d", inode->i_ino, err); out: @@ -492,17 +492,17 @@ static int ubifs_sync_fs(struct super_block *sb, int wait) static int init_constants_early(struct ubifs_info *c) { if (c->vi.corrupted) { - ubifs_warn("UBI volume is corrupted - read-only mode"); + ubifs_warn(c, "UBI volume is corrupted - read-only mode"); c->ro_media = 1; } if (c->di.ro_mode) { - ubifs_msg("read-only UBI device"); + ubifs_msg(c, "read-only UBI device"); c->ro_media = 1; } if (c->vi.vol_type == UBI_STATIC_VOLUME) { - ubifs_msg("static UBI volume - read-only mode"); + ubifs_msg(c, "static UBI volume - read-only mode"); c->ro_media = 1; } @@ -516,19 +516,19 @@ static int init_constants_early(struct ubifs_info *c) c->max_write_shift = fls(c->max_write_size) - 1; if (c->leb_size < UBIFS_MIN_LEB_SZ) { - ubifs_err("too small LEBs (%d bytes), min. is %d bytes", + ubifs_err(c, "too small LEBs (%d bytes), min. is %d bytes", c->leb_size, UBIFS_MIN_LEB_SZ); return -EINVAL; } if (c->leb_cnt < UBIFS_MIN_LEB_CNT) { - ubifs_err("too few LEBs (%d), min. is %d", + ubifs_err(c, "too few LEBs (%d), min. is %d", c->leb_cnt, UBIFS_MIN_LEB_CNT); return -EINVAL; } if (!is_power_of_2(c->min_io_size)) { - ubifs_err("bad min. I/O size %d", c->min_io_size); + ubifs_err(c, "bad min. I/O size %d", c->min_io_size); return -EINVAL; } @@ -539,7 +539,7 @@ static int init_constants_early(struct ubifs_info *c) if (c->max_write_size < c->min_io_size || c->max_write_size % c->min_io_size || !is_power_of_2(c->max_write_size)) { - ubifs_err("bad write buffer size %d for %d min. I/O unit", + ubifs_err(c, "bad write buffer size %d for %d min. I/O unit", c->max_write_size, c->min_io_size); return -EINVAL; } @@ -665,7 +665,7 @@ static int init_constants_sb(struct ubifs_info *c) tmp = UBIFS_CS_NODE_SZ + UBIFS_REF_NODE_SZ * c->jhead_cnt; tmp = ALIGN(tmp, c->min_io_size); if (tmp > c->leb_size) { - ubifs_err("too small LEB size %d, at least %d needed", + ubifs_err(c, "too small LEB size %d, at least %d needed", c->leb_size, tmp); return -EINVAL; } @@ -680,7 +680,7 @@ static int init_constants_sb(struct ubifs_info *c) tmp /= c->leb_size; tmp += 1; if (c->log_lebs < tmp) { - ubifs_err("too small log %d LEBs, required min. %d LEBs", + ubifs_err(c, "too small log %d LEBs, required min. %d LEBs", c->log_lebs, tmp); return -EINVAL; } @@ -772,7 +772,7 @@ static int take_gc_lnum(struct ubifs_info *c) int err; if (c->gc_lnum == -1) { - ubifs_err("no LEB for GC"); + ubifs_err(c, "no LEB for GC"); return -EINVAL; } @@ -857,7 +857,7 @@ static void free_orphans(struct ubifs_info *c) orph = list_entry(c->orph_list.next, struct ubifs_orphan, list); list_del(&orph->list); kfree(orph); - ubifs_err("orphan list not empty at unmount"); + ubifs_err(c, "orphan list not empty at unmount"); } vfree(c->orph_buf); @@ -954,7 +954,8 @@ static const match_table_t tokens = { */ static int parse_standard_option(const char *option) { - ubifs_msg("parse %s", option); + + pr_notice("UBIFS: parse %s\n", option); if (!strcmp(option, "sync")) return MS_SYNCHRONOUS; return 0; @@ -1026,7 +1027,7 @@ static int ubifs_parse_options(struct ubifs_info *c, char *options, else if (!strcmp(name, "zlib")) c->mount_opts.compr_type = UBIFS_COMPR_ZLIB; else { - ubifs_err("unknown compressor \"%s\"", name); + ubifs_err(c, "unknown compressor \"%s\"", name); //FIXME: is c ready? kfree(name); return -EINVAL; } @@ -1042,7 +1043,7 @@ static int ubifs_parse_options(struct ubifs_info *c, char *options, flag = parse_standard_option(p); if (!flag) { - ubifs_err("unrecognized mount option \"%s\" or missing value", + ubifs_err(c, "unrecognized mount option \"%s\" or missing value", p); return -EINVAL; } @@ -1105,7 +1106,7 @@ again: } /* Just disable bulk-read */ - ubifs_warn("cannot allocate %d bytes of memory for bulk-read, disabling it", + ubifs_warn(c, "cannot allocate %d bytes of memory for bulk-read, disabling it", c->max_bu_buf_len); c->mount_opts.bulk_read = 1; c->bulk_read = 0; @@ -1124,7 +1125,7 @@ static int check_free_space(struct ubifs_info *c) { ubifs_assert(c->dark_wm > 0); if (c->lst.total_free + c->lst.total_dirty < c->dark_wm) { - ubifs_err("insufficient free space to mount in R/W mode"); + ubifs_err(c, "insufficient free space to mount in R/W mode"); ubifs_dump_budg(c, &c->bi); ubifs_dump_lprops(c); return -ENOSPC; @@ -1166,14 +1167,14 @@ static int mount_ubifs(struct ubifs_info *c) * This UBI volume is empty, and read-only, or the file system * is mounted read-only - we cannot format it. */ - ubifs_err("can't format empty UBI volume: read-only %s", + ubifs_err(c, "can't format empty UBI volume: read-only %s", c->ro_media ? "UBI volume" : "mount"); err = -EROFS; goto out_free; } if (c->ro_media && !c->ro_mount) { - ubifs_err("cannot mount read-write - read-only media"); + ubifs_err(c, "cannot mount read-write - read-only media"); err = -EROFS; goto out_free; } @@ -1221,7 +1222,7 @@ static int mount_ubifs(struct ubifs_info *c) * or overridden by mount options is actually compiled in. */ if (!ubifs_compr_present(c->default_compr)) { - ubifs_err("'compressor \"%s\" is not compiled in", + ubifs_err(c, "'compressor \"%s\" is not compiled in", ubifs_compr_name(c->default_compr)); err = -ENOTSUPP; goto out_free; @@ -1250,7 +1251,7 @@ static int mount_ubifs(struct ubifs_info *c) if (IS_ERR(c->bgt)) { err = PTR_ERR(c->bgt); c->bgt = NULL; - ubifs_err("cannot spawn \"%s\", error %d", + ubifs_err(c, "cannot spawn \"%s\", error %d", c->bgt_name, err); goto out_wbufs; } @@ -1264,7 +1265,7 @@ static int mount_ubifs(struct ubifs_info *c) init_constants_master(c); if ((c->mst_node->flags & cpu_to_le32(UBIFS_MST_DIRTY)) != 0) { - ubifs_msg("recovery needed"); + ubifs_msg(c, "recovery needed"); c->need_recovery = 1; } @@ -1284,7 +1285,7 @@ static int mount_ubifs(struct ubifs_info *c) goto out_lpt; } - if (!c->ro_mount) { + if (!c->ro_mount && !c->need_recovery) { /* * Set the "dirty" flag so that if we reboot uncleanly we * will notice this immediately on the next mount. @@ -1373,10 +1374,10 @@ static int mount_ubifs(struct ubifs_info *c) if (c->need_recovery) { if (c->ro_mount) - ubifs_msg("recovery deferred"); + ubifs_msg(c, "recovery deferred"); else { c->need_recovery = 0; - ubifs_msg("recovery completed"); + ubifs_msg(c, "recovery completed"); /* * GC LEB has to be empty and taken at this point. But * the journal head LEBs may also be accounted as @@ -1397,20 +1398,20 @@ static int mount_ubifs(struct ubifs_info *c) c->mounting = 0; - ubifs_msg("mounted UBI device %d, volume %d, name \"%s\"%s", + ubifs_msg(c, "UBIFS: mounted UBI device %d, volume %d, name \"%s\"%s", c->vi.ubi_num, c->vi.vol_id, c->vi.name, c->ro_mount ? ", R/O mode" : ""); x = (long long)c->main_lebs * c->leb_size; y = (long long)c->log_lebs * c->leb_size + c->max_bud_bytes; - ubifs_msg("LEB size: %d bytes (%d KiB), min./max. I/O unit sizes: %d bytes/%d bytes", + ubifs_msg(c, "LEB size: %d bytes (%d KiB), min./max. I/O unit sizes: %d bytes/%d bytes", c->leb_size, c->leb_size >> 10, c->min_io_size, c->max_write_size); - ubifs_msg("FS size: %lld bytes (%lld MiB, %d LEBs), journal size %lld bytes (%lld MiB, %d LEBs)", + ubifs_msg(c, "FS size: %lld bytes (%lld MiB, %d LEBs), journal size %lld bytes (%lld MiB, %d LEBs)", x, x >> 20, c->main_lebs, y, y >> 20, c->log_lebs + c->max_bud_cnt); - ubifs_msg("reserved for root: %llu bytes (%llu KiB)", + ubifs_msg(c, "reserved for root: %llu bytes (%llu KiB)", c->report_rp_size, c->report_rp_size >> 10); - ubifs_msg("media format: w%d/r%d (latest is w%d/r%d), UUID %pUB%s", + ubifs_msg(c, "media format: w%d/r%d (latest is w%d/r%d), UUID %pUB%s", c->fmt_version, c->ro_compat_version, UBIFS_FORMAT_VERSION, UBIFS_RO_COMPAT_VERSION, c->uuid, c->big_lpt ? ", big LPT model" : ", small LPT model"); @@ -1543,8 +1544,8 @@ static int ubifs_remount_rw(struct ubifs_info *c) int err, lnum; if (c->rw_incompat) { - ubifs_err("the file-system is not R/W-compatible"); - ubifs_msg("on-flash format version is w%d/r%d, but software only supports up to version w%d/r%d", + ubifs_err(c, "the file-system is not R/W-compatible"); + ubifs_msg(c, "on-flash format version is w%d/r%d, but software only supports up to version w%d/r%d", c->fmt_version, c->ro_compat_version, UBIFS_FORMAT_VERSION, UBIFS_RO_COMPAT_VERSION); return -EROFS; @@ -1581,7 +1582,7 @@ static int ubifs_remount_rw(struct ubifs_info *c) } if (c->need_recovery) { - ubifs_msg("completing deferred recovery"); + ubifs_msg(c, "completing deferred recovery"); err = ubifs_write_rcvrd_mst_node(c); if (err) goto out; @@ -1630,7 +1631,7 @@ static int ubifs_remount_rw(struct ubifs_info *c) if (IS_ERR(c->bgt)) { err = PTR_ERR(c->bgt); c->bgt = NULL; - ubifs_err("cannot spawn \"%s\", error %d", + ubifs_err(c, "cannot spawn \"%s\", error %d", c->bgt_name, err); goto out; } @@ -1664,7 +1665,7 @@ static int ubifs_remount_rw(struct ubifs_info *c) if (c->need_recovery) { c->need_recovery = 0; - ubifs_msg("deferred recovery completed"); + ubifs_msg(c, "deferred recovery completed"); } else { /* * Do not run the debugging space check if the were doing @@ -1752,8 +1753,7 @@ static void ubifs_put_super(struct super_block *sb) int i; struct ubifs_info *c = sb->s_fs_info; - ubifs_msg("un-mount UBI device %d, volume %d", c->vi.ubi_num, - c->vi.vol_id); + ubifs_msg(c, "un-mount UBI device %d", c->vi.ubi_num); /* * The following asserts are only valid if there has not been a failure @@ -1809,7 +1809,7 @@ static void ubifs_put_super(struct super_block *sb) * next mount, so we just print a message and * continue to unmount normally. */ - ubifs_err("failed to write master node, error %d", + ubifs_err(c, "failed to write master node, error %d", err); } else { for (i = 0; i < c->jhead_cnt; i++) @@ -1834,17 +1834,17 @@ static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data) err = ubifs_parse_options(c, data, 1); if (err) { - ubifs_err("invalid or unknown remount parameter"); + ubifs_err(c, "invalid or unknown remount parameter"); return err; } if (c->ro_mount && !(*flags & MS_RDONLY)) { if (c->ro_error) { - ubifs_msg("cannot re-mount R/W due to prior errors"); + ubifs_msg(c, "cannot re-mount R/W due to prior errors"); return -EROFS; } if (c->ro_media) { - ubifs_msg("cannot re-mount R/W - UBI volume is R/O"); + ubifs_msg(c, "cannot re-mount R/W - UBI volume is R/O"); return -EROFS; } err = ubifs_remount_rw(c); @@ -1852,7 +1852,7 @@ static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data) return err; } else if (!c->ro_mount && (*flags & MS_RDONLY)) { if (c->ro_error) { - ubifs_msg("cannot re-mount R/O due to prior errors"); + ubifs_msg(c, "cannot re-mount R/O due to prior errors"); return -EROFS; } ubifs_remount_ro(c); @@ -2104,8 +2104,8 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags, */ ubi = open_ubi(name, UBI_READONLY); if (IS_ERR(ubi)) { - ubifs_err("cannot open \"%s\", error %d", - name, (int)PTR_ERR(ubi)); + pr_err("UBIFS error (pid: %d): cannot open \"%s\", error %d", + current->pid, name, (int)PTR_ERR(ubi)); return ERR_CAST(ubi); } @@ -2233,8 +2233,8 @@ static int __init ubifs_init(void) * UBIFS_BLOCK_SIZE. It is assumed that both are powers of 2. */ if (PAGE_CACHE_SIZE < UBIFS_BLOCK_SIZE) { - ubifs_err("VFS page cache size is %u bytes, but UBIFS requires at least 4096 bytes", - (unsigned int)PAGE_CACHE_SIZE); + pr_err("UBIFS error (pid %d): VFS page cache size is %u bytes, but UBIFS requires at least 4096 bytes", + current->pid, (unsigned int)PAGE_CACHE_SIZE); return -EINVAL; } @@ -2257,7 +2257,8 @@ static int __init ubifs_init(void) err = register_filesystem(&ubifs_fs_type); if (err) { - ubifs_err("cannot register file system, error %d", err); + pr_err("UBIFS error (pid %d): cannot register file system, error %d", + current->pid, err); goto out_dbg; } return 0; diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index 6793db0754f6..957f5757f374 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -98,7 +98,7 @@ static int insert_old_idx(struct ubifs_info *c, int lnum, int offs) else if (offs > o->offs) p = &(*p)->rb_right; else { - ubifs_err("old idx added twice!"); + ubifs_err(c, "old idx added twice!"); kfree(old_idx); return 0; } @@ -447,7 +447,7 @@ static int try_read_node(const struct ubifs_info *c, void *buf, int type, err = ubifs_leb_read(c, lnum, buf, offs, len, 1); if (err) { - ubifs_err("cannot read node type %d from LEB %d:%d, error %d", + ubifs_err(c, "cannot read node type %d from LEB %d:%d, error %d", type, lnum, offs, err); return err; } @@ -1684,27 +1684,27 @@ static int validate_data_node(struct ubifs_info *c, void *buf, int err, len; if (ch->node_type != UBIFS_DATA_NODE) { - ubifs_err("bad node type (%d but expected %d)", + ubifs_err(c, "bad node type (%d but expected %d)", ch->node_type, UBIFS_DATA_NODE); goto out_err; } err = ubifs_check_node(c, buf, zbr->lnum, zbr->offs, 0, 0); if (err) { - ubifs_err("expected node type %d", UBIFS_DATA_NODE); + ubifs_err(c, "expected node type %d", UBIFS_DATA_NODE); goto out; } len = le32_to_cpu(ch->len); if (len != zbr->len) { - ubifs_err("bad node length %d, expected %d", len, zbr->len); + ubifs_err(c, "bad node length %d, expected %d", len, zbr->len); goto out_err; } /* Make sure the key of the read node is correct */ key_read(c, buf + UBIFS_KEY_OFFSET, &key1); if (!keys_eq(c, &zbr->key, &key1)) { - ubifs_err("bad key in node at LEB %d:%d", + ubifs_err(c, "bad key in node at LEB %d:%d", zbr->lnum, zbr->offs); dbg_tnck(&zbr->key, "looked for key "); dbg_tnck(&key1, "found node's key "); @@ -1716,7 +1716,7 @@ static int validate_data_node(struct ubifs_info *c, void *buf, out_err: err = -EINVAL; out: - ubifs_err("bad node at LEB %d:%d", zbr->lnum, zbr->offs); + ubifs_err(c, "bad node at LEB %d:%d", zbr->lnum, zbr->offs); ubifs_dump_node(c, buf); dump_stack(); return err; @@ -1741,7 +1741,7 @@ int ubifs_tnc_bulk_read(struct ubifs_info *c, struct bu_info *bu) len = bu->zbranch[bu->cnt - 1].offs; len += bu->zbranch[bu->cnt - 1].len - offs; if (len > bu->buf_len) { - ubifs_err("buffer too small %d vs %d", bu->buf_len, len); + ubifs_err(c, "buffer too small %d vs %d", bu->buf_len, len); return -EINVAL; } @@ -1757,7 +1757,7 @@ int ubifs_tnc_bulk_read(struct ubifs_info *c, struct bu_info *bu) return -EAGAIN; if (err && err != -EBADMSG) { - ubifs_err("failed to read from LEB %d:%d, error %d", + ubifs_err(c, "failed to read from LEB %d:%d, error %d", lnum, offs, err); dump_stack(); dbg_tnck(&bu->key, "key "); @@ -3313,7 +3313,7 @@ int dbg_check_inode_size(struct ubifs_info *c, const struct inode *inode, out_dump: block = key_block(c, key); - ubifs_err("inode %lu has size %lld, but there are data at offset %lld", + ubifs_err(c, "inode %lu has size %lld, but there are data at offset %lld", (unsigned long)inode->i_ino, size, ((loff_t)block) << UBIFS_BLOCK_SHIFT); mutex_unlock(&c->tnc_mutex); diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c index 7a205e046776..b45345d701e7 100644 --- a/fs/ubifs/tnc_commit.c +++ b/fs/ubifs/tnc_commit.c @@ -53,7 +53,7 @@ static int make_idx_node(struct ubifs_info *c, struct ubifs_idx_node *idx, br->offs = cpu_to_le32(zbr->offs); br->len = cpu_to_le32(zbr->len); if (!zbr->lnum || !zbr->len) { - ubifs_err("bad ref in znode"); + ubifs_err(c, "bad ref in znode"); ubifs_dump_znode(c, znode); if (zbr->znode) ubifs_dump_znode(c, zbr->znode); @@ -384,7 +384,7 @@ static int layout_in_gaps(struct ubifs_info *c, int cnt) * Do not print scary warnings if the debugging * option which forces in-the-gaps is enabled. */ - ubifs_warn("out of space"); + ubifs_warn(c, "out of space"); ubifs_dump_budg(c, &c->bi); ubifs_dump_lprops(c); } @@ -441,7 +441,7 @@ static int layout_in_empty_space(struct ubifs_info *c) /* Determine the index node position */ if (lnum == -1) { if (c->ileb_nxt >= c->ileb_cnt) { - ubifs_err("out of space"); + ubifs_err(c, "out of space"); return -ENOSPC; } lnum = c->ilebs[c->ileb_nxt++]; @@ -855,7 +855,7 @@ static int write_index(struct ubifs_info *c) br->offs = cpu_to_le32(zbr->offs); br->len = cpu_to_le32(zbr->len); if (!zbr->lnum || !zbr->len) { - ubifs_err("bad ref in znode"); + ubifs_err(c, "bad ref in znode"); ubifs_dump_znode(c, znode); if (zbr->znode) ubifs_dump_znode(c, zbr->znode); @@ -875,7 +875,7 @@ static int write_index(struct ubifs_info *c) if (lnum != znode->lnum || offs != znode->offs || len != znode->len) { - ubifs_err("inconsistent znode posn"); + ubifs_err(c, "inconsistent znode posn"); return -EINVAL; } @@ -973,7 +973,7 @@ static int write_index(struct ubifs_info *c) if (lnum != c->dbg->new_ihead_lnum || buf_offs != c->dbg->new_ihead_offs) { - ubifs_err("inconsistent ihead"); + ubifs_err(c, "inconsistent ihead"); return -EINVAL; } diff --git a/fs/ubifs/tnc_misc.c b/fs/ubifs/tnc_misc.c index f6bf8995c7b1..93f5b7859e6f 100644 --- a/fs/ubifs/tnc_misc.c +++ b/fs/ubifs/tnc_misc.c @@ -293,9 +293,9 @@ static int read_znode(struct ubifs_info *c, int lnum, int offs, int len, lnum, offs, znode->level, znode->child_cnt); if (znode->child_cnt > c->fanout || znode->level > UBIFS_MAX_LEVELS) { - ubifs_err("current fanout %d, branch count %d", + ubifs_err(c, "current fanout %d, branch count %d", c->fanout, znode->child_cnt); - ubifs_err("max levels %d, znode level %d", + ubifs_err(c, "max levels %d, znode level %d", UBIFS_MAX_LEVELS, znode->level); err = 1; goto out_dump; @@ -316,7 +316,7 @@ static int read_znode(struct ubifs_info *c, int lnum, int offs, int len, if (zbr->lnum < c->main_first || zbr->lnum >= c->leb_cnt || zbr->offs < 0 || zbr->offs + zbr->len > c->leb_size || zbr->offs & 7) { - ubifs_err("bad branch %d", i); + ubifs_err(c, "bad branch %d", i); err = 2; goto out_dump; } @@ -328,7 +328,7 @@ static int read_znode(struct ubifs_info *c, int lnum, int offs, int len, case UBIFS_XENT_KEY: break; default: - ubifs_err("bad key type at slot %d: %d", + ubifs_err(c, "bad key type at slot %d: %d", i, key_type(c, &zbr->key)); err = 3; goto out_dump; @@ -340,17 +340,17 @@ static int read_znode(struct ubifs_info *c, int lnum, int offs, int len, type = key_type(c, &zbr->key); if (c->ranges[type].max_len == 0) { if (zbr->len != c->ranges[type].len) { - ubifs_err("bad target node (type %d) length (%d)", + ubifs_err(c, "bad target node (type %d) length (%d)", type, zbr->len); - ubifs_err("have to be %d", c->ranges[type].len); + ubifs_err(c, "have to be %d", c->ranges[type].len); err = 4; goto out_dump; } } else if (zbr->len < c->ranges[type].min_len || zbr->len > c->ranges[type].max_len) { - ubifs_err("bad target node (type %d) length (%d)", + ubifs_err(c, "bad target node (type %d) length (%d)", type, zbr->len); - ubifs_err("have to be in range of %d-%d", + ubifs_err(c, "have to be in range of %d-%d", c->ranges[type].min_len, c->ranges[type].max_len); err = 5; @@ -370,12 +370,12 @@ static int read_znode(struct ubifs_info *c, int lnum, int offs, int len, cmp = keys_cmp(c, key1, key2); if (cmp > 0) { - ubifs_err("bad key order (keys %d and %d)", i, i + 1); + ubifs_err(c, "bad key order (keys %d and %d)", i, i + 1); err = 6; goto out_dump; } else if (cmp == 0 && !is_hash_key(c, key1)) { /* These can only be keys with colliding hash */ - ubifs_err("keys %d and %d are not hashed but equivalent", + ubifs_err(c, "keys %d and %d are not hashed but equivalent", i, i + 1); err = 7; goto out_dump; @@ -386,7 +386,7 @@ static int read_znode(struct ubifs_info *c, int lnum, int offs, int len, return 0; out_dump: - ubifs_err("bad indexing node at LEB %d:%d, error %d", lnum, offs, err); + ubifs_err(c, "bad indexing node at LEB %d:%d, error %d", lnum, offs, err); ubifs_dump_node(c, idx); kfree(idx); return -EINVAL; @@ -482,7 +482,7 @@ int ubifs_tnc_read_node(struct ubifs_info *c, struct ubifs_zbranch *zbr, /* Make sure the key of the read node is correct */ key_read(c, node + UBIFS_KEY_OFFSET, &key1); if (!keys_eq(c, key, &key1)) { - ubifs_err("bad key in node at LEB %d:%d", + ubifs_err(c, "bad key in node at LEB %d:%d", zbr->lnum, zbr->offs); dbg_tnck(key, "looked for key "); dbg_tnck(&key1, "but found node's key "); diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index bc04b9c69891..de759022f3d6 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -43,15 +43,19 @@ #define UBIFS_VERSION 1 /* Normal UBIFS messages */ -#define ubifs_msg(fmt, ...) pr_notice("UBIFS: " fmt "\n", ##__VA_ARGS__) +#define ubifs_msg(c, fmt, ...) \ + pr_notice("UBIFS (ubi%d:%d): " fmt "\n", \ + (c)->vi.ubi_num, (c)->vi.vol_id, ##__VA_ARGS__) /* UBIFS error messages */ -#define ubifs_err(fmt, ...) \ - pr_err("UBIFS error (pid %d): %s: " fmt "\n", current->pid, \ +#define ubifs_err(c, fmt, ...) \ + pr_err("UBIFS error (ubi%d:%d pid %d): %s: " fmt "\n", \ + (c)->vi.ubi_num, (c)->vi.vol_id, current->pid, \ __func__, ##__VA_ARGS__) /* UBIFS warning messages */ -#define ubifs_warn(fmt, ...) \ - pr_warn("UBIFS warning (pid %d): %s: " fmt "\n", \ - current->pid, __func__, ##__VA_ARGS__) +#define ubifs_warn(c, fmt, ...) \ + pr_warn("UBIFS warning (ubi%d:%d pid %d): %s: " fmt "\n", \ + (c)->vi.ubi_num, (c)->vi.vol_id, current->pid, \ + __func__, ##__VA_ARGS__) /* * A variant of 'ubifs_err()' which takes the UBIFS file-sytem description * object as an argument. @@ -59,7 +63,7 @@ #define ubifs_errc(c, fmt, ...) \ do { \ if (!(c)->probing) \ - ubifs_err(fmt, ##__VA_ARGS__); \ + ubifs_err(c, fmt, ##__VA_ARGS__); \ } while (0) /* UBIFS file system VFS magic number */ @@ -158,7 +162,7 @@ #define WORST_COMPR_FACTOR 2 /* - * How much memory is needed for a buffer where we comress a data node. + * How much memory is needed for a buffer where we compress a data node. */ #define COMPRESSED_DATA_NODE_BUF_SZ \ (UBIFS_DATA_NODE_SZ + UBIFS_BLOCK_SIZE * WORST_COMPR_FACTOR) @@ -664,7 +668,7 @@ typedef int (*ubifs_lpt_scan_callback)(struct ubifs_info *c, * @lock: serializes @buf, @lnum, @offs, @avail, @used, @next_ino and @inodes * fields * @softlimit: soft write-buffer timeout interval - * @delta: hard and soft timeouts delta (the timer expire inteval is @softlimit + * @delta: hard and soft timeouts delta (the timer expire interval is @softlimit * and @softlimit + @delta) * @timer: write-buffer timer * @no_timer: non-zero if this write-buffer does not have a timer @@ -930,9 +934,9 @@ struct ubifs_orphan { /** * struct ubifs_mount_opts - UBIFS-specific mount options information. * @unmount_mode: selected unmount mode (%0 default, %1 normal, %2 fast) - * @bulk_read: enable/disable bulk-reads (%0 default, %1 disabe, %2 enable) + * @bulk_read: enable/disable bulk-reads (%0 default, %1 disable, %2 enable) * @chk_data_crc: enable/disable CRC data checking when reading data nodes - * (%0 default, %1 disabe, %2 enable) + * (%0 default, %1 disable, %2 enable) * @override_compr: override default compressor (%0 - do not override and use * superblock compressor, %1 - override and use compressor * specified in @compr_type) @@ -962,9 +966,9 @@ struct ubifs_mount_opts { * optimization) * @nospace_rp: the same as @nospace, but additionally means that even reserved * pool is full - * @page_budget: budget for a page (constant, nenver changed after mount) - * @inode_budget: budget for an inode (constant, nenver changed after mount) - * @dent_budget: budget for a directory entry (constant, nenver changed after + * @page_budget: budget for a page (constant, never changed after mount) + * @inode_budget: budget for an inode (constant, never changed after mount) + * @dent_budget: budget for a directory entry (constant, never changed after * mount) */ struct ubifs_budg_info { @@ -1787,10 +1791,10 @@ long ubifs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg); /* compressor.c */ int __init ubifs_compressors_init(void); void ubifs_compressors_exit(void); -void ubifs_compress(const void *in_buf, int in_len, void *out_buf, int *out_len, - int *compr_type); -int ubifs_decompress(const void *buf, int len, void *out, int *out_len, - int compr_type); +void ubifs_compress(const struct ubifs_info *c, const void *in_buf, int in_len, + void *out_buf, int *out_len, int *compr_type); +int ubifs_decompress(const struct ubifs_info *c, const void *buf, int len, + void *out, int *out_len, int compr_type); #include "debug.h" #include "misc.h" diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index a92be244a6fb..3659b1934500 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -108,7 +108,7 @@ static int create_xattr(struct ubifs_info *c, struct inode *host, .dirtied_ino_d = ALIGN(host_ui->data_len, 8) }; if (host_ui->xattr_cnt >= MAX_XATTRS_PER_INODE) { - ubifs_err("inode %lu already has too many xattrs (%d), cannot create more", + ubifs_err(c, "inode %lu already has too many xattrs (%d), cannot create more", host->i_ino, host_ui->xattr_cnt); return -ENOSPC; } @@ -120,7 +120,7 @@ static int create_xattr(struct ubifs_info *c, struct inode *host, */ names_len = host_ui->xattr_names + host_ui->xattr_cnt + nm->len + 1; if (names_len > XATTR_LIST_MAX) { - ubifs_err("cannot add one more xattr name to inode %lu, total names length would become %d, max. is %d", + ubifs_err(c, "cannot add one more xattr name to inode %lu, total names length would become %d, max. is %d", host->i_ino, names_len, XATTR_LIST_MAX); return -ENOSPC; } @@ -288,13 +288,13 @@ static struct inode *iget_xattr(struct ubifs_info *c, ino_t inum) inode = ubifs_iget(c->vfs_sb, inum); if (IS_ERR(inode)) { - ubifs_err("dead extended attribute entry, error %d", + ubifs_err(c, "dead extended attribute entry, error %d", (int)PTR_ERR(inode)); return inode; } if (ubifs_inode(inode)->xattr) return inode; - ubifs_err("corrupt extended attribute entry"); + ubifs_err(c, "corrupt extended attribute entry"); iput(inode); return ERR_PTR(-EINVAL); } @@ -412,7 +412,7 @@ ssize_t ubifs_getxattr(struct dentry *dentry, const char *name, void *buf, if (buf) { /* If @buf is %NULL we are supposed to return the length */ if (ui->data_len > size) { - ubifs_err("buffer size %zd, xattr len %d", + ubifs_err(c, "buffer size %zd, xattr len %d", size, ui->data_len); err = -ERANGE; goto out_iput; @@ -485,7 +485,7 @@ ssize_t ubifs_listxattr(struct dentry *dentry, char *buffer, size_t size) kfree(pxent); if (err != -ENOENT) { - ubifs_err("cannot find next direntry, error %d", err); + ubifs_err(c, "cannot find next direntry, error %d", err); return err; } @@ -657,8 +657,10 @@ int ubifs_init_security(struct inode *dentry, struct inode *inode, &init_xattrs, 0); mutex_unlock(&inode->i_mutex); - if (err) - ubifs_err("cannot initialize security for inode %lu, error %d", + if (err) { + struct ubifs_info *c = dentry->i_sb->s_fs_info; + ubifs_err(c, "cannot initialize security for inode %lu, error %d", inode->i_ino, err); + } return err; } diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c index 1ba2baaf4367..6d6a96b4e73f 100644 --- a/fs/udf/balloc.c +++ b/fs/udf/balloc.c @@ -21,7 +21,6 @@ #include "udfdecl.h" -#include <linux/buffer_head.h> #include <linux/bitops.h> #include "udf_i.h" @@ -63,15 +62,14 @@ static int __load_block_bitmap(struct super_block *sb, block_group, nr_groups); } - if (bitmap->s_block_bitmap[block_group]) { + if (bitmap->s_block_bitmap[block_group]) return block_group; - } else { - retval = read_block_bitmap(sb, bitmap, block_group, - block_group); - if (retval < 0) - return retval; - return block_group; - } + + retval = read_block_bitmap(sb, bitmap, block_group, block_group); + if (retval < 0) + return retval; + + return block_group; } static inline int load_block_bitmap(struct super_block *sb, @@ -358,7 +356,6 @@ static void udf_table_free_blocks(struct super_block *sb, struct kernel_lb_addr eloc; struct extent_position oepos, epos; int8_t etype; - int i; struct udf_inode_info *iinfo; mutex_lock(&sbi->s_alloc_mutex); @@ -425,7 +422,6 @@ static void udf_table_free_blocks(struct super_block *sb, } if (epos.bh != oepos.bh) { - i = -1; oepos.block = epos.block; brelse(oepos.bh); get_bh(epos.bh); @@ -762,7 +758,7 @@ inline int udf_prealloc_blocks(struct super_block *sb, uint32_t block_count) { struct udf_part_map *map = &UDF_SB(sb)->s_partmaps[partition]; - sector_t allocated; + int allocated; if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_BITMAP) allocated = udf_bitmap_prealloc_blocks(sb, diff --git a/fs/udf/dir.c b/fs/udf/dir.c index 05e90edd1992..541a12b5792d 100644 --- a/fs/udf/dir.c +++ b/fs/udf/dir.c @@ -30,7 +30,6 @@ #include <linux/errno.h> #include <linux/mm.h> #include <linux/slab.h> -#include <linux/buffer_head.h> #include "udf_i.h" #include "udf_sb.h" diff --git a/fs/udf/directory.c b/fs/udf/directory.c index 3e44f575fb9c..c763fda257bf 100644 --- a/fs/udf/directory.c +++ b/fs/udf/directory.c @@ -16,7 +16,6 @@ #include <linux/fs.h> #include <linux/string.h> -#include <linux/buffer_head.h> struct fileIdentDesc *udf_fileident_read(struct inode *dir, loff_t *nf_pos, struct udf_fileident_bh *fibh, diff --git a/fs/udf/file.c b/fs/udf/file.c index 08f3555fbeac..5dadad9960b9 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -33,8 +33,7 @@ #include <linux/capability.h> #include <linux/errno.h> #include <linux/pagemap.h> -#include <linux/buffer_head.h> -#include <linux/aio.h> +#include <linux/uio.h> #include "udf_i.h" #include "udf_sb.h" @@ -100,8 +99,7 @@ static int udf_adinicb_write_begin(struct file *file, return 0; } -static ssize_t udf_adinicb_direct_IO(int rw, struct kiocb *iocb, - struct iov_iter *iter, +static ssize_t udf_adinicb_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) { /* Fallback to buffered I/O. */ @@ -121,21 +119,21 @@ static ssize_t udf_file_write_iter(struct kiocb *iocb, struct iov_iter *from) ssize_t retval; struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); - int err, pos; - size_t count = iocb->ki_nbytes; struct udf_inode_info *iinfo = UDF_I(inode); + int err; mutex_lock(&inode->i_mutex); + + retval = generic_write_checks(iocb, from); + if (retval <= 0) + goto out; + down_write(&iinfo->i_data_sem); if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { - if (file->f_flags & O_APPEND) - pos = inode->i_size; - else - pos = iocb->ki_pos; + loff_t end = iocb->ki_pos + iov_iter_count(from); if (inode->i_sb->s_blocksize < - (udf_file_entry_alloc_offset(inode) + - pos + count)) { + (udf_file_entry_alloc_offset(inode) + end)) { err = udf_expand_file_adinicb(inode); if (err) { mutex_unlock(&inode->i_mutex); @@ -143,16 +141,14 @@ static ssize_t udf_file_write_iter(struct kiocb *iocb, struct iov_iter *from) return err; } } else { - if (pos + count > inode->i_size) - iinfo->i_lenAlloc = pos + count; - else - iinfo->i_lenAlloc = inode->i_size; + iinfo->i_lenAlloc = max(end, inode->i_size); up_write(&iinfo->i_data_sem); } } else up_write(&iinfo->i_data_sem); retval = __generic_file_write_iter(iocb, from); +out: mutex_unlock(&inode->i_mutex); if (retval > 0) { @@ -240,12 +236,10 @@ static int udf_release_file(struct inode *inode, struct file *filp) } const struct file_operations udf_file_operations = { - .read = new_sync_read, .read_iter = generic_file_read_iter, .unlocked_ioctl = udf_ioctl, .open = generic_file_open, .mmap = generic_file_mmap, - .write = new_sync_write, .write_iter = udf_file_write_iter, .release = udf_release_file, .fsync = generic_file_fsync, diff --git a/fs/udf/inode.c b/fs/udf/inode.c index a445d599098d..6afac3d561ac 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -33,12 +33,11 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/pagemap.h> -#include <linux/buffer_head.h> #include <linux/writeback.h> #include <linux/slab.h> #include <linux/crc-itu-t.h> #include <linux/mpage.h> -#include <linux/aio.h> +#include <linux/uio.h> #include "udf_i.h" #include "udf_sb.h" @@ -215,8 +214,7 @@ static int udf_write_begin(struct file *file, struct address_space *mapping, return ret; } -static ssize_t udf_direct_IO(int rw, struct kiocb *iocb, - struct iov_iter *iter, +static ssize_t udf_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; @@ -225,8 +223,8 @@ static ssize_t udf_direct_IO(int rw, struct kiocb *iocb, size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, udf_get_block); - if (unlikely(ret < 0 && (rw & WRITE))) + ret = blockdev_direct_IO(iocb, inode, iter, offset, udf_get_block); + if (unlikely(ret < 0 && iov_iter_rw(iter) == WRITE)) udf_write_failed(mapping, offset + count); return ret; } @@ -1637,7 +1635,7 @@ static int udf_update_inode(struct inode *inode, int do_sync) udf_get_lb_pblock(inode->i_sb, &iinfo->i_location, 0)); if (!bh) { udf_debug("getblk failure\n"); - return -ENOMEM; + return -EIO; } lock_buffer(bh); diff --git a/fs/udf/misc.c b/fs/udf/misc.c index c175b4dabc14..71d1c25f360d 100644 --- a/fs/udf/misc.c +++ b/fs/udf/misc.c @@ -23,7 +23,6 @@ #include <linux/fs.h> #include <linux/string.h> -#include <linux/buffer_head.h> #include <linux/crc-itu-t.h> #include "udf_i.h" diff --git a/fs/udf/namei.c b/fs/udf/namei.c index 33b246b82c98..39661977c89c 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -27,7 +27,6 @@ #include <linux/errno.h> #include <linux/mm.h> #include <linux/slab.h> -#include <linux/buffer_head.h> #include <linux/sched.h> #include <linux/crc-itu-t.h> #include <linux/exportfs.h> @@ -569,8 +568,8 @@ static int udf_add_nondir(struct dentry *dentry, struct inode *inode) *(__le32 *)((struct allocDescImpUse *)cfi.icb.impUse)->impUse = cpu_to_le32(iinfo->i_unique & 0x00000000FFFFFFFFUL); udf_write_fi(dir, &cfi, fi, &fibh, NULL, NULL); - if (UDF_I(dir)->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) - mark_inode_dirty(dir); + dir->i_ctime = dir->i_mtime = current_fs_time(dir->i_sb); + mark_inode_dirty(dir); if (fibh.sbh != fibh.ebh) brelse(fibh.ebh); brelse(fibh.sbh); @@ -683,6 +682,7 @@ static int udf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) cfi.fileCharacteristics |= FID_FILE_CHAR_DIRECTORY; udf_write_fi(dir, &cfi, fi, &fibh, NULL, NULL); inc_nlink(dir); + dir->i_ctime = dir->i_mtime = current_fs_time(dir->i_sb); mark_inode_dirty(dir); unlock_new_inode(inode); d_instantiate(dentry, inode); @@ -1024,6 +1024,8 @@ static int udf_link(struct dentry *old_dentry, struct inode *dir, inc_nlink(inode); inode->i_ctime = current_fs_time(inode->i_sb); mark_inode_dirty(inode); + dir->i_ctime = dir->i_mtime = current_fs_time(dir->i_sb); + mark_inode_dirty(dir); ihold(inode); d_instantiate(dentry, inode); @@ -1127,7 +1129,9 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry, inode_dec_link_count(new_inode); } old_dir->i_ctime = old_dir->i_mtime = current_fs_time(old_dir->i_sb); + new_dir->i_ctime = new_dir->i_mtime = current_fs_time(new_dir->i_sb); mark_inode_dirty(old_dir); + mark_inode_dirty(new_dir); if (dir_fi) { dir_fi->icb.extLocation = cpu_to_lelb(UDF_I(new_dir)->i_location); diff --git a/fs/udf/partition.c b/fs/udf/partition.c index d6caf01a2097..5f861ed287c3 100644 --- a/fs/udf/partition.c +++ b/fs/udf/partition.c @@ -24,7 +24,6 @@ #include <linux/fs.h> #include <linux/string.h> -#include <linux/buffer_head.h> #include <linux/mutex.h> uint32_t udf_get_pblock(struct super_block *sb, uint32_t block, diff --git a/fs/udf/super.c b/fs/udf/super.c index f169411c4ea0..6299f341967b 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -48,7 +48,6 @@ #include <linux/stat.h> #include <linux/cdrom.h> #include <linux/nls.h> -#include <linux/buffer_head.h> #include <linux/vfs.h> #include <linux/vmalloc.h> #include <linux/errno.h> diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c index ac10ca939f26..8dfbc4025e2f 100644 --- a/fs/udf/symlink.c +++ b/fs/udf/symlink.c @@ -27,7 +27,6 @@ #include <linux/mm.h> #include <linux/stat.h> #include <linux/pagemap.h> -#include <linux/buffer_head.h> #include "udf_i.h" static int udf_pc_to_char(struct super_block *sb, unsigned char *from, diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c index 8a9657d7f7c6..42b8c57795cb 100644 --- a/fs/udf/truncate.c +++ b/fs/udf/truncate.c @@ -22,7 +22,6 @@ #include "udfdecl.h" #include <linux/fs.h> #include <linux/mm.h> -#include <linux/buffer_head.h> #include "udf_i.h" #include "udf_sb.h" diff --git a/fs/ufs/file.c b/fs/ufs/file.c index c84ec010a676..042ddbf110cc 100644 --- a/fs/ufs/file.c +++ b/fs/ufs/file.c @@ -35,9 +35,7 @@ const struct file_operations ufs_file_operations = { .llseek = generic_file_llseek, - .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = new_sync_write, .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .open = generic_file_open, diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index a6fbf4472017..516162be1398 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -260,6 +260,7 @@ xfs_alloc_fix_len( rlen = rlen - (k - args->mod); else rlen = rlen - args->prod + (args->mod - k); + /* casts to (int) catch length underflows */ if ((int)rlen < (int)args->minlen) return; ASSERT(rlen >= args->minlen && rlen <= args->maxlen); @@ -286,7 +287,8 @@ xfs_alloc_fix_minleft( if (diff >= 0) return 1; args->len += diff; /* shrink the allocated space */ - if (args->len >= args->minlen) + /* casts to (int) catch length underflows */ + if ((int)args->len >= (int)args->minlen) return 1; args->agbno = NULLAGBLOCK; return 0; @@ -315,6 +317,9 @@ xfs_alloc_fixup_trees( xfs_agblock_t nfbno2; /* second new free startblock */ xfs_extlen_t nflen1=0; /* first new free length */ xfs_extlen_t nflen2=0; /* second new free length */ + struct xfs_mount *mp; + + mp = cnt_cur->bc_mp; /* * Look up the record in the by-size tree if necessary. @@ -323,13 +328,13 @@ xfs_alloc_fixup_trees( #ifdef DEBUG if ((error = xfs_alloc_get_rec(cnt_cur, &nfbno1, &nflen1, &i))) return error; - XFS_WANT_CORRUPTED_RETURN( + XFS_WANT_CORRUPTED_RETURN(mp, i == 1 && nfbno1 == fbno && nflen1 == flen); #endif } else { if ((error = xfs_alloc_lookup_eq(cnt_cur, fbno, flen, &i))) return error; - XFS_WANT_CORRUPTED_RETURN(i == 1); + XFS_WANT_CORRUPTED_RETURN(mp, i == 1); } /* * Look up the record in the by-block tree if necessary. @@ -338,13 +343,13 @@ xfs_alloc_fixup_trees( #ifdef DEBUG if ((error = xfs_alloc_get_rec(bno_cur, &nfbno1, &nflen1, &i))) return error; - XFS_WANT_CORRUPTED_RETURN( + XFS_WANT_CORRUPTED_RETURN(mp, i == 1 && nfbno1 == fbno && nflen1 == flen); #endif } else { if ((error = xfs_alloc_lookup_eq(bno_cur, fbno, flen, &i))) return error; - XFS_WANT_CORRUPTED_RETURN(i == 1); + XFS_WANT_CORRUPTED_RETURN(mp, i == 1); } #ifdef DEBUG @@ -355,7 +360,7 @@ xfs_alloc_fixup_trees( bnoblock = XFS_BUF_TO_BLOCK(bno_cur->bc_bufs[0]); cntblock = XFS_BUF_TO_BLOCK(cnt_cur->bc_bufs[0]); - XFS_WANT_CORRUPTED_RETURN( + XFS_WANT_CORRUPTED_RETURN(mp, bnoblock->bb_numrecs == cntblock->bb_numrecs); } #endif @@ -386,25 +391,25 @@ xfs_alloc_fixup_trees( */ if ((error = xfs_btree_delete(cnt_cur, &i))) return error; - XFS_WANT_CORRUPTED_RETURN(i == 1); + XFS_WANT_CORRUPTED_RETURN(mp, i == 1); /* * Add new by-size btree entry(s). */ if (nfbno1 != NULLAGBLOCK) { if ((error = xfs_alloc_lookup_eq(cnt_cur, nfbno1, nflen1, &i))) return error; - XFS_WANT_CORRUPTED_RETURN(i == 0); + XFS_WANT_CORRUPTED_RETURN(mp, i == 0); if ((error = xfs_btree_insert(cnt_cur, &i))) return error; - XFS_WANT_CORRUPTED_RETURN(i == 1); + XFS_WANT_CORRUPTED_RETURN(mp, i == 1); } if (nfbno2 != NULLAGBLOCK) { if ((error = xfs_alloc_lookup_eq(cnt_cur, nfbno2, nflen2, &i))) return error; - XFS_WANT_CORRUPTED_RETURN(i == 0); + XFS_WANT_CORRUPTED_RETURN(mp, i == 0); if ((error = xfs_btree_insert(cnt_cur, &i))) return error; - XFS_WANT_CORRUPTED_RETURN(i == 1); + XFS_WANT_CORRUPTED_RETURN(mp, i == 1); } /* * Fix up the by-block btree entry(s). @@ -415,7 +420,7 @@ xfs_alloc_fixup_trees( */ if ((error = xfs_btree_delete(bno_cur, &i))) return error; - XFS_WANT_CORRUPTED_RETURN(i == 1); + XFS_WANT_CORRUPTED_RETURN(mp, i == 1); } else { /* * Update the by-block entry to start later|be shorter. @@ -429,10 +434,10 @@ xfs_alloc_fixup_trees( */ if ((error = xfs_alloc_lookup_eq(bno_cur, nfbno2, nflen2, &i))) return error; - XFS_WANT_CORRUPTED_RETURN(i == 0); + XFS_WANT_CORRUPTED_RETURN(mp, i == 0); if ((error = xfs_btree_insert(bno_cur, &i))) return error; - XFS_WANT_CORRUPTED_RETURN(i == 1); + XFS_WANT_CORRUPTED_RETURN(mp, i == 1); } return 0; } @@ -682,7 +687,7 @@ xfs_alloc_ag_vextent_exact( error = xfs_alloc_get_rec(bno_cur, &fbno, &flen, &i); if (error) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); ASSERT(fbno <= args->agbno); /* @@ -783,7 +788,7 @@ xfs_alloc_find_best_extent( error = xfs_alloc_get_rec(*scur, sbno, slen, &i); if (error) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); xfs_alloc_compute_aligned(args, *sbno, *slen, sbnoa, slena); /* @@ -946,7 +951,7 @@ restart: if ((error = xfs_alloc_get_rec(cnt_cur, <bno, <len, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); if (ltlen >= args->minlen) break; if ((error = xfs_btree_increment(cnt_cur, 0, &i))) @@ -966,7 +971,7 @@ restart: */ if ((error = xfs_alloc_get_rec(cnt_cur, <bno, <len, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); xfs_alloc_compute_aligned(args, ltbno, ltlen, <bnoa, <lena); if (ltlena < args->minlen) @@ -999,7 +1004,7 @@ restart: cnt_cur->bc_ptrs[0] = besti; if ((error = xfs_alloc_get_rec(cnt_cur, <bno, <len, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); ASSERT(ltbno + ltlen <= be32_to_cpu(XFS_BUF_TO_AGF(args->agbp)->agf_length)); args->len = blen; if (!xfs_alloc_fix_minleft(args)) { @@ -1088,7 +1093,7 @@ restart: if (bno_cur_lt) { if ((error = xfs_alloc_get_rec(bno_cur_lt, <bno, <len, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); xfs_alloc_compute_aligned(args, ltbno, ltlen, <bnoa, <lena); if (ltlena >= args->minlen) @@ -1104,7 +1109,7 @@ restart: if (bno_cur_gt) { if ((error = xfs_alloc_get_rec(bno_cur_gt, >bno, >len, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); xfs_alloc_compute_aligned(args, gtbno, gtlen, >bnoa, >lena); if (gtlena >= args->minlen) @@ -1303,7 +1308,7 @@ restart: error = xfs_alloc_get_rec(cnt_cur, &fbno, &flen, &i); if (error) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); xfs_alloc_compute_aligned(args, fbno, flen, &rbno, &rlen); @@ -1342,7 +1347,7 @@ restart: * This can't happen in the second case above. */ rlen = XFS_EXTLEN_MIN(args->maxlen, rlen); - XFS_WANT_CORRUPTED_GOTO(rlen == 0 || + XFS_WANT_CORRUPTED_GOTO(args->mp, rlen == 0 || (rlen <= flen && rbno + rlen <= fbno + flen), error0); if (rlen < args->maxlen) { xfs_agblock_t bestfbno; @@ -1362,13 +1367,13 @@ restart: if ((error = xfs_alloc_get_rec(cnt_cur, &fbno, &flen, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); if (flen < bestrlen) break; xfs_alloc_compute_aligned(args, fbno, flen, &rbno, &rlen); rlen = XFS_EXTLEN_MIN(args->maxlen, rlen); - XFS_WANT_CORRUPTED_GOTO(rlen == 0 || + XFS_WANT_CORRUPTED_GOTO(args->mp, rlen == 0 || (rlen <= flen && rbno + rlen <= fbno + flen), error0); if (rlen > bestrlen) { @@ -1383,7 +1388,7 @@ restart: if ((error = xfs_alloc_lookup_eq(cnt_cur, bestfbno, bestflen, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); rlen = bestrlen; rbno = bestrbno; flen = bestflen; @@ -1408,7 +1413,7 @@ restart: if (!xfs_alloc_fix_minleft(args)) goto out_nominleft; rlen = args->len; - XFS_WANT_CORRUPTED_GOTO(rlen <= flen, error0); + XFS_WANT_CORRUPTED_GOTO(args->mp, rlen <= flen, error0); /* * Allocate and initialize a cursor for the by-block tree. */ @@ -1422,7 +1427,7 @@ restart: cnt_cur = bno_cur = NULL; args->len = rlen; args->agbno = rbno; - XFS_WANT_CORRUPTED_GOTO( + XFS_WANT_CORRUPTED_GOTO(args->mp, args->agbno + args->len <= be32_to_cpu(XFS_BUF_TO_AGF(args->agbp)->agf_length), error0); @@ -1467,7 +1472,7 @@ xfs_alloc_ag_vextent_small( if (i) { if ((error = xfs_alloc_get_rec(ccur, &fbno, &flen, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); } /* * Nothing in the btree, try the freelist. Make sure @@ -1493,7 +1498,7 @@ xfs_alloc_ag_vextent_small( } args->len = 1; args->agbno = fbno; - XFS_WANT_CORRUPTED_GOTO( + XFS_WANT_CORRUPTED_GOTO(args->mp, args->agbno + args->len <= be32_to_cpu(XFS_BUF_TO_AGF(args->agbp)->agf_length), error0); @@ -1579,7 +1584,7 @@ xfs_free_ag_extent( */ if ((error = xfs_alloc_get_rec(bno_cur, <bno, <len, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); /* * It's not contiguous, though. */ @@ -1591,7 +1596,8 @@ xfs_free_ag_extent( * space was invalid, it's (partly) already free. * Very bad. */ - XFS_WANT_CORRUPTED_GOTO(ltbno + ltlen <= bno, error0); + XFS_WANT_CORRUPTED_GOTO(mp, + ltbno + ltlen <= bno, error0); } } /* @@ -1606,7 +1612,7 @@ xfs_free_ag_extent( */ if ((error = xfs_alloc_get_rec(bno_cur, >bno, >len, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); /* * It's not contiguous, though. */ @@ -1618,7 +1624,7 @@ xfs_free_ag_extent( * space was invalid, it's (partly) already free. * Very bad. */ - XFS_WANT_CORRUPTED_GOTO(gtbno >= bno + len, error0); + XFS_WANT_CORRUPTED_GOTO(mp, gtbno >= bno + len, error0); } } /* @@ -1635,31 +1641,31 @@ xfs_free_ag_extent( */ if ((error = xfs_alloc_lookup_eq(cnt_cur, ltbno, ltlen, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); if ((error = xfs_btree_delete(cnt_cur, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); /* * Delete the old by-size entry on the right. */ if ((error = xfs_alloc_lookup_eq(cnt_cur, gtbno, gtlen, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); if ((error = xfs_btree_delete(cnt_cur, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); /* * Delete the old by-block entry for the right block. */ if ((error = xfs_btree_delete(bno_cur, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); /* * Move the by-block cursor back to the left neighbor. */ if ((error = xfs_btree_decrement(bno_cur, 0, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); #ifdef DEBUG /* * Check that this is the right record: delete didn't @@ -1672,7 +1678,7 @@ xfs_free_ag_extent( if ((error = xfs_alloc_get_rec(bno_cur, &xxbno, &xxlen, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO( + XFS_WANT_CORRUPTED_GOTO(mp, i == 1 && xxbno == ltbno && xxlen == ltlen, error0); } @@ -1695,17 +1701,17 @@ xfs_free_ag_extent( */ if ((error = xfs_alloc_lookup_eq(cnt_cur, ltbno, ltlen, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); if ((error = xfs_btree_delete(cnt_cur, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); /* * Back up the by-block cursor to the left neighbor, and * update its length. */ if ((error = xfs_btree_decrement(bno_cur, 0, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); nbno = ltbno; nlen = len + ltlen; if ((error = xfs_alloc_update(bno_cur, nbno, nlen))) @@ -1721,10 +1727,10 @@ xfs_free_ag_extent( */ if ((error = xfs_alloc_lookup_eq(cnt_cur, gtbno, gtlen, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); if ((error = xfs_btree_delete(cnt_cur, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); /* * Update the starting block and length of the right * neighbor in the by-block tree. @@ -1743,7 +1749,7 @@ xfs_free_ag_extent( nlen = len; if ((error = xfs_btree_insert(bno_cur, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); } xfs_btree_del_cursor(bno_cur, XFS_BTREE_NOERROR); bno_cur = NULL; @@ -1752,10 +1758,10 @@ xfs_free_ag_extent( */ if ((error = xfs_alloc_lookup_eq(cnt_cur, nbno, nlen, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 0, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 0, error0); if ((error = xfs_btree_insert(cnt_cur, &i))) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); cnt_cur = NULL; diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 15105dbc9e28..04e79d57bca6 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -86,8 +86,83 @@ STATIC void xfs_attr3_leaf_moveents(struct xfs_da_args *args, int move_count); STATIC int xfs_attr_leaf_entsize(xfs_attr_leafblock_t *leaf, int index); +/* + * attr3 block 'firstused' conversion helpers. + * + * firstused refers to the offset of the first used byte of the nameval region + * of an attr leaf block. The region starts at the tail of the block and expands + * backwards towards the middle. As such, firstused is initialized to the block + * size for an empty leaf block and is reduced from there. + * + * The attr3 block size is pegged to the fsb size and the maximum fsb is 64k. + * The in-core firstused field is 32-bit and thus supports the maximum fsb size. + * The on-disk field is only 16-bit, however, and overflows at 64k. Since this + * only occurs at exactly 64k, we use zero as a magic on-disk value to represent + * the attr block size. The following helpers manage the conversion between the + * in-core and on-disk formats. + */ + +static void +xfs_attr3_leaf_firstused_from_disk( + struct xfs_da_geometry *geo, + struct xfs_attr3_icleaf_hdr *to, + struct xfs_attr_leafblock *from) +{ + struct xfs_attr3_leaf_hdr *hdr3; + + if (from->hdr.info.magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC)) { + hdr3 = (struct xfs_attr3_leaf_hdr *) from; + to->firstused = be16_to_cpu(hdr3->firstused); + } else { + to->firstused = be16_to_cpu(from->hdr.firstused); + } + + /* + * Convert from the magic fsb size value to actual blocksize. This + * should only occur for empty blocks when the block size overflows + * 16-bits. + */ + if (to->firstused == XFS_ATTR3_LEAF_NULLOFF) { + ASSERT(!to->count && !to->usedbytes); + ASSERT(geo->blksize > USHRT_MAX); + to->firstused = geo->blksize; + } +} + +static void +xfs_attr3_leaf_firstused_to_disk( + struct xfs_da_geometry *geo, + struct xfs_attr_leafblock *to, + struct xfs_attr3_icleaf_hdr *from) +{ + struct xfs_attr3_leaf_hdr *hdr3; + uint32_t firstused; + + /* magic value should only be seen on disk */ + ASSERT(from->firstused != XFS_ATTR3_LEAF_NULLOFF); + + /* + * Scale down the 32-bit in-core firstused value to the 16-bit on-disk + * value. This only overflows at the max supported value of 64k. Use the + * magic on-disk value to represent block size in this case. + */ + firstused = from->firstused; + if (firstused > USHRT_MAX) { + ASSERT(from->firstused == geo->blksize); + firstused = XFS_ATTR3_LEAF_NULLOFF; + } + + if (from->magic == XFS_ATTR3_LEAF_MAGIC) { + hdr3 = (struct xfs_attr3_leaf_hdr *) to; + hdr3->firstused = cpu_to_be16(firstused); + } else { + to->hdr.firstused = cpu_to_be16(firstused); + } +} + void xfs_attr3_leaf_hdr_from_disk( + struct xfs_da_geometry *geo, struct xfs_attr3_icleaf_hdr *to, struct xfs_attr_leafblock *from) { @@ -104,7 +179,7 @@ xfs_attr3_leaf_hdr_from_disk( to->magic = be16_to_cpu(hdr3->info.hdr.magic); to->count = be16_to_cpu(hdr3->count); to->usedbytes = be16_to_cpu(hdr3->usedbytes); - to->firstused = be16_to_cpu(hdr3->firstused); + xfs_attr3_leaf_firstused_from_disk(geo, to, from); to->holes = hdr3->holes; for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) { @@ -118,7 +193,7 @@ xfs_attr3_leaf_hdr_from_disk( to->magic = be16_to_cpu(from->hdr.info.magic); to->count = be16_to_cpu(from->hdr.count); to->usedbytes = be16_to_cpu(from->hdr.usedbytes); - to->firstused = be16_to_cpu(from->hdr.firstused); + xfs_attr3_leaf_firstused_from_disk(geo, to, from); to->holes = from->hdr.holes; for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) { @@ -129,10 +204,11 @@ xfs_attr3_leaf_hdr_from_disk( void xfs_attr3_leaf_hdr_to_disk( + struct xfs_da_geometry *geo, struct xfs_attr_leafblock *to, struct xfs_attr3_icleaf_hdr *from) { - int i; + int i; ASSERT(from->magic == XFS_ATTR_LEAF_MAGIC || from->magic == XFS_ATTR3_LEAF_MAGIC); @@ -145,7 +221,7 @@ xfs_attr3_leaf_hdr_to_disk( hdr3->info.hdr.magic = cpu_to_be16(from->magic); hdr3->count = cpu_to_be16(from->count); hdr3->usedbytes = cpu_to_be16(from->usedbytes); - hdr3->firstused = cpu_to_be16(from->firstused); + xfs_attr3_leaf_firstused_to_disk(geo, to, from); hdr3->holes = from->holes; hdr3->pad1 = 0; @@ -160,7 +236,7 @@ xfs_attr3_leaf_hdr_to_disk( to->hdr.info.magic = cpu_to_be16(from->magic); to->hdr.count = cpu_to_be16(from->count); to->hdr.usedbytes = cpu_to_be16(from->usedbytes); - to->hdr.firstused = cpu_to_be16(from->firstused); + xfs_attr3_leaf_firstused_to_disk(geo, to, from); to->hdr.holes = from->holes; to->hdr.pad1 = 0; @@ -178,7 +254,7 @@ xfs_attr3_leaf_verify( struct xfs_attr_leafblock *leaf = bp->b_addr; struct xfs_attr3_icleaf_hdr ichdr; - xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf); + xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf); if (xfs_sb_version_hascrc(&mp->m_sb)) { struct xfs_da3_node_hdr *hdr3 = bp->b_addr; @@ -757,9 +833,10 @@ xfs_attr_shortform_allfit( struct xfs_attr3_icleaf_hdr leafhdr; int bytes; int i; + struct xfs_mount *mp = bp->b_target->bt_mount; leaf = bp->b_addr; - xfs_attr3_leaf_hdr_from_disk(&leafhdr, leaf); + xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &leafhdr, leaf); entry = xfs_attr3_leaf_entryp(leaf); bytes = sizeof(struct xfs_attr_sf_hdr); @@ -812,7 +889,7 @@ xfs_attr3_leaf_to_shortform( memcpy(tmpbuffer, bp->b_addr, args->geo->blksize); leaf = (xfs_attr_leafblock_t *)tmpbuffer; - xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf); + xfs_attr3_leaf_hdr_from_disk(args->geo, &ichdr, leaf); entry = xfs_attr3_leaf_entryp(leaf); /* XXX (dgc): buffer is about to be marked stale - why zero it? */ @@ -923,7 +1000,7 @@ xfs_attr3_leaf_to_node( btree = dp->d_ops->node_tree_p(node); leaf = bp2->b_addr; - xfs_attr3_leaf_hdr_from_disk(&icleafhdr, leaf); + xfs_attr3_leaf_hdr_from_disk(args->geo, &icleafhdr, leaf); entries = xfs_attr3_leaf_entryp(leaf); /* both on-disk, don't endian-flip twice */ @@ -988,7 +1065,7 @@ xfs_attr3_leaf_create( } ichdr.freemap[0].size = ichdr.firstused - ichdr.freemap[0].base; - xfs_attr3_leaf_hdr_to_disk(leaf, &ichdr); + xfs_attr3_leaf_hdr_to_disk(args->geo, leaf, &ichdr); xfs_trans_log_buf(args->trans, bp, 0, args->geo->blksize - 1); *bpp = bp; @@ -1073,7 +1150,7 @@ xfs_attr3_leaf_add( trace_xfs_attr_leaf_add(args); leaf = bp->b_addr; - xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf); + xfs_attr3_leaf_hdr_from_disk(args->geo, &ichdr, leaf); ASSERT(args->index >= 0 && args->index <= ichdr.count); entsize = xfs_attr_leaf_newentsize(args, NULL); @@ -1126,7 +1203,7 @@ xfs_attr3_leaf_add( tmp = xfs_attr3_leaf_add_work(bp, &ichdr, args, 0); out_log_hdr: - xfs_attr3_leaf_hdr_to_disk(leaf, &ichdr); + xfs_attr3_leaf_hdr_to_disk(args->geo, leaf, &ichdr); xfs_trans_log_buf(args->trans, bp, XFS_DA_LOGRANGE(leaf, &leaf->hdr, xfs_attr3_leaf_hdr_size(leaf))); @@ -1294,7 +1371,7 @@ xfs_attr3_leaf_compact( ichdr_dst->freemap[0].base; /* write the header back to initialise the underlying buffer */ - xfs_attr3_leaf_hdr_to_disk(leaf_dst, ichdr_dst); + xfs_attr3_leaf_hdr_to_disk(args->geo, leaf_dst, ichdr_dst); /* * Copy all entry's in the same (sorted) order, @@ -1344,9 +1421,10 @@ xfs_attr_leaf_order( { struct xfs_attr3_icleaf_hdr ichdr1; struct xfs_attr3_icleaf_hdr ichdr2; + struct xfs_mount *mp = leaf1_bp->b_target->bt_mount; - xfs_attr3_leaf_hdr_from_disk(&ichdr1, leaf1_bp->b_addr); - xfs_attr3_leaf_hdr_from_disk(&ichdr2, leaf2_bp->b_addr); + xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr1, leaf1_bp->b_addr); + xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr2, leaf2_bp->b_addr); return xfs_attr3_leaf_order(leaf1_bp, &ichdr1, leaf2_bp, &ichdr2); } @@ -1388,8 +1466,8 @@ xfs_attr3_leaf_rebalance( ASSERT(blk2->magic == XFS_ATTR_LEAF_MAGIC); leaf1 = blk1->bp->b_addr; leaf2 = blk2->bp->b_addr; - xfs_attr3_leaf_hdr_from_disk(&ichdr1, leaf1); - xfs_attr3_leaf_hdr_from_disk(&ichdr2, leaf2); + xfs_attr3_leaf_hdr_from_disk(state->args->geo, &ichdr1, leaf1); + xfs_attr3_leaf_hdr_from_disk(state->args->geo, &ichdr2, leaf2); ASSERT(ichdr2.count == 0); args = state->args; @@ -1490,8 +1568,8 @@ xfs_attr3_leaf_rebalance( ichdr1.count, count); } - xfs_attr3_leaf_hdr_to_disk(leaf1, &ichdr1); - xfs_attr3_leaf_hdr_to_disk(leaf2, &ichdr2); + xfs_attr3_leaf_hdr_to_disk(state->args->geo, leaf1, &ichdr1); + xfs_attr3_leaf_hdr_to_disk(state->args->geo, leaf2, &ichdr2); xfs_trans_log_buf(args->trans, blk1->bp, 0, args->geo->blksize - 1); xfs_trans_log_buf(args->trans, blk2->bp, 0, args->geo->blksize - 1); @@ -1684,7 +1762,7 @@ xfs_attr3_leaf_toosmall( */ blk = &state->path.blk[ state->path.active-1 ]; leaf = blk->bp->b_addr; - xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf); + xfs_attr3_leaf_hdr_from_disk(state->args->geo, &ichdr, leaf); bytes = xfs_attr3_leaf_hdr_size(leaf) + ichdr.count * sizeof(xfs_attr_leaf_entry_t) + ichdr.usedbytes; @@ -1740,7 +1818,7 @@ xfs_attr3_leaf_toosmall( if (error) return error; - xfs_attr3_leaf_hdr_from_disk(&ichdr2, bp->b_addr); + xfs_attr3_leaf_hdr_from_disk(state->args->geo, &ichdr2, bp->b_addr); bytes = state->args->geo->blksize - (state->args->geo->blksize >> 2) - @@ -1805,7 +1883,7 @@ xfs_attr3_leaf_remove( trace_xfs_attr_leaf_remove(args); leaf = bp->b_addr; - xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf); + xfs_attr3_leaf_hdr_from_disk(args->geo, &ichdr, leaf); ASSERT(ichdr.count > 0 && ichdr.count < args->geo->blksize / 8); ASSERT(args->index >= 0 && args->index < ichdr.count); @@ -1918,12 +1996,11 @@ xfs_attr3_leaf_remove( tmp = be16_to_cpu(entry->nameidx); } ichdr.firstused = tmp; - if (!ichdr.firstused) - ichdr.firstused = tmp - XFS_ATTR_LEAF_NAME_ALIGN; + ASSERT(ichdr.firstused != 0); } else { ichdr.holes = 1; /* mark as needing compaction */ } - xfs_attr3_leaf_hdr_to_disk(leaf, &ichdr); + xfs_attr3_leaf_hdr_to_disk(args->geo, leaf, &ichdr); xfs_trans_log_buf(args->trans, bp, XFS_DA_LOGRANGE(leaf, &leaf->hdr, xfs_attr3_leaf_hdr_size(leaf))); @@ -1957,8 +2034,8 @@ xfs_attr3_leaf_unbalance( drop_leaf = drop_blk->bp->b_addr; save_leaf = save_blk->bp->b_addr; - xfs_attr3_leaf_hdr_from_disk(&drophdr, drop_leaf); - xfs_attr3_leaf_hdr_from_disk(&savehdr, save_leaf); + xfs_attr3_leaf_hdr_from_disk(state->args->geo, &drophdr, drop_leaf); + xfs_attr3_leaf_hdr_from_disk(state->args->geo, &savehdr, save_leaf); entry = xfs_attr3_leaf_entryp(drop_leaf); /* @@ -2012,7 +2089,7 @@ xfs_attr3_leaf_unbalance( tmphdr.firstused = state->args->geo->blksize; /* write the header to the temp buffer to initialise it */ - xfs_attr3_leaf_hdr_to_disk(tmp_leaf, &tmphdr); + xfs_attr3_leaf_hdr_to_disk(state->args->geo, tmp_leaf, &tmphdr); if (xfs_attr3_leaf_order(save_blk->bp, &savehdr, drop_blk->bp, &drophdr)) { @@ -2039,7 +2116,7 @@ xfs_attr3_leaf_unbalance( kmem_free(tmp_leaf); } - xfs_attr3_leaf_hdr_to_disk(save_leaf, &savehdr); + xfs_attr3_leaf_hdr_to_disk(state->args->geo, save_leaf, &savehdr); xfs_trans_log_buf(state->args->trans, save_blk->bp, 0, state->args->geo->blksize - 1); @@ -2085,7 +2162,7 @@ xfs_attr3_leaf_lookup_int( trace_xfs_attr_leaf_lookup(args); leaf = bp->b_addr; - xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf); + xfs_attr3_leaf_hdr_from_disk(args->geo, &ichdr, leaf); entries = xfs_attr3_leaf_entryp(leaf); ASSERT(ichdr.count < args->geo->blksize / 8); @@ -2190,7 +2267,7 @@ xfs_attr3_leaf_getvalue( int valuelen; leaf = bp->b_addr; - xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf); + xfs_attr3_leaf_hdr_from_disk(args->geo, &ichdr, leaf); ASSERT(ichdr.count < args->geo->blksize / 8); ASSERT(args->index < ichdr.count); @@ -2391,8 +2468,9 @@ xfs_attr_leaf_lasthash( { struct xfs_attr3_icleaf_hdr ichdr; struct xfs_attr_leaf_entry *entries; + struct xfs_mount *mp = bp->b_target->bt_mount; - xfs_attr3_leaf_hdr_from_disk(&ichdr, bp->b_addr); + xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, bp->b_addr); entries = xfs_attr3_leaf_entryp(bp->b_addr); if (count) *count = ichdr.count; @@ -2486,7 +2564,7 @@ xfs_attr3_leaf_clearflag( ASSERT(entry->flags & XFS_ATTR_INCOMPLETE); #ifdef DEBUG - xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf); + xfs_attr3_leaf_hdr_from_disk(args->geo, &ichdr, leaf); ASSERT(args->index < ichdr.count); ASSERT(args->index >= 0); @@ -2550,7 +2628,7 @@ xfs_attr3_leaf_setflag( leaf = bp->b_addr; #ifdef DEBUG - xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf); + xfs_attr3_leaf_hdr_from_disk(args->geo, &ichdr, leaf); ASSERT(args->index < ichdr.count); ASSERT(args->index >= 0); #endif @@ -2629,11 +2707,11 @@ xfs_attr3_leaf_flipflags( entry2 = &xfs_attr3_leaf_entryp(leaf2)[args->index2]; #ifdef DEBUG - xfs_attr3_leaf_hdr_from_disk(&ichdr1, leaf1); + xfs_attr3_leaf_hdr_from_disk(args->geo, &ichdr1, leaf1); ASSERT(args->index < ichdr1.count); ASSERT(args->index >= 0); - xfs_attr3_leaf_hdr_from_disk(&ichdr2, leaf2); + xfs_attr3_leaf_hdr_from_disk(args->geo, &ichdr2, leaf2); ASSERT(args->index2 < ichdr2.count); ASSERT(args->index2 >= 0); diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h index e2929da7c3ba..025c4b820c03 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.h +++ b/fs/xfs/libxfs/xfs_attr_leaf.h @@ -100,9 +100,11 @@ int xfs_attr_leaf_newentsize(struct xfs_da_args *args, int *local); int xfs_attr3_leaf_read(struct xfs_trans *tp, struct xfs_inode *dp, xfs_dablk_t bno, xfs_daddr_t mappedbno, struct xfs_buf **bpp); -void xfs_attr3_leaf_hdr_from_disk(struct xfs_attr3_icleaf_hdr *to, +void xfs_attr3_leaf_hdr_from_disk(struct xfs_da_geometry *geo, + struct xfs_attr3_icleaf_hdr *to, struct xfs_attr_leafblock *from); -void xfs_attr3_leaf_hdr_to_disk(struct xfs_attr_leafblock *to, +void xfs_attr3_leaf_hdr_to_disk(struct xfs_da_geometry *geo, + struct xfs_attr_leafblock *to, struct xfs_attr3_icleaf_hdr *from); #endif /* __XFS_ATTR_LEAF_H__ */ diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 61ec015dca16..aeffeaaac0ec 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -244,30 +244,6 @@ xfs_bmap_forkoff_reset( } } -/* - * Debug/sanity checking code - */ - -STATIC int -xfs_bmap_sanity_check( - struct xfs_mount *mp, - struct xfs_buf *bp, - int level) -{ - struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); - - if (block->bb_magic != cpu_to_be32(XFS_BMAP_CRC_MAGIC) && - block->bb_magic != cpu_to_be32(XFS_BMAP_MAGIC)) - return 0; - - if (be16_to_cpu(block->bb_level) != level || - be16_to_cpu(block->bb_numrecs) == 0 || - be16_to_cpu(block->bb_numrecs) > mp->m_bmap_dmxr[level != 0]) - return 0; - - return 1; -} - #ifdef DEBUG STATIC struct xfs_buf * xfs_bmap_get_bp( @@ -410,9 +386,6 @@ xfs_bmap_check_leaf_extents( goto error_norelse; } block = XFS_BUF_TO_BLOCK(bp); - XFS_WANT_CORRUPTED_GOTO( - xfs_bmap_sanity_check(mp, bp, level), - error0); if (level == 0) break; @@ -424,7 +397,8 @@ xfs_bmap_check_leaf_extents( xfs_check_block(block, mp, 0, 0); pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]); bno = be64_to_cpu(*pp); - XFS_WANT_CORRUPTED_GOTO(XFS_FSB_SANITY_CHECK(mp, bno), error0); + XFS_WANT_CORRUPTED_GOTO(mp, + XFS_FSB_SANITY_CHECK(mp, bno), error0); if (bp_release) { bp_release = 0; xfs_trans_brelse(NULL, bp); @@ -1029,7 +1003,7 @@ xfs_bmap_add_attrfork_btree( if ((error = xfs_bmbt_lookup_ge(cur, 0, 0, 0, &stat))) goto error0; /* must be at least one entry */ - XFS_WANT_CORRUPTED_GOTO(stat == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, stat == 1, error0); if ((error = xfs_btree_new_iroot(cur, flags, &stat))) goto error0; if (stat == 0) { @@ -1311,14 +1285,12 @@ xfs_bmap_read_extents( if (error) return error; block = XFS_BUF_TO_BLOCK(bp); - XFS_WANT_CORRUPTED_GOTO( - xfs_bmap_sanity_check(mp, bp, level), - error0); if (level == 0) break; pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]); bno = be64_to_cpu(*pp); - XFS_WANT_CORRUPTED_GOTO(XFS_FSB_SANITY_CHECK(mp, bno), error0); + XFS_WANT_CORRUPTED_GOTO(mp, + XFS_FSB_SANITY_CHECK(mp, bno), error0); xfs_trans_brelse(tp, bp); } /* @@ -1345,9 +1317,6 @@ xfs_bmap_read_extents( XFS_ERRLEVEL_LOW, ip->i_mount, block); goto error0; } - XFS_WANT_CORRUPTED_GOTO( - xfs_bmap_sanity_check(mp, bp, 0), - error0); /* * Read-ahead the next leaf block, if any. */ @@ -1755,7 +1724,9 @@ xfs_bmap_add_extent_delay_real( xfs_filblks_t temp=0; /* value for da_new calculations */ xfs_filblks_t temp2=0;/* value for da_new calculations */ int tmp_rval; /* partial logging flags */ + struct xfs_mount *mp; + mp = bma->tp ? bma->tp->t_mountp : NULL; ifp = XFS_IFORK_PTR(bma->ip, XFS_DATA_FORK); ASSERT(bma->idx >= 0); @@ -1866,15 +1837,15 @@ xfs_bmap_add_extent_delay_real( RIGHT.br_blockcount, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); error = xfs_btree_delete(bma->cur, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); error = xfs_btree_decrement(bma->cur, 0, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); error = xfs_bmbt_update(bma->cur, LEFT.br_startoff, LEFT.br_startblock, LEFT.br_blockcount + @@ -1907,7 +1878,7 @@ xfs_bmap_add_extent_delay_real( &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); error = xfs_bmbt_update(bma->cur, LEFT.br_startoff, LEFT.br_startblock, LEFT.br_blockcount + @@ -1938,7 +1909,7 @@ xfs_bmap_add_extent_delay_real( RIGHT.br_blockcount, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); error = xfs_bmbt_update(bma->cur, PREV.br_startoff, new->br_startblock, PREV.br_blockcount + @@ -1968,12 +1939,12 @@ xfs_bmap_add_extent_delay_real( &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 0, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done); bma->cur->bc_rec.b.br_state = XFS_EXT_NORM; error = xfs_btree_insert(bma->cur, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); } break; @@ -2001,7 +1972,7 @@ xfs_bmap_add_extent_delay_real( &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); error = xfs_bmbt_update(bma->cur, LEFT.br_startoff, LEFT.br_startblock, LEFT.br_blockcount + @@ -2038,12 +2009,12 @@ xfs_bmap_add_extent_delay_real( &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 0, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done); bma->cur->bc_rec.b.br_state = XFS_EXT_NORM; error = xfs_btree_insert(bma->cur, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); } if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) { @@ -2084,7 +2055,7 @@ xfs_bmap_add_extent_delay_real( RIGHT.br_blockcount, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); error = xfs_bmbt_update(bma->cur, new->br_startoff, new->br_startblock, new->br_blockcount + @@ -2122,12 +2093,12 @@ xfs_bmap_add_extent_delay_real( &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 0, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done); bma->cur->bc_rec.b.br_state = XFS_EXT_NORM; error = xfs_btree_insert(bma->cur, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); } if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) { @@ -2191,12 +2162,12 @@ xfs_bmap_add_extent_delay_real( &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 0, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done); bma->cur->bc_rec.b.br_state = XFS_EXT_NORM; error = xfs_btree_insert(bma->cur, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); } if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) { @@ -2212,9 +2183,8 @@ xfs_bmap_add_extent_delay_real( diff = (int)(temp + temp2 - startblockval(PREV.br_startblock) - (bma->cur ? bma->cur->bc_private.b.allocated : 0)); if (diff > 0) { - error = xfs_icsb_modify_counters(bma->ip->i_mount, - XFS_SBS_FDBLOCKS, - -((int64_t)diff), 0); + error = xfs_mod_fdblocks(bma->ip->i_mount, + -((int64_t)diff), false); ASSERT(!error); if (error) goto done; @@ -2265,9 +2235,8 @@ xfs_bmap_add_extent_delay_real( temp += bma->cur->bc_private.b.allocated; ASSERT(temp <= da_old); if (temp < da_old) - xfs_icsb_modify_counters(bma->ip->i_mount, - XFS_SBS_FDBLOCKS, - (int64_t)(da_old - temp), 0); + xfs_mod_fdblocks(bma->ip->i_mount, + (int64_t)(da_old - temp), false); } /* clear out the allocated field, done with it now in any case. */ @@ -2309,6 +2278,7 @@ xfs_bmap_add_extent_unwritten_real( /* left is 0, right is 1, prev is 2 */ int rval=0; /* return value (logging flags) */ int state = 0;/* state bits, accessed thru macros */ + struct xfs_mount *mp = tp->t_mountp; *logflagsp = 0; @@ -2421,19 +2391,19 @@ xfs_bmap_add_extent_unwritten_real( RIGHT.br_startblock, RIGHT.br_blockcount, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); if ((error = xfs_btree_delete(cur, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); if ((error = xfs_btree_decrement(cur, 0, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); if ((error = xfs_btree_delete(cur, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); if ((error = xfs_btree_decrement(cur, 0, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); if ((error = xfs_bmbt_update(cur, LEFT.br_startoff, LEFT.br_startblock, LEFT.br_blockcount + PREV.br_blockcount + @@ -2464,13 +2434,13 @@ xfs_bmap_add_extent_unwritten_real( PREV.br_startblock, PREV.br_blockcount, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); if ((error = xfs_btree_delete(cur, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); if ((error = xfs_btree_decrement(cur, 0, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); if ((error = xfs_bmbt_update(cur, LEFT.br_startoff, LEFT.br_startblock, LEFT.br_blockcount + PREV.br_blockcount, @@ -2499,13 +2469,13 @@ xfs_bmap_add_extent_unwritten_real( RIGHT.br_startblock, RIGHT.br_blockcount, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); if ((error = xfs_btree_delete(cur, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); if ((error = xfs_btree_decrement(cur, 0, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); if ((error = xfs_bmbt_update(cur, new->br_startoff, new->br_startblock, new->br_blockcount + RIGHT.br_blockcount, @@ -2532,7 +2502,7 @@ xfs_bmap_add_extent_unwritten_real( new->br_startblock, new->br_blockcount, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); if ((error = xfs_bmbt_update(cur, new->br_startoff, new->br_startblock, new->br_blockcount, newext))) @@ -2569,7 +2539,7 @@ xfs_bmap_add_extent_unwritten_real( PREV.br_startblock, PREV.br_blockcount, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); if ((error = xfs_bmbt_update(cur, PREV.br_startoff + new->br_blockcount, PREV.br_startblock + new->br_blockcount, @@ -2611,7 +2581,7 @@ xfs_bmap_add_extent_unwritten_real( PREV.br_startblock, PREV.br_blockcount, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); if ((error = xfs_bmbt_update(cur, PREV.br_startoff + new->br_blockcount, PREV.br_startblock + new->br_blockcount, @@ -2621,7 +2591,7 @@ xfs_bmap_add_extent_unwritten_real( cur->bc_rec.b = *new; if ((error = xfs_btree_insert(cur, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); } break; @@ -2651,7 +2621,7 @@ xfs_bmap_add_extent_unwritten_real( PREV.br_startblock, PREV.br_blockcount, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); if ((error = xfs_bmbt_update(cur, PREV.br_startoff, PREV.br_startblock, PREV.br_blockcount - new->br_blockcount, @@ -2689,7 +2659,7 @@ xfs_bmap_add_extent_unwritten_real( PREV.br_startblock, PREV.br_blockcount, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); if ((error = xfs_bmbt_update(cur, PREV.br_startoff, PREV.br_startblock, PREV.br_blockcount - new->br_blockcount, @@ -2699,11 +2669,11 @@ xfs_bmap_add_extent_unwritten_real( new->br_startblock, new->br_blockcount, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 0, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done); cur->bc_rec.b.br_state = XFS_EXT_NORM; if ((error = xfs_btree_insert(cur, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); } break; @@ -2737,7 +2707,7 @@ xfs_bmap_add_extent_unwritten_real( PREV.br_startblock, PREV.br_blockcount, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); /* new right extent - oldext */ if ((error = xfs_bmbt_update(cur, r[1].br_startoff, r[1].br_startblock, r[1].br_blockcount, @@ -2749,7 +2719,7 @@ xfs_bmap_add_extent_unwritten_real( new->br_startoff - PREV.br_startoff; if ((error = xfs_btree_insert(cur, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); /* * Reset the cursor to the position of the new extent * we are about to insert as we can't trust it after @@ -2759,12 +2729,12 @@ xfs_bmap_add_extent_unwritten_real( new->br_startblock, new->br_blockcount, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 0, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done); /* new middle extent - newext */ cur->bc_rec.b.br_state = new->br_state; if ((error = xfs_btree_insert(cur, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); } break; @@ -2944,8 +2914,8 @@ xfs_bmap_add_extent_hole_delay( } if (oldlen != newlen) { ASSERT(oldlen > newlen); - xfs_icsb_modify_counters(ip->i_mount, XFS_SBS_FDBLOCKS, - (int64_t)(oldlen - newlen), 0); + xfs_mod_fdblocks(ip->i_mount, (int64_t)(oldlen - newlen), + false); /* * Nothing to do for disk quota accounting here. */ @@ -2968,7 +2938,9 @@ xfs_bmap_add_extent_hole_real( xfs_bmbt_irec_t right; /* right neighbor extent entry */ int rval=0; /* return value (logging flags) */ int state; /* state bits, accessed thru macros */ + struct xfs_mount *mp; + mp = bma->tp ? bma->tp->t_mountp : NULL; ifp = XFS_IFORK_PTR(bma->ip, whichfork); ASSERT(bma->idx >= 0); @@ -3056,15 +3028,15 @@ xfs_bmap_add_extent_hole_real( &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); error = xfs_btree_delete(bma->cur, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); error = xfs_btree_decrement(bma->cur, 0, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); error = xfs_bmbt_update(bma->cur, left.br_startoff, left.br_startblock, left.br_blockcount + @@ -3097,7 +3069,7 @@ xfs_bmap_add_extent_hole_real( &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); error = xfs_bmbt_update(bma->cur, left.br_startoff, left.br_startblock, left.br_blockcount + @@ -3131,7 +3103,7 @@ xfs_bmap_add_extent_hole_real( right.br_blockcount, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); error = xfs_bmbt_update(bma->cur, new->br_startoff, new->br_startblock, new->br_blockcount + @@ -3161,12 +3133,12 @@ xfs_bmap_add_extent_hole_real( new->br_blockcount, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 0, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done); bma->cur->bc_rec.b.br_state = new->br_state; error = xfs_btree_insert(bma->cur, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); } break; } @@ -4160,18 +4132,15 @@ xfs_bmapi_reserve_delalloc( ASSERT(indlen > 0); if (rt) { - error = xfs_mod_incore_sb(mp, XFS_SBS_FREXTENTS, - -((int64_t)extsz), 0); + error = xfs_mod_frextents(mp, -((int64_t)extsz)); } else { - error = xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS, - -((int64_t)alen), 0); + error = xfs_mod_fdblocks(mp, -((int64_t)alen), false); } if (error) goto out_unreserve_quota; - error = xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS, - -((int64_t)indlen), 0); + error = xfs_mod_fdblocks(mp, -((int64_t)indlen), false); if (error) goto out_unreserve_blocks; @@ -4198,9 +4167,9 @@ xfs_bmapi_reserve_delalloc( out_unreserve_blocks: if (rt) - xfs_mod_incore_sb(mp, XFS_SBS_FREXTENTS, extsz, 0); + xfs_mod_frextents(mp, extsz); else - xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS, alen, 0); + xfs_mod_fdblocks(mp, alen, false); out_unreserve_quota: if (XFS_IS_QUOTA_ON(mp)) xfs_trans_unreserve_quota_nblks(NULL, ip, (long)alen, 0, rt ? @@ -4801,7 +4770,7 @@ xfs_bmap_del_extent( got.br_startblock, got.br_blockcount, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); } da_old = da_new = 0; } else { @@ -4835,7 +4804,7 @@ xfs_bmap_del_extent( } if ((error = xfs_btree_delete(cur, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); break; case 2: @@ -4935,7 +4904,8 @@ xfs_bmap_del_extent( got.br_startblock, temp, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, + i == 1, done); /* * Update the btree record back * to the original value. @@ -4956,7 +4926,7 @@ xfs_bmap_del_extent( error = -ENOSPC; goto done; } - XFS_WANT_CORRUPTED_GOTO(i == 1, done); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); } else flags |= xfs_ilog_fext(whichfork); XFS_IFORK_NEXT_SET(ip, whichfork, @@ -5012,10 +4982,8 @@ xfs_bmap_del_extent( * Nothing to do for disk quota accounting here. */ ASSERT(da_old >= da_new); - if (da_old > da_new) { - xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS, - (int64_t)(da_old - da_new), 0); - } + if (da_old > da_new) + xfs_mod_fdblocks(mp, (int64_t)(da_old - da_new), false); done: *logflagsp = flags; return error; @@ -5284,14 +5252,13 @@ xfs_bunmapi( rtexts = XFS_FSB_TO_B(mp, del.br_blockcount); do_div(rtexts, mp->m_sb.sb_rextsize); - xfs_mod_incore_sb(mp, XFS_SBS_FREXTENTS, - (int64_t)rtexts, 0); + xfs_mod_frextents(mp, (int64_t)rtexts); (void)xfs_trans_reserve_quota_nblks(NULL, ip, -((long)del.br_blockcount), 0, XFS_QMOPT_RES_RTBLKS); } else { - xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS, - (int64_t)del.br_blockcount, 0); + xfs_mod_fdblocks(mp, (int64_t)del.br_blockcount, + false); (void)xfs_trans_reserve_quota_nblks(NULL, ip, -((long)del.br_blockcount), 0, XFS_QMOPT_RES_REGBLKS); @@ -5453,6 +5420,7 @@ xfs_bmse_merge( struct xfs_bmbt_irec left; xfs_filblks_t blockcount; int error, i; + struct xfs_mount *mp = ip->i_mount; xfs_bmbt_get_all(gotp, &got); xfs_bmbt_get_all(leftp, &left); @@ -5487,19 +5455,19 @@ xfs_bmse_merge( got.br_blockcount, &i); if (error) return error; - XFS_WANT_CORRUPTED_RETURN(i == 1); + XFS_WANT_CORRUPTED_RETURN(mp, i == 1); error = xfs_btree_delete(cur, &i); if (error) return error; - XFS_WANT_CORRUPTED_RETURN(i == 1); + XFS_WANT_CORRUPTED_RETURN(mp, i == 1); /* lookup and update size of the previous extent */ error = xfs_bmbt_lookup_eq(cur, left.br_startoff, left.br_startblock, left.br_blockcount, &i); if (error) return error; - XFS_WANT_CORRUPTED_RETURN(i == 1); + XFS_WANT_CORRUPTED_RETURN(mp, i == 1); left.br_blockcount = blockcount; @@ -5518,50 +5486,92 @@ xfs_bmse_shift_one( int *current_ext, struct xfs_bmbt_rec_host *gotp, struct xfs_btree_cur *cur, - int *logflags) + int *logflags, + enum shift_direction direction) { struct xfs_ifork *ifp; + struct xfs_mount *mp; xfs_fileoff_t startoff; - struct xfs_bmbt_rec_host *leftp; + struct xfs_bmbt_rec_host *adj_irecp; struct xfs_bmbt_irec got; - struct xfs_bmbt_irec left; + struct xfs_bmbt_irec adj_irec; int error; int i; + int total_extents; + mp = ip->i_mount; ifp = XFS_IFORK_PTR(ip, whichfork); + total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t); xfs_bmbt_get_all(gotp, &got); - startoff = got.br_startoff - offset_shift_fsb; /* delalloc extents should be prevented by caller */ - XFS_WANT_CORRUPTED_RETURN(!isnullstartblock(got.br_startblock)); + XFS_WANT_CORRUPTED_RETURN(mp, !isnullstartblock(got.br_startblock)); - /* - * Check for merge if we've got an extent to the left, otherwise make - * sure there's enough room at the start of the file for the shift. - */ - if (*current_ext) { - /* grab the left extent and check for a large enough hole */ - leftp = xfs_iext_get_ext(ifp, *current_ext - 1); - xfs_bmbt_get_all(leftp, &left); + if (direction == SHIFT_LEFT) { + startoff = got.br_startoff - offset_shift_fsb; + + /* + * Check for merge if we've got an extent to the left, + * otherwise make sure there's enough room at the start + * of the file for the shift. + */ + if (!*current_ext) { + if (got.br_startoff < offset_shift_fsb) + return -EINVAL; + goto update_current_ext; + } + /* + * grab the left extent and check for a large + * enough hole. + */ + adj_irecp = xfs_iext_get_ext(ifp, *current_ext - 1); + xfs_bmbt_get_all(adj_irecp, &adj_irec); - if (startoff < left.br_startoff + left.br_blockcount) + if (startoff < + adj_irec.br_startoff + adj_irec.br_blockcount) return -EINVAL; /* check whether to merge the extent or shift it down */ - if (xfs_bmse_can_merge(&left, &got, offset_shift_fsb)) { + if (xfs_bmse_can_merge(&adj_irec, &got, + offset_shift_fsb)) { return xfs_bmse_merge(ip, whichfork, offset_shift_fsb, - *current_ext, gotp, leftp, cur, - logflags); + *current_ext, gotp, adj_irecp, + cur, logflags); } - } else if (got.br_startoff < offset_shift_fsb) - return -EINVAL; - + } else { + startoff = got.br_startoff + offset_shift_fsb; + /* nothing to move if this is the last extent */ + if (*current_ext >= (total_extents - 1)) + goto update_current_ext; + /* + * If this is not the last extent in the file, make sure there + * is enough room between current extent and next extent for + * accommodating the shift. + */ + adj_irecp = xfs_iext_get_ext(ifp, *current_ext + 1); + xfs_bmbt_get_all(adj_irecp, &adj_irec); + if (startoff + got.br_blockcount > adj_irec.br_startoff) + return -EINVAL; + /* + * Unlike a left shift (which involves a hole punch), + * a right shift does not modify extent neighbors + * in any way. We should never find mergeable extents + * in this scenario. Check anyways and warn if we + * encounter two extents that could be one. + */ + if (xfs_bmse_can_merge(&got, &adj_irec, offset_shift_fsb)) + WARN_ON_ONCE(1); + } /* * Increment the extent index for the next iteration, update the start * offset of the in-core extent and update the btree if applicable. */ - (*current_ext)++; +update_current_ext: + if (direction == SHIFT_LEFT) + (*current_ext)++; + else + (*current_ext)--; xfs_bmbt_set_startoff(gotp, startoff); *logflags |= XFS_ILOG_CORE; if (!cur) { @@ -5573,18 +5583,18 @@ xfs_bmse_shift_one( got.br_blockcount, &i); if (error) return error; - XFS_WANT_CORRUPTED_RETURN(i == 1); + XFS_WANT_CORRUPTED_RETURN(mp, i == 1); got.br_startoff = startoff; return xfs_bmbt_update(cur, got.br_startoff, got.br_startblock, - got.br_blockcount, got.br_state); + got.br_blockcount, got.br_state); } /* - * Shift extent records to the left to cover a hole. + * Shift extent records to the left/right to cover/create a hole. * * The maximum number of extents to be shifted in a single operation is - * @num_exts. @start_fsb specifies the file offset to start the shift and the + * @num_exts. @stop_fsb specifies the file offset at which to stop shift and the * file offset where we've left off is returned in @next_fsb. @offset_shift_fsb * is the length by which each extent is shifted. If there is no hole to shift * the extents into, this will be considered invalid operation and we abort @@ -5594,12 +5604,13 @@ int xfs_bmap_shift_extents( struct xfs_trans *tp, struct xfs_inode *ip, - xfs_fileoff_t start_fsb, + xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb, int *done, - xfs_fileoff_t *next_fsb, + xfs_fileoff_t stop_fsb, xfs_fsblock_t *firstblock, struct xfs_bmap_free *flist, + enum shift_direction direction, int num_exts) { struct xfs_btree_cur *cur = NULL; @@ -5609,10 +5620,11 @@ xfs_bmap_shift_extents( struct xfs_ifork *ifp; xfs_extnum_t nexts = 0; xfs_extnum_t current_ext; + xfs_extnum_t total_extents; + xfs_extnum_t stop_extent; int error = 0; int whichfork = XFS_DATA_FORK; int logflags = 0; - int total_extents; if (unlikely(XFS_TEST_ERROR( (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS && @@ -5628,6 +5640,8 @@ xfs_bmap_shift_extents( ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + ASSERT(direction == SHIFT_LEFT || direction == SHIFT_RIGHT); + ASSERT(*next_fsb != NULLFSBLOCK || direction == SHIFT_RIGHT); ifp = XFS_IFORK_PTR(ip, whichfork); if (!(ifp->if_flags & XFS_IFEXTENTS)) { @@ -5645,43 +5659,83 @@ xfs_bmap_shift_extents( } /* + * There may be delalloc extents in the data fork before the range we + * are collapsing out, so we cannot use the count of real extents here. + * Instead we have to calculate it from the incore fork. + */ + total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t); + if (total_extents == 0) { + *done = 1; + goto del_cursor; + } + + /* + * In case of first right shift, we need to initialize next_fsb + */ + if (*next_fsb == NULLFSBLOCK) { + gotp = xfs_iext_get_ext(ifp, total_extents - 1); + xfs_bmbt_get_all(gotp, &got); + *next_fsb = got.br_startoff; + if (stop_fsb > *next_fsb) { + *done = 1; + goto del_cursor; + } + } + + /* Lookup the extent index at which we have to stop */ + if (direction == SHIFT_RIGHT) { + gotp = xfs_iext_bno_to_ext(ifp, stop_fsb, &stop_extent); + /* Make stop_extent exclusive of shift range */ + stop_extent--; + } else + stop_extent = total_extents; + + /* * Look up the extent index for the fsb where we start shifting. We can * henceforth iterate with current_ext as extent list changes are locked * out via ilock. * * gotp can be null in 2 cases: 1) if there are no extents or 2) - * start_fsb lies in a hole beyond which there are no extents. Either + * *next_fsb lies in a hole beyond which there are no extents. Either * way, we are done. */ - gotp = xfs_iext_bno_to_ext(ifp, start_fsb, ¤t_ext); + gotp = xfs_iext_bno_to_ext(ifp, *next_fsb, ¤t_ext); if (!gotp) { *done = 1; goto del_cursor; } - /* - * There may be delalloc extents in the data fork before the range we - * are collapsing out, so we cannot use the count of real extents here. - * Instead we have to calculate it from the incore fork. - */ - total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t); - while (nexts++ < num_exts && current_ext < total_extents) { + /* some sanity checking before we finally start shifting extents */ + if ((direction == SHIFT_LEFT && current_ext >= stop_extent) || + (direction == SHIFT_RIGHT && current_ext <= stop_extent)) { + error = -EIO; + goto del_cursor; + } + + while (nexts++ < num_exts) { error = xfs_bmse_shift_one(ip, whichfork, offset_shift_fsb, - ¤t_ext, gotp, cur, &logflags); + ¤t_ext, gotp, cur, &logflags, + direction); if (error) goto del_cursor; + /* + * If there was an extent merge during the shift, the extent + * count can change. Update the total and grade the next record. + */ + if (direction == SHIFT_LEFT) { + total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t); + stop_extent = total_extents; + } - /* update total extent count and grab the next record */ - total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t); - if (current_ext >= total_extents) + if (current_ext == stop_extent) { + *done = 1; + *next_fsb = NULLFSBLOCK; break; + } gotp = xfs_iext_get_ext(ifp, current_ext); } - /* Check if we are done */ - if (current_ext == total_extents) { - *done = 1; - } else if (next_fsb) { + if (!*done) { xfs_bmbt_get_all(gotp, &got); *next_fsb = got.br_startoff; } @@ -5696,3 +5750,189 @@ del_cursor: return error; } + +/* + * Splits an extent into two extents at split_fsb block such that it is + * the first block of the current_ext. @current_ext is a target extent + * to be split. @split_fsb is a block where the extents is split. + * If split_fsb lies in a hole or the first block of extents, just return 0. + */ +STATIC int +xfs_bmap_split_extent_at( + struct xfs_trans *tp, + struct xfs_inode *ip, + xfs_fileoff_t split_fsb, + xfs_fsblock_t *firstfsb, + struct xfs_bmap_free *free_list) +{ + int whichfork = XFS_DATA_FORK; + struct xfs_btree_cur *cur = NULL; + struct xfs_bmbt_rec_host *gotp; + struct xfs_bmbt_irec got; + struct xfs_bmbt_irec new; /* split extent */ + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp; + xfs_fsblock_t gotblkcnt; /* new block count for got */ + xfs_extnum_t current_ext; + int error = 0; + int logflags = 0; + int i = 0; + + if (unlikely(XFS_TEST_ERROR( + (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS && + XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE), + mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) { + XFS_ERROR_REPORT("xfs_bmap_split_extent_at", + XFS_ERRLEVEL_LOW, mp); + return -EFSCORRUPTED; + } + + if (XFS_FORCED_SHUTDOWN(mp)) + return -EIO; + + ifp = XFS_IFORK_PTR(ip, whichfork); + if (!(ifp->if_flags & XFS_IFEXTENTS)) { + /* Read in all the extents */ + error = xfs_iread_extents(tp, ip, whichfork); + if (error) + return error; + } + + /* + * gotp can be null in 2 cases: 1) if there are no extents + * or 2) split_fsb lies in a hole beyond which there are + * no extents. Either way, we are done. + */ + gotp = xfs_iext_bno_to_ext(ifp, split_fsb, ¤t_ext); + if (!gotp) + return 0; + + xfs_bmbt_get_all(gotp, &got); + + /* + * Check split_fsb lies in a hole or the start boundary offset + * of the extent. + */ + if (got.br_startoff >= split_fsb) + return 0; + + gotblkcnt = split_fsb - got.br_startoff; + new.br_startoff = split_fsb; + new.br_startblock = got.br_startblock + gotblkcnt; + new.br_blockcount = got.br_blockcount - gotblkcnt; + new.br_state = got.br_state; + + if (ifp->if_flags & XFS_IFBROOT) { + cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork); + cur->bc_private.b.firstblock = *firstfsb; + cur->bc_private.b.flist = free_list; + cur->bc_private.b.flags = 0; + error = xfs_bmbt_lookup_eq(cur, got.br_startoff, + got.br_startblock, + got.br_blockcount, + &i); + if (error) + goto del_cursor; + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, del_cursor); + } + + xfs_bmbt_set_blockcount(gotp, gotblkcnt); + got.br_blockcount = gotblkcnt; + + logflags = XFS_ILOG_CORE; + if (cur) { + error = xfs_bmbt_update(cur, got.br_startoff, + got.br_startblock, + got.br_blockcount, + got.br_state); + if (error) + goto del_cursor; + } else + logflags |= XFS_ILOG_DEXT; + + /* Add new extent */ + current_ext++; + xfs_iext_insert(ip, current_ext, 1, &new, 0); + XFS_IFORK_NEXT_SET(ip, whichfork, + XFS_IFORK_NEXTENTS(ip, whichfork) + 1); + + if (cur) { + error = xfs_bmbt_lookup_eq(cur, new.br_startoff, + new.br_startblock, new.br_blockcount, + &i); + if (error) + goto del_cursor; + XFS_WANT_CORRUPTED_GOTO(mp, i == 0, del_cursor); + cur->bc_rec.b.br_state = new.br_state; + + error = xfs_btree_insert(cur, &i); + if (error) + goto del_cursor; + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, del_cursor); + } + + /* + * Convert to a btree if necessary. + */ + if (xfs_bmap_needs_btree(ip, whichfork)) { + int tmp_logflags; /* partial log flag return val */ + + ASSERT(cur == NULL); + error = xfs_bmap_extents_to_btree(tp, ip, firstfsb, free_list, + &cur, 0, &tmp_logflags, whichfork); + logflags |= tmp_logflags; + } + +del_cursor: + if (cur) { + cur->bc_private.b.allocated = 0; + xfs_btree_del_cursor(cur, + error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR); + } + + if (logflags) + xfs_trans_log_inode(tp, ip, logflags); + return error; +} + +int +xfs_bmap_split_extent( + struct xfs_inode *ip, + xfs_fileoff_t split_fsb) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_trans *tp; + struct xfs_bmap_free free_list; + xfs_fsblock_t firstfsb; + int committed; + int error; + + tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT); + error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write, + XFS_DIOSTRAT_SPACE_RES(mp, 0), 0); + if (error) { + xfs_trans_cancel(tp, 0); + return error; + } + + xfs_ilock(ip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + + xfs_bmap_init(&free_list, &firstfsb); + + error = xfs_bmap_split_extent_at(tp, ip, split_fsb, + &firstfsb, &free_list); + if (error) + goto out; + + error = xfs_bmap_finish(&tp, &free_list, &committed); + if (error) + goto out; + + return xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES); + + +out: + xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT); + return error; +} diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index b9d8a499d2c4..6aaa0c1c7200 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -166,6 +166,11 @@ static inline void xfs_bmap_init(xfs_bmap_free_t *flp, xfs_fsblock_t *fbp) */ #define XFS_BMAP_MAX_SHIFT_EXTENTS 1 +enum shift_direction { + SHIFT_LEFT = 0, + SHIFT_RIGHT, +}; + #ifdef DEBUG void xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt, int whichfork, unsigned long caller_ip); @@ -211,8 +216,10 @@ int xfs_check_nostate_extents(struct xfs_ifork *ifp, xfs_extnum_t idx, xfs_extnum_t num); uint xfs_default_attroffset(struct xfs_inode *ip); int xfs_bmap_shift_extents(struct xfs_trans *tp, struct xfs_inode *ip, - xfs_fileoff_t start_fsb, xfs_fileoff_t offset_shift_fsb, - int *done, xfs_fileoff_t *next_fsb, xfs_fsblock_t *firstblock, - struct xfs_bmap_free *flist, int num_exts); + xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb, + int *done, xfs_fileoff_t stop_fsb, xfs_fsblock_t *firstblock, + struct xfs_bmap_free *flist, enum shift_direction direction, + int num_exts); +int xfs_bmap_split_extent(struct xfs_inode *ip, xfs_fileoff_t split_offset); #endif /* __XFS_BMAP_H__ */ diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 81cad433df85..c72283dd8d44 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -168,7 +168,7 @@ xfs_btree_check_lptr( xfs_fsblock_t bno, /* btree block disk address */ int level) /* btree block level */ { - XFS_WANT_CORRUPTED_RETURN( + XFS_WANT_CORRUPTED_RETURN(cur->bc_mp, level > 0 && bno != NULLFSBLOCK && XFS_FSB_SANITY_CHECK(cur->bc_mp, bno)); @@ -187,7 +187,7 @@ xfs_btree_check_sptr( { xfs_agblock_t agblocks = cur->bc_mp->m_sb.sb_agblocks; - XFS_WANT_CORRUPTED_RETURN( + XFS_WANT_CORRUPTED_RETURN(cur->bc_mp, level > 0 && bno != NULLAGBLOCK && bno != 0 && @@ -1825,7 +1825,7 @@ xfs_btree_lookup( error = xfs_btree_increment(cur, 0, &i); if (error) goto error0; - XFS_WANT_CORRUPTED_RETURN(i == 1); + XFS_WANT_CORRUPTED_RETURN(cur->bc_mp, i == 1); XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT); *stat = 1; return 0; @@ -2285,7 +2285,7 @@ xfs_btree_rshift( if (error) goto error0; i = xfs_btree_lastrec(tcur, level); - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(cur->bc_mp, i == 1, error0); error = xfs_btree_increment(tcur, level, &i); if (error) @@ -3138,7 +3138,7 @@ xfs_btree_insert( goto error0; } - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(cur->bc_mp, i == 1, error0); level++; /* @@ -3582,15 +3582,15 @@ xfs_btree_delrec( * Actually any entry but the first would suffice. */ i = xfs_btree_lastrec(tcur, level); - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(cur->bc_mp, i == 1, error0); error = xfs_btree_increment(tcur, level, &i); if (error) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(cur->bc_mp, i == 1, error0); i = xfs_btree_lastrec(tcur, level); - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(cur->bc_mp, i == 1, error0); /* Grab a pointer to the block. */ right = xfs_btree_get_block(tcur, level, &rbp); @@ -3634,12 +3634,12 @@ xfs_btree_delrec( rrecs = xfs_btree_get_numrecs(right); if (!xfs_btree_ptr_is_null(cur, &lptr)) { i = xfs_btree_firstrec(tcur, level); - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(cur->bc_mp, i == 1, error0); error = xfs_btree_decrement(tcur, level, &i); if (error) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(cur->bc_mp, i == 1, error0); } } @@ -3653,13 +3653,13 @@ xfs_btree_delrec( * previous block. */ i = xfs_btree_firstrec(tcur, level); - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(cur->bc_mp, i == 1, error0); error = xfs_btree_decrement(tcur, level, &i); if (error) goto error0; i = xfs_btree_firstrec(tcur, level); - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(cur->bc_mp, i == 1, error0); /* Grab a pointer to the block. */ left = xfs_btree_get_block(tcur, level, &lbp); diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index 9cb0115c6bd1..2385f8cd08ab 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -538,12 +538,12 @@ xfs_da3_root_split( oldroot = blk1->bp->b_addr; if (oldroot->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC) || oldroot->hdr.info.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC)) { - struct xfs_da3_icnode_hdr nodehdr; + struct xfs_da3_icnode_hdr icnodehdr; - dp->d_ops->node_hdr_from_disk(&nodehdr, oldroot); + dp->d_ops->node_hdr_from_disk(&icnodehdr, oldroot); btree = dp->d_ops->node_tree_p(oldroot); - size = (int)((char *)&btree[nodehdr.count] - (char *)oldroot); - level = nodehdr.level; + size = (int)((char *)&btree[icnodehdr.count] - (char *)oldroot); + level = icnodehdr.level; /* * we are about to copy oldroot to bp, so set up the type diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h index 0a49b0286372..74bcbabfa523 100644 --- a/fs/xfs/libxfs/xfs_da_format.h +++ b/fs/xfs/libxfs/xfs_da_format.h @@ -725,7 +725,13 @@ struct xfs_attr3_icleaf_hdr { __uint16_t magic; __uint16_t count; __uint16_t usedbytes; - __uint16_t firstused; + /* + * firstused is 32-bit here instead of 16-bit like the on-disk variant + * to support maximum fsb size of 64k without overflow issues throughout + * the attr code. Instead, the overflow condition is handled on + * conversion to/from disk. + */ + __uint32_t firstused; __u8 holes; struct { __uint16_t base; @@ -734,6 +740,12 @@ struct xfs_attr3_icleaf_hdr { }; /* + * Special value to represent fs block size in the leaf header firstused field. + * Only used when block size overflows the 2-bytes available on disk. + */ +#define XFS_ATTR3_LEAF_NULLOFF 0 + +/* * Flags used in the leaf_entry[i].flags field. * NOTE: the INCOMPLETE bit must not collide with the flags bits specified * on the system call, they are "or"ed together for various operations. diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c index 5ff31be9b1cd..de1ea16f5748 100644 --- a/fs/xfs/libxfs/xfs_dir2_data.c +++ b/fs/xfs/libxfs/xfs_dir2_data.c @@ -89,7 +89,7 @@ __xfs_dir3_data_check( * so just ensure that the count falls somewhere inside the * block right now. */ - XFS_WANT_CORRUPTED_RETURN(be32_to_cpu(btp->count) < + XFS_WANT_CORRUPTED_RETURN(mp, be32_to_cpu(btp->count) < ((char *)btp - p) / sizeof(struct xfs_dir2_leaf_entry)); break; case cpu_to_be32(XFS_DIR3_DATA_MAGIC): @@ -107,21 +107,21 @@ __xfs_dir3_data_check( bf = ops->data_bestfree_p(hdr); count = lastfree = freeseen = 0; if (!bf[0].length) { - XFS_WANT_CORRUPTED_RETURN(!bf[0].offset); + XFS_WANT_CORRUPTED_RETURN(mp, !bf[0].offset); freeseen |= 1 << 0; } if (!bf[1].length) { - XFS_WANT_CORRUPTED_RETURN(!bf[1].offset); + XFS_WANT_CORRUPTED_RETURN(mp, !bf[1].offset); freeseen |= 1 << 1; } if (!bf[2].length) { - XFS_WANT_CORRUPTED_RETURN(!bf[2].offset); + XFS_WANT_CORRUPTED_RETURN(mp, !bf[2].offset); freeseen |= 1 << 2; } - XFS_WANT_CORRUPTED_RETURN(be16_to_cpu(bf[0].length) >= + XFS_WANT_CORRUPTED_RETURN(mp, be16_to_cpu(bf[0].length) >= be16_to_cpu(bf[1].length)); - XFS_WANT_CORRUPTED_RETURN(be16_to_cpu(bf[1].length) >= + XFS_WANT_CORRUPTED_RETURN(mp, be16_to_cpu(bf[1].length) >= be16_to_cpu(bf[2].length)); /* * Loop over the data/unused entries. @@ -134,18 +134,18 @@ __xfs_dir3_data_check( * doesn't need to be there. */ if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) { - XFS_WANT_CORRUPTED_RETURN(lastfree == 0); - XFS_WANT_CORRUPTED_RETURN( + XFS_WANT_CORRUPTED_RETURN(mp, lastfree == 0); + XFS_WANT_CORRUPTED_RETURN(mp, be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)) == (char *)dup - (char *)hdr); dfp = xfs_dir2_data_freefind(hdr, bf, dup); if (dfp) { i = (int)(dfp - bf); - XFS_WANT_CORRUPTED_RETURN( + XFS_WANT_CORRUPTED_RETURN(mp, (freeseen & (1 << i)) == 0); freeseen |= 1 << i; } else { - XFS_WANT_CORRUPTED_RETURN( + XFS_WANT_CORRUPTED_RETURN(mp, be16_to_cpu(dup->length) <= be16_to_cpu(bf[2].length)); } @@ -160,13 +160,13 @@ __xfs_dir3_data_check( * The linear search is crude but this is DEBUG code. */ dep = (xfs_dir2_data_entry_t *)p; - XFS_WANT_CORRUPTED_RETURN(dep->namelen != 0); - XFS_WANT_CORRUPTED_RETURN( + XFS_WANT_CORRUPTED_RETURN(mp, dep->namelen != 0); + XFS_WANT_CORRUPTED_RETURN(mp, !xfs_dir_ino_validate(mp, be64_to_cpu(dep->inumber))); - XFS_WANT_CORRUPTED_RETURN( + XFS_WANT_CORRUPTED_RETURN(mp, be16_to_cpu(*ops->data_entry_tag_p(dep)) == (char *)dep - (char *)hdr); - XFS_WANT_CORRUPTED_RETURN( + XFS_WANT_CORRUPTED_RETURN(mp, ops->data_get_ftype(dep) < XFS_DIR3_FT_MAX); count++; lastfree = 0; @@ -183,14 +183,15 @@ __xfs_dir3_data_check( be32_to_cpu(lep[i].hashval) == hash) break; } - XFS_WANT_CORRUPTED_RETURN(i < be32_to_cpu(btp->count)); + XFS_WANT_CORRUPTED_RETURN(mp, + i < be32_to_cpu(btp->count)); } p += ops->data_entsize(dep->namelen); } /* * Need to have seen all the entries and all the bestfree slots. */ - XFS_WANT_CORRUPTED_RETURN(freeseen == 7); + XFS_WANT_CORRUPTED_RETURN(mp, freeseen == 7); if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) || hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) { for (i = stale = 0; i < be32_to_cpu(btp->count); i++) { @@ -198,13 +199,13 @@ __xfs_dir3_data_check( cpu_to_be32(XFS_DIR2_NULL_DATAPTR)) stale++; if (i > 0) - XFS_WANT_CORRUPTED_RETURN( + XFS_WANT_CORRUPTED_RETURN(mp, be32_to_cpu(lep[i].hashval) >= be32_to_cpu(lep[i - 1].hashval)); } - XFS_WANT_CORRUPTED_RETURN(count == + XFS_WANT_CORRUPTED_RETURN(mp, count == be32_to_cpu(btp->count) - be32_to_cpu(btp->stale)); - XFS_WANT_CORRUPTED_RETURN(stale == be32_to_cpu(btp->stale)); + XFS_WANT_CORRUPTED_RETURN(mp, stale == be32_to_cpu(btp->stale)); } return 0; } diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index 8eb718979383..4daaa662337b 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -264,68 +264,6 @@ typedef struct xfs_dsb { /* must be padded to 64 bit alignment */ } xfs_dsb_t; -/* - * Sequence number values for the fields. - */ -typedef enum { - XFS_SBS_MAGICNUM, XFS_SBS_BLOCKSIZE, XFS_SBS_DBLOCKS, XFS_SBS_RBLOCKS, - XFS_SBS_REXTENTS, XFS_SBS_UUID, XFS_SBS_LOGSTART, XFS_SBS_ROOTINO, - XFS_SBS_RBMINO, XFS_SBS_RSUMINO, XFS_SBS_REXTSIZE, XFS_SBS_AGBLOCKS, - XFS_SBS_AGCOUNT, XFS_SBS_RBMBLOCKS, XFS_SBS_LOGBLOCKS, - XFS_SBS_VERSIONNUM, XFS_SBS_SECTSIZE, XFS_SBS_INODESIZE, - XFS_SBS_INOPBLOCK, XFS_SBS_FNAME, XFS_SBS_BLOCKLOG, - XFS_SBS_SECTLOG, XFS_SBS_INODELOG, XFS_SBS_INOPBLOG, XFS_SBS_AGBLKLOG, - XFS_SBS_REXTSLOG, XFS_SBS_INPROGRESS, XFS_SBS_IMAX_PCT, XFS_SBS_ICOUNT, - XFS_SBS_IFREE, XFS_SBS_FDBLOCKS, XFS_SBS_FREXTENTS, XFS_SBS_UQUOTINO, - XFS_SBS_GQUOTINO, XFS_SBS_QFLAGS, XFS_SBS_FLAGS, XFS_SBS_SHARED_VN, - XFS_SBS_INOALIGNMT, XFS_SBS_UNIT, XFS_SBS_WIDTH, XFS_SBS_DIRBLKLOG, - XFS_SBS_LOGSECTLOG, XFS_SBS_LOGSECTSIZE, XFS_SBS_LOGSUNIT, - XFS_SBS_FEATURES2, XFS_SBS_BAD_FEATURES2, XFS_SBS_FEATURES_COMPAT, - XFS_SBS_FEATURES_RO_COMPAT, XFS_SBS_FEATURES_INCOMPAT, - XFS_SBS_FEATURES_LOG_INCOMPAT, XFS_SBS_CRC, XFS_SBS_PAD, - XFS_SBS_PQUOTINO, XFS_SBS_LSN, - XFS_SBS_FIELDCOUNT -} xfs_sb_field_t; - -/* - * Mask values, defined based on the xfs_sb_field_t values. - * Only define the ones we're using. - */ -#define XFS_SB_MVAL(x) (1LL << XFS_SBS_ ## x) -#define XFS_SB_UUID XFS_SB_MVAL(UUID) -#define XFS_SB_FNAME XFS_SB_MVAL(FNAME) -#define XFS_SB_ROOTINO XFS_SB_MVAL(ROOTINO) -#define XFS_SB_RBMINO XFS_SB_MVAL(RBMINO) -#define XFS_SB_RSUMINO XFS_SB_MVAL(RSUMINO) -#define XFS_SB_VERSIONNUM XFS_SB_MVAL(VERSIONNUM) -#define XFS_SB_UQUOTINO XFS_SB_MVAL(UQUOTINO) -#define XFS_SB_GQUOTINO XFS_SB_MVAL(GQUOTINO) -#define XFS_SB_QFLAGS XFS_SB_MVAL(QFLAGS) -#define XFS_SB_SHARED_VN XFS_SB_MVAL(SHARED_VN) -#define XFS_SB_UNIT XFS_SB_MVAL(UNIT) -#define XFS_SB_WIDTH XFS_SB_MVAL(WIDTH) -#define XFS_SB_ICOUNT XFS_SB_MVAL(ICOUNT) -#define XFS_SB_IFREE XFS_SB_MVAL(IFREE) -#define XFS_SB_FDBLOCKS XFS_SB_MVAL(FDBLOCKS) -#define XFS_SB_FEATURES2 (XFS_SB_MVAL(FEATURES2) | \ - XFS_SB_MVAL(BAD_FEATURES2)) -#define XFS_SB_FEATURES_COMPAT XFS_SB_MVAL(FEATURES_COMPAT) -#define XFS_SB_FEATURES_RO_COMPAT XFS_SB_MVAL(FEATURES_RO_COMPAT) -#define XFS_SB_FEATURES_INCOMPAT XFS_SB_MVAL(FEATURES_INCOMPAT) -#define XFS_SB_FEATURES_LOG_INCOMPAT XFS_SB_MVAL(FEATURES_LOG_INCOMPAT) -#define XFS_SB_CRC XFS_SB_MVAL(CRC) -#define XFS_SB_PQUOTINO XFS_SB_MVAL(PQUOTINO) -#define XFS_SB_NUM_BITS ((int)XFS_SBS_FIELDCOUNT) -#define XFS_SB_ALL_BITS ((1LL << XFS_SB_NUM_BITS) - 1) -#define XFS_SB_MOD_BITS \ - (XFS_SB_UUID | XFS_SB_ROOTINO | XFS_SB_RBMINO | XFS_SB_RSUMINO | \ - XFS_SB_VERSIONNUM | XFS_SB_UQUOTINO | XFS_SB_GQUOTINO | \ - XFS_SB_QFLAGS | XFS_SB_SHARED_VN | XFS_SB_UNIT | XFS_SB_WIDTH | \ - XFS_SB_ICOUNT | XFS_SB_IFREE | XFS_SB_FDBLOCKS | XFS_SB_FEATURES2 | \ - XFS_SB_FEATURES_COMPAT | XFS_SB_FEATURES_RO_COMPAT | \ - XFS_SB_FEATURES_INCOMPAT | XFS_SB_FEATURES_LOG_INCOMPAT | \ - XFS_SB_PQUOTINO) - /* * Misc. Flags - warning - these will be cleared by xfs_repair unless diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 116ef1ddb3e3..07349a183a11 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -376,7 +376,8 @@ xfs_ialloc_ag_alloc( */ newlen = args.mp->m_ialloc_inos; if (args.mp->m_maxicount && - args.mp->m_sb.sb_icount + newlen > args.mp->m_maxicount) + percpu_counter_read(&args.mp->m_icount) + newlen > + args.mp->m_maxicount) return -ENOSPC; args.minlen = args.maxlen = args.mp->m_ialloc_blks; /* @@ -700,7 +701,7 @@ xfs_ialloc_next_rec( error = xfs_inobt_get_rec(cur, rec, &i); if (error) return error; - XFS_WANT_CORRUPTED_RETURN(i == 1); + XFS_WANT_CORRUPTED_RETURN(cur->bc_mp, i == 1); } return 0; @@ -724,7 +725,7 @@ xfs_ialloc_get_rec( error = xfs_inobt_get_rec(cur, rec, &i); if (error) return error; - XFS_WANT_CORRUPTED_RETURN(i == 1); + XFS_WANT_CORRUPTED_RETURN(cur->bc_mp, i == 1); } return 0; @@ -783,12 +784,12 @@ xfs_dialloc_ag_inobt( error = xfs_inobt_lookup(cur, pagino, XFS_LOOKUP_LE, &i); if (error) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); error = xfs_inobt_get_rec(cur, &rec, &j); if (error) goto error0; - XFS_WANT_CORRUPTED_GOTO(j == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, j == 1, error0); if (rec.ir_freecount > 0) { /* @@ -944,19 +945,19 @@ newino: error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i); if (error) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); for (;;) { error = xfs_inobt_get_rec(cur, &rec, &i); if (error) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); if (rec.ir_freecount > 0) break; error = xfs_btree_increment(cur, 0, &i); if (error) goto error0; - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); } alloc_inode: @@ -1016,7 +1017,7 @@ xfs_dialloc_ag_finobt_near( error = xfs_inobt_get_rec(lcur, rec, &i); if (error) return error; - XFS_WANT_CORRUPTED_RETURN(i == 1); + XFS_WANT_CORRUPTED_RETURN(lcur->bc_mp, i == 1); /* * See if we've landed in the parent inode record. The finobt @@ -1039,10 +1040,10 @@ xfs_dialloc_ag_finobt_near( error = xfs_inobt_get_rec(rcur, &rrec, &j); if (error) goto error_rcur; - XFS_WANT_CORRUPTED_GOTO(j == 1, error_rcur); + XFS_WANT_CORRUPTED_GOTO(lcur->bc_mp, j == 1, error_rcur); } - XFS_WANT_CORRUPTED_GOTO(i == 1 || j == 1, error_rcur); + XFS_WANT_CORRUPTED_GOTO(lcur->bc_mp, i == 1 || j == 1, error_rcur); if (i == 1 && j == 1) { /* * Both the left and right records are valid. Choose the closer @@ -1095,7 +1096,7 @@ xfs_dialloc_ag_finobt_newino( error = xfs_inobt_get_rec(cur, rec, &i); if (error) return error; - XFS_WANT_CORRUPTED_RETURN(i == 1); + XFS_WANT_CORRUPTED_RETURN(cur->bc_mp, i == 1); return 0; } } @@ -1106,12 +1107,12 @@ xfs_dialloc_ag_finobt_newino( error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i); if (error) return error; - XFS_WANT_CORRUPTED_RETURN(i == 1); + XFS_WANT_CORRUPTED_RETURN(cur->bc_mp, i == 1); error = xfs_inobt_get_rec(cur, rec, &i); if (error) return error; - XFS_WANT_CORRUPTED_RETURN(i == 1); + XFS_WANT_CORRUPTED_RETURN(cur->bc_mp, i == 1); return 0; } @@ -1133,19 +1134,19 @@ xfs_dialloc_ag_update_inobt( error = xfs_inobt_lookup(cur, frec->ir_startino, XFS_LOOKUP_EQ, &i); if (error) return error; - XFS_WANT_CORRUPTED_RETURN(i == 1); + XFS_WANT_CORRUPTED_RETURN(cur->bc_mp, i == 1); error = xfs_inobt_get_rec(cur, &rec, &i); if (error) return error; - XFS_WANT_CORRUPTED_RETURN(i == 1); + XFS_WANT_CORRUPTED_RETURN(cur->bc_mp, i == 1); ASSERT((XFS_AGINO_TO_OFFSET(cur->bc_mp, rec.ir_startino) % XFS_INODES_PER_CHUNK) == 0); rec.ir_free &= ~XFS_INOBT_MASK(offset); rec.ir_freecount--; - XFS_WANT_CORRUPTED_RETURN((rec.ir_free == frec->ir_free) && + XFS_WANT_CORRUPTED_RETURN(cur->bc_mp, (rec.ir_free == frec->ir_free) && (rec.ir_freecount == frec->ir_freecount)); return xfs_inobt_update(cur, &rec); @@ -1340,7 +1341,8 @@ xfs_dialloc( * inode. */ if (mp->m_maxicount && - mp->m_sb.sb_icount + mp->m_ialloc_inos > mp->m_maxicount) { + percpu_counter_read(&mp->m_icount) + mp->m_ialloc_inos > + mp->m_maxicount) { noroom = 1; okalloc = 0; } @@ -1475,14 +1477,14 @@ xfs_difree_inobt( __func__, error); goto error0; } - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); error = xfs_inobt_get_rec(cur, &rec, &i); if (error) { xfs_warn(mp, "%s: xfs_inobt_get_rec() returned error %d.", __func__, error); goto error0; } - XFS_WANT_CORRUPTED_GOTO(i == 1, error0); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error0); /* * Get the offset in the inode chunk. */ @@ -1592,7 +1594,7 @@ xfs_difree_finobt( * freed an inode in a previously fully allocated chunk. If not, * something is out of sync. */ - XFS_WANT_CORRUPTED_GOTO(ibtrec->ir_freecount == 1, error); + XFS_WANT_CORRUPTED_GOTO(mp, ibtrec->ir_freecount == 1, error); error = xfs_inobt_insert_rec(cur, ibtrec->ir_freecount, ibtrec->ir_free, &i); @@ -1613,12 +1615,12 @@ xfs_difree_finobt( error = xfs_inobt_get_rec(cur, &rec, &i); if (error) goto error; - XFS_WANT_CORRUPTED_GOTO(i == 1, error); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, error); rec.ir_free |= XFS_INOBT_MASK(offset); rec.ir_freecount++; - XFS_WANT_CORRUPTED_GOTO((rec.ir_free == ibtrec->ir_free) && + XFS_WANT_CORRUPTED_GOTO(mp, (rec.ir_free == ibtrec->ir_free) && (rec.ir_freecount == ibtrec->ir_freecount), error); diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index b0a5fe95a3e2..dc4bfc5d88fc 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -111,14 +111,6 @@ xfs_mount_validate_sb( bool check_inprogress, bool check_version) { - - /* - * If the log device and data device have the - * same device number, the log is internal. - * Consequently, the sb_logstart should be non-zero. If - * we have a zero sb_logstart in this case, we may be trying to mount - * a volume filesystem in a non-volume manner. - */ if (sbp->sb_magicnum != XFS_SB_MAGIC) { xfs_warn(mp, "bad magic number"); return -EWRONGFS; @@ -743,17 +735,15 @@ xfs_initialize_perag_data( btree += pag->pagf_btreeblks; xfs_perag_put(pag); } - /* - * Overwrite incore superblock counters with just-read data - */ + + /* Overwrite incore superblock counters with just-read data */ spin_lock(&mp->m_sb_lock); sbp->sb_ifree = ifree; sbp->sb_icount = ialloc; sbp->sb_fdblocks = bfree + bfreelst + btree; spin_unlock(&mp->m_sb_lock); - /* Fixup the per-cpu counters as well. */ - xfs_icsb_reinit_counters(mp); + xfs_reinit_percpu_counters(mp); return 0; } @@ -771,6 +761,10 @@ xfs_log_sb( struct xfs_mount *mp = tp->t_mountp; struct xfs_buf *bp = xfs_trans_getsb(tp, mp, 0); + mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount); + mp->m_sb.sb_ifree = percpu_counter_sum(&mp->m_ifree); + mp->m_sb.sb_fdblocks = percpu_counter_sum(&mp->m_fdblocks); + xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb); xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF); xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsb)); diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 3a9b7a1b8704..a56960dd1684 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -31,7 +31,6 @@ #include "xfs_bmap.h" #include "xfs_bmap_util.h" #include "xfs_bmap_btree.h" -#include <linux/aio.h> #include <linux/gfp.h> #include <linux/mpage.h> #include <linux/pagevec.h> @@ -1233,6 +1232,117 @@ xfs_vm_releasepage( return try_to_free_buffers(page); } +/* + * When we map a DIO buffer, we may need to attach an ioend that describes the + * type of write IO we are doing. This passes to the completion function the + * operations it needs to perform. If the mapping is for an overwrite wholly + * within the EOF then we don't need an ioend and so we don't allocate one. + * This avoids the unnecessary overhead of allocating and freeing ioends for + * workloads that don't require transactions on IO completion. + * + * If we get multiple mappings in a single IO, we might be mapping different + * types. But because the direct IO can only have a single private pointer, we + * need to ensure that: + * + * a) i) the ioend spans the entire region of unwritten mappings; or + * ii) the ioend spans all the mappings that cross or are beyond EOF; and + * b) if it contains unwritten extents, it is *permanently* marked as such + * + * We could do this by chaining ioends like buffered IO does, but we only + * actually get one IO completion callback from the direct IO, and that spans + * the entire IO regardless of how many mappings and IOs are needed to complete + * the DIO. There is only going to be one reference to the ioend and its life + * cycle is constrained by the DIO completion code. hence we don't need + * reference counting here. + */ +static void +xfs_map_direct( + struct inode *inode, + struct buffer_head *bh_result, + struct xfs_bmbt_irec *imap, + xfs_off_t offset) +{ + struct xfs_ioend *ioend; + xfs_off_t size = bh_result->b_size; + int type; + + if (ISUNWRITTEN(imap)) + type = XFS_IO_UNWRITTEN; + else + type = XFS_IO_OVERWRITE; + + trace_xfs_gbmap_direct(XFS_I(inode), offset, size, type, imap); + + if (bh_result->b_private) { + ioend = bh_result->b_private; + ASSERT(ioend->io_size > 0); + ASSERT(offset >= ioend->io_offset); + if (offset + size > ioend->io_offset + ioend->io_size) + ioend->io_size = offset - ioend->io_offset + size; + + if (type == XFS_IO_UNWRITTEN && type != ioend->io_type) + ioend->io_type = XFS_IO_UNWRITTEN; + + trace_xfs_gbmap_direct_update(XFS_I(inode), ioend->io_offset, + ioend->io_size, ioend->io_type, + imap); + } else if (type == XFS_IO_UNWRITTEN || + offset + size > i_size_read(inode)) { + ioend = xfs_alloc_ioend(inode, type); + ioend->io_offset = offset; + ioend->io_size = size; + + bh_result->b_private = ioend; + set_buffer_defer_completion(bh_result); + + trace_xfs_gbmap_direct_new(XFS_I(inode), offset, size, type, + imap); + } else { + trace_xfs_gbmap_direct_none(XFS_I(inode), offset, size, type, + imap); + } +} + +/* + * If this is O_DIRECT or the mpage code calling tell them how large the mapping + * is, so that we can avoid repeated get_blocks calls. + * + * If the mapping spans EOF, then we have to break the mapping up as the mapping + * for blocks beyond EOF must be marked new so that sub block regions can be + * correctly zeroed. We can't do this for mappings within EOF unless the mapping + * was just allocated or is unwritten, otherwise the callers would overwrite + * existing data with zeros. Hence we have to split the mapping into a range up + * to and including EOF, and a second mapping for beyond EOF. + */ +static void +xfs_map_trim_size( + struct inode *inode, + sector_t iblock, + struct buffer_head *bh_result, + struct xfs_bmbt_irec *imap, + xfs_off_t offset, + ssize_t size) +{ + xfs_off_t mapping_size; + + mapping_size = imap->br_startoff + imap->br_blockcount - iblock; + mapping_size <<= inode->i_blkbits; + + ASSERT(mapping_size > 0); + if (mapping_size > size) + mapping_size = size; + if (offset < i_size_read(inode) && + offset + mapping_size >= i_size_read(inode)) { + /* limit mapping to block that spans EOF */ + mapping_size = roundup_64(i_size_read(inode) - offset, + 1 << inode->i_blkbits); + } + if (mapping_size > LONG_MAX) + mapping_size = LONG_MAX; + + bh_result->b_size = mapping_size; +} + STATIC int __xfs_get_blocks( struct inode *inode, @@ -1321,31 +1431,37 @@ __xfs_get_blocks( xfs_iunlock(ip, lockmode); } - - trace_xfs_get_blocks_alloc(ip, offset, size, 0, &imap); + trace_xfs_get_blocks_alloc(ip, offset, size, + ISUNWRITTEN(&imap) ? XFS_IO_UNWRITTEN + : XFS_IO_DELALLOC, &imap); } else if (nimaps) { - trace_xfs_get_blocks_found(ip, offset, size, 0, &imap); + trace_xfs_get_blocks_found(ip, offset, size, + ISUNWRITTEN(&imap) ? XFS_IO_UNWRITTEN + : XFS_IO_OVERWRITE, &imap); xfs_iunlock(ip, lockmode); } else { trace_xfs_get_blocks_notfound(ip, offset, size); goto out_unlock; } + /* trim mapping down to size requested */ + if (direct || size > (1 << inode->i_blkbits)) + xfs_map_trim_size(inode, iblock, bh_result, + &imap, offset, size); + + /* + * For unwritten extents do not report a disk address in the buffered + * read case (treat as if we're reading into a hole). + */ if (imap.br_startblock != HOLESTARTBLOCK && - imap.br_startblock != DELAYSTARTBLOCK) { - /* - * For unwritten extents do not report a disk address on - * the read case (treat as if we're reading into a hole). - */ - if (create || !ISUNWRITTEN(&imap)) - xfs_map_buffer(inode, bh_result, &imap, offset); - if (create && ISUNWRITTEN(&imap)) { - if (direct) { - bh_result->b_private = inode; - set_buffer_defer_completion(bh_result); - } + imap.br_startblock != DELAYSTARTBLOCK && + (create || !ISUNWRITTEN(&imap))) { + xfs_map_buffer(inode, bh_result, &imap, offset); + if (ISUNWRITTEN(&imap)) set_buffer_unwritten(bh_result); - } + /* direct IO needs special help */ + if (create && direct) + xfs_map_direct(inode, bh_result, &imap, offset); } /* @@ -1378,39 +1494,6 @@ __xfs_get_blocks( } } - /* - * If this is O_DIRECT or the mpage code calling tell them how large - * the mapping is, so that we can avoid repeated get_blocks calls. - * - * If the mapping spans EOF, then we have to break the mapping up as the - * mapping for blocks beyond EOF must be marked new so that sub block - * regions can be correctly zeroed. We can't do this for mappings within - * EOF unless the mapping was just allocated or is unwritten, otherwise - * the callers would overwrite existing data with zeros. Hence we have - * to split the mapping into a range up to and including EOF, and a - * second mapping for beyond EOF. - */ - if (direct || size > (1 << inode->i_blkbits)) { - xfs_off_t mapping_size; - - mapping_size = imap.br_startoff + imap.br_blockcount - iblock; - mapping_size <<= inode->i_blkbits; - - ASSERT(mapping_size > 0); - if (mapping_size > size) - mapping_size = size; - if (offset < i_size_read(inode) && - offset + mapping_size >= i_size_read(inode)) { - /* limit mapping to block that spans EOF */ - mapping_size = roundup_64(i_size_read(inode) - offset, - 1 << inode->i_blkbits); - } - if (mapping_size > LONG_MAX) - mapping_size = LONG_MAX; - - bh_result->b_size = mapping_size; - } - return 0; out_unlock: @@ -1441,9 +1524,11 @@ xfs_get_blocks_direct( /* * Complete a direct I/O write request. * - * If the private argument is non-NULL __xfs_get_blocks signals us that we - * need to issue a transaction to convert the range from unwritten to written - * extents. + * The ioend structure is passed from __xfs_get_blocks() to tell us what to do. + * If no ioend exists (i.e. @private == NULL) then the write IO is an overwrite + * wholly within the EOF and so there is nothing for us to do. Note that in this + * case the completion can be called in interrupt context, whereas if we have an + * ioend we will always be called in task context (i.e. from a workqueue). */ STATIC void xfs_end_io_direct_write( @@ -1455,48 +1540,75 @@ xfs_end_io_direct_write( struct inode *inode = file_inode(iocb->ki_filp); struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; + struct xfs_ioend *ioend = private; - if (XFS_FORCED_SHUTDOWN(mp)) + trace_xfs_gbmap_direct_endio(ip, offset, size, + ioend ? ioend->io_type : 0, NULL); + + if (!ioend) { + ASSERT(offset + size <= i_size_read(inode)); return; + } + + if (XFS_FORCED_SHUTDOWN(mp)) + goto out_end_io; /* - * While the generic direct I/O code updates the inode size, it does - * so only after the end_io handler is called, which means our - * end_io handler thinks the on-disk size is outside the in-core - * size. To prevent this just update it a little bit earlier here. + * dio completion end_io functions are only called on writes if more + * than 0 bytes was written. */ + ASSERT(size > 0); + + /* + * The ioend only maps whole blocks, while the IO may be sector aligned. + * Hence the ioend offset/size may not match the IO offset/size exactly. + * Because we don't map overwrites within EOF into the ioend, the offset + * may not match, but only if the endio spans EOF. Either way, write + * the IO sizes into the ioend so that completion processing does the + * right thing. + */ + ASSERT(offset + size <= ioend->io_offset + ioend->io_size); + ioend->io_size = size; + ioend->io_offset = offset; + + /* + * The ioend tells us whether we are doing unwritten extent conversion + * or an append transaction that updates the on-disk file size. These + * cases are the only cases where we should *potentially* be needing + * to update the VFS inode size. + * + * We need to update the in-core inode size here so that we don't end up + * with the on-disk inode size being outside the in-core inode size. We + * have no other method of updating EOF for AIO, so always do it here + * if necessary. + * + * We need to lock the test/set EOF update as we can be racing with + * other IO completions here to update the EOF. Failing to serialise + * here can result in EOF moving backwards and Bad Things Happen when + * that occurs. + */ + spin_lock(&ip->i_flags_lock); if (offset + size > i_size_read(inode)) i_size_write(inode, offset + size); + spin_unlock(&ip->i_flags_lock); /* - * For direct I/O we do not know if we need to allocate blocks or not, - * so we can't preallocate an append transaction, as that results in - * nested reservations and log space deadlocks. Hence allocate the - * transaction here. While this is sub-optimal and can block IO - * completion for some time, we're stuck with doing it this way until - * we can pass the ioend to the direct IO allocation callbacks and - * avoid nesting that way. + * If we are doing an append IO that needs to update the EOF on disk, + * do the transaction reserve now so we can use common end io + * processing. Stashing the error (if there is one) in the ioend will + * result in the ioend processing passing on the error if it is + * possible as we can't return it from here. */ - if (private && size > 0) { - xfs_iomap_write_unwritten(ip, offset, size); - } else if (offset + size > ip->i_d.di_size) { - struct xfs_trans *tp; - int error; - - tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS); - error = xfs_trans_reserve(tp, &M_RES(mp)->tr_fsyncts, 0, 0); - if (error) { - xfs_trans_cancel(tp, 0); - return; - } + if (ioend->io_type == XFS_IO_OVERWRITE) + ioend->io_error = xfs_setfilesize_trans_alloc(ioend); - xfs_setfilesize(ip, tp, offset, size); - } +out_end_io: + xfs_end_io(&ioend->io_work); + return; } STATIC ssize_t xfs_vm_direct_IO( - int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t offset) @@ -1504,15 +1616,14 @@ xfs_vm_direct_IO( struct inode *inode = iocb->ki_filp->f_mapping->host; struct block_device *bdev = xfs_find_bdev_for_inode(inode); - if (rw & WRITE) { - return __blockdev_direct_IO(rw, iocb, inode, bdev, iter, - offset, xfs_get_blocks_direct, + if (iov_iter_rw(iter) == WRITE) { + return __blockdev_direct_IO(iocb, inode, bdev, iter, offset, + xfs_get_blocks_direct, xfs_end_io_direct_write, NULL, DIO_ASYNC_EXTEND); } - return __blockdev_direct_IO(rw, iocb, inode, bdev, iter, - offset, xfs_get_blocks_direct, - NULL, NULL, 0); + return __blockdev_direct_IO(iocb, inode, bdev, iter, offset, + xfs_get_blocks_direct, NULL, NULL, 0); } /* diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c index 83af4c149635..f9c1c64782d3 100644 --- a/fs/xfs/xfs_attr_inactive.c +++ b/fs/xfs/xfs_attr_inactive.c @@ -132,9 +132,10 @@ xfs_attr3_leaf_inactive( int size; int tmp; int i; + struct xfs_mount *mp = bp->b_target->bt_mount; leaf = bp->b_addr; - xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf); + xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf); /* * Count the number of "remote" value extents. diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c index a43d370d2c58..65fb37a18e92 100644 --- a/fs/xfs/xfs_attr_list.c +++ b/fs/xfs/xfs_attr_list.c @@ -225,6 +225,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context) int error, i; struct xfs_buf *bp; struct xfs_inode *dp = context->dp; + struct xfs_mount *mp = dp->i_mount; trace_xfs_attr_node_list(context); @@ -256,7 +257,8 @@ xfs_attr_node_list(xfs_attr_list_context_t *context) case XFS_ATTR_LEAF_MAGIC: case XFS_ATTR3_LEAF_MAGIC: leaf = bp->b_addr; - xfs_attr3_leaf_hdr_from_disk(&leafhdr, leaf); + xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, + &leafhdr, leaf); entries = xfs_attr3_leaf_entryp(leaf); if (cursor->hashval > be32_to_cpu( entries[leafhdr.count - 1].hashval)) { @@ -340,7 +342,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context) xfs_trans_brelse(NULL, bp); return error; } - xfs_attr3_leaf_hdr_from_disk(&leafhdr, leaf); + xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &leafhdr, leaf); if (context->seen_enough || leafhdr.forw == 0) break; cursor->blkno = leafhdr.forw; @@ -368,11 +370,12 @@ xfs_attr3_leaf_list_int( struct xfs_attr_leaf_entry *entry; int retval; int i; + struct xfs_mount *mp = context->dp->i_mount; trace_xfs_attr_list_leaf(context); leaf = bp->b_addr; - xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf); + xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf); entries = xfs_attr3_leaf_entryp(leaf); cursor = context->cursor; diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 22a5dcb70b32..a52bbd3abc7d 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1376,22 +1376,19 @@ out: } /* - * xfs_collapse_file_space() - * This routine frees disk space and shift extent for the given file. - * The first thing we do is to free data blocks in the specified range - * by calling xfs_free_file_space(). It would also sync dirty data - * and invalidate page cache over the region on which collapse range - * is working. And Shift extent records to the left to cover a hole. - * RETURNS: - * 0 on success - * errno on error - * + * @next_fsb will keep track of the extent currently undergoing shift. + * @stop_fsb will keep track of the extent at which we have to stop. + * If we are shifting left, we will start with block (offset + len) and + * shift each extent till last extent. + * If we are shifting right, we will start with last extent inside file space + * and continue until we reach the block corresponding to offset. */ -int -xfs_collapse_file_space( - struct xfs_inode *ip, - xfs_off_t offset, - xfs_off_t len) +static int +xfs_shift_file_space( + struct xfs_inode *ip, + xfs_off_t offset, + xfs_off_t len, + enum shift_direction direction) { int done = 0; struct xfs_mount *mp = ip->i_mount; @@ -1400,21 +1397,26 @@ xfs_collapse_file_space( struct xfs_bmap_free free_list; xfs_fsblock_t first_block; int committed; - xfs_fileoff_t start_fsb; + xfs_fileoff_t stop_fsb; xfs_fileoff_t next_fsb; xfs_fileoff_t shift_fsb; - ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); + ASSERT(direction == SHIFT_LEFT || direction == SHIFT_RIGHT); - trace_xfs_collapse_file_space(ip); + if (direction == SHIFT_LEFT) { + next_fsb = XFS_B_TO_FSB(mp, offset + len); + stop_fsb = XFS_B_TO_FSB(mp, VFS_I(ip)->i_size); + } else { + /* + * If right shift, delegate the work of initialization of + * next_fsb to xfs_bmap_shift_extent as it has ilock held. + */ + next_fsb = NULLFSBLOCK; + stop_fsb = XFS_B_TO_FSB(mp, offset); + } - next_fsb = XFS_B_TO_FSB(mp, offset + len); shift_fsb = XFS_B_TO_FSB(mp, len); - error = xfs_free_file_space(ip, offset, len); - if (error) - return error; - /* * Trim eofblocks to avoid shifting uninitialized post-eof preallocation * into the accessible region of the file. @@ -1427,20 +1429,28 @@ xfs_collapse_file_space( /* * Writeback and invalidate cache for the remainder of the file as we're - * about to shift down every extent from the collapse range to EOF. The - * free of the collapse range above might have already done some of - * this, but we shouldn't rely on it to do anything outside of the range - * that was freed. + * about to shift down every extent from offset to EOF. */ error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping, - offset + len, -1); + offset, -1); if (error) return error; error = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping, - (offset + len) >> PAGE_CACHE_SHIFT, -1); + offset >> PAGE_CACHE_SHIFT, -1); if (error) return error; + /* + * The extent shiting code works on extent granularity. So, if + * stop_fsb is not the starting block of extent, we need to split + * the extent at stop_fsb. + */ + if (direction == SHIFT_RIGHT) { + error = xfs_bmap_split_extent(ip, stop_fsb); + if (error) + return error; + } + while (!error && !done) { tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT); /* @@ -1464,7 +1474,7 @@ xfs_collapse_file_space( if (error) goto out; - xfs_trans_ijoin(tp, ip, 0); + xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); xfs_bmap_init(&free_list, &first_block); @@ -1472,10 +1482,9 @@ xfs_collapse_file_space( * We are using the write transaction in which max 2 bmbt * updates are allowed */ - start_fsb = next_fsb; - error = xfs_bmap_shift_extents(tp, ip, start_fsb, shift_fsb, - &done, &next_fsb, &first_block, &free_list, - XFS_BMAP_MAX_SHIFT_EXTENTS); + error = xfs_bmap_shift_extents(tp, ip, &next_fsb, shift_fsb, + &done, stop_fsb, &first_block, &free_list, + direction, XFS_BMAP_MAX_SHIFT_EXTENTS); if (error) goto out; @@ -1484,18 +1493,70 @@ xfs_collapse_file_space( goto out; error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES); - xfs_iunlock(ip, XFS_ILOCK_EXCL); } return error; out: xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT); - xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; } /* + * xfs_collapse_file_space() + * This routine frees disk space and shift extent for the given file. + * The first thing we do is to free data blocks in the specified range + * by calling xfs_free_file_space(). It would also sync dirty data + * and invalidate page cache over the region on which collapse range + * is working. And Shift extent records to the left to cover a hole. + * RETURNS: + * 0 on success + * errno on error + * + */ +int +xfs_collapse_file_space( + struct xfs_inode *ip, + xfs_off_t offset, + xfs_off_t len) +{ + int error; + + ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); + trace_xfs_collapse_file_space(ip); + + error = xfs_free_file_space(ip, offset, len); + if (error) + return error; + + return xfs_shift_file_space(ip, offset, len, SHIFT_LEFT); +} + +/* + * xfs_insert_file_space() + * This routine create hole space by shifting extents for the given file. + * The first thing we do is to sync dirty data and invalidate page cache + * over the region on which insert range is working. And split an extent + * to two extents at given offset by calling xfs_bmap_split_extent. + * And shift all extent records which are laying between [offset, + * last allocated extent] to the right to reserve hole range. + * RETURNS: + * 0 on success + * errno on error + */ +int +xfs_insert_file_space( + struct xfs_inode *ip, + loff_t offset, + loff_t len) +{ + ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); + trace_xfs_insert_file_space(ip); + + return xfs_shift_file_space(ip, offset, len, SHIFT_RIGHT); +} + +/* * We need to check that the format of the data fork in the temporary inode is * valid for the target inode before doing the swap. This is not a problem with * attr1 because of the fixed fork offset, but attr2 has a dynamically sized @@ -1599,13 +1660,6 @@ xfs_swap_extent_flush( /* Verify O_DIRECT for ftmp */ if (VFS_I(ip)->i_mapping->nrpages) return -EINVAL; - - /* - * Don't try to swap extents on mmap()d files because we can't lock - * out races against page faults safely. - */ - if (mapping_mapped(VFS_I(ip)->i_mapping)) - return -EBUSY; return 0; } @@ -1633,13 +1687,14 @@ xfs_swap_extents( } /* - * Lock up the inodes against other IO and truncate to begin with. - * Then we can ensure the inodes are flushed and have no page cache - * safely. Once we have done this we can take the ilocks and do the rest - * of the checks. + * Lock the inodes against other IO, page faults and truncate to + * begin with. Then we can ensure the inodes are flushed and have no + * page cache safely. Once we have done this we can take the ilocks and + * do the rest of the checks. */ - lock_flags = XFS_IOLOCK_EXCL; + lock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL); + xfs_lock_two_inodes(ip, tip, XFS_MMAPLOCK_EXCL); /* Verify that both files have the same format */ if ((ip->i_d.di_mode & S_IFMT) != (tip->i_d.di_mode & S_IFMT)) { @@ -1666,8 +1721,16 @@ xfs_swap_extents( xfs_trans_cancel(tp, 0); goto out_unlock; } + + /* + * Lock and join the inodes to the tansaction so that transaction commit + * or cancel will unlock the inodes from this point onwards. + */ xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL); lock_flags |= XFS_ILOCK_EXCL; + xfs_trans_ijoin(tp, ip, lock_flags); + xfs_trans_ijoin(tp, tip, lock_flags); + /* Verify all data are being swapped */ if (sxp->sx_offset != 0 || @@ -1720,9 +1783,6 @@ xfs_swap_extents( goto out_trans_cancel; } - xfs_trans_ijoin(tp, ip, lock_flags); - xfs_trans_ijoin(tp, tip, lock_flags); - /* * Before we've swapped the forks, lets set the owners of the forks * appropriately. We have to do this as we are demand paging the btree @@ -1856,5 +1916,5 @@ out_unlock: out_trans_cancel: xfs_trans_cancel(tp, 0); - goto out_unlock; + goto out; } diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h index 736429a72a12..af97d9a1dfb4 100644 --- a/fs/xfs/xfs_bmap_util.h +++ b/fs/xfs/xfs_bmap_util.h @@ -63,6 +63,8 @@ int xfs_zero_file_space(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t len); int xfs_collapse_file_space(struct xfs_inode *, xfs_off_t offset, xfs_off_t len); +int xfs_insert_file_space(struct xfs_inode *, xfs_off_t offset, + xfs_off_t len); /* EOF block manipulation functions */ bool xfs_can_free_eofblocks(struct xfs_inode *ip, bool force); diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 507d96a57ac7..092d652bc03d 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -537,9 +537,9 @@ xfs_buf_item_push( /* has a previous flush failed due to IO errors? */ if ((bp->b_flags & XBF_WRITE_FAIL) && - ___ratelimit(&xfs_buf_write_fail_rl_state, "XFS:")) { + ___ratelimit(&xfs_buf_write_fail_rl_state, "XFS: Failing async write")) { xfs_warn(bp->b_target->bt_mount, -"Detected failing async write on buffer block 0x%llx. Retrying async write.", +"Failing async write on buffer block 0x%llx. Retrying async write.", (long long)bp->b_bn); } diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index 799e5a2d334d..e85a9519a5ae 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -84,7 +84,7 @@ xfs_trim_extents( error = xfs_alloc_get_rec(cur, &fbno, &flen, &i); if (error) goto out_del_cursor; - XFS_WANT_CORRUPTED_GOTO(i == 1, out_del_cursor); + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, out_del_cursor); ASSERT(flen <= be32_to_cpu(XFS_BUF_TO_AGF(agbp)->agf_longest)); /* diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index 3ee186ac1093..338e50bbfd1e 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -131,7 +131,7 @@ xfs_error_report( { if (level <= xfs_error_level) { xfs_alert_tag(mp, XFS_PTAG_ERROR_REPORT, - "Internal error %s at line %d of file %s. Caller %pF", + "Internal error %s at line %d of file %s. Caller %pS", tag, linenum, filename, ra); xfs_stack_trace(); diff --git a/fs/xfs/xfs_error.h b/fs/xfs/xfs_error.h index 279a76e52791..c0394ed126fc 100644 --- a/fs/xfs/xfs_error.h +++ b/fs/xfs/xfs_error.h @@ -40,25 +40,25 @@ extern void xfs_verifier_error(struct xfs_buf *bp); /* * Macros to set EFSCORRUPTED & return/branch. */ -#define XFS_WANT_CORRUPTED_GOTO(x,l) \ +#define XFS_WANT_CORRUPTED_GOTO(mp, x, l) \ { \ int fs_is_ok = (x); \ ASSERT(fs_is_ok); \ if (unlikely(!fs_is_ok)) { \ XFS_ERROR_REPORT("XFS_WANT_CORRUPTED_GOTO", \ - XFS_ERRLEVEL_LOW, NULL); \ + XFS_ERRLEVEL_LOW, mp); \ error = -EFSCORRUPTED; \ goto l; \ } \ } -#define XFS_WANT_CORRUPTED_RETURN(x) \ +#define XFS_WANT_CORRUPTED_RETURN(mp, x) \ { \ int fs_is_ok = (x); \ ASSERT(fs_is_ok); \ if (unlikely(!fs_is_ok)) { \ XFS_ERROR_REPORT("XFS_WANT_CORRUPTED_RETURN", \ - XFS_ERRLEVEL_LOW, NULL); \ + XFS_ERRLEVEL_LOW, mp); \ return -EFSCORRUPTED; \ } \ } diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index a2e1cb8a568b..8121e75352ee 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -38,7 +38,6 @@ #include "xfs_icache.h" #include "xfs_pnfs.h" -#include <linux/aio.h> #include <linux/dcache.h> #include <linux/falloc.h> #include <linux/pagevec.h> @@ -280,7 +279,7 @@ xfs_file_read_iter( XFS_STATS_INC(xs_read_calls); - if (unlikely(file->f_flags & O_DIRECT)) + if (unlikely(iocb->ki_flags & IOCB_DIRECT)) ioflags |= XFS_IO_ISDIRECT; if (file->f_mode & FMODE_NOCMTIME) ioflags |= XFS_IO_INVIS; @@ -545,21 +544,22 @@ xfs_zero_eof( */ STATIC ssize_t xfs_file_aio_write_checks( - struct file *file, - loff_t *pos, - size_t *count, + struct kiocb *iocb, + struct iov_iter *from, int *iolock) { + struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct xfs_inode *ip = XFS_I(inode); - int error = 0; + ssize_t error = 0; + size_t count = iov_iter_count(from); restart: - error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode)); - if (error) + error = generic_write_checks(iocb, from); + if (error <= 0) return error; - error = xfs_break_layouts(inode, iolock); + error = xfs_break_layouts(inode, iolock, true); if (error) return error; @@ -569,20 +569,42 @@ restart: * write. If zeroing is needed and we are currently holding the * iolock shared, we need to update it to exclusive which implies * having to redo all checks before. + * + * We need to serialise against EOF updates that occur in IO + * completions here. We want to make sure that nobody is changing the + * size while we do this check until we have placed an IO barrier (i.e. + * hold the XFS_IOLOCK_EXCL) that prevents new IO from being dispatched. + * The spinlock effectively forms a memory barrier once we have the + * XFS_IOLOCK_EXCL so we are guaranteed to see the latest EOF value + * and hence be able to correctly determine if we need to run zeroing. */ - if (*pos > i_size_read(inode)) { + spin_lock(&ip->i_flags_lock); + if (iocb->ki_pos > i_size_read(inode)) { bool zero = false; + spin_unlock(&ip->i_flags_lock); if (*iolock == XFS_IOLOCK_SHARED) { xfs_rw_iunlock(ip, *iolock); *iolock = XFS_IOLOCK_EXCL; xfs_rw_ilock(ip, *iolock); + iov_iter_reexpand(from, count); + + /* + * We now have an IO submission barrier in place, but + * AIO can do EOF updates during IO completion and hence + * we now need to wait for all of them to drain. Non-AIO + * DIO will have drained before we are given the + * XFS_IOLOCK_EXCL, and so for most cases this wait is a + * no-op. + */ + inode_dio_wait(inode); goto restart; } - error = xfs_zero_eof(ip, *pos, i_size_read(inode), &zero); + error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), &zero); if (error) return error; - } + } else + spin_unlock(&ip->i_flags_lock); /* * Updating the timestamps will grab the ilock again from @@ -644,6 +666,8 @@ xfs_file_dio_aio_write( int iolock; size_t count = iov_iter_count(from); loff_t pos = iocb->ki_pos; + loff_t end; + struct iov_iter data; struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ? mp->m_rtdev_targp : mp->m_ddev_targp; @@ -679,14 +703,16 @@ xfs_file_dio_aio_write( xfs_rw_ilock(ip, iolock); } - ret = xfs_file_aio_write_checks(file, &pos, &count, &iolock); + ret = xfs_file_aio_write_checks(iocb, from, &iolock); if (ret) goto out; - iov_iter_truncate(from, count); + count = iov_iter_count(from); + pos = iocb->ki_pos; + end = pos + count - 1; if (mapping->nrpages) { ret = filemap_write_and_wait_range(VFS_I(ip)->i_mapping, - pos, pos + count - 1); + pos, end); if (ret) goto out; /* @@ -696,7 +722,7 @@ xfs_file_dio_aio_write( */ ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping, pos >> PAGE_CACHE_SHIFT, - (pos + count - 1) >> PAGE_CACHE_SHIFT); + end >> PAGE_CACHE_SHIFT); WARN_ON_ONCE(ret); ret = 0; } @@ -713,8 +739,22 @@ xfs_file_dio_aio_write( } trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0); - ret = generic_file_direct_write(iocb, from, pos); + data = *from; + ret = mapping->a_ops->direct_IO(iocb, &data, pos); + + /* see generic_file_direct_write() for why this is necessary */ + if (mapping->nrpages) { + invalidate_inode_pages2_range(mapping, + pos >> PAGE_CACHE_SHIFT, + end >> PAGE_CACHE_SHIFT); + } + + if (ret > 0) { + pos += ret; + iov_iter_advance(from, ret); + iocb->ki_pos = pos; + } out: xfs_rw_iunlock(ip, iolock); @@ -735,24 +775,22 @@ xfs_file_buffered_aio_write( ssize_t ret; int enospc = 0; int iolock = XFS_IOLOCK_EXCL; - loff_t pos = iocb->ki_pos; - size_t count = iov_iter_count(from); xfs_rw_ilock(ip, iolock); - ret = xfs_file_aio_write_checks(file, &pos, &count, &iolock); + ret = xfs_file_aio_write_checks(iocb, from, &iolock); if (ret) goto out; - iov_iter_truncate(from, count); /* We can write back this queue in page reclaim */ current->backing_dev_info = inode_to_bdi(inode); write_retry: - trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, 0); - ret = generic_perform_write(file, from, pos); + trace_xfs_file_buffered_write(ip, iov_iter_count(from), + iocb->ki_pos, 0); + ret = generic_perform_write(file, from, iocb->ki_pos); if (likely(ret >= 0)) - iocb->ki_pos = pos + ret; + iocb->ki_pos += ret; /* * If we hit a space limit, try to free up some lingering preallocated @@ -804,7 +842,7 @@ xfs_file_write_iter( if (XFS_FORCED_SHUTDOWN(ip->i_mount)) return -EIO; - if (unlikely(file->f_flags & O_DIRECT)) + if (unlikely(iocb->ki_flags & IOCB_DIRECT)) ret = xfs_file_dio_aio_write(iocb, from); else ret = xfs_file_buffered_aio_write(iocb, from); @@ -822,6 +860,11 @@ xfs_file_write_iter( return ret; } +#define XFS_FALLOC_FL_SUPPORTED \ + (FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | \ + FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | \ + FALLOC_FL_INSERT_RANGE) + STATIC long xfs_file_fallocate( struct file *file, @@ -835,18 +878,21 @@ xfs_file_fallocate( enum xfs_prealloc_flags flags = 0; uint iolock = XFS_IOLOCK_EXCL; loff_t new_size = 0; + bool do_file_insert = 0; if (!S_ISREG(inode->i_mode)) return -EINVAL; - if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | - FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE)) + if (mode & ~XFS_FALLOC_FL_SUPPORTED) return -EOPNOTSUPP; xfs_ilock(ip, iolock); - error = xfs_break_layouts(inode, &iolock); + error = xfs_break_layouts(inode, &iolock, false); if (error) goto out_unlock; + xfs_ilock(ip, XFS_MMAPLOCK_EXCL); + iolock |= XFS_MMAPLOCK_EXCL; + if (mode & FALLOC_FL_PUNCH_HOLE) { error = xfs_free_file_space(ip, offset, len); if (error) @@ -873,6 +919,27 @@ xfs_file_fallocate( error = xfs_collapse_file_space(ip, offset, len); if (error) goto out_unlock; + } else if (mode & FALLOC_FL_INSERT_RANGE) { + unsigned blksize_mask = (1 << inode->i_blkbits) - 1; + + new_size = i_size_read(inode) + len; + if (offset & blksize_mask || len & blksize_mask) { + error = -EINVAL; + goto out_unlock; + } + + /* check the new inode size does not wrap through zero */ + if (new_size > inode->i_sb->s_maxbytes) { + error = -EFBIG; + goto out_unlock; + } + + /* Offset should be less than i_size */ + if (offset >= i_size_read(inode)) { + error = -EINVAL; + goto out_unlock; + } + do_file_insert = 1; } else { flags |= XFS_PREALLOC_SET; @@ -907,8 +974,19 @@ xfs_file_fallocate( iattr.ia_valid = ATTR_SIZE; iattr.ia_size = new_size; error = xfs_setattr_size(ip, &iattr); + if (error) + goto out_unlock; } + /* + * Perform hole insertion now that the file size has been + * updated so that if we crash during the operation we don't + * leave shifted extents past EOF and hence losing access to + * the data that is contained within them. + */ + if (do_file_insert) + error = xfs_insert_file_space(ip, offset, len); + out_unlock: xfs_iunlock(ip, iolock); return error; @@ -997,20 +1075,6 @@ xfs_file_mmap( } /* - * mmap()d file has taken write protection fault and is being made - * writable. We can set the page state up correctly for a writable - * page, which means we can do correct delalloc accounting (ENOSPC - * checking!) and unwritten extent mapping. - */ -STATIC int -xfs_vm_page_mkwrite( - struct vm_area_struct *vma, - struct vm_fault *vmf) -{ - return block_page_mkwrite(vma, vmf, xfs_get_blocks); -} - -/* * This type is designed to indicate the type of offset we would like * to search from page cache for xfs_seek_hole_data(). */ @@ -1385,10 +1449,57 @@ xfs_file_llseek( } } +/* + * Locking for serialisation of IO during page faults. This results in a lock + * ordering of: + * + * mmap_sem (MM) + * i_mmap_lock (XFS - truncate serialisation) + * page_lock (MM) + * i_lock (XFS - extent map serialisation) + */ +STATIC int +xfs_filemap_fault( + struct vm_area_struct *vma, + struct vm_fault *vmf) +{ + struct xfs_inode *ip = XFS_I(vma->vm_file->f_mapping->host); + int error; + + trace_xfs_filemap_fault(ip); + + xfs_ilock(ip, XFS_MMAPLOCK_SHARED); + error = filemap_fault(vma, vmf); + xfs_iunlock(ip, XFS_MMAPLOCK_SHARED); + + return error; +} + +/* + * mmap()d file has taken write protection fault and is being made writable. We + * can set the page state up correctly for a writable page, which means we can + * do correct delalloc accounting (ENOSPC checking!) and unwritten extent + * mapping. + */ +STATIC int +xfs_filemap_page_mkwrite( + struct vm_area_struct *vma, + struct vm_fault *vmf) +{ + struct xfs_inode *ip = XFS_I(vma->vm_file->f_mapping->host); + int error; + + trace_xfs_filemap_page_mkwrite(ip); + + xfs_ilock(ip, XFS_MMAPLOCK_SHARED); + error = block_page_mkwrite(vma, vmf, xfs_get_blocks); + xfs_iunlock(ip, XFS_MMAPLOCK_SHARED); + + return error; +} + const struct file_operations xfs_file_operations = { .llseek = xfs_file_llseek, - .read = new_sync_read, - .write = new_sync_write, .read_iter = xfs_file_read_iter, .write_iter = xfs_file_write_iter, .splice_read = xfs_file_splice_read, @@ -1417,7 +1528,7 @@ const struct file_operations xfs_dir_file_operations = { }; static const struct vm_operations_struct xfs_file_vm_ops = { - .fault = filemap_fault, + .fault = xfs_filemap_fault, .map_pages = filemap_map_pages, - .page_mkwrite = xfs_vm_page_mkwrite, + .page_mkwrite = xfs_filemap_page_mkwrite, }; diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c index a2e86e8a0fea..8f9f854376c6 100644 --- a/fs/xfs/xfs_filestream.c +++ b/fs/xfs/xfs_filestream.c @@ -322,7 +322,7 @@ xfs_filestream_lookup_ag( pip = xfs_filestream_get_parent(ip); if (!pip) - goto out; + return NULLAGNUMBER; mru = xfs_mru_cache_lookup(mp->m_filestream, pip->i_ino); if (mru) { diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 74efe5b760dc..cb7e8a29dfb6 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -637,12 +637,13 @@ xfs_fs_counts( xfs_mount_t *mp, xfs_fsop_counts_t *cnt) { - xfs_icsb_sync_counters(mp, XFS_ICSB_LAZY_COUNT); + cnt->allocino = percpu_counter_read_positive(&mp->m_icount); + cnt->freeino = percpu_counter_read_positive(&mp->m_ifree); + cnt->freedata = percpu_counter_read_positive(&mp->m_fdblocks) - + XFS_ALLOC_SET_ASIDE(mp); + spin_lock(&mp->m_sb_lock); - cnt->freedata = mp->m_sb.sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp); cnt->freertx = mp->m_sb.sb_frextents; - cnt->freeino = mp->m_sb.sb_ifree; - cnt->allocino = mp->m_sb.sb_icount; spin_unlock(&mp->m_sb_lock); return 0; } @@ -692,14 +693,9 @@ xfs_reserve_blocks( * what to do. This means that the amount of free space can * change while we do this, so we need to retry if we end up * trying to reserve more space than is available. - * - * We also use the xfs_mod_incore_sb() interface so that we - * don't have to care about whether per cpu counter are - * enabled, disabled or even compiled in.... */ retry: spin_lock(&mp->m_sb_lock); - xfs_icsb_sync_counters_locked(mp, 0); /* * If our previous reservation was larger than the current value, @@ -716,7 +712,8 @@ retry: } else { __int64_t free; - free = mp->m_sb.sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp); + free = percpu_counter_sum(&mp->m_fdblocks) - + XFS_ALLOC_SET_ASIDE(mp); if (!free) goto out; /* ENOSPC and fdblks_delta = 0 */ @@ -755,8 +752,7 @@ out: * the extra reserve blocks from the reserve..... */ int error; - error = xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS, - fdblks_delta, 0); + error = xfs_mod_fdblocks(mp, fdblks_delta, 0); if (error == -ENOSPC) goto retry; } diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 9771b7ef62ed..76a9f2783282 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -439,11 +439,11 @@ again: *ipp = ip; /* - * If we have a real type for an on-disk inode, we can set ops(&unlock) + * If we have a real type for an on-disk inode, we can setup the inode * now. If it's a new inode being created, xfs_ialloc will handle it. */ if (xfs_iflags_test(ip, XFS_INEW) && ip->i_d.di_mode != 0) - xfs_setup_inode(ip); + xfs_setup_existing_inode(ip); return 0; out_error_or_again: diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 6163767aa856..d6ebc85192b7 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -117,24 +117,34 @@ xfs_ilock_attr_map_shared( } /* - * The xfs inode contains 2 locks: a multi-reader lock called the - * i_iolock and a multi-reader lock called the i_lock. This routine - * allows either or both of the locks to be obtained. + * The xfs inode contains 3 multi-reader locks: the i_iolock the i_mmap_lock and + * the i_lock. This routine allows various combinations of the locks to be + * obtained. * - * The 2 locks should always be ordered so that the IO lock is - * obtained first in order to prevent deadlock. + * The 3 locks should always be ordered so that the IO lock is obtained first, + * the mmap lock second and the ilock last in order to prevent deadlock. * - * ip -- the inode being locked - * lock_flags -- this parameter indicates the inode's locks - * to be locked. It can be: - * XFS_IOLOCK_SHARED, - * XFS_IOLOCK_EXCL, - * XFS_ILOCK_SHARED, - * XFS_ILOCK_EXCL, - * XFS_IOLOCK_SHARED | XFS_ILOCK_SHARED, - * XFS_IOLOCK_SHARED | XFS_ILOCK_EXCL, - * XFS_IOLOCK_EXCL | XFS_ILOCK_SHARED, - * XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL + * Basic locking order: + * + * i_iolock -> i_mmap_lock -> page_lock -> i_ilock + * + * mmap_sem locking order: + * + * i_iolock -> page lock -> mmap_sem + * mmap_sem -> i_mmap_lock -> page_lock + * + * The difference in mmap_sem locking order mean that we cannot hold the + * i_mmap_lock over syscall based read(2)/write(2) based IO. These IO paths can + * fault in pages during copy in/out (for buffered IO) or require the mmap_sem + * in get_user_pages() to map the user pages into the kernel address space for + * direct IO. Similarly the i_iolock cannot be taken inside a page fault because + * page faults already hold the mmap_sem. + * + * Hence to serialise fully against both syscall and mmap based IO, we need to + * take both the i_iolock and the i_mmap_lock. These locks should *only* be both + * taken in places where we need to invalidate the page cache in a race + * free manner (e.g. truncate, hole punch and other extent manipulation + * functions). */ void xfs_ilock( @@ -150,6 +160,8 @@ xfs_ilock( */ ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) != (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)); + ASSERT((lock_flags & (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)) != + (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)); ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) != (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_DEP_MASK)) == 0); @@ -159,6 +171,11 @@ xfs_ilock( else if (lock_flags & XFS_IOLOCK_SHARED) mraccess_nested(&ip->i_iolock, XFS_IOLOCK_DEP(lock_flags)); + if (lock_flags & XFS_MMAPLOCK_EXCL) + mrupdate_nested(&ip->i_mmaplock, XFS_MMAPLOCK_DEP(lock_flags)); + else if (lock_flags & XFS_MMAPLOCK_SHARED) + mraccess_nested(&ip->i_mmaplock, XFS_MMAPLOCK_DEP(lock_flags)); + if (lock_flags & XFS_ILOCK_EXCL) mrupdate_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags)); else if (lock_flags & XFS_ILOCK_SHARED) @@ -191,6 +208,8 @@ xfs_ilock_nowait( */ ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) != (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)); + ASSERT((lock_flags & (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)) != + (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)); ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) != (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_DEP_MASK)) == 0); @@ -202,21 +221,35 @@ xfs_ilock_nowait( if (!mrtryaccess(&ip->i_iolock)) goto out; } + + if (lock_flags & XFS_MMAPLOCK_EXCL) { + if (!mrtryupdate(&ip->i_mmaplock)) + goto out_undo_iolock; + } else if (lock_flags & XFS_MMAPLOCK_SHARED) { + if (!mrtryaccess(&ip->i_mmaplock)) + goto out_undo_iolock; + } + if (lock_flags & XFS_ILOCK_EXCL) { if (!mrtryupdate(&ip->i_lock)) - goto out_undo_iolock; + goto out_undo_mmaplock; } else if (lock_flags & XFS_ILOCK_SHARED) { if (!mrtryaccess(&ip->i_lock)) - goto out_undo_iolock; + goto out_undo_mmaplock; } return 1; - out_undo_iolock: +out_undo_mmaplock: + if (lock_flags & XFS_MMAPLOCK_EXCL) + mrunlock_excl(&ip->i_mmaplock); + else if (lock_flags & XFS_MMAPLOCK_SHARED) + mrunlock_shared(&ip->i_mmaplock); +out_undo_iolock: if (lock_flags & XFS_IOLOCK_EXCL) mrunlock_excl(&ip->i_iolock); else if (lock_flags & XFS_IOLOCK_SHARED) mrunlock_shared(&ip->i_iolock); - out: +out: return 0; } @@ -244,6 +277,8 @@ xfs_iunlock( */ ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) != (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)); + ASSERT((lock_flags & (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)) != + (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)); ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) != (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_DEP_MASK)) == 0); @@ -254,6 +289,11 @@ xfs_iunlock( else if (lock_flags & XFS_IOLOCK_SHARED) mrunlock_shared(&ip->i_iolock); + if (lock_flags & XFS_MMAPLOCK_EXCL) + mrunlock_excl(&ip->i_mmaplock); + else if (lock_flags & XFS_MMAPLOCK_SHARED) + mrunlock_shared(&ip->i_mmaplock); + if (lock_flags & XFS_ILOCK_EXCL) mrunlock_excl(&ip->i_lock); else if (lock_flags & XFS_ILOCK_SHARED) @@ -271,11 +311,14 @@ xfs_ilock_demote( xfs_inode_t *ip, uint lock_flags) { - ASSERT(lock_flags & (XFS_IOLOCK_EXCL|XFS_ILOCK_EXCL)); - ASSERT((lock_flags & ~(XFS_IOLOCK_EXCL|XFS_ILOCK_EXCL)) == 0); + ASSERT(lock_flags & (XFS_IOLOCK_EXCL|XFS_MMAPLOCK_EXCL|XFS_ILOCK_EXCL)); + ASSERT((lock_flags & + ~(XFS_IOLOCK_EXCL|XFS_MMAPLOCK_EXCL|XFS_ILOCK_EXCL)) == 0); if (lock_flags & XFS_ILOCK_EXCL) mrdemote(&ip->i_lock); + if (lock_flags & XFS_MMAPLOCK_EXCL) + mrdemote(&ip->i_mmaplock); if (lock_flags & XFS_IOLOCK_EXCL) mrdemote(&ip->i_iolock); @@ -294,6 +337,12 @@ xfs_isilocked( return rwsem_is_locked(&ip->i_lock.mr_lock); } + if (lock_flags & (XFS_MMAPLOCK_EXCL|XFS_MMAPLOCK_SHARED)) { + if (!(lock_flags & XFS_MMAPLOCK_SHARED)) + return !!ip->i_mmaplock.mr_writer; + return rwsem_is_locked(&ip->i_mmaplock.mr_lock); + } + if (lock_flags & (XFS_IOLOCK_EXCL|XFS_IOLOCK_SHARED)) { if (!(lock_flags & XFS_IOLOCK_SHARED)) return !!ip->i_iolock.mr_writer; @@ -314,14 +363,27 @@ int xfs_lock_delays; #endif /* - * Bump the subclass so xfs_lock_inodes() acquires each lock with - * a different value + * Bump the subclass so xfs_lock_inodes() acquires each lock with a different + * value. This shouldn't be called for page fault locking, but we also need to + * ensure we don't overrun the number of lockdep subclasses for the iolock or + * mmaplock as that is limited to 12 by the mmap lock lockdep annotations. */ static inline int xfs_lock_inumorder(int lock_mode, int subclass) { - if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)) + if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)) { + ASSERT(subclass + XFS_LOCK_INUMORDER < + (1 << (XFS_MMAPLOCK_SHIFT - XFS_IOLOCK_SHIFT))); lock_mode |= (subclass + XFS_LOCK_INUMORDER) << XFS_IOLOCK_SHIFT; + } + + if (lock_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) { + ASSERT(subclass + XFS_LOCK_INUMORDER < + (1 << (XFS_ILOCK_SHIFT - XFS_MMAPLOCK_SHIFT))); + lock_mode |= (subclass + XFS_LOCK_INUMORDER) << + XFS_MMAPLOCK_SHIFT; + } + if (lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)) lock_mode |= (subclass + XFS_LOCK_INUMORDER) << XFS_ILOCK_SHIFT; @@ -329,15 +391,14 @@ xfs_lock_inumorder(int lock_mode, int subclass) } /* - * The following routine will lock n inodes in exclusive mode. - * We assume the caller calls us with the inodes in i_ino order. + * The following routine will lock n inodes in exclusive mode. We assume the + * caller calls us with the inodes in i_ino order. * - * We need to detect deadlock where an inode that we lock - * is in the AIL and we start waiting for another inode that is locked - * by a thread in a long running transaction (such as truncate). This can - * result in deadlock since the long running trans might need to wait - * for the inode we just locked in order to push the tail and free space - * in the log. + * We need to detect deadlock where an inode that we lock is in the AIL and we + * start waiting for another inode that is locked by a thread in a long running + * transaction (such as truncate). This can result in deadlock since the long + * running trans might need to wait for the inode we just locked in order to + * push the tail and free space in the log. */ void xfs_lock_inodes( @@ -348,30 +409,27 @@ xfs_lock_inodes( int attempts = 0, i, j, try_lock; xfs_log_item_t *lp; - ASSERT(ips && (inodes >= 2)); /* we need at least two */ + /* currently supports between 2 and 5 inodes */ + ASSERT(ips && inodes >= 2 && inodes <= 5); try_lock = 0; i = 0; - again: for (; i < inodes; i++) { ASSERT(ips[i]); - if (i && (ips[i] == ips[i-1])) /* Already locked */ + if (i && (ips[i] == ips[i - 1])) /* Already locked */ continue; /* - * If try_lock is not set yet, make sure all locked inodes - * are not in the AIL. - * If any are, set try_lock to be used later. + * If try_lock is not set yet, make sure all locked inodes are + * not in the AIL. If any are, set try_lock to be used later. */ - if (!try_lock) { for (j = (i - 1); j >= 0 && !try_lock; j--) { lp = (xfs_log_item_t *)ips[j]->i_itemp; - if (lp && (lp->li_flags & XFS_LI_IN_AIL)) { + if (lp && (lp->li_flags & XFS_LI_IN_AIL)) try_lock++; - } } } @@ -381,51 +439,42 @@ again: * we can't get any, we must release all we have * and try again. */ + if (!try_lock) { + xfs_ilock(ips[i], xfs_lock_inumorder(lock_mode, i)); + continue; + } + + /* try_lock means we have an inode locked that is in the AIL. */ + ASSERT(i != 0); + if (xfs_ilock_nowait(ips[i], xfs_lock_inumorder(lock_mode, i))) + continue; - if (try_lock) { - /* try_lock must be 0 if i is 0. */ + /* + * Unlock all previous guys and try again. xfs_iunlock will try + * to push the tail if the inode is in the AIL. + */ + attempts++; + for (j = i - 1; j >= 0; j--) { /* - * try_lock means we have an inode locked - * that is in the AIL. + * Check to see if we've already unlocked this one. Not + * the first one going back, and the inode ptr is the + * same. */ - ASSERT(i != 0); - if (!xfs_ilock_nowait(ips[i], xfs_lock_inumorder(lock_mode, i))) { - attempts++; - - /* - * Unlock all previous guys and try again. - * xfs_iunlock will try to push the tail - * if the inode is in the AIL. - */ - - for(j = i - 1; j >= 0; j--) { - - /* - * Check to see if we've already - * unlocked this one. - * Not the first one going back, - * and the inode ptr is the same. - */ - if ((j != (i - 1)) && ips[j] == - ips[j+1]) - continue; - - xfs_iunlock(ips[j], lock_mode); - } + if (j != (i - 1) && ips[j] == ips[j + 1]) + continue; + + xfs_iunlock(ips[j], lock_mode); + } - if ((attempts % 5) == 0) { - delay(1); /* Don't just spin the CPU */ + if ((attempts % 5) == 0) { + delay(1); /* Don't just spin the CPU */ #ifdef DEBUG - xfs_lock_delays++; + xfs_lock_delays++; #endif - } - i = 0; - try_lock = 0; - goto again; - } - } else { - xfs_ilock(ips[i], xfs_lock_inumorder(lock_mode, i)); } + i = 0; + try_lock = 0; + goto again; } #ifdef DEBUG @@ -440,10 +489,10 @@ again: } /* - * xfs_lock_two_inodes() can only be used to lock one type of lock - * at a time - the iolock or the ilock, but not both at once. If - * we lock both at once, lockdep will report false positives saying - * we have violated locking orders. + * xfs_lock_two_inodes() can only be used to lock one type of lock at a time - + * the iolock, the mmaplock or the ilock, but not more than one at a time. If we + * lock more than one at a time, lockdep will report false positives saying we + * have violated locking orders. */ void xfs_lock_two_inodes( @@ -455,8 +504,12 @@ xfs_lock_two_inodes( int attempts = 0; xfs_log_item_t *lp; - if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)) - ASSERT((lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)) == 0); + if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)) { + ASSERT(!(lock_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL))); + ASSERT(!(lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL))); + } else if (lock_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) + ASSERT(!(lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL))); + ASSERT(ip0->i_ino != ip1->i_ino); if (ip0->i_ino > ip1->i_ino) { @@ -818,7 +871,7 @@ xfs_ialloc( xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); xfs_trans_log_inode(tp, ip, flags); - /* now that we have an i_mode we can setup inode ops and unlock */ + /* now that we have an i_mode we can setup the inode structure */ xfs_setup_inode(ip); *ipp = ip; @@ -1235,12 +1288,14 @@ xfs_create( xfs_trans_cancel(tp, cancel_flags); out_release_inode: /* - * Wait until after the current transaction is aborted to - * release the inode. This prevents recursive transactions - * and deadlocks from xfs_inactive. + * Wait until after the current transaction is aborted to finish the + * setup of the inode and release the inode. This prevents recursive + * transactions and deadlocks from xfs_inactive. */ - if (ip) + if (ip) { + xfs_finish_inode_setup(ip); IRELE(ip); + } xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); @@ -1345,12 +1400,14 @@ xfs_create_tmpfile( xfs_trans_cancel(tp, cancel_flags); out_release_inode: /* - * Wait until after the current transaction is aborted to - * release the inode. This prevents recursive transactions - * and deadlocks from xfs_inactive. + * Wait until after the current transaction is aborted to finish the + * setup of the inode and release the inode. This prevents recursive + * transactions and deadlocks from xfs_inactive. */ - if (ip) + if (ip) { + xfs_finish_inode_setup(ip); IRELE(ip); + } xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); @@ -2611,19 +2668,22 @@ xfs_remove( /* * Enter all inodes for a rename transaction into a sorted array. */ +#define __XFS_SORT_INODES 5 STATIC void xfs_sort_for_rename( - xfs_inode_t *dp1, /* in: old (source) directory inode */ - xfs_inode_t *dp2, /* in: new (target) directory inode */ - xfs_inode_t *ip1, /* in: inode of old entry */ - xfs_inode_t *ip2, /* in: inode of new entry, if it - already exists, NULL otherwise. */ - xfs_inode_t **i_tab,/* out: array of inode returned, sorted */ - int *num_inodes) /* out: number of inodes in array */ + struct xfs_inode *dp1, /* in: old (source) directory inode */ + struct xfs_inode *dp2, /* in: new (target) directory inode */ + struct xfs_inode *ip1, /* in: inode of old entry */ + struct xfs_inode *ip2, /* in: inode of new entry */ + struct xfs_inode *wip, /* in: whiteout inode */ + struct xfs_inode **i_tab,/* out: sorted array of inodes */ + int *num_inodes) /* in/out: inodes in array */ { - xfs_inode_t *temp; int i, j; + ASSERT(*num_inodes == __XFS_SORT_INODES); + memset(i_tab, 0, *num_inodes * sizeof(struct xfs_inode *)); + /* * i_tab contains a list of pointers to inodes. We initialize * the table here & we'll sort it. We will then use it to @@ -2631,25 +2691,24 @@ xfs_sort_for_rename( * * Note that the table may contain duplicates. e.g., dp1 == dp2. */ - i_tab[0] = dp1; - i_tab[1] = dp2; - i_tab[2] = ip1; - if (ip2) { - *num_inodes = 4; - i_tab[3] = ip2; - } else { - *num_inodes = 3; - i_tab[3] = NULL; - } + i = 0; + i_tab[i++] = dp1; + i_tab[i++] = dp2; + i_tab[i++] = ip1; + if (ip2) + i_tab[i++] = ip2; + if (wip) + i_tab[i++] = wip; + *num_inodes = i; /* * Sort the elements via bubble sort. (Remember, there are at - * most 4 elements to sort, so this is adequate.) + * most 5 elements to sort, so this is adequate.) */ for (i = 0; i < *num_inodes; i++) { for (j = 1; j < *num_inodes; j++) { if (i_tab[j]->i_ino < i_tab[j-1]->i_ino) { - temp = i_tab[j]; + struct xfs_inode *temp = i_tab[j]; i_tab[j] = i_tab[j-1]; i_tab[j-1] = temp; } @@ -2657,6 +2716,31 @@ xfs_sort_for_rename( } } +static int +xfs_finish_rename( + struct xfs_trans *tp, + struct xfs_bmap_free *free_list) +{ + int committed = 0; + int error; + + /* + * If this is a synchronous mount, make sure that the rename transaction + * goes to disk before returning to the user. + */ + if (tp->t_mountp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) + xfs_trans_set_sync(tp); + + error = xfs_bmap_finish(&tp, free_list, &committed); + if (error) { + xfs_bmap_cancel(free_list); + xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT); + return error; + } + + return xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES); +} + /* * xfs_cross_rename() * @@ -2685,14 +2769,14 @@ xfs_cross_rename( ip2->i_ino, first_block, free_list, spaceres); if (error) - goto out; + goto out_trans_abort; /* Swap inode number for dirent in second parent */ error = xfs_dir_replace(tp, dp2, name2, ip1->i_ino, first_block, free_list, spaceres); if (error) - goto out; + goto out_trans_abort; /* * If we're renaming one or more directories across different parents, @@ -2707,16 +2791,16 @@ xfs_cross_rename( dp1->i_ino, first_block, free_list, spaceres); if (error) - goto out; + goto out_trans_abort; /* transfer ip2 ".." reference to dp1 */ if (!S_ISDIR(ip1->i_d.di_mode)) { error = xfs_droplink(tp, dp2); if (error) - goto out; + goto out_trans_abort; error = xfs_bumplink(tp, dp1); if (error) - goto out; + goto out_trans_abort; } /* @@ -2734,16 +2818,16 @@ xfs_cross_rename( dp2->i_ino, first_block, free_list, spaceres); if (error) - goto out; + goto out_trans_abort; /* transfer ip1 ".." reference to dp2 */ if (!S_ISDIR(ip2->i_d.di_mode)) { error = xfs_droplink(tp, dp1); if (error) - goto out; + goto out_trans_abort; error = xfs_bumplink(tp, dp2); if (error) - goto out; + goto out_trans_abort; } /* @@ -2771,66 +2855,108 @@ xfs_cross_rename( } xfs_trans_ichgtime(tp, dp1, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); xfs_trans_log_inode(tp, dp1, XFS_ILOG_CORE); -out: + return xfs_finish_rename(tp, free_list); + +out_trans_abort: + xfs_bmap_cancel(free_list); + xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT); return error; } /* + * xfs_rename_alloc_whiteout() + * + * Return a referenced, unlinked, unlocked inode that that can be used as a + * whiteout in a rename transaction. We use a tmpfile inode here so that if we + * crash between allocating the inode and linking it into the rename transaction + * recovery will free the inode and we won't leak it. + */ +static int +xfs_rename_alloc_whiteout( + struct xfs_inode *dp, + struct xfs_inode **wip) +{ + struct xfs_inode *tmpfile; + int error; + + error = xfs_create_tmpfile(dp, NULL, S_IFCHR | WHITEOUT_MODE, &tmpfile); + if (error) + return error; + + /* Satisfy xfs_bumplink that this is a real tmpfile */ + xfs_finish_inode_setup(tmpfile); + VFS_I(tmpfile)->i_state |= I_LINKABLE; + + *wip = tmpfile; + return 0; +} + +/* * xfs_rename */ int xfs_rename( - xfs_inode_t *src_dp, - struct xfs_name *src_name, - xfs_inode_t *src_ip, - xfs_inode_t *target_dp, - struct xfs_name *target_name, - xfs_inode_t *target_ip, - unsigned int flags) + struct xfs_inode *src_dp, + struct xfs_name *src_name, + struct xfs_inode *src_ip, + struct xfs_inode *target_dp, + struct xfs_name *target_name, + struct xfs_inode *target_ip, + unsigned int flags) { - xfs_trans_t *tp = NULL; - xfs_mount_t *mp = src_dp->i_mount; - int new_parent; /* moving to a new dir */ - int src_is_directory; /* src_name is a directory */ - int error; - xfs_bmap_free_t free_list; - xfs_fsblock_t first_block; - int cancel_flags; - int committed; - xfs_inode_t *inodes[4]; - int spaceres; - int num_inodes; + struct xfs_mount *mp = src_dp->i_mount; + struct xfs_trans *tp; + struct xfs_bmap_free free_list; + xfs_fsblock_t first_block; + struct xfs_inode *wip = NULL; /* whiteout inode */ + struct xfs_inode *inodes[__XFS_SORT_INODES]; + int num_inodes = __XFS_SORT_INODES; + bool new_parent = (src_dp != target_dp); + bool src_is_directory = S_ISDIR(src_ip->i_d.di_mode); + int cancel_flags = 0; + int spaceres; + int error; trace_xfs_rename(src_dp, target_dp, src_name, target_name); - new_parent = (src_dp != target_dp); - src_is_directory = S_ISDIR(src_ip->i_d.di_mode); + if ((flags & RENAME_EXCHANGE) && !target_ip) + return -EINVAL; - xfs_sort_for_rename(src_dp, target_dp, src_ip, target_ip, + /* + * If we are doing a whiteout operation, allocate the whiteout inode + * we will be placing at the target and ensure the type is set + * appropriately. + */ + if (flags & RENAME_WHITEOUT) { + ASSERT(!(flags & (RENAME_NOREPLACE | RENAME_EXCHANGE))); + error = xfs_rename_alloc_whiteout(target_dp, &wip); + if (error) + return error; + + /* setup target dirent info as whiteout */ + src_name->type = XFS_DIR3_FT_CHRDEV; + } + + xfs_sort_for_rename(src_dp, target_dp, src_ip, target_ip, wip, inodes, &num_inodes); - xfs_bmap_init(&free_list, &first_block); tp = xfs_trans_alloc(mp, XFS_TRANS_RENAME); - cancel_flags = XFS_TRANS_RELEASE_LOG_RES; spaceres = XFS_RENAME_SPACE_RES(mp, target_name->len); error = xfs_trans_reserve(tp, &M_RES(mp)->tr_rename, spaceres, 0); if (error == -ENOSPC) { spaceres = 0; error = xfs_trans_reserve(tp, &M_RES(mp)->tr_rename, 0, 0); } - if (error) { - xfs_trans_cancel(tp, 0); - goto std_return; - } + if (error) + goto out_trans_cancel; + cancel_flags = XFS_TRANS_RELEASE_LOG_RES; /* * Attach the dquots to the inodes */ error = xfs_qm_vop_rename_dqattach(inodes); - if (error) { - xfs_trans_cancel(tp, cancel_flags); - goto std_return; - } + if (error) + goto out_trans_cancel; /* * Lock all the participating inodes. Depending upon whether @@ -2851,6 +2977,8 @@ xfs_rename( xfs_trans_ijoin(tp, src_ip, XFS_ILOCK_EXCL); if (target_ip) xfs_trans_ijoin(tp, target_ip, XFS_ILOCK_EXCL); + if (wip) + xfs_trans_ijoin(tp, wip, XFS_ILOCK_EXCL); /* * If we are using project inheritance, we only allow renames @@ -2860,24 +2988,16 @@ xfs_rename( if (unlikely((target_dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) && (xfs_get_projid(target_dp) != xfs_get_projid(src_ip)))) { error = -EXDEV; - goto error_return; + goto out_trans_cancel; } - /* - * Handle RENAME_EXCHANGE flags - */ - if (flags & RENAME_EXCHANGE) { - if (target_ip == NULL) { - error = -EINVAL; - goto error_return; - } - error = xfs_cross_rename(tp, src_dp, src_name, src_ip, - target_dp, target_name, target_ip, - &free_list, &first_block, spaceres); - if (error) - goto abort_return; - goto finish_rename; - } + xfs_bmap_init(&free_list, &first_block); + + /* RENAME_EXCHANGE is unique from here on. */ + if (flags & RENAME_EXCHANGE) + return xfs_cross_rename(tp, src_dp, src_name, src_ip, + target_dp, target_name, target_ip, + &free_list, &first_block, spaceres); /* * Set up the target. @@ -2890,7 +3010,7 @@ xfs_rename( if (!spaceres) { error = xfs_dir_canenter(tp, target_dp, target_name); if (error) - goto error_return; + goto out_trans_cancel; } /* * If target does not exist and the rename crosses @@ -2901,9 +3021,9 @@ xfs_rename( src_ip->i_ino, &first_block, &free_list, spaceres); if (error == -ENOSPC) - goto error_return; + goto out_bmap_cancel; if (error) - goto abort_return; + goto out_trans_abort; xfs_trans_ichgtime(tp, target_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); @@ -2911,7 +3031,7 @@ xfs_rename( if (new_parent && src_is_directory) { error = xfs_bumplink(tp, target_dp); if (error) - goto abort_return; + goto out_trans_abort; } } else { /* target_ip != NULL */ /* @@ -2926,7 +3046,7 @@ xfs_rename( if (!(xfs_dir_isempty(target_ip)) || (target_ip->i_d.di_nlink > 2)) { error = -EEXIST; - goto error_return; + goto out_trans_cancel; } } @@ -2943,7 +3063,7 @@ xfs_rename( src_ip->i_ino, &first_block, &free_list, spaceres); if (error) - goto abort_return; + goto out_trans_abort; xfs_trans_ichgtime(tp, target_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); @@ -2954,7 +3074,7 @@ xfs_rename( */ error = xfs_droplink(tp, target_ip); if (error) - goto abort_return; + goto out_trans_abort; if (src_is_directory) { /* @@ -2962,7 +3082,7 @@ xfs_rename( */ error = xfs_droplink(tp, target_ip); if (error) - goto abort_return; + goto out_trans_abort; } } /* target_ip != NULL */ @@ -2979,7 +3099,7 @@ xfs_rename( &first_block, &free_list, spaceres); ASSERT(error != -EEXIST); if (error) - goto abort_return; + goto out_trans_abort; } /* @@ -3005,49 +3125,67 @@ xfs_rename( */ error = xfs_droplink(tp, src_dp); if (error) - goto abort_return; + goto out_trans_abort; } - error = xfs_dir_removename(tp, src_dp, src_name, src_ip->i_ino, + /* + * For whiteouts, we only need to update the source dirent with the + * inode number of the whiteout inode rather than removing it + * altogether. + */ + if (wip) { + error = xfs_dir_replace(tp, src_dp, src_name, wip->i_ino, &first_block, &free_list, spaceres); + } else + error = xfs_dir_removename(tp, src_dp, src_name, src_ip->i_ino, + &first_block, &free_list, spaceres); if (error) - goto abort_return; - - xfs_trans_ichgtime(tp, src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); - xfs_trans_log_inode(tp, src_dp, XFS_ILOG_CORE); - if (new_parent) - xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE); + goto out_trans_abort; -finish_rename: /* - * If this is a synchronous mount, make sure that the - * rename transaction goes to disk before returning to - * the user. + * For whiteouts, we need to bump the link count on the whiteout inode. + * This means that failures all the way up to this point leave the inode + * on the unlinked list and so cleanup is a simple matter of dropping + * the remaining reference to it. If we fail here after bumping the link + * count, we're shutting down the filesystem so we'll never see the + * intermediate state on disk. */ - if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) { - xfs_trans_set_sync(tp); - } + if (wip) { + ASSERT(wip->i_d.di_nlink == 0); + error = xfs_bumplink(tp, wip); + if (error) + goto out_trans_abort; + error = xfs_iunlink_remove(tp, wip); + if (error) + goto out_trans_abort; + xfs_trans_log_inode(tp, wip, XFS_ILOG_CORE); - error = xfs_bmap_finish(&tp, &free_list, &committed); - if (error) { - xfs_bmap_cancel(&free_list); - xfs_trans_cancel(tp, (XFS_TRANS_RELEASE_LOG_RES | - XFS_TRANS_ABORT)); - goto std_return; + /* + * Now we have a real link, clear the "I'm a tmpfile" state + * flag from the inode so it doesn't accidentally get misused in + * future. + */ + VFS_I(wip)->i_state &= ~I_LINKABLE; } - /* - * trans_commit will unlock src_ip, target_ip & decrement - * the vnode references. - */ - return xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES); + xfs_trans_ichgtime(tp, src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + xfs_trans_log_inode(tp, src_dp, XFS_ILOG_CORE); + if (new_parent) + xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE); - abort_return: + error = xfs_finish_rename(tp, &free_list); + if (wip) + IRELE(wip); + return error; + +out_trans_abort: cancel_flags |= XFS_TRANS_ABORT; - error_return: +out_bmap_cancel: xfs_bmap_cancel(&free_list); +out_trans_cancel: xfs_trans_cancel(tp, cancel_flags); - std_return: + if (wip) + IRELE(wip); return error; } diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index a1cd55f3f351..8f22d20368d8 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -56,6 +56,7 @@ typedef struct xfs_inode { struct xfs_inode_log_item *i_itemp; /* logging information */ mrlock_t i_lock; /* inode lock */ mrlock_t i_iolock; /* inode IO lock */ + mrlock_t i_mmaplock; /* inode mmap IO lock */ atomic_t i_pincount; /* inode pin count */ spinlock_t i_flags_lock; /* inode i_flags lock */ /* Miscellaneous state. */ @@ -263,15 +264,20 @@ static inline int xfs_isiflocked(struct xfs_inode *ip) #define XFS_IOLOCK_SHARED (1<<1) #define XFS_ILOCK_EXCL (1<<2) #define XFS_ILOCK_SHARED (1<<3) +#define XFS_MMAPLOCK_EXCL (1<<4) +#define XFS_MMAPLOCK_SHARED (1<<5) #define XFS_LOCK_MASK (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED \ - | XFS_ILOCK_EXCL | XFS_ILOCK_SHARED) + | XFS_ILOCK_EXCL | XFS_ILOCK_SHARED \ + | XFS_MMAPLOCK_EXCL | XFS_MMAPLOCK_SHARED) #define XFS_LOCK_FLAGS \ { XFS_IOLOCK_EXCL, "IOLOCK_EXCL" }, \ { XFS_IOLOCK_SHARED, "IOLOCK_SHARED" }, \ { XFS_ILOCK_EXCL, "ILOCK_EXCL" }, \ - { XFS_ILOCK_SHARED, "ILOCK_SHARED" } + { XFS_ILOCK_SHARED, "ILOCK_SHARED" }, \ + { XFS_MMAPLOCK_EXCL, "MMAPLOCK_EXCL" }, \ + { XFS_MMAPLOCK_SHARED, "MMAPLOCK_SHARED" } /* @@ -302,17 +308,26 @@ static inline int xfs_isiflocked(struct xfs_inode *ip) #define XFS_IOLOCK_SHIFT 16 #define XFS_IOLOCK_PARENT (XFS_LOCK_PARENT << XFS_IOLOCK_SHIFT) +#define XFS_MMAPLOCK_SHIFT 20 + #define XFS_ILOCK_SHIFT 24 #define XFS_ILOCK_PARENT (XFS_LOCK_PARENT << XFS_ILOCK_SHIFT) #define XFS_ILOCK_RTBITMAP (XFS_LOCK_RTBITMAP << XFS_ILOCK_SHIFT) #define XFS_ILOCK_RTSUM (XFS_LOCK_RTSUM << XFS_ILOCK_SHIFT) -#define XFS_IOLOCK_DEP_MASK 0x00ff0000 +#define XFS_IOLOCK_DEP_MASK 0x000f0000 +#define XFS_MMAPLOCK_DEP_MASK 0x00f00000 #define XFS_ILOCK_DEP_MASK 0xff000000 -#define XFS_LOCK_DEP_MASK (XFS_IOLOCK_DEP_MASK | XFS_ILOCK_DEP_MASK) +#define XFS_LOCK_DEP_MASK (XFS_IOLOCK_DEP_MASK | \ + XFS_MMAPLOCK_DEP_MASK | \ + XFS_ILOCK_DEP_MASK) -#define XFS_IOLOCK_DEP(flags) (((flags) & XFS_IOLOCK_DEP_MASK) >> XFS_IOLOCK_SHIFT) -#define XFS_ILOCK_DEP(flags) (((flags) & XFS_ILOCK_DEP_MASK) >> XFS_ILOCK_SHIFT) +#define XFS_IOLOCK_DEP(flags) (((flags) & XFS_IOLOCK_DEP_MASK) \ + >> XFS_IOLOCK_SHIFT) +#define XFS_MMAPLOCK_DEP(flags) (((flags) & XFS_MMAPLOCK_DEP_MASK) \ + >> XFS_MMAPLOCK_SHIFT) +#define XFS_ILOCK_DEP(flags) (((flags) & XFS_ILOCK_DEP_MASK) \ + >> XFS_ILOCK_SHIFT) /* * For multiple groups support: if S_ISGID bit is set in the parent @@ -391,6 +406,28 @@ int xfs_zero_eof(struct xfs_inode *ip, xfs_off_t offset, int xfs_iozero(struct xfs_inode *ip, loff_t pos, size_t count); +/* from xfs_iops.c */ +/* + * When setting up a newly allocated inode, we need to call + * xfs_finish_inode_setup() once the inode is fully instantiated at + * the VFS level to prevent the rest of the world seeing the inode + * before we've completed instantiation. Otherwise we can do it + * the moment the inode lookup is complete. + */ +extern void xfs_setup_inode(struct xfs_inode *ip); +static inline void xfs_finish_inode_setup(struct xfs_inode *ip) +{ + xfs_iflags_clear(ip, XFS_INEW); + barrier(); + unlock_new_inode(VFS_I(ip)); +} + +static inline void xfs_setup_existing_inode(struct xfs_inode *ip) +{ + xfs_setup_inode(ip); + xfs_finish_inode_setup(ip); +} + #define IHOLD(ip) \ do { \ ASSERT(atomic_read(&VFS_I(ip)->i_count) > 0) ; \ diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index ac4feae45eb3..5f4a396f5186 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -631,7 +631,7 @@ xfs_ioc_space( if (filp->f_flags & O_DSYNC) flags |= XFS_PREALLOC_SYNC; - if (ioflags & XFS_IO_INVIS) + if (ioflags & XFS_IO_INVIS) flags |= XFS_PREALLOC_INVISIBLE; error = mnt_want_write_file(filp); @@ -639,10 +639,13 @@ xfs_ioc_space( return error; xfs_ilock(ip, iolock); - error = xfs_break_layouts(inode, &iolock); + error = xfs_break_layouts(inode, &iolock, false); if (error) goto out_unlock; + xfs_ilock(ip, XFS_MMAPLOCK_EXCL); + iolock |= XFS_MMAPLOCK_EXCL; + switch (bf->l_whence) { case 0: /*SEEK_SET*/ break; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index ccb1dd0d509e..38e633bad8c2 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -460,8 +460,7 @@ xfs_iomap_prealloc_size( alloc_blocks = XFS_FILEOFF_MIN(roundup_pow_of_two(MAXEXTLEN), alloc_blocks); - xfs_icsb_sync_counters(mp, XFS_ICSB_LAZY_COUNT); - freesp = mp->m_sb.sb_fdblocks; + freesp = percpu_counter_read_positive(&mp->m_fdblocks); if (freesp < mp->m_low_space[XFS_LOWSP_5_PCNT]) { shift = 2; if (freesp < mp->m_low_space[XFS_LOWSP_4_PCNT]) diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index e53a90331422..2f1839e4dd1b 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -187,6 +187,8 @@ xfs_generic_create( else d_instantiate(dentry, inode); + xfs_finish_inode_setup(ip); + out_free_acl: if (default_acl) posix_acl_release(default_acl); @@ -195,6 +197,7 @@ xfs_generic_create( return error; out_cleanup_inode: + xfs_finish_inode_setup(ip); if (!tmpfile) xfs_cleanup_inode(dir, inode, dentry); iput(inode); @@ -367,9 +370,11 @@ xfs_vn_symlink( goto out_cleanup_inode; d_instantiate(dentry, inode); + xfs_finish_inode_setup(cip); return 0; out_cleanup_inode: + xfs_finish_inode_setup(cip); xfs_cleanup_inode(dir, inode, dentry); iput(inode); out: @@ -389,7 +394,7 @@ xfs_vn_rename( struct xfs_name oname; struct xfs_name nname; - if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) return -EINVAL; /* if we are exchanging files, we need to set i_mode of both files */ @@ -766,6 +771,7 @@ xfs_setattr_size( return error; ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); + ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL)); ASSERT(S_ISREG(ip->i_d.di_mode)); ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET| ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0); @@ -829,55 +835,27 @@ xfs_setattr_size( inode_dio_wait(inode); /* - * Do all the page cache truncate work outside the transaction context - * as the "lock" order is page lock->log space reservation. i.e. - * locking pages inside the transaction can ABBA deadlock with - * writeback. We have to do the VFS inode size update before we truncate - * the pagecache, however, to avoid racing with page faults beyond the - * new EOF they are not serialised against truncate operations except by - * page locks and size updates. + * We've already locked out new page faults, so now we can safely remove + * pages from the page cache knowing they won't get refaulted until we + * drop the XFS_MMAP_EXCL lock after the extent manipulations are + * complete. The truncate_setsize() call also cleans partial EOF page + * PTEs on extending truncates and hence ensures sub-page block size + * filesystems are correctly handled, too. * - * Hence we are in a situation where a truncate can fail with ENOMEM - * from xfs_trans_reserve(), but having already truncated the in-memory - * version of the file (i.e. made user visible changes). There's not - * much we can do about this, except to hope that the caller sees ENOMEM - * and retries the truncate operation. + * We have to do all the page cache truncate work outside the + * transaction context as the "lock" order is page lock->log space + * reservation as defined by extent allocation in the writeback path. + * Hence a truncate can fail with ENOMEM from xfs_trans_reserve(), but + * having already truncated the in-memory version of the file (i.e. made + * user visible changes). There's not much we can do about this, except + * to hope that the caller sees ENOMEM and retries the truncate + * operation. */ error = block_truncate_page(inode->i_mapping, newsize, xfs_get_blocks); if (error) return error; truncate_setsize(inode, newsize); - /* - * The "we can't serialise against page faults" pain gets worse. - * - * If the file is mapped then we have to clean the page at the old EOF - * when extending the file. Extending the file can expose changes the - * underlying page mapping (e.g. from beyond EOF to a hole or - * unwritten), and so on the next attempt to write to that page we need - * to remap it for write. i.e. we need .page_mkwrite() to be called. - * Hence we need to clean the page to clean the pte and so a new write - * fault will be triggered appropriately. - * - * If we do it before we change the inode size, then we can race with a - * page fault that maps the page with exactly the same problem. If we do - * it after we change the file size, then a new page fault can come in - * and allocate space before we've run the rest of the truncate - * transaction. That's kinda grotesque, but it's better than have data - * over a hole, and so that's the lesser evil that has been chosen here. - * - * The real solution, however, is to have some mechanism for locking out - * page faults while a truncate is in progress. - */ - if (newsize > oldsize && mapping_mapped(VFS_I(ip)->i_mapping)) { - error = filemap_write_and_wait_range( - VFS_I(ip)->i_mapping, - round_down(oldsize, PAGE_CACHE_SIZE), - round_up(oldsize, PAGE_CACHE_SIZE) - 1); - if (error) - return error; - } - tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE); error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0); if (error) @@ -975,9 +953,13 @@ xfs_vn_setattr( uint iolock = XFS_IOLOCK_EXCL; xfs_ilock(ip, iolock); - error = xfs_break_layouts(dentry->d_inode, &iolock); - if (!error) + error = xfs_break_layouts(dentry->d_inode, &iolock, true); + if (!error) { + xfs_ilock(ip, XFS_MMAPLOCK_EXCL); + iolock |= XFS_MMAPLOCK_EXCL; + error = xfs_setattr_size(ip, iattr); + } xfs_iunlock(ip, iolock); } else { error = xfs_setattr_nonsize(ip, iattr, 0); @@ -1228,16 +1210,12 @@ xfs_diflags_to_iflags( } /* - * Initialize the Linux inode, set up the operation vectors and - * unlock the inode. + * Initialize the Linux inode and set up the operation vectors. * - * When reading existing inodes from disk this is called directly - * from xfs_iget, when creating a new inode it is called from - * xfs_ialloc after setting up the inode. - * - * We are always called with an uninitialised linux inode here. - * We need to initialise the necessary fields and take a reference - * on it. + * When reading existing inodes from disk this is called directly from xfs_iget, + * when creating a new inode it is called from xfs_ialloc after setting up the + * inode. These callers have different criteria for clearing XFS_INEW, so leave + * it up to the caller to deal with unlocking the inode appropriately. */ void xfs_setup_inode( @@ -1324,9 +1302,4 @@ xfs_setup_inode( inode_has_no_xattr(inode); cache_no_acl(inode); } - - xfs_iflags_clear(ip, XFS_INEW); - barrier(); - - unlock_new_inode(inode); } diff --git a/fs/xfs/xfs_iops.h b/fs/xfs/xfs_iops.h index ea7a98e9cb70..a0f84abb0d09 100644 --- a/fs/xfs/xfs_iops.h +++ b/fs/xfs/xfs_iops.h @@ -25,8 +25,6 @@ extern const struct file_operations xfs_dir_file_operations; extern ssize_t xfs_vn_listxattr(struct dentry *, char *data, size_t size); -extern void xfs_setup_inode(struct xfs_inode *); - /* * Internal setattr interfaces. */ diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index 82e314258f73..80429891dc9b 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -229,7 +229,7 @@ xfs_bulkstat_grab_ichunk( error = xfs_inobt_get_rec(cur, irec, &stat); if (error) return error; - XFS_WANT_CORRUPTED_RETURN(stat == 1); + XFS_WANT_CORRUPTED_RETURN(cur->bc_mp, stat == 1); /* Check if the record contains the inode in request */ if (irec->ir_startino + XFS_INODES_PER_CHUNK <= agino) { diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h index c31d2c2eadc4..7c7842c85a08 100644 --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -116,15 +116,6 @@ typedef __uint64_t __psunsigned_t; #undef XFS_NATIVE_HOST #endif -/* - * Feature macros (disable/enable) - */ -#ifdef CONFIG_SMP -#define HAVE_PERCPU_SB /* per cpu superblock counters are a 2.6 feature */ -#else -#undef HAVE_PERCPU_SB /* per cpu superblock counters are a 2.6 feature */ -#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 diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index a5a945fc3bdc..4f5784f85a5b 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -4463,10 +4463,10 @@ xlog_do_recover( xfs_sb_from_disk(sbp, XFS_BUF_TO_SBP(bp)); ASSERT(sbp->sb_magicnum == XFS_SB_MAGIC); ASSERT(xfs_sb_good_version(sbp)); + xfs_reinit_percpu_counters(log->l_mp); + xfs_buf_relse(bp); - /* We've re-read the superblock so re-initialize per-cpu counters */ - xfs_icsb_reinit_counters(log->l_mp); xlog_recover_check_summary(log); diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 4fa80e63eea2..2ce7ee3b4ec1 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -43,18 +43,6 @@ #include "xfs_sysfs.h" -#ifdef HAVE_PERCPU_SB -STATIC void xfs_icsb_balance_counter(xfs_mount_t *, xfs_sb_field_t, - int); -STATIC void xfs_icsb_balance_counter_locked(xfs_mount_t *, xfs_sb_field_t, - int); -STATIC void xfs_icsb_disable_counter(xfs_mount_t *, xfs_sb_field_t); -#else - -#define xfs_icsb_balance_counter(mp, a, b) do { } while (0) -#define xfs_icsb_balance_counter_locked(mp, a, b) do { } while (0) -#endif - static DEFINE_MUTEX(xfs_uuid_table_mutex); static int xfs_uuid_table_size; static uuid_t *xfs_uuid_table; @@ -347,8 +335,7 @@ reread: goto reread; } - /* Initialize per-cpu counters */ - xfs_icsb_reinit_counters(mp); + xfs_reinit_percpu_counters(mp); /* no need to be quiet anymore, so reset the buf ops */ bp->b_ops = &xfs_sb_buf_ops; @@ -1087,8 +1074,6 @@ xfs_log_sbcount(xfs_mount_t *mp) if (!xfs_fs_writable(mp, SB_FREEZE_COMPLETE)) return 0; - xfs_icsb_sync_counters(mp, 0); - /* * we don't need to do this if we are updating the superblock * counters on every modification. @@ -1099,253 +1084,136 @@ xfs_log_sbcount(xfs_mount_t *mp) return xfs_sync_sb(mp, true); } -/* - * xfs_mod_incore_sb_unlocked() is a utility routine commonly used to apply - * a delta to a specified field in the in-core superblock. Simply - * switch on the field indicated and apply the delta to that field. - * Fields are not allowed to dip below zero, so if the delta would - * do this do not apply it and return EINVAL. - * - * The m_sb_lock must be held when this routine is called. - */ -STATIC int -xfs_mod_incore_sb_unlocked( - xfs_mount_t *mp, - xfs_sb_field_t field, - int64_t delta, - int rsvd) +int +xfs_mod_icount( + struct xfs_mount *mp, + int64_t delta) { - int scounter; /* short counter for 32 bit fields */ - long long lcounter; /* long counter for 64 bit fields */ - long long res_used, rem; - - /* - * With the in-core superblock spin lock held, switch - * on the indicated field. Apply the delta to the - * proper field. If the fields value would dip below - * 0, then do not apply the delta and return EINVAL. - */ - switch (field) { - case XFS_SBS_ICOUNT: - lcounter = (long long)mp->m_sb.sb_icount; - lcounter += delta; - if (lcounter < 0) { - ASSERT(0); - return -EINVAL; - } - mp->m_sb.sb_icount = lcounter; - return 0; - case XFS_SBS_IFREE: - lcounter = (long long)mp->m_sb.sb_ifree; - lcounter += delta; - if (lcounter < 0) { - ASSERT(0); - return -EINVAL; - } - mp->m_sb.sb_ifree = lcounter; - return 0; - case XFS_SBS_FDBLOCKS: - lcounter = (long long) - mp->m_sb.sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp); - res_used = (long long)(mp->m_resblks - mp->m_resblks_avail); - - if (delta > 0) { /* Putting blocks back */ - if (res_used > delta) { - mp->m_resblks_avail += delta; - } else { - rem = delta - res_used; - mp->m_resblks_avail = mp->m_resblks; - lcounter += rem; - } - } else { /* Taking blocks away */ - lcounter += delta; - if (lcounter >= 0) { - mp->m_sb.sb_fdblocks = lcounter + - XFS_ALLOC_SET_ASIDE(mp); - return 0; - } - - /* - * We are out of blocks, use any available reserved - * blocks if were allowed to. - */ - if (!rsvd) - return -ENOSPC; - - lcounter = (long long)mp->m_resblks_avail + delta; - if (lcounter >= 0) { - mp->m_resblks_avail = lcounter; - return 0; - } - printk_once(KERN_WARNING - "Filesystem \"%s\": reserve blocks depleted! " - "Consider increasing reserve pool size.", - mp->m_fsname); - return -ENOSPC; - } - - mp->m_sb.sb_fdblocks = lcounter + XFS_ALLOC_SET_ASIDE(mp); - return 0; - case XFS_SBS_FREXTENTS: - lcounter = (long long)mp->m_sb.sb_frextents; - lcounter += delta; - if (lcounter < 0) { - return -ENOSPC; - } - mp->m_sb.sb_frextents = lcounter; - return 0; - case XFS_SBS_DBLOCKS: - lcounter = (long long)mp->m_sb.sb_dblocks; - lcounter += delta; - if (lcounter < 0) { - ASSERT(0); - return -EINVAL; - } - mp->m_sb.sb_dblocks = lcounter; - return 0; - case XFS_SBS_AGCOUNT: - scounter = mp->m_sb.sb_agcount; - scounter += delta; - if (scounter < 0) { - ASSERT(0); - return -EINVAL; - } - mp->m_sb.sb_agcount = scounter; - return 0; - case XFS_SBS_IMAX_PCT: - scounter = mp->m_sb.sb_imax_pct; - scounter += delta; - if (scounter < 0) { - ASSERT(0); - return -EINVAL; - } - mp->m_sb.sb_imax_pct = scounter; - return 0; - case XFS_SBS_REXTSIZE: - scounter = mp->m_sb.sb_rextsize; - scounter += delta; - if (scounter < 0) { - ASSERT(0); - return -EINVAL; - } - mp->m_sb.sb_rextsize = scounter; - return 0; - case XFS_SBS_RBMBLOCKS: - scounter = mp->m_sb.sb_rbmblocks; - scounter += delta; - if (scounter < 0) { - ASSERT(0); - return -EINVAL; - } - mp->m_sb.sb_rbmblocks = scounter; - return 0; - case XFS_SBS_RBLOCKS: - lcounter = (long long)mp->m_sb.sb_rblocks; - lcounter += delta; - if (lcounter < 0) { - ASSERT(0); - return -EINVAL; - } - mp->m_sb.sb_rblocks = lcounter; - return 0; - case XFS_SBS_REXTENTS: - lcounter = (long long)mp->m_sb.sb_rextents; - lcounter += delta; - if (lcounter < 0) { - ASSERT(0); - return -EINVAL; - } - mp->m_sb.sb_rextents = lcounter; - return 0; - case XFS_SBS_REXTSLOG: - scounter = mp->m_sb.sb_rextslog; - scounter += delta; - if (scounter < 0) { - ASSERT(0); - return -EINVAL; - } - mp->m_sb.sb_rextslog = scounter; - return 0; - default: + /* deltas are +/-64, hence the large batch size of 128. */ + __percpu_counter_add(&mp->m_icount, delta, 128); + if (percpu_counter_compare(&mp->m_icount, 0) < 0) { ASSERT(0); + percpu_counter_add(&mp->m_icount, -delta); return -EINVAL; } + return 0; } -/* - * xfs_mod_incore_sb() is used to change a field in the in-core - * superblock structure by the specified delta. This modification - * is protected by the m_sb_lock. Just use the xfs_mod_incore_sb_unlocked() - * routine to do the work. - */ int -xfs_mod_incore_sb( +xfs_mod_ifree( struct xfs_mount *mp, - xfs_sb_field_t field, - int64_t delta, - int rsvd) + int64_t delta) { - int status; - -#ifdef HAVE_PERCPU_SB - ASSERT(field < XFS_SBS_ICOUNT || field > XFS_SBS_FDBLOCKS); -#endif - spin_lock(&mp->m_sb_lock); - status = xfs_mod_incore_sb_unlocked(mp, field, delta, rsvd); - spin_unlock(&mp->m_sb_lock); - - return status; + percpu_counter_add(&mp->m_ifree, delta); + if (percpu_counter_compare(&mp->m_ifree, 0) < 0) { + ASSERT(0); + percpu_counter_add(&mp->m_ifree, -delta); + return -EINVAL; + } + return 0; } -/* - * Change more than one field in the in-core superblock structure at a time. - * - * The fields and changes to those fields are specified in the array of - * xfs_mod_sb structures passed in. Either all of the specified deltas - * will be applied or none of them will. If any modified field dips below 0, - * then all modifications will be backed out and EINVAL will be returned. - * - * Note that this function may not be used for the superblock values that - * are tracked with the in-memory per-cpu counters - a direct call to - * xfs_icsb_modify_counters is required for these. - */ int -xfs_mod_incore_sb_batch( +xfs_mod_fdblocks( struct xfs_mount *mp, - xfs_mod_sb_t *msb, - uint nmsb, - int rsvd) + int64_t delta, + bool rsvd) { - xfs_mod_sb_t *msbp; - int error = 0; + int64_t lcounter; + long long res_used; + s32 batch; + + if (delta > 0) { + /* + * If the reserve pool is depleted, put blocks back into it + * first. Most of the time the pool is full. + */ + if (likely(mp->m_resblks == mp->m_resblks_avail)) { + percpu_counter_add(&mp->m_fdblocks, delta); + return 0; + } + + spin_lock(&mp->m_sb_lock); + res_used = (long long)(mp->m_resblks - mp->m_resblks_avail); + + if (res_used > delta) { + mp->m_resblks_avail += delta; + } else { + delta -= res_used; + mp->m_resblks_avail = mp->m_resblks; + percpu_counter_add(&mp->m_fdblocks, delta); + } + spin_unlock(&mp->m_sb_lock); + return 0; + } /* - * Loop through the array of mod structures and apply each individually. - * If any fail, then back out all those which have already been applied. - * Do all of this within the scope of the m_sb_lock so that all of the - * changes will be atomic. + * Taking blocks away, need to be more accurate the closer we + * are to zero. + * + * batch size is set to a maximum of 1024 blocks - if we are + * allocating of freeing extents larger than this then we aren't + * going to be hammering the counter lock so a lock per update + * is not a problem. + * + * If the counter has a value of less than 2 * max batch size, + * then make everything serialise as we are real close to + * ENOSPC. + */ +#define __BATCH 1024 + if (percpu_counter_compare(&mp->m_fdblocks, 2 * __BATCH) < 0) + batch = 1; + else + batch = __BATCH; +#undef __BATCH + + __percpu_counter_add(&mp->m_fdblocks, delta, batch); + if (percpu_counter_compare(&mp->m_fdblocks, + XFS_ALLOC_SET_ASIDE(mp)) >= 0) { + /* we had space! */ + return 0; + } + + /* + * lock up the sb for dipping into reserves before releasing the space + * that took us to ENOSPC. */ spin_lock(&mp->m_sb_lock); - for (msbp = msb; msbp < (msb + nmsb); msbp++) { - ASSERT(msbp->msb_field < XFS_SBS_ICOUNT || - msbp->msb_field > XFS_SBS_FDBLOCKS); + percpu_counter_add(&mp->m_fdblocks, -delta); + if (!rsvd) + goto fdblocks_enospc; - error = xfs_mod_incore_sb_unlocked(mp, msbp->msb_field, - msbp->msb_delta, rsvd); - if (error) - goto unwind; + lcounter = (long long)mp->m_resblks_avail + delta; + if (lcounter >= 0) { + mp->m_resblks_avail = lcounter; + spin_unlock(&mp->m_sb_lock); + return 0; } + printk_once(KERN_WARNING + "Filesystem \"%s\": reserve blocks depleted! " + "Consider increasing reserve pool size.", + mp->m_fsname); +fdblocks_enospc: spin_unlock(&mp->m_sb_lock); - return 0; + return -ENOSPC; +} -unwind: - while (--msbp >= msb) { - error = xfs_mod_incore_sb_unlocked(mp, msbp->msb_field, - -msbp->msb_delta, rsvd); - ASSERT(error == 0); - } +int +xfs_mod_frextents( + struct xfs_mount *mp, + int64_t delta) +{ + int64_t lcounter; + int ret = 0; + + spin_lock(&mp->m_sb_lock); + lcounter = mp->m_sb.sb_frextents + delta; + if (lcounter < 0) + ret = -ENOSPC; + else + mp->m_sb.sb_frextents = lcounter; spin_unlock(&mp->m_sb_lock); - return error; + return ret; } /* @@ -1407,573 +1275,3 @@ xfs_dev_is_read_only( } return 0; } - -#ifdef HAVE_PERCPU_SB -/* - * Per-cpu incore superblock counters - * - * Simple concept, difficult implementation - * - * Basically, replace the incore superblock counters with a distributed per cpu - * counter for contended fields (e.g. free block count). - * - * Difficulties arise in that the incore sb is used for ENOSPC checking, and - * hence needs to be accurately read when we are running low on space. Hence - * there is a method to enable and disable the per-cpu counters based on how - * much "stuff" is available in them. - * - * Basically, a counter is enabled if there is enough free resource to justify - * running a per-cpu fast-path. If the per-cpu counter runs out (i.e. a local - * ENOSPC), then we disable the counters to synchronise all callers and - * re-distribute the available resources. - * - * If, once we redistributed the available resources, we still get a failure, - * we disable the per-cpu counter and go through the slow path. - * - * The slow path is the current xfs_mod_incore_sb() function. This means that - * when we disable a per-cpu counter, we need to drain its resources back to - * the global superblock. We do this after disabling the counter to prevent - * more threads from queueing up on the counter. - * - * Essentially, this means that we still need a lock in the fast path to enable - * synchronisation between the global counters and the per-cpu counters. This - * is not a problem because the lock will be local to a CPU almost all the time - * and have little contention except when we get to ENOSPC conditions. - * - * Basically, this lock becomes a barrier that enables us to lock out the fast - * path while we do things like enabling and disabling counters and - * synchronising the counters. - * - * Locking rules: - * - * 1. m_sb_lock before picking up per-cpu locks - * 2. per-cpu locks always picked up via for_each_online_cpu() order - * 3. accurate counter sync requires m_sb_lock + per cpu locks - * 4. modifying per-cpu counters requires holding per-cpu lock - * 5. modifying global counters requires holding m_sb_lock - * 6. enabling or disabling a counter requires holding the m_sb_lock - * and _none_ of the per-cpu locks. - * - * Disabled counters are only ever re-enabled by a balance operation - * that results in more free resources per CPU than a given threshold. - * To ensure counters don't remain disabled, they are rebalanced when - * the global resource goes above a higher threshold (i.e. some hysteresis - * is present to prevent thrashing). - */ - -#ifdef CONFIG_HOTPLUG_CPU -/* - * hot-plug CPU notifier support. - * - * We need a notifier per filesystem as we need to be able to identify - * the filesystem to balance the counters out. This is achieved by - * having a notifier block embedded in the xfs_mount_t and doing pointer - * magic to get the mount pointer from the notifier block address. - */ -STATIC int -xfs_icsb_cpu_notify( - struct notifier_block *nfb, - unsigned long action, - void *hcpu) -{ - xfs_icsb_cnts_t *cntp; - xfs_mount_t *mp; - - mp = (xfs_mount_t *)container_of(nfb, xfs_mount_t, m_icsb_notifier); - cntp = (xfs_icsb_cnts_t *) - per_cpu_ptr(mp->m_sb_cnts, (unsigned long)hcpu); - switch (action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - /* Easy Case - initialize the area and locks, and - * then rebalance when online does everything else for us. */ - memset(cntp, 0, sizeof(xfs_icsb_cnts_t)); - break; - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - xfs_icsb_lock(mp); - xfs_icsb_balance_counter(mp, XFS_SBS_ICOUNT, 0); - xfs_icsb_balance_counter(mp, XFS_SBS_IFREE, 0); - xfs_icsb_balance_counter(mp, XFS_SBS_FDBLOCKS, 0); - xfs_icsb_unlock(mp); - break; - case CPU_DEAD: - case CPU_DEAD_FROZEN: - /* Disable all the counters, then fold the dead cpu's - * count into the total on the global superblock and - * re-enable the counters. */ - xfs_icsb_lock(mp); - spin_lock(&mp->m_sb_lock); - xfs_icsb_disable_counter(mp, XFS_SBS_ICOUNT); - xfs_icsb_disable_counter(mp, XFS_SBS_IFREE); - xfs_icsb_disable_counter(mp, XFS_SBS_FDBLOCKS); - - mp->m_sb.sb_icount += cntp->icsb_icount; - mp->m_sb.sb_ifree += cntp->icsb_ifree; - mp->m_sb.sb_fdblocks += cntp->icsb_fdblocks; - - memset(cntp, 0, sizeof(xfs_icsb_cnts_t)); - - xfs_icsb_balance_counter_locked(mp, XFS_SBS_ICOUNT, 0); - xfs_icsb_balance_counter_locked(mp, XFS_SBS_IFREE, 0); - xfs_icsb_balance_counter_locked(mp, XFS_SBS_FDBLOCKS, 0); - spin_unlock(&mp->m_sb_lock); - xfs_icsb_unlock(mp); - break; - } - - return NOTIFY_OK; -} -#endif /* CONFIG_HOTPLUG_CPU */ - -int -xfs_icsb_init_counters( - xfs_mount_t *mp) -{ - xfs_icsb_cnts_t *cntp; - int i; - - mp->m_sb_cnts = alloc_percpu(xfs_icsb_cnts_t); - if (mp->m_sb_cnts == NULL) - return -ENOMEM; - - for_each_online_cpu(i) { - cntp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, i); - memset(cntp, 0, sizeof(xfs_icsb_cnts_t)); - } - - mutex_init(&mp->m_icsb_mutex); - - /* - * start with all counters disabled so that the - * initial balance kicks us off correctly - */ - mp->m_icsb_counters = -1; - -#ifdef CONFIG_HOTPLUG_CPU - mp->m_icsb_notifier.notifier_call = xfs_icsb_cpu_notify; - mp->m_icsb_notifier.priority = 0; - register_hotcpu_notifier(&mp->m_icsb_notifier); -#endif /* CONFIG_HOTPLUG_CPU */ - - return 0; -} - -void -xfs_icsb_reinit_counters( - xfs_mount_t *mp) -{ - xfs_icsb_lock(mp); - /* - * start with all counters disabled so that the - * initial balance kicks us off correctly - */ - mp->m_icsb_counters = -1; - xfs_icsb_balance_counter(mp, XFS_SBS_ICOUNT, 0); - xfs_icsb_balance_counter(mp, XFS_SBS_IFREE, 0); - xfs_icsb_balance_counter(mp, XFS_SBS_FDBLOCKS, 0); - xfs_icsb_unlock(mp); -} - -void -xfs_icsb_destroy_counters( - xfs_mount_t *mp) -{ - if (mp->m_sb_cnts) { - unregister_hotcpu_notifier(&mp->m_icsb_notifier); - free_percpu(mp->m_sb_cnts); - } - mutex_destroy(&mp->m_icsb_mutex); -} - -STATIC void -xfs_icsb_lock_cntr( - xfs_icsb_cnts_t *icsbp) -{ - while (test_and_set_bit(XFS_ICSB_FLAG_LOCK, &icsbp->icsb_flags)) { - ndelay(1000); - } -} - -STATIC void -xfs_icsb_unlock_cntr( - xfs_icsb_cnts_t *icsbp) -{ - clear_bit(XFS_ICSB_FLAG_LOCK, &icsbp->icsb_flags); -} - - -STATIC void -xfs_icsb_lock_all_counters( - xfs_mount_t *mp) -{ - xfs_icsb_cnts_t *cntp; - int i; - - for_each_online_cpu(i) { - cntp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, i); - xfs_icsb_lock_cntr(cntp); - } -} - -STATIC void -xfs_icsb_unlock_all_counters( - xfs_mount_t *mp) -{ - xfs_icsb_cnts_t *cntp; - int i; - - for_each_online_cpu(i) { - cntp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, i); - xfs_icsb_unlock_cntr(cntp); - } -} - -STATIC void -xfs_icsb_count( - xfs_mount_t *mp, - xfs_icsb_cnts_t *cnt, - int flags) -{ - xfs_icsb_cnts_t *cntp; - int i; - - memset(cnt, 0, sizeof(xfs_icsb_cnts_t)); - - if (!(flags & XFS_ICSB_LAZY_COUNT)) - xfs_icsb_lock_all_counters(mp); - - for_each_online_cpu(i) { - cntp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, i); - cnt->icsb_icount += cntp->icsb_icount; - cnt->icsb_ifree += cntp->icsb_ifree; - cnt->icsb_fdblocks += cntp->icsb_fdblocks; - } - - if (!(flags & XFS_ICSB_LAZY_COUNT)) - xfs_icsb_unlock_all_counters(mp); -} - -STATIC int -xfs_icsb_counter_disabled( - xfs_mount_t *mp, - xfs_sb_field_t field) -{ - ASSERT((field >= XFS_SBS_ICOUNT) && (field <= XFS_SBS_FDBLOCKS)); - return test_bit(field, &mp->m_icsb_counters); -} - -STATIC void -xfs_icsb_disable_counter( - xfs_mount_t *mp, - xfs_sb_field_t field) -{ - xfs_icsb_cnts_t cnt; - - ASSERT((field >= XFS_SBS_ICOUNT) && (field <= XFS_SBS_FDBLOCKS)); - - /* - * If we are already disabled, then there is nothing to do - * here. We check before locking all the counters to avoid - * the expensive lock operation when being called in the - * slow path and the counter is already disabled. This is - * safe because the only time we set or clear this state is under - * the m_icsb_mutex. - */ - if (xfs_icsb_counter_disabled(mp, field)) - return; - - xfs_icsb_lock_all_counters(mp); - if (!test_and_set_bit(field, &mp->m_icsb_counters)) { - /* drain back to superblock */ - - xfs_icsb_count(mp, &cnt, XFS_ICSB_LAZY_COUNT); - switch(field) { - case XFS_SBS_ICOUNT: - mp->m_sb.sb_icount = cnt.icsb_icount; - break; - case XFS_SBS_IFREE: - mp->m_sb.sb_ifree = cnt.icsb_ifree; - break; - case XFS_SBS_FDBLOCKS: - mp->m_sb.sb_fdblocks = cnt.icsb_fdblocks; - break; - default: - BUG(); - } - } - - xfs_icsb_unlock_all_counters(mp); -} - -STATIC void -xfs_icsb_enable_counter( - xfs_mount_t *mp, - xfs_sb_field_t field, - uint64_t count, - uint64_t resid) -{ - xfs_icsb_cnts_t *cntp; - int i; - - ASSERT((field >= XFS_SBS_ICOUNT) && (field <= XFS_SBS_FDBLOCKS)); - - xfs_icsb_lock_all_counters(mp); - for_each_online_cpu(i) { - cntp = per_cpu_ptr(mp->m_sb_cnts, i); - switch (field) { - case XFS_SBS_ICOUNT: - cntp->icsb_icount = count + resid; - break; - case XFS_SBS_IFREE: - cntp->icsb_ifree = count + resid; - break; - case XFS_SBS_FDBLOCKS: - cntp->icsb_fdblocks = count + resid; - break; - default: - BUG(); - break; - } - resid = 0; - } - clear_bit(field, &mp->m_icsb_counters); - xfs_icsb_unlock_all_counters(mp); -} - -void -xfs_icsb_sync_counters_locked( - xfs_mount_t *mp, - int flags) -{ - xfs_icsb_cnts_t cnt; - - xfs_icsb_count(mp, &cnt, flags); - - if (!xfs_icsb_counter_disabled(mp, XFS_SBS_ICOUNT)) - mp->m_sb.sb_icount = cnt.icsb_icount; - if (!xfs_icsb_counter_disabled(mp, XFS_SBS_IFREE)) - mp->m_sb.sb_ifree = cnt.icsb_ifree; - if (!xfs_icsb_counter_disabled(mp, XFS_SBS_FDBLOCKS)) - mp->m_sb.sb_fdblocks = cnt.icsb_fdblocks; -} - -/* - * Accurate update of per-cpu counters to incore superblock - */ -void -xfs_icsb_sync_counters( - xfs_mount_t *mp, - int flags) -{ - spin_lock(&mp->m_sb_lock); - xfs_icsb_sync_counters_locked(mp, flags); - spin_unlock(&mp->m_sb_lock); -} - -/* - * Balance and enable/disable counters as necessary. - * - * Thresholds for re-enabling counters are somewhat magic. inode counts are - * chosen to be the same number as single on disk allocation chunk per CPU, and - * free blocks is something far enough zero that we aren't going thrash when we - * get near ENOSPC. We also need to supply a minimum we require per cpu to - * prevent looping endlessly when xfs_alloc_space asks for more than will - * be distributed to a single CPU but each CPU has enough blocks to be - * reenabled. - * - * Note that we can be called when counters are already disabled. - * xfs_icsb_disable_counter() optimises the counter locking in this case to - * prevent locking every per-cpu counter needlessly. - */ - -#define XFS_ICSB_INO_CNTR_REENABLE (uint64_t)64 -#define XFS_ICSB_FDBLK_CNTR_REENABLE(mp) \ - (uint64_t)(512 + XFS_ALLOC_SET_ASIDE(mp)) -STATIC void -xfs_icsb_balance_counter_locked( - xfs_mount_t *mp, - xfs_sb_field_t field, - int min_per_cpu) -{ - uint64_t count, resid; - int weight = num_online_cpus(); - uint64_t min = (uint64_t)min_per_cpu; - - /* disable counter and sync counter */ - xfs_icsb_disable_counter(mp, field); - - /* update counters - first CPU gets residual*/ - switch (field) { - case XFS_SBS_ICOUNT: - count = mp->m_sb.sb_icount; - resid = do_div(count, weight); - if (count < max(min, XFS_ICSB_INO_CNTR_REENABLE)) - return; - break; - case XFS_SBS_IFREE: - count = mp->m_sb.sb_ifree; - resid = do_div(count, weight); - if (count < max(min, XFS_ICSB_INO_CNTR_REENABLE)) - return; - break; - case XFS_SBS_FDBLOCKS: - count = mp->m_sb.sb_fdblocks; - resid = do_div(count, weight); - if (count < max(min, XFS_ICSB_FDBLK_CNTR_REENABLE(mp))) - return; - break; - default: - BUG(); - count = resid = 0; /* quiet, gcc */ - break; - } - - xfs_icsb_enable_counter(mp, field, count, resid); -} - -STATIC void -xfs_icsb_balance_counter( - xfs_mount_t *mp, - xfs_sb_field_t fields, - int min_per_cpu) -{ - spin_lock(&mp->m_sb_lock); - xfs_icsb_balance_counter_locked(mp, fields, min_per_cpu); - spin_unlock(&mp->m_sb_lock); -} - -int -xfs_icsb_modify_counters( - xfs_mount_t *mp, - xfs_sb_field_t field, - int64_t delta, - int rsvd) -{ - xfs_icsb_cnts_t *icsbp; - long long lcounter; /* long counter for 64 bit fields */ - int ret = 0; - - might_sleep(); -again: - preempt_disable(); - icsbp = this_cpu_ptr(mp->m_sb_cnts); - - /* - * if the counter is disabled, go to slow path - */ - if (unlikely(xfs_icsb_counter_disabled(mp, field))) - goto slow_path; - xfs_icsb_lock_cntr(icsbp); - if (unlikely(xfs_icsb_counter_disabled(mp, field))) { - xfs_icsb_unlock_cntr(icsbp); - goto slow_path; - } - - switch (field) { - case XFS_SBS_ICOUNT: - lcounter = icsbp->icsb_icount; - lcounter += delta; - if (unlikely(lcounter < 0)) - goto balance_counter; - icsbp->icsb_icount = lcounter; - break; - - case XFS_SBS_IFREE: - lcounter = icsbp->icsb_ifree; - lcounter += delta; - if (unlikely(lcounter < 0)) - goto balance_counter; - icsbp->icsb_ifree = lcounter; - break; - - case XFS_SBS_FDBLOCKS: - BUG_ON((mp->m_resblks - mp->m_resblks_avail) != 0); - - lcounter = icsbp->icsb_fdblocks - XFS_ALLOC_SET_ASIDE(mp); - lcounter += delta; - if (unlikely(lcounter < 0)) - goto balance_counter; - icsbp->icsb_fdblocks = lcounter + XFS_ALLOC_SET_ASIDE(mp); - break; - default: - BUG(); - break; - } - xfs_icsb_unlock_cntr(icsbp); - preempt_enable(); - return 0; - -slow_path: - preempt_enable(); - - /* - * serialise with a mutex so we don't burn lots of cpu on - * the superblock lock. We still need to hold the superblock - * lock, however, when we modify the global structures. - */ - xfs_icsb_lock(mp); - - /* - * Now running atomically. - * - * If the counter is enabled, someone has beaten us to rebalancing. - * Drop the lock and try again in the fast path.... - */ - if (!(xfs_icsb_counter_disabled(mp, field))) { - xfs_icsb_unlock(mp); - goto again; - } - - /* - * The counter is currently disabled. Because we are - * running atomically here, we know a rebalance cannot - * be in progress. Hence we can go straight to operating - * on the global superblock. We do not call xfs_mod_incore_sb() - * here even though we need to get the m_sb_lock. Doing so - * will cause us to re-enter this function and deadlock. - * Hence we get the m_sb_lock ourselves and then call - * xfs_mod_incore_sb_unlocked() as the unlocked path operates - * directly on the global counters. - */ - spin_lock(&mp->m_sb_lock); - ret = xfs_mod_incore_sb_unlocked(mp, field, delta, rsvd); - spin_unlock(&mp->m_sb_lock); - - /* - * Now that we've modified the global superblock, we - * may be able to re-enable the distributed counters - * (e.g. lots of space just got freed). After that - * we are done. - */ - if (ret != -ENOSPC) - xfs_icsb_balance_counter(mp, field, 0); - xfs_icsb_unlock(mp); - return ret; - -balance_counter: - xfs_icsb_unlock_cntr(icsbp); - preempt_enable(); - - /* - * We may have multiple threads here if multiple per-cpu - * counters run dry at the same time. This will mean we can - * do more balances than strictly necessary but it is not - * the common slowpath case. - */ - xfs_icsb_lock(mp); - - /* - * running atomically. - * - * This will leave the counter in the correct state for future - * accesses. After the rebalance, we simply try again and our retry - * will either succeed through the fast path or slow path without - * another balance operation being required. - */ - xfs_icsb_balance_counter(mp, field, delta); - xfs_icsb_unlock(mp); - goto again; -} - -#endif diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 0d8abd6364d9..8c995a2ccb6f 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -18,8 +18,6 @@ #ifndef __XFS_MOUNT_H__ #define __XFS_MOUNT_H__ -#ifdef __KERNEL__ - struct xlog; struct xfs_inode; struct xfs_mru_cache; @@ -29,44 +27,6 @@ struct xfs_quotainfo; struct xfs_dir_ops; struct xfs_da_geometry; -#ifdef HAVE_PERCPU_SB - -/* - * Valid per-cpu incore superblock counters. Note that if you add new counters, - * you may need to define new counter disabled bit field descriptors as there - * are more possible fields in the superblock that can fit in a bitfield on a - * 32 bit platform. The XFS_SBS_* values for the current current counters just - * fit. - */ -typedef struct xfs_icsb_cnts { - uint64_t icsb_fdblocks; - uint64_t icsb_ifree; - uint64_t icsb_icount; - unsigned long icsb_flags; -} xfs_icsb_cnts_t; - -#define XFS_ICSB_FLAG_LOCK (1 << 0) /* counter lock bit */ - -#define XFS_ICSB_LAZY_COUNT (1 << 1) /* accuracy not needed */ - -extern int xfs_icsb_init_counters(struct xfs_mount *); -extern void xfs_icsb_reinit_counters(struct xfs_mount *); -extern void xfs_icsb_destroy_counters(struct xfs_mount *); -extern void xfs_icsb_sync_counters(struct xfs_mount *, int); -extern void xfs_icsb_sync_counters_locked(struct xfs_mount *, int); -extern int xfs_icsb_modify_counters(struct xfs_mount *, xfs_sb_field_t, - int64_t, int); - -#else -#define xfs_icsb_init_counters(mp) (0) -#define xfs_icsb_destroy_counters(mp) do { } while (0) -#define xfs_icsb_reinit_counters(mp) do { } while (0) -#define xfs_icsb_sync_counters(mp, flags) do { } while (0) -#define xfs_icsb_sync_counters_locked(mp, flags) do { } while (0) -#define xfs_icsb_modify_counters(mp, field, delta, rsvd) \ - xfs_mod_incore_sb(mp, field, delta, rsvd) -#endif - /* dynamic preallocation free space thresholds, 5% down to 1% */ enum { XFS_LOWSP_1_PCNT = 0, @@ -81,8 +41,13 @@ typedef struct xfs_mount { struct super_block *m_super; xfs_tid_t m_tid; /* next unused tid for fs */ struct xfs_ail *m_ail; /* fs active log item list */ - xfs_sb_t m_sb; /* copy of fs superblock */ + + struct xfs_sb m_sb; /* copy of fs superblock */ spinlock_t m_sb_lock; /* sb counter lock */ + struct percpu_counter m_icount; /* allocated inodes counter */ + struct percpu_counter m_ifree; /* free inodes counter */ + struct percpu_counter m_fdblocks; /* free block counter */ + struct xfs_buf *m_sb_bp; /* buffer for superblock */ char *m_fsname; /* filesystem name */ int m_fsname_len; /* strlen of fs name */ @@ -152,12 +117,6 @@ typedef struct xfs_mount { const struct xfs_dir_ops *m_nondir_inode_ops; /* !dir inode ops */ uint m_chsize; /* size of next field */ atomic_t m_active_trans; /* number trans frozen */ -#ifdef HAVE_PERCPU_SB - xfs_icsb_cnts_t __percpu *m_sb_cnts; /* per-cpu superblock counters */ - unsigned long m_icsb_counters; /* disabled per-cpu counters */ - struct notifier_block m_icsb_notifier; /* hotplug cpu notifier */ - struct mutex m_icsb_mutex; /* balancer sync lock */ -#endif struct xfs_mru_cache *m_filestream; /* per-mount filestream data */ struct delayed_work m_reclaim_work; /* background inode reclaim */ struct delayed_work m_eofblocks_work; /* background eof blocks @@ -301,35 +260,6 @@ xfs_daddr_to_agbno(struct xfs_mount *mp, xfs_daddr_t d) } /* - * Per-cpu superblock locking functions - */ -#ifdef HAVE_PERCPU_SB -static inline void -xfs_icsb_lock(xfs_mount_t *mp) -{ - mutex_lock(&mp->m_icsb_mutex); -} - -static inline void -xfs_icsb_unlock(xfs_mount_t *mp) -{ - mutex_unlock(&mp->m_icsb_mutex); -} -#else -#define xfs_icsb_lock(mp) -#define xfs_icsb_unlock(mp) -#endif - -/* - * This structure is for use by the xfs_mod_incore_sb_batch() routine. - * xfs_growfs can specify a few fields which are more than int limit - */ -typedef struct xfs_mod_sb { - xfs_sb_field_t msb_field; /* Field to modify, see below */ - int64_t msb_delta; /* Change to make to specified field */ -} xfs_mod_sb_t; - -/* * Per-ag incore structure, copies of information in agf and agi, to improve the * performance of allocation group selection. */ @@ -383,11 +313,14 @@ extern __uint64_t xfs_default_resblks(xfs_mount_t *mp); extern int xfs_mountfs(xfs_mount_t *mp); extern int xfs_initialize_perag(xfs_mount_t *mp, xfs_agnumber_t agcount, xfs_agnumber_t *maxagi); - extern void xfs_unmountfs(xfs_mount_t *); -extern int xfs_mod_incore_sb(xfs_mount_t *, xfs_sb_field_t, int64_t, int); -extern int xfs_mod_incore_sb_batch(xfs_mount_t *, xfs_mod_sb_t *, - uint, int); + +extern int xfs_mod_icount(struct xfs_mount *mp, int64_t delta); +extern int xfs_mod_ifree(struct xfs_mount *mp, int64_t delta); +extern int xfs_mod_fdblocks(struct xfs_mount *mp, int64_t delta, + bool reserved); +extern int xfs_mod_frextents(struct xfs_mount *mp, int64_t delta); + extern int xfs_mount_log_sb(xfs_mount_t *); extern struct xfs_buf *xfs_getsb(xfs_mount_t *, int); extern int xfs_readsb(xfs_mount_t *, int); @@ -399,6 +332,4 @@ extern int xfs_dev_is_read_only(struct xfs_mount *, char *); extern void xfs_set_low_space_thresholds(struct xfs_mount *); -#endif /* __KERNEL__ */ - #endif /* __XFS_MOUNT_H__ */ diff --git a/fs/xfs/xfs_mru_cache.c b/fs/xfs/xfs_mru_cache.c index 30ecca3037e3..f8a674d7f092 100644 --- a/fs/xfs/xfs_mru_cache.c +++ b/fs/xfs/xfs_mru_cache.c @@ -437,7 +437,7 @@ xfs_mru_cache_insert( if (!mru || !mru->lists) return -EINVAL; - if (radix_tree_preload(GFP_KERNEL)) + if (radix_tree_preload(GFP_NOFS)) return -ENOMEM; INIT_LIST_HEAD(&elem->list_node); diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index 365dd57ea760..981a657eca39 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -31,7 +31,8 @@ int xfs_break_layouts( struct inode *inode, - uint *iolock) + uint *iolock, + bool with_imutex) { struct xfs_inode *ip = XFS_I(inode); int error; @@ -40,8 +41,12 @@ xfs_break_layouts( while ((error = break_layout(inode, false) == -EWOULDBLOCK)) { xfs_iunlock(ip, *iolock); + if (with_imutex && (*iolock & XFS_IOLOCK_EXCL)) + mutex_unlock(&inode->i_mutex); error = break_layout(inode, true); *iolock = XFS_IOLOCK_EXCL; + if (with_imutex) + mutex_lock(&inode->i_mutex); xfs_ilock(ip, *iolock); } diff --git a/fs/xfs/xfs_pnfs.h b/fs/xfs/xfs_pnfs.h index b7fbfce660f6..8147ac108820 100644 --- a/fs/xfs/xfs_pnfs.h +++ b/fs/xfs/xfs_pnfs.h @@ -8,9 +8,10 @@ int xfs_fs_map_blocks(struct inode *inode, loff_t offset, u64 length, int xfs_fs_commit_blocks(struct inode *inode, struct iomap *maps, int nr_maps, struct iattr *iattr); -int xfs_break_layouts(struct inode *inode, uint *iolock); +int xfs_break_layouts(struct inode *inode, uint *iolock, bool with_imutex); #else -static inline int xfs_break_layouts(struct inode *inode, uint *iolock) +static inline int +xfs_break_layouts(struct inode *inode, uint *iolock, bool with_imutex) { return 0; } diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index fbbb9e62e274..5538468c7f63 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -719,6 +719,7 @@ xfs_qm_qino_alloc( xfs_trans_t *tp; int error; int committed; + bool need_alloc = true; *ip = NULL; /* @@ -747,6 +748,7 @@ xfs_qm_qino_alloc( return error; mp->m_sb.sb_gquotino = NULLFSINO; mp->m_sb.sb_pquotino = NULLFSINO; + need_alloc = false; } } @@ -758,7 +760,7 @@ xfs_qm_qino_alloc( return error; } - if (!*ip) { + if (need_alloc) { error = xfs_dir_ialloc(&tp, NULL, S_IFREG, 1, 0, 0, 1, ip, &committed); if (error) { @@ -794,11 +796,14 @@ xfs_qm_qino_alloc( spin_unlock(&mp->m_sb_lock); xfs_log_sb(tp); - if ((error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES))) { + error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES); + if (error) { + ASSERT(XFS_FORCED_SHUTDOWN(mp)); xfs_alert(mp, "%s failed (error %d)!", __func__, error); - return error; } - return 0; + if (need_alloc) + xfs_finish_inode_setup(*ip); + return error; } diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h index 0d4d3590cf85..996a04064894 100644 --- a/fs/xfs/xfs_qm.h +++ b/fs/xfs/xfs_qm.h @@ -168,10 +168,6 @@ extern int xfs_qm_scall_getquota(struct xfs_mount *, xfs_dqid_t, uint, struct qc_dqblk *); extern int xfs_qm_scall_setqlim(struct xfs_mount *, xfs_dqid_t, uint, struct qc_dqblk *); -extern int xfs_qm_scall_getqstat(struct xfs_mount *, - struct fs_quota_stat *); -extern int xfs_qm_scall_getqstatv(struct xfs_mount *, - struct fs_quota_statv *); extern int xfs_qm_scall_quotaon(struct xfs_mount *, uint); extern int xfs_qm_scall_quotaoff(struct xfs_mount *, uint); diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c index 9b965db45800..9a25c9275fb3 100644 --- a/fs/xfs/xfs_qm_syscalls.c +++ b/fs/xfs/xfs_qm_syscalls.c @@ -38,7 +38,6 @@ STATIC int xfs_qm_log_quotaoff(xfs_mount_t *, xfs_qoff_logitem_t **, uint); STATIC int xfs_qm_log_quotaoff_end(xfs_mount_t *, xfs_qoff_logitem_t *, uint); -STATIC uint xfs_qm_export_flags(uint); /* * Turn off quota accounting and/or enforcement for all udquots and/or @@ -389,159 +388,6 @@ xfs_qm_scall_quotaon( return 0; } - -/* - * Return quota status information, such as uquota-off, enforcements, etc. - * for Q_XGETQSTAT command. - */ -int -xfs_qm_scall_getqstat( - struct xfs_mount *mp, - struct fs_quota_stat *out) -{ - struct xfs_quotainfo *q = mp->m_quotainfo; - struct xfs_inode *uip = NULL; - struct xfs_inode *gip = NULL; - struct xfs_inode *pip = NULL; - bool tempuqip = false; - bool tempgqip = false; - bool temppqip = false; - - memset(out, 0, sizeof(fs_quota_stat_t)); - - out->qs_version = FS_QSTAT_VERSION; - out->qs_flags = (__uint16_t) xfs_qm_export_flags(mp->m_qflags & - (XFS_ALL_QUOTA_ACCT| - XFS_ALL_QUOTA_ENFD)); - uip = q->qi_uquotaip; - gip = q->qi_gquotaip; - pip = q->qi_pquotaip; - if (!uip && mp->m_sb.sb_uquotino != NULLFSINO) { - if (xfs_iget(mp, NULL, mp->m_sb.sb_uquotino, - 0, 0, &uip) == 0) - tempuqip = true; - } - if (!gip && mp->m_sb.sb_gquotino != NULLFSINO) { - if (xfs_iget(mp, NULL, mp->m_sb.sb_gquotino, - 0, 0, &gip) == 0) - tempgqip = true; - } - /* - * Q_XGETQSTAT doesn't have room for both group and project quotas. - * So, allow the project quota values to be copied out only if - * there is no group quota information available. - */ - if (!gip) { - if (!pip && mp->m_sb.sb_pquotino != NULLFSINO) { - if (xfs_iget(mp, NULL, mp->m_sb.sb_pquotino, - 0, 0, &pip) == 0) - temppqip = true; - } - } else - pip = NULL; - if (uip) { - out->qs_uquota.qfs_ino = mp->m_sb.sb_uquotino; - out->qs_uquota.qfs_nblks = uip->i_d.di_nblocks; - out->qs_uquota.qfs_nextents = uip->i_d.di_nextents; - if (tempuqip) - IRELE(uip); - } - - if (gip) { - out->qs_gquota.qfs_ino = mp->m_sb.sb_gquotino; - out->qs_gquota.qfs_nblks = gip->i_d.di_nblocks; - out->qs_gquota.qfs_nextents = gip->i_d.di_nextents; - if (tempgqip) - IRELE(gip); - } - if (pip) { - out->qs_gquota.qfs_ino = mp->m_sb.sb_gquotino; - out->qs_gquota.qfs_nblks = pip->i_d.di_nblocks; - out->qs_gquota.qfs_nextents = pip->i_d.di_nextents; - if (temppqip) - IRELE(pip); - } - out->qs_incoredqs = q->qi_dquots; - out->qs_btimelimit = q->qi_btimelimit; - out->qs_itimelimit = q->qi_itimelimit; - out->qs_rtbtimelimit = q->qi_rtbtimelimit; - out->qs_bwarnlimit = q->qi_bwarnlimit; - out->qs_iwarnlimit = q->qi_iwarnlimit; - - return 0; -} - -/* - * Return quota status information, such as uquota-off, enforcements, etc. - * for Q_XGETQSTATV command, to support separate project quota field. - */ -int -xfs_qm_scall_getqstatv( - struct xfs_mount *mp, - struct fs_quota_statv *out) -{ - struct xfs_quotainfo *q = mp->m_quotainfo; - struct xfs_inode *uip = NULL; - struct xfs_inode *gip = NULL; - struct xfs_inode *pip = NULL; - bool tempuqip = false; - bool tempgqip = false; - bool temppqip = false; - - out->qs_flags = (__uint16_t) xfs_qm_export_flags(mp->m_qflags & - (XFS_ALL_QUOTA_ACCT| - XFS_ALL_QUOTA_ENFD)); - out->qs_uquota.qfs_ino = mp->m_sb.sb_uquotino; - out->qs_gquota.qfs_ino = mp->m_sb.sb_gquotino; - out->qs_pquota.qfs_ino = mp->m_sb.sb_pquotino; - - uip = q->qi_uquotaip; - gip = q->qi_gquotaip; - pip = q->qi_pquotaip; - if (!uip && mp->m_sb.sb_uquotino != NULLFSINO) { - if (xfs_iget(mp, NULL, mp->m_sb.sb_uquotino, - 0, 0, &uip) == 0) - tempuqip = true; - } - if (!gip && mp->m_sb.sb_gquotino != NULLFSINO) { - if (xfs_iget(mp, NULL, mp->m_sb.sb_gquotino, - 0, 0, &gip) == 0) - tempgqip = true; - } - if (!pip && mp->m_sb.sb_pquotino != NULLFSINO) { - if (xfs_iget(mp, NULL, mp->m_sb.sb_pquotino, - 0, 0, &pip) == 0) - temppqip = true; - } - if (uip) { - out->qs_uquota.qfs_nblks = uip->i_d.di_nblocks; - out->qs_uquota.qfs_nextents = uip->i_d.di_nextents; - if (tempuqip) - IRELE(uip); - } - - if (gip) { - out->qs_gquota.qfs_nblks = gip->i_d.di_nblocks; - out->qs_gquota.qfs_nextents = gip->i_d.di_nextents; - if (tempgqip) - IRELE(gip); - } - if (pip) { - out->qs_pquota.qfs_nblks = pip->i_d.di_nblocks; - out->qs_pquota.qfs_nextents = pip->i_d.di_nextents; - if (temppqip) - IRELE(pip); - } - out->qs_incoredqs = q->qi_dquots; - out->qs_btimelimit = q->qi_btimelimit; - out->qs_itimelimit = q->qi_itimelimit; - out->qs_rtbtimelimit = q->qi_rtbtimelimit; - out->qs_bwarnlimit = q->qi_bwarnlimit; - out->qs_iwarnlimit = q->qi_iwarnlimit; - - return 0; -} - #define XFS_QC_MASK \ (QC_LIMIT_MASK | QC_TIMER_MASK | QC_WARNS_MASK) @@ -873,28 +719,6 @@ out_put: return error; } -STATIC uint -xfs_qm_export_flags( - uint flags) -{ - uint uflags; - - uflags = 0; - if (flags & XFS_UQUOTA_ACCT) - uflags |= FS_QUOTA_UDQ_ACCT; - if (flags & XFS_GQUOTA_ACCT) - uflags |= FS_QUOTA_GDQ_ACCT; - if (flags & XFS_PQUOTA_ACCT) - uflags |= FS_QUOTA_PDQ_ACCT; - if (flags & XFS_UQUOTA_ENFD) - uflags |= FS_QUOTA_UDQ_ENFD; - if (flags & XFS_GQUOTA_ENFD) - uflags |= FS_QUOTA_GDQ_ENFD; - if (flags & XFS_PQUOTA_ENFD) - uflags |= FS_QUOTA_PDQ_ENFD; - return uflags; -} - STATIC int xfs_dqrele_inode( diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c index 6923905ab33d..7795e0d01382 100644 --- a/fs/xfs/xfs_quotaops.c +++ b/fs/xfs/xfs_quotaops.c @@ -23,10 +23,81 @@ #include "xfs_inode.h" #include "xfs_quota.h" #include "xfs_trans.h" +#include "xfs_trace.h" +#include "xfs_icache.h" #include "xfs_qm.h" #include <linux/quota.h> +static void +xfs_qm_fill_state( + struct qc_type_state *tstate, + struct xfs_mount *mp, + struct xfs_inode *ip, + xfs_ino_t ino) +{ + struct xfs_quotainfo *q = mp->m_quotainfo; + bool tempqip = false; + + tstate->ino = ino; + if (!ip && ino == NULLFSINO) + return; + if (!ip) { + if (xfs_iget(mp, NULL, ino, 0, 0, &ip)) + return; + tempqip = true; + } + tstate->flags |= QCI_SYSFILE; + tstate->blocks = ip->i_d.di_nblocks; + tstate->nextents = ip->i_d.di_nextents; + tstate->spc_timelimit = q->qi_btimelimit; + tstate->ino_timelimit = q->qi_itimelimit; + tstate->rt_spc_timelimit = q->qi_rtbtimelimit; + tstate->spc_warnlimit = q->qi_bwarnlimit; + tstate->ino_warnlimit = q->qi_iwarnlimit; + tstate->rt_spc_warnlimit = q->qi_rtbwarnlimit; + if (tempqip) + IRELE(ip); +} + +/* + * Return quota status information, such as enforcements, quota file inode + * numbers etc. + */ +static int +xfs_fs_get_quota_state( + struct super_block *sb, + struct qc_state *state) +{ + struct xfs_mount *mp = XFS_M(sb); + struct xfs_quotainfo *q = mp->m_quotainfo; + + memset(state, 0, sizeof(*state)); + if (!XFS_IS_QUOTA_RUNNING(mp)) + return 0; + state->s_incoredqs = q->qi_dquots; + if (XFS_IS_UQUOTA_RUNNING(mp)) + state->s_state[USRQUOTA].flags |= QCI_ACCT_ENABLED; + if (XFS_IS_UQUOTA_ENFORCED(mp)) + state->s_state[USRQUOTA].flags |= QCI_LIMITS_ENFORCED; + if (XFS_IS_GQUOTA_RUNNING(mp)) + state->s_state[GRPQUOTA].flags |= QCI_ACCT_ENABLED; + if (XFS_IS_GQUOTA_ENFORCED(mp)) + state->s_state[GRPQUOTA].flags |= QCI_LIMITS_ENFORCED; + if (XFS_IS_PQUOTA_RUNNING(mp)) + state->s_state[PRJQUOTA].flags |= QCI_ACCT_ENABLED; + if (XFS_IS_PQUOTA_ENFORCED(mp)) + state->s_state[PRJQUOTA].flags |= QCI_LIMITS_ENFORCED; + + xfs_qm_fill_state(&state->s_state[USRQUOTA], mp, q->qi_uquotaip, + mp->m_sb.sb_uquotino); + xfs_qm_fill_state(&state->s_state[GRPQUOTA], mp, q->qi_gquotaip, + mp->m_sb.sb_gquotino); + xfs_qm_fill_state(&state->s_state[PRJQUOTA], mp, q->qi_pquotaip, + mp->m_sb.sb_pquotino); + return 0; +} + STATIC int xfs_quota_type(int type) { @@ -40,28 +111,40 @@ xfs_quota_type(int type) } } -STATIC int -xfs_fs_get_xstate( +#define XFS_QC_SETINFO_MASK (QC_TIMER_MASK | QC_WARNS_MASK) + +/* + * Adjust quota timers & warnings + */ +static int +xfs_fs_set_info( struct super_block *sb, - struct fs_quota_stat *fqs) + int type, + struct qc_info *info) { - struct xfs_mount *mp = XFS_M(sb); + struct xfs_mount *mp = XFS_M(sb); + struct qc_dqblk newlim; + if (sb->s_flags & MS_RDONLY) + return -EROFS; if (!XFS_IS_QUOTA_RUNNING(mp)) return -ENOSYS; - return xfs_qm_scall_getqstat(mp, fqs); -} + if (!XFS_IS_QUOTA_ON(mp)) + return -ESRCH; + if (info->i_fieldmask & ~XFS_QC_SETINFO_MASK) + return -EINVAL; + if ((info->i_fieldmask & XFS_QC_SETINFO_MASK) == 0) + return 0; -STATIC int -xfs_fs_get_xstatev( - struct super_block *sb, - struct fs_quota_statv *fqs) -{ - struct xfs_mount *mp = XFS_M(sb); + newlim.d_fieldmask = info->i_fieldmask; + newlim.d_spc_timer = info->i_spc_timelimit; + newlim.d_ino_timer = info->i_ino_timelimit; + newlim.d_rt_spc_timer = info->i_rt_spc_timelimit; + newlim.d_ino_warns = info->i_ino_warnlimit; + newlim.d_spc_warns = info->i_spc_warnlimit; + newlim.d_rt_spc_warns = info->i_rt_spc_warnlimit; - if (!XFS_IS_QUOTA_RUNNING(mp)) - return -ENOSYS; - return xfs_qm_scall_getqstatv(mp, fqs); + return xfs_qm_scall_setqlim(mp, 0, xfs_quota_type(type), &newlim); } static unsigned int @@ -178,8 +261,8 @@ xfs_fs_set_dqblk( } const struct quotactl_ops xfs_quotactl_operations = { - .get_xstatev = xfs_fs_get_xstatev, - .get_xstate = xfs_fs_get_xstate, + .get_state = xfs_fs_get_quota_state, + .set_info = xfs_fs_set_info, .quota_enable = xfs_quota_enable, .quota_disable = xfs_quota_disable, .rm_xquota = xfs_fs_rm_xquota, diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 8fcc4ccc5c79..5f357ca97e76 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -109,8 +109,6 @@ static struct xfs_kobj xfs_dbg_kobj; /* global debug sysfs attrs */ #define MNTOPT_GQUOTANOENF "gqnoenforce"/* group quota limit enforcement */ #define MNTOPT_PQUOTANOENF "pqnoenforce"/* project quota limit enforcement */ #define MNTOPT_QUOTANOENF "qnoenforce" /* same as uqnoenforce */ -#define MNTOPT_DELAYLOG "delaylog" /* Delayed logging enabled */ -#define MNTOPT_NODELAYLOG "nodelaylog" /* Delayed logging disabled */ #define MNTOPT_DISCARD "discard" /* Discard unused blocks */ #define MNTOPT_NODISCARD "nodiscard" /* Do not discard unused blocks */ @@ -361,28 +359,10 @@ xfs_parseargs( } else if (!strcmp(this_char, MNTOPT_GQUOTANOENF)) { mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE); mp->m_qflags &= ~XFS_GQUOTA_ENFD; - } else if (!strcmp(this_char, MNTOPT_DELAYLOG)) { - xfs_warn(mp, - "delaylog is the default now, option is deprecated."); - } else if (!strcmp(this_char, MNTOPT_NODELAYLOG)) { - xfs_warn(mp, - "nodelaylog support has been removed, option is deprecated."); } else if (!strcmp(this_char, MNTOPT_DISCARD)) { mp->m_flags |= XFS_MOUNT_DISCARD; } else if (!strcmp(this_char, MNTOPT_NODISCARD)) { mp->m_flags &= ~XFS_MOUNT_DISCARD; - } else if (!strcmp(this_char, "ihashsize")) { - xfs_warn(mp, - "ihashsize no longer used, option is deprecated."); - } else if (!strcmp(this_char, "osyncisdsync")) { - xfs_warn(mp, - "osyncisdsync has no effect, option is deprecated."); - } else if (!strcmp(this_char, "osyncisosync")) { - xfs_warn(mp, - "osyncisosync has no effect, option is deprecated."); - } else if (!strcmp(this_char, "irixsgid")) { - xfs_warn(mp, - "irixsgid is now a sysctl(2) variable, option is deprecated."); } else { xfs_warn(mp, "unknown mount option [%s].", this_char); return -EINVAL; @@ -986,6 +966,8 @@ xfs_fs_inode_init_once( atomic_set(&ip->i_pincount, 0); spin_lock_init(&ip->i_flags_lock); + mrlock_init(&ip->i_mmaplock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER, + "xfsino", ip->i_ino); mrlock_init(&ip->i_lock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER, "xfsino", ip->i_ino); } @@ -1033,23 +1015,6 @@ xfs_free_fsname( kfree(mp->m_logname); } -STATIC void -xfs_fs_put_super( - struct super_block *sb) -{ - struct xfs_mount *mp = XFS_M(sb); - - xfs_filestream_unmount(mp); - xfs_unmountfs(mp); - - xfs_freesb(mp); - xfs_icsb_destroy_counters(mp); - xfs_destroy_mount_workqueues(mp); - xfs_close_devices(mp); - xfs_free_fsname(mp); - kfree(mp); -} - STATIC int xfs_fs_sync_fs( struct super_block *sb, @@ -1085,6 +1050,9 @@ xfs_fs_statfs( xfs_sb_t *sbp = &mp->m_sb; struct xfs_inode *ip = XFS_I(dentry->d_inode); __uint64_t fakeinos, id; + __uint64_t icount; + __uint64_t ifree; + __uint64_t fdblocks; xfs_extlen_t lsize; __int64_t ffree; @@ -1095,17 +1063,21 @@ xfs_fs_statfs( statp->f_fsid.val[0] = (u32)id; statp->f_fsid.val[1] = (u32)(id >> 32); - xfs_icsb_sync_counters(mp, XFS_ICSB_LAZY_COUNT); + icount = percpu_counter_sum(&mp->m_icount); + ifree = percpu_counter_sum(&mp->m_ifree); + fdblocks = percpu_counter_sum(&mp->m_fdblocks); spin_lock(&mp->m_sb_lock); statp->f_bsize = sbp->sb_blocksize; lsize = sbp->sb_logstart ? sbp->sb_logblocks : 0; statp->f_blocks = sbp->sb_dblocks - lsize; - statp->f_bfree = statp->f_bavail = - sbp->sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp); + spin_unlock(&mp->m_sb_lock); + + statp->f_bfree = fdblocks - XFS_ALLOC_SET_ASIDE(mp); + statp->f_bavail = statp->f_bfree; + fakeinos = statp->f_bfree << sbp->sb_inopblog; - statp->f_files = - MIN(sbp->sb_icount + fakeinos, (__uint64_t)XFS_MAXINUMBER); + statp->f_files = MIN(icount + fakeinos, (__uint64_t)XFS_MAXINUMBER); if (mp->m_maxicount) statp->f_files = min_t(typeof(statp->f_files), statp->f_files, @@ -1117,10 +1089,9 @@ xfs_fs_statfs( sbp->sb_icount); /* make sure statp->f_ffree does not underflow */ - ffree = statp->f_files - (sbp->sb_icount - sbp->sb_ifree); + ffree = statp->f_files - (icount - ifree); statp->f_ffree = max_t(__int64_t, ffree, 0); - spin_unlock(&mp->m_sb_lock); if ((ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) && ((mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))) == @@ -1256,6 +1227,12 @@ xfs_fs_remount( /* ro -> rw */ if ((mp->m_flags & XFS_MOUNT_RDONLY) && !(*flags & MS_RDONLY)) { + if (mp->m_flags & XFS_MOUNT_NORECOVERY) { + xfs_warn(mp, + "ro->rw transition prohibited on norecovery mount"); + return -EINVAL; + } + mp->m_flags &= ~XFS_MOUNT_RDONLY; /* @@ -1401,6 +1378,51 @@ xfs_finish_flags( return 0; } +static int +xfs_init_percpu_counters( + struct xfs_mount *mp) +{ + int error; + + error = percpu_counter_init(&mp->m_icount, 0, GFP_KERNEL); + if (error) + return -ENOMEM; + + error = percpu_counter_init(&mp->m_ifree, 0, GFP_KERNEL); + if (error) + goto free_icount; + + error = percpu_counter_init(&mp->m_fdblocks, 0, GFP_KERNEL); + if (error) + goto free_ifree; + + return 0; + +free_ifree: + percpu_counter_destroy(&mp->m_ifree); +free_icount: + percpu_counter_destroy(&mp->m_icount); + return -ENOMEM; +} + +void +xfs_reinit_percpu_counters( + struct xfs_mount *mp) +{ + percpu_counter_set(&mp->m_icount, mp->m_sb.sb_icount); + percpu_counter_set(&mp->m_ifree, mp->m_sb.sb_ifree); + percpu_counter_set(&mp->m_fdblocks, mp->m_sb.sb_fdblocks); +} + +static void +xfs_destroy_percpu_counters( + struct xfs_mount *mp) +{ + percpu_counter_destroy(&mp->m_icount); + percpu_counter_destroy(&mp->m_ifree); + percpu_counter_destroy(&mp->m_fdblocks); +} + STATIC int xfs_fs_fill_super( struct super_block *sb, @@ -1449,7 +1471,7 @@ xfs_fs_fill_super( if (error) goto out_close_devices; - error = xfs_icsb_init_counters(mp); + error = xfs_init_percpu_counters(mp); if (error) goto out_destroy_workqueues; @@ -1507,7 +1529,7 @@ xfs_fs_fill_super( out_free_sb: xfs_freesb(mp); out_destroy_counters: - xfs_icsb_destroy_counters(mp); + xfs_destroy_percpu_counters(mp); out_destroy_workqueues: xfs_destroy_mount_workqueues(mp); out_close_devices: @@ -1524,6 +1546,24 @@ out_destroy_workqueues: goto out_free_sb; } +STATIC void +xfs_fs_put_super( + struct super_block *sb) +{ + struct xfs_mount *mp = XFS_M(sb); + + xfs_notice(mp, "Unmounting Filesystem"); + xfs_filestream_unmount(mp); + xfs_unmountfs(mp); + + xfs_freesb(mp); + xfs_destroy_percpu_counters(mp); + xfs_destroy_mount_workqueues(mp); + xfs_close_devices(mp); + xfs_free_fsname(mp); + kfree(mp); +} + STATIC struct dentry * xfs_fs_mount( struct file_system_type *fs_type, diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h index 2b830c2f322e..499058fea303 100644 --- a/fs/xfs/xfs_super.h +++ b/fs/xfs/xfs_super.h @@ -72,6 +72,8 @@ extern const struct export_operations xfs_export_operations; extern const struct xattr_handler *xfs_xattr_handlers[]; extern const struct quotactl_ops xfs_quotactl_operations; +extern void xfs_reinit_percpu_counters(struct xfs_mount *mp); + #define XFS_M(sb) ((struct xfs_mount *)((sb)->s_fs_info)) #endif /* __XFS_SUPER_H__ */ diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index 25791df6f638..3df411eadb86 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -177,7 +177,7 @@ xfs_symlink( int pathlen; struct xfs_bmap_free free_list; xfs_fsblock_t first_block; - bool unlock_dp_on_error = false; + bool unlock_dp_on_error = false; uint cancel_flags; int committed; xfs_fileoff_t first_fsb; @@ -221,7 +221,7 @@ xfs_symlink( XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) - goto std_return; + return error; tp = xfs_trans_alloc(mp, XFS_TRANS_SYMLINK); cancel_flags = XFS_TRANS_RELEASE_LOG_RES; @@ -241,7 +241,7 @@ xfs_symlink( } if (error) { cancel_flags = 0; - goto error_return; + goto out_trans_cancel; } xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT); @@ -252,7 +252,7 @@ xfs_symlink( */ if (dp->i_d.di_flags & XFS_DIFLAG_NOSYMLINKS) { error = -EPERM; - goto error_return; + goto out_trans_cancel; } /* @@ -261,7 +261,7 @@ xfs_symlink( error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp, pdqp, resblks, 1, 0); if (error) - goto error_return; + goto out_trans_cancel; /* * Check for ability to enter directory entry, if no space reserved. @@ -269,7 +269,7 @@ xfs_symlink( if (!resblks) { error = xfs_dir_canenter(tp, dp, link_name); if (error) - goto error_return; + goto out_trans_cancel; } /* * Initialize the bmap freelist prior to calling either @@ -282,15 +282,14 @@ xfs_symlink( */ error = xfs_dir_ialloc(&tp, dp, S_IFLNK | (mode & ~S_IFMT), 1, 0, prid, resblks > 0, &ip, NULL); - if (error) { - if (error == -ENOSPC) - goto error_return; - goto error1; - } + if (error) + goto out_trans_cancel; /* - * An error after we've joined dp to the transaction will result in the - * transaction cancel unlocking dp so don't do it explicitly in the + * Now we join the directory inode to the transaction. We do not do it + * earlier because xfs_dir_ialloc might commit the previous transaction + * (and release all the locks). An error from here on will result in + * the transaction cancel unlocking dp so don't do it explicitly in the * error path. */ xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL); @@ -330,7 +329,7 @@ xfs_symlink( XFS_BMAPI_METADATA, &first_block, resblks, mval, &nmaps, &free_list); if (error) - goto error2; + goto out_bmap_cancel; if (resblks) resblks -= fs_blocks; @@ -348,7 +347,7 @@ xfs_symlink( BTOBB(byte_cnt), 0); if (!bp) { error = -ENOMEM; - goto error2; + goto out_bmap_cancel; } bp->b_ops = &xfs_symlink_buf_ops; @@ -378,7 +377,7 @@ xfs_symlink( error = xfs_dir_createname(tp, dp, link_name, ip->i_ino, &first_block, &free_list, resblks); if (error) - goto error2; + goto out_bmap_cancel; xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE); @@ -392,10 +391,13 @@ xfs_symlink( } error = xfs_bmap_finish(&tp, &free_list, &committed); - if (error) { - goto error2; - } + if (error) + goto out_bmap_cancel; + error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES); + if (error) + goto out_release_inode; + xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); xfs_qm_dqrele(pdqp); @@ -403,20 +405,28 @@ xfs_symlink( *ipp = ip; return 0; - error2: - IRELE(ip); - error1: +out_bmap_cancel: xfs_bmap_cancel(&free_list); cancel_flags |= XFS_TRANS_ABORT; - error_return: +out_trans_cancel: xfs_trans_cancel(tp, cancel_flags); +out_release_inode: + /* + * Wait until after the current transaction is aborted to finish the + * setup of the inode and release the inode. This prevents recursive + * transactions and deadlocks from xfs_inactive. + */ + if (ip) { + xfs_finish_inode_setup(ip); + IRELE(ip); + } + xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); xfs_qm_dqrele(pdqp); if (unlock_dp_on_error) xfs_iunlock(dp, XFS_ILOCK_EXCL); - std_return: return error; } diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 51372e34d988..615781bf4ee5 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -115,7 +115,7 @@ DECLARE_EVENT_CLASS(xfs_perag_class, __entry->refcount = refcount; __entry->caller_ip = caller_ip; ), - TP_printk("dev %d:%d agno %u refcount %d caller %pf", + TP_printk("dev %d:%d agno %u refcount %d caller %ps", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, __entry->refcount, @@ -239,7 +239,7 @@ TRACE_EVENT(xfs_iext_insert, __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d ino 0x%llx state %s idx %ld " - "offset %lld block %lld count %lld flag %d caller %pf", + "offset %lld block %lld count %lld flag %d caller %ps", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __print_flags(__entry->bmap_state, "|", XFS_BMAP_EXT_FLAGS), @@ -283,7 +283,7 @@ DECLARE_EVENT_CLASS(xfs_bmap_class, __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d ino 0x%llx state %s idx %ld " - "offset %lld block %lld count %lld flag %d caller %pf", + "offset %lld block %lld count %lld flag %d caller %ps", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __print_flags(__entry->bmap_state, "|", XFS_BMAP_EXT_FLAGS), @@ -329,7 +329,7 @@ DECLARE_EVENT_CLASS(xfs_buf_class, __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d bno 0x%llx nblks 0x%x hold %d pincount %d " - "lock %d flags %s caller %pf", + "lock %d flags %s caller %ps", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->bno, __entry->nblks, @@ -402,7 +402,7 @@ DECLARE_EVENT_CLASS(xfs_buf_flags_class, __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d bno 0x%llx len 0x%zx hold %d pincount %d " - "lock %d flags %s caller %pf", + "lock %d flags %s caller %ps", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->bno, __entry->buffer_length, @@ -447,7 +447,7 @@ TRACE_EVENT(xfs_buf_ioerror, __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d bno 0x%llx len 0x%zx hold %d pincount %d " - "lock %d error %d flags %s caller %pf", + "lock %d error %d flags %s caller %ps", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->bno, __entry->buffer_length, @@ -613,7 +613,7 @@ DECLARE_EVENT_CLASS(xfs_lock_class, __entry->lock_flags = lock_flags; __entry->caller_ip = caller_ip; ), - TP_printk("dev %d:%d ino 0x%llx flags %s caller %pf", + TP_printk("dev %d:%d ino 0x%llx flags %s caller %ps", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __print_flags(__entry->lock_flags, "|", XFS_LOCK_FLAGS), @@ -664,6 +664,7 @@ DEFINE_INODE_EVENT(xfs_alloc_file_space); DEFINE_INODE_EVENT(xfs_free_file_space); DEFINE_INODE_EVENT(xfs_zero_file_space); DEFINE_INODE_EVENT(xfs_collapse_file_space); +DEFINE_INODE_EVENT(xfs_insert_file_space); DEFINE_INODE_EVENT(xfs_readdir); #ifdef CONFIG_XFS_POSIX_ACL DEFINE_INODE_EVENT(xfs_get_acl); @@ -685,6 +686,9 @@ DEFINE_INODE_EVENT(xfs_inode_set_eofblocks_tag); DEFINE_INODE_EVENT(xfs_inode_clear_eofblocks_tag); DEFINE_INODE_EVENT(xfs_inode_free_eofblocks_invalid); +DEFINE_INODE_EVENT(xfs_filemap_fault); +DEFINE_INODE_EVENT(xfs_filemap_page_mkwrite); + DECLARE_EVENT_CLASS(xfs_iref_class, TP_PROTO(struct xfs_inode *ip, unsigned long caller_ip), TP_ARGS(ip, caller_ip), @@ -702,7 +706,7 @@ DECLARE_EVENT_CLASS(xfs_iref_class, __entry->pincount = atomic_read(&ip->i_pincount); __entry->caller_ip = caller_ip; ), - TP_printk("dev %d:%d ino 0x%llx count %d pincount %d caller %pf", + TP_printk("dev %d:%d ino 0x%llx count %d pincount %d caller %ps", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->count, @@ -1217,6 +1221,11 @@ DEFINE_IOMAP_EVENT(xfs_map_blocks_found); DEFINE_IOMAP_EVENT(xfs_map_blocks_alloc); DEFINE_IOMAP_EVENT(xfs_get_blocks_found); DEFINE_IOMAP_EVENT(xfs_get_blocks_alloc); +DEFINE_IOMAP_EVENT(xfs_gbmap_direct); +DEFINE_IOMAP_EVENT(xfs_gbmap_direct_new); +DEFINE_IOMAP_EVENT(xfs_gbmap_direct_update); +DEFINE_IOMAP_EVENT(xfs_gbmap_direct_none); +DEFINE_IOMAP_EVENT(xfs_gbmap_direct_endio); DECLARE_EVENT_CLASS(xfs_simple_io_class, TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count), @@ -1333,7 +1342,7 @@ TRACE_EVENT(xfs_bunmap, __entry->flags = flags; ), TP_printk("dev %d:%d ino 0x%llx size 0x%llx bno 0x%llx len 0x%llx" - "flags %s caller %pf", + "flags %s caller %ps", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->size, @@ -1466,7 +1475,7 @@ TRACE_EVENT(xfs_agf, ), TP_printk("dev %d:%d agno %u flags %s length %u roots b %u c %u " "levels b %u c %u flfirst %u fllast %u flcount %u " - "freeblks %u longest %u caller %pf", + "freeblks %u longest %u caller %ps", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, __print_flags(__entry->flags, "|", XFS_AGF_FLAGS), diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index eb90cd59a0ec..220ef2c906b2 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -173,7 +173,7 @@ xfs_trans_reserve( uint rtextents) { int error = 0; - int rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0; + bool rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0; /* Mark this thread as being in a transaction */ current_set_flags_nested(&tp->t_pflags, PF_FSTRANS); @@ -184,8 +184,7 @@ xfs_trans_reserve( * fail if the count would go below zero. */ if (blocks > 0) { - error = xfs_icsb_modify_counters(tp->t_mountp, XFS_SBS_FDBLOCKS, - -((int64_t)blocks), rsvd); + error = xfs_mod_fdblocks(tp->t_mountp, -((int64_t)blocks), rsvd); if (error != 0) { current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS); return -ENOSPC; @@ -236,8 +235,7 @@ xfs_trans_reserve( * fail if the count would go below zero. */ if (rtextents > 0) { - error = xfs_mod_incore_sb(tp->t_mountp, XFS_SBS_FREXTENTS, - -((int64_t)rtextents), rsvd); + error = xfs_mod_frextents(tp->t_mountp, -((int64_t)rtextents)); if (error) { error = -ENOSPC; goto undo_log; @@ -268,8 +266,7 @@ undo_log: undo_blocks: if (blocks > 0) { - xfs_icsb_modify_counters(tp->t_mountp, XFS_SBS_FDBLOCKS, - (int64_t)blocks, rsvd); + xfs_mod_fdblocks(tp->t_mountp, -((int64_t)blocks), rsvd); tp->t_blk_res = 0; } @@ -488,6 +485,54 @@ xfs_trans_apply_sb_deltas( sizeof(sbp->sb_frextents) - 1); } +STATIC int +xfs_sb_mod8( + uint8_t *field, + int8_t delta) +{ + int8_t counter = *field; + + counter += delta; + if (counter < 0) { + ASSERT(0); + return -EINVAL; + } + *field = counter; + return 0; +} + +STATIC int +xfs_sb_mod32( + uint32_t *field, + int32_t delta) +{ + int32_t counter = *field; + + counter += delta; + if (counter < 0) { + ASSERT(0); + return -EINVAL; + } + *field = counter; + return 0; +} + +STATIC int +xfs_sb_mod64( + uint64_t *field, + int64_t delta) +{ + int64_t counter = *field; + + counter += delta; + if (counter < 0) { + ASSERT(0); + return -EINVAL; + } + *field = counter; + return 0; +} + /* * xfs_trans_unreserve_and_mod_sb() is called to release unused reservations * and apply superblock counter changes to the in-core superblock. The @@ -495,13 +540,6 @@ xfs_trans_apply_sb_deltas( * applied to the in-core superblock. The idea is that that has already been * done. * - * This is done efficiently with a single call to xfs_mod_incore_sb_batch(). - * However, we have to ensure that we only modify each superblock field only - * once because the application of the delta values may not be atomic. That can - * lead to ENOSPC races occurring if we have two separate modifcations of the - * free space counter to put back the entire reservation and then take away - * what we used. - * * If we are not logging superblock counters, then the inode allocated/free and * used block counts are not updated in the on disk superblock. In this case, * XFS_TRANS_SB_DIRTY will not be set when the transaction is updated but we @@ -509,21 +547,15 @@ xfs_trans_apply_sb_deltas( */ void xfs_trans_unreserve_and_mod_sb( - xfs_trans_t *tp) + struct xfs_trans *tp) { - xfs_mod_sb_t msb[9]; /* If you add cases, add entries */ - xfs_mod_sb_t *msbp; - xfs_mount_t *mp = tp->t_mountp; - /* REFERENCED */ - int error; - int rsvd; - int64_t blkdelta = 0; - int64_t rtxdelta = 0; - int64_t idelta = 0; - int64_t ifreedelta = 0; - - msbp = msb; - rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0; + struct xfs_mount *mp = tp->t_mountp; + bool rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0; + int64_t blkdelta = 0; + int64_t rtxdelta = 0; + int64_t idelta = 0; + int64_t ifreedelta = 0; + int error; /* calculate deltas */ if (tp->t_blk_res > 0) @@ -547,97 +579,115 @@ xfs_trans_unreserve_and_mod_sb( /* apply the per-cpu counters */ if (blkdelta) { - error = xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS, - blkdelta, rsvd); + error = xfs_mod_fdblocks(mp, blkdelta, rsvd); if (error) goto out; } if (idelta) { - error = xfs_icsb_modify_counters(mp, XFS_SBS_ICOUNT, - idelta, rsvd); + error = xfs_mod_icount(mp, idelta); if (error) goto out_undo_fdblocks; } if (ifreedelta) { - error = xfs_icsb_modify_counters(mp, XFS_SBS_IFREE, - ifreedelta, rsvd); + error = xfs_mod_ifree(mp, ifreedelta); if (error) goto out_undo_icount; } + if (rtxdelta == 0 && !(tp->t_flags & XFS_TRANS_SB_DIRTY)) + return; + /* apply remaining deltas */ - if (rtxdelta != 0) { - msbp->msb_field = XFS_SBS_FREXTENTS; - msbp->msb_delta = rtxdelta; - msbp++; + spin_lock(&mp->m_sb_lock); + if (rtxdelta) { + error = xfs_sb_mod64(&mp->m_sb.sb_frextents, rtxdelta); + if (error) + goto out_undo_ifree; } - if (tp->t_flags & XFS_TRANS_SB_DIRTY) { - if (tp->t_dblocks_delta != 0) { - msbp->msb_field = XFS_SBS_DBLOCKS; - msbp->msb_delta = tp->t_dblocks_delta; - msbp++; - } - if (tp->t_agcount_delta != 0) { - msbp->msb_field = XFS_SBS_AGCOUNT; - msbp->msb_delta = tp->t_agcount_delta; - msbp++; - } - if (tp->t_imaxpct_delta != 0) { - msbp->msb_field = XFS_SBS_IMAX_PCT; - msbp->msb_delta = tp->t_imaxpct_delta; - msbp++; - } - if (tp->t_rextsize_delta != 0) { - msbp->msb_field = XFS_SBS_REXTSIZE; - msbp->msb_delta = tp->t_rextsize_delta; - msbp++; - } - if (tp->t_rbmblocks_delta != 0) { - msbp->msb_field = XFS_SBS_RBMBLOCKS; - msbp->msb_delta = tp->t_rbmblocks_delta; - msbp++; - } - if (tp->t_rblocks_delta != 0) { - msbp->msb_field = XFS_SBS_RBLOCKS; - msbp->msb_delta = tp->t_rblocks_delta; - msbp++; - } - if (tp->t_rextents_delta != 0) { - msbp->msb_field = XFS_SBS_REXTENTS; - msbp->msb_delta = tp->t_rextents_delta; - msbp++; - } - if (tp->t_rextslog_delta != 0) { - msbp->msb_field = XFS_SBS_REXTSLOG; - msbp->msb_delta = tp->t_rextslog_delta; - msbp++; - } + if (tp->t_dblocks_delta != 0) { + error = xfs_sb_mod64(&mp->m_sb.sb_dblocks, tp->t_dblocks_delta); + if (error) + goto out_undo_frextents; } - - /* - * If we need to change anything, do it. - */ - if (msbp > msb) { - error = xfs_mod_incore_sb_batch(tp->t_mountp, msb, - (uint)(msbp - msb), rsvd); + if (tp->t_agcount_delta != 0) { + error = xfs_sb_mod32(&mp->m_sb.sb_agcount, tp->t_agcount_delta); if (error) - goto out_undo_ifreecount; + goto out_undo_dblocks; } - + if (tp->t_imaxpct_delta != 0) { + error = xfs_sb_mod8(&mp->m_sb.sb_imax_pct, tp->t_imaxpct_delta); + if (error) + goto out_undo_agcount; + } + if (tp->t_rextsize_delta != 0) { + error = xfs_sb_mod32(&mp->m_sb.sb_rextsize, + tp->t_rextsize_delta); + if (error) + goto out_undo_imaxpct; + } + if (tp->t_rbmblocks_delta != 0) { + error = xfs_sb_mod32(&mp->m_sb.sb_rbmblocks, + tp->t_rbmblocks_delta); + if (error) + goto out_undo_rextsize; + } + if (tp->t_rblocks_delta != 0) { + error = xfs_sb_mod64(&mp->m_sb.sb_rblocks, tp->t_rblocks_delta); + if (error) + goto out_undo_rbmblocks; + } + if (tp->t_rextents_delta != 0) { + error = xfs_sb_mod64(&mp->m_sb.sb_rextents, + tp->t_rextents_delta); + if (error) + goto out_undo_rblocks; + } + if (tp->t_rextslog_delta != 0) { + error = xfs_sb_mod8(&mp->m_sb.sb_rextslog, + tp->t_rextslog_delta); + if (error) + goto out_undo_rextents; + } + spin_unlock(&mp->m_sb_lock); return; -out_undo_ifreecount: +out_undo_rextents: + if (tp->t_rextents_delta) + xfs_sb_mod64(&mp->m_sb.sb_rextents, -tp->t_rextents_delta); +out_undo_rblocks: + if (tp->t_rblocks_delta) + xfs_sb_mod64(&mp->m_sb.sb_rblocks, -tp->t_rblocks_delta); +out_undo_rbmblocks: + if (tp->t_rbmblocks_delta) + xfs_sb_mod32(&mp->m_sb.sb_rbmblocks, -tp->t_rbmblocks_delta); +out_undo_rextsize: + if (tp->t_rextsize_delta) + xfs_sb_mod32(&mp->m_sb.sb_rextsize, -tp->t_rextsize_delta); +out_undo_imaxpct: + if (tp->t_rextsize_delta) + xfs_sb_mod8(&mp->m_sb.sb_imax_pct, -tp->t_imaxpct_delta); +out_undo_agcount: + if (tp->t_agcount_delta) + xfs_sb_mod32(&mp->m_sb.sb_agcount, -tp->t_agcount_delta); +out_undo_dblocks: + if (tp->t_dblocks_delta) + xfs_sb_mod64(&mp->m_sb.sb_dblocks, -tp->t_dblocks_delta); +out_undo_frextents: + if (rtxdelta) + xfs_sb_mod64(&mp->m_sb.sb_frextents, -rtxdelta); +out_undo_ifree: + spin_unlock(&mp->m_sb_lock); if (ifreedelta) - xfs_icsb_modify_counters(mp, XFS_SBS_IFREE, -ifreedelta, rsvd); + xfs_mod_ifree(mp, -ifreedelta); out_undo_icount: if (idelta) - xfs_icsb_modify_counters(mp, XFS_SBS_ICOUNT, -idelta, rsvd); + xfs_mod_icount(mp, -idelta); out_undo_fdblocks: if (blkdelta) - xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS, -blkdelta, rsvd); + xfs_mod_fdblocks(mp, -blkdelta, rsvd); out: ASSERT(error == 0); return; |