diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 812154aff981..b266f734bd53 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1404,7 +1404,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, /* Expect a negative dentry */ BUG_ON(dentry->d_inode); - dfprintk(VFS, "NFS: atomic_open(%s/%ld), %pd\n", + dfprintk(VFS, "NFS: atomic_open(%s/%lu), %pd\n", dir->i_sb->s_id, dir->i_ino, dentry); err = nfs_check_flags(open_flags); @@ -1594,7 +1594,7 @@ int nfs_create(struct inode *dir, struct dentry *dentry, int open_flags = excl ? O_CREAT | O_EXCL : O_CREAT; int error; - dfprintk(VFS, "NFS: create(%s/%ld), %pd\n", + dfprintk(VFS, "NFS: create(%s/%lu), %pd\n", dir->i_sb->s_id, dir->i_ino, dentry); attr.ia_mode = mode; @@ -1621,7 +1621,7 @@ nfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) struct iattr attr; int status; - dfprintk(VFS, "NFS: mknod(%s/%ld), %pd\n", + dfprintk(VFS, "NFS: mknod(%s/%lu), %pd\n", dir->i_sb->s_id, dir->i_ino, dentry); if (!new_valid_dev(rdev)) @@ -1650,7 +1650,7 @@ int nfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) struct iattr attr; int error; - dfprintk(VFS, "NFS: mkdir(%s/%ld), %pd\n", + dfprintk(VFS, "NFS: mkdir(%s/%lu), %pd\n", dir->i_sb->s_id, dir->i_ino, dentry); attr.ia_valid = ATTR_MODE; @@ -1678,7 +1678,7 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry) { int error; - dfprintk(VFS, "NFS: rmdir(%s/%ld), %pd\n", + dfprintk(VFS, "NFS: rmdir(%s/%lu), %pd\n", dir->i_sb->s_id, dir->i_ino, dentry); trace_nfs_rmdir_enter(dir, dentry); @@ -1747,7 +1747,7 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry) int error; int need_rehash = 0; - dfprintk(VFS, "NFS: unlink(%s/%ld, %pd)\n", dir->i_sb->s_id, + dfprintk(VFS, "NFS: unlink(%s/%lu, %pd)\n", dir->i_sb->s_id, dir->i_ino, dentry); trace_nfs_unlink_enter(dir, dentry); @@ -1798,7 +1798,7 @@ int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) unsigned int pathlen = strlen(symname); int error; - dfprintk(VFS, "NFS: symlink(%s/%ld, %pd, %s)\n", dir->i_sb->s_id, + dfprintk(VFS, "NFS: symlink(%s/%lu, %pd, %s)\n", dir->i_sb->s_id, dir->i_ino, dentry, symname); if (pathlen > PAGE_SIZE) @@ -1821,7 +1821,7 @@ int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) error = NFS_PROTO(dir)->symlink(dir, dentry, page, pathlen, &attr); trace_nfs_symlink_exit(dir, dentry, error); if (error != 0) { - dfprintk(VFS, "NFS: symlink(%s/%ld, %pd, %s) error %d\n", + dfprintk(VFS, "NFS: symlink(%s/%lu, %pd, %s) error %d\n", dir->i_sb->s_id, dir->i_ino, dentry, symname, error); d_drop(dentry); @@ -2304,7 +2304,7 @@ int nfs_permission(struct inode *inode, int mask) if (!res && (mask & MAY_EXEC) && !execute_ok(inode)) res = -EACCES; - dfprintk(VFS, "NFS: permission(%s/%ld), mask=0x%x, res=%d\n", + dfprintk(VFS, "NFS: permission(%s/%lu), mask=0x%x, res=%d\n", inode->i_sb->s_id, inode->i_ino, mask, res); return res; out_notsup: diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index d71d66c9e0a1..b8797ae6831f 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -222,14 +222,31 @@ static ssize_t nfs_direct_wait(struct nfs_direct_req *dreq) * Synchronous I/O uses a stack-allocated iocb. Thus we can't trust * the iocb is still valid here if this is a synchronous request. */ -static void nfs_direct_complete(struct nfs_direct_req *dreq) +static void nfs_direct_complete(struct nfs_direct_req *dreq, bool write) { + struct inode *inode = dreq->inode; + + if (dreq->iocb && write) { + loff_t pos = dreq->iocb->ki_pos + dreq->count; + + spin_lock(&inode->i_lock); + if (i_size_read(inode) < pos) + i_size_write(inode, pos); + spin_unlock(&inode->i_lock); + } + + if (write) + nfs_zap_mapping(inode, inode->i_mapping); + + inode_dio_done(inode); + if (dreq->iocb) { long res = (long) dreq->error; if (!res) res = (long) dreq->count; aio_complete(dreq->iocb, res, 0); } + complete_all(&dreq->completion); nfs_direct_req_release(dreq); @@ -237,9 +254,9 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq) static void nfs_direct_readpage_release(struct nfs_page *req) { - dprintk("NFS: direct read done (%s/%lld %d@%lld)\n", + dprintk("NFS: direct read done (%s/%llu %d@%lld)\n", req->wb_context->dentry->d_inode->i_sb->s_id, - (long long)NFS_FILEID(req->wb_context->dentry->d_inode), + (unsigned long long)NFS_FILEID(req->wb_context->dentry->d_inode), req->wb_bytes, (long long)req_offset(req)); nfs_release_request(req); @@ -272,7 +289,7 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr) } out_put: if (put_dreq(dreq)) - nfs_direct_complete(dreq); + nfs_direct_complete(dreq, false); hdr->release(hdr); } @@ -402,6 +419,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, loff_t pos, bool uio) { struct nfs_pageio_descriptor desc; + struct inode *inode = dreq->inode; ssize_t result = -EINVAL; size_t requested_bytes = 0; unsigned long seg; @@ -410,6 +428,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, &nfs_direct_read_completion_ops); get_dreq(dreq); desc.pg_dreq = dreq; + atomic_inc(&inode->i_dio_count); for (seg = 0; seg < nr_segs; seg++) { const struct iovec *vec = &iov[seg]; @@ -429,26 +448,69 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, * generic layer handle the completion. */ if (requested_bytes == 0) { + inode_dio_done(inode); nfs_direct_req_release(dreq); return result < 0 ? result : -EIO; } if (put_dreq(dreq)) - nfs_direct_complete(dreq); + nfs_direct_complete(dreq, false); return 0; } -static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos, bool uio) +/** + * nfs_file_direct_read - file direct read operation for NFS files + * @iocb: target I/O control block + * @iov: vector of user buffers into which to read data + * @nr_segs: size of iov vector + * @pos: byte offset in file where reading starts + * + * We use this function for direct reads instead of calling + * generic_file_aio_read() in order to avoid gfar's check to see if + * the request starts before the end of the file. For that check + * to work, we must generate a GETATTR before each direct read, and + * even then there is a window between the GETATTR and the subsequent + * READ where the file size could change. Our preference is simply + * to do all reads the application wants, and the server will take + * care of managing the end of file boundary. + * + * This function also eliminates unnecessarily updating the file's + * atime locally, as the NFS server sets the file's atime, and this + * client must read the updated atime from the server back into its + * cache. + */ +ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos, bool uio) { - ssize_t result = -ENOMEM; - struct inode *inode = iocb->ki_filp->f_mapping->host; + struct file *file = iocb->ki_filp; + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; struct nfs_direct_req *dreq; struct nfs_lock_context *l_ctx; + ssize_t result = -EINVAL; + size_t count; + count = iov_length(iov, nr_segs); + nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count); + + dfprintk(FILE, "NFS: direct read(%pD2, %zd@%Ld)\n", + file, count, (long long) pos); + + result = 0; + if (!count) + goto out; + + mutex_lock(&inode->i_mutex); + result = nfs_sync_mapping(mapping); + if (result) + goto out_unlock; + + task_io_account_read(count); + + result = -ENOMEM; dreq = nfs_direct_req_alloc(); if (dreq == NULL) - goto out; + goto out_unlock; dreq->inode = inode; dreq->bytes_left = iov_length(iov, nr_segs); @@ -464,20 +526,26 @@ static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov, NFS_I(inode)->read_io += iov_length(iov, nr_segs); result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos, uio); - if (!result) + + mutex_unlock(&inode->i_mutex); + + if (!result) { result = nfs_direct_wait(dreq); + if (result > 0) + iocb->ki_pos = pos + result; + } + + nfs_direct_req_release(dreq); + return result; + out_release: nfs_direct_req_release(dreq); +out_unlock: + mutex_unlock(&inode->i_mutex); out: return result; } -static void nfs_inode_dio_write_done(struct inode *inode) -{ - nfs_zap_mapping(inode, inode->i_mapping); - inode_dio_done(inode); -} - #if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4) static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) { @@ -593,8 +661,7 @@ static void nfs_direct_write_schedule_work(struct work_struct *work) nfs_direct_write_reschedule(dreq); break; default: - nfs_inode_dio_write_done(dreq->inode); - nfs_direct_complete(dreq); + nfs_direct_complete(dreq, true); } } @@ -610,8 +677,7 @@ static void nfs_direct_write_schedule_work(struct work_struct *work) static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode) { - nfs_inode_dio_write_done(inode); - nfs_direct_complete(dreq); + nfs_direct_complete(dreq, true); } #endif @@ -842,93 +908,6 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, return 0; } -static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos, - size_t count, bool uio) -{ - ssize_t result = -ENOMEM; - struct inode *inode = iocb->ki_filp->f_mapping->host; - struct nfs_direct_req *dreq; - struct nfs_lock_context *l_ctx; - - dreq = nfs_direct_req_alloc(); - if (!dreq) - goto out; - - dreq->inode = inode; - dreq->bytes_left = count; - dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp)); - l_ctx = nfs_get_lock_context(dreq->ctx); - if (IS_ERR(l_ctx)) { - result = PTR_ERR(l_ctx); - goto out_release; - } - dreq->l_ctx = l_ctx; - if (!is_sync_kiocb(iocb)) - dreq->iocb = iocb; - - result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, uio); - if (!result) - result = nfs_direct_wait(dreq); -out_release: - nfs_direct_req_release(dreq); -out: - return result; -} - -/** - * nfs_file_direct_read - file direct read operation for NFS files - * @iocb: target I/O control block - * @iov: vector of user buffers into which to read data - * @nr_segs: size of iov vector - * @pos: byte offset in file where reading starts - * - * We use this function for direct reads instead of calling - * generic_file_aio_read() in order to avoid gfar's check to see if - * the request starts before the end of the file. For that check - * to work, we must generate a GETATTR before each direct read, and - * even then there is a window between the GETATTR and the subsequent - * READ where the file size could change. Our preference is simply - * to do all reads the application wants, and the server will take - * care of managing the end of file boundary. - * - * This function also eliminates unnecessarily updating the file's - * atime locally, as the NFS server sets the file's atime, and this - * client must read the updated atime from the server back into its - * cache. - */ -ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos, bool uio) -{ - ssize_t retval = -EINVAL; - struct file *file = iocb->ki_filp; - struct address_space *mapping = file->f_mapping; - size_t count; - - count = iov_length(iov, nr_segs); - nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count); - - dfprintk(FILE, "NFS: direct read(%pD2, %zd@%Ld)\n", - file, count, (long long) pos); - - retval = 0; - if (!count) - goto out; - - retval = nfs_sync_mapping(mapping); - if (retval) - goto out; - - task_io_account_read(count); - - retval = nfs_direct_read(iocb, iov, nr_segs, pos, uio); - if (retval > 0) - iocb->ki_pos = pos + retval; - -out: - return retval; -} - /** * nfs_file_direct_write - file direct write operation for NFS files * @iocb: target I/O control block @@ -954,46 +933,96 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov, ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos, bool uio) { - ssize_t retval = -EINVAL; + ssize_t result = -EINVAL; struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + struct nfs_direct_req *dreq; + struct nfs_lock_context *l_ctx; + loff_t end; size_t count; count = iov_length(iov, nr_segs); + end = (pos + count - 1) >> PAGE_CACHE_SHIFT; + nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES, count); dfprintk(FILE, "NFS: direct write(%pD2, %zd@%Ld)\n", file, count, (long long) pos); - retval = generic_write_checks(file, &pos, &count, 0); - if (retval) + result = generic_write_checks(file, &pos, &count, 0); + if (result) goto out; - retval = -EINVAL; + result = -EINVAL; if ((ssize_t) count < 0) goto out; - retval = 0; + result = 0; if (!count) goto out; - retval = nfs_sync_mapping(mapping); - if (retval) - goto out; + mutex_lock(&inode->i_mutex); + + result = nfs_sync_mapping(mapping); + if (result) + goto out_unlock; + + if (mapping->nrpages) { + result = invalidate_inode_pages2_range(mapping, + pos >> PAGE_CACHE_SHIFT, end); + if (result) + goto out_unlock; + } task_io_account_write(count); - retval = nfs_direct_write(iocb, iov, nr_segs, pos, count, uio); - if (retval > 0) { - struct inode *inode = mapping->host; + result = -ENOMEM; + dreq = nfs_direct_req_alloc(); + if (!dreq) + goto out_unlock; - iocb->ki_pos = pos + retval; - spin_lock(&inode->i_lock); - if (i_size_read(inode) < iocb->ki_pos) - i_size_write(inode, iocb->ki_pos); - spin_unlock(&inode->i_lock); + dreq->inode = inode; + dreq->bytes_left = count; + dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp)); + l_ctx = nfs_get_lock_context(dreq->ctx); + if (IS_ERR(l_ctx)) { + result = PTR_ERR(l_ctx); + goto out_release; } + dreq->l_ctx = l_ctx; + if (!is_sync_kiocb(iocb)) + dreq->iocb = iocb; + + result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, uio); + + if (mapping->nrpages) { + invalidate_inode_pages2_range(mapping, + pos >> PAGE_CACHE_SHIFT, end); + } + + mutex_unlock(&inode->i_mutex); + + if (!result) { + result = nfs_direct_wait(dreq); + if (result > 0) { + struct inode *inode = mapping->host; + + iocb->ki_pos = pos + result; + spin_lock(&inode->i_lock); + if (i_size_read(inode) < iocb->ki_pos) + i_size_write(inode, iocb->ki_pos); + spin_unlock(&inode->i_lock); + } + } + nfs_direct_req_release(dreq); + return result; + +out_release: + nfs_direct_req_release(dreq); +out_unlock: + mutex_unlock(&inode->i_mutex); out: - return retval; + return result; } /** diff --git a/fs/nfs/file.c b/fs/nfs/file.c index e2fcacf07de3..5bb790a69c71 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -354,7 +354,7 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping, struct page *page; int once_thru = 0; - dfprintk(PAGECACHE, "NFS: write_begin(%pD2(%ld), %u@%lld)\n", + dfprintk(PAGECACHE, "NFS: write_begin(%pD2(%lu), %u@%lld)\n", file, mapping->host->i_ino, len, (long long) pos); start: @@ -395,7 +395,7 @@ static int nfs_write_end(struct file *file, struct address_space *mapping, struct nfs_open_context *ctx = nfs_file_open_context(file); int status; - dfprintk(PAGECACHE, "NFS: write_end(%pD2(%ld), %u@%lld)\n", + dfprintk(PAGECACHE, "NFS: write_end(%pD2(%lu), %u@%lld)\n", file, mapping->host->i_ino, len, (long long) pos); /* @@ -585,7 +585,7 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) int ret = VM_FAULT_NOPAGE; struct address_space *mapping; - dfprintk(PAGECACHE, "NFS: vm_page_mkwrite(%pD2(%ld), offset %lld)\n", + dfprintk(PAGECACHE, "NFS: vm_page_mkwrite(%pD2(%lu), offset %lld)\n", filp, filp->f_mapping->host->i_ino, (long long)page_offset(page)); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index ecd11ba7f960..ea00b34ff071 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -458,9 +458,9 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st unlock_new_inode(inode); } else nfs_refresh_inode(inode, fattr); - dprintk("NFS: nfs_fhget(%s/%Ld fh_crc=0x%08x ct=%d)\n", + dprintk("NFS: nfs_fhget(%s/%Lu fh_crc=0x%08x ct=%d)\n", inode->i_sb->s_id, - (long long)NFS_FILEID(inode), + (unsigned long long)NFS_FILEID(inode), nfs_display_fhandle_hash(fh), atomic_read(&inode->i_count)); @@ -870,8 +870,8 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) struct nfs_fattr *fattr = NULL; struct nfs_inode *nfsi = NFS_I(inode); - dfprintk(PAGECACHE, "NFS: revalidating (%s/%Ld)\n", - inode->i_sb->s_id, (long long)NFS_FILEID(inode)); + dfprintk(PAGECACHE, "NFS: revalidating (%s/%Lu)\n", + inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode)); trace_nfs_revalidate_inode_enter(inode); @@ -895,9 +895,9 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), fattr, label); if (status != 0) { - dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Ld) getattr failed, error=%d\n", + dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) getattr failed, error=%d\n", inode->i_sb->s_id, - (long long)NFS_FILEID(inode), status); + (unsigned long long)NFS_FILEID(inode), status); if (status == -ESTALE) { nfs_zap_caches(inode); if (!S_ISDIR(inode->i_mode)) @@ -908,9 +908,9 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) status = nfs_refresh_inode(inode, fattr); if (status) { - dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Ld) refresh failed, error=%d\n", + dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) refresh failed, error=%d\n", inode->i_sb->s_id, - (long long)NFS_FILEID(inode), status); + (unsigned long long)NFS_FILEID(inode), status); goto err_out; } @@ -919,9 +919,9 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) nfs_setsecurity(inode, fattr, label); - dfprintk(PAGECACHE, "NFS: (%s/%Ld) revalidation complete\n", + dfprintk(PAGECACHE, "NFS: (%s/%Lu) revalidation complete\n", inode->i_sb->s_id, - (long long)NFS_FILEID(inode)); + (unsigned long long)NFS_FILEID(inode)); err_out: nfs4_label_free(label); @@ -985,8 +985,9 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE); nfs_fscache_wait_on_invalidate(inode); - dfprintk(PAGECACHE, "NFS: (%s/%Ld) data cache invalidated\n", - inode->i_sb->s_id, (long long)NFS_FILEID(inode)); + dfprintk(PAGECACHE, "NFS: (%s/%Lu) data cache invalidated\n", + inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(inode)); return 0; } @@ -1282,12 +1283,28 @@ static int nfs_inode_attrs_need_update(const struct inode *inode, const struct n ((long)nfsi->attr_gencount - (long)nfs_read_attr_generation_counter() > 0); } +/* + * Don't trust the change_attribute, mtime, ctime or size if + * a pnfs LAYOUTCOMMIT is outstanding + */ +static void nfs_inode_attrs_handle_layoutcommit(struct inode *inode, + struct nfs_fattr *fattr) +{ + if (pnfs_layoutcommit_outstanding(inode)) + fattr->valid &= ~(NFS_ATTR_FATTR_CHANGE | + NFS_ATTR_FATTR_MTIME | + NFS_ATTR_FATTR_CTIME | + NFS_ATTR_FATTR_SIZE); +} + static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr) { int ret; trace_nfs_refresh_inode_enter(inode); + nfs_inode_attrs_handle_layoutcommit(inode, fattr); + if (nfs_inode_attrs_need_update(inode, fattr)) ret = nfs_update_inode(inode, fattr); else @@ -1434,7 +1451,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) unsigned long now = jiffies; unsigned long save_cache_validity; - dfprintk(VFS, "NFS: %s(%s/%ld fh_crc=0x%08x ct=%d info=0x%x)\n", + dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n", __func__, inode->i_sb->s_id, inode->i_ino, nfs_display_fhandle_hash(NFS_FH(inode)), atomic_read(&inode->i_count), fattr->valid); @@ -1455,7 +1472,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) /* * Big trouble! The inode has become a different object. */ - printk(KERN_DEBUG "NFS: %s: inode %ld mode changed, %07o to %07o\n", + printk(KERN_DEBUG "NFS: %s: inode %lu mode changed, %07o to %07o\n", __func__, inode->i_ino, inode->i_mode, fattr->mode); goto out_err; } @@ -1517,8 +1534,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) if (new_isize != cur_isize) { /* Do we perhaps have any outstanding writes, or has * the file grown beyond our last write? */ - if ((nfsi->npages == 0 && !test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) || - new_isize > cur_isize) { + if ((nfsi->npages == 0) || new_isize > cur_isize) { i_size_write(inode, new_isize); invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA; } diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index b4a160a405ce..73d4ecda1e36 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "internal.h" #include "callback.h" #include "delegation.h" @@ -370,7 +371,11 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp, __set_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags); __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); __set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags); - error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_GSS_KRB5I); + + error = -EINVAL; + if (gssd_running(clp->cl_net)) + error = nfs_create_rpc_client(clp, timeparms, + RPC_AUTH_GSS_KRB5I); if (error == -EINVAL) error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX); if (error < 0) @@ -409,13 +414,11 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp, error = nfs4_discover_server_trunking(clp, &old); if (error < 0) goto error; - nfs_put_client(clp); - if (clp != old) { - clp->cl_preserve_clid = true; - clp = old; - } - return clp; + if (clp != old) + clp->cl_preserve_clid = true; + nfs_put_client(clp); + return old; error: nfs_mark_client_ready(clp, error); @@ -493,9 +496,10 @@ int nfs40_walk_client_list(struct nfs_client *new, prev = pos; status = nfs_wait_client_init_complete(pos); - spin_lock(&nn->nfs_client_lock); if (status < 0) - continue; + goto out; + status = -NFS4ERR_STALE_CLIENTID; + spin_lock(&nn->nfs_client_lock); } if (pos->cl_cons_state != NFS_CS_READY) continue; @@ -633,7 +637,8 @@ int nfs41_walk_client_list(struct nfs_client *new, } spin_lock(&nn->nfs_client_lock); if (status < 0) - continue; + break; + status = -NFS4ERR_STALE_CLIENTID; } if (pos->cl_cons_state != NFS_CS_READY) continue; diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index b86464ba25e1..03fd8be8c0c5 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -91,10 +91,10 @@ static void filelayout_reset_write(struct nfs_write_data *data) if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { dprintk("%s Reset task %5u for i/o through MDS " - "(req %s/%lld, %u bytes @ offset %llu)\n", __func__, + "(req %s/%llu, %u bytes @ offset %llu)\n", __func__, data->task.tk_pid, hdr->inode->i_sb->s_id, - (long long)NFS_FILEID(hdr->inode), + (unsigned long long)NFS_FILEID(hdr->inode), data->args.count, (unsigned long long)data->args.offset); @@ -112,10 +112,10 @@ static void filelayout_reset_read(struct nfs_read_data *data) if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { dprintk("%s Reset task %5u for i/o through MDS " - "(req %s/%lld, %u bytes @ offset %llu)\n", __func__, + "(req %s/%llu, %u bytes @ offset %llu)\n", __func__, data->task.tk_pid, hdr->inode->i_sb->s_id, - (long long)NFS_FILEID(hdr->inode), + (unsigned long long)NFS_FILEID(hdr->inode), data->args.count, (unsigned long long)data->args.offset); @@ -1216,17 +1216,17 @@ static void filelayout_recover_commit_reqs(struct list_head *dst, struct pnfs_commit_bucket *b; int i; - /* NOTE cinfo->lock is NOT held, relying on fact that this is - * only called on single thread per dreq. - * Can't take the lock because need to do pnfs_put_lseg - */ + spin_lock(cinfo->lock); for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) { if (transfer_commit_list(&b->written, dst, cinfo, 0)) { + spin_unlock(cinfo->lock); pnfs_put_lseg(b->wlseg); b->wlseg = NULL; + spin_lock(cinfo->lock); } } cinfo->ds->nwritten = 0; + spin_unlock(cinfo->lock); } static unsigned int diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c index c7c295e556ed..efac602edb37 100644 --- a/fs/nfs/nfs4filelayoutdev.c +++ b/fs/nfs/nfs4filelayoutdev.c @@ -95,7 +95,7 @@ same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2) b6 = (struct sockaddr_in6 *)addr2; /* LINKLOCAL addresses must have matching scope_id */ - if (ipv6_addr_scope(&a6->sin6_addr) == + if (ipv6_addr_src_scope(&a6->sin6_addr) == IPV6_ADDR_SCOPE_LINKLOCAL && a6->sin6_scope_id != b6->sin6_scope_id) return false; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 15052b81df42..a1965329a12c 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7409,9 +7409,9 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata) struct nfs_server *server = NFS_SERVER(inode); struct pnfs_layout_hdr *lo; struct nfs4_state *state = NULL; - unsigned long timeo, giveup; + unsigned long timeo, now, giveup; - dprintk("--> %s\n", __func__); + dprintk("--> %s tk_status => %d\n", __func__, -task->tk_status); if (!nfs41_sequence_done(task, &lgp->res.seq_res)) goto out; @@ -7419,12 +7419,38 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata) switch (task->tk_status) { case 0: goto out; + /* + * NFS4ERR_LAYOUTTRYLATER is a conflict with another client + * (or clients) writing to the same RAID stripe + */ case -NFS4ERR_LAYOUTTRYLATER: + /* + * NFS4ERR_RECALLCONFLICT is when conflict with self (must recall + * existing layout before getting a new one). + */ case -NFS4ERR_RECALLCONFLICT: timeo = rpc_get_timeout(task->tk_client); giveup = lgp->args.timestamp + timeo; - if (time_after(giveup, jiffies)) - task->tk_status = -NFS4ERR_DELAY; + now = jiffies; + if (time_after(giveup, now)) { + unsigned long delay; + + /* Delay for: + * - Not less then NFS4_POLL_RETRY_MIN. + * - One last time a jiffie before we give up + * - exponential backoff (time_now minus start_attempt) + */ + delay = max_t(unsigned long, NFS4_POLL_RETRY_MIN, + min((giveup - now - 1), + now - lgp->args.timestamp)); + + dprintk("%s: NFS4ERR_RECALLCONFLICT waiting %lu\n", + __func__, delay); + rpc_delay(task, delay); + task->tk_status = 0; + rpc_restart_call_prepare(task); + goto out; /* Do not call nfs4_async_handle_error() */ + } break; case -NFS4ERR_EXPIRED: case -NFS4ERR_BAD_STATEID: @@ -7780,10 +7806,7 @@ nfs4_layoutcommit_done(struct rpc_task *task, void *calldata) case -NFS4ERR_BADLAYOUT: /* no layout */ case -NFS4ERR_GRACE: /* loca_recalim always false */ task->tk_status = 0; - break; case 0: - nfs_post_op_update_inode_force_wcc(data->args.inode, - data->res.fattr); break; default: if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) { @@ -7798,6 +7821,8 @@ static void nfs4_layoutcommit_release(void *calldata) struct nfs4_layoutcommit_data *data = calldata; pnfs_cleanup_layoutcommit(data); + nfs_post_op_update_inode_force_wcc(data->args.inode, + data->res.fattr); put_rpccred(data->cred); kfree(data); } @@ -7920,7 +7945,7 @@ nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle, switch (err) { case 0: case -NFS4ERR_WRONGSEC: - case -NFS4ERR_NOTSUPP: + case -ENOTSUPP: goto out; default: err = nfs4_handle_exception(server, err, &exception); @@ -7954,7 +7979,7 @@ nfs41_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle, * Fall back on "guess and check" method if * the server doesn't support SECINFO_NO_NAME */ - if (err == -NFS4ERR_WRONGSEC || err == -NFS4ERR_NOTSUPP) { + if (err == -NFS4ERR_WRONGSEC || err == -ENOTSUPP) { err = nfs4_find_root_sec(server, fhandle, info); goto out_freepage; } diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 059c01b67a71..e5be72518bd7 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1071,7 +1071,7 @@ void nfs_free_seqid(struct nfs_seqid *seqid) /* * Increment the seqid if the OPEN/OPEN_DOWNGRADE/CLOSE succeeded, or * failed with a seqid incrementing error - - * see comments nfs_fs.h:seqid_mutating_error() + * see comments nfs4.h:seqid_mutating_error() */ static void nfs_increment_seqid(int status, struct nfs_seqid *seqid) { @@ -1116,7 +1116,7 @@ void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid) /* * Increment the seqid if the LOCK/LOCKU succeeded, or * failed with a seqid incrementing error - - * see comments nfs_fs.h:seqid_mutating_error() + * see comments nfs4.h:seqid_mutating_error() */ void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid) { diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c index 65ab0a0ca1c4..808f29574412 100644 --- a/fs/nfs/nfs4super.c +++ b/fs/nfs/nfs4super.c @@ -77,17 +77,9 @@ static int nfs4_write_inode(struct inode *inode, struct writeback_control *wbc) { int ret = nfs_write_inode(inode, wbc); - if (ret >= 0 && test_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(inode)->flags)) { - int status; - bool sync = true; - - if (wbc->sync_mode == WB_SYNC_NONE) - sync = false; - - status = pnfs_layoutcommit_inode(inode, sync); - if (status < 0) - return status; - } + if (ret == 0) + ret = pnfs_layoutcommit_inode(inode, + wbc->sync_mode == WB_SYNC_ALL); return ret; } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 5be2868c02f1..8c21d69a9dc1 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -3097,7 +3097,8 @@ static int decode_compound_hdr(struct xdr_stream *xdr, struct compound_hdr *hdr) return -EIO; } -static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected) +static bool __decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected, + int *nfs_retval) { __be32 *p; uint32_t opnum; @@ -3107,19 +3108,32 @@ static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected) if (unlikely(!p)) goto out_overflow; opnum = be32_to_cpup(p++); - if (opnum != expected) { - dprintk("nfs: Server returned operation" - " %d but we issued a request for %d\n", - opnum, expected); - return -EIO; - } + if (unlikely(opnum != expected)) + goto out_bad_operation; nfserr = be32_to_cpup(p); - if (nfserr != NFS_OK) - return nfs4_stat_to_errno(nfserr); - return 0; + if (nfserr == NFS_OK) + *nfs_retval = 0; + else + *nfs_retval = nfs4_stat_to_errno(nfserr); + return true; +out_bad_operation: + dprintk("nfs: Server returned operation" + " %d but we issued a request for %d\n", + opnum, expected); + *nfs_retval = -EREMOTEIO; + return false; out_overflow: print_overflow_msg(__func__, xdr); - return -EIO; + *nfs_retval = -EIO; + return false; +} + +static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected) +{ + int retval; + + __decode_op_hdr(xdr, expected, &retval); + return retval; } /* Dummy routine */ @@ -5001,11 +5015,12 @@ static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res) uint32_t savewords, bmlen, i; int status; - status = decode_op_hdr(xdr, OP_OPEN); - if (status != -EIO) - nfs_increment_open_seqid(status, res->seqid); - if (!status) - status = decode_stateid(xdr, &res->stateid); + if (!__decode_op_hdr(xdr, OP_OPEN, &status)) + return status; + nfs_increment_open_seqid(status, res->seqid); + if (status) + return status; + status = decode_stateid(xdr, &res->stateid); if (unlikely(status)) return status; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index d75d938d36cb..4755858e37a0 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1790,6 +1790,15 @@ pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) } EXPORT_SYMBOL_GPL(pnfs_generic_pg_readpages); +static void pnfs_clear_layoutcommitting(struct inode *inode) +{ + unsigned long *bitlock = &NFS_I(inode)->flags; + + clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock); + smp_mb__after_clear_bit(); + wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING); +} + /* * There can be multiple RW segments. */ @@ -1807,7 +1816,6 @@ static void pnfs_list_write_lseg(struct inode *inode, struct list_head *listp) static void pnfs_list_write_lseg_done(struct inode *inode, struct list_head *listp) { struct pnfs_layout_segment *lseg, *tmp; - unsigned long *bitlock = &NFS_I(inode)->flags; /* Matched by references in pnfs_set_layoutcommit */ list_for_each_entry_safe(lseg, tmp, listp, pls_lc_list) { @@ -1815,9 +1823,7 @@ static void pnfs_list_write_lseg_done(struct inode *inode, struct list_head *lis pnfs_put_lseg(lseg); } - clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock); - smp_mb__after_clear_bit(); - wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING); + pnfs_clear_layoutcommitting(inode); } void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg) @@ -1881,43 +1887,37 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync) struct nfs4_layoutcommit_data *data; struct nfs_inode *nfsi = NFS_I(inode); loff_t end_pos; - int status = 0; + int status; + + if (!pnfs_layoutcommit_outstanding(inode)) + return 0; dprintk("--> %s inode %lu\n", __func__, inode->i_ino); - if (!test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) - return 0; + status = -EAGAIN; + if (test_and_set_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags)) { + if (!sync) + goto out; + status = wait_on_bit_lock(&nfsi->flags, + NFS_INO_LAYOUTCOMMITTING, + nfs_wait_bit_killable, + TASK_KILLABLE); + if (status) + goto out; + } + status = -ENOMEM; /* Note kzalloc ensures data->res.seq_res.sr_slot == NULL */ data = kzalloc(sizeof(*data), GFP_NOFS); - if (!data) { - status = -ENOMEM; - goto out; - } + if (!data) + goto clear_layoutcommitting; - if (!test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) - goto out_free; - - if (test_and_set_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags)) { - if (!sync) { - status = -EAGAIN; - goto out_free; - } - status = wait_on_bit_lock(&nfsi->flags, NFS_INO_LAYOUTCOMMITTING, - nfs_wait_bit_killable, TASK_KILLABLE); - if (status) - goto out_free; - } + status = 0; + spin_lock(&inode->i_lock); + if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) + goto out_unlock; INIT_LIST_HEAD(&data->lseg_list); - spin_lock(&inode->i_lock); - if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) { - clear_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags); - spin_unlock(&inode->i_lock); - wake_up_bit(&nfsi->flags, NFS_INO_LAYOUTCOMMITTING); - goto out_free; - } - pnfs_list_write_lseg(inode, &data->lseg_list); end_pos = nfsi->layout->plh_lwb; @@ -1940,8 +1940,11 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync) mark_inode_dirty_sync(inode); dprintk("<-- %s status %d\n", __func__, status); return status; -out_free: +out_unlock: + spin_unlock(&inode->i_lock); kfree(data); +clear_layoutcommitting: + pnfs_clear_layoutcommitting(inode); goto out; } diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index a4f41810a7f4..023793909778 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -359,6 +359,15 @@ pnfs_ld_layoutret_on_setattr(struct inode *inode) PNFS_LAYOUTRET_ON_SETATTR; } +static inline bool +pnfs_layoutcommit_outstanding(struct inode *inode) +{ + struct nfs_inode *nfsi = NFS_I(inode); + + return test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags) != 0 || + test_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags) != 0; +} + static inline int pnfs_return_layout(struct inode *ino) { struct nfs_inode *nfsi = NFS_I(ino); @@ -515,6 +524,13 @@ pnfs_use_threshold(struct nfs4_threshold **dst, struct nfs4_threshold *src, return false; } +static inline bool +pnfs_layoutcommit_outstanding(struct inode *inode) +{ + return false; +} + + static inline struct nfs4_threshold *pnfs_mdsthreshold_alloc(void) { return NULL; diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 31db5c366b81..411aedda14bb 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -163,9 +163,9 @@ static void nfs_readpage_release(struct nfs_page *req) unlock_page(req->wb_page); - dprintk("NFS: read done (%s/%Ld %d@%Ld)\n", + dprintk("NFS: read done (%s/%Lu %d@%Ld)\n", req->wb_context->dentry->d_inode->i_sb->s_id, - (long long)NFS_FILEID(req->wb_context->dentry->d_inode), + (unsigned long long)NFS_FILEID(req->wb_context->dentry->d_inode), req->wb_bytes, (long long)req_offset(req)); nfs_release_request(req); @@ -228,11 +228,11 @@ int nfs_initiate_read(struct rpc_clnt *clnt, /* Set up the initial task struct. */ NFS_PROTO(inode)->read_setup(data, &msg); - dprintk("NFS: %5u initiated read call (req %s/%lld, %u bytes @ " + dprintk("NFS: %5u initiated read call (req %s/%llu, %u bytes @ " "offset %llu)\n", data->task.tk_pid, inode->i_sb->s_id, - (long long)NFS_FILEID(inode), + (unsigned long long)NFS_FILEID(inode), data->args.count, (unsigned long long)data->args.offset); @@ -630,9 +630,9 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, unsigned long npages; int ret = -ESTALE; - dprintk("NFS: nfs_readpages (%s/%Ld %d)\n", + dprintk("NFS: nfs_readpages (%s/%Lu %d)\n", inode->i_sb->s_id, - (long long)NFS_FILEID(inode), + (unsigned long long)NFS_FILEID(inode), nr_pages); nfs_inc_stats(inode, NFSIOS_VFSREADPAGES); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index c1d548211c31..a44a87268a6e 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -922,19 +922,20 @@ static bool nfs_write_pageuptodate(struct page *page, struct inode *inode) * extend the write to cover the entire page in order to avoid fragmentation * inefficiencies. * - * If the file is opened for synchronous writes or if we have a write delegation - * from the server then we can just skip the rest of the checks. + * If the file is opened for synchronous writes then we can just skip the rest + * of the checks. */ static int nfs_can_extend_write(struct file *file, struct page *page, struct inode *inode) { if (file->f_flags & O_DSYNC) return 0; + if (!nfs_write_pageuptodate(page, inode)) + return 0; if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) return 1; - if (nfs_write_pageuptodate(page, inode) && (inode->i_flock == NULL || - (inode->i_flock->fl_start == 0 && + if (inode->i_flock == NULL || (inode->i_flock->fl_start == 0 && inode->i_flock->fl_end == OFFSET_MAX && - inode->i_flock->fl_type != F_RDLCK))) + inode->i_flock->fl_type != F_RDLCK)) return 1; return 0; } @@ -1013,10 +1014,10 @@ int nfs_initiate_write(struct rpc_clnt *clnt, NFS_PROTO(inode)->write_setup(data, &msg); dprintk("NFS: %5u initiated write call " - "(req %s/%lld, %u bytes @ offset %llu)\n", + "(req %s/%llu, %u bytes @ offset %llu)\n", data->task.tk_pid, inode->i_sb->s_id, - (long long)NFS_FILEID(inode), + (unsigned long long)NFS_FILEID(inode), data->args.count, (unsigned long long)data->args.offset); @@ -1606,9 +1607,9 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) nfs_list_remove_request(req); nfs_clear_page_commit(req->wb_page); - dprintk("NFS: commit (%s/%lld %d@%lld)", + dprintk("NFS: commit (%s/%llu %d@%lld)", req->wb_context->dentry->d_sb->s_id, - (long long)NFS_FILEID(req->wb_context->dentry->d_inode), + (unsigned long long)NFS_FILEID(req->wb_context->dentry->d_inode), req->wb_bytes, (long long)req_offset(req)); if (status < 0) { diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index a353e0300b54..7f490bef9e99 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -84,7 +84,8 @@ enum { extern struct dentry *rpc_d_lookup_sb(const struct super_block *sb, const unsigned char *dir_name); -extern void rpc_pipefs_init_net(struct net *net); +extern int rpc_pipefs_init_net(struct net *net); +extern void rpc_pipefs_exit_net(struct net *net); extern struct super_block *rpc_get_sb_net(const struct net *net); extern void rpc_put_sb_net(const struct net *net); @@ -130,5 +131,7 @@ extern int rpc_unlink(struct dentry *); extern int register_rpc_pipefs(void); extern void unregister_rpc_pipefs(void); +extern bool gssd_running(struct net *net); + #endif #endif diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index d51d16c7afd8..ddc179b7a105 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -301,6 +301,7 @@ DECLARE_EVENT_CLASS(xs_socket_event_done, DEFINE_RPC_SOCKET_EVENT(rpc_socket_state_change); DEFINE_RPC_SOCKET_EVENT_DONE(rpc_socket_connect); +DEFINE_RPC_SOCKET_EVENT_DONE(rpc_socket_error); DEFINE_RPC_SOCKET_EVENT_DONE(rpc_socket_reset_connection); DEFINE_RPC_SOCKET_EVENT(rpc_socket_close); DEFINE_RPC_SOCKET_EVENT(rpc_socket_shutdown); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 42fdfc634e56..0a2aee060f9f 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -536,8 +536,7 @@ static void warn_gssd(void) unsigned long now = jiffies; if (time_after(now, ratelimit)) { - printk(KERN_WARNING "RPC: AUTH_GSS upcall timed out.\n" - "Please check user daemon is running.\n"); + pr_warn("RPC: AUTH_GSS upcall failed. Please check user daemon is running.\n"); ratelimit = now + 15*HZ; } } @@ -600,7 +599,6 @@ gss_create_upcall(struct gss_auth *gss_auth, struct gss_cred *gss_cred) struct rpc_pipe *pipe; struct rpc_cred *cred = &gss_cred->gc_base; struct gss_upcall_msg *gss_msg; - unsigned long timeout; DEFINE_WAIT(wait); int err; @@ -608,17 +606,16 @@ gss_create_upcall(struct gss_auth *gss_auth, struct gss_cred *gss_cred) __func__, from_kuid(&init_user_ns, cred->cr_uid)); retry: err = 0; - /* Default timeout is 15s unless we know that gssd is not running */ - timeout = 15 * HZ; - if (!sn->gssd_running) - timeout = HZ >> 2; + /* if gssd is down, just skip upcalling altogether */ + if (!gssd_running(net)) { + warn_gssd(); + return -EACCES; + } gss_msg = gss_setup_upcall(gss_auth, cred); if (PTR_ERR(gss_msg) == -EAGAIN) { err = wait_event_interruptible_timeout(pipe_version_waitqueue, - sn->pipe_version >= 0, timeout); + sn->pipe_version >= 0, 15 * HZ); if (sn->pipe_version < 0) { - if (err == 0) - sn->gssd_running = 0; warn_gssd(); err = -EACCES; } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index f09b7db2c492..0edada973434 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1529,9 +1529,13 @@ call_refreshresult(struct rpc_task *task) task->tk_action = call_refresh; switch (status) { case 0: - if (rpcauth_uptodatecred(task)) + if (rpcauth_uptodatecred(task)) { task->tk_action = call_allocate; - return; + return; + } + /* Use rate-limiting and a max number of retries if refresh + * had status 0 but failed to update the cred. + */ case -ETIMEDOUT: rpc_delay(task, 3*HZ); case -EAGAIN: @@ -1729,6 +1733,7 @@ call_bind_status(struct rpc_task *task) return; case -ECONNREFUSED: /* connection problems */ case -ECONNRESET: + case -ECONNABORTED: case -ENOTCONN: case -EHOSTDOWN: case -EHOSTUNREACH: @@ -1799,7 +1804,9 @@ call_connect_status(struct rpc_task *task) return; case -ECONNREFUSED: case -ECONNRESET: + case -ECONNABORTED: case -ENETUNREACH: + case -EHOSTUNREACH: /* retry with existing socket, after a delay */ rpc_delay(task, 3*HZ); if (RPC_IS_SOFTCONN(task)) @@ -1902,6 +1909,7 @@ call_transmit_status(struct rpc_task *task) break; } case -ECONNRESET: + case -ECONNABORTED: case -ENOTCONN: case -EPIPE: rpc_task_force_reencode(task); @@ -2011,8 +2019,9 @@ call_status(struct rpc_task *task) xprt_conditional_disconnect(req->rq_xprt, req->rq_connect_cookie); break; - case -ECONNRESET: case -ECONNREFUSED: + case -ECONNRESET: + case -ECONNABORTED: rpc_force_rebind(clnt); rpc_delay(task, 3*HZ); case -EPIPE: diff --git a/net/sunrpc/netns.h b/net/sunrpc/netns.h index 779742cfc1ff..94e506f9d72b 100644 --- a/net/sunrpc/netns.h +++ b/net/sunrpc/netns.h @@ -14,6 +14,7 @@ struct sunrpc_net { struct cache_detail *rsi_cache; struct super_block *pipefs_sb; + struct rpc_pipe *gssd_dummy; struct mutex pipefs_sb_lock; struct list_head all_clients; @@ -32,8 +33,6 @@ struct sunrpc_net { int pipe_version; atomic_t pipe_users; struct proc_dir_entry *use_gssp_proc; - - unsigned int gssd_running; }; extern int sunrpc_net_id; diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index bf04b30a788a..b18554898562 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -38,7 +39,7 @@ #define NET_NAME(net) ((net == &init_net) ? " (init_net)" : "") static struct file_system_type rpc_pipe_fs_type; - +static const struct rpc_pipe_ops gssd_dummy_pipe_ops; static struct kmem_cache *rpc_inode_cachep __read_mostly; @@ -216,14 +217,11 @@ rpc_destroy_inode(struct inode *inode) static int rpc_pipe_open(struct inode *inode, struct file *filp) { - struct net *net = inode->i_sb->s_fs_info; - struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct rpc_pipe *pipe; int first_open; int res = -ENXIO; mutex_lock(&inode->i_mutex); - sn->gssd_running = 1; pipe = RPC_I(inode)->pipe; if (pipe == NULL) goto out; @@ -1159,6 +1157,7 @@ enum { RPCAUTH_nfsd4_cb, RPCAUTH_cache, RPCAUTH_nfsd, + RPCAUTH_gssd, RPCAUTH_RootEOF }; @@ -1195,6 +1194,10 @@ static const struct rpc_filelist files[] = { .name = "nfsd", .mode = S_IFDIR | S_IRUGO | S_IXUGO, }, + [RPCAUTH_gssd] = { + .name = "gssd", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, }; /* @@ -1208,13 +1211,24 @@ struct dentry *rpc_d_lookup_sb(const struct super_block *sb, } EXPORT_SYMBOL_GPL(rpc_d_lookup_sb); -void rpc_pipefs_init_net(struct net *net) +int rpc_pipefs_init_net(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); + sn->gssd_dummy = rpc_mkpipe_data(&gssd_dummy_pipe_ops, 0); + if (IS_ERR(sn->gssd_dummy)) + return PTR_ERR(sn->gssd_dummy); + mutex_init(&sn->pipefs_sb_lock); - sn->gssd_running = 1; sn->pipe_version = -1; + return 0; +} + +void rpc_pipefs_exit_net(struct net *net) +{ + struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); + + rpc_destroy_pipe_data(sn->gssd_dummy); } /* @@ -1244,11 +1258,134 @@ void rpc_put_sb_net(const struct net *net) } EXPORT_SYMBOL_GPL(rpc_put_sb_net); +static const struct rpc_filelist gssd_dummy_clnt_dir[] = { + [0] = { + .name = "clntXX", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, +}; + +static ssize_t +dummy_downcall(struct file *filp, const char __user *src, size_t len) +{ + return -EINVAL; +} + +static const struct rpc_pipe_ops gssd_dummy_pipe_ops = { + .upcall = rpc_pipe_generic_upcall, + .downcall = dummy_downcall, +}; + +/* + * Here we present a bogus "info" file to keep rpc.gssd happy. We don't expect + * that it will ever use this info to handle an upcall, but rpc.gssd expects + * that this file will be there and have a certain format. + */ +static int +rpc_show_dummy_info(struct seq_file *m, void *v) +{ + seq_printf(m, "RPC server: %s\n", utsname()->nodename); + seq_printf(m, "service: foo (1) version 0\n"); + seq_printf(m, "address: 127.0.0.1\n"); + seq_printf(m, "protocol: tcp\n"); + seq_printf(m, "port: 0\n"); + return 0; +} + +static int +rpc_dummy_info_open(struct inode *inode, struct file *file) +{ + return single_open(file, rpc_show_dummy_info, NULL); +} + +static const struct file_operations rpc_dummy_info_operations = { + .owner = THIS_MODULE, + .open = rpc_dummy_info_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static const struct rpc_filelist gssd_dummy_info_file[] = { + [0] = { + .name = "info", + .i_fop = &rpc_dummy_info_operations, + .mode = S_IFREG | S_IRUSR, + }, +}; + +/** + * rpc_gssd_dummy_populate - create a dummy gssd pipe + * @root: root of the rpc_pipefs filesystem + * @pipe_data: pipe data created when netns is initialized + * + * Create a dummy set of directories and a pipe that gssd can hold open to + * indicate that it is up and running. + */ +static struct dentry * +rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data) +{ + int ret = 0; + struct dentry *gssd_dentry; + struct dentry *clnt_dentry = NULL; + struct dentry *pipe_dentry = NULL; + struct qstr q = QSTR_INIT(files[RPCAUTH_gssd].name, + strlen(files[RPCAUTH_gssd].name)); + + /* We should never get this far if "gssd" doesn't exist */ + gssd_dentry = d_hash_and_lookup(root, &q); + if (!gssd_dentry) + return ERR_PTR(-ENOENT); + + ret = rpc_populate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1, NULL); + if (ret) { + pipe_dentry = ERR_PTR(ret); + goto out; + } + + q.name = gssd_dummy_clnt_dir[0].name; + q.len = strlen(gssd_dummy_clnt_dir[0].name); + clnt_dentry = d_hash_and_lookup(gssd_dentry, &q); + if (!clnt_dentry) { + pipe_dentry = ERR_PTR(-ENOENT); + goto out; + } + + ret = rpc_populate(clnt_dentry, gssd_dummy_info_file, 0, 1, NULL); + if (ret) { + __rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1); + pipe_dentry = ERR_PTR(ret); + goto out; + } + + pipe_dentry = rpc_mkpipe_dentry(clnt_dentry, "gssd", NULL, pipe_data); + if (IS_ERR(pipe_dentry)) { + __rpc_depopulate(clnt_dentry, gssd_dummy_info_file, 0, 1); + __rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1); + } +out: + dput(clnt_dentry); + dput(gssd_dentry); + return pipe_dentry; +} + +static void +rpc_gssd_dummy_depopulate(struct dentry *pipe_dentry) +{ + struct dentry *clnt_dir = pipe_dentry->d_parent; + struct dentry *gssd_dir = clnt_dir->d_parent; + + __rpc_rmpipe(clnt_dir->d_inode, pipe_dentry); + __rpc_depopulate(clnt_dir, gssd_dummy_info_file, 0, 1); + __rpc_depopulate(gssd_dir, gssd_dummy_clnt_dir, 0, 1); + dput(pipe_dentry); +} + static int rpc_fill_super(struct super_block *sb, void *data, int silent) { struct inode *inode; - struct dentry *root; + struct dentry *root, *gssd_dentry; struct net *net = data; struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); int err; @@ -1266,6 +1403,13 @@ rpc_fill_super(struct super_block *sb, void *data, int silent) return -ENOMEM; if (rpc_populate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF, NULL)) return -ENOMEM; + + gssd_dentry = rpc_gssd_dummy_populate(root, sn->gssd_dummy); + if (IS_ERR(gssd_dentry)) { + __rpc_depopulate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF); + return PTR_ERR(gssd_dentry); + } + dprintk("RPC: sending pipefs MOUNT notification for net %p%s\n", net, NET_NAME(net)); mutex_lock(&sn->pipefs_sb_lock); @@ -1280,6 +1424,7 @@ rpc_fill_super(struct super_block *sb, void *data, int silent) return 0; err_depopulate: + rpc_gssd_dummy_depopulate(gssd_dentry); blocking_notifier_call_chain(&rpc_pipefs_notifier_list, RPC_PIPEFS_UMOUNT, sb); @@ -1289,6 +1434,16 @@ rpc_fill_super(struct super_block *sb, void *data, int silent) return err; } +bool +gssd_running(struct net *net) +{ + struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); + struct rpc_pipe *pipe = sn->gssd_dummy; + + return pipe->nreaders || pipe->nwriters; +} +EXPORT_SYMBOL_GPL(gssd_running); + static struct dentry * rpc_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index 3d6498af9adc..cd30120de9e4 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -44,12 +44,17 @@ static __net_init int sunrpc_init_net(struct net *net) if (err) goto err_unixgid; - rpc_pipefs_init_net(net); + err = rpc_pipefs_init_net(net); + if (err) + goto err_pipefs; + INIT_LIST_HEAD(&sn->all_clients); spin_lock_init(&sn->rpc_client_lock); spin_lock_init(&sn->rpcb_clnt_lock); return 0; +err_pipefs: + unix_gid_cache_destroy(net); err_unixgid: ip_map_cache_destroy(net); err_ipmap: @@ -60,6 +65,7 @@ static __net_init int sunrpc_init_net(struct net *net) static __net_exit void sunrpc_exit_net(struct net *net) { + rpc_pipefs_exit_net(net); unix_gid_cache_destroy(net); ip_map_cache_destroy(net); rpc_proc_exit(net); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 1750048130a7..7d4df99f761f 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -749,6 +749,11 @@ static void xprt_connect_status(struct rpc_task *task) } switch (task->tk_status) { + case -ECONNREFUSED: + case -ECONNRESET: + case -ECONNABORTED: + case -ENETUNREACH: + case -EHOSTUNREACH: case -EAGAIN: dprintk("RPC: %5u xprt_connect_status: retrying\n", task->tk_pid); break; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 75b045e1cd50..2a7ca8ffe83a 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -257,6 +257,7 @@ struct sock_xprt { void (*old_data_ready)(struct sock *, int); void (*old_state_change)(struct sock *); void (*old_write_space)(struct sock *); + void (*old_error_report)(struct sock *); }; /* @@ -274,6 +275,11 @@ struct sock_xprt { */ #define TCP_RPC_REPLY (1UL << 6) +static inline struct rpc_xprt *xprt_from_sock(struct sock *sk) +{ + return (struct rpc_xprt *) sk->sk_user_data; +} + static inline struct sockaddr *xs_addr(struct rpc_xprt *xprt) { return (struct sockaddr *) &xprt->addr; @@ -799,6 +805,7 @@ static void xs_save_old_callbacks(struct sock_xprt *transport, struct sock *sk) transport->old_data_ready = sk->sk_data_ready; transport->old_state_change = sk->sk_state_change; transport->old_write_space = sk->sk_write_space; + transport->old_error_report = sk->sk_error_report; } static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *sk) @@ -806,6 +813,34 @@ static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *s sk->sk_data_ready = transport->old_data_ready; sk->sk_state_change = transport->old_state_change; sk->sk_write_space = transport->old_write_space; + sk->sk_error_report = transport->old_error_report; +} + +/** + * xs_error_report - callback to handle TCP socket state errors + * @sk: socket + * + * Note: we don't call sock_error() since there may be a rpc_task + * using the socket, and so we don't want to clear sk->sk_err. + */ +static void xs_error_report(struct sock *sk) +{ + struct rpc_xprt *xprt; + int err; + + read_lock_bh(&sk->sk_callback_lock); + if (!(xprt = xprt_from_sock(sk))) + goto out; + + err = -sk->sk_err; + if (err == 0) + goto out; + dprintk("RPC: xs_error_report client %p, error=%d...\n", + xprt, -err); + trace_rpc_socket_error(xprt, sk->sk_socket, err); + xprt_wake_pending_tasks(xprt, err); + out: + read_unlock_bh(&sk->sk_callback_lock); } static void xs_reset_transport(struct sock_xprt *transport) @@ -885,11 +920,6 @@ static void xs_destroy(struct rpc_xprt *xprt) module_put(THIS_MODULE); } -static inline struct rpc_xprt *xprt_from_sock(struct sock *sk) -{ - return (struct rpc_xprt *) sk->sk_user_data; -} - static int xs_local_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb) { struct xdr_skb_reader desc = { @@ -1869,6 +1899,7 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt, sk->sk_user_data = xprt; sk->sk_data_ready = xs_local_data_ready; sk->sk_write_space = xs_udp_write_space; + sk->sk_error_report = xs_error_report; sk->sk_allocation = GFP_ATOMIC; xprt_clear_connected(xprt); @@ -2146,6 +2177,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_data_ready = xs_tcp_data_ready; sk->sk_state_change = xs_tcp_state_change; sk->sk_write_space = xs_tcp_write_space; + sk->sk_error_report = xs_error_report; sk->sk_allocation = GFP_ATOMIC; /* socket options */