diff options
Diffstat (limited to 'fs/nfs')
-rw-r--r-- | fs/nfs/blocklayout/blocklayout.c | 58 | ||||
-rw-r--r-- | fs/nfs/blocklayout/blocklayout.h | 4 | ||||
-rw-r--r-- | fs/nfs/blocklayout/blocklayoutdev.c | 35 | ||||
-rw-r--r-- | fs/nfs/callback.c | 4 | ||||
-rw-r--r-- | fs/nfs/callback_xdr.c | 12 | ||||
-rw-r--r-- | fs/nfs/client.c | 11 | ||||
-rw-r--r-- | fs/nfs/delegation.c | 2 | ||||
-rw-r--r-- | fs/nfs/dir.c | 2 | ||||
-rw-r--r-- | fs/nfs/file.c | 112 | ||||
-rw-r--r-- | fs/nfs/fscache-index.c | 4 | ||||
-rw-r--r-- | fs/nfs/idmap.c | 25 | ||||
-rw-r--r-- | fs/nfs/inode.c | 24 | ||||
-rw-r--r-- | fs/nfs/internal.h | 12 | ||||
-rw-r--r-- | fs/nfs/nfs3proc.c | 1 | ||||
-rw-r--r-- | fs/nfs/nfs4_fs.h | 24 | ||||
-rw-r--r-- | fs/nfs/nfs4filelayout.c | 41 | ||||
-rw-r--r-- | fs/nfs/nfs4proc.c | 123 | ||||
-rw-r--r-- | fs/nfs/nfs4state.c | 33 | ||||
-rw-r--r-- | fs/nfs/nfs4xdr.c | 2 | ||||
-rw-r--r-- | fs/nfs/objlayout/objio_osd.c | 872 | ||||
-rw-r--r-- | fs/nfs/objlayout/objlayout.c | 209 | ||||
-rw-r--r-- | fs/nfs/objlayout/objlayout.h | 48 | ||||
-rw-r--r-- | fs/nfs/pagelist.c | 3 | ||||
-rw-r--r-- | fs/nfs/pnfs.c | 96 | ||||
-rw-r--r-- | fs/nfs/pnfs.h | 5 | ||||
-rw-r--r-- | fs/nfs/pnfs_dev.c | 1 | ||||
-rw-r--r-- | fs/nfs/proc.c | 1 | ||||
-rw-r--r-- | fs/nfs/read.c | 30 | ||||
-rw-r--r-- | fs/nfs/super.c | 54 | ||||
-rw-r--r-- | fs/nfs/unlink.c | 4 | ||||
-rw-r--r-- | fs/nfs/write.c | 77 |
31 files changed, 670 insertions, 1259 deletions
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 9561c8fc8bdb..281ae95932c9 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -176,17 +176,6 @@ retry: return bio; } -static void bl_set_lo_fail(struct pnfs_layout_segment *lseg) -{ - if (lseg->pls_range.iomode == IOMODE_RW) { - dprintk("%s Setting layout IOMODE_RW fail bit\n", __func__); - set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags); - } else { - dprintk("%s Setting layout IOMODE_READ fail bit\n", __func__); - set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags); - } -} - /* This is basically copied from mpage_end_io_read */ static void bl_end_io_read(struct bio *bio, int err) { @@ -206,7 +195,7 @@ static void bl_end_io_read(struct bio *bio, int err) if (!uptodate) { if (!rdata->pnfs_error) rdata->pnfs_error = -EIO; - bl_set_lo_fail(rdata->lseg); + pnfs_set_lo_fail(rdata->lseg); } bio_put(bio); put_parallel(par); @@ -303,6 +292,7 @@ bl_read_pagelist(struct nfs_read_data *rdata) bl_end_io_read, par); if (IS_ERR(bio)) { rdata->pnfs_error = PTR_ERR(bio); + bio = NULL; goto out; } } @@ -370,7 +360,7 @@ static void bl_end_io_write_zero(struct bio *bio, int err) if (!uptodate) { if (!wdata->pnfs_error) wdata->pnfs_error = -EIO; - bl_set_lo_fail(wdata->lseg); + pnfs_set_lo_fail(wdata->lseg); } bio_put(bio); put_parallel(par); @@ -386,7 +376,7 @@ static void bl_end_io_write(struct bio *bio, int err) if (!uptodate) { if (!wdata->pnfs_error) wdata->pnfs_error = -EIO; - bl_set_lo_fail(wdata->lseg); + pnfs_set_lo_fail(wdata->lseg); } bio_put(bio); put_parallel(par); @@ -543,6 +533,11 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync) fill_invalid_ext: dprintk("%s need to zero %d pages\n", __func__, npg_zero); for (;npg_zero > 0; npg_zero--) { + if (bl_is_sector_init(be->be_inval, isect)) { + dprintk("isect %llu already init\n", + (unsigned long long)isect); + goto next_page; + } /* page ref released in bl_end_io_write_zero */ index = isect >> PAGE_CACHE_SECTOR_SHIFT; dprintk("%s zero %dth page: index %lu isect %llu\n", @@ -562,8 +557,7 @@ fill_invalid_ext: * PageUptodate: It was read before * sector_initialized: already written out */ - if (PageDirty(page) || PageWriteback(page) || - bl_is_sector_init(be->be_inval, isect)) { + if (PageDirty(page) || PageWriteback(page)) { print_page(page); unlock_page(page); page_cache_release(page); @@ -592,6 +586,7 @@ fill_invalid_ext: bl_end_io_write_zero, par); if (IS_ERR(bio)) { wdata->pnfs_error = PTR_ERR(bio); + bio = NULL; goto out; } /* FIXME: This should be done in bi_end_io */ @@ -640,6 +635,7 @@ next_page: bl_end_io_write, par); if (IS_ERR(bio)) { wdata->pnfs_error = PTR_ERR(bio); + bio = NULL; goto out; } isect += PAGE_CACHE_SECTORS; @@ -805,7 +801,7 @@ nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh, struct nfs4_deviceid *d_id) { struct pnfs_device *dev; - struct pnfs_block_dev *rv = NULL; + struct pnfs_block_dev *rv; u32 max_resp_sz; int max_pages; struct page **pages = NULL; @@ -823,18 +819,20 @@ nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh, dev = kmalloc(sizeof(*dev), GFP_NOFS); if (!dev) { dprintk("%s kmalloc failed\n", __func__); - return NULL; + return ERR_PTR(-ENOMEM); } pages = kzalloc(max_pages * sizeof(struct page *), GFP_NOFS); if (pages == NULL) { kfree(dev); - return NULL; + return ERR_PTR(-ENOMEM); } for (i = 0; i < max_pages; i++) { pages[i] = alloc_page(GFP_NOFS); - if (!pages[i]) + if (!pages[i]) { + rv = ERR_PTR(-ENOMEM); goto out_free; + } } memcpy(&dev->dev_id, d_id, sizeof(*d_id)); @@ -847,8 +845,10 @@ nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh, dprintk("%s: dev_id: %s\n", __func__, dev->dev_id.data); rc = nfs4_proc_getdeviceinfo(server, dev); dprintk("%s getdevice info returns %d\n", __func__, rc); - if (rc) + if (rc) { + rv = ERR_PTR(rc); goto out_free; + } rv = nfs4_blk_decode_device(server, dev); out_free: @@ -866,7 +866,7 @@ bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh) struct pnfs_devicelist *dlist = NULL; struct pnfs_block_dev *bdev; LIST_HEAD(block_disklist); - int status = 0, i; + int status, i; dprintk("%s enter\n", __func__); @@ -898,8 +898,8 @@ bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh) for (i = 0; i < dlist->num_devs; i++) { bdev = nfs4_blk_get_deviceinfo(server, fh, &dlist->dev_id[i]); - if (!bdev) { - status = -ENODEV; + if (IS_ERR(bdev)) { + status = PTR_ERR(bdev); goto out_error; } spin_lock(&b_mt_id->bm_lock); @@ -960,7 +960,7 @@ static struct pnfs_layoutdriver_type blocklayout_type = { }; static const struct rpc_pipe_ops bl_upcall_ops = { - .upcall = bl_pipe_upcall, + .upcall = rpc_pipe_generic_upcall, .downcall = bl_pipe_downcall, .destroy_msg = bl_pipe_destroy_msg, }; @@ -989,17 +989,20 @@ static int __init nfs4blocklayout_init(void) mnt, NFS_PIPE_DIRNAME, 0, &path); if (ret) - goto out_remove; + goto out_putrpc; bl_device_pipe = rpc_mkpipe(path.dentry, "blocklayout", NULL, &bl_upcall_ops, 0); + path_put(&path); if (IS_ERR(bl_device_pipe)) { ret = PTR_ERR(bl_device_pipe); - goto out_remove; + goto out_putrpc; } out: return ret; +out_putrpc: + rpc_put_mount(); out_remove: pnfs_unregister_layoutdriver(&blocklayout_type); return ret; @@ -1012,6 +1015,7 @@ static void __exit nfs4blocklayout_exit(void) pnfs_unregister_layoutdriver(&blocklayout_type); rpc_unlink(bl_device_pipe); + rpc_put_mount(); } MODULE_ALIAS("nfs-layouttype4-3"); diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h index f27d827960a3..42acf7ef5992 100644 --- a/fs/nfs/blocklayout/blocklayout.h +++ b/fs/nfs/blocklayout/blocklayout.h @@ -150,7 +150,7 @@ BLK_LSEG2EXT(struct pnfs_layout_segment *lseg) } struct bl_dev_msg { - int status; + int32_t status; uint32_t major, minor; }; @@ -169,8 +169,6 @@ extern wait_queue_head_t bl_wq; #define BL_DEVICE_REQUEST_ERR 0x2 /* User level process fails */ /* blocklayoutdev.c */ -ssize_t bl_pipe_upcall(struct file *, struct rpc_pipe_msg *, - char __user *, size_t); ssize_t bl_pipe_downcall(struct file *, const char __user *, size_t); void bl_pipe_destroy_msg(struct rpc_pipe_msg *); struct block_device *nfs4_blkdev_get(dev_t dev); diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c index a83b393fb01c..d08ba9107fde 100644 --- a/fs/nfs/blocklayout/blocklayoutdev.c +++ b/fs/nfs/blocklayout/blocklayoutdev.c @@ -79,28 +79,6 @@ int nfs4_blkdev_put(struct block_device *bdev) return blkdev_put(bdev, FMODE_READ); } -/* - * Shouldn't there be a rpc_generic_upcall() to do this for us? - */ -ssize_t bl_pipe_upcall(struct file *filp, struct rpc_pipe_msg *msg, - char __user *dst, size_t buflen) -{ - char *data = (char *)msg->data + msg->copied; - size_t mlen = min(msg->len - msg->copied, buflen); - unsigned long left; - - left = copy_to_user(dst, data, mlen); - if (left == mlen) { - msg->errno = -EFAULT; - return -EFAULT; - } - - mlen -= left; - msg->copied += mlen; - msg->errno = 0; - return mlen; -} - static struct bl_dev_msg bl_mount_reply; ssize_t bl_pipe_downcall(struct file *filp, const char __user *src, @@ -131,7 +109,7 @@ struct pnfs_block_dev * nfs4_blk_decode_device(struct nfs_server *server, struct pnfs_device *dev) { - struct pnfs_block_dev *rv = NULL; + struct pnfs_block_dev *rv; struct block_device *bd = NULL; struct rpc_pipe_msg msg; struct bl_msg_hdr bl_msg = { @@ -141,7 +119,7 @@ nfs4_blk_decode_device(struct nfs_server *server, uint8_t *dataptr; DECLARE_WAITQUEUE(wq, current); struct bl_dev_msg *reply = &bl_mount_reply; - int offset, len, i; + int offset, len, i, rc; dprintk("%s CREATING PIPEFS MESSAGE\n", __func__); dprintk("%s: deviceid: %s, mincount: %d\n", __func__, dev->dev_id.data, @@ -168,8 +146,10 @@ nfs4_blk_decode_device(struct nfs_server *server, dprintk("%s CALLING USERSPACE DAEMON\n", __func__); add_wait_queue(&bl_wq, &wq); - if (rpc_queue_upcall(bl_device_pipe->d_inode, &msg) < 0) { + rc = rpc_queue_upcall(bl_device_pipe->d_inode, &msg); + if (rc < 0) { remove_wait_queue(&bl_wq, &wq); + rv = ERR_PTR(rc); goto out; } @@ -187,8 +167,9 @@ nfs4_blk_decode_device(struct nfs_server *server, bd = nfs4_blkdev_get(MKDEV(reply->major, reply->minor)); if (IS_ERR(bd)) { - dprintk("%s failed to open device : %ld\n", - __func__, PTR_ERR(bd)); + rc = PTR_ERR(bd); + dprintk("%s failed to open device : %d\n", __func__, rc); + rv = ERR_PTR(rc); goto out; } diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index e3d294269058..516f3375e067 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -125,7 +125,7 @@ nfs4_callback_up(struct svc_serv *serv) else goto out_err; - return svc_prepare_thread(serv, &serv->sv_pools[0]); + return svc_prepare_thread(serv, &serv->sv_pools[0], NUMA_NO_NODE); out_err: if (ret == 0) @@ -199,7 +199,7 @@ nfs41_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt) INIT_LIST_HEAD(&serv->sv_cb_list); spin_lock_init(&serv->sv_cb_lock); init_waitqueue_head(&serv->sv_cb_waitq); - rqstp = svc_prepare_thread(serv, &serv->sv_pools[0]); + rqstp = svc_prepare_thread(serv, &serv->sv_pools[0], NUMA_NO_NODE); if (IS_ERR(rqstp)) { svc_xprt_put(serv->sv_bc_xprt); serv->sv_bc_xprt = NULL; diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 918ad647afea..726e59a9e50f 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -488,17 +488,18 @@ static __be32 decode_recallany_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct cb_recallanyargs *args) { - __be32 *p; + uint32_t bitmap[2]; + __be32 *p, status; args->craa_addr = svc_addr(rqstp); p = read_buf(xdr, 4); if (unlikely(p == NULL)) return htonl(NFS4ERR_BADXDR); args->craa_objs_to_keep = ntohl(*p++); - p = read_buf(xdr, 4); - if (unlikely(p == NULL)) - return htonl(NFS4ERR_BADXDR); - args->craa_type_mask = ntohl(*p); + status = decode_bitmap(xdr, bitmap); + if (unlikely(status)) + return status; + args->craa_type_mask = bitmap[0]; return 0; } @@ -986,4 +987,5 @@ struct svc_version nfs4_callback_version4 = { .vs_proc = nfs4_callback_procedures1, .vs_xdrsize = NFS4_CALLBACK_XDRSIZE, .vs_dispatch = NULL, + .vs_hidden = 1, }; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 5833fbbf59b0..873bf00d51a2 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -336,11 +336,12 @@ static int nfs_sockaddr_match_ipaddr6(const struct sockaddr *sa1, const struct sockaddr_in6 *sin1 = (const struct sockaddr_in6 *)sa1; const struct sockaddr_in6 *sin2 = (const struct sockaddr_in6 *)sa2; - if (ipv6_addr_scope(&sin1->sin6_addr) == IPV6_ADDR_SCOPE_LINKLOCAL && - sin1->sin6_scope_id != sin2->sin6_scope_id) + if (!ipv6_addr_equal(&sin1->sin6_addr, &sin2->sin6_addr)) return 0; + else if (ipv6_addr_type(&sin1->sin6_addr) & IPV6_ADDR_LINKLOCAL) + return sin1->sin6_scope_id == sin2->sin6_scope_id; - return ipv6_addr_equal(&sin1->sin6_addr, &sin2->sin6_addr); + return 1; } #else /* !defined(CONFIG_IPV6) && !defined(CONFIG_IPV6_MODULE) */ static int nfs_sockaddr_match_ipaddr6(const struct sockaddr *sa1, @@ -1867,6 +1868,10 @@ static int nfs_server_list_show(struct seq_file *m, void *v) /* display one transport per line on subsequent lines */ clp = list_entry(v, struct nfs_client, cl_share_link); + /* Check if the client is initialized */ + if (clp->cl_cons_state != NFS_CS_READY) + return 0; + seq_printf(m, "v%u %s %s %3d %s\n", clp->rpc_ops->version, rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_ADDR), diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 321a66bc3846..7f2654069806 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -240,7 +240,7 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct sizeof(delegation->stateid.data)); delegation->type = res->delegation_type; delegation->maxsize = res->maxsize; - delegation->change_attr = nfsi->change_attr; + delegation->change_attr = inode->i_version; delegation->cred = get_rpccred(cred); delegation->inode = inode; delegation->flags = 1<<NFS_DELEGATION_REFERENCED; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index b238d95ac48c..ac2899098147 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1468,12 +1468,12 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry res = NULL; goto out; /* This turned out not to be a regular file */ + case -EISDIR: case -ENOTDIR: goto no_open; case -ELOOP: if (!(nd->intent.open.flags & O_NOFOLLOW)) goto no_open; - /* case -EISDIR: */ /* case -EINVAL: */ default: res = ERR_CAST(inode); diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 28b8c3f3cda3..606ef0f20aed 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -40,48 +40,8 @@ #define NFSDBG_FACILITY NFSDBG_FILE -static int nfs_file_open(struct inode *, struct file *); -static int nfs_file_release(struct inode *, struct file *); -static loff_t nfs_file_llseek(struct file *file, loff_t offset, int origin); -static int nfs_file_mmap(struct file *, struct vm_area_struct *); -static ssize_t nfs_file_splice_read(struct file *filp, loff_t *ppos, - struct pipe_inode_info *pipe, - size_t count, unsigned int flags); -static ssize_t nfs_file_read(struct kiocb *, const struct iovec *iov, - unsigned long nr_segs, loff_t pos); -static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe, - struct file *filp, loff_t *ppos, - size_t count, unsigned int flags); -static ssize_t nfs_file_write(struct kiocb *, const struct iovec *iov, - unsigned long nr_segs, loff_t pos); -static int nfs_file_flush(struct file *, fl_owner_t id); -static int nfs_file_fsync(struct file *, loff_t, loff_t, int datasync); -static int nfs_check_flags(int flags); -static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl); -static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl); -static int nfs_setlease(struct file *file, long arg, struct file_lock **fl); - static const struct vm_operations_struct nfs_file_vm_ops; -const struct file_operations nfs_file_operations = { - .llseek = nfs_file_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = nfs_file_read, - .aio_write = nfs_file_write, - .mmap = nfs_file_mmap, - .open = nfs_file_open, - .flush = nfs_file_flush, - .release = nfs_file_release, - .fsync = nfs_file_fsync, - .lock = nfs_lock, - .flock = nfs_flock, - .splice_read = nfs_file_splice_read, - .splice_write = nfs_file_splice_write, - .check_flags = nfs_check_flags, - .setlease = nfs_setlease, -}; - const struct inode_operations nfs_file_inode_operations = { .permission = nfs_permission, .getattr = nfs_getattr, @@ -137,11 +97,9 @@ nfs_file_open(struct inode *inode, struct file *filp) static int nfs_file_release(struct inode *inode, struct file *filp) { - struct dentry *dentry = filp->f_path.dentry; - dprintk("NFS: release(%s/%s)\n", - dentry->d_parent->d_name.name, - dentry->d_name.name); + filp->f_path.dentry->d_parent->d_name.name, + filp->f_path.dentry->d_name.name); nfs_inc_stats(inode, NFSIOS_VFSRELEASE); return nfs_release(inode, filp); @@ -180,8 +138,6 @@ force_reval: static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin) { - loff_t loff; - dprintk("NFS: llseek file(%s/%s, %lld, %d)\n", filp->f_path.dentry->d_parent->d_name.name, filp->f_path.dentry->d_name.name, @@ -191,19 +147,15 @@ static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin) * origin == SEEK_END || SEEK_DATA || SEEK_HOLE => we must revalidate * the cached file length */ - if (origin != SEEK_SET || origin != SEEK_CUR) { + if (origin != SEEK_SET && origin != SEEK_CUR) { struct inode *inode = filp->f_mapping->host; int retval = nfs_revalidate_file_size(inode, filp); if (retval < 0) return (loff_t)retval; + } - spin_lock(&inode->i_lock); - loff = generic_file_llseek_unlocked(filp, offset, origin); - spin_unlock(&inode->i_lock); - } else - loff = generic_file_llseek_unlocked(filp, offset, origin); - return loff; + return generic_file_llseek(filp, offset, origin); } /* @@ -234,14 +186,13 @@ nfs_file_read(struct kiocb *iocb, const struct iovec *iov, struct dentry * dentry = iocb->ki_filp->f_path.dentry; struct inode * inode = dentry->d_inode; ssize_t result; - size_t count = iov_length(iov, nr_segs); if (iocb->ki_filp->f_flags & O_DIRECT) return nfs_file_direct_read(iocb, iov, nr_segs, pos); dprintk("NFS: read(%s/%s, %lu@%lu)\n", dentry->d_parent->d_name.name, dentry->d_name.name, - (unsigned long) count, (unsigned long) pos); + (unsigned long) iov_length(iov, nr_segs), (unsigned long) pos); result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping); if (!result) { @@ -895,3 +846,54 @@ static int nfs_setlease(struct file *file, long arg, struct file_lock **fl) file->f_path.dentry->d_name.name, arg); return -EINVAL; } + +const struct file_operations nfs_file_operations = { + .llseek = nfs_file_llseek, + .read = do_sync_read, + .write = do_sync_write, + .aio_read = nfs_file_read, + .aio_write = nfs_file_write, + .mmap = nfs_file_mmap, + .open = nfs_file_open, + .flush = nfs_file_flush, + .release = nfs_file_release, + .fsync = nfs_file_fsync, + .lock = nfs_lock, + .flock = nfs_flock, + .splice_read = nfs_file_splice_read, + .splice_write = nfs_file_splice_write, + .check_flags = nfs_check_flags, + .setlease = nfs_setlease, +}; + +#ifdef CONFIG_NFS_V4 +static int +nfs4_file_open(struct inode *inode, struct file *filp) +{ + /* + * NFSv4 opens are handled in d_lookup and d_revalidate. If we get to + * this point, then something is very wrong + */ + dprintk("NFS: %s called! inode=%p filp=%p\n", __func__, inode, filp); + return -ENOTDIR; +} + +const struct file_operations nfs4_file_operations = { + .llseek = nfs_file_llseek, + .read = do_sync_read, + .write = do_sync_write, + .aio_read = nfs_file_read, + .aio_write = nfs_file_write, + .mmap = nfs_file_mmap, + .open = nfs4_file_open, + .flush = nfs_file_flush, + .release = nfs_file_release, + .fsync = nfs_file_fsync, + .lock = nfs_lock, + .flock = nfs_flock, + .splice_read = nfs_file_splice_read, + .splice_write = nfs_file_splice_write, + .check_flags = nfs_check_flags, + .setlease = nfs_setlease, +}; +#endif /* CONFIG_NFS_V4 */ diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c index 5b1006480bc2..7cf2c4699b08 100644 --- a/fs/nfs/fscache-index.c +++ b/fs/nfs/fscache-index.c @@ -212,7 +212,7 @@ static uint16_t nfs_fscache_inode_get_aux(const void *cookie_netfs_data, auxdata.ctime = nfsi->vfs_inode.i_ctime; if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4) - auxdata.change_attr = nfsi->change_attr; + auxdata.change_attr = nfsi->vfs_inode.i_version; if (bufmax > sizeof(auxdata)) bufmax = sizeof(auxdata); @@ -244,7 +244,7 @@ enum fscache_checkaux nfs_fscache_inode_check_aux(void *cookie_netfs_data, auxdata.ctime = nfsi->vfs_inode.i_ctime; if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4) - auxdata.change_attr = nfsi->change_attr; + auxdata.change_attr = nfsi->vfs_inode.i_version; if (memcmp(data, &auxdata, datalen) != 0) return FSCACHE_CHECKAUX_OBSOLETE; diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index f20801ae0a16..47d1c6ff2d8e 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -336,8 +336,6 @@ struct idmap { struct idmap_hashtable idmap_group_hash; }; -static ssize_t idmap_pipe_upcall(struct file *, struct rpc_pipe_msg *, - char __user *, size_t); static ssize_t idmap_pipe_downcall(struct file *, const char __user *, size_t); static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *); @@ -345,7 +343,7 @@ static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *); static unsigned int fnvhash32(const void *, size_t); static const struct rpc_pipe_ops idmap_upcall_ops = { - .upcall = idmap_pipe_upcall, + .upcall = rpc_pipe_generic_upcall, .downcall = idmap_pipe_downcall, .destroy_msg = idmap_pipe_destroy_msg, }; @@ -595,27 +593,6 @@ nfs_idmap_name(struct idmap *idmap, struct idmap_hashtable *h, return ret; } -/* RPC pipefs upcall/downcall routines */ -static ssize_t -idmap_pipe_upcall(struct file *filp, struct rpc_pipe_msg *msg, - char __user *dst, size_t buflen) -{ - char *data = (char *)msg->data + msg->copied; - size_t mlen = min(msg->len, buflen); - unsigned long left; - - left = copy_to_user(dst, data, mlen); - if (left == mlen) { - msg->errno = -EFAULT; - return -EFAULT; - } - - mlen -= left; - msg->copied += mlen; - msg->errno = 0; - return mlen; -} - static ssize_t idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) { diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index fe1203797b2b..50a15fa8cf98 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -291,7 +291,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) */ inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->file_inode_ops; if (S_ISREG(inode->i_mode)) { - inode->i_fop = &nfs_file_operations; + inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops; inode->i_data.a_ops = &nfs_file_aops; inode->i_data.backing_dev_info = &NFS_SB(sb)->backing_dev_info; } else if (S_ISDIR(inode->i_mode)) { @@ -318,9 +318,9 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) memset(&inode->i_atime, 0, sizeof(inode->i_atime)); memset(&inode->i_mtime, 0, sizeof(inode->i_mtime)); memset(&inode->i_ctime, 0, sizeof(inode->i_ctime)); - nfsi->change_attr = 0; + inode->i_version = 0; inode->i_size = 0; - inode->i_nlink = 0; + clear_nlink(inode); inode->i_uid = -2; inode->i_gid = -2; inode->i_blocks = 0; @@ -344,7 +344,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL; if (fattr->valid & NFS_ATTR_FATTR_CHANGE) - nfsi->change_attr = fattr->change_attr; + inode->i_version = fattr->change_attr; else if (nfs_server_capable(inode, NFS_CAP_CHANGE_ATTR)) nfsi->cache_validity |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_DATA; @@ -355,7 +355,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) | NFS_INO_INVALID_DATA | NFS_INO_REVAL_PAGECACHE; if (fattr->valid & NFS_ATTR_FATTR_NLINK) - inode->i_nlink = fattr->nlink; + set_nlink(inode, fattr->nlink); else if (nfs_server_capable(inode, NFS_CAP_NLINK)) nfsi->cache_validity |= NFS_INO_INVALID_ATTR; if (fattr->valid & NFS_ATTR_FATTR_OWNER) @@ -897,8 +897,8 @@ static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE) && (fattr->valid & NFS_ATTR_FATTR_CHANGE) - && nfsi->change_attr == fattr->pre_change_attr) { - nfsi->change_attr = fattr->change_attr; + && inode->i_version == fattr->pre_change_attr) { + inode->i_version = fattr->change_attr; if (S_ISDIR(inode->i_mode)) nfsi->cache_validity |= NFS_INO_INVALID_DATA; ret |= NFS_INO_INVALID_ATTR; @@ -952,7 +952,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat return -EIO; if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && - nfsi->change_attr != fattr->change_attr) + inode->i_version != fattr->change_attr) invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE; /* Verify a few of the more important attributes */ @@ -1163,7 +1163,7 @@ int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fa } if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && (fattr->valid & NFS_ATTR_FATTR_PRECHANGE) == 0) { - fattr->pre_change_attr = NFS_I(inode)->change_attr; + fattr->pre_change_attr = inode->i_version; fattr->valid |= NFS_ATTR_FATTR_PRECHANGE; } if ((fattr->valid & NFS_ATTR_FATTR_CTIME) != 0 && @@ -1244,13 +1244,13 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) /* More cache consistency checks */ if (fattr->valid & NFS_ATTR_FATTR_CHANGE) { - if (nfsi->change_attr != fattr->change_attr) { + if (inode->i_version != fattr->change_attr) { dprintk("NFS: change_attr change on server for file %s/%ld\n", inode->i_sb->s_id, inode->i_ino); invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; if (S_ISDIR(inode->i_mode)) nfs_force_lookup_revalidate(inode); - nfsi->change_attr = fattr->change_attr; + inode->i_version = fattr->change_attr; } } else if (server->caps & NFS_CAP_CHANGE_ATTR) invalid |= save_cache_validity; @@ -1361,7 +1361,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) invalid |= NFS_INO_INVALID_ATTR; if (S_ISDIR(inode->i_mode)) invalid |= NFS_INO_INVALID_DATA; - inode->i_nlink = fattr->nlink; + set_nlink(inode, fattr->nlink); } } else if (server->caps & NFS_CAP_NLINK) invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index ab12913dd473..3f4d95751d52 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -299,6 +299,8 @@ extern void nfs_read_prepare(struct rpc_task *task, void *calldata); extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc, struct list_head *head); +extern void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio, + struct inode *inode); extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); extern void nfs_readdata_release(struct nfs_read_data *rdata); @@ -457,13 +459,3 @@ unsigned int nfs_page_array_len(unsigned int base, size_t len) PAGE_SIZE - 1) >> PAGE_SHIFT; } -/* - * Helper for restarting RPC calls in the possible presence of NFSv4.1 - * sessions. - */ -static inline int nfs_restart_rpc(struct rpc_task *task, const struct nfs_client *clp) -{ - if (nfs4_has_session(clp)) - return rpc_restart_call_prepare(task); - return rpc_restart_call(task); -} diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 85f1690ca08c..d4bc9ed91748 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -853,6 +853,7 @@ const struct nfs_rpc_ops nfs_v3_clientops = { .dentry_ops = &nfs_dentry_operations, .dir_inode_ops = &nfs3_dir_inode_operations, .file_inode_ops = &nfs3_file_inode_operations, + .file_ops = &nfs_file_operations, .getroot = nfs3_proc_get_root, .getattr = nfs3_proc_getattr, .setattr = nfs3_proc_setattr, diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 3e93e9a1bee1..693ae22f8731 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -13,30 +13,6 @@ struct idmap; -/* - * In a seqid-mutating op, this macro controls which error return - * values trigger incrementation of the seqid. - * - * from rfc 3010: - * The client MUST monotonically increment the sequence number for the - * CLOSE, LOCK, LOCKU, OPEN, OPEN_CONFIRM, and OPEN_DOWNGRADE - * operations. This is true even in the event that the previous - * operation that used the sequence number received an error. The only - * exception to this rule is if the previous operation received one of - * the following errors: NFSERR_STALE_CLIENTID, NFSERR_STALE_STATEID, - * NFSERR_BAD_STATEID, NFSERR_BAD_SEQID, NFSERR_BADXDR, - * NFSERR_RESOURCE, NFSERR_NOFILEHANDLE. - * - */ -#define seqid_mutating_err(err) \ -(((err) != NFSERR_STALE_CLIENTID) && \ - ((err) != NFSERR_STALE_STATEID) && \ - ((err) != NFSERR_BAD_STATEID) && \ - ((err) != NFSERR_BAD_SEQID) && \ - ((err) != NFSERR_BAD_XDR) && \ - ((err) != NFSERR_RESOURCE) && \ - ((err) != NFSERR_NOFILEHANDLE)) - enum nfs4_client_state { NFS4CLNT_MANAGER_RUNNING = 0, NFS4CLNT_CHECK_LEASE, diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index e8915d4840ad..a62d36b9a99e 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -31,6 +31,7 @@ #include <linux/nfs_fs.h> #include <linux/nfs_page.h> +#include <linux/module.h> #include "internal.h" #include "nfs4filelayout.h" @@ -77,19 +78,6 @@ filelayout_get_dserver_offset(struct pnfs_layout_segment *lseg, loff_t offset) BUG(); } -/* For data server errors we don't recover from */ -static void -filelayout_set_lo_fail(struct pnfs_layout_segment *lseg) -{ - if (lseg->pls_range.iomode == IOMODE_RW) { - dprintk("%s Setting layout IOMODE_RW fail bit\n", __func__); - set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags); - } else { - dprintk("%s Setting layout IOMODE_READ fail bit\n", __func__); - set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags); - } -} - static int filelayout_async_handle_error(struct rpc_task *task, struct nfs4_state *state, struct nfs_client *clp, @@ -135,7 +123,6 @@ static int filelayout_async_handle_error(struct rpc_task *task, static int filelayout_read_done_cb(struct rpc_task *task, struct nfs_read_data *data) { - struct nfs_client *clp = data->ds_clp; int reset = 0; dprintk("%s DS read\n", __func__); @@ -145,11 +132,10 @@ static int filelayout_read_done_cb(struct rpc_task *task, dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n", __func__, data->ds_clp, data->ds_clp->cl_session); if (reset) { - filelayout_set_lo_fail(data->lseg); + pnfs_set_lo_fail(data->lseg); nfs4_reset_read(task, data); - clp = NFS_SERVER(data->inode)->nfs_client; } - nfs_restart_rpc(task, clp); + rpc_restart_call_prepare(task); return -EAGAIN; } @@ -216,17 +202,13 @@ static int filelayout_write_done_cb(struct rpc_task *task, if (filelayout_async_handle_error(task, data->args.context->state, data->ds_clp, &reset) == -EAGAIN) { - struct nfs_client *clp; - dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n", __func__, data->ds_clp, data->ds_clp->cl_session); if (reset) { - filelayout_set_lo_fail(data->lseg); + pnfs_set_lo_fail(data->lseg); nfs4_reset_write(task, data); - clp = NFS_SERVER(data->inode)->nfs_client; - } else - clp = data->ds_clp; - nfs_restart_rpc(task, clp); + } + rpc_restart_call_prepare(task); return -EAGAIN; } @@ -256,9 +238,9 @@ static int filelayout_commit_done_cb(struct rpc_task *task, __func__, data->ds_clp, data->ds_clp->cl_session); if (reset) { prepare_to_resend_writes(data); - filelayout_set_lo_fail(data->lseg); + pnfs_set_lo_fail(data->lseg); } else - nfs_restart_rpc(task, data->ds_clp); + rpc_restart_call_prepare(task); return -EAGAIN; } @@ -468,9 +450,8 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo, fl->dsaddr = dsaddr; - if (fl->first_stripe_index < 0 || - fl->first_stripe_index >= dsaddr->stripe_count) { - dprintk("%s Bad first_stripe_index %d\n", + if (fl->first_stripe_index >= dsaddr->stripe_count) { + dprintk("%s Bad first_stripe_index %u\n", __func__, fl->first_stripe_index); goto out_put; } @@ -571,7 +552,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo, /* Note that a zero value for num_fh is legal for STRIPE_SPARSE. * Futher checking is done in filelayout_check_layout */ - if (fl->num_fh < 0 || fl->num_fh > + if (fl->num_fh > max(NFS4_PNFS_MAX_STRIPE_CNT, NFS4_PNFS_MAX_MULTI_CNT)) goto out_err; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 4700fae1ada0..d9f4d78c3413 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -39,6 +39,8 @@ #include <linux/delay.h> #include <linux/errno.h> #include <linux/string.h> +#include <linux/ratelimit.h> +#include <linux/printk.h> #include <linux/slab.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/gss_api.h> @@ -73,9 +75,6 @@ static int _nfs4_proc_open(struct nfs4_opendata *data); static int _nfs4_recover_proc_open(struct nfs4_opendata *data); static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *, struct nfs4_state *); -static int _nfs4_proc_lookup(struct rpc_clnt *client, struct inode *dir, - const struct qstr *name, struct nfs_fh *fhandle, - struct nfs_fattr *fattr); static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr); static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred, struct nfs_fattr *fattr, struct iattr *sattr, @@ -753,9 +752,9 @@ static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo) spin_lock(&dir->i_lock); nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_DATA; - if (!cinfo->atomic || cinfo->before != nfsi->change_attr) + if (!cinfo->atomic || cinfo->before != dir->i_version) nfs_force_lookup_revalidate(dir); - nfsi->change_attr = cinfo->after; + dir->i_version = cinfo->after; spin_unlock(&dir->i_lock); } @@ -897,6 +896,8 @@ out: static int can_open_delegated(struct nfs_delegation *delegation, fmode_t fmode) { + if (delegation == NULL) + return 0; if ((delegation->type & fmode) != fmode) return 0; if (test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags)) @@ -1039,8 +1040,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata) } rcu_read_lock(); delegation = rcu_dereference(nfsi->delegation); - if (delegation == NULL || - !can_open_delegated(delegation, fmode)) { + if (!can_open_delegated(delegation, fmode)) { rcu_read_unlock(); break; } @@ -1094,7 +1094,12 @@ static struct nfs4_state *nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data if (delegation) delegation_flags = delegation->flags; rcu_read_unlock(); - if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0) + if (data->o_arg.claim == NFS4_OPEN_CLAIM_DELEGATE_CUR) { + pr_err_ratelimited("NFS: Broken NFSv4 server %s is " + "returning a delegation for " + "OPEN(CLAIM_DELEGATE_CUR)\n", + NFS_CLIENT(inode)->cl_server); + } else if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0) nfs_inode_set_delegation(state->inode, data->owner->so_cred, &data->o_res); @@ -1426,11 +1431,9 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata) goto out_no_action; rcu_read_lock(); delegation = rcu_dereference(NFS_I(data->state->inode)->delegation); - if (delegation != NULL && - test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags) == 0) { - rcu_read_unlock(); - goto out_no_action; - } + if (data->o_arg.claim != NFS4_OPEN_CLAIM_DELEGATE_CUR && + can_open_delegated(delegation, data->o_arg.fmode)) + goto unlock_no_action; rcu_read_unlock(); } /* Update sequence id. */ @@ -1447,6 +1450,8 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata) return; rpc_call_start(task); return; +unlock_no_action: + rcu_read_unlock(); out_no_action: task->tk_action = NULL; @@ -1596,8 +1601,14 @@ static int _nfs4_proc_open(struct nfs4_opendata *data) int status; status = nfs4_run_open_task(data, 0); - if (status != 0 || !data->rpc_done) + if (!data->rpc_done) + return status; + if (status != 0) { + if (status == -NFS4ERR_BADNAME && + !(o_arg->open_flags & O_CREAT)) + return -ENOENT; return status; + } if (o_arg->open_flags & O_CREAT) { update_changeattr(dir, &o_res->cinfo); @@ -2408,14 +2419,15 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, return status; } -static int _nfs4_proc_lookupfh(struct rpc_clnt *clnt, struct nfs_server *server, - const struct nfs_fh *dirfh, const struct qstr *name, - struct nfs_fh *fhandle, struct nfs_fattr *fattr) +static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, + const struct qstr *name, struct nfs_fh *fhandle, + struct nfs_fattr *fattr) { + struct nfs_server *server = NFS_SERVER(dir); int status; struct nfs4_lookup_arg args = { .bitmask = server->attr_bitmask, - .dir_fh = dirfh, + .dir_fh = NFS_FH(dir), .name = name, }; struct nfs4_lookup_res res = { @@ -2431,40 +2443,8 @@ static int _nfs4_proc_lookupfh(struct rpc_clnt *clnt, struct nfs_server *server, nfs_fattr_init(fattr); - dprintk("NFS call lookupfh %s\n", name->name); - status = nfs4_call_sync(clnt, server, &msg, &args.seq_args, &res.seq_res, 0); - dprintk("NFS reply lookupfh: %d\n", status); - return status; -} - -static int nfs4_proc_lookupfh(struct nfs_server *server, struct nfs_fh *dirfh, - struct qstr *name, struct nfs_fh *fhandle, - struct nfs_fattr *fattr) -{ - struct nfs4_exception exception = { }; - int err; - do { - err = _nfs4_proc_lookupfh(server->client, server, dirfh, name, fhandle, fattr); - /* FIXME: !!!! */ - if (err == -NFS4ERR_MOVED) { - err = -EREMOTE; - break; - } - err = nfs4_handle_exception(server, err, &exception); - } while (exception.retry); - return err; -} - -static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, - const struct qstr *name, struct nfs_fh *fhandle, - struct nfs_fattr *fattr) -{ - int status; - dprintk("NFS call lookup %s\n", name->name); - status = _nfs4_proc_lookupfh(clnt, NFS_SERVER(dir), NFS_FH(dir), name, fhandle, fattr); - if (status == -NFS4ERR_MOVED) - status = nfs4_get_referral(dir, name, fattr, fhandle); + status = nfs4_call_sync(clnt, server, &msg, &args.seq_args, &res.seq_res, 0); dprintk("NFS reply lookup: %d\n", status); return status; } @@ -2485,11 +2465,19 @@ static int nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qst struct nfs4_exception exception = { }; int err; do { - err = nfs4_handle_exception(NFS_SERVER(dir), - _nfs4_proc_lookup(clnt, dir, name, fhandle, fattr), - &exception); - if (err == -EPERM) + int status; + + status = _nfs4_proc_lookup(clnt, dir, name, fhandle, fattr); + switch (status) { + case -NFS4ERR_BADNAME: + return -ENOENT; + case -NFS4ERR_MOVED: + return nfs4_get_referral(dir, name, fattr, fhandle); + case -NFS4ERR_WRONGSEC: nfs_fixup_secinfo_attributes(fattr, fhandle); + } + err = nfs4_handle_exception(NFS_SERVER(dir), + status, &exception); } while (exception.retry); return err; } @@ -3210,7 +3198,7 @@ static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data) struct nfs_server *server = NFS_SERVER(data->inode); if (nfs4_async_handle_error(task, server, data->args.context->state) == -EAGAIN) { - nfs_restart_rpc(task, server->nfs_client); + rpc_restart_call_prepare(task); return -EAGAIN; } @@ -3260,7 +3248,7 @@ static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data struct inode *inode = data->inode; if (nfs4_async_handle_error(task, NFS_SERVER(inode), data->args.context->state) == -EAGAIN) { - nfs_restart_rpc(task, NFS_SERVER(inode)->nfs_client); + rpc_restart_call_prepare(task); return -EAGAIN; } if (task->tk_status >= 0) { @@ -3317,7 +3305,7 @@ static int nfs4_commit_done_cb(struct rpc_task *task, struct nfs_write_data *dat struct inode *inode = data->inode; if (nfs4_async_handle_error(task, NFS_SERVER(inode), NULL) == -EAGAIN) { - nfs_restart_rpc(task, NFS_SERVER(inode)->nfs_client); + rpc_restart_call_prepare(task); return -EAGAIN; } nfs_refresh_inode(inode, data->res.fattr); @@ -3857,7 +3845,7 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) default: if (nfs4_async_handle_error(task, data->res.server, NULL) == -EAGAIN) { - nfs_restart_rpc(task, data->res.server->nfs_client); + rpc_restart_call_prepare(task); return; } } @@ -4111,8 +4099,7 @@ static void nfs4_locku_done(struct rpc_task *task, void *data) break; default: if (nfs4_async_handle_error(task, calldata->server, NULL) == -EAGAIN) - nfs_restart_rpc(task, - calldata->server->nfs_client); + rpc_restart_call_prepare(task); } } @@ -4945,7 +4932,7 @@ static void nfs4_get_lease_time_done(struct rpc_task *task, void *calldata) task->tk_status = 0; /* fall through */ case -NFS4ERR_RETRY_UNCACHED_REP: - nfs_restart_rpc(task, data->clp); + rpc_restart_call_prepare(task); return; } dprintk("<-- %s\n", __func__); @@ -5786,7 +5773,7 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) server = NFS_SERVER(lrp->args.inode); if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) { - nfs_restart_rpc(task, lrp->clp); + rpc_restart_call_prepare(task); return; } spin_lock(&lo->plh_inode->i_lock); @@ -5957,7 +5944,7 @@ nfs4_layoutcommit_done(struct rpc_task *task, void *calldata) } if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) { - nfs_restart_rpc(task, server->nfs_client); + rpc_restart_call_prepare(task); return; } @@ -5970,6 +5957,7 @@ static void nfs4_layoutcommit_release(void *calldata) { struct nfs4_layoutcommit_data *data = calldata; struct pnfs_layout_segment *lseg, *tmp; + unsigned long *bitlock = &NFS_I(data->args.inode)->flags; pnfs_cleanup_layoutcommit(data); /* Matched by references in pnfs_set_layoutcommit */ @@ -5979,6 +5967,11 @@ static void nfs4_layoutcommit_release(void *calldata) &lseg->pls_flags)) put_lseg(lseg); } + + clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock); + smp_mb__after_clear_bit(); + wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING); + put_rpccred(data->cred); kfree(data); } @@ -6267,10 +6260,10 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .dentry_ops = &nfs4_dentry_operations, .dir_inode_ops = &nfs4_dir_inode_operations, .file_inode_ops = &nfs4_file_inode_operations, + .file_ops = &nfs4_file_operations, .getroot = nfs4_proc_get_root, .getattr = nfs4_proc_getattr, .setattr = nfs4_proc_setattr, - .lookupfh = nfs4_proc_lookupfh, .lookup = nfs4_proc_lookup, .access = nfs4_proc_access, .readlink = nfs4_proc_readlink, diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 39914be40b03..6a7107ae6b72 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1156,11 +1156,13 @@ restart: if (status >= 0) { status = nfs4_reclaim_locks(state, ops); if (status >= 0) { + spin_lock(&state->state_lock); list_for_each_entry(lock, &state->lock_states, ls_locks) { if (!(lock->ls_flags & NFS_LOCK_INITIALIZED)) printk("%s: Lock reclaim failed!\n", __func__); } + spin_unlock(&state->state_lock); nfs4_put_open_state(state); goto restart; } @@ -1224,10 +1226,12 @@ static void nfs4_clear_open_state(struct nfs4_state *state) clear_bit(NFS_O_RDONLY_STATE, &state->flags); clear_bit(NFS_O_WRONLY_STATE, &state->flags); clear_bit(NFS_O_RDWR_STATE, &state->flags); + spin_lock(&state->state_lock); list_for_each_entry(lock, &state->lock_states, ls_locks) { lock->ls_seqid.flags = 0; lock->ls_flags &= ~NFS_LOCK_INITIALIZED; } + spin_unlock(&state->state_lock); } static void nfs4_reset_seqids(struct nfs_server *server, @@ -1350,12 +1354,14 @@ static void nfs4_warn_keyexpired(const char *s) static int nfs4_recovery_handle_error(struct nfs_client *clp, int error) { switch (error) { + case 0: + break; case -NFS4ERR_CB_PATH_DOWN: nfs_handle_cb_pathdown(clp); - return 0; + break; case -NFS4ERR_NO_GRACE: nfs4_state_end_reclaim_reboot(clp); - return 0; + break; case -NFS4ERR_STALE_CLIENTID: case -NFS4ERR_LEASE_MOVED: set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); @@ -1375,13 +1381,15 @@ static int nfs4_recovery_handle_error(struct nfs_client *clp, int error) case -NFS4ERR_SEQ_MISORDERED: set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state); /* Zero session reset errors */ - return 0; + break; case -EKEYEXPIRED: /* Nothing we can do */ nfs4_warn_keyexpired(clp->cl_hostname); - return 0; + break; + default: + return error; } - return error; + return 0; } static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recovery_ops *ops) @@ -1428,7 +1436,7 @@ static int nfs4_check_lease(struct nfs_client *clp) struct rpc_cred *cred; const struct nfs4_state_maintenance_ops *ops = clp->cl_mvops->state_renewal_ops; - int status = -NFS4ERR_EXPIRED; + int status; /* Is the client already known to have an expired lease? */ if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) @@ -1438,6 +1446,7 @@ static int nfs4_check_lease(struct nfs_client *clp) spin_unlock(&clp->cl_lock); if (cred == NULL) { cred = nfs4_get_setclientid_cred(clp); + status = -ENOKEY; if (cred == NULL) goto out; } @@ -1525,16 +1534,16 @@ void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags) { if (!flags) return; - else if (flags & SEQ4_STATUS_RESTART_RECLAIM_NEEDED) + if (flags & SEQ4_STATUS_RESTART_RECLAIM_NEEDED) nfs41_handle_server_reboot(clp); - else if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED | + if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED | SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED | SEQ4_STATUS_ADMIN_STATE_REVOKED | SEQ4_STATUS_LEASE_MOVED)) nfs41_handle_state_revoked(clp); - else if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED) + if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED) nfs41_handle_recallable_state_revoked(clp); - else if (flags & (SEQ4_STATUS_CB_PATH_DOWN | + if (flags & (SEQ4_STATUS_CB_PATH_DOWN | SEQ4_STATUS_BACKCHANNEL_FAULT | SEQ4_STATUS_CB_PATH_DOWN_SESSION)) nfs41_handle_cb_path_down(clp); @@ -1662,10 +1671,10 @@ static void nfs4_state_manager(struct nfs_client *clp) if (test_and_clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state)) { status = nfs4_check_lease(clp); + if (status < 0) + goto out_error; if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) continue; - if (status < 0 && status != -NFS4ERR_CB_PATH_DOWN) - goto out_error; } /* Initialize or reset the session */ diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 1dce12f41a4f..e6161b213ed1 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -6602,8 +6602,6 @@ static int nfs4_xdr_dec_secinfo(struct rpc_rqst *rqstp, if (status) goto out; status = decode_secinfo(xdr, res); - if (status) - goto out; out: return status; } diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index d0cda12fddc3..c807ab93140e 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -38,21 +38,15 @@ */ #include <linux/module.h> -#include <scsi/osd_initiator.h> +#include <scsi/osd_ore.h> #include "objlayout.h" #define NFSDBG_FACILITY NFSDBG_PNFS_LD -#define _LLU(x) ((unsigned long long)x) - -enum { BIO_MAX_PAGES_KMALLOC = - (PAGE_SIZE - sizeof(struct bio)) / sizeof(struct bio_vec), -}; - struct objio_dev_ent { struct nfs4_deviceid_node id_node; - struct osd_dev *od; + struct ore_dev od; }; static void @@ -60,8 +54,8 @@ objio_free_deviceid_node(struct nfs4_deviceid_node *d) { struct objio_dev_ent *de = container_of(d, struct objio_dev_ent, id_node); - dprintk("%s: free od=%p\n", __func__, de->od); - osduld_put_device(de->od); + dprintk("%s: free od=%p\n", __func__, de->od.od); + osduld_put_device(de->od.od); kfree(de); } @@ -98,12 +92,12 @@ _dev_list_add(const struct nfs_server *nfss, nfss->pnfs_curr_ld, nfss->nfs_client, d_id); - de->od = od; + de->od.od = od; d = nfs4_insert_deviceid_node(&de->id_node); n = container_of(d, struct objio_dev_ent, id_node); if (n != de) { - dprintk("%s: Race with other n->od=%p\n", __func__, n->od); + dprintk("%s: Race with other n->od=%p\n", __func__, n->od.od); objio_free_deviceid_node(&de->id_node); de = n; } @@ -111,28 +105,11 @@ _dev_list_add(const struct nfs_server *nfss, return de; } -struct caps_buffers { - u8 caps_key[OSD_CRYPTO_KEYID_SIZE]; - u8 creds[OSD_CAP_LEN]; -}; - struct objio_segment { struct pnfs_layout_segment lseg; - struct pnfs_osd_object_cred *comps; - - unsigned mirrors_p1; - unsigned stripe_unit; - unsigned group_width; /* Data stripe_units without integrity comps */ - u64 group_depth; - unsigned group_count; - - unsigned max_io_size; - - unsigned comps_index; - unsigned num_comps; - /* variable length */ - struct objio_dev_ent *ods[]; + struct ore_layout layout; + struct ore_components oc; }; static inline struct objio_segment * @@ -141,59 +118,44 @@ OBJIO_LSEG(struct pnfs_layout_segment *lseg) return container_of(lseg, struct objio_segment, lseg); } -struct objio_state; -typedef ssize_t (*objio_done_fn)(struct objio_state *ios); - struct objio_state { /* Generic layer */ - struct objlayout_io_state ol_state; - - struct objio_segment *layout; - - struct kref kref; - objio_done_fn done; - void *private; - - unsigned long length; - unsigned numdevs; /* Actually used devs in this IO */ - /* A per-device variable array of size numdevs */ - struct _objio_per_comp { - struct bio *bio; - struct osd_request *or; - unsigned long length; - u64 offset; - unsigned dev; - } per_dev[]; + struct objlayout_io_res oir; + + bool sync; + /*FIXME: Support for extra_bytes at ore_get_rw_state() */ + struct ore_io_state *ios; }; /* Send and wait for a get_device_info of devices in the layout, then look them up with the osd_initiator library */ -static struct objio_dev_ent *_device_lookup(struct pnfs_layout_hdr *pnfslay, - struct objio_segment *objio_seg, unsigned comp, - gfp_t gfp_flags) +static int objio_devices_lookup(struct pnfs_layout_hdr *pnfslay, + struct objio_segment *objio_seg, unsigned c, struct nfs4_deviceid *d_id, + gfp_t gfp_flags) { struct pnfs_osd_deviceaddr *deviceaddr; - struct nfs4_deviceid *d_id; struct objio_dev_ent *ode; struct osd_dev *od; struct osd_dev_info odi; int err; - d_id = &objio_seg->comps[comp].oc_object_id.oid_device_id; - ode = _dev_list_find(NFS_SERVER(pnfslay->plh_inode), d_id); - if (ode) - return ode; + if (ode) { + objio_seg->oc.ods[c] = &ode->od; /* must use container_of */ + return 0; + } err = objlayout_get_deviceinfo(pnfslay, d_id, &deviceaddr, gfp_flags); if (unlikely(err)) { dprintk("%s: objlayout_get_deviceinfo dev(%llx:%llx) =>%d\n", __func__, _DEVID_LO(d_id), _DEVID_HI(d_id), err); - return ERR_PTR(err); + return err; } odi.systemid_len = deviceaddr->oda_systemid.len; if (odi.systemid_len > sizeof(odi.systemid)) { + dprintk("%s: odi.systemid_len > sizeof(systemid=%zd)\n", + __func__, sizeof(odi.systemid)); err = -EINVAL; goto out; } else if (odi.systemid_len) @@ -218,96 +180,53 @@ static struct objio_dev_ent *_device_lookup(struct pnfs_layout_hdr *pnfslay, ode = _dev_list_add(NFS_SERVER(pnfslay->plh_inode), d_id, od, gfp_flags); - + objio_seg->oc.ods[c] = &ode->od; /* must use container_of */ + dprintk("Adding new dev_id(%llx:%llx)\n", + _DEVID_LO(d_id), _DEVID_HI(d_id)); out: - dprintk("%s: return=%d\n", __func__, err); objlayout_put_deviceinfo(deviceaddr); - return err ? ERR_PTR(err) : ode; + return err; } -static int objio_devices_lookup(struct pnfs_layout_hdr *pnfslay, - struct objio_segment *objio_seg, - gfp_t gfp_flags) +static void copy_single_comp(struct ore_components *oc, unsigned c, + struct pnfs_osd_object_cred *src_comp) { - unsigned i; - int err; + struct ore_comp *ocomp = &oc->comps[c]; - /* lookup all devices */ - for (i = 0; i < objio_seg->num_comps; i++) { - struct objio_dev_ent *ode; + WARN_ON(src_comp->oc_cap_key.cred_len > 0); /* libosd is NO_SEC only */ + WARN_ON(src_comp->oc_cap.cred_len > sizeof(ocomp->cred)); - ode = _device_lookup(pnfslay, objio_seg, i, gfp_flags); - if (unlikely(IS_ERR(ode))) { - err = PTR_ERR(ode); - goto out; - } - objio_seg->ods[i] = ode; - } - err = 0; + ocomp->obj.partition = src_comp->oc_object_id.oid_partition_id; + ocomp->obj.id = src_comp->oc_object_id.oid_object_id; -out: - dprintk("%s: return=%d\n", __func__, err); - return err; + memcpy(ocomp->cred, src_comp->oc_cap.cred, sizeof(ocomp->cred)); } -static int _verify_data_map(struct pnfs_osd_layout *layout) +int __alloc_objio_seg(unsigned numdevs, gfp_t gfp_flags, + struct objio_segment **pseg) { - struct pnfs_osd_data_map *data_map = &layout->olo_map; - u64 stripe_length; - u32 group_width; - -/* FIXME: Only raid0 for now. if not go through MDS */ - if (data_map->odm_raid_algorithm != PNFS_OSD_RAID_0) { - printk(KERN_ERR "Only RAID_0 for now\n"); - return -ENOTSUPP; - } - if (0 != (data_map->odm_num_comps % (data_map->odm_mirror_cnt + 1))) { - printk(KERN_ERR "Data Map wrong, num_comps=%u mirrors=%u\n", - data_map->odm_num_comps, data_map->odm_mirror_cnt); - return -EINVAL; - } + struct __alloc_objio_segment { + struct objio_segment olseg; + struct ore_dev *ods[numdevs]; + struct ore_comp comps[numdevs]; + } *aolseg; - if (data_map->odm_group_width) - group_width = data_map->odm_group_width; - else - group_width = data_map->odm_num_comps / - (data_map->odm_mirror_cnt + 1); - - stripe_length = (u64)data_map->odm_stripe_unit * group_width; - if (stripe_length >= (1ULL << 32)) { - printk(KERN_ERR "Total Stripe length(0x%llx)" - " >= 32bit is not supported\n", _LLU(stripe_length)); - return -ENOTSUPP; + aolseg = kzalloc(sizeof(*aolseg), gfp_flags); + if (unlikely(!aolseg)) { + dprintk("%s: Faild allocation numdevs=%d size=%zd\n", __func__, + numdevs, sizeof(*aolseg)); + return -ENOMEM; } - if (0 != (data_map->odm_stripe_unit & ~PAGE_MASK)) { - printk(KERN_ERR "Stripe Unit(0x%llx)" - " must be Multples of PAGE_SIZE(0x%lx)\n", - _LLU(data_map->odm_stripe_unit), PAGE_SIZE); - return -ENOTSUPP; - } + aolseg->olseg.oc.numdevs = numdevs; + aolseg->olseg.oc.single_comp = EC_MULTPLE_COMPS; + aolseg->olseg.oc.comps = aolseg->comps; + aolseg->olseg.oc.ods = aolseg->ods; + *pseg = &aolseg->olseg; return 0; } -static void copy_single_comp(struct pnfs_osd_object_cred *cur_comp, - struct pnfs_osd_object_cred *src_comp, - struct caps_buffers *caps_p) -{ - WARN_ON(src_comp->oc_cap_key.cred_len > sizeof(caps_p->caps_key)); - WARN_ON(src_comp->oc_cap.cred_len > sizeof(caps_p->creds)); - - *cur_comp = *src_comp; - - memcpy(caps_p->caps_key, src_comp->oc_cap_key.cred, - sizeof(caps_p->caps_key)); - cur_comp->oc_cap_key.cred = caps_p->caps_key; - - memcpy(caps_p->creds, src_comp->oc_cap.cred, - sizeof(caps_p->creds)); - cur_comp->oc_cap.cred = caps_p->creds; -} - int objio_alloc_lseg(struct pnfs_layout_segment **outp, struct pnfs_layout_hdr *pnfslay, struct pnfs_layout_range *range, @@ -317,59 +236,43 @@ int objio_alloc_lseg(struct pnfs_layout_segment **outp, struct objio_segment *objio_seg; struct pnfs_osd_xdr_decode_layout_iter iter; struct pnfs_osd_layout layout; - struct pnfs_osd_object_cred *cur_comp, src_comp; - struct caps_buffers *caps_p; + struct pnfs_osd_object_cred src_comp; + unsigned cur_comp; int err; err = pnfs_osd_xdr_decode_layout_map(&layout, &iter, xdr); if (unlikely(err)) return err; - err = _verify_data_map(&layout); + err = __alloc_objio_seg(layout.olo_num_comps, gfp_flags, &objio_seg); if (unlikely(err)) return err; - objio_seg = kzalloc(sizeof(*objio_seg) + - sizeof(objio_seg->ods[0]) * layout.olo_num_comps + - sizeof(*objio_seg->comps) * layout.olo_num_comps + - sizeof(struct caps_buffers) * layout.olo_num_comps, - gfp_flags); - if (!objio_seg) - return -ENOMEM; + objio_seg->layout.stripe_unit = layout.olo_map.odm_stripe_unit; + objio_seg->layout.group_width = layout.olo_map.odm_group_width; + objio_seg->layout.group_depth = layout.olo_map.odm_group_depth; + objio_seg->layout.mirrors_p1 = layout.olo_map.odm_mirror_cnt + 1; + objio_seg->layout.raid_algorithm = layout.olo_map.odm_raid_algorithm; - objio_seg->comps = (void *)(objio_seg->ods + layout.olo_num_comps); - cur_comp = objio_seg->comps; - caps_p = (void *)(cur_comp + layout.olo_num_comps); - while (pnfs_osd_xdr_decode_layout_comp(&src_comp, &iter, xdr, &err)) - copy_single_comp(cur_comp++, &src_comp, caps_p++); + err = ore_verify_layout(layout.olo_map.odm_num_comps, + &objio_seg->layout); if (unlikely(err)) goto err; - objio_seg->num_comps = layout.olo_num_comps; - objio_seg->comps_index = layout.olo_comps_index; - err = objio_devices_lookup(pnfslay, objio_seg, gfp_flags); - if (err) - goto err; - - objio_seg->mirrors_p1 = layout.olo_map.odm_mirror_cnt + 1; - objio_seg->stripe_unit = layout.olo_map.odm_stripe_unit; - if (layout.olo_map.odm_group_width) { - objio_seg->group_width = layout.olo_map.odm_group_width; - objio_seg->group_depth = layout.olo_map.odm_group_depth; - objio_seg->group_count = layout.olo_map.odm_num_comps / - objio_seg->mirrors_p1 / - objio_seg->group_width; - } else { - objio_seg->group_width = layout.olo_map.odm_num_comps / - objio_seg->mirrors_p1; - objio_seg->group_depth = -1; - objio_seg->group_count = 1; + objio_seg->oc.first_dev = layout.olo_comps_index; + cur_comp = 0; + while (pnfs_osd_xdr_decode_layout_comp(&src_comp, &iter, xdr, &err)) { + copy_single_comp(&objio_seg->oc, cur_comp, &src_comp); + err = objio_devices_lookup(pnfslay, objio_seg, cur_comp, + &src_comp.oc_object_id.oid_device_id, + gfp_flags); + if (err) + goto err; + ++cur_comp; } - - /* Cache this calculation it will hit for every page */ - objio_seg->max_io_size = (BIO_MAX_PAGES_KMALLOC * PAGE_SIZE - - objio_seg->stripe_unit) * - objio_seg->group_width; + /* pnfs_osd_xdr_decode_layout_comp returns false on error */ + if (unlikely(err)) + goto err; *outp = &objio_seg->lseg; return 0; @@ -386,43 +289,63 @@ void objio_free_lseg(struct pnfs_layout_segment *lseg) int i; struct objio_segment *objio_seg = OBJIO_LSEG(lseg); - for (i = 0; i < objio_seg->num_comps; i++) { - if (!objio_seg->ods[i]) + for (i = 0; i < objio_seg->oc.numdevs; i++) { + struct ore_dev *od = objio_seg->oc.ods[i]; + struct objio_dev_ent *ode; + + if (!od) break; - nfs4_put_deviceid_node(&objio_seg->ods[i]->id_node); + ode = container_of(od, typeof(*ode), od); + nfs4_put_deviceid_node(&ode->id_node); } kfree(objio_seg); } -int objio_alloc_io_state(struct pnfs_layout_segment *lseg, - struct objlayout_io_state **outp, - gfp_t gfp_flags) +static int +objio_alloc_io_state(struct pnfs_layout_hdr *pnfs_layout_type, bool is_reading, + struct pnfs_layout_segment *lseg, struct page **pages, unsigned pgbase, + loff_t offset, size_t count, void *rpcdata, gfp_t gfp_flags, + struct objio_state **outp) { struct objio_segment *objio_seg = OBJIO_LSEG(lseg); - struct objio_state *ios; - const unsigned first_size = sizeof(*ios) + - objio_seg->num_comps * sizeof(ios->per_dev[0]); - const unsigned sec_size = objio_seg->num_comps * - sizeof(ios->ol_state.ioerrs[0]); - - ios = kzalloc(first_size + sec_size, gfp_flags); - if (unlikely(!ios)) + struct ore_io_state *ios; + int ret; + struct __alloc_objio_state { + struct objio_state objios; + struct pnfs_osd_ioerr ioerrs[objio_seg->oc.numdevs]; + } *aos; + + aos = kzalloc(sizeof(*aos), gfp_flags); + if (unlikely(!aos)) return -ENOMEM; - ios->layout = objio_seg; - ios->ol_state.ioerrs = ((void *)ios) + first_size; - ios->ol_state.num_comps = objio_seg->num_comps; + objlayout_init_ioerrs(&aos->objios.oir, objio_seg->oc.numdevs, + aos->ioerrs, rpcdata, pnfs_layout_type); - *outp = &ios->ol_state; + ret = ore_get_rw_state(&objio_seg->layout, &objio_seg->oc, is_reading, + offset, count, &ios); + if (unlikely(ret)) { + kfree(aos); + return ret; + } + + ios->pages = pages; + ios->pgbase = pgbase; + ios->private = aos; + BUG_ON(ios->nr_pages > (pgbase + count + PAGE_SIZE - 1) >> PAGE_SHIFT); + + aos->objios.sync = 0; + aos->objios.ios = ios; + *outp = &aos->objios; return 0; } -void objio_free_io_state(struct objlayout_io_state *ol_state) +void objio_free_result(struct objlayout_io_res *oir) { - struct objio_state *ios = container_of(ol_state, struct objio_state, - ol_state); + struct objio_state *objios = container_of(oir, struct objio_state, oir); - kfree(ios); + ore_put_io_state(objios->ios); + kfree(objios); } enum pnfs_osd_errno osd_pri_2_pnfs_err(enum osd_err_priority oep) @@ -455,539 +378,152 @@ enum pnfs_osd_errno osd_pri_2_pnfs_err(enum osd_err_priority oep) } } -static void _clear_bio(struct bio *bio) +static void __on_dev_error(struct ore_io_state *ios, + struct ore_dev *od, unsigned dev_index, enum osd_err_priority oep, + u64 dev_offset, u64 dev_len) { - struct bio_vec *bv; - unsigned i; - - __bio_for_each_segment(bv, bio, i, 0) { - unsigned this_count = bv->bv_len; - - if (likely(PAGE_SIZE == this_count)) - clear_highpage(bv->bv_page); - else - zero_user(bv->bv_page, bv->bv_offset, this_count); - } -} - -static int _io_check(struct objio_state *ios, bool is_write) -{ - enum osd_err_priority oep = OSD_ERR_PRI_NO_ERROR; - int lin_ret = 0; - int i; - - for (i = 0; i < ios->numdevs; i++) { - struct osd_sense_info osi; - struct osd_request *or = ios->per_dev[i].or; - int ret; - - if (!or) - continue; + struct objio_state *objios = ios->private; + struct pnfs_osd_objid pooid; + struct objio_dev_ent *ode = container_of(od, typeof(*ode), od); + /* FIXME: what to do with more-then-one-group layouts. We need to + * translate from ore_io_state index to oc->comps index + */ + unsigned comp = dev_index; - ret = osd_req_decode_sense(or, &osi); - if (likely(!ret)) - continue; + pooid.oid_device_id = ode->id_node.deviceid; + pooid.oid_partition_id = ios->oc->comps[comp].obj.partition; + pooid.oid_object_id = ios->oc->comps[comp].obj.id; - if (OSD_ERR_PRI_CLEAR_PAGES == osi.osd_err_pri) { - /* start read offset passed endof file */ - BUG_ON(is_write); - _clear_bio(ios->per_dev[i].bio); - dprintk("%s: start read offset passed end of file " - "offset=0x%llx, length=0x%lx\n", __func__, - _LLU(ios->per_dev[i].offset), - ios->per_dev[i].length); - - continue; /* we recovered */ - } - objlayout_io_set_result(&ios->ol_state, i, - &ios->layout->comps[i].oc_object_id, - osd_pri_2_pnfs_err(osi.osd_err_pri), - ios->per_dev[i].offset, - ios->per_dev[i].length, - is_write); - - if (osi.osd_err_pri >= oep) { - oep = osi.osd_err_pri; - lin_ret = ret; - } - } - - return lin_ret; -} - -/* - * Common IO state helpers. - */ -static void _io_free(struct objio_state *ios) -{ - unsigned i; - - for (i = 0; i < ios->numdevs; i++) { - struct _objio_per_comp *per_dev = &ios->per_dev[i]; - - if (per_dev->or) { - osd_end_request(per_dev->or); - per_dev->or = NULL; - } - - if (per_dev->bio) { - bio_put(per_dev->bio); - per_dev->bio = NULL; - } - } -} - -struct osd_dev *_io_od(struct objio_state *ios, unsigned dev) -{ - unsigned min_dev = ios->layout->comps_index; - unsigned max_dev = min_dev + ios->layout->num_comps; - - BUG_ON(dev < min_dev || max_dev <= dev); - return ios->layout->ods[dev - min_dev]->od; -} - -struct _striping_info { - u64 obj_offset; - u64 group_length; - unsigned dev; - unsigned unit_off; -}; - -static void _calc_stripe_info(struct objio_state *ios, u64 file_offset, - struct _striping_info *si) -{ - u32 stripe_unit = ios->layout->stripe_unit; - u32 group_width = ios->layout->group_width; - u64 group_depth = ios->layout->group_depth; - u32 U = stripe_unit * group_width; - - u64 T = U * group_depth; - u64 S = T * ios->layout->group_count; - u64 M = div64_u64(file_offset, S); - - /* - G = (L - (M * S)) / T - H = (L - (M * S)) % T - */ - u64 LmodU = file_offset - M * S; - u32 G = div64_u64(LmodU, T); - u64 H = LmodU - G * T; - - u32 N = div_u64(H, U); - - div_u64_rem(file_offset, stripe_unit, &si->unit_off); - si->obj_offset = si->unit_off + (N * stripe_unit) + - (M * group_depth * stripe_unit); - - /* "H - (N * U)" is just "H % U" so it's bound to u32 */ - si->dev = (u32)(H - (N * U)) / stripe_unit + G * group_width; - si->dev *= ios->layout->mirrors_p1; - - si->group_length = T - H; -} - -static int _add_stripe_unit(struct objio_state *ios, unsigned *cur_pg, - unsigned pgbase, struct _objio_per_comp *per_dev, int len, - gfp_t gfp_flags) -{ - unsigned pg = *cur_pg; - int cur_len = len; - struct request_queue *q = - osd_request_queue(_io_od(ios, per_dev->dev)); - - if (per_dev->bio == NULL) { - unsigned pages_in_stripe = ios->layout->group_width * - (ios->layout->stripe_unit / PAGE_SIZE); - unsigned bio_size = (ios->ol_state.nr_pages + pages_in_stripe) / - ios->layout->group_width; - - if (BIO_MAX_PAGES_KMALLOC < bio_size) - bio_size = BIO_MAX_PAGES_KMALLOC; - - per_dev->bio = bio_kmalloc(gfp_flags, bio_size); - if (unlikely(!per_dev->bio)) { - dprintk("Faild to allocate BIO size=%u\n", bio_size); - return -ENOMEM; - } - } - - while (cur_len > 0) { - unsigned pglen = min_t(unsigned, PAGE_SIZE - pgbase, cur_len); - unsigned added_len; - - BUG_ON(ios->ol_state.nr_pages <= pg); - cur_len -= pglen; - - added_len = bio_add_pc_page(q, per_dev->bio, - ios->ol_state.pages[pg], pglen, pgbase); - if (unlikely(pglen != added_len)) - return -ENOMEM; - pgbase = 0; - ++pg; - } - BUG_ON(cur_len); - - per_dev->length += len; - *cur_pg = pg; - return 0; -} - -static int _prepare_one_group(struct objio_state *ios, u64 length, - struct _striping_info *si, unsigned *last_pg, - gfp_t gfp_flags) -{ - unsigned stripe_unit = ios->layout->stripe_unit; - unsigned mirrors_p1 = ios->layout->mirrors_p1; - unsigned devs_in_group = ios->layout->group_width * mirrors_p1; - unsigned dev = si->dev; - unsigned first_dev = dev - (dev % devs_in_group); - unsigned max_comp = ios->numdevs ? ios->numdevs - mirrors_p1 : 0; - unsigned cur_pg = *last_pg; - int ret = 0; - - while (length) { - struct _objio_per_comp *per_dev = &ios->per_dev[dev - first_dev]; - unsigned cur_len, page_off = 0; - - if (!per_dev->length) { - per_dev->dev = dev; - if (dev < si->dev) { - per_dev->offset = si->obj_offset + stripe_unit - - si->unit_off; - cur_len = stripe_unit; - } else if (dev == si->dev) { - per_dev->offset = si->obj_offset; - cur_len = stripe_unit - si->unit_off; - page_off = si->unit_off & ~PAGE_MASK; - BUG_ON(page_off && - (page_off != ios->ol_state.pgbase)); - } else { /* dev > si->dev */ - per_dev->offset = si->obj_offset - si->unit_off; - cur_len = stripe_unit; - } - - if (max_comp < dev - first_dev) - max_comp = dev - first_dev; - } else { - cur_len = stripe_unit; - } - if (cur_len >= length) - cur_len = length; - - ret = _add_stripe_unit(ios, &cur_pg, page_off , per_dev, - cur_len, gfp_flags); - if (unlikely(ret)) - goto out; - - dev += mirrors_p1; - dev = (dev % devs_in_group) + first_dev; - - length -= cur_len; - ios->length += cur_len; - } -out: - ios->numdevs = max_comp + mirrors_p1; - *last_pg = cur_pg; - return ret; -} - -static int _io_rw_pagelist(struct objio_state *ios, gfp_t gfp_flags) -{ - u64 length = ios->ol_state.count; - u64 offset = ios->ol_state.offset; - struct _striping_info si; - unsigned last_pg = 0; - int ret = 0; - - while (length) { - _calc_stripe_info(ios, offset, &si); - - if (length < si.group_length) - si.group_length = length; - - ret = _prepare_one_group(ios, si.group_length, &si, &last_pg, gfp_flags); - if (unlikely(ret)) - goto out; - - offset += si.group_length; - length -= si.group_length; - } - -out: - if (!ios->length) - return ret; - - return 0; -} - -static ssize_t _sync_done(struct objio_state *ios) -{ - struct completion *waiting = ios->private; - - complete(waiting); - return 0; -} - -static void _last_io(struct kref *kref) -{ - struct objio_state *ios = container_of(kref, struct objio_state, kref); - - ios->done(ios); -} - -static void _done_io(struct osd_request *or, void *p) -{ - struct objio_state *ios = p; - - kref_put(&ios->kref, _last_io); -} - -static ssize_t _io_exec(struct objio_state *ios) -{ - DECLARE_COMPLETION_ONSTACK(wait); - ssize_t status = 0; /* sync status */ - unsigned i; - objio_done_fn saved_done_fn = ios->done; - bool sync = ios->ol_state.sync; - - if (sync) { - ios->done = _sync_done; - ios->private = &wait; - } - - kref_init(&ios->kref); - - for (i = 0; i < ios->numdevs; i++) { - struct osd_request *or = ios->per_dev[i].or; - - if (!or) - continue; - - kref_get(&ios->kref); - osd_execute_request_async(or, _done_io, ios); - } - - kref_put(&ios->kref, _last_io); - - if (sync) { - wait_for_completion(&wait); - status = saved_done_fn(ios); - } - - return status; + objlayout_io_set_result(&objios->oir, comp, + &pooid, osd_pri_2_pnfs_err(oep), + dev_offset, dev_len, !ios->reading); } /* * read */ -static ssize_t _read_done(struct objio_state *ios) +static void _read_done(struct ore_io_state *ios, void *private) { + struct objio_state *objios = private; ssize_t status; - int ret = _io_check(ios, false); + int ret = ore_check_io(ios, &__on_dev_error); - _io_free(ios); + /* FIXME: _io_free(ios) can we dealocate the libosd resources; */ if (likely(!ret)) status = ios->length; else status = ret; - objlayout_read_done(&ios->ol_state, status, ios->ol_state.sync); - return status; + objlayout_read_done(&objios->oir, status, objios->sync); } -static int _read_mirrors(struct objio_state *ios, unsigned cur_comp) +int objio_read_pagelist(struct nfs_read_data *rdata) { - struct osd_request *or = NULL; - struct _objio_per_comp *per_dev = &ios->per_dev[cur_comp]; - unsigned dev = per_dev->dev; - struct pnfs_osd_object_cred *cred = - &ios->layout->comps[cur_comp]; - struct osd_obj_id obj = { - .partition = cred->oc_object_id.oid_partition_id, - .id = cred->oc_object_id.oid_object_id, - }; + struct objio_state *objios; int ret; - or = osd_start_request(_io_od(ios, dev), GFP_KERNEL); - if (unlikely(!or)) { - ret = -ENOMEM; - goto err; - } - per_dev->or = or; - - osd_req_read(or, &obj, per_dev->offset, per_dev->bio, per_dev->length); - - ret = osd_finalize_request(or, 0, cred->oc_cap.cred, NULL); - if (ret) { - dprintk("%s: Faild to osd_finalize_request() => %d\n", - __func__, ret); - goto err; - } - - dprintk("%s:[%d] dev=%d obj=0x%llx start=0x%llx length=0x%lx\n", - __func__, cur_comp, dev, obj.id, _LLU(per_dev->offset), - per_dev->length); - -err: - return ret; -} - -static ssize_t _read_exec(struct objio_state *ios) -{ - unsigned i; - int ret; - - for (i = 0; i < ios->numdevs; i += ios->layout->mirrors_p1) { - if (!ios->per_dev[i].length) - continue; - ret = _read_mirrors(ios, i); - if (unlikely(ret)) - goto err; - } - - ios->done = _read_done; - return _io_exec(ios); /* In sync mode exec returns the io status */ - -err: - _io_free(ios); - return ret; -} - -ssize_t objio_read_pagelist(struct objlayout_io_state *ol_state) -{ - struct objio_state *ios = container_of(ol_state, struct objio_state, - ol_state); - int ret; - - ret = _io_rw_pagelist(ios, GFP_KERNEL); + ret = objio_alloc_io_state(NFS_I(rdata->inode)->layout, true, + rdata->lseg, rdata->args.pages, rdata->args.pgbase, + rdata->args.offset, rdata->args.count, rdata, + GFP_KERNEL, &objios); if (unlikely(ret)) return ret; - return _read_exec(ios); + objios->ios->done = _read_done; + dprintk("%s: offset=0x%llx length=0x%x\n", __func__, + rdata->args.offset, rdata->args.count); + return ore_read(objios->ios); } /* * write */ -static ssize_t _write_done(struct objio_state *ios) +static void _write_done(struct ore_io_state *ios, void *private) { + struct objio_state *objios = private; ssize_t status; - int ret = _io_check(ios, true); + int ret = ore_check_io(ios, &__on_dev_error); - _io_free(ios); + /* FIXME: _io_free(ios) can we dealocate the libosd resources; */ if (likely(!ret)) { /* FIXME: should be based on the OSD's persistence model * See OSD2r05 Section 4.13 Data persistence model */ - ios->ol_state.committed = NFS_FILE_SYNC; + objios->oir.committed = NFS_FILE_SYNC; status = ios->length; } else { status = ret; } - objlayout_write_done(&ios->ol_state, status, ios->ol_state.sync); - return status; + objlayout_write_done(&objios->oir, status, objios->sync); } -static int _write_mirrors(struct objio_state *ios, unsigned cur_comp) +static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) { - struct _objio_per_comp *master_dev = &ios->per_dev[cur_comp]; - unsigned dev = ios->per_dev[cur_comp].dev; - unsigned last_comp = cur_comp + ios->layout->mirrors_p1; - int ret; - - for (; cur_comp < last_comp; ++cur_comp, ++dev) { - struct osd_request *or = NULL; - struct pnfs_osd_object_cred *cred = - &ios->layout->comps[cur_comp]; - struct osd_obj_id obj = { - .partition = cred->oc_object_id.oid_partition_id, - .id = cred->oc_object_id.oid_object_id, - }; - struct _objio_per_comp *per_dev = &ios->per_dev[cur_comp]; - struct bio *bio; - - or = osd_start_request(_io_od(ios, dev), GFP_NOFS); - if (unlikely(!or)) { - ret = -ENOMEM; - goto err; - } - per_dev->or = or; - - if (per_dev != master_dev) { - bio = bio_kmalloc(GFP_NOFS, - master_dev->bio->bi_max_vecs); - if (unlikely(!bio)) { - dprintk("Faild to allocate BIO size=%u\n", - master_dev->bio->bi_max_vecs); - ret = -ENOMEM; - goto err; - } - - __bio_clone(bio, master_dev->bio); - bio->bi_bdev = NULL; - bio->bi_next = NULL; - per_dev->bio = bio; - per_dev->dev = dev; - per_dev->length = master_dev->length; - per_dev->offset = master_dev->offset; - } else { - bio = master_dev->bio; - bio->bi_rw |= REQ_WRITE; - } - - osd_req_write(or, &obj, per_dev->offset, bio, per_dev->length); + struct objio_state *objios = priv; + struct nfs_write_data *wdata = objios->oir.rpcdata; + pgoff_t index = offset / PAGE_SIZE; + struct page *page = find_get_page(wdata->inode->i_mapping, index); - ret = osd_finalize_request(or, 0, cred->oc_cap.cred, NULL); - if (ret) { - dprintk("%s: Faild to osd_finalize_request() => %d\n", - __func__, ret); - goto err; + if (!page) { + page = find_or_create_page(wdata->inode->i_mapping, + index, GFP_NOFS); + if (unlikely(!page)) { + dprintk("%s: grab_cache_page Failed index=0x%lx\n", + __func__, index); + return NULL; } - - dprintk("%s:[%d] dev=%d obj=0x%llx start=0x%llx length=0x%lx\n", - __func__, cur_comp, dev, obj.id, _LLU(per_dev->offset), - per_dev->length); + unlock_page(page); } + if (PageDirty(page) || PageWriteback(page)) + *uptodate = true; + else + *uptodate = PageUptodate(page); + dprintk("%s: index=0x%lx uptodate=%d\n", __func__, index, *uptodate); + return page; +} -err: - return ret; +static void __r4w_put_page(void *priv, struct page *page) +{ + dprintk("%s: index=0x%lx\n", __func__, page->index); + page_cache_release(page); + return; } -static ssize_t _write_exec(struct objio_state *ios) +static const struct _ore_r4w_op _r4w_op = { + .get_page = &__r4w_get_page, + .put_page = &__r4w_put_page, +}; + +int objio_write_pagelist(struct nfs_write_data *wdata, int how) { - unsigned i; + struct objio_state *objios; int ret; - for (i = 0; i < ios->numdevs; i += ios->layout->mirrors_p1) { - if (!ios->per_dev[i].length) - continue; - ret = _write_mirrors(ios, i); - if (unlikely(ret)) - goto err; - } - - ios->done = _write_done; - return _io_exec(ios); /* In sync mode exec returns the io->status */ + ret = objio_alloc_io_state(NFS_I(wdata->inode)->layout, false, + wdata->lseg, wdata->args.pages, wdata->args.pgbase, + wdata->args.offset, wdata->args.count, wdata, GFP_NOFS, + &objios); + if (unlikely(ret)) + return ret; -err: - _io_free(ios); - return ret; -} + objios->sync = 0 != (how & FLUSH_SYNC); + objios->ios->r4w = &_r4w_op; -ssize_t objio_write_pagelist(struct objlayout_io_state *ol_state, bool stable) -{ - struct objio_state *ios = container_of(ol_state, struct objio_state, - ol_state); - int ret; + if (!objios->sync) + objios->ios->done = _write_done; - /* TODO: ios->stable = stable; */ - ret = _io_rw_pagelist(ios, GFP_NOFS); + dprintk("%s: offset=0x%llx length=0x%x\n", __func__, + wdata->args.offset, wdata->args.count); + ret = ore_write(objios->ios); if (unlikely(ret)) return ret; - return _write_exec(ios); + if (objios->sync) + _write_done(objios->ios, objios); + + return 0; } static bool objio_pg_test(struct nfs_pageio_descriptor *pgio, @@ -997,7 +533,7 @@ static bool objio_pg_test(struct nfs_pageio_descriptor *pgio, return false; return pgio->pg_count + req->wb_bytes <= - OBJIO_LSEG(pgio->pg_lseg)->max_io_size; + OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length; } static const struct nfs_pageio_ops objio_pg_read_ops = { diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c index 1d06f8e2adea..72074e3a04f9 100644 --- a/fs/nfs/objlayout/objlayout.c +++ b/fs/nfs/objlayout/objlayout.c @@ -156,77 +156,39 @@ last_byte_offset(u64 start, u64 len) return end > start ? end - 1 : NFS4_MAX_UINT64; } -static struct objlayout_io_state * -objlayout_alloc_io_state(struct pnfs_layout_hdr *pnfs_layout_type, - struct page **pages, - unsigned pgbase, - loff_t offset, - size_t count, - struct pnfs_layout_segment *lseg, - void *rpcdata, - gfp_t gfp_flags) +void _fix_verify_io_params(struct pnfs_layout_segment *lseg, + struct page ***p_pages, unsigned *p_pgbase, + u64 offset, unsigned long count) { - struct objlayout_io_state *state; u64 lseg_end_offset; - dprintk("%s: allocating io_state\n", __func__); - if (objio_alloc_io_state(lseg, &state, gfp_flags)) - return NULL; - BUG_ON(offset < lseg->pls_range.offset); lseg_end_offset = end_offset(lseg->pls_range.offset, lseg->pls_range.length); BUG_ON(offset >= lseg_end_offset); - if (offset + count > lseg_end_offset) { - count = lseg->pls_range.length - - (offset - lseg->pls_range.offset); - dprintk("%s: truncated count %Zd\n", __func__, count); - } + WARN_ON(offset + count > lseg_end_offset); - if (pgbase > PAGE_SIZE) { - pages += pgbase >> PAGE_SHIFT; - pgbase &= ~PAGE_MASK; + if (*p_pgbase > PAGE_SIZE) { + dprintk("%s: pgbase(0x%x) > PAGE_SIZE\n", __func__, *p_pgbase); + *p_pages += *p_pgbase >> PAGE_SHIFT; + *p_pgbase &= ~PAGE_MASK; } - - INIT_LIST_HEAD(&state->err_list); - state->lseg = lseg; - state->rpcdata = rpcdata; - state->pages = pages; - state->pgbase = pgbase; - state->nr_pages = (pgbase + count + PAGE_SIZE - 1) >> PAGE_SHIFT; - state->offset = offset; - state->count = count; - state->sync = 0; - - return state; -} - -static void -objlayout_free_io_state(struct objlayout_io_state *state) -{ - dprintk("%s: freeing io_state\n", __func__); - if (unlikely(!state)) - return; - - objio_free_io_state(state); } /* * I/O done common code */ static void -objlayout_iodone(struct objlayout_io_state *state) +objlayout_iodone(struct objlayout_io_res *oir) { - dprintk("%s: state %p status\n", __func__, state); - - if (likely(state->status >= 0)) { - objlayout_free_io_state(state); + if (likely(oir->status >= 0)) { + objio_free_result(oir); } else { - struct objlayout *objlay = OBJLAYOUT(state->lseg->pls_layout); + struct objlayout *objlay = oir->objlay; spin_lock(&objlay->lock); objlay->delta_space_valid = OBJ_DSU_INVALID; - list_add(&objlay->err_list, &state->err_list); + list_add(&objlay->err_list, &oir->err_list); spin_unlock(&objlay->lock); } } @@ -238,13 +200,13 @@ objlayout_iodone(struct objlayout_io_state *state) * the error for later reporting at layout-return. */ void -objlayout_io_set_result(struct objlayout_io_state *state, unsigned index, +objlayout_io_set_result(struct objlayout_io_res *oir, unsigned index, struct pnfs_osd_objid *pooid, int osd_error, u64 offset, u64 length, bool is_write) { - struct pnfs_osd_ioerr *ioerr = &state->ioerrs[index]; + struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[index]; - BUG_ON(index >= state->num_comps); + BUG_ON(index >= oir->num_comps); if (osd_error) { ioerr->oer_component = *pooid; ioerr->oer_comp_offset = offset; @@ -285,21 +247,18 @@ static void _rpc_read_complete(struct work_struct *work) } void -objlayout_read_done(struct objlayout_io_state *state, ssize_t status, bool sync) +objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync) { - int eof = state->eof; - struct nfs_read_data *rdata; + struct nfs_read_data *rdata = oir->rpcdata; - state->status = status; - dprintk("%s: Begin status=%zd eof=%d\n", __func__, status, eof); - rdata = state->rpcdata; - rdata->task.tk_status = status; - if (status >= 0) { + oir->status = rdata->task.tk_status = status; + if (status >= 0) rdata->res.count = status; - rdata->res.eof = eof; - } - objlayout_iodone(state); - /* must not use state after this point */ + objlayout_iodone(oir); + /* must not use oir after this point */ + + dprintk("%s: Return status=%zd eof=%d sync=%d\n", __func__, + status, rdata->res.eof, sync); if (sync) pnfs_ld_read_done(rdata); @@ -317,40 +276,36 @@ objlayout_read_pagelist(struct nfs_read_data *rdata) { loff_t offset = rdata->args.offset; size_t count = rdata->args.count; - struct objlayout_io_state *state; - ssize_t status = 0; + int err; loff_t eof; - dprintk("%s: Begin inode %p offset %llu count %d\n", - __func__, rdata->inode, offset, (int)count); - eof = i_size_read(rdata->inode); if (unlikely(offset + count > eof)) { if (offset >= eof) { - status = 0; + err = 0; rdata->res.count = 0; rdata->res.eof = 1; + /*FIXME: do we need to call pnfs_ld_read_done() */ goto out; } count = eof - offset; } - state = objlayout_alloc_io_state(NFS_I(rdata->inode)->layout, - rdata->args.pages, rdata->args.pgbase, - offset, count, - rdata->lseg, rdata, - GFP_KERNEL); - if (unlikely(!state)) { - status = -ENOMEM; - goto out; - } + rdata->res.eof = (offset + count) >= eof; + _fix_verify_io_params(rdata->lseg, &rdata->args.pages, + &rdata->args.pgbase, + rdata->args.offset, rdata->args.count); - state->eof = state->offset + state->count >= eof; + dprintk("%s: inode(%lx) offset 0x%llx count 0x%Zx eof=%d\n", + __func__, rdata->inode->i_ino, offset, count, rdata->res.eof); - status = objio_read_pagelist(state); + err = objio_read_pagelist(rdata); out: - dprintk("%s: Return status %Zd\n", __func__, status); - rdata->pnfs_error = status; + if (unlikely(err)) { + rdata->pnfs_error = err; + dprintk("%s: Returned Error %d\n", __func__, err); + return PNFS_NOT_ATTEMPTED; + } return PNFS_ATTEMPTED; } @@ -371,26 +326,20 @@ static void _rpc_write_complete(struct work_struct *work) } void -objlayout_write_done(struct objlayout_io_state *state, ssize_t status, - bool sync) +objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync) { - struct nfs_write_data *wdata; + struct nfs_write_data *wdata = oir->rpcdata; - dprintk("%s: Begin\n", __func__); - wdata = state->rpcdata; - state->status = status; - wdata->task.tk_status = status; + oir->status = wdata->task.tk_status = status; if (status >= 0) { wdata->res.count = status; - wdata->verf.committed = state->committed; - dprintk("%s: Return status %d committed %d\n", - __func__, wdata->task.tk_status, - wdata->verf.committed); - } else - dprintk("%s: Return status %d\n", - __func__, wdata->task.tk_status); - objlayout_iodone(state); - /* must not use state after this point */ + wdata->verf.committed = oir->committed; + } + objlayout_iodone(oir); + /* must not use oir after this point */ + + dprintk("%s: Return status %zd committed %d sync=%d\n", __func__, + status, wdata->verf.committed, sync); if (sync) pnfs_ld_write_done(wdata); @@ -407,30 +356,18 @@ enum pnfs_try_status objlayout_write_pagelist(struct nfs_write_data *wdata, int how) { - struct objlayout_io_state *state; - ssize_t status; - - dprintk("%s: Begin inode %p offset %llu count %u\n", - __func__, wdata->inode, wdata->args.offset, wdata->args.count); - - state = objlayout_alloc_io_state(NFS_I(wdata->inode)->layout, - wdata->args.pages, - wdata->args.pgbase, - wdata->args.offset, - wdata->args.count, - wdata->lseg, wdata, - GFP_NOFS); - if (unlikely(!state)) { - status = -ENOMEM; - goto out; - } + int err; - state->sync = how & FLUSH_SYNC; + _fix_verify_io_params(wdata->lseg, &wdata->args.pages, + &wdata->args.pgbase, + wdata->args.offset, wdata->args.count); - status = objio_write_pagelist(state, how & FLUSH_STABLE); - out: - dprintk("%s: Return status %Zd\n", __func__, status); - wdata->pnfs_error = status; + err = objio_write_pagelist(wdata, how); + if (unlikely(err)) { + wdata->pnfs_error = err; + dprintk("%s: Returned Error %d\n", __func__, err); + return PNFS_NOT_ATTEMPTED; + } return PNFS_ATTEMPTED; } @@ -537,14 +474,14 @@ merge_ioerr(struct pnfs_osd_ioerr *dest_err, static void encode_accumulated_error(struct objlayout *objlay, __be32 *p) { - struct objlayout_io_state *state, *tmp; + struct objlayout_io_res *oir, *tmp; struct pnfs_osd_ioerr accumulated_err = {.oer_errno = 0}; - list_for_each_entry_safe(state, tmp, &objlay->err_list, err_list) { + list_for_each_entry_safe(oir, tmp, &objlay->err_list, err_list) { unsigned i; - for (i = 0; i < state->num_comps; i++) { - struct pnfs_osd_ioerr *ioerr = &state->ioerrs[i]; + for (i = 0; i < oir->num_comps; i++) { + struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[i]; if (!ioerr->oer_errno) continue; @@ -563,8 +500,8 @@ encode_accumulated_error(struct objlayout *objlay, __be32 *p) merge_ioerr(&accumulated_err, ioerr); } - list_del(&state->err_list); - objlayout_free_io_state(state); + list_del(&oir->err_list); + objio_free_result(oir); } pnfs_osd_xdr_encode_ioerr(p, &accumulated_err); @@ -576,7 +513,7 @@ objlayout_encode_layoutreturn(struct pnfs_layout_hdr *pnfslay, const struct nfs4_layoutreturn_args *args) { struct objlayout *objlay = OBJLAYOUT(pnfslay); - struct objlayout_io_state *state, *tmp; + struct objlayout_io_res *oir, *tmp; __be32 *start; dprintk("%s: Begin\n", __func__); @@ -585,13 +522,13 @@ objlayout_encode_layoutreturn(struct pnfs_layout_hdr *pnfslay, spin_lock(&objlay->lock); - list_for_each_entry_safe(state, tmp, &objlay->err_list, err_list) { + list_for_each_entry_safe(oir, tmp, &objlay->err_list, err_list) { __be32 *last_xdr = NULL, *p; unsigned i; int res = 0; - for (i = 0; i < state->num_comps; i++) { - struct pnfs_osd_ioerr *ioerr = &state->ioerrs[i]; + for (i = 0; i < oir->num_comps; i++) { + struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[i]; if (!ioerr->oer_errno) continue; @@ -615,7 +552,7 @@ objlayout_encode_layoutreturn(struct pnfs_layout_hdr *pnfslay, } last_xdr = p; - pnfs_osd_xdr_encode_ioerr(p, &state->ioerrs[i]); + pnfs_osd_xdr_encode_ioerr(p, &oir->ioerrs[i]); } /* TODO: use xdr_write_pages */ @@ -631,8 +568,8 @@ objlayout_encode_layoutreturn(struct pnfs_layout_hdr *pnfslay, encode_accumulated_error(objlay, last_xdr); goto loop_done; } - list_del(&state->err_list); - objlayout_free_io_state(state); + list_del(&oir->err_list); + objio_free_result(oir); } loop_done: spin_unlock(&objlay->lock); diff --git a/fs/nfs/objlayout/objlayout.h b/fs/nfs/objlayout/objlayout.h index a8244c8e042d..8ec34727ed21 100644 --- a/fs/nfs/objlayout/objlayout.h +++ b/fs/nfs/objlayout/objlayout.h @@ -74,19 +74,11 @@ OBJLAYOUT(struct pnfs_layout_hdr *lo) * per-I/O operation state * embedded in objects provider io_state data structure */ -struct objlayout_io_state { - struct pnfs_layout_segment *lseg; - - struct page **pages; - unsigned pgbase; - unsigned nr_pages; - unsigned long count; - loff_t offset; - bool sync; +struct objlayout_io_res { + struct objlayout *objlay; void *rpcdata; int status; /* res */ - int eof; /* res */ int committed; /* res */ /* Error reporting (layout_return) */ @@ -100,6 +92,18 @@ struct objlayout_io_state { struct pnfs_osd_ioerr *ioerrs; }; +static inline +void objlayout_init_ioerrs(struct objlayout_io_res *oir, unsigned num_comps, + struct pnfs_osd_ioerr *ioerrs, void *rpcdata, + struct pnfs_layout_hdr *pnfs_layout_type) +{ + oir->objlay = OBJLAYOUT(pnfs_layout_type); + oir->rpcdata = rpcdata; + INIT_LIST_HEAD(&oir->err_list); + oir->num_comps = num_comps; + oir->ioerrs = ioerrs; +} + /* * Raid engine I/O API */ @@ -110,28 +114,24 @@ extern int objio_alloc_lseg(struct pnfs_layout_segment **outp, gfp_t gfp_flags); extern void objio_free_lseg(struct pnfs_layout_segment *lseg); -extern int objio_alloc_io_state( - struct pnfs_layout_segment *lseg, - struct objlayout_io_state **outp, - gfp_t gfp_flags); -extern void objio_free_io_state(struct objlayout_io_state *state); +/* objio_free_result will free these @oir structs recieved from + * objlayout_{read,write}_done + */ +extern void objio_free_result(struct objlayout_io_res *oir); -extern ssize_t objio_read_pagelist(struct objlayout_io_state *ol_state); -extern ssize_t objio_write_pagelist(struct objlayout_io_state *ol_state, - bool stable); +extern int objio_read_pagelist(struct nfs_read_data *rdata); +extern int objio_write_pagelist(struct nfs_write_data *wdata, int how); /* * callback API */ -extern void objlayout_io_set_result(struct objlayout_io_state *state, +extern void objlayout_io_set_result(struct objlayout_io_res *oir, unsigned index, struct pnfs_osd_objid *pooid, int osd_error, u64 offset, u64 length, bool is_write); static inline void -objlayout_add_delta_space_used(struct objlayout_io_state *state, s64 space_used) +objlayout_add_delta_space_used(struct objlayout *objlay, s64 space_used) { - struct objlayout *objlay = OBJLAYOUT(state->lseg->pls_layout); - /* If one of the I/Os errored out and the delta_space_used was * invalid we render the complete report as invalid. Protocol mandate * the DSU be accurate or not reported. @@ -144,9 +144,9 @@ objlayout_add_delta_space_used(struct objlayout_io_state *state, s64 space_used) spin_unlock(&objlay->lock); } -extern void objlayout_read_done(struct objlayout_io_state *state, +extern void objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync); -extern void objlayout_write_done(struct objlayout_io_state *state, +extern void objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync); extern int objlayout_get_deviceinfo(struct pnfs_layout_hdr *pnfslay, diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index b60970cc7f1f..5668f7c54c41 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -18,6 +18,7 @@ #include <linux/nfs_page.h> #include <linux/nfs_fs.h> #include <linux/nfs_mount.h> +#include <linux/export.h> #include "internal.h" #include "pnfs.h" @@ -41,7 +42,7 @@ nfs_page_free(struct nfs_page *p) /** * nfs_create_request - Create an NFS read/write request. - * @file: file descriptor to use + * @ctx: open context to use * @inode: inode to which the request is attached * @page: page to write * @offset: starting offset within the page for the write diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index e550e8836c37..8e672a2b2d69 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -29,6 +29,7 @@ #include <linux/nfs_fs.h> #include <linux/nfs_page.h> +#include <linux/module.h> #include "internal.h" #include "pnfs.h" #include "iostat.h" @@ -1168,23 +1169,17 @@ EXPORT_SYMBOL_GPL(pnfs_generic_pg_test); /* * Called by non rpc-based layout drivers */ -int -pnfs_ld_write_done(struct nfs_write_data *data) +void pnfs_ld_write_done(struct nfs_write_data *data) { - int status; - - if (!data->pnfs_error) { + if (likely(!data->pnfs_error)) { pnfs_set_layoutcommit(data); data->mds_ops->rpc_call_done(&data->task, data); - data->mds_ops->rpc_release(data); - return 0; + } else { + put_lseg(data->lseg); + data->lseg = NULL; + dprintk("pnfs write error = %d\n", data->pnfs_error); } - - dprintk("%s: pnfs_error=%d, retry via MDS\n", __func__, - data->pnfs_error); - status = nfs_initiate_write(data, NFS_CLIENT(data->inode), - data->mds_ops, NFS_FILE_SYNC); - return status ? : -EAGAIN; + data->mds_ops->rpc_release(data); } EXPORT_SYMBOL_GPL(pnfs_ld_write_done); @@ -1265,26 +1260,36 @@ pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) } EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages); +static void pnfs_ld_handle_read_error(struct nfs_read_data *data) +{ + struct nfs_pageio_descriptor pgio; + + put_lseg(data->lseg); + data->lseg = NULL; + dprintk("pnfs write error = %d\n", data->pnfs_error); + + nfs_pageio_init_read_mds(&pgio, data->inode); + + while (!list_empty(&data->pages)) { + struct nfs_page *req = nfs_list_entry(data->pages.next); + + nfs_list_remove_request(req); + nfs_pageio_add_request(&pgio, req); + } + nfs_pageio_complete(&pgio); +} + /* * Called by non rpc-based layout drivers */ -int -pnfs_ld_read_done(struct nfs_read_data *data) +void pnfs_ld_read_done(struct nfs_read_data *data) { - int status; - - if (!data->pnfs_error) { + if (likely(!data->pnfs_error)) { __nfs4_read_done_cb(data); data->mds_ops->rpc_call_done(&data->task, data); - data->mds_ops->rpc_release(data); - return 0; - } - - dprintk("%s: pnfs_error=%d, retry via MDS\n", __func__, - data->pnfs_error); - status = nfs_initiate_read(data, NFS_CLIENT(data->inode), - data->mds_ops); - return status ? : -EAGAIN; + } else + pnfs_ld_handle_read_error(data); + data->mds_ops->rpc_release(data); } EXPORT_SYMBOL_GPL(pnfs_ld_read_done); @@ -1381,6 +1386,18 @@ static void pnfs_list_write_lseg(struct inode *inode, struct list_head *listp) } } +void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg) +{ + if (lseg->pls_range.iomode == IOMODE_RW) { + dprintk("%s Setting layout IOMODE_RW fail bit\n", __func__); + set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags); + } else { + dprintk("%s Setting layout IOMODE_READ fail bit\n", __func__); + set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags); + } +} +EXPORT_SYMBOL_GPL(pnfs_set_lo_fail); + void pnfs_set_layoutcommit(struct nfs_write_data *wdata) { @@ -1443,17 +1460,31 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync) /* Note kzalloc ensures data->res.seq_res.sr_slot == NULL */ data = kzalloc(sizeof(*data), GFP_NOFS); if (!data) { - mark_inode_dirty_sync(inode); status = -ENOMEM; goto out; } + 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; + } + 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); - kfree(data); - goto out; + wake_up_bit(&nfsi->flags, NFS_INO_LAYOUTCOMMITTING); + goto out_free; } pnfs_list_write_lseg(inode, &data->lseg_list); @@ -1475,6 +1506,11 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync) status = nfs4_proc_layoutcommit(data, sync); out: + if (status) + mark_inode_dirty_sync(inode); dprintk("<-- %s status %d\n", __func__, status); return status; +out_free: + kfree(data); + goto out; } diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 01cbfd54f3cb..1509530cb111 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -178,6 +178,7 @@ int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc); void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *, struct nfs_page *); int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc); bool pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req); +void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg); int pnfs_layout_process(struct nfs4_layoutget *lgp); void pnfs_free_lseg_list(struct list_head *tmp_list); void pnfs_destroy_layout(struct nfs_inode *); @@ -200,8 +201,8 @@ void pnfs_set_layoutcommit(struct nfs_write_data *wdata); void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data); int pnfs_layoutcommit_inode(struct inode *inode, bool sync); int _pnfs_return_layout(struct inode *); -int pnfs_ld_write_done(struct nfs_write_data *); -int pnfs_ld_read_done(struct nfs_read_data *); +void pnfs_ld_write_done(struct nfs_write_data *); +void pnfs_ld_read_done(struct nfs_read_data *); struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx, loff_t pos, diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c index 6fda5228ef56..4f359d2a26eb 100644 --- a/fs/nfs/pnfs_dev.c +++ b/fs/nfs/pnfs_dev.c @@ -28,6 +28,7 @@ * such damages. */ +#include <linux/export.h> #include "pnfs.h" #define NFSDBG_FACILITY NFSDBG_PNFS diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index ac40b8535d7e..f48125da198a 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -710,6 +710,7 @@ const struct nfs_rpc_ops nfs_v2_clientops = { .dentry_ops = &nfs_dentry_operations, .dir_inode_ops = &nfs_dir_inode_operations, .file_inode_ops = &nfs_file_inode_operations, + .file_ops = &nfs_file_operations, .getroot = nfs_proc_get_root, .getattr = nfs_proc_getattr, .setattr = nfs_proc_setattr, diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 2171c043ab08..cfa175c223dc 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -35,16 +35,13 @@ static const struct rpc_call_ops nfs_read_partial_ops; static const struct rpc_call_ops nfs_read_full_ops; static struct kmem_cache *nfs_rdata_cachep; -static mempool_t *nfs_rdata_mempool; - -#define MIN_POOL_READ (32) struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount) { - struct nfs_read_data *p = mempool_alloc(nfs_rdata_mempool, GFP_KERNEL); + struct nfs_read_data *p; + p = kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL); if (p) { - memset(p, 0, sizeof(*p)); INIT_LIST_HEAD(&p->pages); p->npages = pagecount; if (pagecount <= ARRAY_SIZE(p->page_array)) @@ -52,7 +49,7 @@ struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount) else { p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL); if (!p->pagevec) { - mempool_free(p, nfs_rdata_mempool); + kmem_cache_free(nfs_rdata_cachep, p); p = NULL; } } @@ -64,7 +61,7 @@ void nfs_readdata_free(struct nfs_read_data *p) { if (p && (p->pagevec != &p->page_array[0])) kfree(p->pagevec); - mempool_free(p, nfs_rdata_mempool); + kmem_cache_free(nfs_rdata_cachep, p); } void nfs_readdata_release(struct nfs_read_data *rdata) @@ -112,7 +109,7 @@ static void nfs_readpage_truncate_uninitialised_page(struct nfs_read_data *data) } } -static void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio, +void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio, struct inode *inode) { nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops, @@ -276,7 +273,6 @@ nfs_async_read_error(struct list_head *head) while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); - SetPageError(req->wb_page); nfs_readpage_release(req); } } @@ -322,7 +318,6 @@ static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc, struct list_head offset += len; } while(nbytes != 0); atomic_set(&req->wb_complete, requests); - ClearPageError(page); desc->pg_rpc_callops = &nfs_read_partial_ops; return ret; out_bad: @@ -331,7 +326,6 @@ out_bad: list_del(&data->list); nfs_readdata_free(data); } - SetPageError(page); nfs_readpage_release(req); return -ENOMEM; } @@ -357,7 +351,6 @@ static int nfs_pagein_one(struct nfs_pageio_descriptor *desc, struct list_head * req = nfs_list_entry(head->next); nfs_list_remove_request(req); nfs_list_add_request(req, &data->pages); - ClearPageError(req->wb_page); *pages++ = req->wb_page; } req = nfs_list_entry(data->pages.next); @@ -435,7 +428,7 @@ static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data argp->offset += resp->count; argp->pgbase += resp->count; argp->count -= resp->count; - nfs_restart_rpc(task, NFS_SERVER(data->inode)->nfs_client); + rpc_restart_call_prepare(task); } /* @@ -462,10 +455,10 @@ static void nfs_readpage_release_partial(void *calldata) int status = data->task.tk_status; if (status < 0) - SetPageError(page); + set_bit(PG_PARTIAL_READ_FAILED, &req->wb_flags); if (atomic_dec_and_test(&req->wb_complete)) { - if (!PageError(page)) + if (!test_bit(PG_PARTIAL_READ_FAILED, &req->wb_flags)) SetPageUptodate(page); nfs_readpage_release(req); } @@ -648,7 +641,6 @@ readpage_async_filler(void *data, struct page *page) return 0; out_error: error = PTR_ERR(new); - SetPageError(page); out_unlock: unlock_page(page); return error; @@ -711,16 +703,10 @@ int __init nfs_init_readpagecache(void) if (nfs_rdata_cachep == NULL) return -ENOMEM; - nfs_rdata_mempool = mempool_create_slab_pool(MIN_POOL_READ, - nfs_rdata_cachep); - if (nfs_rdata_mempool == NULL) - return -ENOMEM; - return 0; } void nfs_destroy_readpagecache(void) { - mempool_destroy(nfs_rdata_mempool); kmem_cache_destroy(nfs_rdata_cachep); } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 5b19b6aabe18..134777406ee3 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -733,18 +733,22 @@ static int nfs_show_options(struct seq_file *m, struct vfsmount *mnt) return 0; } + +#ifdef CONFIG_NFS_V4 #ifdef CONFIG_NFS_V4_1 -void show_sessions(struct seq_file *m, struct nfs_server *server) +static void show_sessions(struct seq_file *m, struct nfs_server *server) { if (nfs4_has_session(server->nfs_client)) seq_printf(m, ",sessions"); } #else -void show_sessions(struct seq_file *m, struct nfs_server *server) {} +static void show_sessions(struct seq_file *m, struct nfs_server *server) {} +#endif #endif +#ifdef CONFIG_NFS_V4 #ifdef CONFIG_NFS_V4_1 -void show_pnfs(struct seq_file *m, struct nfs_server *server) +static void show_pnfs(struct seq_file *m, struct nfs_server *server) { seq_printf(m, ",pnfs="); if (server->pnfs_curr_ld) @@ -752,9 +756,10 @@ void show_pnfs(struct seq_file *m, struct nfs_server *server) else seq_printf(m, "not configured"); } -#else /* CONFIG_NFS_V4_1 */ -void show_pnfs(struct seq_file *m, struct nfs_server *server) {} -#endif /* CONFIG_NFS_V4_1 */ +#else +static void show_pnfs(struct seq_file *m, struct nfs_server *server) {} +#endif +#endif static int nfs_show_devname(struct seq_file *m, struct vfsmount *mnt) { @@ -2782,43 +2787,18 @@ static void nfs_referral_loop_unprotect(void) static struct dentry *nfs_follow_remote_path(struct vfsmount *root_mnt, const char *export_path) { - struct mnt_namespace *ns_private; - struct super_block *s; struct dentry *dentry; - struct path path; - int ret; - - ns_private = create_mnt_ns(root_mnt); - ret = PTR_ERR(ns_private); - if (IS_ERR(ns_private)) - goto out_mntput; + int ret = nfs_referral_loop_protect(); - ret = nfs_referral_loop_protect(); - if (ret != 0) - goto out_put_mnt_ns; - - ret = vfs_path_lookup(root_mnt->mnt_root, root_mnt, - export_path, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path); + if (ret) { + mntput(root_mnt); + return ERR_PTR(ret); + } + dentry = mount_subtree(root_mnt, export_path); nfs_referral_loop_unprotect(); - put_mnt_ns(ns_private); - - if (ret != 0) - goto out_err; - - s = path.mnt->mnt_sb; - atomic_inc(&s->s_active); - dentry = dget(path.dentry); - path_put(&path); - down_write(&s->s_umount); return dentry; -out_put_mnt_ns: - put_mnt_ns(ns_private); -out_mntput: - mntput(root_mnt); -out_err: - return ERR_PTR(ret); } static struct dentry *nfs4_try_mount(int flags, const char *dev_name, diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index b2fbbde58e44..4f9319a2e567 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -87,7 +87,7 @@ static void nfs_async_unlink_done(struct rpc_task *task, void *calldata) struct inode *dir = data->dir; if (!NFS_PROTO(dir)->unlink_done(task, dir)) - nfs_restart_rpc(task, NFS_SERVER(dir)->nfs_client); + rpc_restart_call_prepare(task); } /** @@ -369,7 +369,7 @@ static void nfs_async_rename_done(struct rpc_task *task, void *calldata) struct dentry *new_dentry = data->new_dentry; if (!NFS_PROTO(old_dir)->rename_done(task, old_dir, new_dir)) { - nfs_restart_rpc(task, NFS_SERVER(old_dir)->nfs_client); + rpc_restart_call_prepare(task); return; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index c9bd2a6b7d4b..1dda78db6a73 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -20,6 +20,7 @@ #include <linux/nfs_mount.h> #include <linux/nfs_page.h> #include <linux/backing-dev.h> +#include <linux/export.h> #include <asm/uaccess.h> @@ -390,7 +391,7 @@ static int nfs_inode_add_request(struct inode *inode, struct nfs_page *req) error = radix_tree_insert(&nfsi->nfs_page_tree, req->wb_index, req); BUG_ON(error); if (!nfsi->npages && nfs_have_delegation(inode, FMODE_WRITE)) - nfsi->change_attr++; + inode->i_version++; set_bit(PG_MAPPED, &req->wb_flags); SetPagePrivate(req->wb_page); set_page_private(req->wb_page, (unsigned long)req); @@ -428,7 +429,6 @@ static void nfs_mark_request_dirty(struct nfs_page *req) { __set_page_dirty_nobuffers(req->wb_page); - __mark_inode_dirty(req->wb_page->mapping->host, I_DIRTY_DATASYNC); } #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) @@ -762,6 +762,8 @@ int nfs_updatepage(struct file *file, struct page *page, status = nfs_writepage_setup(ctx, page, offset, count); if (status < 0) nfs_set_pageerror(page); + else + __set_page_dirty_nobuffers(page); dprintk("NFS: nfs_updatepage returns %d (isize %lld)\n", status, (long long)i_size_read(inode)); @@ -1010,7 +1012,6 @@ static int nfs_flush_one(struct nfs_pageio_descriptor *desc, struct list_head *r req = nfs_list_entry(head->next); nfs_list_remove_request(req); nfs_list_add_request(req, &data->pages); - ClearPageError(req->wb_page); *pages++ = req->wb_page; } req = nfs_list_entry(data->pages.next); @@ -1165,7 +1166,13 @@ static void nfs_writeback_done_full(struct rpc_task *task, void *calldata) static void nfs_writeback_release_full(void *calldata) { struct nfs_write_data *data = calldata; - int status = data->task.tk_status; + int ret, status = data->task.tk_status; + struct nfs_pageio_descriptor pgio; + + if (data->pnfs_error) { + nfs_pageio_init_write_mds(&pgio, data->inode, FLUSH_STABLE); + pgio.pg_recoalesce = 1; + } /* Update attributes as result of writeback. */ while (!list_empty(&data->pages)) { @@ -1181,6 +1188,11 @@ static void nfs_writeback_release_full(void *calldata) req->wb_bytes, (long long)req_offset(req)); + if (data->pnfs_error) { + dprintk(", pnfs error = %d\n", data->pnfs_error); + goto next; + } + if (status < 0) { nfs_set_pageerror(page); nfs_context_set_write_error(req->wb_context, status); @@ -1200,7 +1212,19 @@ remove_request: next: nfs_clear_page_tag_locked(req); nfs_end_page_writeback(page); + if (data->pnfs_error) { + lock_page(page); + nfs_pageio_cond_complete(&pgio, page->index); + ret = nfs_page_async_flush(&pgio, page, 0); + if (ret) { + nfs_set_pageerror(page); + dprintk("rewrite to MDS error = %d\n", ret); + } + unlock_page(page); + } } + if (data->pnfs_error) + nfs_pageio_complete(&pgio); nfs_writedata_release(calldata); } @@ -1220,7 +1244,6 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) { struct nfs_writeargs *argp = &data->args; struct nfs_writeres *resp = &data->res; - struct nfs_server *server = NFS_SERVER(data->inode); int status; dprintk("NFS: %5u nfs_writeback_done (status %d)\n", @@ -1254,7 +1277,7 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) if (time_before(complain, jiffies)) { dprintk("NFS: faulty NFS server %s:" " (committed = %d) != (stable = %d)\n", - server->nfs_client->cl_hostname, + NFS_SERVER(data->inode)->nfs_client->cl_hostname, resp->verf->committed, argp->stable); complain = jiffies + 300 * HZ; } @@ -1281,7 +1304,7 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) */ argp->stable = NFS_FILE_SYNC; } - nfs_restart_rpc(task, server->nfs_client); + rpc_restart_call_prepare(task); return; } if (time_before(complain, jiffies)) { @@ -1553,6 +1576,10 @@ static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_contr int flags = FLUSH_SYNC; int ret = 0; + /* no commits means nothing needs to be done */ + if (!nfsi->ncommit) + return ret; + if (wbc->sync_mode == WB_SYNC_NONE) { /* Don't commit yet if this is a non-blocking flush and there * are a lot of outstanding writes for this mapping. @@ -1686,34 +1713,20 @@ out_error: int nfs_migrate_page(struct address_space *mapping, struct page *newpage, struct page *page) { - struct nfs_page *req; - int ret; + /* + * If PagePrivate is set, then the page is currently associated with + * an in-progress read or write request. Don't try to migrate it. + * + * FIXME: we could do this in principle, but we'll need a way to ensure + * that we can safely release the inode reference while holding + * the page lock. + */ + if (PagePrivate(page)) + return -EBUSY; nfs_fscache_release_page(page, GFP_KERNEL); - req = nfs_find_and_lock_request(page, false); - ret = PTR_ERR(req); - if (IS_ERR(req)) - goto out; - - ret = migrate_page(mapping, newpage, page); - if (!req) - goto out; - if (ret) - goto out_unlock; - page_cache_get(newpage); - spin_lock(&mapping->host->i_lock); - req->wb_page = newpage; - SetPagePrivate(newpage); - set_page_private(newpage, (unsigned long)req); - ClearPagePrivate(page); - set_page_private(page, 0); - spin_unlock(&mapping->host->i_lock); - page_cache_release(page); -out_unlock: - nfs_clear_page_tag_locked(req); -out: - return ret; + return migrate_page(mapping, newpage, page); } #endif |