diff options
Diffstat (limited to 'net')
92 files changed, 923 insertions, 656 deletions
diff --git a/net/9p/client.c b/net/9p/client.c index 5c1343195292..deae53a7dffc 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -283,8 +283,9 @@ p9_tag_alloc(struct p9_client *c, u16 tag, unsigned int max_size) return ERR_PTR(-ENOMEM); } for (col = 0; col < P9_ROW_MAXTAG; col++) { - c->reqs[row][col].status = REQ_STATUS_IDLE; - c->reqs[row][col].tc = NULL; + req = &c->reqs[row][col]; + req->status = REQ_STATUS_IDLE; + init_waitqueue_head(&req->wq); } c->max_tag += P9_ROW_MAXTAG; } @@ -294,13 +295,6 @@ p9_tag_alloc(struct p9_client *c, u16 tag, unsigned int max_size) col = tag % P9_ROW_MAXTAG; req = &c->reqs[row][col]; - if (!req->wq) { - req->wq = kmalloc(sizeof(wait_queue_head_t), GFP_NOFS); - if (!req->wq) - goto grow_failed; - init_waitqueue_head(req->wq); - } - if (!req->tc) req->tc = p9_fcall_alloc(alloc_msize); if (!req->rc) @@ -320,9 +314,7 @@ grow_failed: pr_err("Couldn't grow tag array\n"); kfree(req->tc); kfree(req->rc); - kfree(req->wq); req->tc = req->rc = NULL; - req->wq = NULL; return ERR_PTR(-ENOMEM); } @@ -341,7 +333,7 @@ struct p9_req_t *p9_tag_lookup(struct p9_client *c, u16 tag) * buffer to read the data into */ tag++; - if(tag >= c->max_tag) + if (tag >= c->max_tag) return NULL; row = tag / P9_ROW_MAXTAG; @@ -410,7 +402,6 @@ static void p9_tag_cleanup(struct p9_client *c) /* free requests associated with tags */ for (row = 0; row < (c->max_tag/P9_ROW_MAXTAG); row++) { for (col = 0; col < P9_ROW_MAXTAG; col++) { - kfree(c->reqs[row][col].wq); kfree(c->reqs[row][col].tc); kfree(c->reqs[row][col].rc); } @@ -448,12 +439,12 @@ void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status) /* * This barrier is needed to make sure any change made to req before - * the other thread wakes up will indeed be seen by the waiting side. + * the status change is visible to another thread */ smp_wmb(); req->status = status; - wake_up(req->wq); + wake_up(&req->wq); p9_debug(P9_DEBUG_MUX, "wakeup: %d\n", req->tc->tag); } EXPORT_SYMBOL(p9_client_cb); @@ -478,20 +469,11 @@ p9_parse_header(struct p9_fcall *pdu, int32_t *size, int8_t *type, int16_t *tag, int err; pdu->offset = 0; - if (pdu->size == 0) - pdu->size = 7; err = p9pdu_readf(pdu, 0, "dbw", &r_size, &r_type, &r_tag); if (err) goto rewind_and_exit; - pdu->size = r_size; - pdu->id = r_type; - pdu->tag = r_tag; - - p9_debug(P9_DEBUG_9P, "<<< size=%d type: %d tag: %d\n", - pdu->size, pdu->id, pdu->tag); - if (type) *type = r_type; if (tag) @@ -499,6 +481,16 @@ p9_parse_header(struct p9_fcall *pdu, int32_t *size, int8_t *type, int16_t *tag, if (size) *size = r_size; + if (pdu->size != r_size || r_size < 7) { + err = -EINVAL; + goto rewind_and_exit; + } + + pdu->id = r_type; + pdu->tag = r_tag; + + p9_debug(P9_DEBUG_9P, "<<< size=%d type: %d tag: %d\n", + pdu->size, pdu->id, pdu->tag); rewind_and_exit: if (rewind) @@ -525,6 +517,12 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req) int ecode; err = p9_parse_header(req->rc, NULL, &type, NULL, 0); + if (req->rc->size >= c->msize) { + p9_debug(P9_DEBUG_ERROR, + "requested packet size too big: %d\n", + req->rc->size); + return -EIO; + } /* * dump the response from server * This should be after check errors which poplulate pdu_fcall. @@ -774,7 +772,7 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...) } again: /* Wait for the response */ - err = wait_event_killable(*req->wq, req->status >= REQ_STATUS_RCVD); + err = wait_event_killable(req->wq, req->status >= REQ_STATUS_RCVD); /* * Make sure our req is coherent with regard to updates in other @@ -909,34 +907,31 @@ static struct p9_fid *p9_fid_create(struct p9_client *clnt) { int ret; struct p9_fid *fid; - unsigned long flags; p9_debug(P9_DEBUG_FID, "clnt %p\n", clnt); fid = kmalloc(sizeof(struct p9_fid), GFP_KERNEL); if (!fid) - return ERR_PTR(-ENOMEM); - - ret = p9_idpool_get(clnt->fidpool); - if (ret < 0) { - ret = -ENOSPC; - goto error; - } - fid->fid = ret; + return NULL; memset(&fid->qid, 0, sizeof(struct p9_qid)); fid->mode = -1; fid->uid = current_fsuid(); fid->clnt = clnt; fid->rdir = NULL; - spin_lock_irqsave(&clnt->lock, flags); - list_add(&fid->flist, &clnt->fidlist); - spin_unlock_irqrestore(&clnt->lock, flags); + fid->fid = 0; - return fid; + idr_preload(GFP_KERNEL); + spin_lock_irq(&clnt->lock); + ret = idr_alloc_u32(&clnt->fids, fid, &fid->fid, P9_NOFID - 1, + GFP_NOWAIT); + spin_unlock_irq(&clnt->lock); + idr_preload_end(); + + if (!ret) + return fid; -error: kfree(fid); - return ERR_PTR(ret); + return NULL; } static void p9_fid_destroy(struct p9_fid *fid) @@ -946,9 +941,8 @@ static void p9_fid_destroy(struct p9_fid *fid) p9_debug(P9_DEBUG_FID, "fid %d\n", fid->fid); clnt = fid->clnt; - p9_idpool_put(fid->fid, clnt->fidpool); spin_lock_irqsave(&clnt->lock, flags); - list_del(&fid->flist); + idr_remove(&clnt->fids, fid->fid); spin_unlock_irqrestore(&clnt->lock, flags); kfree(fid->rdir); kfree(fid); @@ -958,7 +952,7 @@ static int p9_client_version(struct p9_client *c) { int err = 0; struct p9_req_t *req; - char *version; + char *version = NULL; int msize; p9_debug(P9_DEBUG_9P, ">>> TVERSION msize %d protocol %d\n", @@ -1031,7 +1025,7 @@ struct p9_client *p9_client_create(const char *dev_name, char *options) memcpy(clnt->name, client_id, strlen(client_id) + 1); spin_lock_init(&clnt->lock); - INIT_LIST_HEAD(&clnt->fidlist); + idr_init(&clnt->fids); err = p9_tag_init(clnt); if (err < 0) @@ -1051,18 +1045,12 @@ struct p9_client *p9_client_create(const char *dev_name, char *options) goto destroy_tagpool; } - clnt->fidpool = p9_idpool_create(); - if (IS_ERR(clnt->fidpool)) { - err = PTR_ERR(clnt->fidpool); - goto put_trans; - } - p9_debug(P9_DEBUG_MUX, "clnt %p trans %p msize %d protocol %d\n", clnt, clnt->trans_mod, clnt->msize, clnt->proto_version); err = clnt->trans_mod->create(clnt, dev_name, options); if (err) - goto destroy_fidpool; + goto put_trans; if (clnt->msize > clnt->trans_mod->maxsize) clnt->msize = clnt->trans_mod->maxsize; @@ -1075,8 +1063,6 @@ struct p9_client *p9_client_create(const char *dev_name, char *options) close_trans: clnt->trans_mod->close(clnt); -destroy_fidpool: - p9_idpool_destroy(clnt->fidpool); put_trans: v9fs_put_trans(clnt->trans_mod); destroy_tagpool: @@ -1089,7 +1075,8 @@ EXPORT_SYMBOL(p9_client_create); void p9_client_destroy(struct p9_client *clnt) { - struct p9_fid *fid, *fidptr; + struct p9_fid *fid; + int id; p9_debug(P9_DEBUG_MUX, "clnt %p\n", clnt); @@ -1098,14 +1085,11 @@ void p9_client_destroy(struct p9_client *clnt) v9fs_put_trans(clnt->trans_mod); - list_for_each_entry_safe(fid, fidptr, &clnt->fidlist, flist) { + idr_for_each_entry(&clnt->fids, fid, id) { pr_info("Found fid %d not clunked\n", fid->fid); p9_fid_destroy(fid); } - if (clnt->fidpool) - p9_idpool_destroy(clnt->fidpool); - p9_tag_cleanup(clnt); kfree(clnt); @@ -1138,9 +1122,8 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid, p9_debug(P9_DEBUG_9P, ">>> TATTACH afid %d uname %s aname %s\n", afid ? afid->fid : -1, uname, aname); fid = p9_fid_create(clnt); - if (IS_ERR(fid)) { - err = PTR_ERR(fid); - fid = NULL; + if (!fid) { + err = -ENOMEM; goto error; } fid->uid = n_uname; @@ -1189,9 +1172,8 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname, clnt = oldfid->clnt; if (clone) { fid = p9_fid_create(clnt); - if (IS_ERR(fid)) { - err = PTR_ERR(fid); - fid = NULL; + if (!fid) { + err = -ENOMEM; goto error; } @@ -1576,7 +1558,7 @@ p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err) int count = iov_iter_count(to); int rsize, non_zc = 0; char *dataptr; - + rsize = fid->iounit; if (!rsize || rsize > clnt->msize-P9_IOHDRSZ) rsize = clnt->msize - P9_IOHDRSZ; @@ -1790,7 +1772,7 @@ struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid, "<<< st_mtime_sec=%lld st_mtime_nsec=%lld\n" "<<< st_ctime_sec=%lld st_ctime_nsec=%lld\n" "<<< st_btime_sec=%lld st_btime_nsec=%lld\n" - "<<< st_gen=%lld st_data_version=%lld", + "<<< st_gen=%lld st_data_version=%lld\n", ret->st_result_mask, ret->qid.type, ret->qid.path, ret->qid.version, ret->st_mode, ret->st_nlink, from_kuid(&init_user_ns, ret->st_uid), @@ -2019,9 +2001,8 @@ struct p9_fid *p9_client_xattrwalk(struct p9_fid *file_fid, err = 0; clnt = file_fid->clnt; attr_fid = p9_fid_create(clnt); - if (IS_ERR(attr_fid)) { - err = PTR_ERR(attr_fid); - attr_fid = NULL; + if (!attr_fid) { + err = -ENOMEM; goto error; } p9_debug(P9_DEBUG_9P, diff --git a/net/9p/protocol.c b/net/9p/protocol.c index 931ea00c4fed..4a1e1dd30b52 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -156,7 +156,7 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, *sptr = kmalloc(len + 1, GFP_NOFS); if (*sptr == NULL) { - errcode = -EFAULT; + errcode = -ENOMEM; break; } if (pdu_read(pdu, *sptr, len)) { diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 588bf88c3305..e2ef3c782c53 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -185,6 +185,8 @@ static void p9_mux_poll_stop(struct p9_conn *m) spin_lock_irqsave(&p9_poll_lock, flags); list_del_init(&m->poll_pending_link); spin_unlock_irqrestore(&p9_poll_lock, flags); + + flush_work(&p9_poll_work); } /** @@ -197,15 +199,14 @@ static void p9_mux_poll_stop(struct p9_conn *m) static void p9_conn_cancel(struct p9_conn *m, int err) { struct p9_req_t *req, *rtmp; - unsigned long flags; LIST_HEAD(cancel_list); p9_debug(P9_DEBUG_ERROR, "mux %p err %d\n", m, err); - spin_lock_irqsave(&m->client->lock, flags); + spin_lock(&m->client->lock); if (m->err) { - spin_unlock_irqrestore(&m->client->lock, flags); + spin_unlock(&m->client->lock); return; } @@ -217,7 +218,6 @@ static void p9_conn_cancel(struct p9_conn *m, int err) list_for_each_entry_safe(req, rtmp, &m->unsent_req_list, req_list) { list_move(&req->req_list, &cancel_list); } - spin_unlock_irqrestore(&m->client->lock, flags); list_for_each_entry_safe(req, rtmp, &cancel_list, req_list) { p9_debug(P9_DEBUG_ERROR, "call back req %p\n", req); @@ -226,6 +226,7 @@ static void p9_conn_cancel(struct p9_conn *m, int err) req->t_err = err; p9_client_cb(m->client, req, REQ_STATUS_ERROR); } + spin_unlock(&m->client->lock); } static __poll_t @@ -324,7 +325,9 @@ static void p9_read_work(struct work_struct *work) if ((!m->req) && (m->rc.offset == m->rc.capacity)) { p9_debug(P9_DEBUG_TRANS, "got new header\n"); - err = p9_parse_header(&m->rc, NULL, NULL, NULL, 0); + /* Header size */ + m->rc.size = 7; + err = p9_parse_header(&m->rc, &m->rc.size, NULL, NULL, 0); if (err) { p9_debug(P9_DEBUG_ERROR, "error parsing header: %d\n", err); @@ -369,12 +372,14 @@ static void p9_read_work(struct work_struct *work) */ if ((m->req) && (m->rc.offset == m->rc.capacity)) { p9_debug(P9_DEBUG_TRANS, "got new packet\n"); + m->req->rc->size = m->rc.offset; spin_lock(&m->client->lock); if (m->req->status != REQ_STATUS_ERROR) status = REQ_STATUS_RCVD; list_del(&m->req->req_list); - spin_unlock(&m->client->lock); + /* update req->status while holding client->lock */ p9_client_cb(m->client, m->req, status); + spin_unlock(&m->client->lock); m->rc.sdata = NULL; m->rc.offset = 0; m->rc.capacity = 0; @@ -940,7 +945,7 @@ p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args) if (err < 0) return err; - if (valid_ipaddr4(addr) < 0) + if (addr == NULL || valid_ipaddr4(addr) < 0) return -EINVAL; csocket = NULL; @@ -990,6 +995,9 @@ p9_fd_create_unix(struct p9_client *client, const char *addr, char *args) csocket = NULL; + if (addr == NULL) + return -EINVAL; + if (strlen(addr) >= UNIX_PATH_MAX) { pr_err("%s (%d): address too long: %s\n", __func__, task_pid_nr(current), addr); diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 3d414acb7015..b513cffeeb3c 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -320,6 +320,7 @@ recv_done(struct ib_cq *cq, struct ib_wc *wc) if (wc->status != IB_WC_SUCCESS) goto err_out; + c->rc->size = wc->byte_len; err = p9_parse_header(c->rc, NULL, NULL, &tag, 1); if (err) goto err_out; @@ -396,7 +397,7 @@ static int post_recv(struct p9_client *client, struct p9_rdma_context *c) { struct p9_trans_rdma *rdma = client->trans; - struct ib_recv_wr wr, *bad_wr; + struct ib_recv_wr wr; struct ib_sge sge; c->busa = ib_dma_map_single(rdma->cm_id->device, @@ -415,7 +416,7 @@ post_recv(struct p9_client *client, struct p9_rdma_context *c) wr.wr_cqe = &c->cqe; wr.sg_list = &sge; wr.num_sge = 1; - return ib_post_recv(rdma->qp, &wr, &bad_wr); + return ib_post_recv(rdma->qp, &wr, NULL); error: p9_debug(P9_DEBUG_ERROR, "EIO\n"); @@ -425,7 +426,7 @@ post_recv(struct p9_client *client, struct p9_rdma_context *c) static int rdma_request(struct p9_client *client, struct p9_req_t *req) { struct p9_trans_rdma *rdma = client->trans; - struct ib_send_wr wr, *bad_wr; + struct ib_send_wr wr; struct ib_sge sge; int err = 0; unsigned long flags; @@ -520,7 +521,7 @@ dont_need_post_recv: * status in case of a very fast reply. */ req->status = REQ_STATUS_SENT; - err = ib_post_send(rdma->qp, &wr, &bad_wr); + err = ib_post_send(rdma->qp, &wr, NULL); if (err) goto send_error; @@ -644,6 +645,9 @@ rdma_create_trans(struct p9_client *client, const char *addr, char *args) struct rdma_conn_param conn_param; struct ib_qp_init_attr qp_attr; + if (addr == NULL) + return -EINVAL; + /* Parse the transport specific mount options */ err = parse_opts(args, &opts); if (err < 0) diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 05006cbb3361..7728b0acde09 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -89,10 +89,8 @@ struct virtio_chan { unsigned long p9_max_pages; /* Scatterlist: can be too big for stack. */ struct scatterlist sg[VIRTQUEUE_NUM]; - - int tag_len; /* - * tag name to identify a mount Non-null terminated + * tag name to identify a mount null terminated */ char *tag; @@ -144,24 +142,27 @@ static void req_done(struct virtqueue *vq) struct virtio_chan *chan = vq->vdev->priv; unsigned int len; struct p9_req_t *req; + bool need_wakeup = false; unsigned long flags; p9_debug(P9_DEBUG_TRANS, ": request done\n"); - while (1) { - spin_lock_irqsave(&chan->lock, flags); - req = virtqueue_get_buf(chan->vq, &len); - if (req == NULL) { - spin_unlock_irqrestore(&chan->lock, flags); - break; + spin_lock_irqsave(&chan->lock, flags); + while ((req = virtqueue_get_buf(chan->vq, &len)) != NULL) { + if (!chan->ring_bufs_avail) { + chan->ring_bufs_avail = 1; + need_wakeup = true; } - chan->ring_bufs_avail = 1; - spin_unlock_irqrestore(&chan->lock, flags); - /* Wakeup if anyone waiting for VirtIO ring space. */ - wake_up(chan->vc_wq); - if (len) + + if (len) { + req->rc->size = len; p9_client_cb(chan->client, req, REQ_STATUS_RCVD); + } } + spin_unlock_irqrestore(&chan->lock, flags); + /* Wakeup if anyone waiting for VirtIO ring space. */ + if (need_wakeup) + wake_up(chan->vc_wq); } /** @@ -188,7 +189,7 @@ static int pack_sg_list(struct scatterlist *sg, int start, s = rest_of_page(data); if (s > count) s = count; - BUG_ON(index > limit); + BUG_ON(index >= limit); /* Make sure we don't terminate early. */ sg_unmark_end(&sg[index]); sg_set_buf(&sg[index++], data, s); @@ -233,6 +234,7 @@ pack_sg_list_p(struct scatterlist *sg, int start, int limit, s = PAGE_SIZE - data_off; if (s > count) s = count; + BUG_ON(index >= limit); /* Make sure we don't terminate early. */ sg_unmark_end(&sg[index]); sg_set_page(&sg[index++], pdata[i++], s, data_off); @@ -382,8 +384,8 @@ static int p9_get_mapped_pages(struct virtio_chan *chan, * p9_virtio_zc_request - issue a zero copy request * @client: client instance issuing the request * @req: request to be issued - * @uidata: user bffer that should be ued for zero copy read - * @uodata: user buffer that shoud be user for zero copy write + * @uidata: user buffer that should be used for zero copy read + * @uodata: user buffer that should be used for zero copy write * @inlen: read buffer size * @outlen: write buffer size * @in_hdr_len: reader header size, This is the size of response protocol data @@ -406,6 +408,7 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req, p9_debug(P9_DEBUG_TRANS, "virtio request\n"); if (uodata) { + __le32 sz; int n = p9_get_mapped_pages(chan, &out_pages, uodata, outlen, &offs, &need_drop); if (n < 0) @@ -416,6 +419,12 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req, memcpy(&req->tc->sdata[req->tc->size - 4], &v, 4); outlen = n; } + /* The size field of the message must include the length of the + * header and the length of the data. We didn't actually know + * the length of the data until this point so add it in now. + */ + sz = cpu_to_le32(req->tc->size + outlen); + memcpy(&req->tc->sdata[0], &sz, sizeof(sz)); } else if (uidata) { int n = p9_get_mapped_pages(chan, &in_pages, uidata, inlen, &offs, &need_drop); @@ -446,7 +455,7 @@ req_retry_pinned: out += pack_sg_list_p(chan->sg, out, VIRTQUEUE_NUM, out_pages, out_nr_pages, offs, outlen); } - + /* * Take care of in data * For example TREAD have 11. @@ -490,7 +499,7 @@ req_retry_pinned: virtqueue_kick(chan->vq); spin_unlock_irqrestore(&chan->lock, flags); p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n"); - err = wait_event_killable(*req->wq, req->status >= REQ_STATUS_RCVD); + err = wait_event_killable(req->wq, req->status >= REQ_STATUS_RCVD); /* * Non kernel buffers are pinned, unpin them */ @@ -517,14 +526,15 @@ static ssize_t p9_mount_tag_show(struct device *dev, { struct virtio_chan *chan; struct virtio_device *vdev; + int tag_len; vdev = dev_to_virtio(dev); chan = vdev->priv; + tag_len = strlen(chan->tag); - memcpy(buf, chan->tag, chan->tag_len); - buf[chan->tag_len] = 0; + memcpy(buf, chan->tag, tag_len + 1); - return chan->tag_len + 1; + return tag_len + 1; } static DEVICE_ATTR(mount_tag, 0444, p9_mount_tag_show, NULL); @@ -563,7 +573,7 @@ static int p9_virtio_probe(struct virtio_device *vdev) chan->vq = virtio_find_single_vq(vdev, req_done, "requests"); if (IS_ERR(chan->vq)) { err = PTR_ERR(chan->vq); - goto out_free_vq; + goto out_free_chan; } chan->vq->vdev->priv = chan; spin_lock_init(&chan->lock); @@ -577,7 +587,7 @@ static int p9_virtio_probe(struct virtio_device *vdev) err = -EINVAL; goto out_free_vq; } - tag = kmalloc(tag_len, GFP_KERNEL); + tag = kzalloc(tag_len + 1, GFP_KERNEL); if (!tag) { err = -ENOMEM; goto out_free_vq; @@ -586,7 +596,6 @@ static int p9_virtio_probe(struct virtio_device *vdev) virtio_cread_bytes(vdev, offsetof(struct virtio_9p_config, tag), tag, tag_len); chan->tag = tag; - chan->tag_len = tag_len; err = sysfs_create_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr); if (err) { goto out_free_tag; @@ -616,6 +625,7 @@ out_free_tag: kfree(tag); out_free_vq: vdev->config->del_vqs(vdev); +out_free_chan: kfree(chan); fail: return err; @@ -643,10 +653,12 @@ p9_virtio_create(struct p9_client *client, const char *devname, char *args) int ret = -ENOENT; int found = 0; + if (devname == NULL) + return -EINVAL; + mutex_lock(&virtio_9p_lock); list_for_each_entry(chan, &virtio_chan_list, chan_list) { - if (!strncmp(devname, chan->tag, chan->tag_len) && - strlen(devname) == chan->tag_len) { + if (!strcmp(devname, chan->tag)) { if (!chan->inuse) { chan->inuse = true; found = 1; diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index 2e2b8bca54f3..c2d54ac76bfd 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -94,6 +94,9 @@ static int p9_xen_create(struct p9_client *client, const char *addr, char *args) { struct xen_9pfs_front_priv *priv; + if (addr == NULL) + return -EINVAL; + read_lock(&xen_9pfs_lock); list_for_each_entry(priv, &xen_9pfs_devs, list) { if (!strcmp(priv->tag, addr)) { diff --git a/net/9p/util.c b/net/9p/util.c index 59f278e64f58..55ad98277e85 100644 --- a/net/9p/util.c +++ b/net/9p/util.c @@ -138,4 +138,3 @@ int p9_idpool_check(int id, struct p9_idpool *p) return idr_find(&p->pool, id) != NULL; } EXPORT_SYMBOL(p9_idpool_check); - diff --git a/net/ceph/Kconfig b/net/ceph/Kconfig index f8cceb99e732..cd2d5b9301a1 100644 --- a/net/ceph/Kconfig +++ b/net/ceph/Kconfig @@ -41,4 +41,3 @@ config CEPH_LIB_USE_DNS_RESOLVER Documentation/networking/dns_resolver.txt If unsure, say N. - diff --git a/net/ceph/Makefile b/net/ceph/Makefile index 12bf49772d24..db09defe27d0 100644 --- a/net/ceph/Makefile +++ b/net/ceph/Makefile @@ -15,4 +15,3 @@ libceph-y := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \ auth_x.o \ ceph_fs.o ceph_strings.o ceph_hash.o \ pagevec.o snapshot.o string_table.o - diff --git a/net/ceph/auth.c b/net/ceph/auth.c index dbde2b3c3c15..fbeee068ea14 100644 --- a/net/ceph/auth.c +++ b/net/ceph/auth.c @@ -315,6 +315,22 @@ int ceph_auth_update_authorizer(struct ceph_auth_client *ac, } EXPORT_SYMBOL(ceph_auth_update_authorizer); +int ceph_auth_add_authorizer_challenge(struct ceph_auth_client *ac, + struct ceph_authorizer *a, + void *challenge_buf, + int challenge_buf_len) +{ + int ret = 0; + + mutex_lock(&ac->mutex); + if (ac->ops && ac->ops->add_authorizer_challenge) + ret = ac->ops->add_authorizer_challenge(ac, a, challenge_buf, + challenge_buf_len); + mutex_unlock(&ac->mutex); + return ret; +} +EXPORT_SYMBOL(ceph_auth_add_authorizer_challenge); + int ceph_auth_verify_authorizer_reply(struct ceph_auth_client *ac, struct ceph_authorizer *a) { diff --git a/net/ceph/auth_none.c b/net/ceph/auth_none.c index 41d2a0c72236..edb7042479ed 100644 --- a/net/ceph/auth_none.c +++ b/net/ceph/auth_none.c @@ -142,4 +142,3 @@ int ceph_auth_none_init(struct ceph_auth_client *ac) ac->ops = &ceph_auth_none_ops; return 0; } - diff --git a/net/ceph/auth_none.h b/net/ceph/auth_none.h index 860ed9875791..4158f064302e 100644 --- a/net/ceph/auth_none.h +++ b/net/ceph/auth_none.h @@ -26,4 +26,3 @@ struct ceph_auth_none_info { int ceph_auth_none_init(struct ceph_auth_client *ac); #endif - diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c index 2f4a1baf5f52..b52732337ca6 100644 --- a/net/ceph/auth_x.c +++ b/net/ceph/auth_x.c @@ -9,6 +9,7 @@ #include <linux/ceph/decode.h> #include <linux/ceph/auth.h> +#include <linux/ceph/ceph_features.h> #include <linux/ceph/libceph.h> #include <linux/ceph/messenger.h> @@ -70,25 +71,40 @@ static int ceph_x_encrypt(struct ceph_crypto_key *secret, void *buf, return sizeof(u32) + ciphertext_len; } +static int __ceph_x_decrypt(struct ceph_crypto_key *secret, void *p, + int ciphertext_len) +{ + struct ceph_x_encrypt_header *hdr = p; + int plaintext_len; + int ret; + + ret = ceph_crypt(secret, false, p, ciphertext_len, ciphertext_len, + &plaintext_len); + if (ret) + return ret; + + if (le64_to_cpu(hdr->magic) != CEPHX_ENC_MAGIC) { + pr_err("%s bad magic\n", __func__); + return -EINVAL; + } + + return plaintext_len - sizeof(*hdr); +} + static int ceph_x_decrypt(struct ceph_crypto_key *secret, void **p, void *end) { - struct ceph_x_encrypt_header *hdr = *p + sizeof(u32); - int ciphertext_len, plaintext_len; + int ciphertext_len; int ret; ceph_decode_32_safe(p, end, ciphertext_len, e_inval); ceph_decode_need(p, end, ciphertext_len, e_inval); - ret = ceph_crypt(secret, false, *p, end - *p, ciphertext_len, - &plaintext_len); - if (ret) + ret = __ceph_x_decrypt(secret, *p, ciphertext_len); + if (ret < 0) return ret; - if (hdr->struct_v != 1 || le64_to_cpu(hdr->magic) != CEPHX_ENC_MAGIC) - return -EPERM; - *p += ciphertext_len; - return plaintext_len - sizeof(struct ceph_x_encrypt_header); + return ret; e_inval: return -EINVAL; @@ -149,12 +165,12 @@ static int process_one_ticket(struct ceph_auth_client *ac, void *dp, *dend; int dlen; char is_enc; - struct timespec validity; + struct timespec64 validity; void *tp, *tpend; void **ptp; struct ceph_crypto_key new_session_key = { 0 }; struct ceph_buffer *new_ticket_blob; - unsigned long new_expires, new_renew_after; + time64_t new_expires, new_renew_after; u64 new_secret_id; int ret; @@ -189,11 +205,11 @@ static int process_one_ticket(struct ceph_auth_client *ac, if (ret) goto out; - ceph_decode_timespec(&validity, dp); + ceph_decode_timespec64(&validity, dp); dp += sizeof(struct ceph_timespec); - new_expires = get_seconds() + validity.tv_sec; + new_expires = ktime_get_real_seconds() + validity.tv_sec; new_renew_after = new_expires - (validity.tv_sec / 4); - dout(" expires=%lu renew_after=%lu\n", new_expires, + dout(" expires=%llu renew_after=%llu\n", new_expires, new_renew_after); /* ticket blob for service */ @@ -275,6 +291,51 @@ bad: return -EINVAL; } +/* + * Encode and encrypt the second part (ceph_x_authorize_b) of the + * authorizer. The first part (ceph_x_authorize_a) should already be + * encoded. + */ +static int encrypt_authorizer(struct ceph_x_authorizer *au, + u64 *server_challenge) +{ + struct ceph_x_authorize_a *msg_a; + struct ceph_x_authorize_b *msg_b; + void *p, *end; + int ret; + + msg_a = au->buf->vec.iov_base; + WARN_ON(msg_a->ticket_blob.secret_id != cpu_to_le64(au->secret_id)); + p = (void *)(msg_a + 1) + le32_to_cpu(msg_a->ticket_blob.blob_len); + end = au->buf->vec.iov_base + au->buf->vec.iov_len; + + msg_b = p + ceph_x_encrypt_offset(); + msg_b->struct_v = 2; + msg_b->nonce = cpu_to_le64(au->nonce); + if (server_challenge) { + msg_b->have_challenge = 1; + msg_b->server_challenge_plus_one = + cpu_to_le64(*server_challenge + 1); + } else { + msg_b->have_challenge = 0; + msg_b->server_challenge_plus_one = 0; + } + + ret = ceph_x_encrypt(&au->session_key, p, end - p, sizeof(*msg_b)); + if (ret < 0) + return ret; + + p += ret; + if (server_challenge) { + WARN_ON(p != end); + } else { + WARN_ON(p > end); + au->buf->vec.iov_len = p - au->buf->vec.iov_base; + } + + return 0; +} + static void ceph_x_authorizer_cleanup(struct ceph_x_authorizer *au) { ceph_crypto_key_destroy(&au->session_key); @@ -291,7 +352,6 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac, int maxlen; struct ceph_x_authorize_a *msg_a; struct ceph_x_authorize_b *msg_b; - void *p, *end; int ret; int ticket_blob_len = (th->ticket_blob ? th->ticket_blob->vec.iov_len : 0); @@ -335,21 +395,13 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac, dout(" th %p secret_id %lld %lld\n", th, th->secret_id, le64_to_cpu(msg_a->ticket_blob.secret_id)); - p = msg_a + 1; - p += ticket_blob_len; - end = au->buf->vec.iov_base + au->buf->vec.iov_len; - - msg_b = p + ceph_x_encrypt_offset(); - msg_b->struct_v = 1; get_random_bytes(&au->nonce, sizeof(au->nonce)); - msg_b->nonce = cpu_to_le64(au->nonce); - ret = ceph_x_encrypt(&au->session_key, p, end - p, sizeof(*msg_b)); - if (ret < 0) + ret = encrypt_authorizer(au, NULL); + if (ret) { + pr_err("failed to encrypt authorizer: %d", ret); goto out_au; + } - p += ret; - WARN_ON(p > end); - au->buf->vec.iov_len = p - au->buf->vec.iov_base; dout(" built authorizer nonce %llx len %d\n", au->nonce, (int)au->buf->vec.iov_len); return 0; @@ -385,13 +437,13 @@ static bool need_key(struct ceph_x_ticket_handler *th) if (!th->have_key) return true; - return get_seconds() >= th->renew_after; + return ktime_get_real_seconds() >= th->renew_after; } static bool have_key(struct ceph_x_ticket_handler *th) { if (th->have_key) { - if (get_seconds() >= th->expires) + if (ktime_get_real_seconds() >= th->expires) th->have_key = false; } @@ -626,6 +678,54 @@ static int ceph_x_update_authorizer( return 0; } +static int decrypt_authorize_challenge(struct ceph_x_authorizer *au, + void *challenge_buf, + int challenge_buf_len, + u64 *server_challenge) +{ + struct ceph_x_authorize_challenge *ch = + challenge_buf + sizeof(struct ceph_x_encrypt_header); + int ret; + + /* no leading len */ + ret = __ceph_x_decrypt(&au->session_key, challenge_buf, + challenge_buf_len); + if (ret < 0) + return ret; + if (ret < sizeof(*ch)) { + pr_err("bad size %d for ceph_x_authorize_challenge\n", ret); + return -EINVAL; + } + + *server_challenge = le64_to_cpu(ch->server_challenge); + return 0; +} + +static int ceph_x_add_authorizer_challenge(struct ceph_auth_client *ac, + struct ceph_authorizer *a, + void *challenge_buf, + int challenge_buf_len) +{ + struct ceph_x_authorizer *au = (void *)a; + u64 server_challenge; + int ret; + + ret = decrypt_authorize_challenge(au, challenge_buf, challenge_buf_len, + &server_challenge); + if (ret) { + pr_err("failed to decrypt authorize challenge: %d", ret); + return ret; + } + + ret = encrypt_authorizer(au, &server_challenge); + if (ret) { + pr_err("failed to encrypt authorizer w/ challenge: %d", ret); + return ret; + } + + return 0; +} + static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac, struct ceph_authorizer *a) { @@ -637,8 +737,10 @@ static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac, ret = ceph_x_decrypt(&au->session_key, &p, p + CEPHX_AU_ENC_BUF_LEN); if (ret < 0) return ret; - if (ret != sizeof(*reply)) - return -EPERM; + if (ret < sizeof(*reply)) { + pr_err("bad size %d for ceph_x_authorize_reply\n", ret); + return -EINVAL; + } if (au->nonce + 1 != le64_to_cpu(reply->nonce_plus_one)) ret = -EPERM; @@ -704,26 +806,64 @@ static int calc_signature(struct ceph_x_authorizer *au, struct ceph_msg *msg, __le64 *psig) { void *enc_buf = au->enc_buf; - struct { - __le32 len; - __le32 header_crc; - __le32 front_crc; - __le32 middle_crc; - __le32 data_crc; - } __packed *sigblock = enc_buf + ceph_x_encrypt_offset(); int ret; - sigblock->len = cpu_to_le32(4*sizeof(u32)); - sigblock->header_crc = msg->hdr.crc; - sigblock->front_crc = msg->footer.front_crc; - sigblock->middle_crc = msg->footer.middle_crc; - sigblock->data_crc = msg->footer.data_crc; - ret = ceph_x_encrypt(&au->session_key, enc_buf, CEPHX_AU_ENC_BUF_LEN, - sizeof(*sigblock)); - if (ret < 0) - return ret; + if (!CEPH_HAVE_FEATURE(msg->con->peer_features, CEPHX_V2)) { + struct { + __le32 len; + __le32 header_crc; + __le32 front_crc; + __le32 middle_crc; + __le32 data_crc; + } __packed *sigblock = enc_buf + ceph_x_encrypt_offset(); + + sigblock->len = cpu_to_le32(4*sizeof(u32)); + sigblock->header_crc = msg->hdr.crc; + sigblock->front_crc = msg->footer.front_crc; + sigblock->middle_crc = msg->footer.middle_crc; + sigblock->data_crc = msg->footer.data_crc; + + ret = ceph_x_encrypt(&au->session_key, enc_buf, + CEPHX_AU_ENC_BUF_LEN, sizeof(*sigblock)); + if (ret < 0) + return ret; + + *psig = *(__le64 *)(enc_buf + sizeof(u32)); + } else { + struct { + __le32 header_crc; + __le32 front_crc; + __le32 front_len; + __le32 middle_crc; + __le32 middle_len; + __le32 data_crc; + __le32 data_len; + __le32 seq_lower_word; + } __packed *sigblock = enc_buf; + struct { + __le64 a, b, c, d; + } __packed *penc = enc_buf; + int ciphertext_len; + + sigblock->header_crc = msg->hdr.crc; + sigblock->front_crc = msg->footer.front_crc; + sigblock->front_len = msg->hdr.front_len; + sigblock->middle_crc = msg->footer.middle_crc; + sigblock->middle_len = msg->hdr.middle_len; + sigblock->data_crc = msg->footer.data_crc; + sigblock->data_len = msg->hdr.data_len; + sigblock->seq_lower_word = *(__le32 *)&msg->hdr.seq; + + /* no leading len, no ceph_x_encrypt_header */ + ret = ceph_crypt(&au->session_key, true, enc_buf, + CEPHX_AU_ENC_BUF_LEN, sizeof(*sigblock), + &ciphertext_len); + if (ret) + return ret; + + *psig = penc->a ^ penc->b ^ penc->c ^ penc->d; + } - *psig = *(__le64 *)(enc_buf + sizeof(u32)); return 0; } @@ -778,6 +918,7 @@ static const struct ceph_auth_client_ops ceph_x_ops = { .handle_reply = ceph_x_handle_reply, .create_authorizer = ceph_x_create_authorizer, .update_authorizer = ceph_x_update_authorizer, + .add_authorizer_challenge = ceph_x_add_authorizer_challenge, .verify_authorizer_reply = ceph_x_verify_authorizer_reply, .invalidate_authorizer = ceph_x_invalidate_authorizer, .reset = ceph_x_reset, @@ -823,5 +964,3 @@ out_nomem: out: return ret; } - - diff --git a/net/ceph/auth_x.h b/net/ceph/auth_x.h index 454cb54568af..c03735f96df9 100644 --- a/net/ceph/auth_x.h +++ b/net/ceph/auth_x.h @@ -22,7 +22,7 @@ struct ceph_x_ticket_handler { u64 secret_id; struct ceph_buffer *ticket_blob; - unsigned long renew_after, expires; + time64_t renew_after, expires; }; #define CEPHX_AU_ENC_BUF_LEN 128 /* big enough for encrypted blob */ @@ -52,4 +52,3 @@ struct ceph_x_info { int ceph_x_init(struct ceph_auth_client *ac); #endif - diff --git a/net/ceph/auth_x_protocol.h b/net/ceph/auth_x_protocol.h index 32c13d763b9a..24b0b74564d0 100644 --- a/net/ceph/auth_x_protocol.h +++ b/net/ceph/auth_x_protocol.h @@ -70,6 +70,13 @@ struct ceph_x_authorize_a { struct ceph_x_authorize_b { __u8 struct_v; __le64 nonce; + __u8 have_challenge; + __le64 server_challenge_plus_one; +} __attribute__ ((packed)); + +struct ceph_x_authorize_challenge { + __u8 struct_v; + __le64 server_challenge; } __attribute__ ((packed)); struct ceph_x_authorize_reply { diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 584fdbef2088..87afb9ec4c68 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -304,7 +304,7 @@ static int get_secret(struct ceph_crypto_key *dst, const char *name) { struct ceph_crypto_key *ckey; ukey = request_key(&key_type_ceph, name, NULL); - if (!ukey || IS_ERR(ukey)) { + if (IS_ERR(ukey)) { /* request_key errors don't map nicely to mount(2) errors; don't even try, but still printk */ key_err = PTR_ERR(ukey); @@ -379,7 +379,7 @@ ceph_parse_options(char *options, const char *dev_name, /* parse mount options */ while ((c = strsep(&options, ",")) != NULL) { - int token, intval, ret; + int token, intval; if (!*c) continue; err = -EINVAL; @@ -394,11 +394,10 @@ ceph_parse_options(char *options, const char *dev_name, continue; } if (token < Opt_last_int) { - ret = match_int(&argstr[0], &intval); - if (ret < 0) { - pr_err("bad mount option arg (not int) " - "at '%s'\n", c); - continue; + err = match_int(&argstr[0], &intval); + if (err < 0) { + pr_err("bad option arg (not int) at '%s'\n", c); + goto out; } dout("got int token %d val %d\n", token, intval); } else if (token > Opt_last_int && token < Opt_last_string) { diff --git a/net/ceph/cls_lock_client.c b/net/ceph/cls_lock_client.c index 8d2032b2f225..2105a6eaa66c 100644 --- a/net/ceph/cls_lock_client.c +++ b/net/ceph/cls_lock_client.c @@ -32,7 +32,7 @@ int ceph_cls_lock(struct ceph_osd_client *osdc, int desc_len = strlen(desc); void *p, *end; struct page *lock_op_page; - struct timespec mtime; + struct timespec64 mtime; int ret; lock_op_buf_size = name_len + sizeof(__le32) + @@ -63,7 +63,7 @@ int ceph_cls_lock(struct ceph_osd_client *osdc, ceph_encode_string(&p, end, desc, desc_len); /* only support infinite duration */ memset(&mtime, 0, sizeof(mtime)); - ceph_encode_timespec(p, &mtime); + ceph_encode_timespec64(p, &mtime); p += sizeof(struct ceph_timespec); ceph_encode_8(&p, flags); diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index 417df675c71b..3f323ed9df52 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -514,7 +514,7 @@ static int crush_choose_firstn(const struct crush_map *map, in, work->work[-1-in->id], x, r, (choose_args ? - &choose_args[-1-in->id] : 0), + &choose_args[-1-in->id] : NULL), outpos); if (item >= map->max_devices) { dprintk(" bad item %d\n", item); @@ -725,7 +725,7 @@ static void crush_choose_indep(const struct crush_map *map, in, work->work[-1-in->id], x, r, (choose_args ? - &choose_args[-1-in->id] : 0), + &choose_args[-1-in->id] : NULL), outpos); if (item >= map->max_devices) { dprintk(" bad item %d\n", item); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index c6413c360771..0a187196aeed 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1417,11 +1417,11 @@ static void prepare_write_keepalive(struct ceph_connection *con) dout("prepare_write_keepalive %p\n", con); con_out_kvec_reset(con); if (con->peer_features & CEPH_FEATURE_MSGR_KEEPALIVE2) { - struct timespec now; + struct timespec64 now; - ktime_get_real_ts(&now); + ktime_get_real_ts64(&now); con_out_kvec_add(con, sizeof(tag_keepalive2), &tag_keepalive2); - ceph_encode_timespec(&con->out_temp_keepalive2, &now); + ceph_encode_timespec64(&con->out_temp_keepalive2, &now); con_out_kvec_add(con, sizeof(con->out_temp_keepalive2), &con->out_temp_keepalive2); } else { @@ -1434,24 +1434,26 @@ static void prepare_write_keepalive(struct ceph_connection *con) * Connection negotiation. */ -static struct ceph_auth_handshake *get_connect_authorizer(struct ceph_connection *con, - int *auth_proto) +static int get_connect_authorizer(struct ceph_connection *con) { struct ceph_auth_handshake *auth; + int auth_proto; if (!con->ops->get_authorizer) { + con->auth = NULL; con->out_connect.authorizer_protocol = CEPH_AUTH_UNKNOWN; con->out_connect.authorizer_len = 0; - return NULL; + return 0; } - auth = con->ops->get_authorizer(con, auth_proto, con->auth_retry); + auth = con->ops->get_authorizer(con, &auth_proto, con->auth_retry); if (IS_ERR(auth)) - return auth; + return PTR_ERR(auth); - con->auth_reply_buf = auth->authorizer_reply_buf; - con->auth_reply_buf_len = auth->authorizer_reply_buf_len; - return auth; + con->auth = auth; + con->out_connect.authorizer_protocol = cpu_to_le32(auth_proto); + con->out_connect.authorizer_len = cpu_to_le32(auth->authorizer_buf_len); + return 0; } /* @@ -1467,12 +1469,22 @@ static void prepare_write_banner(struct ceph_connection *con) con_flag_set(con, CON_FLAG_WRITE_PENDING); } +static void __prepare_write_connect(struct ceph_connection *con) +{ + con_out_kvec_add(con, sizeof(con->out_connect), &con->out_connect); + if (con->auth) + con_out_kvec_add(con, con->auth->authorizer_buf_len, + con->auth->authorizer_buf); + + con->out_more = 0; + con_flag_set(con, CON_FLAG_WRITE_PENDING); +} + static int prepare_write_connect(struct ceph_connection *con) { unsigned int global_seq = get_global_seq(con->msgr, 0); int proto; - int auth_proto; - struct ceph_auth_handshake *auth; + int ret; switch (con->peer_name.type) { case CEPH_ENTITY_TYPE_MON: @@ -1499,24 +1511,11 @@ static int prepare_write_connect(struct ceph_connection *con) con->out_connect.protocol_version = cpu_to_le32(proto); con->out_connect.flags = 0; - auth_proto = CEPH_AUTH_UNKNOWN; - auth = get_connect_authorizer(con, &auth_proto); - if (IS_ERR(auth)) - return PTR_ERR(auth); - - con->out_connect.authorizer_protocol = cpu_to_le32(auth_proto); - con->out_connect.authorizer_len = auth ? - cpu_to_le32(auth->authorizer_buf_len) : 0; - - con_out_kvec_add(con, sizeof (con->out_connect), - &con->out_connect); - if (auth && auth->authorizer_buf_len) - con_out_kvec_add(con, auth->authorizer_buf_len, - auth->authorizer_buf); - - con->out_more = 0; - con_flag_set(con, CON_FLAG_WRITE_PENDING); + ret = get_connect_authorizer(con); + if (ret) + return ret; + __prepare_write_connect(con); return 0; } @@ -1781,11 +1780,21 @@ static int read_partial_connect(struct ceph_connection *con) if (ret <= 0) goto out; - size = le32_to_cpu(con->in_reply.authorizer_len); - end += size; - ret = read_partial(con, end, size, con->auth_reply_buf); - if (ret <= 0) - goto out; + if (con->auth) { + size = le32_to_cpu(con->in_reply.authorizer_len); + if (size > con->auth->authorizer_reply_buf_len) { + pr_err("authorizer reply too big: %d > %zu\n", size, + con->auth->authorizer_reply_buf_len); + ret = -EINVAL; + goto out; + } + + end += size; + ret = read_partial(con, end, size, + con->auth->authorizer_reply_buf); + if (ret <= 0) + goto out; + } dout("read_partial_connect %p tag %d, con_seq = %u, g_seq = %u\n", con, (int)con->in_reply.tag, @@ -1793,7 +1802,6 @@ static int read_partial_connect(struct ceph_connection *con) le32_to_cpu(con->in_reply.global_seq)); out: return ret; - } /* @@ -2076,12 +2084,27 @@ static int process_connect(struct ceph_connection *con) dout("process_connect on %p tag %d\n", con, (int)con->in_tag); - if (con->auth_reply_buf) { + if (con->auth) { /* * Any connection that defines ->get_authorizer() - * should also define ->verify_authorizer_reply(). + * should also define ->add_authorizer_challenge() and + * ->verify_authorizer_reply(). + * * See get_connect_authorizer(). */ + if (con->in_reply.tag == CEPH_MSGR_TAG_CHALLENGE_AUTHORIZER) { + ret = con->ops->add_authorizer_challenge( + con, con->auth->authorizer_reply_buf, + le32_to_cpu(con->in_reply.authorizer_len)); + if (ret < 0) + return ret; + + con_out_kvec_reset(con); + __prepare_write_connect(con); + prepare_read_connect(con); + return 0; + } + ret = con->ops->verify_authorizer_reply(con); if (ret < 0) { con->error_msg = "bad authorize reply"; @@ -2555,7 +2578,7 @@ static int read_keepalive_ack(struct ceph_connection *con) int ret = read_partial(con, size, size, &ceph_ts); if (ret <= 0) return ret; - ceph_decode_timespec(&con->last_keepalive_ack, &ceph_ts); + ceph_decode_timespec64(&con->last_keepalive_ack, &ceph_ts); prepare_read_tag(con); return 1; } @@ -3223,12 +3246,12 @@ bool ceph_con_keepalive_expired(struct ceph_connection *con, { if (interval > 0 && (con->peer_features & CEPH_FEATURE_MSGR_KEEPALIVE2)) { - struct timespec now; - struct timespec ts; - ktime_get_real_ts(&now); - jiffies_to_timespec(interval, &ts); - ts = timespec_add(con->last_keepalive_ack, ts); - return timespec_compare(&now, &ts) >= 0; + struct timespec64 now; + struct timespec64 ts; + ktime_get_real_ts64(&now); + jiffies_to_timespec64(interval, &ts); + ts = timespec64_add(con->last_keepalive_ack, ts); + return timespec64_compare(&now, &ts) >= 0; } return false; } diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index d7a7a2330ef7..18deb3d889c4 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -1249,7 +1249,7 @@ static void dispatch(struct ceph_connection *con, struct ceph_msg *msg) if (monc->client->extra_mon_dispatch && monc->client->extra_mon_dispatch(monc->client, msg) == 0) break; - + pr_err("received unknown message type %d %s\n", type, ceph_msg_type_name(type)); } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index a00c74f1154e..60934bd8796c 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1978,7 +1978,7 @@ static void encode_request_partial(struct ceph_osd_request *req, p += sizeof(struct ceph_blkin_trace_info); ceph_encode_32(&p, 0); /* client_inc, always 0 */ - ceph_encode_timespec(p, &req->r_mtime); + ceph_encode_timespec64(p, &req->r_mtime); p += sizeof(struct ceph_timespec); encode_oloc(&p, end, &req->r_t.target_oloc); @@ -4512,7 +4512,7 @@ ceph_osdc_watch(struct ceph_osd_client *osdc, ceph_oid_copy(&lreq->t.base_oid, oid); ceph_oloc_copy(&lreq->t.base_oloc, oloc); lreq->t.flags = CEPH_OSD_FLAG_WRITE; - ktime_get_real_ts(&lreq->mtime); + ktime_get_real_ts64(&lreq->mtime); lreq->reg_req = alloc_linger_request(lreq); if (!lreq->reg_req) { @@ -4570,7 +4570,7 @@ int ceph_osdc_unwatch(struct ceph_osd_client *osdc, ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid); ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc); req->r_flags = CEPH_OSD_FLAG_WRITE; - ktime_get_real_ts(&req->r_mtime); + ktime_get_real_ts64(&req->r_mtime); osd_req_op_watch_init(req, 0, lreq->linger_id, CEPH_OSD_WATCH_OP_UNWATCH); @@ -4591,7 +4591,7 @@ EXPORT_SYMBOL(ceph_osdc_unwatch); static int osd_req_op_notify_ack_init(struct ceph_osd_request *req, int which, u64 notify_id, u64 cookie, void *payload, - size_t payload_len) + u32 payload_len) { struct ceph_osd_req_op *op; struct ceph_pagelist *pl; @@ -4628,7 +4628,7 @@ int ceph_osdc_notify_ack(struct ceph_osd_client *osdc, u64 notify_id, u64 cookie, void *payload, - size_t payload_len) + u32 payload_len) { struct ceph_osd_request *req; int ret; @@ -4661,7 +4661,7 @@ EXPORT_SYMBOL(ceph_osdc_notify_ack); static int osd_req_op_notify_init(struct ceph_osd_request *req, int which, u64 cookie, u32 prot_ver, u32 timeout, - void *payload, size_t payload_len) + void *payload, u32 payload_len) { struct ceph_osd_req_op *op; struct ceph_pagelist *pl; @@ -4701,7 +4701,7 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc, struct ceph_object_id *oid, struct ceph_object_locator *oloc, void *payload, - size_t payload_len, + u32 payload_len, u32 timeout, struct page ***preply_pages, size_t *preply_len) @@ -5136,7 +5136,7 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino, struct ceph_snap_context *snapc, u64 off, u64 len, u32 truncate_seq, u64 truncate_size, - struct timespec *mtime, + struct timespec64 *mtime, struct page **pages, int num_pages) { struct ceph_osd_request *req; @@ -5393,6 +5393,16 @@ static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con, return auth; } +static int add_authorizer_challenge(struct ceph_connection *con, + void *challenge_buf, int challenge_buf_len) +{ + struct ceph_osd *o = con->private; + struct ceph_osd_client *osdc = o->o_osdc; + struct ceph_auth_client *ac = osdc->client->monc.auth; + + return ceph_auth_add_authorizer_challenge(ac, o->o_auth.authorizer, + challenge_buf, challenge_buf_len); +} static int verify_authorizer_reply(struct ceph_connection *con) { @@ -5442,6 +5452,7 @@ static const struct ceph_connection_operations osd_con_ops = { .put = put_osd_con, .dispatch = dispatch, .get_authorizer = get_authorizer, + .add_authorizer_challenge = add_authorizer_challenge, .verify_authorizer_reply = verify_authorizer_reply, .invalidate_authorizer = invalidate_authorizer, .alloc_msg = alloc_msg, diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c index e560d3975f41..d3736f5bffec 100644 --- a/net/ceph/pagevec.c +++ b/net/ceph/pagevec.c @@ -197,4 +197,3 @@ void ceph_zero_page_vector_range(int off, int len, struct page **pages) } } EXPORT_SYMBOL(ceph_zero_page_vector_range); - diff --git a/net/core/filter.c b/net/core/filter.c index fd423ce3da34..c25eb36f1320 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3246,31 +3246,33 @@ static void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index) } } -static inline bool xdp_map_invalid(const struct bpf_prog *xdp_prog, - unsigned long aux) +void bpf_clear_redirect_map(struct bpf_map *map) { - return (unsigned long)xdp_prog->aux != aux; + struct bpf_redirect_info *ri; + int cpu; + + for_each_possible_cpu(cpu) { + ri = per_cpu_ptr(&bpf_redirect_info, cpu); + /* Avoid polluting remote cacheline due to writes if + * not needed. Once we pass this test, we need the + * cmpxchg() to make sure it hasn't been changed in + * the meantime by remote CPU. + */ + if (unlikely(READ_ONCE(ri->map) == map)) + cmpxchg(&ri->map, map, NULL); + } } static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog) + struct bpf_prog *xdp_prog, struct bpf_map *map) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); - unsigned long map_owner = ri->map_owner; - struct bpf_map *map = ri->map; u32 index = ri->ifindex; void *fwd = NULL; int err; ri->ifindex = 0; - ri->map = NULL; - ri->map_owner = 0; - - if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) { - err = -EFAULT; - map = NULL; - goto err; - } + WRITE_ONCE(ri->map, NULL); fwd = __xdp_map_lookup_elem(map, index); if (!fwd) { @@ -3296,12 +3298,13 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_map *map = READ_ONCE(ri->map); struct net_device *fwd; u32 index = ri->ifindex; int err; - if (ri->map) - return xdp_do_redirect_map(dev, xdp, xdp_prog); + if (map) + return xdp_do_redirect_map(dev, xdp, xdp_prog, map); fwd = dev_get_by_index_rcu(dev_net(dev), index); ri->ifindex = 0; @@ -3325,24 +3328,17 @@ EXPORT_SYMBOL_GPL(xdp_do_redirect); static int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog) + struct bpf_prog *xdp_prog, + struct bpf_map *map) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); - unsigned long map_owner = ri->map_owner; - struct bpf_map *map = ri->map; u32 index = ri->ifindex; void *fwd = NULL; int err = 0; ri->ifindex = 0; - ri->map = NULL; - ri->map_owner = 0; + WRITE_ONCE(ri->map, NULL); - if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) { - err = -EFAULT; - map = NULL; - goto err; - } fwd = __xdp_map_lookup_elem(map, index); if (unlikely(!fwd)) { err = -EINVAL; @@ -3379,13 +3375,14 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_map *map = READ_ONCE(ri->map); u32 index = ri->ifindex; struct net_device *fwd; int err = 0; - if (ri->map) - return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog); - + if (map) + return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, + map); ri->ifindex = 0; fwd = dev_get_by_index_rcu(dev_net(dev), index); if (unlikely(!fwd)) { @@ -3416,8 +3413,7 @@ BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags) ri->ifindex = ifindex; ri->flags = flags; - ri->map = NULL; - ri->map_owner = 0; + WRITE_ONCE(ri->map, NULL); return XDP_REDIRECT; } @@ -3430,8 +3426,8 @@ static const struct bpf_func_proto bpf_xdp_redirect_proto = { .arg2_type = ARG_ANYTHING, }; -BPF_CALL_4(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, u64, flags, - unsigned long, map_owner) +BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, + u64, flags) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); @@ -3440,15 +3436,11 @@ BPF_CALL_4(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, u64, flags ri->ifindex = ifindex; ri->flags = flags; - ri->map = map; - ri->map_owner = map_owner; + WRITE_ONCE(ri->map, map); return XDP_REDIRECT; } -/* Note, arg4 is hidden from users and populated by the verifier - * with the right pointer. - */ static const struct bpf_func_proto bpf_xdp_redirect_map_proto = { .func = bpf_xdp_redirect_map, .gpl_only = false, diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 7232274de334..af6ad467ed61 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -140,6 +140,7 @@ u32 secure_tcp_seq(__be32 saddr, __be32 daddr, &net_secret); return seq_scale(hash); } +EXPORT_SYMBOL_GPL(secure_tcp_seq); u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) { diff --git a/net/core/xdp.c b/net/core/xdp.c index 3dd99e1c04f5..89b6785cef2a 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -98,23 +98,15 @@ static void __xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) { struct xdp_mem_allocator *xa; int id = xdp_rxq->mem.id; - int err; if (id == 0) return; mutex_lock(&mem_id_lock); - xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params); - if (!xa) { - mutex_unlock(&mem_id_lock); - return; - } - - err = rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params); - WARN_ON(err); - - call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free); + xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params); + if (xa && !rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params)) + call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free); mutex_unlock(&mem_id_lock); } diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 3f091ccad9af..f38cb21d773d 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -438,7 +438,8 @@ static int __net_init vti_init_net(struct net *net) if (err) return err; itn = net_generic(net, vti_net_id); - vti_fb_tunnel_init(itn->fb_tunnel_dev); + if (itn->fb_tunnel_dev) + vti_fb_tunnel_init(itn->fb_tunnel_dev); return 0; } diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 622caa4039e0..a5995bb2eaca 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -51,7 +51,7 @@ static const struct tcp_ulp_ops *__tcp_ulp_find_autoload(const char *name) #ifdef CONFIG_MODULES if (!ulp && capable(CAP_NET_ADMIN)) { rcu_read_unlock(); - request_module("%s", name); + request_module("tcp-ulp-%s", name); rcu_read_lock(); ulp = tcp_ulp_find(name); } @@ -129,6 +129,8 @@ void tcp_cleanup_ulp(struct sock *sk) if (icsk->icsk_ulp_ops->release) icsk->icsk_ulp_ops->release(sk); module_put(icsk->icsk_ulp_ops->owner); + + icsk->icsk_ulp_ops = NULL; } /* Change upper layer protocol for socket */ diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index c72ae3a4fe09..38dec9da90d3 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -503,17 +503,9 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) skb->dev = skb_dst(skb)->dev; err = dst_output(t->net, skb->sk, skb); - if (net_xmit_eval(err) == 0) { - struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); - - u64_stats_update_begin(&tstats->syncp); - tstats->tx_bytes += pkt_len; - tstats->tx_packets++; - u64_stats_update_end(&tstats->syncp); - } else { - stats->tx_errors++; - stats->tx_aborted_errors++; - } + if (net_xmit_eval(err) == 0) + err = pkt_len; + iptunnel_xmit_stats(dev, err); return 0; tx_err_link_failure: @@ -1114,6 +1106,8 @@ static int __net_init vti6_init_net(struct net *net) ip6n->tnls[0] = ip6n->tnls_wc; ip6n->tnls[1] = ip6n->tnls_r_l; + if (!net_has_fallback_tunnels(net)) + return 0; err = -ENOMEM; ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6_vti0", NET_NAME_UNKNOWN, vti6_dev_setup); diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index 0fe61ede77c6..c3c6b09acdc4 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -26,6 +26,12 @@ static bool rpfilter_addr_unicast(const struct in6_addr *addr) return addr_type & IPV6_ADDR_UNICAST; } +static bool rpfilter_addr_linklocal(const struct in6_addr *addr) +{ + int addr_type = ipv6_addr_type(addr); + return addr_type & IPV6_ADDR_LINKLOCAL; +} + static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, const struct net_device *dev, u8 flags) { @@ -48,7 +54,11 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, } fl6.flowi6_mark = flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; - if ((flags & XT_RPFILTER_LOOSE) == 0) + + if (rpfilter_addr_linklocal(&iph->saddr)) { + lookup_flags |= RT6_LOOKUP_F_IFACE; + fl6.flowi6_oif = dev->ifindex; + } else if ((flags & XT_RPFILTER_LOOSE) == 0) fl6.flowi6_oif = dev->ifindex; rt = (void *)ip6_route_lookup(net, &fl6, skb, lookup_flags); diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index 05dc1b77e466..cad48d07c818 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -296,10 +296,10 @@ config IP_VS_MH_TAB_INDEX stored in a hash table. This table is assigned by a preference list of the positions to each destination until all slots in the table are filled. The index determines the prime for size of - the table as 251, 509, 1021, 2039, 4093, 8191, 16381, 32749, - 65521 or 131071. When using weights to allow destinations to - receive more connections, the table is assigned an amount - proportional to the weights specified. The table needs to be large + the table as 251, 509, 1021, 2039, 4093, 8191, 16381, 32749, + 65521 or 131071. When using weights to allow destinations to + receive more connections, the table is assigned an amount + proportional to the weights specified. The table needs to be large enough to effectively fit all the destinations multiplied by their respective weights. diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 0edc62910ebf..5b2b17867cb1 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1117,24 +1117,28 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v) #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) seq_printf(seq, "%-3s %pI6 %04X %pI6 %04X " - "%s %04X %-11s %7lu%s\n", + "%s %04X %-11s %7u%s\n", ip_vs_proto_name(cp->protocol), &cp->caddr.in6, ntohs(cp->cport), &cp->vaddr.in6, ntohs(cp->vport), dbuf, ntohs(cp->dport), ip_vs_state_name(cp), - (cp->timer.expires-jiffies)/HZ, pe_data); + jiffies_delta_to_msecs(cp->timer.expires - + jiffies) / 1000, + pe_data); else #endif seq_printf(seq, "%-3s %08X %04X %08X %04X" - " %s %04X %-11s %7lu%s\n", + " %s %04X %-11s %7u%s\n", ip_vs_proto_name(cp->protocol), ntohl(cp->caddr.ip), ntohs(cp->cport), ntohl(cp->vaddr.ip), ntohs(cp->vport), dbuf, ntohs(cp->dport), ip_vs_state_name(cp), - (cp->timer.expires-jiffies)/HZ, pe_data); + jiffies_delta_to_msecs(cp->timer.expires - + jiffies) / 1000, + pe_data); } return 0; } @@ -1179,26 +1183,28 @@ static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v) #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) seq_printf(seq, "%-3s %pI6 %04X %pI6 %04X " - "%s %04X %-11s %-6s %7lu\n", + "%s %04X %-11s %-6s %7u\n", ip_vs_proto_name(cp->protocol), &cp->caddr.in6, ntohs(cp->cport), &cp->vaddr.in6, ntohs(cp->vport), dbuf, ntohs(cp->dport), ip_vs_state_name(cp), ip_vs_origin_name(cp->flags), - (cp->timer.expires-jiffies)/HZ); + jiffies_delta_to_msecs(cp->timer.expires - + jiffies) / 1000); else #endif seq_printf(seq, "%-3s %08X %04X %08X %04X " - "%s %04X %-11s %-6s %7lu\n", + "%s %04X %-11s %-6s %7u\n", ip_vs_proto_name(cp->protocol), ntohl(cp->caddr.ip), ntohs(cp->cport), ntohl(cp->vaddr.ip), ntohs(cp->vport), dbuf, ntohs(cp->dport), ip_vs_state_name(cp), ip_vs_origin_name(cp->flags), - (cp->timer.expires-jiffies)/HZ); + jiffies_delta_to_msecs(cp->timer.expires - + jiffies) / 1000); } return 0; } diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 0679dd101e72..7ca926a03b81 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1972,13 +1972,20 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { /* the destination server is not available */ - if (sysctl_expire_nodest_conn(ipvs)) { + __u32 flags = cp->flags; + + /* when timer already started, silently drop the packet.*/ + if (timer_pending(&cp->timer)) + __ip_vs_conn_put(cp); + else + ip_vs_conn_put(cp); + + if (sysctl_expire_nodest_conn(ipvs) && + !(flags & IP_VS_CONN_F_ONE_PACKET)) { /* try to expire the connection immediately */ ip_vs_conn_expire_now(cp); } - /* don't restart its timer, and silently - drop the packet. */ - __ip_vs_conn_put(cp); + return NF_DROP; } diff --git a/net/netfilter/ipvs/ip_vs_mh.c b/net/netfilter/ipvs/ip_vs_mh.c index 0f795b186eb3..94d9d349ebb0 100644 --- a/net/netfilter/ipvs/ip_vs_mh.c +++ b/net/netfilter/ipvs/ip_vs_mh.c @@ -5,10 +5,10 @@ * */ -/* The mh algorithm is to assign a preference list of all the lookup +/* The mh algorithm is to assign a preference list of all the lookup * table positions to each destination and populate the table with * the most-preferred position of destinations. Then it is to select - * destination with the hash key of source IP address through looking + * destination with the hash key of source IP address through looking * up a the lookup table. * * The algorithm is detailed in: diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index f981bfa8db72..036207ecaf16 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -846,6 +846,21 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[]) #endif } +static int ctnetlink_start(struct netlink_callback *cb) +{ + const struct nlattr * const *cda = cb->data; + struct ctnetlink_filter *filter = NULL; + + if (cda[CTA_MARK] && cda[CTA_MARK_MASK]) { + filter = ctnetlink_alloc_filter(cda); + if (IS_ERR(filter)) + return PTR_ERR(filter); + } + + cb->data = filter; + return 0; +} + static int ctnetlink_filter_match(struct nf_conn *ct, void *data) { struct ctnetlink_filter *filter = data; @@ -1290,19 +1305,12 @@ static int ctnetlink_get_conntrack(struct net *net, struct sock *ctnl, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = ctnetlink_start, .dump = ctnetlink_dump_table, .done = ctnetlink_done, + .data = (void *)cda, }; - if (cda[CTA_MARK] && cda[CTA_MARK_MASK]) { - struct ctnetlink_filter *filter; - - filter = ctnetlink_alloc_filter(cda); - if (IS_ERR(filter)) - return PTR_ERR(filter); - - c.data = filter; - } return netlink_dump_start(ctnl, skb, nlh, &c); } diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 30070732ee50..9f14b0df6960 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -312,7 +312,9 @@ void nf_ct_l4proto_unregister_one(const struct nf_conntrack_l4proto *l4proto) __nf_ct_l4proto_unregister_one(l4proto); mutex_unlock(&nf_ct_proto_mutex); - synchronize_rcu(); + synchronize_net(); + /* Remove all contrack entries for this protocol */ + nf_ct_iterate_destroy(kill_l4proto, (void *)l4proto); } EXPORT_SYMBOL_GPL(nf_ct_l4proto_unregister_one); @@ -333,14 +335,17 @@ static void nf_ct_l4proto_unregister(const struct nf_conntrack_l4proto * const l4proto[], unsigned int num_proto) { + int i; + mutex_lock(&nf_ct_proto_mutex); - while (num_proto-- != 0) - __nf_ct_l4proto_unregister_one(l4proto[num_proto]); + for (i = 0; i < num_proto; i++) + __nf_ct_l4proto_unregister_one(l4proto[i]); mutex_unlock(&nf_ct_proto_mutex); synchronize_net(); - /* Remove all contrack entries for this protocol */ - nf_ct_iterate_destroy(kill_l4proto, (void *)l4proto); + + for (i = 0; i < num_proto; i++) + nf_ct_iterate_destroy(kill_l4proto, (void *)l4proto[i]); } static int diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 67cdd5c4f4f5..1dca5683f59f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3354,7 +3354,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, struct nft_set *set; struct nft_ctx ctx; char *name; - unsigned int size; + u64 size; u64 timeout; u32 ktype, dtype, flags, policy, gc_int, objtype; struct nft_set_desc desc; @@ -5925,10 +5925,7 @@ static int nf_tables_flowtable_event(struct notifier_block *this, if (event != NETDEV_UNREGISTER) return 0; - net = maybe_get_net(dev_net(dev)); - if (!net) - return 0; - + net = dev_net(dev); mutex_lock(&net->nft.commit_mutex); list_for_each_entry(table, &net->nft.tables, list) { list_for_each_entry(flowtable, &table->flowtables, list) { @@ -5936,7 +5933,7 @@ static int nf_tables_flowtable_event(struct notifier_block *this, } } mutex_unlock(&net->nft.commit_mutex); - put_net(net); + return NOTIFY_DONE; } @@ -7273,21 +7270,36 @@ static int __init nf_tables_module_init(void) { int err; - nft_chain_filter_init(); + err = register_pernet_subsys(&nf_tables_net_ops); + if (err < 0) + return err; + + err = nft_chain_filter_init(); + if (err < 0) + goto err1; err = nf_tables_core_module_init(); if (err < 0) - return err; + goto err2; - err = nfnetlink_subsys_register(&nf_tables_subsys); + err = register_netdevice_notifier(&nf_tables_flowtable_notifier); if (err < 0) - goto err; + goto err3; - register_netdevice_notifier(&nf_tables_flowtable_notifier); + /* must be last */ + err = nfnetlink_subsys_register(&nf_tables_subsys); + if (err < 0) + goto err4; - return register_pernet_subsys(&nf_tables_net_ops); -err: + return err; +err4: + unregister_netdevice_notifier(&nf_tables_flowtable_notifier); +err3: nf_tables_core_module_exit(); +err2: + nft_chain_filter_fini(); +err1: + unregister_pernet_subsys(&nf_tables_net_ops); return err; } diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index a0e5adf0b3b6..8fa8bf7c48e6 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -238,29 +238,33 @@ static const struct nla_policy filter_policy[NFACCT_FILTER_MAX + 1] = { [NFACCT_FILTER_VALUE] = { .type = NLA_U32 }, }; -static struct nfacct_filter * -nfacct_filter_alloc(const struct nlattr * const attr) +static int nfnl_acct_start(struct netlink_callback *cb) { - struct nfacct_filter *filter; + const struct nlattr *const attr = cb->data; struct nlattr *tb[NFACCT_FILTER_MAX + 1]; + struct nfacct_filter *filter; int err; + if (!attr) + return 0; + err = nla_parse_nested(tb, NFACCT_FILTER_MAX, attr, filter_policy, NULL); if (err < 0) - return ERR_PTR(err); + return err; if (!tb[NFACCT_FILTER_MASK] || !tb[NFACCT_FILTER_VALUE]) - return ERR_PTR(-EINVAL); + return -EINVAL; filter = kzalloc(sizeof(struct nfacct_filter), GFP_KERNEL); if (!filter) - return ERR_PTR(-ENOMEM); + return -ENOMEM; filter->mask = ntohl(nla_get_be32(tb[NFACCT_FILTER_MASK])); filter->value = ntohl(nla_get_be32(tb[NFACCT_FILTER_VALUE])); + cb->data = filter; - return filter; + return 0; } static int nfnl_acct_get(struct net *net, struct sock *nfnl, @@ -275,18 +279,11 @@ static int nfnl_acct_get(struct net *net, struct sock *nfnl, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = nfnl_acct_dump, + .start = nfnl_acct_start, .done = nfnl_acct_done, + .data = (void *)tb[NFACCT_FILTER], }; - if (tb[NFACCT_FILTER]) { - struct nfacct_filter *filter; - - filter = nfacct_filter_alloc(tb[NFACCT_FILTER]); - if (IS_ERR(filter)) - return PTR_ERR(filter); - - c.data = filter; - } return netlink_dump_start(nfnl, skb, nlh, &c); } diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index ea5b7c4944f6..3fd540b2c6ba 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -293,6 +293,13 @@ static void nft_netdev_event(unsigned long event, struct net_device *dev, if (strcmp(basechain->dev_name, dev->name) != 0) return; + /* UNREGISTER events are also happpening on netns exit. + * + * Altough nf_tables core releases all tables/chains, only + * this event handler provides guarantee that + * basechain.ops->dev is still accessible, so we cannot + * skip exiting net namespaces. + */ __nft_release_basechain(ctx); break; case NETDEV_CHANGENAME: @@ -318,10 +325,6 @@ static int nf_tables_netdev_event(struct notifier_block *this, event != NETDEV_CHANGENAME) return NOTIFY_DONE; - ctx.net = maybe_get_net(ctx.net); - if (!ctx.net) - return NOTIFY_DONE; - mutex_lock(&ctx.net->nft.commit_mutex); list_for_each_entry(table, &ctx.net->nft.tables, list) { if (table->family != NFPROTO_NETDEV) @@ -338,7 +341,6 @@ static int nf_tables_netdev_event(struct notifier_block *this, } } mutex_unlock(&ctx.net->nft.commit_mutex); - put_net(ctx.net); return NOTIFY_DONE; } @@ -392,7 +394,7 @@ int __init nft_chain_filter_init(void) return 0; } -void __exit nft_chain_filter_fini(void) +void nft_chain_filter_fini(void) { nft_chain_filter_bridge_fini(); nft_chain_filter_inet_fini(); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 4855d4ce1c8f..26a8baebd072 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -832,12 +832,13 @@ static int nft_ct_timeout_obj_init(const struct nft_ctx *ctx, __u8 l4num; int ret; - if (!tb[NFTA_CT_TIMEOUT_L3PROTO] || - !tb[NFTA_CT_TIMEOUT_L4PROTO] || + if (!tb[NFTA_CT_TIMEOUT_L4PROTO] || !tb[NFTA_CT_TIMEOUT_DATA]) return -EINVAL; - l3num = ntohs(nla_get_be16(tb[NFTA_CT_TIMEOUT_L3PROTO])); + if (tb[NFTA_CT_TIMEOUT_L3PROTO]) + l3num = ntohs(nla_get_be16(tb[NFTA_CT_TIMEOUT_L3PROTO])); + l4num = nla_get_u8(tb[NFTA_CT_TIMEOUT_L4PROTO]); priv->l4proto = l4num; diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 81184c244d1a..6e91a37d57f2 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -187,8 +187,6 @@ static int nft_dynset_init(const struct nft_ctx *ctx, if (tb[NFTA_DYNSET_EXPR] != NULL) { if (!(set->flags & NFT_SET_EVAL)) return -EINVAL; - if (!nft_set_is_anonymous(set)) - return -EOPNOTSUPP; priv->expr = nft_expr_init(ctx, tb[NFTA_DYNSET_EXPR]); if (IS_ERR(priv->expr)) diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 128bc16f52dd..f866bd41e5d2 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -248,13 +248,13 @@ static inline u32 nft_bitmap_size(u32 klen) return ((2 << ((klen * BITS_PER_BYTE) - 1)) / BITS_PER_BYTE) << 1; } -static inline u32 nft_bitmap_total_size(u32 klen) +static inline u64 nft_bitmap_total_size(u32 klen) { return sizeof(struct nft_bitmap) + nft_bitmap_size(klen); } -static unsigned int nft_bitmap_privsize(const struct nlattr * const nla[], - const struct nft_set_desc *desc) +static u64 nft_bitmap_privsize(const struct nlattr * const nla[], + const struct nft_set_desc *desc) { u32 klen = ntohl(nla_get_be32(nla[NFTA_SET_KEY_LEN])); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 90c3e7e6cacb..015124e649cb 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -341,8 +341,8 @@ schedule: nft_set_gc_interval(set)); } -static unsigned int nft_rhash_privsize(const struct nlattr * const nla[], - const struct nft_set_desc *desc) +static u64 nft_rhash_privsize(const struct nlattr * const nla[], + const struct nft_set_desc *desc) { return sizeof(struct nft_rhash); } @@ -585,8 +585,8 @@ cont: } } -static unsigned int nft_hash_privsize(const struct nlattr * const nla[], - const struct nft_set_desc *desc) +static u64 nft_hash_privsize(const struct nlattr * const nla[], + const struct nft_set_desc *desc) { return sizeof(struct nft_hash) + nft_hash_buckets(desc->size) * sizeof(struct hlist_head); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 9873d734b494..55e2d9215c0d 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -411,8 +411,8 @@ static void nft_rbtree_gc(struct work_struct *work) nft_set_gc_interval(set)); } -static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[], - const struct nft_set_desc *desc) +static u64 nft_rbtree_privsize(const struct nlattr * const nla[], + const struct nft_set_desc *desc) { return sizeof(struct nft_rbtree); } diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index eff99dffc842..f92a82c73880 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -82,13 +82,15 @@ static void nft_tproxy_eval_v6(const struct nft_expr *expr, const struct nft_tproxy *priv = nft_expr_priv(expr); struct sk_buff *skb = pkt->skb; const struct ipv6hdr *iph = ipv6_hdr(skb); - struct in6_addr taddr = {0}; + struct in6_addr taddr; int thoff = pkt->xt.thoff; struct udphdr _hdr, *hp; __be16 tport = 0; struct sock *sk; int l4proto; + memset(&taddr, 0, sizeof(taddr)); + if (!pkt->tprot_set) { regs->verdict.code = NFT_BREAK; return; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index d0d8397c9588..aecadd471e1d 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1178,12 +1178,7 @@ struct xt_table_info *xt_alloc_table_info(unsigned int size) if (sz < sizeof(*info) || sz >= XT_MAX_TABLE_SIZE) return NULL; - /* __GFP_NORETRY is not fully supported by kvmalloc but it should - * work reasonably well if sz is too large and bail out rather - * than shoot all processes down before realizing there is nothing - * more to reclaim. - */ - info = kvmalloc(sz, GFP_KERNEL | __GFP_NORETRY); + info = kvmalloc(sz, GFP_KERNEL_ACCOUNT); if (!info) return NULL; diff --git a/net/rds/ib.c b/net/rds/ib.c index 89c6333ecd39..c1d97640c0be 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -144,7 +144,7 @@ static void rds_ib_add_one(struct ib_device *device) INIT_WORK(&rds_ibdev->free_work, rds_ib_dev_free); rds_ibdev->max_wrs = device->attrs.max_qp_wr; - rds_ibdev->max_sge = min(device->attrs.max_sge, RDS_IB_MAX_SGE); + rds_ibdev->max_sge = min(device->attrs.max_send_sge, RDS_IB_MAX_SGE); has_fr = (device->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS); diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c index 8596eed6d9a8..6431a023ac89 100644 --- a/net/rds/ib_frmr.c +++ b/net/rds/ib_frmr.c @@ -103,7 +103,6 @@ static void rds_ib_free_frmr(struct rds_ib_mr *ibmr, bool drop) static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr) { struct rds_ib_frmr *frmr = &ibmr->u.frmr; - struct ib_send_wr *failed_wr; struct ib_reg_wr reg_wr; int ret, off = 0; @@ -136,9 +135,7 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr) IB_ACCESS_REMOTE_WRITE; reg_wr.wr.send_flags = IB_SEND_SIGNALED; - failed_wr = ®_wr.wr; - ret = ib_post_send(ibmr->ic->i_cm_id->qp, ®_wr.wr, &failed_wr); - WARN_ON(failed_wr != ®_wr.wr); + ret = ib_post_send(ibmr->ic->i_cm_id->qp, ®_wr.wr, NULL); if (unlikely(ret)) { /* Failure here can be because of -ENOMEM as well */ frmr->fr_state = FRMR_IS_STALE; @@ -231,7 +228,7 @@ out_unmap: static int rds_ib_post_inv(struct rds_ib_mr *ibmr) { - struct ib_send_wr *s_wr, *failed_wr; + struct ib_send_wr *s_wr; struct rds_ib_frmr *frmr = &ibmr->u.frmr; struct rdma_cm_id *i_cm_id = ibmr->ic->i_cm_id; int ret = -EINVAL; @@ -256,9 +253,7 @@ static int rds_ib_post_inv(struct rds_ib_mr *ibmr) s_wr->ex.invalidate_rkey = frmr->mr->rkey; s_wr->send_flags = IB_SEND_SIGNALED; - failed_wr = s_wr; - ret = ib_post_send(i_cm_id->qp, s_wr, &failed_wr); - WARN_ON(failed_wr != s_wr); + ret = ib_post_send(i_cm_id->qp, s_wr, NULL); if (unlikely(ret)) { frmr->fr_state = FRMR_IS_STALE; frmr->fr_inv = false; diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index d300186b8dc0..2f16146e4ec9 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -381,7 +381,6 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp) { struct rds_ib_connection *ic = conn->c_transport_data; struct rds_ib_recv_work *recv; - struct ib_recv_wr *failed_wr; unsigned int posted = 0; int ret = 0; bool can_wait = !!(gfp & __GFP_DIRECT_RECLAIM); @@ -415,7 +414,7 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp) &recv->r_frag->f_sg)); /* XXX when can this fail? */ - ret = ib_post_recv(ic->i_cm_id->qp, &recv->r_wr, &failed_wr); + ret = ib_post_recv(ic->i_cm_id->qp, &recv->r_wr, NULL); if (ret) { rds_ib_conn_error(conn, "recv post on " "%pI6c returned %d, disconnecting and " @@ -648,7 +647,6 @@ static u64 rds_ib_get_ack(struct rds_ib_connection *ic) static void rds_ib_send_ack(struct rds_ib_connection *ic, unsigned int adv_credits) { struct rds_header *hdr = ic->i_ack; - struct ib_send_wr *failed_wr; u64 seq; int ret; @@ -661,7 +659,7 @@ static void rds_ib_send_ack(struct rds_ib_connection *ic, unsigned int adv_credi rds_message_make_checksum(hdr); ic->i_ack_queued = jiffies; - ret = ib_post_send(ic->i_cm_id->qp, &ic->i_ack_wr, &failed_wr); + ret = ib_post_send(ic->i_cm_id->qp, &ic->i_ack_wr, NULL); if (unlikely(ret)) { /* Failed to send. Release the WR, and * force another ACK. diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index c8dd3125d398..2dcb555e6350 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -492,7 +492,7 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, struct rds_ib_send_work *send = NULL; struct rds_ib_send_work *first; struct rds_ib_send_work *prev; - struct ib_send_wr *failed_wr; + const struct ib_send_wr *failed_wr; struct scatterlist *scat; u32 pos; u32 i; @@ -758,7 +758,7 @@ int rds_ib_xmit_atomic(struct rds_connection *conn, struct rm_atomic_op *op) { struct rds_ib_connection *ic = conn->c_transport_data; struct rds_ib_send_work *send = NULL; - struct ib_send_wr *failed_wr; + const struct ib_send_wr *failed_wr; u32 pos; u32 work_alloc; int ret; @@ -846,7 +846,7 @@ int rds_ib_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op) struct rds_ib_send_work *send = NULL; struct rds_ib_send_work *first; struct rds_ib_send_work *prev; - struct ib_send_wr *failed_wr; + const struct ib_send_wr *failed_wr; struct scatterlist *scat; unsigned long len; u64 remote_addr = op->op_remote_addr; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 9b30e62805c7..d30b23e42436 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -147,7 +147,7 @@ static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act, struct tcf_t tm; int ret; - spin_lock(&prog->tcf_lock); + spin_lock_bh(&prog->tcf_lock); opt.action = prog->tcf_action; if (nla_put(skb, TCA_ACT_BPF_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -164,11 +164,11 @@ static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act, TCA_ACT_BPF_PAD)) goto nla_put_failure; - spin_unlock(&prog->tcf_lock); + spin_unlock_bh(&prog->tcf_lock); return skb->len; nla_put_failure: - spin_unlock(&prog->tcf_lock); + spin_unlock_bh(&prog->tcf_lock); nlmsg_trim(skb, tp); return -1; } @@ -340,7 +340,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, prog = to_bpf(*act); - spin_lock(&prog->tcf_lock); + spin_lock_bh(&prog->tcf_lock); if (res != ACT_P_CREATED) tcf_bpf_prog_fill_cfg(prog, &old); @@ -352,7 +352,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, prog->tcf_action = parm->action; rcu_assign_pointer(prog->filter, cfg.filter); - spin_unlock(&prog->tcf_lock); + spin_unlock_bh(&prog->tcf_lock); if (res == ACT_P_CREATED) { tcf_idr_insert(tn, *act); diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 5596fae4e478..e698d3fe2080 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -96,11 +96,11 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, } params_new->update_flags = parm->update_flags; - spin_lock(&p->tcf_lock); + spin_lock_bh(&p->tcf_lock); p->tcf_action = parm->action; rcu_swap_protected(p->params, params_new, lockdep_is_held(&p->tcf_lock)); - spin_unlock(&p->tcf_lock); + spin_unlock_bh(&p->tcf_lock); if (params_new) kfree_rcu(params_new, rcu); @@ -604,7 +604,7 @@ static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind, }; struct tcf_t t; - spin_lock(&p->tcf_lock); + spin_lock_bh(&p->tcf_lock); params = rcu_dereference_protected(p->params, lockdep_is_held(&p->tcf_lock)); opt.action = p->tcf_action; @@ -616,12 +616,12 @@ static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind, tcf_tm_dump(&t, &p->tcf_tm); if (nla_put_64bit(skb, TCA_CSUM_TM, sizeof(t), &t, TCA_CSUM_PAD)) goto nla_put_failure; - spin_unlock(&p->tcf_lock); + spin_unlock_bh(&p->tcf_lock); return skb->len; nla_put_failure: - spin_unlock(&p->tcf_lock); + spin_unlock_bh(&p->tcf_lock); nlmsg_trim(skb, b); return -1; } diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 52a3e474d822..6a3f25a8ffb3 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -113,7 +113,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, gact = to_gact(*a); - spin_lock(&gact->tcf_lock); + spin_lock_bh(&gact->tcf_lock); gact->tcf_action = parm->action; #ifdef CONFIG_GACT_PROB if (p_parm) { @@ -126,7 +126,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, gact->tcfg_ptype = p_parm->ptype; } #endif - spin_unlock(&gact->tcf_lock); + spin_unlock_bh(&gact->tcf_lock); if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); @@ -183,7 +183,7 @@ static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, }; struct tcf_t t; - spin_lock(&gact->tcf_lock); + spin_lock_bh(&gact->tcf_lock); opt.action = gact->tcf_action; if (nla_put(skb, TCA_GACT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -202,12 +202,12 @@ static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, tcf_tm_dump(&t, &gact->tcf_tm); if (nla_put_64bit(skb, TCA_GACT_TM, sizeof(t), &t, TCA_GACT_PAD)) goto nla_put_failure; - spin_unlock(&gact->tcf_lock); + spin_unlock_bh(&gact->tcf_lock); return skb->len; nla_put_failure: - spin_unlock(&gact->tcf_lock); + spin_unlock_bh(&gact->tcf_lock); nlmsg_trim(skb, b); return -1; } diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index fdb928ca81bb..d1081bdf1bdb 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -551,9 +551,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, NULL, NULL); if (err) { metadata_parse_err: - if (ret == ACT_P_CREATED) - tcf_idr_release(*a, bind); - if (exists) spin_unlock_bh(&ife->tcf_lock); tcf_idr_release(*a, bind); @@ -574,11 +571,10 @@ metadata_parse_err: */ err = use_all_metadata(ife); if (err) { - if (ret == ACT_P_CREATED) - tcf_idr_release(*a, bind); - if (exists) spin_unlock_bh(&ife->tcf_lock); + tcf_idr_release(*a, bind); + kfree(p); return err; } diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 8ec216001077..38fd20f10f67 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -159,14 +159,14 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, } m = to_mirred(*a); - spin_lock(&m->tcf_lock); + spin_lock_bh(&m->tcf_lock); m->tcf_action = parm->action; m->tcfm_eaction = parm->eaction; if (parm->ifindex) { dev = dev_get_by_index(net, parm->ifindex); if (!dev) { - spin_unlock(&m->tcf_lock); + spin_unlock_bh(&m->tcf_lock); tcf_idr_release(*a, bind); return -ENODEV; } @@ -177,7 +177,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, dev_put(dev); m->tcfm_mac_header_xmit = mac_header_xmit; } - spin_unlock(&m->tcf_lock); + spin_unlock_bh(&m->tcf_lock); if (ret == ACT_P_CREATED) { spin_lock(&mirred_list_lock); @@ -305,7 +305,7 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, struct net_device *dev; struct tcf_t t; - spin_lock(&m->tcf_lock); + spin_lock_bh(&m->tcf_lock); opt.action = m->tcf_action; opt.eaction = m->tcfm_eaction; dev = tcf_mirred_dev_dereference(m); @@ -318,12 +318,12 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, tcf_tm_dump(&t, &m->tcf_tm); if (nla_put_64bit(skb, TCA_MIRRED_TM, sizeof(t), &t, TCA_MIRRED_PAD)) goto nla_put_failure; - spin_unlock(&m->tcf_lock); + spin_unlock_bh(&m->tcf_lock); return skb->len; nla_put_failure: - spin_unlock(&m->tcf_lock); + spin_unlock_bh(&m->tcf_lock); nlmsg_trim(skb, b); return -1; } @@ -356,7 +356,7 @@ static int mirred_device_event(struct notifier_block *unused, if (event == NETDEV_UNREGISTER) { spin_lock(&mirred_list_lock); list_for_each_entry(m, &mirred_list, tcfm_list) { - spin_lock(&m->tcf_lock); + spin_lock_bh(&m->tcf_lock); if (tcf_mirred_dev_dereference(m) == dev) { dev_put(dev); /* Note : no rcu grace period necessary, as @@ -364,7 +364,7 @@ static int mirred_device_event(struct notifier_block *unused, */ RCU_INIT_POINTER(m->tcfm_dev, NULL); } - spin_unlock(&m->tcf_lock); + spin_unlock_bh(&m->tcf_lock); } spin_unlock(&mirred_list_lock); } diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 81071afe1b43..207b4132d1b0 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -44,6 +44,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, struct nlattr *tb[TCA_SAMPLE_MAX + 1]; struct psample_group *psample_group; struct tc_sample *parm; + u32 psample_group_num; struct tcf_sample *s; bool exists = false; int ret, err; @@ -78,25 +79,27 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, tcf_idr_release(*a, bind); return -EEXIST; } - s = to_sample(*a); - spin_lock(&s->tcf_lock); - s->tcf_action = parm->action; - s->rate = nla_get_u32(tb[TCA_SAMPLE_RATE]); - s->psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]); - psample_group = psample_group_get(net, s->psample_group_num); + psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]); + psample_group = psample_group_get(net, psample_group_num); if (!psample_group) { - spin_unlock(&s->tcf_lock); tcf_idr_release(*a, bind); return -ENOMEM; } + + s = to_sample(*a); + + spin_lock_bh(&s->tcf_lock); + s->tcf_action = parm->action; + s->rate = nla_get_u32(tb[TCA_SAMPLE_RATE]); + s->psample_group_num = psample_group_num; RCU_INIT_POINTER(s->psample_group, psample_group); if (tb[TCA_SAMPLE_TRUNC_SIZE]) { s->truncate = true; s->trunc_size = nla_get_u32(tb[TCA_SAMPLE_TRUNC_SIZE]); } - spin_unlock(&s->tcf_lock); + spin_unlock_bh(&s->tcf_lock); if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); @@ -183,7 +186,7 @@ static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a, }; struct tcf_t t; - spin_lock(&s->tcf_lock); + spin_lock_bh(&s->tcf_lock); opt.action = s->tcf_action; if (nla_put(skb, TCA_SAMPLE_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -201,12 +204,12 @@ static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a, if (nla_put_u32(skb, TCA_SAMPLE_PSAMPLE_GROUP, s->psample_group_num)) goto nla_put_failure; - spin_unlock(&s->tcf_lock); + spin_unlock_bh(&s->tcf_lock); return skb->len; nla_put_failure: - spin_unlock(&s->tcf_lock); + spin_unlock_bh(&s->tcf_lock); nlmsg_trim(skb, b); return -1; } diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index ba2ae9f75ef5..8f09cf08d8fe 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -354,11 +354,11 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, params_new->tcft_action = parm->t_action; params_new->tcft_enc_metadata = metadata; - spin_lock(&t->tcf_lock); + spin_lock_bh(&t->tcf_lock); t->tcf_action = parm->action; rcu_swap_protected(t->params, params_new, lockdep_is_held(&t->tcf_lock)); - spin_unlock(&t->tcf_lock); + spin_unlock_bh(&t->tcf_lock); if (params_new) kfree_rcu(params_new, rcu); @@ -485,7 +485,7 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, }; struct tcf_t tm; - spin_lock(&t->tcf_lock); + spin_lock_bh(&t->tcf_lock); params = rcu_dereference_protected(t->params, lockdep_is_held(&t->tcf_lock)); opt.action = t->tcf_action; @@ -520,12 +520,12 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, if (nla_put_64bit(skb, TCA_TUNNEL_KEY_TM, sizeof(tm), &tm, TCA_TUNNEL_KEY_PAD)) goto nla_put_failure; - spin_unlock(&t->tcf_lock); + spin_unlock_bh(&t->tcf_lock); return skb->len; nla_put_failure: - spin_unlock(&t->tcf_lock); + spin_unlock_bh(&t->tcf_lock); nlmsg_trim(skb, b); return -1; } diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index d1f5028384c9..209e70ad2c09 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -213,10 +213,10 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, p->tcfv_push_prio = push_prio; p->tcfv_push_proto = push_proto; - spin_lock(&v->tcf_lock); + spin_lock_bh(&v->tcf_lock); v->tcf_action = parm->action; rcu_swap_protected(v->vlan_p, p, lockdep_is_held(&v->tcf_lock)); - spin_unlock(&v->tcf_lock); + spin_unlock_bh(&v->tcf_lock); if (p) kfree_rcu(p, rcu); @@ -249,7 +249,7 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, }; struct tcf_t t; - spin_lock(&v->tcf_lock); + spin_lock_bh(&v->tcf_lock); opt.action = v->tcf_action; p = rcu_dereference_protected(v->vlan_p, lockdep_is_held(&v->tcf_lock)); opt.v_action = p->tcfv_action; @@ -268,12 +268,12 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, tcf_tm_dump(&t, &v->tcf_tm); if (nla_put_64bit(skb, TCA_VLAN_TM, sizeof(t), &t, TCA_VLAN_PAD)) goto nla_put_failure; - spin_unlock(&v->tcf_lock); + spin_unlock_bh(&v->tcf_lock); return skb->len; nla_put_failure: - spin_unlock(&v->tcf_lock); + spin_unlock_bh(&v->tcf_lock); nlmsg_trim(skb, b); return -1; } diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index af16f36ed578..856fa79d4ffd 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -113,6 +113,8 @@ static void mall_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) if (!head) return; + tcf_unbind_filter(tp, &head->res); + if (!tc_skip_hw(head->flags)) mall_destroy_hw_filter(tp, head, (unsigned long) head, extack); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index a46418f45ecd..e871368500e3 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -16,6 +16,7 @@ #include <net/tcp.h> #include <net/sock.h> #include <rdma/ib_verbs.h> +#include <rdma/ib_cache.h> #include "smc.h" #include "smc_clc.h" diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 2cc64bc8ae20..e519ef29c0ff 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -16,6 +16,7 @@ #include <linux/workqueue.h> #include <linux/scatterlist.h> #include <rdma/ib_verbs.h> +#include <rdma/ib_cache.h> #include "smc_pnet.h" #include "smc_ib.h" @@ -144,17 +145,21 @@ out: static int smc_ib_fill_mac(struct smc_ib_device *smcibdev, u8 ibport) { - struct ib_gid_attr gattr; - union ib_gid gid; - int rc; + const struct ib_gid_attr *attr; + int rc = 0; - rc = ib_query_gid(smcibdev->ibdev, ibport, 0, &gid, &gattr); - if (rc || !gattr.ndev) + attr = rdma_get_gid_attr(smcibdev->ibdev, ibport, 0); + if (IS_ERR(attr)) return -ENODEV; - memcpy(smcibdev->mac[ibport - 1], gattr.ndev->dev_addr, ETH_ALEN); - dev_put(gattr.ndev); - return 0; + if (attr->ndev) + memcpy(smcibdev->mac[ibport - 1], attr->ndev->dev_addr, + ETH_ALEN); + else + rc = -ENODEV; + + rdma_put_gid_attr(attr); + return rc; } /* Create an identifier unique for this instance of SMC-R. @@ -179,29 +184,27 @@ bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport) int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, unsigned short vlan_id, u8 gid[], u8 *sgid_index) { - struct ib_gid_attr gattr; - union ib_gid _gid; + const struct ib_gid_attr *attr; int i; for (i = 0; i < smcibdev->pattr[ibport - 1].gid_tbl_len; i++) { - memset(&_gid, 0, SMC_GID_SIZE); - memset(&gattr, 0, sizeof(gattr)); - if (ib_query_gid(smcibdev->ibdev, ibport, i, &_gid, &gattr)) + attr = rdma_get_gid_attr(smcibdev->ibdev, ibport, i); + if (IS_ERR(attr)) continue; - if (!gattr.ndev) - continue; - if (((!vlan_id && !is_vlan_dev(gattr.ndev)) || - (vlan_id && is_vlan_dev(gattr.ndev) && - vlan_dev_vlan_id(gattr.ndev) == vlan_id)) && - gattr.gid_type == IB_GID_TYPE_IB) { + + if (attr->ndev && + ((!vlan_id && !is_vlan_dev(attr->ndev)) || + (vlan_id && is_vlan_dev(attr->ndev) && + vlan_dev_vlan_id(attr->ndev) == vlan_id)) && + attr->gid_type == IB_GID_TYPE_ROCE) { if (gid) - memcpy(gid, &_gid, SMC_GID_SIZE); + memcpy(gid, &attr->gid, SMC_GID_SIZE); if (sgid_index) - *sgid_index = i; - dev_put(gattr.ndev); + *sgid_index = attr->index; + rdma_put_gid_attr(attr); return 0; } - dev_put(gattr.ndev); + rdma_put_gid_attr(attr); } return -ENODEV; } diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 2f5e324e54b9..d8366ed51757 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -270,7 +270,6 @@ static int smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset, int num_sges, struct ib_sge sges[]) { struct smc_link_group *lgr = conn->lgr; - struct ib_send_wr *failed_wr = NULL; struct ib_rdma_wr rdma_wr; struct smc_link *link; int rc; @@ -288,7 +287,7 @@ static int smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset, /* offset within RMBE */ peer_rmbe_offset; rdma_wr.rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey; - rc = ib_post_send(link->roce_qp, &rdma_wr.wr, &failed_wr); + rc = ib_post_send(link->roce_qp, &rdma_wr.wr, NULL); if (rc) { conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1; smc_lgr_terminate(lgr); diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index f856b8402b3f..3c458d279855 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -232,15 +232,13 @@ int smc_wr_tx_put_slot(struct smc_link *link, */ int smc_wr_tx_send(struct smc_link *link, struct smc_wr_tx_pend_priv *priv) { - struct ib_send_wr *failed_wr = NULL; struct smc_wr_tx_pend *pend; int rc; ib_req_notify_cq(link->smcibdev->roce_cq_send, IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS); pend = container_of(priv, struct smc_wr_tx_pend, priv); - rc = ib_post_send(link->roce_qp, &link->wr_tx_ibs[pend->idx], - &failed_wr); + rc = ib_post_send(link->roce_qp, &link->wr_tx_ibs[pend->idx], NULL); if (rc) { smc_wr_tx_put_slot(link, priv); smc_lgr_terminate(smc_get_lgr(link)); @@ -251,7 +249,6 @@ int smc_wr_tx_send(struct smc_link *link, struct smc_wr_tx_pend_priv *priv) /* Register a memory region and wait for result. */ int smc_wr_reg_send(struct smc_link *link, struct ib_mr *mr) { - struct ib_send_wr *failed_wr = NULL; int rc; ib_req_notify_cq(link->smcibdev->roce_cq_send, @@ -260,9 +257,7 @@ int smc_wr_reg_send(struct smc_link *link, struct ib_mr *mr) link->wr_reg.wr.wr_id = (u64)(uintptr_t)mr; link->wr_reg.mr = mr; link->wr_reg.key = mr->rkey; - failed_wr = &link->wr_reg.wr; - rc = ib_post_send(link->roce_qp, &link->wr_reg.wr, &failed_wr); - WARN_ON(failed_wr != &link->wr_reg.wr); + rc = ib_post_send(link->roce_qp, &link->wr_reg.wr, NULL); if (rc) return rc; diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h index 210bec3c3ebe..1d85bb14fd6f 100644 --- a/net/smc/smc_wr.h +++ b/net/smc/smc_wr.h @@ -63,7 +63,6 @@ static inline void smc_wr_tx_set_wr_id(atomic_long_t *wr_tx_id, long val) /* post a new receive work request to fill a completed old work request entry */ static inline int smc_wr_rx_post(struct smc_link *link) { - struct ib_recv_wr *bad_recv_wr = NULL; int rc; u64 wr_id, temp_wr_id; u32 index; @@ -72,7 +71,7 @@ static inline int smc_wr_rx_post(struct smc_link *link) temp_wr_id = wr_id; index = do_div(temp_wr_id, link->wr_rx_cnt); link->wr_rx_ibs[index].wr_id = wr_id; - rc = ib_post_recv(link->roce_qp, &link->wr_rx_ibs[index], &bad_recv_wr); + rc = ib_post_recv(link->roce_qp, &link->wr_rx_ibs[index], NULL); return rc; } diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index d2623b9f23d6..305ecea92170 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -50,7 +50,7 @@ static int param_set_hashtbl_sz(const char *val, const struct kernel_param *kp) if (!val) goto out_inval; ret = kstrtoul(val, 0, &num); - if (ret == -EINVAL) + if (ret) goto out_inval; nbits = fls(num - 1); if (nbits > MAX_HASHTABLE_BITS || nbits < 2) @@ -253,7 +253,7 @@ rpcauth_list_flavors(rpc_authflavor_t *array, int size) EXPORT_SYMBOL_GPL(rpcauth_list_flavors); struct rpc_auth * -rpcauth_create(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) +rpcauth_create(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) { struct rpc_auth *auth; const struct rpc_authops *ops; diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 0fc397fae42b..21c0aa0a0d1d 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -284,7 +284,12 @@ err: return p; } -#define UPCALL_BUF_LEN 128 +/* XXX: Need some documentation about why UPCALL_BUF_LEN is so small. + * Is user space expecting no more than UPCALL_BUF_LEN bytes? + * Note that there are now _two_ NI_MAXHOST sized data items + * being passed in this string. + */ +#define UPCALL_BUF_LEN 256 struct gss_upcall_msg { refcount_t count; @@ -456,18 +461,44 @@ static int gss_encode_v1_msg(struct gss_upcall_msg *gss_msg, buflen -= len; p += len; gss_msg->msg.len = len; + + /* + * target= is a full service principal that names the remote + * identity that we are authenticating to. + */ if (target_name) { len = scnprintf(p, buflen, "target=%s ", target_name); buflen -= len; p += len; gss_msg->msg.len += len; } - if (service_name != NULL) { - len = scnprintf(p, buflen, "service=%s ", service_name); + + /* + * gssd uses service= and srchost= to select a matching key from + * the system's keytab to use as the source principal. + * + * service= is the service name part of the source principal, + * or "*" (meaning choose any). + * + * srchost= is the hostname part of the source principal. When + * not provided, gssd uses the local hostname. + */ + if (service_name) { + char *c = strchr(service_name, '@'); + + if (!c) + len = scnprintf(p, buflen, "service=%s ", + service_name); + else + len = scnprintf(p, buflen, + "service=%.*s srchost=%s ", + (int)(c - service_name), + service_name, c + 1); buflen -= len; p += len; gss_msg->msg.len += len; } + if (mech->gm_upcall_enctypes) { len = scnprintf(p, buflen, "enctypes=%s ", mech->gm_upcall_enctypes); @@ -985,7 +1016,7 @@ static void gss_pipe_free(struct gss_pipe *p) * parameters based on the input flavor (which must be a pseudoflavor) */ static struct gss_auth * -gss_create_new(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) +gss_create_new(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) { rpc_authflavor_t flavor = args->pseudoflavor; struct gss_auth *gss_auth; @@ -1132,7 +1163,7 @@ gss_destroy(struct rpc_auth *auth) * (which is guaranteed to last as long as any of its descendants). */ static struct gss_auth * -gss_auth_find_or_add_hashed(struct rpc_auth_create_args *args, +gss_auth_find_or_add_hashed(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt, struct gss_auth *new) { @@ -1169,7 +1200,8 @@ out: } static struct gss_auth * -gss_create_hashed(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) +gss_create_hashed(const struct rpc_auth_create_args *args, + struct rpc_clnt *clnt) { struct gss_auth *gss_auth; struct gss_auth *new; @@ -1188,7 +1220,7 @@ out: } static struct rpc_auth * -gss_create(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) +gss_create(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) { struct gss_auth *gss_auth; struct rpc_xprt_switch *xps = rcu_access_pointer(clnt->cl_xpi.xpi_xpswitch); @@ -1571,7 +1603,7 @@ static int gss_cred_is_negative_entry(struct rpc_cred *cred) if (test_bit(RPCAUTH_CRED_NEGATIVE, &cred->cr_flags)) { unsigned long now = jiffies; unsigned long begin, expire; - struct gss_cred *gss_cred; + struct gss_cred *gss_cred; gss_cred = container_of(cred, struct gss_cred, gc_base); begin = gss_cred->gc_upcall_timestamp; diff --git a/net/sunrpc/auth_gss/gss_generic_token.c b/net/sunrpc/auth_gss/gss_generic_token.c index 254defe446a7..fe97f3106536 100644 --- a/net/sunrpc/auth_gss/gss_generic_token.c +++ b/net/sunrpc/auth_gss/gss_generic_token.c @@ -231,4 +231,3 @@ g_verify_token_header(struct xdr_netobj *mech, int *body_size, } EXPORT_SYMBOL_GPL(g_verify_token_header); - diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 8654494b4d0a..0220e1ca5280 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -169,7 +169,7 @@ make_checksum_hmac_md5(struct krb5_ctx *kctx, char *header, int hdrlen, struct scatterlist sg[1]; int err = -1; u8 *checksumdata; - u8 rc4salt[4]; + u8 *rc4salt; struct crypto_ahash *md5; struct crypto_ahash *hmac_md5; struct ahash_request *req; @@ -183,14 +183,18 @@ make_checksum_hmac_md5(struct krb5_ctx *kctx, char *header, int hdrlen, return GSS_S_FAILURE; } + rc4salt = kmalloc_array(4, sizeof(*rc4salt), GFP_NOFS); + if (!rc4salt) + return GSS_S_FAILURE; + if (arcfour_hmac_md5_usage_to_salt(usage, rc4salt)) { dprintk("%s: invalid usage value %u\n", __func__, usage); - return GSS_S_FAILURE; + goto out_free_rc4salt; } checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_NOFS); if (!checksumdata) - return GSS_S_FAILURE; + goto out_free_rc4salt; md5 = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(md5)) @@ -258,6 +262,8 @@ out_free_md5: crypto_free_ahash(md5); out_free_cksum: kfree(checksumdata); +out_free_rc4salt: + kfree(rc4salt); return err ? GSS_S_FAILURE : 0; } @@ -373,7 +379,6 @@ make_checksum_v2(struct krb5_ctx *kctx, char *header, int hdrlen, struct scatterlist sg[1]; int err = -1; u8 *checksumdata; - unsigned int checksumlen; if (kctx->gk5e->keyed_cksum == 0) { dprintk("%s: expected keyed hash for %s\n", @@ -393,7 +398,6 @@ make_checksum_v2(struct krb5_ctx *kctx, char *header, int hdrlen, tfm = crypto_alloc_ahash(kctx->gk5e->cksum_name, 0, CRYPTO_ALG_ASYNC); if (IS_ERR(tfm)) goto out_free_cksum; - checksumlen = crypto_ahash_digestsize(tfm); req = ahash_request_alloc(tfm, GFP_NOFS); if (!req) @@ -1077,4 +1081,3 @@ out_err: dprintk("%s: returning %d\n", __func__, err); return err; } - diff --git a/net/sunrpc/auth_gss/gss_krb5_keys.c b/net/sunrpc/auth_gss/gss_krb5_keys.c index 870133146026..f7fe2d2b851f 100644 --- a/net/sunrpc/auth_gss/gss_krb5_keys.c +++ b/net/sunrpc/auth_gss/gss_krb5_keys.c @@ -324,4 +324,3 @@ u32 gss_krb5_aes_make_key(const struct gss_krb5_enctype *gk5e, err_out: return ret; } - diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c index 94a2b3f082a8..eaad9bc7a0bd 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seal.c +++ b/net/sunrpc/auth_gss/gss_krb5_seal.c @@ -229,4 +229,3 @@ gss_get_mic_kerberos(struct gss_ctx *gss_ctx, struct xdr_buf *text, return gss_get_mic_v2(ctx, text, token); } } - diff --git a/net/sunrpc/auth_gss/gss_krb5_unseal.c b/net/sunrpc/auth_gss/gss_krb5_unseal.c index b601a73cc9db..ef2b25b86d2f 100644 --- a/net/sunrpc/auth_gss/gss_krb5_unseal.c +++ b/net/sunrpc/auth_gss/gss_krb5_unseal.c @@ -225,4 +225,3 @@ gss_verify_mic_kerberos(struct gss_ctx *gss_ctx, return gss_verify_mic_v2(ctx, message_buffer, read_token); } } - diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index a737c2da0837..39a2e672900b 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -440,7 +440,6 @@ static u32 gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, struct page **pages) { - int blocksize; u8 *ptr, *plainhdr; s32 now; u8 flags = 0x00; @@ -473,7 +472,6 @@ gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset, *ptr++ = 0xff; be16ptr = (__be16 *)ptr; - blocksize = crypto_skcipher_blocksize(kctx->acceptor_enc); *be16ptr++ = 0; /* "inner" token header always uses 0 for RRC */ *be16ptr++ = 0; @@ -623,4 +621,3 @@ gss_unwrap_kerberos(struct gss_ctx *gctx, int offset, struct xdr_buf *buf) return gss_unwrap_kerberos_v2(kctx, offset, buf); } } - diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index 1c7c49dbf8ba..73dcda060335 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -234,6 +234,35 @@ static int gssp_alloc_receive_pages(struct gssx_arg_accept_sec_context *arg) return 0; } +static char *gssp_stringify(struct xdr_netobj *netobj) +{ + return kstrndup(netobj->data, netobj->len, GFP_KERNEL); +} + +static void gssp_hostbased_service(char **principal) +{ + char *c; + + if (!*principal) + return; + + /* terminate and remove realm part */ + c = strchr(*principal, '@'); + if (c) { + *c = '\0'; + + /* change service-hostname delimiter */ + c = strchr(*principal, '/'); + if (c) + *c = '@'; + } + if (!c) { + /* not a service principal */ + kfree(*principal); + *principal = NULL; + } +} + /* * Public functions */ @@ -262,6 +291,7 @@ int gssp_accept_sec_context_upcall(struct net *net, */ .exported_context_token.len = GSSX_max_output_handle_sz, .mech.len = GSS_OID_MAX_LEN, + .targ_name.display_name.len = GSSX_max_princ_sz, .src_name.display_name.len = GSSX_max_princ_sz }; struct gssx_res_accept_sec_context res = { @@ -275,6 +305,7 @@ int gssp_accept_sec_context_upcall(struct net *net, .rpc_cred = NULL, /* FIXME ? */ }; struct xdr_netobj client_name = { 0 , NULL }; + struct xdr_netobj target_name = { 0, NULL }; int ret; if (data->in_handle.len != 0) @@ -285,8 +316,6 @@ int gssp_accept_sec_context_upcall(struct net *net, if (ret) return ret; - /* use nfs/ for targ_name ? */ - ret = gssp_call(net, &msg); gssp_free_receive_pages(&arg); @@ -304,6 +333,7 @@ int gssp_accept_sec_context_upcall(struct net *net, kfree(rctxh.mech.data); } client_name = rctxh.src_name.display_name; + target_name = rctxh.targ_name.display_name; } if (res.options.count == 1) { @@ -325,32 +355,22 @@ int gssp_accept_sec_context_upcall(struct net *net, } /* convert to GSS_NT_HOSTBASED_SERVICE form and set into creds */ - if (data->found_creds && client_name.data != NULL) { - char *c; - - data->creds.cr_raw_principal = kstrndup(client_name.data, - client_name.len, GFP_KERNEL); - - data->creds.cr_principal = kstrndup(client_name.data, - client_name.len, GFP_KERNEL); - if (data->creds.cr_principal) { - /* terminate and remove realm part */ - c = strchr(data->creds.cr_principal, '@'); - if (c) { - *c = '\0'; - - /* change service-hostname delimiter */ - c = strchr(data->creds.cr_principal, '/'); - if (c) *c = '@'; - } - if (!c) { - /* not a service principal */ - kfree(data->creds.cr_principal); - data->creds.cr_principal = NULL; - } + if (data->found_creds) { + if (client_name.data) { + data->creds.cr_raw_principal = + gssp_stringify(&client_name); + data->creds.cr_principal = + gssp_stringify(&client_name); + gssp_hostbased_service(&data->creds.cr_principal); + } + if (target_name.data) { + data->creds.cr_targ_princ = + gssp_stringify(&target_name); + gssp_hostbased_service(&data->creds.cr_targ_princ); } } kfree(client_name.data); + kfree(target_name.data); return ret; } diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 5089dbb96d58..860f2a1bbb67 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1389,7 +1389,7 @@ static void destroy_use_gss_proxy_proc_entry(struct net *net) struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); if (sn->use_gssp_proc) { - remove_proc_entry("use-gss-proxy", sn->proc_net_rpc); + remove_proc_entry("use-gss-proxy", sn->proc_net_rpc); clear_gssp_clnt(sn); } } diff --git a/net/sunrpc/auth_null.c b/net/sunrpc/auth_null.c index 75d72e109a04..4b48228ee8c7 100644 --- a/net/sunrpc/auth_null.c +++ b/net/sunrpc/auth_null.c @@ -19,7 +19,7 @@ static struct rpc_auth null_auth; static struct rpc_cred null_cred; static struct rpc_auth * -nul_create(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) +nul_create(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) { atomic_inc(&null_auth.au_count); return &null_auth; diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c index dafd6b870ba3..185e56d4f9ae 100644 --- a/net/sunrpc/auth_unix.c +++ b/net/sunrpc/auth_unix.c @@ -30,7 +30,7 @@ static struct rpc_auth unix_auth; static const struct rpc_credops unix_credops; static struct rpc_auth * -unx_create(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) +unx_create(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) { dprintk("RPC: creating UNIX authenticator for client %p\n", clnt); diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index c2c68a15b59d..3c15a99b9700 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -362,4 +362,3 @@ void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied) wake_up(&bc_serv->sv_cb_waitq); spin_unlock(&bc_serv->sv_cb_lock); } - diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index d839c33ae7d9..8ea2f5fadd96 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -892,7 +892,7 @@ rpc_free_client(struct rpc_clnt *clnt) /* * Free an RPC client */ -static struct rpc_clnt * +static struct rpc_clnt * rpc_free_auth(struct rpc_clnt *clnt) { if (clnt->cl_auth == NULL) @@ -965,10 +965,20 @@ out: } EXPORT_SYMBOL_GPL(rpc_bind_new_program); +void rpc_task_release_transport(struct rpc_task *task) +{ + struct rpc_xprt *xprt = task->tk_xprt; + + if (xprt) { + task->tk_xprt = NULL; + xprt_put(xprt); + } +} +EXPORT_SYMBOL_GPL(rpc_task_release_transport); + void rpc_task_release_client(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; - struct rpc_xprt *xprt = task->tk_xprt; if (clnt != NULL) { /* Remove from client task list */ @@ -979,12 +989,14 @@ void rpc_task_release_client(struct rpc_task *task) rpc_release_client(clnt); } + rpc_task_release_transport(task); +} - if (xprt != NULL) { - task->tk_xprt = NULL; - - xprt_put(xprt); - } +static +void rpc_task_set_transport(struct rpc_task *task, struct rpc_clnt *clnt) +{ + if (!task->tk_xprt) + task->tk_xprt = xprt_iter_get_next(&clnt->cl_xpi); } static @@ -992,8 +1004,7 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt) { if (clnt != NULL) { - if (task->tk_xprt == NULL) - task->tk_xprt = xprt_iter_get_next(&clnt->cl_xpi); + rpc_task_set_transport(task, clnt); task->tk_client = clnt; atomic_inc(&clnt->cl_count); if (clnt->cl_softrtry) @@ -1512,6 +1523,7 @@ call_start(struct rpc_task *task) clnt->cl_program->version[clnt->cl_vers]->counts[idx]++; clnt->cl_stats->rpccnt++; task->tk_action = call_reserve; + rpc_task_set_transport(task, clnt); } /* diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index c526f8fb37c9..c7872bc13860 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -213,7 +213,7 @@ static void rpcb_set_local(struct net *net, struct rpc_clnt *clnt, sn->rpcb_local_clnt = clnt; sn->rpcb_local_clnt4 = clnt4; sn->rpcb_is_af_local = is_af_local ? 1 : 0; - smp_wmb(); + smp_wmb(); sn->rpcb_users = 1; dprintk("RPC: created new rpcb local clients (rpcb_local_clnt: " "%p, rpcb_local_clnt4: %p) for net %x%s\n", diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index f68aa46c9dd7..71166b393732 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -208,13 +208,39 @@ static void _print_name(struct seq_file *seq, unsigned int op, seq_printf(seq, "\t%12u: ", op); } -void rpc_print_iostats(struct seq_file *seq, struct rpc_clnt *clnt) +static void _add_rpc_iostats(struct rpc_iostats *a, struct rpc_iostats *b) +{ + a->om_ops += b->om_ops; + a->om_ntrans += b->om_ntrans; + a->om_timeouts += b->om_timeouts; + a->om_bytes_sent += b->om_bytes_sent; + a->om_bytes_recv += b->om_bytes_recv; + a->om_queue = ktime_add(a->om_queue, b->om_queue); + a->om_rtt = ktime_add(a->om_rtt, b->om_rtt); + a->om_execute = ktime_add(a->om_execute, b->om_execute); +} + +static void _print_rpc_iostats(struct seq_file *seq, struct rpc_iostats *stats, + int op, const struct rpc_procinfo *procs) +{ + _print_name(seq, op, procs); + seq_printf(seq, "%lu %lu %lu %Lu %Lu %Lu %Lu %Lu\n", + stats->om_ops, + stats->om_ntrans, + stats->om_timeouts, + stats->om_bytes_sent, + stats->om_bytes_recv, + ktime_to_ms(stats->om_queue), + ktime_to_ms(stats->om_rtt), + ktime_to_ms(stats->om_execute)); +} + +void rpc_clnt_show_stats(struct seq_file *seq, struct rpc_clnt *clnt) { - struct rpc_iostats *stats = clnt->cl_metrics; struct rpc_xprt *xprt; unsigned int op, maxproc = clnt->cl_maxproc; - if (!stats) + if (!clnt->cl_metrics) return; seq_printf(seq, "\tRPC iostats version: %s ", RPC_IOSTATS_VERS); @@ -229,20 +255,18 @@ void rpc_print_iostats(struct seq_file *seq, struct rpc_clnt *clnt) seq_printf(seq, "\tper-op statistics\n"); for (op = 0; op < maxproc; op++) { - struct rpc_iostats *metrics = &stats[op]; - _print_name(seq, op, clnt->cl_procinfo); - seq_printf(seq, "%lu %lu %lu %Lu %Lu %Lu %Lu %Lu\n", - metrics->om_ops, - metrics->om_ntrans, - metrics->om_timeouts, - metrics->om_bytes_sent, - metrics->om_bytes_recv, - ktime_to_ms(metrics->om_queue), - ktime_to_ms(metrics->om_rtt), - ktime_to_ms(metrics->om_execute)); + struct rpc_iostats stats = {}; + struct rpc_clnt *next = clnt; + do { + _add_rpc_iostats(&stats, &next->cl_metrics[op]); + if (next == next->cl_parent) + break; + next = next->cl_parent; + } while (next); + _print_rpc_iostats(seq, &stats, op, clnt->cl_procinfo); } } -EXPORT_SYMBOL_GPL(rpc_print_iostats); +EXPORT_SYMBOL_GPL(rpc_clnt_show_stats); /* * Register/unregister RPC proc files @@ -310,4 +334,3 @@ void rpc_proc_exit(struct net *net) dprintk("RPC: unregistering /proc/net/rpc\n"); remove_proc_entry("rpc", net->proc_net); } - diff --git a/net/sunrpc/sunrpc.h b/net/sunrpc/sunrpc.h index 09a0315ea77b..c9bacb3c930f 100644 --- a/net/sunrpc/sunrpc.h +++ b/net/sunrpc/sunrpc.h @@ -57,4 +57,3 @@ int svc_send_common(struct socket *sock, struct xdr_buf *xdr, int rpc_clients_notifier_register(void); void rpc_clients_notifier_unregister(void); #endif /* _NET_SUNRPC_SUNRPC_H */ - diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 30a4226baf03..d13e05f1a990 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1537,16 +1537,16 @@ EXPORT_SYMBOL_GPL(svc_max_payload); /** * svc_fill_write_vector - Construct data argument for VFS write call * @rqstp: svc_rqst to operate on + * @pages: list of pages containing data payload * @first: buffer containing first section of write payload * @total: total number of bytes of write payload * - * Returns the number of elements populated in the data argument array. + * Fills in rqstp::rq_vec, and returns the number of elements. */ -unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, struct kvec *first, - size_t total) +unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, struct page **pages, + struct kvec *first, size_t total) { struct kvec *vec = rqstp->rq_vec; - struct page **pages; unsigned int i; /* Some types of transport can present the write payload @@ -1560,14 +1560,11 @@ unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, struct kvec *first, ++i; } - WARN_ON_ONCE(rqstp->rq_arg.page_base != 0); - pages = rqstp->rq_arg.pages; while (total) { vec[i].iov_base = page_address(*pages); vec[i].iov_len = min_t(size_t, total, PAGE_SIZE); total -= vec[i].iov_len; ++i; - ++pages; } @@ -1580,65 +1577,48 @@ EXPORT_SYMBOL_GPL(svc_fill_write_vector); * svc_fill_symlink_pathname - Construct pathname argument for VFS symlink call * @rqstp: svc_rqst to operate on * @first: buffer containing first section of pathname + * @p: buffer containing remaining section of pathname * @total: total length of the pathname argument * - * Returns pointer to a NUL-terminated string, or an ERR_PTR. The buffer is - * released automatically when @rqstp is recycled. + * The VFS symlink API demands a NUL-terminated pathname in mapped memory. + * Returns pointer to a NUL-terminated string, or an ERR_PTR. Caller must free + * the returned string. */ char *svc_fill_symlink_pathname(struct svc_rqst *rqstp, struct kvec *first, - size_t total) + void *p, size_t total) { - struct xdr_buf *arg = &rqstp->rq_arg; - struct page **pages; - char *result; - - /* VFS API demands a NUL-terminated pathname. This function - * uses a page from @rqstp as the pathname buffer, to enable - * direct placement. Thus the total buffer size is PAGE_SIZE. - * Space in this buffer for NUL-termination requires that we - * cap the size of the returned symlink pathname just a - * little early. - */ - if (total > PAGE_SIZE - 1) - return ERR_PTR(-ENAMETOOLONG); + size_t len, remaining; + char *result, *dst; - /* Some types of transport can present the pathname entirely - * in rq_arg.pages. If not, then copy the pathname into one - * page. - */ - pages = arg->pages; - WARN_ON_ONCE(arg->page_base != 0); - if (first->iov_base == 0) { - result = page_address(*pages); - result[total] = '\0'; - } else { - size_t len, remaining; - char *dst; + result = kmalloc(total + 1, GFP_KERNEL); + if (!result) + return ERR_PTR(-ESERVERFAULT); - result = page_address(*(rqstp->rq_next_page++)); - dst = result; - remaining = total; + dst = result; + remaining = total; - len = min_t(size_t, total, first->iov_len); + len = min_t(size_t, total, first->iov_len); + if (len) { memcpy(dst, first->iov_base, len); dst += len; remaining -= len; + } - /* No more than one page left */ - if (remaining) { - len = min_t(size_t, remaining, PAGE_SIZE); - memcpy(dst, page_address(*pages), len); - dst += len; - } - - *dst = '\0'; + if (remaining) { + len = min_t(size_t, remaining, PAGE_SIZE); + memcpy(dst, p, len); + dst += len; } - /* Sanity check: we don't allow the pathname argument to + *dst = '\0'; + + /* Sanity check: Linux doesn't allow the pathname argument to * contain a NUL byte. */ - if (strlen(result) != total) + if (strlen(result) != total) { + kfree(result); return ERR_PTR(-EINVAL); + } return result; } EXPORT_SYMBOL_GPL(svc_fill_symlink_pathname); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 3fabf9f6a0f9..a8db2e3f8904 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -880,7 +880,7 @@ static void xprt_wait_on_pinned_rqst(struct rpc_rqst *req) __must_hold(&req->rq_xprt->recv_lock) { struct rpc_task *task = req->rq_task; - + if (task && test_bit(RPC_TASK_MSG_RECV, &task->tk_runstate)) { spin_unlock(&req->rq_xprt->recv_lock); set_bit(RPC_TASK_MSG_RECV_WAIT, &task->tk_runstate); diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index 17fb1e025654..0f7c465d9a5a 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -279,9 +279,7 @@ out_maperr: static int fmr_op_send(struct rpcrdma_ia *ia, struct rpcrdma_req *req) { - struct ib_send_wr *bad_wr; - - return ib_post_send(ia->ri_id->qp, &req->rl_sendctx->sc_wr, &bad_wr); + return ib_post_send(ia->ri_id->qp, &req->rl_sendctx->sc_wr, NULL); } /* Invalidate all memory regions that were registered for "req". diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index c040de196e13..1bb00dd6ccdb 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -464,7 +464,7 @@ out_mapmr_err: static int frwr_op_send(struct rpcrdma_ia *ia, struct rpcrdma_req *req) { - struct ib_send_wr *post_wr, *bad_wr; + struct ib_send_wr *post_wr; struct rpcrdma_mr *mr; post_wr = &req->rl_sendctx->sc_wr; @@ -486,7 +486,7 @@ frwr_op_send(struct rpcrdma_ia *ia, struct rpcrdma_req *req) /* If ib_post_send fails, the next ->send_request for * @req will queue these MWs for recovery. */ - return ib_post_send(ia->ri_id->qp, post_wr, &bad_wr); + return ib_post_send(ia->ri_id->qp, post_wr, NULL); } /* Handle a remotely invalidated mr on the @mrs list @@ -517,7 +517,8 @@ frwr_op_reminv(struct rpcrdma_rep *rep, struct list_head *mrs) static void frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct list_head *mrs) { - struct ib_send_wr *first, **prev, *last, *bad_wr; + struct ib_send_wr *first, **prev, *last; + const struct ib_send_wr *bad_wr; struct rpcrdma_ia *ia = &r_xprt->rx_ia; struct rpcrdma_frwr *frwr; struct rpcrdma_mr *mr; diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index 357ba90c382d..134bef6a451e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -94,7 +94,6 @@ static int read_reset_stat(struct ctl_table *table, int write, atomic_set(stat, 0); else { char str_buf[32]; - char *data; int len = snprintf(str_buf, 32, "%d\n", atomic_read(stat)); if (len >= 32) return -EFAULT; @@ -103,7 +102,6 @@ static int read_reset_stat(struct ctl_table *table, int write, *lenp = 0; return 0; } - data = &str_buf[*ppos]; len -= *ppos; if (len > *lenp) len = *lenp; diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 841fca143804..b24d5b8f2fee 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -229,11 +229,10 @@ void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma, static int __svc_rdma_post_recv(struct svcxprt_rdma *rdma, struct svc_rdma_recv_ctxt *ctxt) { - struct ib_recv_wr *bad_recv_wr; int ret; svc_xprt_get(&rdma->sc_xprt); - ret = ib_post_recv(rdma->sc_qp, &ctxt->rc_recv_wr, &bad_recv_wr); + ret = ib_post_recv(rdma->sc_qp, &ctxt->rc_recv_wr, NULL); trace_svcrdma_post_recv(&ctxt->rc_recv_wr, ret); if (ret) goto err_post; @@ -366,9 +365,6 @@ static void svc_rdma_build_arg_xdr(struct svc_rqst *rqstp, arg->page_base = 0; arg->buflen = ctxt->rc_byte_len; arg->len = ctxt->rc_byte_len; - - rqstp->rq_respages = &rqstp->rq_pages[0]; - rqstp->rq_next_page = rqstp->rq_respages + 1; } /* This accommodates the largest possible Write chunk, @@ -730,6 +726,12 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) svc_rdma_build_arg_xdr(rqstp, ctxt); + /* Prevent svc_xprt_release from releasing pages in rq_pages + * if we return 0 or an error. + */ + rqstp->rq_respages = rqstp->rq_pages; + rqstp->rq_next_page = rqstp->rq_respages; + p = (__be32 *)rqstp->rq_arg.head[0].iov_base; ret = svc_rdma_xdr_decode_req(&rqstp->rq_arg); if (ret < 0) diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index ce3ea8419704..dc1951759a8e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -307,7 +307,8 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc) { struct svcxprt_rdma *rdma = cc->cc_rdma; struct svc_xprt *xprt = &rdma->sc_xprt; - struct ib_send_wr *first_wr, *bad_wr; + struct ib_send_wr *first_wr; + const struct ib_send_wr *bad_wr; struct list_head *tmp; struct ib_cqe *cqe; int ret; @@ -679,6 +680,7 @@ static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp, struct svc_rdma_read_info *info, __be32 *p) { + unsigned int i; int ret; ret = -EINVAL; @@ -701,6 +703,12 @@ static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp, info->ri_chunklen += rs_length; } + /* Pages under I/O have been copied to head->rc_pages. + * Prevent their premature release by svc_xprt_release() . + */ + for (i = 0; i < info->ri_readctxt->rc_page_count; i++) + rqstp->rq_pages[i] = NULL; + return ret; } @@ -816,7 +824,6 @@ int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp, struct svc_rdma_recv_ctxt *head, __be32 *p) { struct svc_rdma_read_info *info; - struct page **page; int ret; /* The request (with page list) is constructed in @@ -843,27 +850,15 @@ int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp, ret = svc_rdma_build_normal_read_chunk(rqstp, info, p); else ret = svc_rdma_build_pz_read_chunk(rqstp, info, p); - - /* Mark the start of the pages that can be used for the reply */ - if (info->ri_pageoff > 0) - info->ri_pageno++; - rqstp->rq_respages = &rqstp->rq_pages[info->ri_pageno]; - rqstp->rq_next_page = rqstp->rq_respages + 1; - if (ret < 0) - goto out; + goto out_err; ret = svc_rdma_post_chunk_ctxt(&info->ri_cc); - -out: - /* Read sink pages have been moved from rqstp->rq_pages to - * head->rc_arg.pages. Force svc_recv to refill those slots - * in rq_pages. - */ - for (page = rqstp->rq_pages; page < rqstp->rq_respages; page++) - *page = NULL; - if (ret < 0) - svc_rdma_read_info_free(info); + goto out_err; + return 0; + +out_err: + svc_rdma_read_info_free(info); return ret; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 4a3efaea277c..8602a5f1b515 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -291,7 +291,6 @@ static void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc) */ int svc_rdma_send(struct svcxprt_rdma *rdma, struct ib_send_wr *wr) { - struct ib_send_wr *bad_wr; int ret; might_sleep(); @@ -311,7 +310,7 @@ int svc_rdma_send(struct svcxprt_rdma *rdma, struct ib_send_wr *wr) } svc_xprt_get(&rdma->sc_xprt); - ret = ib_post_send(rdma->sc_qp, wr, &bad_wr); + ret = ib_post_send(rdma->sc_qp, wr, NULL); trace_svcrdma_post_send(wr, ret); if (ret) { set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags); @@ -657,7 +656,9 @@ static void svc_rdma_save_io_pages(struct svc_rqst *rqstp, ctxt->sc_pages[i] = rqstp->rq_respages[i]; rqstp->rq_respages[i] = NULL; } - rqstp->rq_next_page = rqstp->rq_respages + 1; + + /* Prevent svc_xprt_release from releasing pages in rq_pages */ + rqstp->rq_next_page = rqstp->rq_respages; } /* Prepare the portion of the RPC Reply that will be transmitted diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index e9535a66bab0..2848cafd4a17 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -296,7 +296,6 @@ static int rdma_listen_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) { struct sockaddr *sap = (struct sockaddr *)&cma_id->route.addr.src_addr; - int ret = 0; trace_svcrdma_cm_event(event, sap); @@ -315,7 +314,7 @@ static int rdma_listen_handler(struct rdma_cm_id *cma_id, break; } - return ret; + return 0; } static int rdma_cma_handler(struct rdma_cm_id *cma_id, @@ -476,7 +475,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) /* Qualify the transport resource defaults with the * capabilities of this particular device */ - newxprt->sc_max_send_sges = dev->attrs.max_sge; + newxprt->sc_max_send_sges = dev->attrs.max_send_sge; /* transport hdr, head iovec, one page list entry, tail iovec */ if (newxprt->sc_max_send_sges < 4) { pr_err("svcrdma: too few Send SGEs available (%d)\n", diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 16161a36dc73..956a5ea47b58 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -280,7 +280,6 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) ++xprt->rx_xprt.connect_cookie; connstate = -ECONNABORTED; connected: - xprt->rx_buf.rb_credits = 1; ep->rep_connected = connstate; rpcrdma_conn_func(ep); wake_up_all(&ep->rep_connect_wait); @@ -508,7 +507,7 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, unsigned int max_sge; int rc; - max_sge = min_t(unsigned int, ia->ri_device->attrs.max_sge, + max_sge = min_t(unsigned int, ia->ri_device->attrs.max_send_sge, RPCRDMA_MAX_SEND_SGES); if (max_sge < RPCRDMA_MIN_SEND_SGES) { pr_warn("rpcrdma: HCA provides only %d send SGEs\n", max_sge); @@ -755,6 +754,7 @@ retry: } ep->rep_connected = 0; + rpcrdma_post_recvs(r_xprt, true); rc = rdma_connect(ia->ri_id, &ep->rep_remote_cma); if (rc) { @@ -773,8 +773,6 @@ retry: dprintk("RPC: %s: connected\n", __func__); - rpcrdma_post_recvs(r_xprt, true); - out: if (rc) ep->rep_connected = rc; @@ -1171,6 +1169,7 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) list_add(&req->rl_list, &buf->rb_send_bufs); } + buf->rb_credits = 1; buf->rb_posted_receives = 0; INIT_LIST_HEAD(&buf->rb_recv_bufs); @@ -1559,7 +1558,8 @@ rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp) if (!count) return; - rc = ib_post_recv(r_xprt->rx_ia.ri_id->qp, wr, &bad_wr); + rc = ib_post_recv(r_xprt->rx_ia.ri_id->qp, wr, + (const struct ib_recv_wr **)&bad_wr); if (rc) { for (wr = bad_wr; wr; wr = wr->next) { struct rpcrdma_rep *rep; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 9e1c5024aba9..6b7539c0466e 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -3375,4 +3375,3 @@ module_param_named(tcp_max_slot_table_entries, xprt_max_tcp_slot_table_entries, max_slot_table_size, 0644); module_param_named(udp_slot_table_entries, xprt_udp_slot_table_entries, slot_table_size, 0644); - diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index b09867c8b817..93c0c225ab34 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -45,6 +45,7 @@ MODULE_AUTHOR("Mellanox Technologies"); MODULE_DESCRIPTION("Transport Layer Security Support"); MODULE_LICENSE("Dual BSD/GPL"); +MODULE_ALIAS_TCP_ULP("tls"); enum { TLSV4, |
