diff options
Diffstat (limited to 'net')
227 files changed, 2403 insertions, 1223 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 7850412f52b..0eb1a886b37 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -124,6 +124,9 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) grp->nr_vlans--; + if (vlan->flags & VLAN_FLAG_GVRP) + vlan_gvrp_request_leave(dev); + vlan_group_set_device(grp, vlan_id, NULL); if (!grp->killall) synchronize_net(); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index ae610f046de..b2ff6c8d360 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -487,9 +487,6 @@ static int vlan_dev_stop(struct net_device *dev) struct vlan_dev_info *vlan = vlan_dev_info(dev); struct net_device *real_dev = vlan->real_dev; - if (vlan->flags & VLAN_FLAG_GVRP) - vlan_gvrp_request_leave(dev); - dev_mc_unsync(real_dev, dev); dev_uc_unsync(real_dev, dev); if (dev->flags & IFF_ALLMULTI) @@ -720,6 +717,7 @@ static int vlan_dev_init(struct net_device *dev) dev->fcoe_ddp_xid = real_dev->fcoe_ddp_xid; #endif + dev->needed_headroom = real_dev->needed_headroom; if (real_dev->features & NETIF_F_HW_VLAN_TX) { dev->header_ops = real_dev->header_ops; dev->hard_header_len = real_dev->hard_header_len; diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c index d1314cf18ad..d940c49d168 100644 --- a/net/8021q/vlanproc.c +++ b/net/8021q/vlanproc.c @@ -54,7 +54,7 @@ static const char name_conf[] = "config"; /* * Structures for interfacing with the /proc filesystem. - * VLAN creates its own directory /proc/net/vlan with the folowing + * VLAN creates its own directory /proc/net/vlan with the following * entries: * config device status/configuration * <device> entry for each device diff --git a/net/9p/client.c b/net/9p/client.c index 347ec0cd271..a9aa2dd6648 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -178,7 +178,7 @@ free_and_return: * @tag: numeric id for transaction * * this is a simple array lookup, but will grow the - * request_slots as necessary to accomodate transaction + * request_slots as necessary to accommodate transaction * ids which did not previously have a slot. * * this code relies on the client spinlock to manage locks, its @@ -223,7 +223,7 @@ static struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag) req = &c->reqs[row][col]; if (!req->tc) { - req->wq = kmalloc(sizeof(wait_queue_head_t), GFP_KERNEL); + req->wq = kmalloc(sizeof(wait_queue_head_t), GFP_NOFS); if (!req->wq) { printk(KERN_ERR "Couldn't grow tag array\n"); return ERR_PTR(-ENOMEM); @@ -233,17 +233,17 @@ static struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag) P9_TRANS_PREF_PAYLOAD_SEP) { int alloc_msize = min(c->msize, 4096); req->tc = kmalloc(sizeof(struct p9_fcall)+alloc_msize, - GFP_KERNEL); + GFP_NOFS); req->tc->capacity = alloc_msize; req->rc = kmalloc(sizeof(struct p9_fcall)+alloc_msize, - GFP_KERNEL); + GFP_NOFS); req->rc->capacity = alloc_msize; } else { req->tc = kmalloc(sizeof(struct p9_fcall)+c->msize, - GFP_KERNEL); + GFP_NOFS); req->tc->capacity = c->msize; req->rc = kmalloc(sizeof(struct p9_fcall)+c->msize, - GFP_KERNEL); + GFP_NOFS); req->rc->capacity = c->msize; } if ((!req->tc) || (!req->rc)) { @@ -614,7 +614,7 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...) err = c->trans_mod->request(c, req); if (err < 0) { - if (err != -ERESTARTSYS) + if (err != -ERESTARTSYS && err != -EFAULT) c->status = Disconnected; goto reterr; } @@ -929,15 +929,15 @@ error: } EXPORT_SYMBOL(p9_client_attach); -struct p9_fid *p9_client_walk(struct p9_fid *oldfid, int nwname, char **wnames, - int clone) +struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname, + char **wnames, int clone) { int err; struct p9_client *clnt; struct p9_fid *fid; struct p9_qid *wqids; struct p9_req_t *req; - int16_t nwqids, count; + uint16_t nwqids, count; err = 0; wqids = NULL; @@ -955,7 +955,7 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, int nwname, char **wnames, fid = oldfid; - P9_DPRINTK(P9_DEBUG_9P, ">>> TWALK fids %d,%d nwname %d wname[0] %s\n", + P9_DPRINTK(P9_DEBUG_9P, ">>> TWALK fids %d,%d nwname %ud wname[0] %s\n", oldfid->fid, fid->fid, nwname, wnames ? wnames[0] : NULL); req = p9_client_rpc(clnt, P9_TWALK, "ddT", oldfid->fid, fid->fid, @@ -1220,27 +1220,6 @@ error: } EXPORT_SYMBOL(p9_client_fsync); -int p9_client_sync_fs(struct p9_fid *fid) -{ - int err = 0; - struct p9_req_t *req; - struct p9_client *clnt; - - P9_DPRINTK(P9_DEBUG_9P, ">>> TSYNC_FS fid %d\n", fid->fid); - - clnt = fid->clnt; - req = p9_client_rpc(clnt, P9_TSYNCFS, "d", fid->fid); - if (IS_ERR(req)) { - err = PTR_ERR(req); - goto error; - } - P9_DPRINTK(P9_DEBUG_9P, "<<< RSYNCFS fid %d\n", fid->fid); - p9_free_req(clnt, req); -error: - return err; -} -EXPORT_SYMBOL(p9_client_sync_fs); - int p9_client_clunk(struct p9_fid *fid) { int err; diff --git a/net/9p/protocol.c b/net/9p/protocol.c index 2ce515b859b..a873277cb99 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -205,7 +205,7 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, if (errcode) break; - *sptr = kmalloc(len + 1, GFP_KERNEL); + *sptr = kmalloc(len + 1, GFP_NOFS); if (*sptr == NULL) { errcode = -EFAULT; break; @@ -265,7 +265,7 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, } break; case 'T':{ - int16_t *nwname = va_arg(ap, int16_t *); + uint16_t *nwname = va_arg(ap, uint16_t *); char ***wnames = va_arg(ap, char ***); errcode = p9pdu_readf(pdu, proto_version, @@ -273,7 +273,7 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, if (!errcode) { *wnames = kmalloc(sizeof(char *) * *nwname, - GFP_KERNEL); + GFP_NOFS); if (!*wnames) errcode = -ENOMEM; } @@ -317,7 +317,7 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, *wqids = kmalloc(*nwqid * sizeof(struct p9_qid), - GFP_KERNEL); + GFP_NOFS); if (*wqids == NULL) errcode = -ENOMEM; } @@ -468,7 +468,8 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt, case 'E':{ int32_t cnt = va_arg(ap, int32_t); const char *k = va_arg(ap, const void *); - const char *u = va_arg(ap, const void *); + const char __user *u = va_arg(ap, + const void __user *); errcode = p9pdu_writef(pdu, proto_version, "d", cnt); if (!errcode && pdu_write_urw(pdu, k, u, cnt)) @@ -495,7 +496,7 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt, } break; case 'T':{ - int16_t nwname = va_arg(ap, int); + uint16_t nwname = va_arg(ap, int); const char **wnames = va_arg(ap, const char **); errcode = p9pdu_writef(pdu, proto_version, "w", @@ -673,6 +674,7 @@ int p9dirent_read(char *buf, int len, struct p9_dirent *dirent, } strcpy(dirent->d_name, nameptr); + kfree(nameptr); out: return fake_pdu.offset; diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c index d62b9aa58df..9a70ebdec56 100644 --- a/net/9p/trans_common.c +++ b/net/9p/trans_common.c @@ -36,14 +36,14 @@ p9_release_req_pages(struct trans_rpage_info *rpinfo) EXPORT_SYMBOL(p9_release_req_pages); /** - * p9_nr_pages - Return number of pages needed to accomodate the payload. + * p9_nr_pages - Return number of pages needed to accommodate the payload. */ int p9_nr_pages(struct p9_req_t *req) { - int start_page, end_page; - start_page = (unsigned long long)req->tc->pubuf >> PAGE_SHIFT; - end_page = ((unsigned long long)req->tc->pubuf + req->tc->pbuf_size + + unsigned long start_page, end_page; + start_page = (unsigned long)req->tc->pubuf >> PAGE_SHIFT; + end_page = ((unsigned long)req->tc->pubuf + req->tc->pbuf_size + PAGE_SIZE - 1) >> PAGE_SHIFT; return end_page - start_page; } @@ -55,7 +55,7 @@ EXPORT_SYMBOL(p9_nr_pages); * @req: Request to be sent to server. * @pdata_off: data offset into the first page after translation (gup). * @pdata_len: Total length of the IO. gup may not return requested # of pages. - * @nr_pages: number of pages to accomodate the payload + * @nr_pages: number of pages to accommodate the payload * @rw: Indicates if the pages are for read or write. */ int @@ -63,26 +63,21 @@ p9_payload_gup(struct p9_req_t *req, size_t *pdata_off, int *pdata_len, int nr_pages, u8 rw) { uint32_t first_page_bytes = 0; - uint32_t pdata_mapped_pages; + int32_t pdata_mapped_pages; struct trans_rpage_info *rpinfo; - *pdata_off = (size_t)req->tc->pubuf & (PAGE_SIZE-1); + *pdata_off = (__force size_t)req->tc->pubuf & (PAGE_SIZE-1); if (*pdata_off) - first_page_bytes = min((PAGE_SIZE - *pdata_off), - req->tc->pbuf_size); + first_page_bytes = min(((size_t)PAGE_SIZE - *pdata_off), + req->tc->pbuf_size); rpinfo = req->tc->private; pdata_mapped_pages = get_user_pages_fast((unsigned long)req->tc->pubuf, nr_pages, rw, &rpinfo->rp_data[0]); + if (pdata_mapped_pages <= 0) + return pdata_mapped_pages; - if (pdata_mapped_pages < 0) { - printk(KERN_ERR "get_user_pages_fast failed:%d udata:%p" - "nr_pages:%d\n", pdata_mapped_pages, - req->tc->pubuf, nr_pages); - pdata_mapped_pages = 0; - return -EIO; - } rpinfo->rp_nr_pages = pdata_mapped_pages; if (*pdata_off) { *pdata_len = first_page_bytes; diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index a30471e5174..aa5672b15ea 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -350,7 +350,7 @@ static void p9_read_work(struct work_struct *work) if (m->req->rc == NULL) { m->req->rc = kmalloc(sizeof(struct p9_fcall) + - m->client->msize, GFP_KERNEL); + m->client->msize, GFP_NOFS); if (!m->req->rc) { m->req = NULL; err = -ENOMEM; diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 29a54ccd213..150e0c4bbf4 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -424,7 +424,7 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) struct p9_rdma_context *rpl_context = NULL; /* Allocate an fcall for the reply */ - rpl_context = kmalloc(sizeof *rpl_context, GFP_KERNEL); + rpl_context = kmalloc(sizeof *rpl_context, GFP_NOFS); if (!rpl_context) { err = -ENOMEM; goto err_close; @@ -437,7 +437,7 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) */ if (!req->rc) { req->rc = kmalloc(sizeof(struct p9_fcall)+client->msize, - GFP_KERNEL); + GFP_NOFS); if (req->rc) { req->rc->sdata = (char *) req->rc + sizeof(struct p9_fcall); @@ -468,7 +468,7 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) req->rc = NULL; /* Post the request */ - c = kmalloc(sizeof *c, GFP_KERNEL); + c = kmalloc(sizeof *c, GFP_NOFS); if (!c) { err = -ENOMEM; goto err_free1; diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 9b550ed9c71..244e7074218 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -43,6 +43,7 @@ #include <net/9p/client.h> #include <net/9p/transport.h> #include <linux/scatterlist.h> +#include <linux/swap.h> #include <linux/virtio.h> #include <linux/virtio_9p.h> #include "trans_common.h" @@ -51,6 +52,8 @@ /* a single mutex to manage channel initialization and attachment */ static DEFINE_MUTEX(virtio_9p_lock); +static DECLARE_WAIT_QUEUE_HEAD(vp_wq); +static atomic_t vp_pinned = ATOMIC_INIT(0); /** * struct virtio_chan - per-instance transport information @@ -78,7 +81,10 @@ struct virtio_chan { struct virtqueue *vq; int ring_bufs_avail; wait_queue_head_t *vc_wq; - + /* This is global limit. Since we don't have a global structure, + * will be placing it in each channel. + */ + int p9_max_pages; /* Scatterlist: can be too big for stack. */ struct scatterlist sg[VIRTQUEUE_NUM]; @@ -141,34 +147,36 @@ static void req_done(struct virtqueue *vq) P9_DPRINTK(P9_DEBUG_TRANS, ": request done\n"); - do { + while (1) { spin_lock_irqsave(&chan->lock, flags); rc = virtqueue_get_buf(chan->vq, &len); - if (rc != NULL) { - if (!chan->ring_bufs_avail) { - chan->ring_bufs_avail = 1; - wake_up(chan->vc_wq); - } - spin_unlock_irqrestore(&chan->lock, flags); - P9_DPRINTK(P9_DEBUG_TRANS, ": rc %p\n", rc); - P9_DPRINTK(P9_DEBUG_TRANS, ": lookup tag %d\n", - rc->tag); - req = p9_tag_lookup(chan->client, rc->tag); - req->status = REQ_STATUS_RCVD; - if (req->tc->private) { - struct trans_rpage_info *rp = req->tc->private; - /*Release pages */ - p9_release_req_pages(rp); - if (rp->rp_alloc) - kfree(rp); - req->tc->private = NULL; - } - p9_client_cb(chan->client, req); - } else { + if (rc == NULL) { spin_unlock_irqrestore(&chan->lock, flags); + break; + } + + chan->ring_bufs_avail = 1; + spin_unlock_irqrestore(&chan->lock, flags); + /* Wakeup if anyone waiting for VirtIO ring space. */ + wake_up(chan->vc_wq); + P9_DPRINTK(P9_DEBUG_TRANS, ": rc %p\n", rc); + P9_DPRINTK(P9_DEBUG_TRANS, ": lookup tag %d\n", rc->tag); + req = p9_tag_lookup(chan->client, rc->tag); + if (req->tc->private) { + struct trans_rpage_info *rp = req->tc->private; + int p = rp->rp_nr_pages; + /*Release pages */ + p9_release_req_pages(rp); + atomic_sub(p, &vp_pinned); + wake_up(&vp_wq); + if (rp->rp_alloc) + kfree(rp); + req->tc->private = NULL; } - } while (rc != NULL); + req->status = REQ_STATUS_RCVD; + p9_client_cb(chan->client, req); + } } /** @@ -263,7 +271,6 @@ p9_virtio_request(struct p9_client *client, struct p9_req_t *req) P9_DPRINTK(P9_DEBUG_TRANS, "9p debug: virtio request\n"); -req_retry: req->status = REQ_STATUS_SENT; if (req->tc->pbuf_size && (req->tc->pubuf && P9_IS_USER_CONTEXT)) { @@ -271,6 +278,14 @@ req_retry: int rpinfo_size = sizeof(struct trans_rpage_info) + sizeof(struct page *) * nr_pages; + if (atomic_read(&vp_pinned) >= chan->p9_max_pages) { + err = wait_event_interruptible(vp_wq, + atomic_read(&vp_pinned) < chan->p9_max_pages); + if (err == -ERESTARTSYS) + return err; + P9_DPRINTK(P9_DEBUG_TRANS, "9p: May gup pages now.\n"); + } + if (rpinfo_size <= (req->tc->capacity - req->tc->size)) { /* We can use sdata */ req->tc->private = req->tc->sdata + req->tc->size; @@ -293,9 +308,12 @@ req_retry: if (rpinfo->rp_alloc) kfree(rpinfo); return err; + } else { + atomic_add(rpinfo->rp_nr_pages, &vp_pinned); } } +req_retry_pinned: spin_lock_irqsave(&chan->lock, flags); /* Handle out VirtIO ring buffers */ @@ -308,8 +326,11 @@ req_retry: outp = pack_sg_list_p(chan->sg, out, VIRTQUEUE_NUM, pdata_off, rpinfo->rp_data, pdata_len); } else { - char *pbuf = req->tc->pubuf ? req->tc->pubuf : - req->tc->pkbuf; + char *pbuf; + if (req->tc->pubuf) + pbuf = (__force char *) req->tc->pubuf; + else + pbuf = req->tc->pkbuf; outp = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM, pbuf, req->tc->pbuf_size); } @@ -334,8 +355,12 @@ req_retry: in = pack_sg_list_p(chan->sg, out+inp, VIRTQUEUE_NUM, pdata_off, rpinfo->rp_data, pdata_len); } else { - char *pbuf = req->tc->pubuf ? req->tc->pubuf : - req->tc->pkbuf; + char *pbuf; + if (req->tc->pubuf) + pbuf = (__force char *) req->tc->pubuf; + else + pbuf = req->tc->pkbuf; + in = pack_sg_list(chan->sg, out+inp, VIRTQUEUE_NUM, pbuf, req->tc->pbuf_size); } @@ -356,7 +381,7 @@ req_retry: return err; P9_DPRINTK(P9_DEBUG_TRANS, "9p:Retry virtio request\n"); - goto req_retry; + goto req_retry_pinned; } else { spin_unlock_irqrestore(&chan->lock, flags); P9_DPRINTK(P9_DEBUG_TRANS, @@ -453,6 +478,8 @@ static int p9_virtio_probe(struct virtio_device *vdev) } init_waitqueue_head(chan->vc_wq); chan->ring_bufs_avail = 1; + /* Ceiling limit to avoid denial of service attacks */ + chan->p9_max_pages = nr_free_buffer_pages()/4; mutex_lock(&virtio_9p_lock); list_add_tail(&chan->chan_list, &virtio_chan_list); diff --git a/net/9p/util.c b/net/9p/util.c index e048701a72d..da6af81e59d 100644 --- a/net/9p/util.c +++ b/net/9p/util.c @@ -67,7 +67,7 @@ EXPORT_SYMBOL(p9_idpool_create); /** * p9_idpool_destroy - create a new per-connection id pool - * @p: idpool to destory + * @p: idpool to destroy */ void p9_idpool_destroy(struct p9_idpool *p) @@ -92,7 +92,7 @@ int p9_idpool_get(struct p9_idpool *p) unsigned long flags; retry: - if (idr_pre_get(&p->pool, GFP_KERNEL) == 0) + if (idr_pre_get(&p->pool, GFP_NOFS) == 0) return 0; spin_lock_irqsave(&p->lock, flags); diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 3d4f4b04340..956a5302002 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1051,13 +1051,17 @@ static int atalk_release(struct socket *sock) { struct sock *sk = sock->sk; - lock_sock(sk); if (sk) { + sock_hold(sk); + lock_sock(sk); + sock_orphan(sk); sock->sk = NULL; atalk_destroy_socket(sk); + + release_sock(sk); + sock_put(sk); } - release_sock(sk); return 0; } diff --git a/net/atm/br2684.c b/net/atm/br2684.c index fce2eae8d47..2252c2085da 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -509,7 +509,7 @@ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg) write_lock_irq(&devs_lock); net_dev = br2684_find_dev(&be.ifspec); if (net_dev == NULL) { - pr_err("tried to attach to non-existant device\n"); + pr_err("tried to attach to non-existent device\n"); err = -ENXIO; goto error; } diff --git a/net/atm/common.c b/net/atm/common.c index 1b9c52a02cd..22b963d06a1 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -252,6 +252,7 @@ void atm_dev_release_vccs(struct atm_dev *dev) } write_unlock_irq(&vcc_sklist_lock); } +EXPORT_SYMBOL(atm_dev_release_vccs); static int adjust_tp(struct atm_trafprm *tp, unsigned char aal) { diff --git a/net/atm/lec.h b/net/atm/lec.h index 9d14d196cc1..dfc07196646 100644 --- a/net/atm/lec.h +++ b/net/atm/lec.h @@ -35,7 +35,7 @@ struct lecdatahdr_8025 { * Operations that LANE2 capable device can do. Two first functions * are used to make the device do things. See spec 3.1.3 and 3.1.4. * - * The third function is intented for the MPOA component sitting on + * The third function is intended for the MPOA component sitting on * top of the LANE device. The MPOA component assigns it's own function * to (*associate_indicator)() and the LANE device will use that * function to tell about TLVs it sees floating through. diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 9ed26140a26..824e1f6e50f 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -474,7 +474,7 @@ void interface_rx(struct net_device *soft_iface, goto dropped; skb->protocol = eth_type_trans(skb, soft_iface); - /* should not be neccesary anymore as we use skb_pull_rcsum() + /* should not be necessary anymore as we use skb_pull_rcsum() * TODO: please verify this and remove this TODO * -- Dec 21st 2009, Simon Wunderlich */ diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index b372fb8bcdc..b5a8afc2be3 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -186,6 +186,7 @@ static void hci_reset_req(struct hci_dev *hdev, unsigned long opt) BT_DBG("%s %ld", hdev->name, opt); /* Reset device */ + set_bit(HCI_RESET, &hdev->flags); hci_send_cmd(hdev, HCI_OP_RESET, 0, NULL); } @@ -213,8 +214,10 @@ static void hci_init_req(struct hci_dev *hdev, unsigned long opt) /* Mandatory initialization */ /* Reset */ - if (!test_bit(HCI_QUIRK_NO_RESET, &hdev->quirks)) + if (!test_bit(HCI_QUIRK_NO_RESET, &hdev->quirks)) { + set_bit(HCI_RESET, &hdev->flags); hci_send_cmd(hdev, HCI_OP_RESET, 0, NULL); + } /* Read Local Supported Features */ hci_send_cmd(hdev, HCI_OP_READ_LOCAL_FEATURES, 0, NULL); @@ -585,6 +588,7 @@ static int hci_dev_do_close(struct hci_dev *hdev) hci_req_lock(hdev); if (!test_and_clear_bit(HCI_UP, &hdev->flags)) { + del_timer_sync(&hdev->cmd_timer); hci_req_unlock(hdev); return 0; } @@ -1074,6 +1078,7 @@ static void hci_cmd_timer(unsigned long arg) BT_ERR("%s command tx timeout", hdev->name); atomic_set(&hdev->cmd_cnt, 1); + clear_bit(HCI_RESET, &hdev->flags); tasklet_schedule(&hdev->cmd_task); } @@ -1877,7 +1882,7 @@ static void hci_tx_task(unsigned long arg) read_unlock(&hci_task_lock); } -/* ----- HCI RX task (incoming data proccessing) ----- */ +/* ----- HCI RX task (incoming data processing) ----- */ /* ACL data packet */ static inline void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 3fbfa50c2bf..b2570159a04 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -183,6 +183,8 @@ static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb) BT_DBG("%s status 0x%x", hdev->name, status); + clear_bit(HCI_RESET, &hdev->flags); + hci_req_complete(hdev, HCI_OP_RESET, status); } @@ -1847,7 +1849,7 @@ static inline void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb) if (ev->opcode != HCI_OP_NOP) del_timer(&hdev->cmd_timer); - if (ev->ncmd) { + if (ev->ncmd && !test_bit(HCI_RESET, &hdev->flags)) { atomic_set(&hdev->cmd_cnt, 1); if (!skb_queue_empty(&hdev->cmd_q)) tasklet_schedule(&hdev->cmd_task); @@ -2385,8 +2387,6 @@ static inline void hci_io_capa_reply_evt(struct hci_dev *hdev, struct sk_buff *s if (!conn) goto unlock; - hci_conn_hold(conn); - conn->remote_cap = ev->capability; conn->remote_oob = ev->oob_data; conn->remote_auth = ev->authentication; diff --git a/net/bluetooth/hidp/hidp.h b/net/bluetooth/hidp/hidp.h index 13de5fa0348..c9be80395c3 100644 --- a/net/bluetooth/hidp/hidp.h +++ b/net/bluetooth/hidp/hidp.h @@ -80,7 +80,7 @@ #define HIDP_VIRTUAL_CABLE_UNPLUG 0 #define HIDP_BOOT_PROTOCOL_MODE 1 #define HIDP_BLUETOOTH_VENDOR_ID 9 -#define HIDP_WAITING_FOR_RETURN 10 +#define HIDP_WAITING_FOR_RETURN 10 #define HIDP_WAITING_FOR_SEND_ACK 11 struct hidp_connadd_req { diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index c9f9cecca52..2c8dd4494c6 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1051,6 +1051,7 @@ static void l2cap_retransmit_one_frame(struct sock *sk, u8 tx_seq) tx_skb = skb_clone(skb, GFP_ATOMIC); bt_cb(skb)->retries++; control = get_unaligned_le16(tx_skb->data + L2CAP_HDR_SIZE); + control &= L2CAP_CTRL_SAR; if (pi->conn_state & L2CAP_CONN_SEND_FBIT) { control |= L2CAP_CTRL_FINAL; @@ -1116,7 +1117,9 @@ int l2cap_ertm_send(struct sock *sk) bt_cb(skb)->tx_seq = pi->next_tx_seq; pi->next_tx_seq = (pi->next_tx_seq + 1) % 64; - pi->unacked_frames++; + if (bt_cb(skb)->retries == 1) + pi->unacked_frames++; + pi->frames_sent++; if (skb_queue_is_last(TX_QUEUE(sk), skb)) diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index fc85e7ae33c..299fe56a966 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -679,7 +679,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, ch if (opt == BT_FLUSHABLE_OFF) { struct l2cap_conn *conn = l2cap_pi(sk)->conn; - /* proceed futher only when we have l2cap_conn and + /* proceed further only when we have l2cap_conn and No Flush support in the LM */ if (!conn || !lmp_no_flush_capable(conn->hcon->hdev)) { err = -EINVAL; @@ -923,8 +923,9 @@ void __l2cap_sock_close(struct sock *sk, int reason) rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); l2cap_send_cmd(conn, l2cap_pi(sk)->ident, L2CAP_CONN_RSP, sizeof(rsp), &rsp); - } else - l2cap_chan_del(sk, reason); + } + + l2cap_chan_del(sk, reason); break; case BT_CONNECT: diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 0054c74e27b..4476d8e3c0f 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -1230,6 +1230,8 @@ static int user_confirm_reply(struct sock *sk, u16 index, unsigned char *data, if (!hdev) return cmd_status(sk, index, mgmt_op, ENODEV); + hci_dev_lock_bh(hdev); + if (!test_bit(HCI_UP, &hdev->flags)) { err = cmd_status(sk, index, mgmt_op, ENETDOWN); goto failed; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 88485cc74dc..cc4d3c5ab1c 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -169,7 +169,7 @@ void br_fdb_flush(struct net_bridge *br) spin_unlock_bh(&br->hash_lock); } -/* Flush all entries refering to a specific port. +/* Flush all entries referring to a specific port. * if do_all is set also flush static entries */ void br_fdb_delete_by_port(struct net_bridge *br, diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index dce8f0009a1..718b60366df 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -389,6 +389,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) { struct net_bridge_port *p; int err = 0; + bool changed_addr; /* Don't allow bridging non-ethernet like devices */ if ((dev->flags & IFF_LOOPBACK) || @@ -446,7 +447,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) list_add_rcu(&p->list, &br->port_list); spin_lock_bh(&br->lock); - br_stp_recalculate_bridge_id(br); + changed_addr = br_stp_recalculate_bridge_id(br); br_features_recompute(br); if ((dev->flags & IFF_UP) && netif_carrier_ok(dev) && @@ -456,6 +457,9 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) br_ifinfo_notify(RTM_NEWLINK, p); + if (changed_addr) + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + dev_set_mtu(br->dev, br_min_mtu(br)); kobject_uevent(&p->kobj, KOBJ_ADD); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index e2160792e1b..0c7badad62a 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -164,7 +164,7 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) goto drop; /* If STP is turned off, then forward */ - if (p->br->stp_enabled == BR_NO_STP) + if (p->br->stp_enabled == BR_NO_STP && dest[5] == 0) goto forward; if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, skb->dev, diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c index cb43312b846..3d9fca0e337 100644 --- a/net/bridge/br_ioctl.c +++ b/net/bridge/br_ioctl.c @@ -106,7 +106,7 @@ static int add_del_if(struct net_bridge *br, int ifindex, int isadd) /* * Legacy ioctl's through SIOCDEVPRIVATE * This interface is deprecated because it was too difficult to - * to do the translation for 32/64bit ioctl compatability. + * to do the translation for 32/64bit ioctl compatibility. */ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) { diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 030a002ff8e..59660c909a7 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -445,9 +445,9 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, ip6h->payload_len = htons(8 + sizeof(*mldq)); ip6h->nexthdr = IPPROTO_HOPOPTS; ip6h->hop_limit = 1; + ipv6_addr_set(&ip6h->daddr, htonl(0xff020000), 0, 0, htonl(1)); ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0, &ip6h->saddr); - ipv6_addr_set(&ip6h->daddr, htonl(0xff020000), 0, 0, htonl(1)); ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest); hopopt = (u8 *)(ip6h + 1); @@ -1475,7 +1475,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, ip6h->payload_len == 0) return 0; - len = ntohs(ip6h->payload_len); + len = ntohs(ip6h->payload_len) + sizeof(*ip6h); if (skb->len < len) return -EINVAL; diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index f97af5590ba..74ef4d4846a 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -249,11 +249,9 @@ static int br_parse_ip_options(struct sk_buff *skb) goto drop; } - /* Zero out the CB buffer if no options present */ - if (iph->ihl == 5) { - memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + if (iph->ihl == 5) return 0; - } opt->optlen = iph->ihl*4 - sizeof(struct iphdr); if (ip_options_compile(dev_net(dev), opt, skb)) @@ -739,6 +737,9 @@ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff *skb, nf_bridge->mask |= BRNF_PKT_TYPE; } + if (pf == PF_INET && br_parse_ip_options(skb)) + return NF_DROP; + /* The physdev module checks on this */ nf_bridge->mask |= BRNF_BRIDGED; nf_bridge->physoutdev = skb->dev; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 19e2f46ed08..387013d3374 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -497,7 +497,7 @@ extern void br_stp_disable_bridge(struct net_bridge *br); extern void br_stp_set_enabled(struct net_bridge *br, unsigned long val); extern void br_stp_enable_port(struct net_bridge_port *p); extern void br_stp_disable_port(struct net_bridge_port *p); -extern void br_stp_recalculate_bridge_id(struct net_bridge *br); +extern bool br_stp_recalculate_bridge_id(struct net_bridge *br); extern void br_stp_change_bridge_id(struct net_bridge *br, const unsigned char *a); extern void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio); diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 79372d4a405..9b61d09de9b 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -204,7 +204,7 @@ void br_stp_change_bridge_id(struct net_bridge *br, const unsigned char *addr) static const unsigned short br_mac_zero_aligned[ETH_ALEN >> 1]; /* called under bridge lock */ -void br_stp_recalculate_bridge_id(struct net_bridge *br) +bool br_stp_recalculate_bridge_id(struct net_bridge *br) { const unsigned char *br_mac_zero = (const unsigned char *)br_mac_zero_aligned; @@ -213,7 +213,7 @@ void br_stp_recalculate_bridge_id(struct net_bridge *br) /* user has chosen a value so keep it */ if (br->flags & BR_SET_MAC_ADDR) - return; + return false; list_for_each_entry(p, &br->port_list, list) { if (addr == br_mac_zero || @@ -222,8 +222,11 @@ void br_stp_recalculate_bridge_id(struct net_bridge *br) } - if (compare_ether_addr(br->bridge_id.addr, addr)) - br_stp_change_bridge_id(br, addr); + if (compare_ether_addr(br->bridge_id.addr, addr) == 0) + return false; /* no change */ + + br_stp_change_bridge_id(br, addr); + return true; } /* called under bridge lock */ diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 893669caa8d..1a92b369c82 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1766,7 +1766,7 @@ static int compat_table_info(const struct ebt_table_info *info, newinfo->entries_size = size; - xt_compat_init_offsets(AF_INET, info->nentries); + xt_compat_init_offsets(NFPROTO_BRIDGE, info->nentries); return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info, entries, newinfo); } @@ -1882,7 +1882,7 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, struct xt_match *match; struct xt_target *wt; void *dst = NULL; - int off, pad = 0, ret = 0; + int off, pad = 0; unsigned int size_kern, entry_offset, match_size = mwt->match_size; strlcpy(name, mwt->u.name, sizeof(name)); @@ -1935,13 +1935,6 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, break; } - if (!dst) { - ret = xt_compat_add_offset(NFPROTO_BRIDGE, entry_offset, - off + ebt_compat_entry_padsize()); - if (ret < 0) - return ret; - } - state->buf_kern_offset += match_size + off; state->buf_user_offset += match_size; pad = XT_ALIGN(size_kern) - size_kern; @@ -2016,50 +2009,6 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, return growth; } -#define EBT_COMPAT_WATCHER_ITERATE(e, fn, args...) \ -({ \ - unsigned int __i; \ - int __ret = 0; \ - struct compat_ebt_entry_mwt *__watcher; \ - \ - for (__i = e->watchers_offset; \ - __i < (e)->target_offset; \ - __i += __watcher->watcher_size + \ - sizeof(struct compat_ebt_entry_mwt)) { \ - __watcher = (void *)(e) + __i; \ - __ret = fn(__watcher , ## args); \ - if (__ret != 0) \ - break; \ - } \ - if (__ret == 0) { \ - if (__i != (e)->target_offset) \ - __ret = -EINVAL; \ - } \ - __ret; \ -}) - -#define EBT_COMPAT_MATCH_ITERATE(e, fn, args...) \ -({ \ - unsigned int __i; \ - int __ret = 0; \ - struct compat_ebt_entry_mwt *__match; \ - \ - for (__i = sizeof(struct ebt_entry); \ - __i < (e)->watchers_offset; \ - __i += __match->match_size + \ - sizeof(struct compat_ebt_entry_mwt)) { \ - __match = (void *)(e) + __i; \ - __ret = fn(__match , ## args); \ - if (__ret != 0) \ - break; \ - } \ - if (__ret == 0) { \ - if (__i != (e)->watchers_offset) \ - __ret = -EINVAL; \ - } \ - __ret; \ -}) - /* called for all ebt_entry structures. */ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, unsigned int *total, @@ -2132,6 +2081,14 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, } } + if (state->buf_kern_start == NULL) { + unsigned int offset = buf_start - (char *) base; + + ret = xt_compat_add_offset(NFPROTO_BRIDGE, offset, new_offset); + if (ret < 0) + return ret; + } + startoff = state->buf_user_offset - startoff; BUG_ON(*total < startoff); @@ -2240,6 +2197,7 @@ static int compat_do_replace(struct net *net, void __user *user, xt_compat_lock(NFPROTO_BRIDGE); + xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries); ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); if (ret < 0) goto out_unlock; diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 8184c031d02..37a4034dfc2 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -852,7 +852,7 @@ static int caif_connect(struct socket *sock, struct sockaddr *uaddr, sock->state = SS_CONNECTING; sk->sk_state = CAIF_CONNECTING; - /* Check priority value comming from socket */ + /* Check priority value coming from socket */ /* if priority value is out of range it will be ajusted */ if (cf_sk->sk.sk_priority > CAIF_PRIO_MAX) cf_sk->conn_req.priority = CAIF_PRIO_MAX; diff --git a/net/caif/cfdgml.c b/net/caif/cfdgml.c index 27dab26ad3b..054fdb5aeb8 100644 --- a/net/caif/cfdgml.c +++ b/net/caif/cfdgml.c @@ -13,6 +13,7 @@ #include <net/caif/cfsrvl.h> #include <net/caif/cfpkt.h> + #define container_obj(layr) ((struct cfsrvl *) layr) #define DGM_CMD_BIT 0x80 @@ -83,6 +84,7 @@ static int cfdgml_receive(struct cflayer *layr, struct cfpkt *pkt) static int cfdgml_transmit(struct cflayer *layr, struct cfpkt *pkt) { + u8 packet_type; u32 zero = 0; struct caif_payload_info *info; struct cfsrvl *service = container_obj(layr); @@ -94,7 +96,9 @@ static int cfdgml_transmit(struct cflayer *layr, struct cfpkt *pkt) if (cfpkt_getlen(pkt) > DGM_MTU) return -EMSGSIZE; - cfpkt_add_head(pkt, &zero, 4); + cfpkt_add_head(pkt, &zero, 3); + packet_type = 0x08; /* B9 set - UNCLASSIFIED */ + cfpkt_add_head(pkt, &packet_type, 1); /* Add info for MUX-layer to route the packet out. */ info = cfpkt_info(pkt); diff --git a/net/caif/cfmuxl.c b/net/caif/cfmuxl.c index 46f34b2e047..24f1ffa74b0 100644 --- a/net/caif/cfmuxl.c +++ b/net/caif/cfmuxl.c @@ -244,9 +244,9 @@ static void cfmuxl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, int phyid) { struct cfmuxl *muxl = container_obj(layr); - struct list_head *node; + struct list_head *node, *next; struct cflayer *layer; - list_for_each(node, &muxl->srvl_list) { + list_for_each_safe(node, next, &muxl->srvl_list) { layer = list_entry(node, struct cflayer, node); if (cfsrvl_phyid_match(layer, phyid)) layer->ctrlcmd(layer, ctrl, phyid); diff --git a/net/can/af_can.c b/net/can/af_can.c index 702be5a2c95..733d66f1b05 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -95,7 +95,7 @@ struct s_pstats can_pstats; /* receive list statistics */ * af_can socket functions */ -static int can_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +int can_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; @@ -108,6 +108,7 @@ static int can_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) return -ENOIOCTLCMD; } } +EXPORT_SYMBOL(can_ioctl); static void can_sock_destruct(struct sock *sk) { @@ -698,13 +699,9 @@ int can_proto_register(struct can_proto *cp) printk(KERN_ERR "can: protocol %d already registered\n", proto); err = -EBUSY; - } else { + } else proto_tab[proto] = cp; - /* use generic ioctl function if not defined by module */ - if (!cp->ops->ioctl) - cp->ops->ioctl = can_ioctl; - } spin_unlock(&proto_tab_lock); if (err < 0) diff --git a/net/can/bcm.c b/net/can/bcm.c index 092dc88a7c6..8a6a05e7c3c 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -387,7 +387,7 @@ static void bcm_tx_timeout_tsklet(unsigned long data) } /* - * bcm_tx_timeout_handler - performes cyclic CAN frame transmissions + * bcm_tx_timeout_handler - performs cyclic CAN frame transmissions */ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) { @@ -1427,9 +1427,14 @@ static int bcm_init(struct sock *sk) static int bcm_release(struct socket *sock) { struct sock *sk = sock->sk; - struct bcm_sock *bo = bcm_sk(sk); + struct bcm_sock *bo; struct bcm_op *op, *next; + if (sk == NULL) + return 0; + + bo = bcm_sk(sk); + /* remove bcm_ops, timer, rx_unregister(), etc. */ unregister_netdevice_notifier(&bo->notifier); @@ -1569,7 +1574,7 @@ static int bcm_recvmsg(struct kiocb *iocb, struct socket *sock, return size; } -static struct proto_ops bcm_ops __read_mostly = { +static const struct proto_ops bcm_ops = { .family = PF_CAN, .release = bcm_release, .bind = sock_no_bind, @@ -1578,7 +1583,7 @@ static struct proto_ops bcm_ops __read_mostly = { .accept = sock_no_accept, .getname = sock_no_getname, .poll = datagram_poll, - .ioctl = NULL, /* use can_ioctl() from af_can.c */ + .ioctl = can_ioctl, /* use can_ioctl() from af_can.c */ .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = sock_no_setsockopt, diff --git a/net/can/raw.c b/net/can/raw.c index 883e9d74fdd..0eb39a7fdf6 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -305,7 +305,12 @@ static int raw_init(struct sock *sk) static int raw_release(struct socket *sock) { struct sock *sk = sock->sk; - struct raw_sock *ro = raw_sk(sk); + struct raw_sock *ro; + + if (!sk) + return 0; + + ro = raw_sk(sk); unregister_netdevice_notifier(&ro->notifier); @@ -742,7 +747,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock, return size; } -static struct proto_ops raw_ops __read_mostly = { +static const struct proto_ops raw_ops = { .family = PF_CAN, .release = raw_release, .bind = raw_bind, @@ -751,7 +756,7 @@ static struct proto_ops raw_ops __read_mostly = { .accept = sock_no_accept, .getname = raw_getname, .poll = datagram_poll, - .ioctl = NULL, /* use can_ioctl() from af_can.c */ + .ioctl = can_ioctl, /* use can_ioctl() from af_can.c */ .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = raw_setsockopt, diff --git a/net/ceph/Kconfig b/net/ceph/Kconfig index ad424049b0c..be683f2d401 100644 --- a/net/ceph/Kconfig +++ b/net/ceph/Kconfig @@ -4,6 +4,7 @@ config CEPH_LIB select LIBCRC32C select CRYPTO_AES select CRYPTO + select KEYS default n help Choose Y or M here to include cephlib, which provides the diff --git a/net/ceph/armor.c b/net/ceph/armor.c index eb2a666b0be..1fc1ee11dfa 100644 --- a/net/ceph/armor.c +++ b/net/ceph/armor.c @@ -78,8 +78,10 @@ int ceph_unarmor(char *dst, const char *src, const char *end) while (src < end) { int a, b, c, d; - if (src < end && src[0] == '\n') + if (src[0] == '\n') { src++; + continue; + } if (src + 4 > end) return -EINVAL; a = decode_bits(src[0]); diff --git a/net/ceph/auth.c b/net/ceph/auth.c index 549c1f43e1d..b4bf4ac090f 100644 --- a/net/ceph/auth.c +++ b/net/ceph/auth.c @@ -35,12 +35,12 @@ static int ceph_auth_init_protocol(struct ceph_auth_client *ac, int protocol) /* * setup, teardown. */ -struct ceph_auth_client *ceph_auth_init(const char *name, const char *secret) +struct ceph_auth_client *ceph_auth_init(const char *name, const struct ceph_crypto_key *key) { struct ceph_auth_client *ac; int ret; - dout("auth_init name '%s' secret '%s'\n", name, secret); + dout("auth_init name '%s'\n", name); ret = -ENOMEM; ac = kzalloc(sizeof(*ac), GFP_NOFS); @@ -52,8 +52,8 @@ struct ceph_auth_client *ceph_auth_init(const char *name, const char *secret) ac->name = name; else ac->name = CEPH_AUTH_NAME_DEFAULT; - dout("auth_init name %s secret %s\n", ac->name, secret); - ac->secret = secret; + dout("auth_init name %s\n", ac->name); + ac->key = key; return ac; out: diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c index 7fd5dfcf6e1..1587dc6010c 100644 --- a/net/ceph/auth_x.c +++ b/net/ceph/auth_x.c @@ -662,14 +662,16 @@ int ceph_x_init(struct ceph_auth_client *ac) goto out; ret = -EINVAL; - if (!ac->secret) { + if (!ac->key) { pr_err("no secret set (for auth_x protocol)\n"); goto out_nomem; } - ret = ceph_crypto_key_unarmor(&xi->secret, ac->secret); - if (ret) + ret = ceph_crypto_key_clone(&xi->secret, ac->key); + if (ret < 0) { + pr_err("cannot clone key: %d\n", ret); goto out_nomem; + } xi->starting = true; xi->ticket_handlers = RB_ROOT; diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index f3e4a13fea0..132963abc26 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -5,6 +5,8 @@ #include <linux/fs.h> #include <linux/inet.h> #include <linux/in6.h> +#include <linux/key.h> +#include <keys/ceph-type.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/parser.h> @@ -20,6 +22,7 @@ #include <linux/ceph/decode.h> #include <linux/ceph/mon_client.h> #include <linux/ceph/auth.h> +#include "crypto.h" @@ -62,6 +65,7 @@ const char *ceph_msg_type_name(int type) case CEPH_MSG_OSD_MAP: return "osd_map"; case CEPH_MSG_OSD_OP: return "osd_op"; case CEPH_MSG_OSD_OPREPLY: return "osd_opreply"; + case CEPH_MSG_WATCH_NOTIFY: return "watch_notify"; default: return "unknown"; } } @@ -116,9 +120,29 @@ int ceph_compare_options(struct ceph_options *new_opt, if (ret) return ret; - ret = strcmp_null(opt1->secret, opt2->secret); - if (ret) - return ret; + if (opt1->key && !opt2->key) + return -1; + if (!opt1->key && opt2->key) + return 1; + if (opt1->key && opt2->key) { + if (opt1->key->type != opt2->key->type) + return -1; + if (opt1->key->created.tv_sec != opt2->key->created.tv_sec) + return -1; + if (opt1->key->created.tv_nsec != opt2->key->created.tv_nsec) + return -1; + if (opt1->key->len != opt2->key->len) + return -1; + if (opt1->key->key && !opt2->key->key) + return -1; + if (!opt1->key->key && opt2->key->key) + return 1; + if (opt1->key->key && opt2->key->key) { + ret = memcmp(opt1->key->key, opt2->key->key, opt1->key->len); + if (ret) + return ret; + } + } /* any matching mon ip implies a match */ for (i = 0; i < opt1->num_mon; i++) { @@ -175,6 +199,7 @@ enum { Opt_fsid, Opt_name, Opt_secret, + Opt_key, Opt_ip, Opt_last_string, /* string args above */ @@ -191,6 +216,7 @@ static match_table_t opt_tokens = { {Opt_fsid, "fsid=%s"}, {Opt_name, "name=%s"}, {Opt_secret, "secret=%s"}, + {Opt_key, "key=%s"}, {Opt_ip, "ip=%s"}, /* string args above */ {Opt_noshare, "noshare"}, @@ -202,11 +228,56 @@ void ceph_destroy_options(struct ceph_options *opt) { dout("destroy_options %p\n", opt); kfree(opt->name); - kfree(opt->secret); + if (opt->key) { + ceph_crypto_key_destroy(opt->key); + kfree(opt->key); + } kfree(opt); } EXPORT_SYMBOL(ceph_destroy_options); +/* get secret from key store */ +static int get_secret(struct ceph_crypto_key *dst, const char *name) { + struct key *ukey; + int key_err; + int err = 0; + struct ceph_crypto_key *ckey; + + ukey = request_key(&key_type_ceph, name, NULL); + if (!ukey || 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); + switch (key_err) { + case -ENOKEY: + pr_warning("ceph: Mount failed due to key not found: %s\n", name); + break; + case -EKEYEXPIRED: + pr_warning("ceph: Mount failed due to expired key: %s\n", name); + break; + case -EKEYREVOKED: + pr_warning("ceph: Mount failed due to revoked key: %s\n", name); + break; + default: + pr_warning("ceph: Mount failed due to unknown key error" + " %d: %s\n", key_err, name); + } + err = -EPERM; + goto out; + } + + ckey = ukey->payload.data; + err = ceph_crypto_key_clone(dst, ckey); + if (err) + goto out_key; + /* pass through, err is 0 */ + +out_key: + key_put(ukey); +out: + return err; +} + int ceph_parse_options(struct ceph_options **popt, char *options, const char *dev_name, const char *dev_name_end, int (*parse_extra_token)(char *c, void *private), @@ -294,9 +365,24 @@ int ceph_parse_options(struct ceph_options **popt, char *options, GFP_KERNEL); break; case Opt_secret: - opt->secret = kstrndup(argstr[0].from, - argstr[0].to-argstr[0].from, - GFP_KERNEL); + opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL); + if (!opt->key) { + err = -ENOMEM; + goto out; + } + err = ceph_crypto_key_unarmor(opt->key, argstr[0].from); + if (err < 0) + goto out; + break; + case Opt_key: + opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL); + if (!opt->key) { + err = -ENOMEM; + goto out; + } + err = get_secret(opt->key, argstr[0].from); + if (err < 0) + goto out; break; /* misc */ @@ -393,8 +479,8 @@ void ceph_destroy_client(struct ceph_client *client) ceph_osdc_stop(&client->osdc); /* - * make sure mds and osd connections close out before destroying - * the auth module, which is needed to free those connections' + * make sure osd connections close out before destroying the + * auth module, which is needed to free those connections' * ceph_authorizers. */ ceph_msgr_flush(); @@ -495,10 +581,14 @@ static int __init init_ceph_lib(void) if (ret < 0) goto out; - ret = ceph_msgr_init(); + ret = ceph_crypto_init(); if (ret < 0) goto out_debugfs; + ret = ceph_msgr_init(); + if (ret < 0) + goto out_crypto; + pr_info("loaded (mon/osd proto %d/%d, osdmap %d/%d %d/%d)\n", CEPH_MONC_PROTOCOL, CEPH_OSDC_PROTOCOL, CEPH_OSDMAP_VERSION, CEPH_OSDMAP_VERSION_EXT, @@ -506,6 +596,8 @@ static int __init init_ceph_lib(void) return 0; +out_crypto: + ceph_crypto_shutdown(); out_debugfs: ceph_debugfs_cleanup(); out: @@ -516,6 +608,7 @@ static void __exit exit_ceph_lib(void) { dout("exit_ceph_lib\n"); ceph_msgr_exit(); + ceph_crypto_shutdown(); ceph_debugfs_cleanup(); } diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c index 7b505b0c983..5a8009c9e0c 100644 --- a/net/ceph/crypto.c +++ b/net/ceph/crypto.c @@ -5,10 +5,23 @@ #include <linux/scatterlist.h> #include <linux/slab.h> #include <crypto/hash.h> +#include <linux/key-type.h> +#include <keys/ceph-type.h> #include <linux/ceph/decode.h> #include "crypto.h" +int ceph_crypto_key_clone(struct ceph_crypto_key *dst, + const struct ceph_crypto_key *src) +{ + memcpy(dst, src, sizeof(struct ceph_crypto_key)); + dst->key = kmalloc(src->len, GFP_NOFS); + if (!dst->key) + return -ENOMEM; + memcpy(dst->key, src->key, src->len); + return 0; +} + int ceph_crypto_key_encode(struct ceph_crypto_key *key, void **p, void *end) { if (*p + sizeof(u16) + sizeof(key->created) + @@ -410,3 +423,63 @@ int ceph_encrypt2(struct ceph_crypto_key *secret, void *dst, size_t *dst_len, return -EINVAL; } } + +int ceph_key_instantiate(struct key *key, const void *data, size_t datalen) +{ + struct ceph_crypto_key *ckey; + int ret; + void *p; + + ret = -EINVAL; + if (datalen <= 0 || datalen > 32767 || !data) + goto err; + + ret = key_payload_reserve(key, datalen); + if (ret < 0) + goto err; + + ret = -ENOMEM; + ckey = kmalloc(sizeof(*ckey), GFP_KERNEL); + if (!ckey) + goto err; + + /* TODO ceph_crypto_key_decode should really take const input */ + p = (void*)data; + ret = ceph_crypto_key_decode(ckey, &p, (char*)data+datalen); + if (ret < 0) + goto err_ckey; + + key->payload.data = ckey; + return 0; + +err_ckey: + kfree(ckey); +err: + return ret; +} + +int ceph_key_match(const struct key *key, const void *description) +{ + return strcmp(key->description, description) == 0; +} + +void ceph_key_destroy(struct key *key) { + struct ceph_crypto_key *ckey = key->payload.data; + + ceph_crypto_key_destroy(ckey); +} + +struct key_type key_type_ceph = { + .name = "ceph", + .instantiate = ceph_key_instantiate, + .match = ceph_key_match, + .destroy = ceph_key_destroy, +}; + +int ceph_crypto_init(void) { + return register_key_type(&key_type_ceph); +} + +void ceph_crypto_shutdown(void) { + unregister_key_type(&key_type_ceph); +} diff --git a/net/ceph/crypto.h b/net/ceph/crypto.h index f9eccace592..1919d1550d7 100644 --- a/net/ceph/crypto.h +++ b/net/ceph/crypto.h @@ -19,6 +19,8 @@ static inline void ceph_crypto_key_destroy(struct ceph_crypto_key *key) kfree(key->key); } +extern int ceph_crypto_key_clone(struct ceph_crypto_key *dst, + const struct ceph_crypto_key *src); extern int ceph_crypto_key_encode(struct ceph_crypto_key *key, void **p, void *end); extern int ceph_crypto_key_decode(struct ceph_crypto_key *key, @@ -40,6 +42,8 @@ extern int ceph_encrypt2(struct ceph_crypto_key *secret, void *dst, size_t *dst_len, const void *src1, size_t src1_len, const void *src2, size_t src2_len); +extern int ceph_crypto_init(void); +extern void ceph_crypto_shutdown(void); /* armor.c */ extern int ceph_armor(char *dst, const char *src, const char *end); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 05f357828a2..e15a82ccc05 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -2267,6 +2267,19 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags) m->more_to_follow = false; m->pool = NULL; + /* middle */ + m->middle = NULL; + + /* data */ + m->nr_pages = 0; + m->page_alignment = 0; + m->pages = NULL; + m->pagelist = NULL; + m->bio = NULL; + m->bio_iter = NULL; + m->bio_seg = 0; + m->trail = NULL; + /* front */ if (front_len) { if (front_len > PAGE_CACHE_SIZE) { @@ -2286,19 +2299,6 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags) } m->front.iov_len = front_len; - /* middle */ - m->middle = NULL; - - /* data */ - m->nr_pages = 0; - m->page_alignment = 0; - m->pages = NULL; - m->pagelist = NULL; - m->bio = NULL; - m->bio_iter = NULL; - m->bio_seg = 0; - m->trail = NULL; - dout("ceph_msg_new %p front %d\n", m, front_len); return m; diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 8a079399174..cbe31fa4550 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -759,7 +759,7 @@ int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl) /* authentication */ monc->auth = ceph_auth_init(cl->options->name, - cl->options->secret); + cl->options->key); if (IS_ERR(monc->auth)) return PTR_ERR(monc->auth); monc->auth->want_keys = diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 3e20a122ffa..6b5dda1cb5d 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -22,10 +22,15 @@ #define OSD_OPREPLY_FRONT_LEN 512 static const struct ceph_connection_operations osd_con_ops; -static int __kick_requests(struct ceph_osd_client *osdc, - struct ceph_osd *kickosd); -static void kick_requests(struct ceph_osd_client *osdc, struct ceph_osd *osd); +static void send_queued(struct ceph_osd_client *osdc); +static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd); +static void __register_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req); +static void __unregister_linger_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req); +static int __send_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req); static int op_needs_trail(int op) { @@ -34,6 +39,7 @@ static int op_needs_trail(int op) case CEPH_OSD_OP_SETXATTR: case CEPH_OSD_OP_CMPXATTR: case CEPH_OSD_OP_CALL: + case CEPH_OSD_OP_NOTIFY: return 1; default: return 0; @@ -209,6 +215,8 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, init_completion(&req->r_completion); init_completion(&req->r_safe_completion); INIT_LIST_HEAD(&req->r_unsafe_item); + INIT_LIST_HEAD(&req->r_linger_item); + INIT_LIST_HEAD(&req->r_linger_osd); req->r_flags = flags; WARN_ON((flags & (CEPH_OSD_FLAG_READ|CEPH_OSD_FLAG_WRITE)) == 0); @@ -315,6 +323,24 @@ static void osd_req_encode_op(struct ceph_osd_request *req, break; case CEPH_OSD_OP_STARTSYNC: break; + case CEPH_OSD_OP_NOTIFY: + { + __le32 prot_ver = cpu_to_le32(src->watch.prot_ver); + __le32 timeout = cpu_to_le32(src->watch.timeout); + + BUG_ON(!req->r_trail); + + ceph_pagelist_append(req->r_trail, + &prot_ver, sizeof(prot_ver)); + ceph_pagelist_append(req->r_trail, + &timeout, sizeof(timeout)); + } + case CEPH_OSD_OP_NOTIFY_ACK: + case CEPH_OSD_OP_WATCH: + dst->watch.cookie = cpu_to_le64(src->watch.cookie); + dst->watch.ver = cpu_to_le64(src->watch.ver); + dst->watch.flag = src->watch.flag; + break; default: pr_err("unrecognized osd opcode %d\n", dst->op); WARN_ON(1); @@ -444,8 +470,8 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, snapc, ops, use_mempool, GFP_NOFS, NULL, NULL); - if (IS_ERR(req)) - return req; + if (!req) + return NULL; /* calculate max write size */ calc_layout(osdc, vino, layout, off, plen, req, ops); @@ -529,6 +555,51 @@ __lookup_request_ge(struct ceph_osd_client *osdc, return NULL; } +/* + * Resubmit requests pending on the given osd. + */ +static void __kick_osd_requests(struct ceph_osd_client *osdc, + struct ceph_osd *osd) +{ + struct ceph_osd_request *req, *nreq; + int err; + + dout("__kick_osd_requests osd%d\n", osd->o_osd); + err = __reset_osd(osdc, osd); + if (err == -EAGAIN) + return; + + list_for_each_entry(req, &osd->o_requests, r_osd_item) { + list_move(&req->r_req_lru_item, &osdc->req_unsent); + dout("requeued %p tid %llu osd%d\n", req, req->r_tid, + osd->o_osd); + if (!req->r_linger) + req->r_flags |= CEPH_OSD_FLAG_RETRY; + } + + list_for_each_entry_safe(req, nreq, &osd->o_linger_requests, + r_linger_osd) { + /* + * reregister request prior to unregistering linger so + * that r_osd is preserved. + */ + BUG_ON(!list_empty(&req->r_req_lru_item)); + __register_request(osdc, req); + list_add(&req->r_req_lru_item, &osdc->req_unsent); + list_add(&req->r_osd_item, &req->r_osd->o_requests); + __unregister_linger_request(osdc, req); + dout("requeued lingering %p tid %llu osd%d\n", req, req->r_tid, + osd->o_osd); + } +} + +static void kick_osd_requests(struct ceph_osd_client *osdc, + struct ceph_osd *kickosd) +{ + mutex_lock(&osdc->request_mutex); + __kick_osd_requests(osdc, kickosd); + mutex_unlock(&osdc->request_mutex); +} /* * If the osd connection drops, we need to resubmit all requests. @@ -543,7 +614,8 @@ static void osd_reset(struct ceph_connection *con) dout("osd_reset osd%d\n", osd->o_osd); osdc = osd->o_osdc; down_read(&osdc->map_sem); - kick_requests(osdc, osd); + kick_osd_requests(osdc, osd); + send_queued(osdc); up_read(&osdc->map_sem); } @@ -561,6 +633,7 @@ static struct ceph_osd *create_osd(struct ceph_osd_client *osdc) atomic_set(&osd->o_ref, 1); osd->o_osdc = osdc; INIT_LIST_HEAD(&osd->o_requests); + INIT_LIST_HEAD(&osd->o_linger_requests); INIT_LIST_HEAD(&osd->o_osd_lru); osd->o_incarnation = 1; @@ -650,7 +723,8 @@ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) int ret = 0; dout("__reset_osd %p osd%d\n", osd, osd->o_osd); - if (list_empty(&osd->o_requests)) { + if (list_empty(&osd->o_requests) && + list_empty(&osd->o_linger_requests)) { __remove_osd(osdc, osd); } else if (memcmp(&osdc->osdmap->osd_addr[osd->o_osd], &osd->o_con.peer_addr, @@ -723,15 +797,14 @@ static void __cancel_osd_timeout(struct ceph_osd_client *osdc) * Register request, assign tid. If this is the first request, set up * the timeout event. */ -static void register_request(struct ceph_osd_client *osdc, - struct ceph_osd_request *req) +static void __register_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req) { - mutex_lock(&osdc->request_mutex); req->r_tid = ++osdc->last_tid; req->r_request->hdr.tid = cpu_to_le64(req->r_tid); INIT_LIST_HEAD(&req->r_req_lru_item); - dout("register_request %p tid %lld\n", req, req->r_tid); + dout("__register_request %p tid %lld\n", req, req->r_tid); __insert_request(osdc, req); ceph_osdc_get_request(req); osdc->num_requests++; @@ -740,6 +813,13 @@ static void register_request(struct ceph_osd_client *osdc, dout(" first request, scheduling timeout\n"); __schedule_osd_timeout(osdc); } +} + +static void register_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req) +{ + mutex_lock(&osdc->request_mutex); + __register_request(osdc, req); mutex_unlock(&osdc->request_mutex); } @@ -758,9 +838,13 @@ static void __unregister_request(struct ceph_osd_client *osdc, ceph_con_revoke(&req->r_osd->o_con, req->r_request); list_del_init(&req->r_osd_item); - if (list_empty(&req->r_osd->o_requests)) + if (list_empty(&req->r_osd->o_requests) && + list_empty(&req->r_osd->o_linger_requests)) { + dout("moving osd to %p lru\n", req->r_osd); __move_osd_to_lru(osdc, req->r_osd); - req->r_osd = NULL; + } + if (list_empty(&req->r_linger_item)) + req->r_osd = NULL; } ceph_osdc_put_request(req); @@ -781,20 +865,73 @@ static void __cancel_request(struct ceph_osd_request *req) ceph_con_revoke(&req->r_osd->o_con, req->r_request); req->r_sent = 0; } - list_del_init(&req->r_req_lru_item); } +static void __register_linger_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req) +{ + dout("__register_linger_request %p\n", req); + list_add_tail(&req->r_linger_item, &osdc->req_linger); + list_add_tail(&req->r_linger_osd, &req->r_osd->o_linger_requests); +} + +static void __unregister_linger_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req) +{ + dout("__unregister_linger_request %p\n", req); + if (req->r_osd) { + list_del_init(&req->r_linger_item); + list_del_init(&req->r_linger_osd); + + if (list_empty(&req->r_osd->o_requests) && + list_empty(&req->r_osd->o_linger_requests)) { + dout("moving osd to %p lru\n", req->r_osd); + __move_osd_to_lru(osdc, req->r_osd); + } + if (list_empty(&req->r_osd_item)) + req->r_osd = NULL; + } +} + +void ceph_osdc_unregister_linger_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req) +{ + mutex_lock(&osdc->request_mutex); + if (req->r_linger) { + __unregister_linger_request(osdc, req); + ceph_osdc_put_request(req); + } + mutex_unlock(&osdc->request_mutex); +} +EXPORT_SYMBOL(ceph_osdc_unregister_linger_request); + +void ceph_osdc_set_request_linger(struct ceph_osd_client *osdc, + struct ceph_osd_request *req) +{ + if (!req->r_linger) { + dout("set_request_linger %p\n", req); + req->r_linger = 1; + /* + * caller is now responsible for calling + * unregister_linger_request + */ + ceph_osdc_get_request(req); + } +} +EXPORT_SYMBOL(ceph_osdc_set_request_linger); + /* * Pick an osd (the first 'up' osd in the pg), allocate the osd struct * (as needed), and set the request r_osd appropriately. If there is - * no up osd, set r_osd to NULL. + * no up osd, set r_osd to NULL. Move the request to the appropriate list + * (unsent, homeless) or leave on in-flight lru. * * Return 0 if unchanged, 1 if changed, or negative on error. * * Caller should hold map_sem for read and request_mutex. */ -static int __map_osds(struct ceph_osd_client *osdc, - struct ceph_osd_request *req) +static int __map_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req) { struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base; struct ceph_pg pgid; @@ -802,11 +939,13 @@ static int __map_osds(struct ceph_osd_client *osdc, int o = -1, num = 0; int err; - dout("map_osds %p tid %lld\n", req, req->r_tid); + dout("map_request %p tid %lld\n", req, req->r_tid); err = ceph_calc_object_layout(&reqhead->layout, req->r_oid, &req->r_file_layout, osdc->osdmap); - if (err) + if (err) { + list_move(&req->r_req_lru_item, &osdc->req_notarget); return err; + } pgid = reqhead->layout.ol_pgid; req->r_pgid = pgid; @@ -823,7 +962,7 @@ static int __map_osds(struct ceph_osd_client *osdc, (req->r_osd == NULL && o == -1)) return 0; /* no change */ - dout("map_osds tid %llu pgid %d.%x osd%d (was osd%d)\n", + dout("map_request tid %llu pgid %d.%x osd%d (was osd%d)\n", req->r_tid, le32_to_cpu(pgid.pool), le16_to_cpu(pgid.ps), o, req->r_osd ? req->r_osd->o_osd : -1); @@ -841,10 +980,12 @@ static int __map_osds(struct ceph_osd_client *osdc, if (!req->r_osd && o >= 0) { err = -ENOMEM; req->r_osd = create_osd(osdc); - if (!req->r_osd) + if (!req->r_osd) { + list_move(&req->r_req_lru_item, &osdc->req_notarget); goto out; + } - dout("map_osds osd %p is osd%d\n", req->r_osd, o); + dout("map_request osd %p is osd%d\n", req->r_osd, o); req->r_osd->o_osd = o; req->r_osd->o_con.peer_name.num = cpu_to_le64(o); __insert_osd(osdc, req->r_osd); @@ -855,6 +996,9 @@ static int __map_osds(struct ceph_osd_client *osdc, if (req->r_osd) { __remove_osd_from_lru(req->r_osd); list_add(&req->r_osd_item, &req->r_osd->o_requests); + list_move(&req->r_req_lru_item, &osdc->req_unsent); + } else { + list_move(&req->r_req_lru_item, &osdc->req_notarget); } err = 1; /* osd or pg changed */ @@ -869,16 +1013,6 @@ static int __send_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req) { struct ceph_osd_request_head *reqhead; - int err; - - err = __map_osds(osdc, req); - if (err < 0) - return err; - if (req->r_osd == NULL) { - dout("send_request %p no up osds in pg\n", req); - ceph_monc_request_next_osdmap(&osdc->client->monc); - return 0; - } dout("send_request %p tid %llu to osd%d flags %d\n", req, req->r_tid, req->r_osd->o_osd, req->r_flags); @@ -898,6 +1032,21 @@ static int __send_request(struct ceph_osd_client *osdc, } /* + * Send any requests in the queue (req_unsent). + */ +static void send_queued(struct ceph_osd_client *osdc) +{ + struct ceph_osd_request *req, *tmp; + + dout("send_queued\n"); + mutex_lock(&osdc->request_mutex); + list_for_each_entry_safe(req, tmp, &osdc->req_unsent, r_req_lru_item) { + __send_request(osdc, req); + } + mutex_unlock(&osdc->request_mutex); +} + +/* * Timeout callback, called every N seconds when 1 or more osd * requests has been active for more than N seconds. When this * happens, we ping all OSDs with requests who have timed out to @@ -916,30 +1065,13 @@ static void handle_timeout(struct work_struct *work) unsigned long keepalive = osdc->client->options->osd_keepalive_timeout * HZ; unsigned long last_stamp = 0; - struct rb_node *p; struct list_head slow_osds; - dout("timeout\n"); down_read(&osdc->map_sem); ceph_monc_request_next_osdmap(&osdc->client->monc); mutex_lock(&osdc->request_mutex); - for (p = rb_first(&osdc->requests); p; p = rb_next(p)) { - req = rb_entry(p, struct ceph_osd_request, r_node); - - if (req->r_resend) { - int err; - - dout("osdc resending prev failed %lld\n", req->r_tid); - err = __send_request(osdc, req); - if (err) - dout("osdc failed again on %lld\n", req->r_tid); - else - req->r_resend = false; - continue; - } - } /* * reset osds that appear to be _really_ unresponsive. this @@ -963,7 +1095,7 @@ static void handle_timeout(struct work_struct *work) BUG_ON(!osd); pr_warning(" tid %llu timed out on osd%d, will reset osd\n", req->r_tid, osd->o_osd); - __kick_requests(osdc, osd); + __kick_osd_requests(osdc, osd); } /* @@ -991,7 +1123,7 @@ static void handle_timeout(struct work_struct *work) __schedule_osd_timeout(osdc); mutex_unlock(&osdc->request_mutex); - + send_queued(osdc); up_read(&osdc->map_sem); } @@ -1035,7 +1167,6 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, numops * sizeof(struct ceph_osd_op)) goto bad; dout("handle_reply %p tid %llu result %d\n", msg, tid, (int)result); - /* lookup */ mutex_lock(&osdc->request_mutex); req = __lookup_request(osdc, tid); @@ -1079,6 +1210,9 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, dout("handle_reply tid %llu flags %d\n", tid, flags); + if (req->r_linger && (flags & CEPH_OSD_FLAG_ONDISK)) + __register_linger_request(osdc, req); + /* either this is a read, or we got the safe response */ if (result < 0 || (flags & CEPH_OSD_FLAG_ONDISK) || @@ -1099,6 +1233,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, } done: + dout("req=%p req->r_linger=%d\n", req, req->r_linger); ceph_osdc_put_request(req); return; @@ -1109,108 +1244,83 @@ bad: ceph_msg_dump(msg); } - -static int __kick_requests(struct ceph_osd_client *osdc, - struct ceph_osd *kickosd) +static void reset_changed_osds(struct ceph_osd_client *osdc) { - struct ceph_osd_request *req; struct rb_node *p, *n; - int needmap = 0; - int err; - dout("kick_requests osd%d\n", kickosd ? kickosd->o_osd : -1); - if (kickosd) { - err = __reset_osd(osdc, kickosd); - if (err == -EAGAIN) - return 1; - } else { - for (p = rb_first(&osdc->osds); p; p = n) { - struct ceph_osd *osd = - rb_entry(p, struct ceph_osd, o_node); - - n = rb_next(p); - if (!ceph_osd_is_up(osdc->osdmap, osd->o_osd) || - memcmp(&osd->o_con.peer_addr, - ceph_osd_addr(osdc->osdmap, - osd->o_osd), - sizeof(struct ceph_entity_addr)) != 0) - __reset_osd(osdc, osd); - } + for (p = rb_first(&osdc->osds); p; p = n) { + struct ceph_osd *osd = rb_entry(p, struct ceph_osd, o_node); + + n = rb_next(p); + if (!ceph_osd_is_up(osdc->osdmap, osd->o_osd) || + memcmp(&osd->o_con.peer_addr, + ceph_osd_addr(osdc->osdmap, + osd->o_osd), + sizeof(struct ceph_entity_addr)) != 0) + __reset_osd(osdc, osd); } +} + +/* + * Requeue requests whose mapping to an OSD has changed. If requests map to + * no osd, request a new map. + * + * Caller should hold map_sem for read and request_mutex. + */ +static void kick_requests(struct ceph_osd_client *osdc) +{ + struct ceph_osd_request *req, *nreq; + struct rb_node *p; + int needmap = 0; + int err; + dout("kick_requests\n"); + mutex_lock(&osdc->request_mutex); for (p = rb_first(&osdc->requests); p; p = rb_next(p)) { req = rb_entry(p, struct ceph_osd_request, r_node); - - if (req->r_resend) { - dout(" r_resend set on tid %llu\n", req->r_tid); - __cancel_request(req); - goto kick; - } - if (req->r_osd && kickosd == req->r_osd) { - __cancel_request(req); - goto kick; + err = __map_request(osdc, req); + if (err < 0) + continue; /* error */ + if (req->r_osd == NULL) { + dout("%p tid %llu maps to no osd\n", req, req->r_tid); + needmap++; /* request a newer map */ + } else if (err > 0) { + dout("%p tid %llu requeued on osd%d\n", req, req->r_tid, + req->r_osd ? req->r_osd->o_osd : -1); + if (!req->r_linger) + req->r_flags |= CEPH_OSD_FLAG_RETRY; } + } - err = __map_osds(osdc, req); + list_for_each_entry_safe(req, nreq, &osdc->req_linger, + r_linger_item) { + dout("linger req=%p req->r_osd=%p\n", req, req->r_osd); + + err = __map_request(osdc, req); if (err == 0) - continue; /* no change */ - if (err < 0) { - /* - * FIXME: really, we should set the request - * error and fail if this isn't a 'nofail' - * request, but that's a fair bit more - * complicated to do. So retry! - */ - dout(" setting r_resend on %llu\n", req->r_tid); - req->r_resend = true; - continue; - } + continue; /* no change and no osd was specified */ + if (err < 0) + continue; /* hrm! */ if (req->r_osd == NULL) { dout("tid %llu maps to no valid osd\n", req->r_tid); needmap++; /* request a newer map */ continue; } -kick: - dout("kicking %p tid %llu osd%d\n", req, req->r_tid, + dout("kicking lingering %p tid %llu osd%d\n", req, req->r_tid, req->r_osd ? req->r_osd->o_osd : -1); - req->r_flags |= CEPH_OSD_FLAG_RETRY; - err = __send_request(osdc, req); - if (err) { - dout(" setting r_resend on %llu\n", req->r_tid); - req->r_resend = true; - } + __unregister_linger_request(osdc, req); + __register_request(osdc, req); } - - return needmap; -} - -/* - * Resubmit osd requests whose osd or osd address has changed. Request - * a new osd map if osds are down, or we are otherwise unable to determine - * how to direct a request. - * - * Close connections to down osds. - * - * If @who is specified, resubmit requests for that specific osd. - * - * Caller should hold map_sem for read and request_mutex. - */ -static void kick_requests(struct ceph_osd_client *osdc, - struct ceph_osd *kickosd) -{ - int needmap; - - mutex_lock(&osdc->request_mutex); - needmap = __kick_requests(osdc, kickosd); mutex_unlock(&osdc->request_mutex); if (needmap) { dout("%d requests for down osds, need new map\n", needmap); ceph_monc_request_next_osdmap(&osdc->client->monc); } - } + + /* * Process updated osd map. * @@ -1263,6 +1373,8 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) ceph_osdmap_destroy(osdc->osdmap); osdc->osdmap = newmap; } + kick_requests(osdc); + reset_changed_osds(osdc); } else { dout("ignoring incremental map %u len %d\n", epoch, maplen); @@ -1300,6 +1412,7 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) osdc->osdmap = newmap; if (oldmap) ceph_osdmap_destroy(oldmap); + kick_requests(osdc); } p += maplen; nr_maps--; @@ -1308,8 +1421,7 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) done: downgrade_write(&osdc->map_sem); ceph_monc_got_osdmap(&osdc->client->monc, osdc->osdmap->epoch); - if (newmap) - kick_requests(osdc, NULL); + send_queued(osdc); up_read(&osdc->map_sem); wake_up_all(&osdc->client->auth_wq); return; @@ -1322,6 +1434,223 @@ bad: } /* + * watch/notify callback event infrastructure + * + * These callbacks are used both for watch and notify operations. + */ +static void __release_event(struct kref *kref) +{ + struct ceph_osd_event *event = + container_of(kref, struct ceph_osd_event, kref); + + dout("__release_event %p\n", event); + kfree(event); +} + +static void get_event(struct ceph_osd_event *event) +{ + kref_get(&event->kref); +} + +void ceph_osdc_put_event(struct ceph_osd_event *event) +{ + kref_put(&event->kref, __release_event); +} +EXPORT_SYMBOL(ceph_osdc_put_event); + +static void __insert_event(struct ceph_osd_client *osdc, + struct ceph_osd_event *new) +{ + struct rb_node **p = &osdc->event_tree.rb_node; + struct rb_node *parent = NULL; + struct ceph_osd_event *event = NULL; + + while (*p) { + parent = *p; + event = rb_entry(parent, struct ceph_osd_event, node); + if (new->cookie < event->cookie) + p = &(*p)->rb_left; + else if (new->cookie > event->cookie) + p = &(*p)->rb_right; + else + BUG(); + } + + rb_link_node(&new->node, parent, p); + rb_insert_color(&new->node, &osdc->event_tree); +} + +static struct ceph_osd_event *__find_event(struct ceph_osd_client *osdc, + u64 cookie) +{ + struct rb_node **p = &osdc->event_tree.rb_node; + struct rb_node *parent = NULL; + struct ceph_osd_event *event = NULL; + + while (*p) { + parent = *p; + event = rb_entry(parent, struct ceph_osd_event, node); + if (cookie < event->cookie) + p = &(*p)->rb_left; + else if (cookie > event->cookie) + p = &(*p)->rb_right; + else + return event; + } + return NULL; +} + +static void __remove_event(struct ceph_osd_event *event) +{ + struct ceph_osd_client *osdc = event->osdc; + + if (!RB_EMPTY_NODE(&event->node)) { + dout("__remove_event removed %p\n", event); + rb_erase(&event->node, &osdc->event_tree); + ceph_osdc_put_event(event); + } else { + dout("__remove_event didn't remove %p\n", event); + } +} + +int ceph_osdc_create_event(struct ceph_osd_client *osdc, + void (*event_cb)(u64, u64, u8, void *), + int one_shot, void *data, + struct ceph_osd_event **pevent) +{ + struct ceph_osd_event *event; + + event = kmalloc(sizeof(*event), GFP_NOIO); + if (!event) + return -ENOMEM; + + dout("create_event %p\n", event); + event->cb = event_cb; + event->one_shot = one_shot; + event->data = data; + event->osdc = osdc; + INIT_LIST_HEAD(&event->osd_node); + kref_init(&event->kref); /* one ref for us */ + kref_get(&event->kref); /* one ref for the caller */ + init_completion(&event->completion); + + spin_lock(&osdc->event_lock); + event->cookie = ++osdc->event_count; + __insert_event(osdc, event); + spin_unlock(&osdc->event_lock); + + *pevent = event; + return 0; +} +EXPORT_SYMBOL(ceph_osdc_create_event); + +void ceph_osdc_cancel_event(struct ceph_osd_event *event) +{ + struct ceph_osd_client *osdc = event->osdc; + + dout("cancel_event %p\n", event); + spin_lock(&osdc->event_lock); + __remove_event(event); + spin_unlock(&osdc->event_lock); + ceph_osdc_put_event(event); /* caller's */ +} +EXPORT_SYMBOL(ceph_osdc_cancel_event); + + +static void do_event_work(struct work_struct *work) +{ + struct ceph_osd_event_work *event_work = + container_of(work, struct ceph_osd_event_work, work); + struct ceph_osd_event *event = event_work->event; + u64 ver = event_work->ver; + u64 notify_id = event_work->notify_id; + u8 opcode = event_work->opcode; + + dout("do_event_work completing %p\n", event); + event->cb(ver, notify_id, opcode, event->data); + complete(&event->completion); + dout("do_event_work completed %p\n", event); + ceph_osdc_put_event(event); + kfree(event_work); +} + + +/* + * Process osd watch notifications + */ +void handle_watch_notify(struct ceph_osd_client *osdc, struct ceph_msg *msg) +{ + void *p, *end; + u8 proto_ver; + u64 cookie, ver, notify_id; + u8 opcode; + struct ceph_osd_event *event; + struct ceph_osd_event_work *event_work; + + p = msg->front.iov_base; + end = p + msg->front.iov_len; + + ceph_decode_8_safe(&p, end, proto_ver, bad); + ceph_decode_8_safe(&p, end, opcode, bad); + ceph_decode_64_safe(&p, end, cookie, bad); + ceph_decode_64_safe(&p, end, ver, bad); + ceph_decode_64_safe(&p, end, notify_id, bad); + + spin_lock(&osdc->event_lock); + event = __find_event(osdc, cookie); + if (event) { + get_event(event); + if (event->one_shot) + __remove_event(event); + } + spin_unlock(&osdc->event_lock); + dout("handle_watch_notify cookie %lld ver %lld event %p\n", + cookie, ver, event); + if (event) { + event_work = kmalloc(sizeof(*event_work), GFP_NOIO); + if (!event_work) { + dout("ERROR: could not allocate event_work\n"); + goto done_err; + } + INIT_WORK(&event_work->work, do_event_work); + event_work->event = event; + event_work->ver = ver; + event_work->notify_id = notify_id; + event_work->opcode = opcode; + if (!queue_work(osdc->notify_wq, &event_work->work)) { + dout("WARNING: failed to queue notify event work\n"); + goto done_err; + } + } + + return; + +done_err: + complete(&event->completion); + ceph_osdc_put_event(event); + return; + +bad: + pr_err("osdc handle_watch_notify corrupt msg\n"); + return; +} + +int ceph_osdc_wait_event(struct ceph_osd_event *event, unsigned long timeout) +{ + int err; + + dout("wait_event %p\n", event); + err = wait_for_completion_interruptible_timeout(&event->completion, + timeout * HZ); + ceph_osdc_put_event(event); + if (err > 0) + err = 0; + dout("wait_event %p returns %d\n", event, err); + return err; +} +EXPORT_SYMBOL(ceph_osdc_wait_event); + +/* * Register request, send initial attempt. */ int ceph_osdc_start_request(struct ceph_osd_client *osdc, @@ -1347,18 +1676,27 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc, * the request still han't been touched yet. */ if (req->r_sent == 0) { - rc = __send_request(osdc, req); - if (rc) { - if (nofail) { - dout("osdc_start_request failed send, " - " marking %lld\n", req->r_tid); - req->r_resend = true; - rc = 0; - } else { - __unregister_request(osdc, req); + rc = __map_request(osdc, req); + if (rc < 0) + goto out_unlock; + if (req->r_osd == NULL) { + dout("send_request %p no up osds in pg\n", req); + ceph_monc_request_next_osdmap(&osdc->client->monc); + } else { + rc = __send_request(osdc, req); + if (rc) { + if (nofail) { + dout("osdc_start_request failed send, " + " will retry %lld\n", req->r_tid); + rc = 0; + } else { + __unregister_request(osdc, req); + } } } } + +out_unlock: mutex_unlock(&osdc->request_mutex); up_read(&osdc->map_sem); return rc; @@ -1441,9 +1779,15 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client) INIT_LIST_HEAD(&osdc->osd_lru); osdc->requests = RB_ROOT; INIT_LIST_HEAD(&osdc->req_lru); + INIT_LIST_HEAD(&osdc->req_unsent); + INIT_LIST_HEAD(&osdc->req_notarget); + INIT_LIST_HEAD(&osdc->req_linger); osdc->num_requests = 0; INIT_DELAYED_WORK(&osdc->timeout_work, handle_timeout); INIT_DELAYED_WORK(&osdc->osds_timeout_work, handle_osds_timeout); + spin_lock_init(&osdc->event_lock); + osdc->event_tree = RB_ROOT; + osdc->event_count = 0; schedule_delayed_work(&osdc->osds_timeout_work, round_jiffies_relative(osdc->client->options->osd_idle_ttl * HZ)); @@ -1463,6 +1807,13 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client) "osd_op_reply"); if (err < 0) goto out_msgpool; + + osdc->notify_wq = create_singlethread_workqueue("ceph-watch-notify"); + if (IS_ERR(osdc->notify_wq)) { + err = PTR_ERR(osdc->notify_wq); + osdc->notify_wq = NULL; + goto out_msgpool; + } return 0; out_msgpool: @@ -1476,6 +1827,8 @@ EXPORT_SYMBOL(ceph_osdc_init); void ceph_osdc_stop(struct ceph_osd_client *osdc) { + flush_workqueue(osdc->notify_wq); + destroy_workqueue(osdc->notify_wq); cancel_delayed_work_sync(&osdc->timeout_work); cancel_delayed_work_sync(&osdc->osds_timeout_work); if (osdc->osdmap) { @@ -1483,6 +1836,7 @@ void ceph_osdc_stop(struct ceph_osd_client *osdc) osdc->osdmap = NULL; } remove_old_osds(osdc, 1); + WARN_ON(!RB_EMPTY_ROOT(&osdc->osds)); mempool_destroy(osdc->req_mempool); ceph_msgpool_destroy(&osdc->msgpool_op); ceph_msgpool_destroy(&osdc->msgpool_op_reply); @@ -1591,6 +1945,9 @@ static void dispatch(struct ceph_connection *con, struct ceph_msg *msg) case CEPH_MSG_OSD_OPREPLY: handle_reply(osdc, msg, con); break; + case CEPH_MSG_WATCH_NOTIFY: + handle_watch_notify(osdc, msg); + break; default: pr_err("received unknown message type %d %s\n", type, @@ -1684,6 +2041,7 @@ static struct ceph_msg *alloc_msg(struct ceph_connection *con, switch (type) { case CEPH_MSG_OSD_MAP: + case CEPH_MSG_WATCH_NOTIFY: return ceph_msg_new(type, front, GFP_NOFS); case CEPH_MSG_OSD_OPREPLY: return get_reply(con, hdr, skip); diff --git a/net/core/dev.c b/net/core/dev.c index 0b88eba97da..b624fe4d9bd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1140,9 +1140,6 @@ static int __dev_open(struct net_device *dev) ASSERT_RTNL(); - /* - * Is it even present? - */ if (!netif_device_present(dev)) return -ENODEV; @@ -1151,9 +1148,6 @@ static int __dev_open(struct net_device *dev) if (ret) return ret; - /* - * Call device private open method - */ set_bit(__LINK_STATE_START, &dev->state); if (ops->ndo_validate_addr) @@ -1162,31 +1156,12 @@ static int __dev_open(struct net_device *dev) if (!ret && ops->ndo_open) ret = ops->ndo_open(dev); - /* - * If it went open OK then: - */ - if (ret) clear_bit(__LINK_STATE_START, &dev->state); else { - /* - * Set the flags. - */ dev->flags |= IFF_UP; - - /* - * Enable NET_DMA - */ net_dmaengine_get(); - - /* - * Initialize multicasting status - */ dev_set_rx_mode(dev); - - /* - * Wakeup transmit queue engine - */ dev_activate(dev); } @@ -1209,22 +1184,13 @@ int dev_open(struct net_device *dev) { int ret; - /* - * Is it already up? - */ if (dev->flags & IFF_UP) return 0; - /* - * Open device - */ ret = __dev_open(dev); if (ret < 0) return ret; - /* - * ... and announce new interface. - */ rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); call_netdevice_notifiers(NETDEV_UP, dev); @@ -1240,10 +1206,6 @@ static int __dev_close_many(struct list_head *head) might_sleep(); list_for_each_entry(dev, head, unreg_list) { - /* - * Tell people we are going down, so that they can - * prepare to death, when device is still operating. - */ call_netdevice_notifiers(NETDEV_GOING_DOWN, dev); clear_bit(__LINK_STATE_START, &dev->state); @@ -1272,15 +1234,7 @@ static int __dev_close_many(struct list_head *head) if (ops->ndo_stop) ops->ndo_stop(dev); - /* - * Device is now down. - */ - dev->flags &= ~IFF_UP; - - /* - * Shutdown NET_DMA - */ net_dmaengine_put(); } @@ -1309,9 +1263,6 @@ static int dev_close_many(struct list_head *head) __dev_close_many(head); - /* - * Tell people we are down - */ list_for_each_entry(dev, head, unreg_list) { rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); call_netdevice_notifiers(NETDEV_DOWN, dev); @@ -1333,11 +1284,13 @@ static int dev_close_many(struct list_head *head) */ int dev_close(struct net_device *dev) { - LIST_HEAD(single); + if (dev->flags & IFF_UP) { + LIST_HEAD(single); - list_add(&dev->unreg_list, &single); - dev_close_many(&single); - list_del(&single); + list_add(&dev->unreg_list, &single); + dev_close_many(&single); + list_del(&single); + } return 0; } EXPORT_SYMBOL(dev_close); @@ -1353,14 +1306,17 @@ EXPORT_SYMBOL(dev_close); */ void dev_disable_lro(struct net_device *dev) { - if (dev->ethtool_ops && dev->ethtool_ops->get_flags && - dev->ethtool_ops->set_flags) { - u32 flags = dev->ethtool_ops->get_flags(dev); - if (flags & ETH_FLAG_LRO) { - flags &= ~ETH_FLAG_LRO; - dev->ethtool_ops->set_flags(dev, flags); - } - } + u32 flags; + + if (dev->ethtool_ops && dev->ethtool_ops->get_flags) + flags = dev->ethtool_ops->get_flags(dev); + else + flags = ethtool_op_get_flags(dev); + + if (!(flags & ETH_FLAG_LRO)) + return; + + __ethtool_set_flags(dev, flags & ~ETH_FLAG_LRO); WARN_ON(dev->features & NETIF_F_LRO); } EXPORT_SYMBOL(dev_disable_lro); @@ -1368,11 +1324,6 @@ EXPORT_SYMBOL(dev_disable_lro); static int dev_boot_phase = 1; -/* - * Device change register/unregister. These are not inline or static - * as we export them to the world. - */ - /** * register_netdevice_notifier - register a network notifier block * @nb: notifier @@ -1474,6 +1425,7 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev) ASSERT_RTNL(); return raw_notifier_call_chain(&netdev_chain, val, dev); } +EXPORT_SYMBOL(call_netdevice_notifiers); /* When > 0 there are consumers of rx skb time stamps */ static atomic_t netstamp_needed = ATOMIC_INIT(0); @@ -1504,6 +1456,27 @@ static inline void net_timestamp_check(struct sk_buff *skb) __net_timestamp(skb); } +static inline bool is_skb_forwardable(struct net_device *dev, + struct sk_buff *skb) +{ + unsigned int len; + + if (!(dev->flags & IFF_UP)) + return false; + + len = dev->mtu + dev->hard_header_len + VLAN_HLEN; + if (skb->len <= len) + return true; + + /* if TSO is enabled, we don't care about the length as the packet + * could be forwarded without being segmented before + */ + if (skb_is_gso(skb)) + return true; + + return false; +} + /** * dev_forward_skb - loopback an skb to another netif * @@ -1527,8 +1500,7 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) skb_orphan(skb); nf_reset(skb); - if (unlikely(!(dev->flags & IFF_UP) || - (skb->len > (dev->mtu + dev->hard_header_len + VLAN_HLEN)))) { + if (unlikely(!is_skb_forwardable(dev, skb))) { atomic_long_inc(&dev->rx_dropped); kfree_skb(skb); return NET_RX_DROP; @@ -2121,7 +2093,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, u32 features; /* - * If device doesnt need skb->dst, release it right now while + * If device doesn't need skb->dst, release it right now while * its hot in this cpu cache */ if (dev->priv_flags & IFF_XMIT_DST_RELEASE) @@ -2181,7 +2153,7 @@ gso: nskb->next = NULL; /* - * If device doesnt need nskb->dst, release it right now while + * If device doesn't need nskb->dst, release it right now while * its hot in this cpu cache */ if (dev->priv_flags & IFF_XMIT_DST_RELEASE) @@ -3000,8 +2972,8 @@ EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); * when CONFIG_NET_CLS_ACT is? otherwise some useless instructions * a compare and 2 stores extra right now if we dont have it on * but have CONFIG_NET_CLS_ACT - * NOTE: This doesnt stop any functionality; if you dont have - * the ingress scheduler, you just cant add policies on ingress. + * NOTE: This doesn't stop any functionality; if you dont have + * the ingress scheduler, you just can't add policies on ingress. * */ static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq) @@ -3830,7 +3802,7 @@ static void net_rx_action(struct softirq_action *h) * with netpoll's poll_napi(). Only the entity which * obtains the lock and sees NAPI_STATE_SCHED set will * actually make the ->poll() call. Therefore we avoid - * accidently calling ->poll() when NAPI is not scheduled. + * accidentally calling ->poll() when NAPI is not scheduled. */ work = 0; if (test_bit(NAPI_STATE_SCHED, &n->state)) { @@ -4803,7 +4775,7 @@ static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cm * is never reached */ WARN_ON(1); - err = -EINVAL; + err = -ENOTTY; break; } @@ -5071,7 +5043,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) /* Set the per device memory buffer space. * Not applicable in our case */ case SIOCSIFLINK: - return -EINVAL; + return -ENOTTY; /* * Unknown or private ioctl. @@ -5092,7 +5064,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) /* Take care of Wireless Extensions */ if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) return wext_handle_ioctl(net, &ifr, cmd, arg); - return -EINVAL; + return -ENOTTY; } } @@ -5214,33 +5186,37 @@ u32 netdev_fix_features(struct net_device *dev, u32 features) /* Fix illegal checksum combinations */ if ((features & NETIF_F_HW_CSUM) && (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { - netdev_info(dev, "mixed HW and IP checksum settings.\n"); + netdev_warn(dev, "mixed HW and IP checksum settings.\n"); features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); } if ((features & NETIF_F_NO_CSUM) && (features & (NETIF_F_HW_CSUM|NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { - netdev_info(dev, "mixed no checksumming and other settings.\n"); + netdev_warn(dev, "mixed no checksumming and other settings.\n"); features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM); } /* Fix illegal SG+CSUM combinations. */ if ((features & NETIF_F_SG) && !(features & NETIF_F_ALL_CSUM)) { - netdev_info(dev, - "Dropping NETIF_F_SG since no checksum feature.\n"); + netdev_dbg(dev, + "Dropping NETIF_F_SG since no checksum feature.\n"); features &= ~NETIF_F_SG; } /* TSO requires that SG is present as well. */ - if ((features & NETIF_F_TSO) && !(features & NETIF_F_SG)) { - netdev_info(dev, "Dropping NETIF_F_TSO since no SG feature.\n"); - features &= ~NETIF_F_TSO; + if ((features & NETIF_F_ALL_TSO) && !(features & NETIF_F_SG)) { + netdev_dbg(dev, "Dropping TSO features since no SG feature.\n"); + features &= ~NETIF_F_ALL_TSO; } + /* TSO ECN requires that TSO is present as well. */ + if ((features & NETIF_F_ALL_TSO) == NETIF_F_TSO_ECN) + features &= ~NETIF_F_TSO_ECN; + /* Software GSO depends on SG. */ if ((features & NETIF_F_GSO) && !(features & NETIF_F_SG)) { - netdev_info(dev, "Dropping NETIF_F_GSO since no SG feature.\n"); + netdev_dbg(dev, "Dropping NETIF_F_GSO since no SG feature.\n"); features &= ~NETIF_F_GSO; } @@ -5250,13 +5226,13 @@ u32 netdev_fix_features(struct net_device *dev, u32 features) if (!((features & NETIF_F_GEN_CSUM) || (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)) == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { - netdev_info(dev, + netdev_dbg(dev, "Dropping NETIF_F_UFO since no checksum offload features.\n"); features &= ~NETIF_F_UFO; } if (!(features & NETIF_F_SG)) { - netdev_info(dev, + netdev_dbg(dev, "Dropping NETIF_F_UFO since no NETIF_F_SG feature.\n"); features &= ~NETIF_F_UFO; } @@ -5438,12 +5414,6 @@ int register_netdevice(struct net_device *dev) dev->features |= NETIF_F_SOFT_FEATURES; dev->wanted_features = dev->features & dev->hw_features; - /* Avoid warning from netdev_fix_features() for GSO without SG */ - if (!(dev->wanted_features & NETIF_F_SG)) { - dev->wanted_features &= ~NETIF_F_GSO; - dev->features &= ~NETIF_F_GSO; - } - /* Enable GRO and NETIF_F_HIGHDMA for vlans by default, * vlan_dev_init() will do the dev->features check, so these features * are enabled only if supported by underlying device. @@ -6366,7 +6336,7 @@ static void __net_exit default_device_exit(struct net *net) if (dev->rtnl_link_ops) continue; - /* Push remaing network devices to init_net */ + /* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 36e603c78ce..706502ff64a 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -350,7 +350,7 @@ static int __init init_net_drop_monitor(void) struct per_cpu_dm_data *data; int cpu, rc; - printk(KERN_INFO "Initalizing network drop monitor service\n"); + printk(KERN_INFO "Initializing network drop monitor service\n"); if (sizeof(void *) > 8) { printk(KERN_ERR "Unable to store program counters on this arch, Drop monitor failed\n"); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index c1a71bb738d..74ead9eca12 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -141,9 +141,24 @@ u32 ethtool_op_get_flags(struct net_device *dev) } EXPORT_SYMBOL(ethtool_op_get_flags); +/* Check if device can enable (or disable) particular feature coded in "data" + * argument. Flags "supported" describe features that can be toggled by device. + * If feature can not be toggled, it state (enabled or disabled) must match + * hardcoded device features state, otherwise flags are marked as invalid. + */ +bool ethtool_invalid_flags(struct net_device *dev, u32 data, u32 supported) +{ + u32 features = dev->features & flags_dup_features; + /* "data" can contain only flags_dup_features bits, + * see __ethtool_set_flags */ + + return (features & ~supported) != (data & ~supported); +} +EXPORT_SYMBOL(ethtool_invalid_flags); + int ethtool_op_set_flags(struct net_device *dev, u32 data, u32 supported) { - if (data & ~supported) + if (ethtool_invalid_flags(dev, data, supported)) return -EINVAL; dev->features = ((dev->features & ~flags_dup_features) | @@ -513,7 +528,7 @@ static int ethtool_set_one_feature(struct net_device *dev, } } -static int __ethtool_set_flags(struct net_device *dev, u32 data) +int __ethtool_set_flags(struct net_device *dev, u32 data) { u32 changed; @@ -1457,6 +1472,9 @@ static int __ethtool_set_sg(struct net_device *dev, u32 data) { int err; + if (!dev->ethtool_ops->set_sg) + return -EOPNOTSUPP; + if (data && !(dev->features & NETIF_F_ALL_CSUM)) return -EINVAL; diff --git a/net/core/filter.c b/net/core/filter.c index 232b1873bb2..afb8afb066b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -425,7 +425,7 @@ EXPORT_SYMBOL(sk_run_filter); * As we dont want to clear mem[] array for each packet going through * sk_run_filter(), we check that filter loaded by user never try to read * a cell if not previously written, and we check all branches to be sure - * a malicious user doesnt try to abuse us. + * a malicious user doesn't try to abuse us. */ static int check_load_and_stores(struct sock_filter *filter, int flen) { diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 01a1101b593..a7b34213186 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -129,7 +129,7 @@ static void linkwatch_schedule_work(int urgent) if (!cancel_delayed_work(&linkwatch_work)) return; - /* Otherwise we reschedule it again for immediate exection. */ + /* Otherwise we reschedule it again for immediate execution. */ schedule_delayed_work(&linkwatch_work, 0); } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 0c55eaa70e3..aeeece72b72 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3761,7 +3761,10 @@ static int __init pktgen_create_thread(int cpu) list_add_tail(&t->th_list, &pktgen_threads); init_completion(&t->start_done); - p = kthread_create(pktgen_thread_worker, t, "kpktgend_%d", cpu); + p = kthread_create_on_node(pktgen_thread_worker, + t, + cpu_to_node(cpu), + "kpktgend_%d", cpu); if (IS_ERR(p)) { pr_err("kernel_thread() failed for cpu %d\n", t->cpu); list_del(&t->th_list); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 49f7ea5b4c7..d7c4bb4b182 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -196,7 +196,7 @@ EXPORT_SYMBOL_GPL(__rtnl_register); * as failure of this function is very unlikely, it can only happen due * to lack of memory when allocating the chain to store all message * handlers for a protocol. Meant for use in init functions where lack - * of memory implies no sense in continueing. + * of memory implies no sense in continuing. */ void rtnl_register(int protocol, int msgtype, rtnl_doit_func doit, rtnl_dumpit_func dumpit) @@ -1440,7 +1440,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, errout: if (err < 0 && modified && net_ratelimit()) printk(KERN_WARNING "A link change request failed with " - "some changes comitted already. Interface %s may " + "some changes committed already. Interface %s may " "have been left with an inconsistent configuration, " "please check.\n", dev->name); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 801dd08908f..7ebeed0a877 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2267,7 +2267,7 @@ EXPORT_SYMBOL(skb_prepare_seq_read); * of bytes already consumed and the next call to * skb_seq_read() will return the remaining part of the block. * - * Note 1: The size of each block of data returned can be arbitary, + * Note 1: The size of each block of data returned can be arbitrary, * this limitation is the cost for zerocopy seqeuental * reads of potentially non linear data. * diff --git a/net/core/sock.c b/net/core/sock.c index 7dfed792434..6e819780c23 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -215,7 +215,7 @@ __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; -/* Maximal space eaten by iovec or ancilliary data plus some space */ +/* Maximal space eaten by iovec or ancillary data plus some space */ int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); EXPORT_SYMBOL(sysctl_optmem_max); @@ -1175,7 +1175,7 @@ static void __sk_free(struct sock *sk) void sk_free(struct sock *sk) { /* - * We substract one from sk_wmem_alloc and can know if + * We subtract one from sk_wmem_alloc and can know if * some packets are still in some tx queue. * If not null, sock_wfree() will call __sk_free(sk) later */ @@ -1185,10 +1185,10 @@ void sk_free(struct sock *sk) EXPORT_SYMBOL(sk_free); /* - * Last sock_put should drop referrence to sk->sk_net. It has already - * been dropped in sk_change_net. Taking referrence to stopping namespace + * Last sock_put should drop reference to sk->sk_net. It has already + * been dropped in sk_change_net. Taking reference to stopping namespace * is not an option. - * Take referrence to a socket to remove it from hash _alive_ and after that + * Take reference to a socket to remove it from hash _alive_ and after that * destroy it in the context of init_net. */ void sk_release_kernel(struct sock *sk) diff --git a/net/dccp/options.c b/net/dccp/options.c index f06ffcfc8d7..4b2ab657ac8 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -123,6 +123,8 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, case DCCPO_CHANGE_L ... DCCPO_CONFIRM_R: if (pkt_type == DCCP_PKT_DATA) /* RFC 4340, 6 */ break; + if (len == 0) + goto out_invalid_option; rc = dccp_feat_parse_options(sk, dreq, mandatory, opt, *value, value + 1, len - 1); if (rc) diff --git a/net/dccp/output.c b/net/dccp/output.c index 784d3021054..136d41cbcd0 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -143,7 +143,7 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) } /** - * dccp_determine_ccmps - Find out about CCID-specfic packet-size limits + * dccp_determine_ccmps - Find out about CCID-specific packet-size limits * We only consider the HC-sender CCID for setting the CCMPS (RFC 4340, 14.), * since the RX CCID is restricted to feedback packets (Acks), which are small * in comparison with the data traffic. A value of 0 means "no current CCMPS". diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 87bb5f4de0e..c53ded2a98d 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -41,12 +41,12 @@ config NET_DSA_MV88E6XXX_NEED_PPU default n config NET_DSA_MV88E6131 - bool "Marvell 88E6095/6095F/6131 ethernet switch chip support" + bool "Marvell 88E6085/6095/6095F/6131 ethernet switch chip support" select NET_DSA_MV88E6XXX select NET_DSA_MV88E6XXX_NEED_PPU select NET_DSA_TAG_DSA ---help--- - This enables support for the Marvell 88E6095/6095F/6131 + This enables support for the Marvell 88E6085/6095/6095F/6131 ethernet switch chips. config NET_DSA_MV88E6123_61_65 diff --git a/net/dsa/mv88e6131.c b/net/dsa/mv88e6131.c index bb2b41bc854..45f7411e90b 100644 --- a/net/dsa/mv88e6131.c +++ b/net/dsa/mv88e6131.c @@ -14,6 +14,13 @@ #include "dsa_priv.h" #include "mv88e6xxx.h" +/* + * Switch product IDs + */ +#define ID_6085 0x04a0 +#define ID_6095 0x0950 +#define ID_6131 0x1060 + static char *mv88e6131_probe(struct mii_bus *bus, int sw_addr) { int ret; @@ -21,9 +28,11 @@ static char *mv88e6131_probe(struct mii_bus *bus, int sw_addr) ret = __mv88e6xxx_reg_read(bus, sw_addr, REG_PORT(0), 0x03); if (ret >= 0) { ret &= 0xfff0; - if (ret == 0x0950) + if (ret == ID_6085) + return "Marvell 88E6085"; + if (ret == ID_6095) return "Marvell 88E6095/88E6095F"; - if (ret == 0x1060) + if (ret == ID_6131) return "Marvell 88E6131"; } @@ -124,7 +133,7 @@ static int mv88e6131_setup_global(struct dsa_switch *ds) * Ignore removed tag data on doubly tagged packets, disable * flow control messages, force flow control priority to the * highest, and send all special multicast frames to the CPU - * port at the higest priority. + * port at the highest priority. */ REG_WRITE(REG_GLOBAL2, 0x05, 0x00ff); @@ -164,6 +173,7 @@ static int mv88e6131_setup_global(struct dsa_switch *ds) static int mv88e6131_setup_port(struct dsa_switch *ds, int p) { + struct mv88e6xxx_priv_state *ps = (void *)(ds + 1); int addr = REG_PORT(p); u16 val; @@ -171,10 +181,13 @@ static int mv88e6131_setup_port(struct dsa_switch *ds, int p) * MAC Forcing register: don't force link, speed, duplex * or flow control state to any particular values on physical * ports, but force the CPU port and all DSA ports to 1000 Mb/s - * full duplex. + * (100 Mb/s on 6085) full duplex. */ if (dsa_is_cpu_port(ds, p) || ds->dsa_port_mask & (1 << p)) - REG_WRITE(addr, 0x01, 0x003e); + if (ps->id == ID_6085) + REG_WRITE(addr, 0x01, 0x003d); /* 100 Mb/s */ + else + REG_WRITE(addr, 0x01, 0x003e); /* 1000 Mb/s */ else REG_WRITE(addr, 0x01, 0x0003); @@ -194,8 +207,15 @@ static int mv88e6131_setup_port(struct dsa_switch *ds, int p) * mode, but do not enable forwarding of unknown unicasts. */ val = 0x0433; - if (p == dsa_upstream_port(ds)) + if (p == dsa_upstream_port(ds)) { val |= 0x0104; + /* + * On 6085, unknown multicast forward is controlled + * here rather than in Port Control 2 register. + */ + if (ps->id == ID_6085) + val |= 0x0008; + } if (ds->dsa_port_mask & (1 << p)) val |= 0x0100; REG_WRITE(addr, 0x04, val); @@ -238,10 +258,19 @@ static int mv88e6131_setup_port(struct dsa_switch *ds, int p) * If this is the upstream port for this switch, enable * forwarding of unknown multicast addresses. */ - val = 0x0080 | dsa_upstream_port(ds); - if (p == dsa_upstream_port(ds)) - val |= 0x0040; - REG_WRITE(addr, 0x08, val); + if (ps->id == ID_6085) + /* + * on 6085, bits 3:0 are reserved, bit 6 control ARP + * mirroring, and multicast forward is handled in + * Port Control register. + */ + REG_WRITE(addr, 0x08, 0x0080); + else { + val = 0x0080 | dsa_upstream_port(ds); + if (p == dsa_upstream_port(ds)) + val |= 0x0040; + REG_WRITE(addr, 0x08, val); + } /* * Rate Control: disable ingress rate limiting. @@ -286,6 +315,8 @@ static int mv88e6131_setup(struct dsa_switch *ds) mv88e6xxx_ppu_state_init(ds); mutex_init(&ps->stats_mutex); + ps->id = REG_READ(REG_PORT(0), 0x03) & 0xfff0; + ret = mv88e6131_switch_reset(ds); if (ret < 0) return ret; diff --git a/net/dsa/mv88e6xxx.h b/net/dsa/mv88e6xxx.h index eb0e0aaa9f1..61156ca26a0 100644 --- a/net/dsa/mv88e6xxx.h +++ b/net/dsa/mv88e6xxx.h @@ -39,6 +39,8 @@ struct mv88e6xxx_priv_state { * Hold this mutex over snapshot + dump sequences. */ struct mutex stats_mutex; + + int id; /* switch product id */ }; struct mv88e6xxx_hw_stat { diff --git a/net/econet/af_econet.c b/net/econet/af_econet.c index 0c282633791..116d3fd3d66 100644 --- a/net/econet/af_econet.c +++ b/net/econet/af_econet.c @@ -435,10 +435,10 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, udpdest.sin_addr.s_addr = htonl(network | addr.station); } + memset(&ah, 0, sizeof(ah)); ah.port = port; ah.cb = cb & 0x7f; ah.code = 2; /* magic */ - ah.pad = 0; /* tack our header on the front of the iovec */ size = sizeof(struct aunhdr); diff --git a/net/ieee802154/Makefile b/net/ieee802154/Makefile index ce2d3358285..5761185f884 100644 --- a/net/ieee802154/Makefile +++ b/net/ieee802154/Makefile @@ -1,5 +1,3 @@ obj-$(CONFIG_IEEE802154) += ieee802154.o af_802154.o ieee802154-y := netlink.o nl-mac.o nl-phy.o nl_policy.o wpan-class.o af_802154-y := af_ieee802154.o raw.o dgram.o - -ccflags-y += -Wall -DDEBUG diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 090d273d786..1b74d3b6437 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -215,6 +215,9 @@ int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir) case ARPHRD_INFINIBAND: ip_ib_mc_map(addr, dev->broadcast, haddr); return 0; + case ARPHRD_IPGRE: + ip_ipgre_mc_map(addr, dev->broadcast, haddr); + return 0; default: if (dir) { memcpy(haddr, dev->broadcast, dev->addr_len); diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 094e150c626..a0af7ea8787 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -112,7 +112,7 @@ int cipso_v4_rbm_strictvalid = 1; /* The maximum number of category ranges permitted in the ranged category tag * (tag #5). You may note that the IETF draft states that the maximum number * of category ranges is 7, but if the low end of the last category range is - * zero then it is possibile to fit 8 category ranges because the zero should + * zero then it is possible to fit 8 category ranges because the zero should * be omitted. */ #define CIPSO_V4_TAG_RNG_CAT_MAX 8 @@ -438,7 +438,7 @@ cache_add_failure: * * Description: * Search the DOI definition list for a DOI definition with a DOI value that - * matches @doi. The caller is responsibile for calling rcu_read_[un]lock(). + * matches @doi. The caller is responsible for calling rcu_read_[un]lock(). * Returns a pointer to the DOI definition on success and NULL on failure. */ static struct cipso_v4_doi *cipso_v4_doi_search(u32 doi) @@ -1293,7 +1293,7 @@ static int cipso_v4_gentag_rbm(const struct cipso_v4_doi *doi_def, return ret_val; /* This will send packets using the "optimized" format when - * possibile as specified in section 3.4.2.6 of the + * possible as specified in section 3.4.2.6 of the * CIPSO draft. */ if (cipso_v4_rbm_optfmt && ret_val > 0 && ret_val <= 10) tag_len = 14; @@ -1752,7 +1752,7 @@ validate_return: } /** - * cipso_v4_error - Send the correct reponse for a bad packet + * cipso_v4_error - Send the correct response for a bad packet * @skb: the packet * @error: the error code * @gateway: CIPSO gateway flag diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 6d85800daeb..cd9ca0811cf 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -64,6 +64,8 @@ #include <net/rtnetlink.h> #include <net/net_namespace.h> +#include "fib_lookup.h" + static struct ipv4_devconf ipv4_devconf = { .data = { [IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1, @@ -151,6 +153,20 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) break; } } + if (!result) { + struct flowi4 fl4 = { .daddr = addr }; + struct fib_result res = { 0 }; + struct fib_table *local; + + /* Fallback to FIB local table so that communication + * over loopback subnets work. + */ + local = fib_get_table(net, RT_TABLE_LOCAL); + if (local && + !fib_table_lookup(local, &fl4, &res, FIB_LOOKUP_NOREF) && + res.type == RTN_LOCAL) + result = FIB_RES_DEV(res); + } if (result && devref) dev_hold(result); rcu_read_unlock(); @@ -345,6 +361,17 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, } } + /* On promotion all secondaries from subnet are changing + * the primary IP, we must remove all their routes silently + * and later to add them back with new prefsrc. Do this + * while all addresses are on the device list. + */ + for (ifa = promote; ifa; ifa = ifa->ifa_next) { + if (ifa1->ifa_mask == ifa->ifa_mask && + inet_ifa_match(ifa1->ifa_address, ifa)) + fib_del_ifaddr(ifa, ifa1); + } + /* 2. Unlink it */ *ifap = ifa1->ifa_next; @@ -364,6 +391,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa1); if (promote) { + struct in_ifaddr *next_sec = promote->ifa_next; if (prev_prom) { prev_prom->ifa_next = promote->ifa_next; @@ -375,7 +403,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, rtmsg_ifa(RTM_NEWADDR, promote, nlh, pid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, promote); - for (ifa = promote->ifa_next; ifa; ifa = ifa->ifa_next) { + for (ifa = next_sec; ifa; ifa = ifa->ifa_next) { if (ifa1->ifa_mask != ifa->ifa_mask || !inet_ifa_match(ifa1->ifa_address, ifa)) continue; @@ -1652,7 +1680,7 @@ static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf) return; cnf->sysctl = NULL; - unregister_sysctl_table(t->sysctl_header); + unregister_net_sysctl_table(t->sysctl_header); kfree(t->dev_name); kfree(t); } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index a373a259253..451088330bb 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -228,7 +228,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, if (res.type != RTN_LOCAL || !accept_local) goto e_inval; } - *spec_dst = FIB_RES_PREFSRC(res); + *spec_dst = FIB_RES_PREFSRC(net, res); fib_combine_itag(itag, &res); dev_match = false; @@ -258,7 +258,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, ret = 0; if (fib_lookup(net, &fl4, &res) == 0) { if (res.type == RTN_UNICAST) { - *spec_dst = FIB_RES_PREFSRC(res); + *spec_dst = FIB_RES_PREFSRC(net, res); ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST; } } @@ -722,12 +722,17 @@ void fib_add_ifaddr(struct in_ifaddr *ifa) } } -static void fib_del_ifaddr(struct in_ifaddr *ifa) +/* Delete primary or secondary address. + * Optionally, on secondary address promotion consider the addresses + * from subnet iprim as deleted, even if they are in device list. + * In this case the secondary ifa can be in device list. + */ +void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) { struct in_device *in_dev = ifa->ifa_dev; struct net_device *dev = in_dev->dev; struct in_ifaddr *ifa1; - struct in_ifaddr *prim = ifa; + struct in_ifaddr *prim = ifa, *prim1 = NULL; __be32 brd = ifa->ifa_address | ~ifa->ifa_mask; __be32 any = ifa->ifa_address & ifa->ifa_mask; #define LOCAL_OK 1 @@ -735,17 +740,26 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa) #define BRD0_OK 4 #define BRD1_OK 8 unsigned ok = 0; + int subnet = 0; /* Primary network */ + int gone = 1; /* Address is missing */ + int same_prefsrc = 0; /* Another primary with same IP */ - if (!(ifa->ifa_flags & IFA_F_SECONDARY)) - fib_magic(RTM_DELROUTE, - dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, - any, ifa->ifa_prefixlen, prim); - else { + if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask); if (prim == NULL) { printk(KERN_WARNING "fib_del_ifaddr: bug: prim == NULL\n"); return; } + if (iprim && iprim != prim) { + printk(KERN_WARNING "fib_del_ifaddr: bug: iprim != prim\n"); + return; + } + } else if (!ipv4_is_zeronet(any) && + (any != ifa->ifa_local || ifa->ifa_prefixlen < 32)) { + fib_magic(RTM_DELROUTE, + dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, + any, ifa->ifa_prefixlen, prim); + subnet = 1; } /* Deletion is more complicated than add. @@ -755,6 +769,49 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa) */ for (ifa1 = in_dev->ifa_list; ifa1; ifa1 = ifa1->ifa_next) { + if (ifa1 == ifa) { + /* promotion, keep the IP */ + gone = 0; + continue; + } + /* Ignore IFAs from our subnet */ + if (iprim && ifa1->ifa_mask == iprim->ifa_mask && + inet_ifa_match(ifa1->ifa_address, iprim)) + continue; + + /* Ignore ifa1 if it uses different primary IP (prefsrc) */ + if (ifa1->ifa_flags & IFA_F_SECONDARY) { + /* Another address from our subnet? */ + if (ifa1->ifa_mask == prim->ifa_mask && + inet_ifa_match(ifa1->ifa_address, prim)) + prim1 = prim; + else { + /* We reached the secondaries, so + * same_prefsrc should be determined. + */ + if (!same_prefsrc) + continue; + /* Search new prim1 if ifa1 is not + * using the current prim1 + */ + if (!prim1 || + ifa1->ifa_mask != prim1->ifa_mask || + !inet_ifa_match(ifa1->ifa_address, prim1)) + prim1 = inet_ifa_byprefix(in_dev, + ifa1->ifa_address, + ifa1->ifa_mask); + if (!prim1) + continue; + if (prim1->ifa_local != prim->ifa_local) + continue; + } + } else { + if (prim->ifa_local != ifa1->ifa_local) + continue; + prim1 = ifa1; + if (prim != prim1) + same_prefsrc = 1; + } if (ifa->ifa_local == ifa1->ifa_local) ok |= LOCAL_OK; if (ifa->ifa_broadcast == ifa1->ifa_broadcast) @@ -763,19 +820,37 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa) ok |= BRD1_OK; if (any == ifa1->ifa_broadcast) ok |= BRD0_OK; + /* primary has network specific broadcasts */ + if (prim1 == ifa1 && ifa1->ifa_prefixlen < 31) { + __be32 brd1 = ifa1->ifa_address | ~ifa1->ifa_mask; + __be32 any1 = ifa1->ifa_address & ifa1->ifa_mask; + + if (!ipv4_is_zeronet(any1)) { + if (ifa->ifa_broadcast == brd1 || + ifa->ifa_broadcast == any1) + ok |= BRD_OK; + if (brd == brd1 || brd == any1) + ok |= BRD1_OK; + if (any == brd1 || any == any1) + ok |= BRD0_OK; + } + } } if (!(ok & BRD_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim); - if (!(ok & BRD1_OK)) - fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32, prim); - if (!(ok & BRD0_OK)) - fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim); + if (subnet && ifa->ifa_prefixlen < 31) { + if (!(ok & BRD1_OK)) + fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32, prim); + if (!(ok & BRD0_OK)) + fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim); + } if (!(ok & LOCAL_OK)) { fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim); /* Check, that this local address finally disappeared. */ - if (inet_addr_type(dev_net(dev), ifa->ifa_local) != RTN_LOCAL) { + if (gone && + inet_addr_type(dev_net(dev), ifa->ifa_local) != RTN_LOCAL) { /* And the last, but not the least thing. * We must flush stray FIB entries. * @@ -885,6 +960,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, { struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; struct net_device *dev = ifa->ifa_dev->dev; + struct net *net = dev_net(dev); switch (event) { case NETDEV_UP: @@ -892,12 +968,12 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, #ifdef CONFIG_IP_ROUTE_MULTIPATH fib_sync_up(dev); #endif - fib_update_nh_saddrs(dev); + atomic_inc(&net->ipv4.dev_addr_genid); rt_cache_flush(dev_net(dev), -1); break; case NETDEV_DOWN: - fib_del_ifaddr(ifa); - fib_update_nh_saddrs(dev); + fib_del_ifaddr(ifa, NULL); + atomic_inc(&net->ipv4.dev_addr_genid); if (ifa->ifa_dev->ifa_list == NULL) { /* Last address was deleted from this interface. * Disable IP. @@ -915,6 +991,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo { struct net_device *dev = ptr; struct in_device *in_dev = __in_dev_get_rtnl(dev); + struct net *net = dev_net(dev); if (event == NETDEV_UNREGISTER) { fib_disable_ip(dev, 2, -1); @@ -932,6 +1009,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo #ifdef CONFIG_IP_ROUTE_MULTIPATH fib_sync_up(dev); #endif + atomic_inc(&net->ipv4.dev_addr_genid); rt_cache_flush(dev_net(dev), -1); break; case NETDEV_DOWN: @@ -990,6 +1068,7 @@ static void ip_fib_net_exit(struct net *net) fib4_rules_exit(net); #endif + rtnl_lock(); for (i = 0; i < FIB_TABLE_HASHSZ; i++) { struct fib_table *tb; struct hlist_head *head; @@ -1002,6 +1081,7 @@ static void ip_fib_net_exit(struct net *net) fib_free_table(tb); } } + rtnl_unlock(); kfree(net->ipv4.fib_table_hash); } diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index 4ec323875a0..af0f14aba16 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -10,7 +10,6 @@ struct fib_alias { struct fib_info *fa_info; u8 fa_tos; u8 fa_type; - u8 fa_scope; u8 fa_state; struct rcu_head rcu; }; @@ -29,7 +28,7 @@ extern void fib_release_info(struct fib_info *); extern struct fib_info *fib_create_info(struct fib_config *cfg); extern int fib_nh_match(struct fib_config *cfg, struct fib_info *fi); extern int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, - u32 tb_id, u8 type, u8 scope, __be32 dst, + u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos, struct fib_info *fi, unsigned int); extern void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 622ac4c9502..641a5a2a9f9 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -222,7 +222,7 @@ static inline unsigned int fib_info_hashfn(const struct fib_info *fi) unsigned int mask = (fib_info_hash_size - 1); unsigned int val = fi->fib_nhs; - val ^= fi->fib_protocol; + val ^= (fi->fib_protocol << 8) | fi->fib_scope; val ^= (__force u32)fi->fib_prefsrc; val ^= fi->fib_priority; for_nexthops(fi) { @@ -248,10 +248,11 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi) if (fi->fib_nhs != nfi->fib_nhs) continue; if (nfi->fib_protocol == fi->fib_protocol && + nfi->fib_scope == fi->fib_scope && nfi->fib_prefsrc == fi->fib_prefsrc && nfi->fib_priority == fi->fib_priority && memcmp(nfi->fib_metrics, fi->fib_metrics, - sizeof(fi->fib_metrics)) == 0 && + sizeof(u32) * RTAX_MAX) == 0 && ((nfi->fib_flags ^ fi->fib_flags) & ~RTNH_F_DEAD) == 0 && (nfi->fib_nhs == 0 || nh_comp(fi, nfi) == 0)) return fi; @@ -328,7 +329,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, goto errout; err = fib_dump_info(skb, info->pid, seq, event, tb_id, - fa->fa_type, fa->fa_scope, key, dst_len, + fa->fa_type, key, dst_len, fa->fa_tos, fa->fa_info, nlm_flags); if (err < 0) { /* -EMSGSIZE implies BUG in fib_nlmsg_size() */ @@ -695,6 +696,16 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash, fib_info_hash_free(old_laddrhash, bytes); } +__be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh) +{ + nh->nh_saddr = inet_select_addr(nh->nh_dev, + nh->nh_gw, + nh->nh_parent->fib_scope); + nh->nh_saddr_genid = atomic_read(&net->ipv4.dev_addr_genid); + + return nh->nh_saddr; +} + struct fib_info *fib_create_info(struct fib_config *cfg) { int err; @@ -753,6 +764,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) fi->fib_net = hold_net(net); fi->fib_protocol = cfg->fc_protocol; + fi->fib_scope = cfg->fc_scope; fi->fib_flags = cfg->fc_flags; fi->fib_priority = cfg->fc_priority; fi->fib_prefsrc = cfg->fc_prefsrc; @@ -854,10 +866,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) } change_nexthops(fi) { - nexthop_nh->nh_cfg_scope = cfg->fc_scope; - nexthop_nh->nh_saddr = inet_select_addr(nexthop_nh->nh_dev, - nexthop_nh->nh_gw, - nexthop_nh->nh_cfg_scope); + fib_info_update_nh_saddr(net, nexthop_nh); } endfor_nexthops(fi) link_it: @@ -906,7 +915,7 @@ failure: } int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, - u32 tb_id, u8 type, u8 scope, __be32 dst, int dst_len, u8 tos, + u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos, struct fib_info *fi, unsigned int flags) { struct nlmsghdr *nlh; @@ -928,7 +937,7 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, NLA_PUT_U32(skb, RTA_TABLE, tb_id); rtm->rtm_type = type; rtm->rtm_flags = fi->fib_flags; - rtm->rtm_scope = scope; + rtm->rtm_scope = fi->fib_scope; rtm->rtm_protocol = fi->fib_protocol; if (rtm->rtm_dst_len) @@ -1084,7 +1093,7 @@ void fib_select_default(struct fib_result *res) list_for_each_entry_rcu(fa, fa_head, fa_list) { struct fib_info *next_fi = fa->fa_info; - if (fa->fa_scope != res->scope || + if (next_fi->fib_scope != res->scope || fa->fa_type != RTN_UNICAST) continue; @@ -1128,24 +1137,6 @@ out: return; } -void fib_update_nh_saddrs(struct net_device *dev) -{ - struct hlist_head *head; - struct hlist_node *node; - struct fib_nh *nh; - unsigned int hash; - - hash = fib_devindex_hashfn(dev->ifindex); - head = &fib_info_devhash[hash]; - hlist_for_each_entry(nh, node, head, nh_hash) { - if (nh->nh_dev != dev) - continue; - nh->nh_saddr = inet_select_addr(nh->nh_dev, - nh->nh_gw, - nh->nh_cfg_scope); - } -} - #ifdef CONFIG_IP_ROUTE_MULTIPATH /* diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 3d28a35c2e1..5fe9b8b41df 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -12,7 +12,7 @@ * * Hans Liss <hans.liss@its.uu.se> Uppsala Universitet * - * This work is based on the LPC-trie which is originally descibed in: + * This work is based on the LPC-trie which is originally described in: * * An experimental study of compression methods for dynamic tries * Stefan Nilsson and Matti Tikkanen. Algorithmica, 33(1):19-33, 2002. @@ -1245,7 +1245,6 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) if (fa->fa_info->fib_priority != fi->fib_priority) break; if (fa->fa_type == cfg->fc_type && - fa->fa_scope == cfg->fc_scope && fa->fa_info == fi) { fa_match = fa; break; @@ -1271,7 +1270,6 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) new_fa->fa_tos = fa->fa_tos; new_fa->fa_info = fi; new_fa->fa_type = cfg->fc_type; - new_fa->fa_scope = cfg->fc_scope; state = fa->fa_state; new_fa->fa_state = state & ~FA_S_ACCESSED; @@ -1308,7 +1306,6 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) new_fa->fa_info = fi; new_fa->fa_tos = tos; new_fa->fa_type = cfg->fc_type; - new_fa->fa_scope = cfg->fc_scope; new_fa->fa_state = 0; /* * Insert new entry to the list. @@ -1362,15 +1359,15 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l, if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos) continue; - if (fa->fa_scope < flp->flowi4_scope) + if (fa->fa_info->fib_scope < flp->flowi4_scope) continue; fib_alias_accessed(fa); err = fib_props[fa->fa_type].error; if (err) { #ifdef CONFIG_IP_FIB_TRIE_STATS - t->stats.semantic_match_miss++; + t->stats.semantic_match_passed++; #endif - return 1; + return err; } if (fi->fib_flags & RTNH_F_DEAD) continue; @@ -1388,7 +1385,7 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l, res->prefixlen = plen; res->nh_sel = nhsel; res->type = fa->fa_type; - res->scope = fa->fa_scope; + res->scope = fa->fa_info->fib_scope; res->fi = fi; res->table = tb; res->fa_head = &li->falh; @@ -1664,7 +1661,9 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) if ((!cfg->fc_type || fa->fa_type == cfg->fc_type) && (cfg->fc_scope == RT_SCOPE_NOWHERE || - fa->fa_scope == cfg->fc_scope) && + fa->fa_info->fib_scope == cfg->fc_scope) && + (!cfg->fc_prefsrc || + fi->fib_prefsrc == cfg->fc_prefsrc) && (!cfg->fc_protocol || fi->fib_protocol == cfg->fc_protocol) && fib_nh_match(cfg, fi) == 0) { @@ -1861,7 +1860,6 @@ static int fn_trie_dump_fa(t_key key, int plen, struct list_head *fah, RTM_NEWROUTE, tb->tb_id, fa->fa_type, - fa->fa_scope, xkey, plen, fa->fa_tos, @@ -1980,9 +1978,6 @@ struct fib_table *fib_trie_table(u32 id) t = (struct trie *) tb->tb_data; memset(t, 0, sizeof(*t)); - if (id == RT_TABLE_LOCAL) - pr_info("IPv4 FIB: Using LC-trie version %s\n", VERSION); - return tb; } @@ -2382,7 +2377,7 @@ static int fib_trie_seq_show(struct seq_file *seq, void *v) seq_indent(seq, iter->depth+1); seq_printf(seq, " /%d %s %s", li->plen, rtn_scope(buf1, sizeof(buf1), - fa->fa_scope), + fa->fa_info->fib_scope), rtn_type(buf2, sizeof(buf2), fa->fa_type)); if (fa->fa_tos) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index a91dc161108..e5f8a71d3a2 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -704,7 +704,7 @@ static void icmp_unreach(struct sk_buff *skb) */ /* - * Check the other end isnt violating RFC 1122. Some routers send + * Check the other end isn't violating RFC 1122. Some routers send * bogus responses to broadcast frames. If you see this message * first check your netmask matches at both ends, if it does then * get the other vendor to fix their kit. diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 6c0b7f4a3d7..38f23e721b8 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -73,7 +73,7 @@ int inet_csk_bind_conflict(const struct sock *sk, !sk2->sk_bound_dev_if || sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) { if (!reuse || !sk2->sk_reuse || - ((1 << sk2->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))) { + sk2->sk_state == TCP_LISTEN) { const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2); if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) || sk2_rcv_saddr == sk_rcv_saddr(sk)) @@ -122,8 +122,7 @@ again: (tb->num_owners < smallest_size || smallest_size == -1)) { smallest_size = tb->num_owners; smallest_rover = rover; - if (atomic_read(&hashinfo->bsockets) > (high - low) + 1 && - !inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) { + if (atomic_read(&hashinfo->bsockets) > (high - low) + 1) { spin_unlock(&head->lock); snum = smallest_rover; goto have_snum; diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index dd1b20eca1a..9df4e635fb5 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -354,7 +354,8 @@ static void inetpeer_free_rcu(struct rcu_head *head) } /* May be called with local BH enabled. */ -static void unlink_from_pool(struct inet_peer *p, struct inet_peer_base *base) +static void unlink_from_pool(struct inet_peer *p, struct inet_peer_base *base, + struct inet_peer __rcu **stack[PEER_MAXDEPTH]) { int do_free; @@ -368,7 +369,6 @@ static void unlink_from_pool(struct inet_peer *p, struct inet_peer_base *base) * We use refcnt=-1 to alert lockless readers this entry is deleted. */ if (atomic_cmpxchg(&p->refcnt, 1, -1) == 1) { - struct inet_peer __rcu **stack[PEER_MAXDEPTH]; struct inet_peer __rcu ***stackptr, ***delp; if (lookup(&p->daddr, stack, base) != p) BUG(); @@ -422,7 +422,7 @@ static struct inet_peer_base *peer_to_base(struct inet_peer *p) } /* May be called with local BH enabled. */ -static int cleanup_once(unsigned long ttl) +static int cleanup_once(unsigned long ttl, struct inet_peer __rcu **stack[PEER_MAXDEPTH]) { struct inet_peer *p = NULL; @@ -454,7 +454,7 @@ static int cleanup_once(unsigned long ttl) * happen because of entry limits in route cache. */ return -1; - unlink_from_pool(p, peer_to_base(p)); + unlink_from_pool(p, peer_to_base(p), stack); return 0; } @@ -524,7 +524,7 @@ struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create) if (base->total >= inet_peer_threshold) /* Remove one less-recently-used entry. */ - cleanup_once(0); + cleanup_once(0, stack); return p; } @@ -540,6 +540,7 @@ static void peer_check_expire(unsigned long dummy) { unsigned long now = jiffies; int ttl, total; + struct inet_peer __rcu **stack[PEER_MAXDEPTH]; total = compute_total(); if (total >= inet_peer_threshold) @@ -548,7 +549,7 @@ static void peer_check_expire(unsigned long dummy) ttl = inet_peer_maxttl - (inet_peer_maxttl - inet_peer_minttl) / HZ * total / inet_peer_threshold * HZ; - while (!cleanup_once(ttl)) { + while (!cleanup_once(ttl, stack)) { if (jiffies != now) break; } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index a1151b8adf3..b1d282f11be 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -223,31 +223,30 @@ static void ip_expire(unsigned long arg) if ((qp->q.last_in & INET_FRAG_FIRST_IN) && qp->q.fragments != NULL) { struct sk_buff *head = qp->q.fragments; + const struct iphdr *iph; + int err; rcu_read_lock(); head->dev = dev_get_by_index_rcu(net, qp->iif); if (!head->dev) goto out_rcu_unlock; + /* skb dst is stale, drop it, and perform route lookup again */ + skb_dst_drop(head); + iph = ip_hdr(head); + err = ip_route_input_noref(head, iph->daddr, iph->saddr, + iph->tos, head->dev); + if (err) + goto out_rcu_unlock; + /* - * Only search router table for the head fragment, - * when defraging timeout at PRE_ROUTING HOOK. + * Only an end host needs to send an ICMP + * "Fragment Reassembly Timeout" message, per RFC792. */ - if (qp->user == IP_DEFRAG_CONNTRACK_IN && !skb_dst(head)) { - const struct iphdr *iph = ip_hdr(head); - int err = ip_route_input(head, iph->daddr, iph->saddr, - iph->tos, head->dev); - if (unlikely(err)) - goto out_rcu_unlock; - - /* - * Only an end host needs to send an ICMP - * "Fragment Reassembly Timeout" message, per RFC792. - */ - if (skb_rtable(head)->rt_type != RTN_LOCAL) - goto out_rcu_unlock; + if (qp->user == IP_DEFRAG_CONNTRACK_IN && + skb_rtable(head)->rt_type != RTN_LOCAL) + goto out_rcu_unlock; - } /* Send an ICMP "Fragment Reassembly Timeout" message. */ icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0); diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 1906fa35860..2391b24e825 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -140,11 +140,11 @@ int ip_options_echo(struct ip_options * dopt, struct sk_buff * skb) } else { dopt->ts_needtime = 0; - if (soffset + 8 <= optlen) { + if (soffset + 7 <= optlen) { __be32 addr; - memcpy(&addr, sptr+soffset-1, 4); - if (inet_addr_type(dev_net(skb_dst(skb)->dev), addr) != RTN_LOCAL) { + memcpy(&addr, dptr+soffset-1, 4); + if (inet_addr_type(dev_net(skb_dst(skb)->dev), addr) != RTN_UNICAST) { dopt->ts_needtime = 1; soffset += 8; } @@ -329,7 +329,7 @@ int ip_options_compile(struct net *net, pp_ptr = optptr + 2; goto error; } - if (skb) { + if (rt) { memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4); opt->is_changed = 1; } @@ -371,7 +371,7 @@ int ip_options_compile(struct net *net, goto error; } opt->ts = optptr - iph; - if (skb) { + if (rt) { memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4); timeptr = (__be32*)&optptr[optptr[2]+3]; } @@ -603,7 +603,7 @@ int ip_options_rcv_srr(struct sk_buff *skb) unsigned long orefdst; int err; - if (!opt->srr) + if (!opt->srr || !rt) return 0; if (skb->pkt_type != PACKET_HOST) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 67f241b9764..459c011b1d4 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -603,7 +603,7 @@ slow_path: /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > mtu) len = mtu; - /* IF: we are not sending upto and including the packet end + /* IF: we are not sending up to and including the packet end then align the next start on an eight byte boundary */ if (len < left) { len &= ~7; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 2b097752426..cbff2ecccf3 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1444,7 +1444,7 @@ static int __init ip_auto_config(void) root_server_addr = addr; /* - * Use defaults whereever applicable. + * Use defaults wherever applicable. */ if (ic_defaults() < 0) return -1; diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index f3c0b549b8e..4614babdc45 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -221,9 +221,10 @@ static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook, return csum; } -static int nf_ip_route(struct dst_entry **dst, struct flowi *fl) +static int nf_ip_route(struct net *net, struct dst_entry **dst, + struct flowi *fl, bool strict __always_unused) { - struct rtable *rt = ip_route_output_key(&init_net, &fl->u.ip4); + struct rtable *rt = ip_route_output_key(net, &fl->u.ip4); if (IS_ERR(rt)) return PTR_ERR(rt); *dst = &rt->dst; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 4b5d457c2d7..89bc7e66d59 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -76,7 +76,7 @@ static inline int arp_devaddr_compare(const struct arpt_devaddr_info *ap, } /* - * Unfortunatly, _b and _mask are not aligned to an int (or long int) + * Unfortunately, _b and _mask are not aligned to an int (or long int) * Some arches dont care, unrolling the loop is a win on them. * For other arches, we only have a 16bit alignement. */ @@ -1874,7 +1874,7 @@ static int __init arp_tables_init(void) if (ret < 0) goto err1; - /* Noone else will be downing sem now, so we won't sleep */ + /* No one else will be downing sem now, so we won't sleep */ ret = xt_register_targets(arpt_builtin_tg, ARRAY_SIZE(arpt_builtin_tg)); if (ret < 0) goto err2; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index b09ed0d080f..70491502800 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -387,7 +387,7 @@ ipt_do_table(struct sk_buff *skb, verdict = (unsigned)(-v) - 1; break; } - if (*stackptr == 0) { + if (*stackptr <= origptr) { e = get_entry(table_base, private->underflow[hook]); pr_debug("Underflow (this is normal) " @@ -427,10 +427,10 @@ ipt_do_table(struct sk_buff *skb, /* Verdict */ break; } while (!acpar.hotdrop); - xt_info_rdunlock_bh(); pr_debug("Exiting %s; resetting sp from %u to %u\n", __func__, *stackptr, origptr); *stackptr = origptr; + xt_info_rdunlock_bh(); #ifdef DEBUG_ALLOW_ALL return NF_ACCEPT; #else @@ -2233,7 +2233,7 @@ static int __init ip_tables_init(void) if (ret < 0) goto err1; - /* Noone else will be downing sem now, so we won't sleep */ + /* No one else will be downing sem now, so we won't sleep */ ret = xt_register_targets(ipt_builtin_tg, ARRAY_SIZE(ipt_builtin_tg)); if (ret < 0) goto err2; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 403ca57f601..d609ac3cb9a 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -664,8 +664,11 @@ static ssize_t clusterip_proc_write(struct file *file, const char __user *input, char buffer[PROC_WRITELEN+1]; unsigned long nodenum; - if (copy_from_user(buffer, input, PROC_WRITELEN)) + if (size > PROC_WRITELEN) + return -EIO; + if (copy_from_user(buffer, input, size)) return -EFAULT; + buffer[size] = 0; if (*buffer == '+') { nodenum = simple_strtoul(buffer+1, NULL, 10); diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 21bcf471b25..9c71b2755ce 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -521,7 +521,7 @@ int nf_nat_protocol_register(const struct nf_nat_protocol *proto) } EXPORT_SYMBOL(nf_nat_protocol_register); -/* Noone stores the protocol anywhere; simply delete it. */ +/* No one stores the protocol anywhere; simply delete it. */ void nf_nat_protocol_unregister(const struct nf_nat_protocol *proto) { spin_lock_bh(&nf_nat_lock); @@ -532,7 +532,7 @@ void nf_nat_protocol_unregister(const struct nf_nat_protocol *proto) } EXPORT_SYMBOL(nf_nat_protocol_unregister); -/* Noone using conntrack by the time this called. */ +/* No one using conntrack by the time this called. */ static void nf_nat_cleanup_conntrack(struct nf_conn *ct) { struct nf_conn_nat *nat = nf_ct_ext_find(ct, NF_CT_EXT_NAT); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index e837ffd3edc..bceaec42c37 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -569,6 +569,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, rt = ip_route_output_flow(sock_net(sk), &fl4, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); + rt = NULL; goto done; } } @@ -621,7 +622,7 @@ do_confirm: static void raw_close(struct sock *sk, long timeout) { /* - * Raw sockets may have direct kernel refereneces. Kill them. + * Raw sockets may have direct kernel references. Kill them. */ ip_ra_control(sk, 0, NULL); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 870b5182ddd..99e6e4bb1c7 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -821,7 +821,7 @@ static int has_noalias(const struct rtable *head, const struct rtable *rth) } /* - * Pertubation of rt_genid by a small quantity [1..256] + * Perturbation of rt_genid by a small quantity [1..256] * Using 8 bits of shuffling ensure we can call rt_cache_invalidate() * many times (2^24) without giving recent rt_genid. * Jenkins hash is strong enough that litle changes of rt_genid are OK. @@ -1191,7 +1191,7 @@ restart: #endif /* * Since lookup is lockfree, we must make sure - * previous writes to rt are comitted to memory + * previous writes to rt are committed to memory * before making rt visible to other CPUS. */ rcu_assign_pointer(rt_hash_table[hash].chain, rt); @@ -1593,8 +1593,6 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) rt->rt_peer_genid = rt_peer_genid(); } check_peer_pmtu(dst, peer); - - inet_putpeer(peer); } } @@ -1720,7 +1718,7 @@ void ip_rt_get_source(u8 *addr, struct rtable *rt) rcu_read_lock(); if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res) == 0) - src = FIB_RES_PREFSRC(res); + src = FIB_RES_PREFSRC(dev_net(rt->dst.dev), res); else src = inet_select_addr(rt->dst.dev, rt->rt_gateway, RT_SCOPE_UNIVERSE); @@ -1893,6 +1891,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif + rth->rt_route_iif = dev->ifindex; rth->rt_iif = dev->ifindex; rth->dst.dev = init_net.loopback_dev; dev_hold(rth->dst.dev); @@ -2028,6 +2027,7 @@ static int __mkroute_input(struct sk_buff *skb, rth->rt_key_src = saddr; rth->rt_src = saddr; rth->rt_gateway = daddr; + rth->rt_route_iif = in_dev->dev->ifindex; rth->rt_iif = in_dev->dev->ifindex; rth->dst.dev = (out_dev)->dev; dev_hold(rth->dst.dev); @@ -2204,6 +2204,7 @@ local_input: #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif + rth->rt_route_iif = dev->ifindex; rth->rt_iif = dev->ifindex; rth->dst.dev = net->loopback_dev; dev_hold(rth->dst.dev); @@ -2403,7 +2404,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res, rth->rt_mark = oldflp4->flowi4_mark; rth->rt_dst = fl4->daddr; rth->rt_src = fl4->saddr; - rth->rt_iif = 0; + rth->rt_route_iif = 0; + rth->rt_iif = oldflp4->flowi4_oif ? : dev_out->ifindex; /* get references to the devices that are to be hold by the routing cache entry */ rth->dst.dev = dev_out; @@ -2617,7 +2619,7 @@ static struct rtable *ip_route_output_slow(struct net *net, fib_select_default(&res); if (!fl4.saddr) - fl4.saddr = FIB_RES_PREFSRC(res); + fl4.saddr = FIB_RES_PREFSRC(net, res); dev_out = FIB_RES_DEV(res); fl4.flowi4_oif = dev_out->ifindex; @@ -2688,6 +2690,12 @@ static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) { } +static u32 *ipv4_rt_blackhole_cow_metrics(struct dst_entry *dst, + unsigned long old) +{ + return NULL; +} + static struct dst_ops ipv4_dst_blackhole_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), @@ -2696,6 +2704,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = { .default_mtu = ipv4_blackhole_default_mtu, .default_advmss = ipv4_default_advmss, .update_pmtu = ipv4_rt_blackhole_update_pmtu, + .cow_metrics = ipv4_rt_blackhole_cow_metrics, }; struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig) @@ -2718,6 +2727,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_key_dst = ort->rt_key_dst; rt->rt_key_src = ort->rt_key_src; rt->rt_tos = ort->rt_tos; + rt->rt_route_iif = ort->rt_route_iif; rt->rt_iif = ort->rt_iif; rt->rt_oif = ort->rt_oif; rt->rt_mark = ort->rt_mark; @@ -2727,7 +2737,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_type = ort->rt_type; rt->rt_dst = ort->rt_dst; rt->rt_src = ort->rt_src; - rt->rt_iif = ort->rt_iif; rt->rt_gateway = ort->rt_gateway; rt->rt_spec_dst = ort->rt_spec_dst; rt->peer = ort->peer; @@ -3221,6 +3230,8 @@ static __net_init int rt_genid_init(struct net *net) { get_random_bytes(&net->ipv4.rt_genid, sizeof(net->ipv4.rt_genid)); + get_random_bytes(&net->ipv4.dev_addr_genid, + sizeof(net->ipv4.dev_addr_genid)); return 0; } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 1a456652086..321e6e84dbc 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -311,7 +311,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_do_large_bitmap, }, -#ifdef CONFIG_IP_MULTICAST { .procname = "igmp_max_memberships", .data = &sysctl_igmp_max_memberships, @@ -319,8 +318,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - -#endif { .procname = "igmp_max_msf", .data = &sysctl_igmp_max_msf, diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 34340c9c95f..f376b05cca8 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -93,6 +93,7 @@ struct bictcp { u32 ack_cnt; /* number of acks */ u32 tcp_cwnd; /* estimated tcp cwnd */ #define ACK_RATIO_SHIFT 4 +#define ACK_RATIO_LIMIT (32u << ACK_RATIO_SHIFT) u16 delayed_ack; /* estimate the ratio of Packets/ACKs << 4 */ u8 sample_cnt; /* number of samples to decide curr_rtt */ u8 found; /* the exit point is found? */ @@ -398,8 +399,12 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us) u32 delay; if (icsk->icsk_ca_state == TCP_CA_Open) { - cnt -= ca->delayed_ack >> ACK_RATIO_SHIFT; - ca->delayed_ack += cnt; + u32 ratio = ca->delayed_ack; + + ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT; + ratio += cnt; + + ca->delayed_ack = min(ratio, ACK_RATIO_LIMIT); } /* Some calls are for duplicates without timetamps */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index da782e7ab16..bef9f04c22b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2659,7 +2659,7 @@ static void DBGUNDO(struct sock *sk, const char *msg) #define DBGUNDO(x...) do { } while (0) #endif -static void tcp_undo_cwr(struct sock *sk, const int undo) +static void tcp_undo_cwr(struct sock *sk, const bool undo_ssthresh) { struct tcp_sock *tp = tcp_sk(sk); @@ -2671,14 +2671,13 @@ static void tcp_undo_cwr(struct sock *sk, const int undo) else tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh << 1); - if (undo && tp->prior_ssthresh > tp->snd_ssthresh) { + if (undo_ssthresh && tp->prior_ssthresh > tp->snd_ssthresh) { tp->snd_ssthresh = tp->prior_ssthresh; TCP_ECN_withdraw_cwr(tp); } } else { tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh); } - tcp_moderate_cwnd(tp); tp->snd_cwnd_stamp = tcp_time_stamp; } @@ -2699,7 +2698,7 @@ static int tcp_try_undo_recovery(struct sock *sk) * or our original transmission succeeded. */ DBGUNDO(sk, inet_csk(sk)->icsk_ca_state == TCP_CA_Loss ? "loss" : "retrans"); - tcp_undo_cwr(sk, 1); + tcp_undo_cwr(sk, true); if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss) mib_idx = LINUX_MIB_TCPLOSSUNDO; else @@ -2726,7 +2725,7 @@ static void tcp_try_undo_dsack(struct sock *sk) if (tp->undo_marker && !tp->undo_retrans) { DBGUNDO(sk, "D-SACK"); - tcp_undo_cwr(sk, 1); + tcp_undo_cwr(sk, true); tp->undo_marker = 0; NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDSACKUNDO); } @@ -2779,7 +2778,7 @@ static int tcp_try_undo_partial(struct sock *sk, int acked) tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1); DBGUNDO(sk, "Hoe"); - tcp_undo_cwr(sk, 0); + tcp_undo_cwr(sk, false); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO); /* So... Do not make Hoe's retransmit yet. @@ -2808,7 +2807,7 @@ static int tcp_try_undo_loss(struct sock *sk) DBGUNDO(sk, "partial loss"); tp->lost_out = 0; - tcp_undo_cwr(sk, 1); + tcp_undo_cwr(sk, true); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSUNDO); inet_csk(sk)->icsk_retransmits = 0; tp->undo_marker = 0; @@ -2822,8 +2821,11 @@ static int tcp_try_undo_loss(struct sock *sk) static inline void tcp_complete_cwr(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh); - tp->snd_cwnd_stamp = tcp_time_stamp; + /* Do not moderate cwnd if it's already undone in cwr or recovery */ + if (tp->undo_marker && tp->snd_cwnd > tp->snd_ssthresh) { + tp->snd_cwnd = tp->snd_ssthresh; + tp->snd_cwnd_stamp = tcp_time_stamp; + } tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR); } @@ -3494,7 +3496,7 @@ static void tcp_undo_spur_to_response(struct sock *sk, int flag) if (flag & FLAG_ECE) tcp_ratehalving_spur_to_response(sk); else - tcp_undo_cwr(sk, 1); + tcp_undo_cwr(sk, true); } /* F-RTO spurious RTO detection algorithm (RFC4138) diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index 656d431c99a..72f7218b03f 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -12,7 +12,7 @@ * within cong_avoid. * o Error correcting in remote HZ, therefore remote HZ will be keeped * on checking and updating. - * o Handling calculation of One-Way-Delay (OWD) within rtt_sample, sicne + * o Handling calculation of One-Way-Delay (OWD) within rtt_sample, since * OWD have a similar meaning as RTT. Also correct the buggy formular. * o Handle reaction for Early Congestion Indication (ECI) within * pkts_acked, as mentioned within pseudo code. diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index dfa5beb0c1c..17388c7f49c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -73,7 +73,7 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) tcp_advance_send_head(sk, skb); tp->snd_nxt = TCP_SKB_CB(skb)->end_seq; - /* Don't override Nagle indefinately with F-RTO */ + /* Don't override Nagle indefinitely with F-RTO */ if (tp->frto_counter == 2) tp->frto_counter = 3; @@ -1003,7 +1003,8 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, int nlen; u8 flags; - BUG_ON(len > skb->len); + if (WARN_ON(len > skb->len)) + return -EINVAL; nsize = skb_headlen(skb) - len; if (nsize < 0) diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index dc7f43179c9..05c3b6f0e8e 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -20,7 +20,7 @@ #define TCP_YEAH_DELTA 3 //log minimum fraction of cwnd to be removed on loss #define TCP_YEAH_EPSILON 1 //log maximum fraction to be removed on early decongestion #define TCP_YEAH_PHY 8 //lin maximum delta from base -#define TCP_YEAH_RHO 16 //lin minumum number of consecutive rtt to consider competition on loss +#define TCP_YEAH_RHO 16 //lin minimum number of consecutive rtt to consider competition on loss #define TCP_YEAH_ZETA 50 //lin minimum number of state switchs to reset reno_count #define TCP_SCALABLE_AI_CNT 100U diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 588f47af5fa..f87a8eb76f3 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -189,7 +189,7 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num, * @sk: socket struct in question * @snum: port number to look up * @saddr_comp: AF-dependent comparison of bound local IP addresses - * @hash2_nulladdr: AF-dependant hash value in secondary hash chains, + * @hash2_nulladdr: AF-dependent hash value in secondary hash chains, * with NULL address */ int udp_lib_get_port(struct sock *sk, unsigned short snum, diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 571aa96a175..2d51840e53a 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -69,7 +69,7 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb) } EXPORT_SYMBOL(xfrm4_prepare_output); -static int xfrm4_output_finish(struct sk_buff *skb) +int xfrm4_output_finish(struct sk_buff *skb) { #ifdef CONFIG_NETFILTER if (!skb_dst(skb)->xfrm) { @@ -86,7 +86,11 @@ static int xfrm4_output_finish(struct sk_buff *skb) int xfrm4_output(struct sk_buff *skb) { + struct dst_entry *dst = skb_dst(skb); + struct xfrm_state *x = dst->xfrm; + return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, - NULL, skb_dst(skb)->dev, xfrm4_output_finish, + NULL, dst->dev, + x->outer_mode->afinfo->output_finish, !(IPCB(skb)->flags & IPSKB_REROUTED)); } diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 13e0e7f659f..d20a05e970d 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -74,6 +74,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, rt->rt_key_dst = fl4->daddr; rt->rt_key_src = fl4->saddr; rt->rt_tos = fl4->flowi4_tos; + rt->rt_route_iif = fl4->flowi4_iif; rt->rt_iif = fl4->flowi4_iif; rt->rt_oif = fl4->flowi4_oif; rt->rt_mark = fl4->flowi4_mark; diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index 1717c64628d..805d63ef434 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -78,6 +78,7 @@ static struct xfrm_state_afinfo xfrm4_state_afinfo = { .init_tempsel = __xfrm4_init_tempsel, .init_temprop = xfrm4_init_temprop, .output = xfrm4_output, + .output_finish = xfrm4_output_finish, .extract_input = xfrm4_extract_input, .extract_output = xfrm4_extract_output, .transport_finish = xfrm4_transport_finish, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 3daaf3c7703..a7bda075705 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1084,7 +1084,7 @@ static int ipv6_get_saddr_eval(struct net *net, case IPV6_SADDR_RULE_PRIVACY: { /* Rule 7: Prefer public address - * Note: prefer temprary address if use_tempaddr >= 2 + * Note: prefer temporary address if use_tempaddr >= 2 */ int preftmp = dst->prefs & (IPV6_PREFER_SRC_PUBLIC|IPV6_PREFER_SRC_TMP) ? !!(dst->prefs & IPV6_PREFER_SRC_TMP) : @@ -1968,7 +1968,7 @@ ok: * to the stored lifetime since we'll * be updating the timestamp below, * else we'll set it back to the - * minumum. + * minimum. */ if (prefered_lft != ifp->prefered_lft) { valid_lft = stored_lft; @@ -4537,7 +4537,7 @@ static void __addrconf_sysctl_unregister(struct ipv6_devconf *p) t = p->sysctl; p->sysctl = NULL; - unregister_sysctl_table(t->sysctl_header); + unregister_net_sysctl_table(t->sysctl_header); kfree(t->dev_name); kfree(t); } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 4b13d5d8890..afcc7099f96 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1113,7 +1113,7 @@ static int __init inet6_init(void) /* * ipngwg API draft makes clear that the correct semantics * for TCP and UDP is to consider one TCP and UDP instance - * in a host availiable by both INET and INET6 APIs and + * in a host available by both INET and INET6 APIs and * able to communicate via both network protocols. */ diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 5aa8ec88f19..59dccfbb5b1 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -371,7 +371,7 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb) iv = esp_tmp_iv(aead, tmp, seqhilen); req = esp_tmp_req(aead, iv); asg = esp_req_sg(aead, req); - sg = asg + 1; + sg = asg + sglists; skb->ip_summed = CHECKSUM_NONE; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 16605465046..f2c5b0fc0f2 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -44,7 +44,7 @@ int inet6_csk_bind_conflict(const struct sock *sk, !sk2->sk_bound_dev_if || sk->sk_bound_dev_if == sk2->sk_bound_dev_if) && (!sk->sk_reuse || !sk2->sk_reuse || - ((1 << sk2->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))) && + sk2->sk_state == TCP_LISTEN) && ipv6_rcv_saddr_equal(sk, sk2)) break; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 18208876aa8..46cf7bea676 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -779,7 +779,7 @@ slow_path: /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > mtu) len = mtu; - /* IF: we are not sending upto and including the packet end + /* IF: we are not sending up to and including the packet end then align the next start on an eight byte boundary */ if (len < left) { len &= ~7; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 7ff0343e05c..29e48593bf2 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -663,7 +663,7 @@ static int pim6_rcv(struct sk_buff *skb) skb_pull(skb, (u8 *)encap - skb->data); skb_reset_network_header(skb); skb->protocol = htons(ETH_P_IPV6); - skb->ip_summed = 0; + skb->ip_summed = CHECKSUM_NONE; skb->pkt_type = PACKET_HOST; skb_tunnel_rx(skb, reg_dev); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 0e49c9db3c9..92f952d093d 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -341,6 +341,8 @@ int ndisc_mc_map(struct in6_addr *addr, char *buf, struct net_device *dev, int d case ARPHRD_INFINIBAND: ipv6_ib_mc_map(addr, dev->broadcast, buf); return 0; + case ARPHRD_IPGRE: + return ipv6_ipgre_mc_map(addr, dev->broadcast, buf); default: if (dir) { memcpy(buf, dev->broadcast, dev->addr_len); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 39aaca2b4fd..28bc1f644b7 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -90,9 +90,18 @@ static int nf_ip6_reroute(struct sk_buff *skb, return 0; } -static int nf_ip6_route(struct dst_entry **dst, struct flowi *fl) +static int nf_ip6_route(struct net *net, struct dst_entry **dst, + struct flowi *fl, bool strict) { - *dst = ip6_route_output(&init_net, NULL, &fl->u.ip6); + static const struct ipv6_pinfo fake_pinfo; + static const struct inet_sock fake_sk = { + /* makes ip6_route_output set RT6_LOOKUP_F_IFACE: */ + .sk.sk_bound_dev_if = 1, + .pinet6 = (struct ipv6_pinfo *) &fake_pinfo, + }; + const void *sk = strict ? &fake_sk : NULL; + + *dst = ip6_route_output(net, sk, &fl->u.ip6); return (*dst)->error; } diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index c9598a9067d..5a1c6f27ffa 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -410,7 +410,7 @@ ip6t_do_table(struct sk_buff *skb, verdict = (unsigned)(-v) - 1; break; } - if (*stackptr == 0) + if (*stackptr <= origptr) e = get_entry(table_base, private->underflow[hook]); else @@ -441,8 +441,8 @@ ip6t_do_table(struct sk_buff *skb, break; } while (!acpar.hotdrop); - xt_info_rdunlock_bh(); *stackptr = origptr; + xt_info_rdunlock_bh(); #ifdef DEBUG_ALLOW_ALL return NF_ACCEPT; @@ -2248,7 +2248,7 @@ static int __init ip6_tables_init(void) if (ret < 0) goto err1; - /* Noone else will be downing sem now, so we won't sleep */ + /* No one else will be downing sem now, so we won't sleep */ ret = xt_register_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); if (ret < 0) goto err2; diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 28e74488a32..a5a4c5dd539 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -45,6 +45,8 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) int tcphoff, needs_ack; const struct ipv6hdr *oip6h = ipv6_hdr(oldskb); struct ipv6hdr *ip6h; +#define DEFAULT_TOS_VALUE 0x0U + const __u8 tclass = DEFAULT_TOS_VALUE; struct dst_entry *dst = NULL; u8 proto; struct flowi6 fl6; @@ -124,7 +126,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) skb_put(nskb, sizeof(struct ipv6hdr)); skb_reset_network_header(nskb); ip6h = ipv6_hdr(nskb); - ip6h->version = 6; + *(__be32 *)ip6h = htonl(0x60000000 | (tclass << 20)); ip6h->hop_limit = ip6_dst_hoplimit(dst); ip6h->nexthdr = IPPROTO_TCP; ipv6_addr_copy(&ip6h->saddr, &oip6h->daddr); diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index 97c5b21b967..cdd6d045e42 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -71,7 +71,7 @@ static unsigned int ipv6_defrag(unsigned int hooknum, if (reasm == NULL) return NF_STOLEN; - /* error occured or not fragmented */ + /* error occurred or not fragmented */ if (reasm == skb) return NF_ACCEPT; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 6814c8722fa..fd0eec6f88c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -153,6 +153,12 @@ static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) { } +static u32 *ip6_rt_blackhole_cow_metrics(struct dst_entry *dst, + unsigned long old) +{ + return NULL; +} + static struct dst_ops ip6_dst_blackhole_ops = { .family = AF_INET6, .protocol = cpu_to_be16(ETH_P_IPV6), @@ -161,6 +167,7 @@ static struct dst_ops ip6_dst_blackhole_ops = { .default_mtu = ip6_blackhole_default_mtu, .default_advmss = ip6_default_advmss, .update_pmtu = ip6_rt_blackhole_update_pmtu, + .cow_metrics = ip6_rt_blackhole_cow_metrics, }; static const u32 ip6_template_metrics[RTAX_MAX] = { @@ -854,7 +861,7 @@ static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags); } -struct dst_entry * ip6_route_output(struct net *net, struct sock *sk, +struct dst_entry * ip6_route_output(struct net *net, const struct sock *sk, struct flowi6 *fl6) { int flags = 0; @@ -2012,7 +2019,6 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->dst.output = ip6_output; rt->rt6i_dev = net->loopback_dev; rt->rt6i_idev = idev; - dst_metric_set(&rt->dst, RTAX_HOPLIMIT, -1); rt->dst.obsolete = -1; rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP; diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 7cb65ef79f9..6dcf5e7d661 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -17,6 +17,16 @@ static struct ctl_table empty[1]; +static ctl_table ipv6_static_skeleton[] = { + { + .procname = "neigh", + .maxlen = 0, + .mode = 0555, + .child = empty, + }, + { } +}; + static ctl_table ipv6_table_template[] = { { .procname = "route", @@ -37,12 +47,6 @@ static ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "neigh", - .maxlen = 0, - .mode = 0555, - .child = empty, - }, { } }; @@ -160,7 +164,7 @@ static struct ctl_table_header *ip6_base; int ipv6_static_sysctl_register(void) { - ip6_base = register_sysctl_paths(net_ipv6_ctl_path, empty); + ip6_base = register_sysctl_paths(net_ipv6_ctl_path, ipv6_static_skeleton); if (ip6_base == NULL) return -ENOMEM; return 0; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2b0c186862c..4f49e5dd41b 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -503,6 +503,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false); if (IS_ERR(dst)) { err = PTR_ERR(dst); + dst = NULL; goto done; } skb = tcp_make_synack(sk, dst, req, rvp); @@ -1621,6 +1622,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) opt_skb = skb_clone(skb, GFP_ATOMIC); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ + sock_rps_save_rxhash(sk, skb->rxhash); if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) goto reset; if (opt_skb) @@ -1648,7 +1650,8 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) __kfree_skb(opt_skb); return 0; } - } + } else + sock_rps_save_rxhash(sk, skb->rxhash); if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) goto reset; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index d7037c006e1..9e305d74b3d 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -505,6 +505,9 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) int rc; int is_udplite = IS_UDPLITE(sk); + if (!ipv6_addr_any(&inet6_sk(sk)->daddr)) + sock_rps_save_rxhash(sk, skb->rxhash); + if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto drop; @@ -1332,7 +1335,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, u32 features) skb->ip_summed = CHECKSUM_NONE; /* Check if there is enough headroom to insert fragment header. */ - if ((skb_headroom(skb) < frag_hdr_sz) && + if ((skb_mac_header(skb) < skb->head + frag_hdr_sz) && pskb_expand_head(skb, frag_hdr_sz, 0, GFP_ATOMIC)) goto out; diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 8e688b3de9a..49a91c5f562 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -79,7 +79,7 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) } EXPORT_SYMBOL(xfrm6_prepare_output); -static int xfrm6_output_finish(struct sk_buff *skb) +int xfrm6_output_finish(struct sk_buff *skb) { #ifdef CONFIG_NETFILTER IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED; @@ -97,9 +97,9 @@ static int __xfrm6_output(struct sk_buff *skb) if ((x && x->props.mode == XFRM_MODE_TUNNEL) && ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || dst_allfrag(skb_dst(skb)))) { - return ip6_fragment(skb, xfrm6_output_finish); + return ip6_fragment(skb, x->outer_mode->afinfo->output_finish); } - return xfrm6_output_finish(skb); + return x->outer_mode->afinfo->output_finish(skb); } int xfrm6_output(struct sk_buff *skb) diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index afe941e9415..248f0b2a7ee 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -178,6 +178,7 @@ static struct xfrm_state_afinfo xfrm6_state_afinfo = { .tmpl_sort = __xfrm6_tmpl_sort, .state_sort = __xfrm6_state_sort, .output = xfrm6_output, + .output_finish = xfrm6_output_finish, .extract_input = xfrm6_extract_input, .extract_output = xfrm6_extract_output, .transport_finish = xfrm6_transport_finish, diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index 2731b51923d..9680226640e 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -148,7 +148,6 @@ static void ipx_destroy_socket(struct sock *sk) ipx_remove_socket(sk); skb_queue_purge(&sk->sk_receive_queue); sk_refcnt_debug_dec(sk); - sock_put(sk); } /* @@ -1404,6 +1403,7 @@ static int ipx_release(struct socket *sock) sk_refcnt_debug_release(sk); ipx_destroy_socket(sk); release_sock(sk); + sock_put(sk); out: return 0; } diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index c9890e25cd4..cc616974a44 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1297,8 +1297,7 @@ static int irda_sendmsg(struct kiocb *iocb, struct socket *sock, /* Note : socket.c set MSG_EOR on SEQPACKET sockets */ if (msg->msg_flags & ~(MSG_DONTWAIT | MSG_EOR | MSG_CMSG_COMPAT | MSG_NOSIGNAL)) { - err = -EINVAL; - goto out; + return -EINVAL; } lock_sock(sk); diff --git a/net/irda/iriap.c b/net/irda/iriap.c index 5b743bdd89b..36477538cea 100644 --- a/net/irda/iriap.c +++ b/net/irda/iriap.c @@ -656,10 +656,16 @@ static void iriap_getvaluebyclass_indication(struct iriap_cb *self, n = 1; name_len = fp[n++]; + + IRDA_ASSERT(name_len < IAS_MAX_CLASSNAME + 1, return;); + memcpy(name, fp+n, name_len); n+=name_len; name[name_len] = '\0'; attr_len = fp[n++]; + + IRDA_ASSERT(attr_len < IAS_MAX_ATTRIBNAME + 1, return;); + memcpy(attr, fp+n, attr_len); n+=attr_len; attr[attr_len] = '\0'; diff --git a/net/irda/irlap.c b/net/irda/irlap.c index 783c5f367d2..005b424494a 100644 --- a/net/irda/irlap.c +++ b/net/irda/irlap.c @@ -165,7 +165,7 @@ struct irlap_cb *irlap_open(struct net_device *dev, struct qos_info *qos, irlap_apply_default_connection_parameters(self); - self->N3 = 3; /* # connections attemts to try before giving up */ + self->N3 = 3; /* # connections attempts to try before giving up */ self->state = LAP_NDM; diff --git a/net/irda/irlap_event.c b/net/irda/irlap_event.c index d434c888074..bb47021c9a5 100644 --- a/net/irda/irlap_event.c +++ b/net/irda/irlap_event.c @@ -708,7 +708,7 @@ static int irlap_state_reply(struct irlap_cb *self, IRLAP_EVENT event, self->frame_sent = TRUE; } - /* Readjust our timer to accomodate devices + /* Readjust our timer to accommodate devices * doing faster or slower discovery than us... * Jean II */ irlap_start_query_timer(self, info->S, info->s); @@ -931,7 +931,7 @@ static int irlap_state_setup(struct irlap_cb *self, IRLAP_EVENT event, irlap_send_rr_frame(self, CMD_FRAME); /* The timer is set to half the normal timer to quickly - * detect a failure to negociate the new connection + * detect a failure to negotiate the new connection * parameters. IrLAP 6.11.3.2, note 3. * Note that currently we don't process this failure * properly, as we should do a quick disconnect. @@ -1052,7 +1052,7 @@ static int irlap_state_xmit_p(struct irlap_cb *self, IRLAP_EVENT event, return -EPROTO; } - /* Substract space used by this skb */ + /* Subtract space used by this skb */ self->bytes_left -= skb->len; #else /* CONFIG_IRDA_DYNAMIC_WINDOW */ /* Window has been adjusted for the max packet @@ -1808,7 +1808,7 @@ static int irlap_state_xmit_s(struct irlap_cb *self, IRLAP_EVENT event, return -EPROTO; /* Try again later */ } - /* Substract space used by this skb */ + /* Subtract space used by this skb */ self->bytes_left -= skb->len; #else /* CONFIG_IRDA_DYNAMIC_WINDOW */ /* Window has been adjusted for the max packet diff --git a/net/irda/irlap_frame.c b/net/irda/irlap_frame.c index 688222cbf55..8c004161a84 100644 --- a/net/irda/irlap_frame.c +++ b/net/irda/irlap_frame.c @@ -848,7 +848,7 @@ void irlap_send_data_primary_poll(struct irlap_cb *self, struct sk_buff *skb) * though IrLAP is currently sending the *last* frame of the * tx-window, the driver most likely has only just started * sending the *first* frame of the same tx-window. - * I.e. we are always at the very begining of or Tx window. + * I.e. we are always at the very beginning of or Tx window. * Now, we are supposed to set the final timer from the end * of our tx-window to let the other peer reply. So, we need * to add extra time to compensate for the fact that we diff --git a/net/irda/irlmp_event.c b/net/irda/irlmp_event.c index c1fb5db8104..9505a7d06f1 100644 --- a/net/irda/irlmp_event.c +++ b/net/irda/irlmp_event.c @@ -498,7 +498,7 @@ static int irlmp_state_disconnected(struct lsap_cb *self, IRLMP_EVENT event, switch (event) { #ifdef CONFIG_IRDA_ULTRA case LM_UDATA_INDICATION: - /* This is most bizzare. Those packets are aka unreliable + /* This is most bizarre. Those packets are aka unreliable * connected, aka IrLPT or SOCK_DGRAM/IRDAPROTO_UNITDATA. * Why do we pass them as Ultra ??? Jean II */ irlmp_connless_data_indication(self, skb); diff --git a/net/irda/irnet/irnet.h b/net/irda/irnet/irnet.h index 0d82ff5aeff..979ecb2435a 100644 --- a/net/irda/irnet/irnet.h +++ b/net/irda/irnet/irnet.h @@ -73,7 +73,7 @@ * Infinite thanks to those brave souls for providing the infrastructure * upon which IrNET is built. * - * Thanks to all my collegues in HP for helping me. In particular, + * Thanks to all my colleagues in HP for helping me. In particular, * thanks to Salil Pradhan and Bill Serra for W2k testing... * Thanks to Luiz Magalhaes for irnetd and much testing... * diff --git a/net/irda/irnet/irnet_ppp.c b/net/irda/irnet/irnet_ppp.c index 7c567b8aa89..2bb2beb6a37 100644 --- a/net/irda/irnet/irnet_ppp.c +++ b/net/irda/irnet/irnet_ppp.c @@ -105,6 +105,9 @@ irnet_ctrl_write(irnet_socket * ap, while(isspace(start[length - 1])) length--; + DABORT(length < 5 || length > NICKNAME_MAX_LEN + 5, + -EINVAL, CTRL_ERROR, "Invalid nickname.\n"); + /* Copy the name for later reuse */ memcpy(ap->rname, start + 5, length - 5); ap->rname[length - 5] = '\0'; diff --git a/net/irda/irqueue.c b/net/irda/irqueue.c index 849aaf0dabb..9715e6e5900 100644 --- a/net/irda/irqueue.c +++ b/net/irda/irqueue.c @@ -40,7 +40,7 @@ * o the hash function for ints is pathetic (but could be changed) * o locking is sometime suspicious (especially during enumeration) * o most users have only a few elements (== overhead) - * o most users never use seach, so don't benefit from hashing + * o most users never use search, so don't benefit from hashing * Problem already fixed : * o not 64 bit compliant (most users do hashv = (int) self) * o hashbin_remove() is broken => use hashbin_remove_this() diff --git a/net/irda/irttp.c b/net/irda/irttp.c index f6054f9ccbe..9d9af460697 100644 --- a/net/irda/irttp.c +++ b/net/irda/irttp.c @@ -1193,7 +1193,7 @@ EXPORT_SYMBOL(irttp_connect_request); /* * Function irttp_connect_confirm (handle, qos, skb) * - * Sevice user confirms TSAP connection with peer. + * Service user confirms TSAP connection with peer. * */ static void irttp_connect_confirm(void *instance, void *sap, diff --git a/net/irda/qos.c b/net/irda/qos.c index 2b00974e5ba..1b51bcf4239 100644 --- a/net/irda/qos.c +++ b/net/irda/qos.c @@ -39,16 +39,16 @@ #include <net/irda/irlap_frame.h> /* - * Maximum values of the baud rate we negociate with the other end. + * Maximum values of the baud rate we negotiate with the other end. * Most often, you don't have to change that, because Linux-IrDA will * use the maximum offered by the link layer, which usually works fine. * In some very rare cases, you may want to limit it to lower speeds... */ int sysctl_max_baud_rate = 16000000; /* - * Maximum value of the lap disconnect timer we negociate with the other end. + * Maximum value of the lap disconnect timer we negotiate with the other end. * Most often, the value below represent the best compromise, but some user - * may want to keep the LAP alive longuer or shorter in case of link failure. + * may want to keep the LAP alive longer or shorter in case of link failure. * Remember that the threshold time (early warning) is fixed to 3s... */ int sysctl_max_noreply_time = 12; @@ -411,7 +411,7 @@ static void irlap_adjust_qos_settings(struct qos_info *qos) * Fix tx data size according to user limits - Jean II */ if (qos->data_size.value > sysctl_max_tx_data_size) - /* Allow non discrete adjustement to avoid loosing capacity */ + /* Allow non discrete adjustement to avoid losing capacity */ qos->data_size.value = sysctl_max_tx_data_size; /* * Override Tx window if user request it. - Jean II diff --git a/net/irda/timer.c b/net/irda/timer.c index 0335ba0cc59..f418cb2ad49 100644 --- a/net/irda/timer.c +++ b/net/irda/timer.c @@ -59,7 +59,7 @@ void irlap_start_query_timer(struct irlap_cb *self, int S, int s) * slot time, plus add some extra time to properly receive the last * discovery packet (which is longer due to extra discovery info), * to avoid messing with for incomming connections requests and - * to accomodate devices that perform discovery slower than us. + * to accommodate devices that perform discovery slower than us. * Jean II */ timeout = ((sysctl_slot_timeout * HZ / 1000) * (S - s) + XIDEXTRA_TIMEOUT + SMALLBUSY_TIMEOUT); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 9637e45744f..986b2a5e876 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -250,7 +250,7 @@ static struct device *af_iucv_dev; * PRMDATA[0..6] socket data (max 7 bytes); * PRMDATA[7] socket data length value (len is 0xff - PRMDATA[7]) * - * The socket data length is computed by substracting the socket data length + * The socket data length is computed by subtracting the socket data length * value from 0xFF. * If the socket data len is greater 7, then PRMDATA can be used for special * notifications (see iucv_sock_shutdown); and further, diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 1ee5dab3cfa..8f156bd86be 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -735,7 +735,7 @@ static void iucv_cleanup_queue(void) struct iucv_irq_list *p, *n; /* - * When a path is severed, the pathid can be reused immediatly + * When a path is severed, the pathid can be reused immediately * on a iucv connect or a connection pending interrupt. Remove * all entries from the task queue that refer to a stale pathid * (iucv_path_table[ix] == NULL). Only then do the iucv connect @@ -807,7 +807,7 @@ void iucv_unregister(struct iucv_handler *handler, int smp) spin_lock_bh(&iucv_table_lock); /* Remove handler from the iucv_handler_list. */ list_del_init(&handler->list); - /* Sever all pathids still refering to the handler. */ + /* Sever all pathids still referring to the handler. */ list_for_each_entry_safe(p, n, &handler->paths, list) { iucv_sever_pathid(p->pathid, NULL); iucv_path_table[p->pathid] = NULL; diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 8d9ce0accc9..a8193f52c13 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -283,7 +283,7 @@ static __net_init int l2tp_eth_init_net(struct net *net) return 0; } -static __net_initdata struct pernet_operations l2tp_eth_net_ops = { +static struct pernet_operations l2tp_eth_net_ops = { .init = l2tp_eth_init_net, .id = &l2tp_eth_net_id, .size = sizeof(struct l2tp_eth_net), diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index fce9bd3bd3f..5c04f3e4270 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -667,7 +667,7 @@ MODULE_AUTHOR("James Chapman <jchapman@katalix.com>"); MODULE_DESCRIPTION("L2TP over IP"); MODULE_VERSION("1.0"); -/* Use the value of SOCK_DGRAM (2) directory, because __stringify does't like +/* Use the value of SOCK_DGRAM (2) directory, because __stringify doesn't like * enums */ MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 2, IPPROTO_L2TP); diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c index 058f1e9a912..90324211131 100644 --- a/net/llc/llc_input.c +++ b/net/llc/llc_input.c @@ -121,8 +121,7 @@ static inline int llc_fixup_skb(struct sk_buff *skb) s32 data_size = ntohs(pdulen) - llc_len; if (data_size < 0 || - ((skb_tail_pointer(skb) - - (u8 *)pdu) - llc_len) < data_size) + !pskb_may_pull(skb, data_size)) return 0; if (unlikely(pskb_trim_rcsum(skb, data_size))) return 0; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 334213571ad..44049733c4e 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1504,6 +1504,8 @@ int __ieee80211_request_smps(struct ieee80211_sub_if_data *sdata, enum ieee80211_smps_mode old_req; int err; + lockdep_assert_held(&sdata->u.mgd.mtx); + old_req = sdata->u.mgd.req_smps; sdata->u.mgd.req_smps = smps_mode; diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index dacace6b139..9ea7c0d0103 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -177,9 +177,9 @@ static int ieee80211_set_smps(struct ieee80211_sub_if_data *sdata, if (sdata->vif.type != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; - mutex_lock(&local->iflist_mtx); + mutex_lock(&sdata->u.mgd.mtx); err = __ieee80211_request_smps(sdata, smps_mode); - mutex_unlock(&local->iflist_mtx); + mutex_unlock(&sdata->u.mgd.mtx); return err; } diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index a4040170142..c18396c248d 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -97,7 +97,7 @@ struct ieee80211_bss { size_t supp_rates_len; /* - * During assocation, we save an ERP value from a probe response so + * During association, we save an ERP value from a probe response so * that we can feed ERP info to the driver when handling the * association completes. these fields probably won't be up-to-date * otherwise, you probably don't want to use them. diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 8c02469b717..af3c56482c8 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -342,7 +342,7 @@ struct ieee80211_key *ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, if (IS_ERR(key->u.ccmp.tfm)) { err = PTR_ERR(key->u.ccmp.tfm); kfree(key); - key = ERR_PTR(err); + return ERR_PTR(err); } break; case WLAN_CIPHER_SUITE_AES_CMAC: @@ -360,7 +360,7 @@ struct ieee80211_key *ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, if (IS_ERR(key->u.aes_cmac.tfm)) { err = PTR_ERR(key->u.aes_cmac.tfm); kfree(key); - key = ERR_PTR(err); + return ERR_PTR(err); } break; } @@ -400,11 +400,12 @@ int ieee80211_key_link(struct ieee80211_key *key, { struct ieee80211_key *old_key; int idx, ret; - bool pairwise = key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE; + bool pairwise; BUG_ON(!sdata); BUG_ON(!key); + pairwise = key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE; idx = key->conf.keyidx; key->local = sdata->local; key->sdata = sdata; diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 8d65b47d983..336ca9d0c5c 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -628,7 +628,7 @@ void mesh_path_discard_frame(struct sk_buff *skb, * * @mpath: mesh path whose queue has to be freed * - * Locking: the function must me called withing a rcu_read_lock region + * Locking: the function must me called within a rcu_read_lock region */ void mesh_path_flush_pending(struct mesh_path *mpath) { diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 8212a8bebf0..c06aa3ac6b9 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -259,7 +259,7 @@ minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) } } - /* try to sample up to half of the availble rates during each interval */ + /* try to sample up to half of the available rates during each interval */ mi->sample_count *= 4; cur_prob = 0; @@ -659,18 +659,14 @@ minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband, struct ieee80211_mcs_info *mcs = &sta->ht_cap.mcs; struct ieee80211_local *local = hw_to_local(mp->hw); u16 sta_cap = sta->ht_cap.cap; + int n_supported = 0; int ack_dur; int stbc; int i; /* fall back to the old minstrel for legacy stations */ - if (!sta->ht_cap.ht_supported) { - msp->is_ht = false; - memset(&msp->legacy, 0, sizeof(msp->legacy)); - msp->legacy.r = msp->ratelist; - msp->legacy.sample_table = msp->sample_table; - return mac80211_minstrel.rate_init(priv, sband, sta, &msp->legacy); - } + if (!sta->ht_cap.ht_supported) + goto use_legacy; BUILD_BUG_ON(ARRAY_SIZE(minstrel_mcs_groups) != MINSTREL_MAX_STREAMS * MINSTREL_STREAM_GROUPS); @@ -725,7 +721,22 @@ minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband, mi->groups[i].supported = mcs->rx_mask[minstrel_mcs_groups[i].streams - 1]; + + if (mi->groups[i].supported) + n_supported++; } + + if (!n_supported) + goto use_legacy; + + return; + +use_legacy: + msp->is_ht = false; + memset(&msp->legacy, 0, sizeof(msp->legacy)); + msp->legacy.r = msp->ratelist; + msp->legacy.sample_table = msp->sample_table; + return mac80211_minstrel.rate_init(priv, sband, sta, &msp->legacy); } static void diff --git a/net/mac80211/rc80211_pid.h b/net/mac80211/rc80211_pid.h index 6510f8ee738..19111c7bf45 100644 --- a/net/mac80211/rc80211_pid.h +++ b/net/mac80211/rc80211_pid.h @@ -77,7 +77,7 @@ union rc_pid_event_data { }; struct rc_pid_event { - /* The time when the event occured */ + /* The time when the event occurred */ unsigned long timestamp; /* Event ID number */ diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 5c1930ba8eb..c5d4530d828 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -381,7 +381,7 @@ static void ieee80211_parse_qos(struct ieee80211_rx_data *rx) * specs were sane enough this time around to require padding each A-MSDU * subframe to a length that is a multiple of four. * - * Padding like Atheros hardware adds which is inbetween the 802.11 header and + * Padding like Atheros hardware adds which is between the 802.11 header and * the payload is not supported, the driver is required to move the 802.11 * header to be directly in front of the payload in that case. */ @@ -612,7 +612,8 @@ static void ieee80211_sta_reorder_release(struct ieee80211_hw *hw, skipped++; continue; } - if (!time_after(jiffies, tid_agg_rx->reorder_time[j] + + if (skipped && + !time_after(jiffies, tid_agg_rx->reorder_time[j] + HT_RX_REORDER_BUF_TIMEOUT)) goto set_release_timer; @@ -2540,7 +2541,6 @@ static void ieee80211_rx_handlers(struct ieee80211_rx_data *rx) * same TID from the same station */ rx->skb = skb; - rx->flags = 0; CALL_RXH(ieee80211_rx_h_decrypt) CALL_RXH(ieee80211_rx_h_check_more_data) @@ -2611,6 +2611,7 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid) .sdata = sta->sdata, .local = sta->local, .queue = tid, + .flags = 0, }; struct tid_ampdu_rx *tid_agg_rx; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 5a11078827a..13e8c30adf0 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -47,9 +47,9 @@ * Station entries are added by mac80211 when you establish a link with a * peer. This means different things for the different type of interfaces * we support. For a regular station this mean we add the AP sta when we - * receive an assocation response from the AP. For IBSS this occurs when + * receive an association response from the AP. For IBSS this occurs when * get to know about a peer on the same IBSS. For WDS we add the sta for - * the peer imediately upon device open. When using AP mode we add stations + * the peer immediately upon device open. When using AP mode we add stations * for each respective station upon request from userspace through nl80211. * * In order to remove a STA info structure, various sta_info_destroy_*() @@ -243,6 +243,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, memcpy(sta->sta.addr, addr, ETH_ALEN); sta->local = local; sta->sdata = sdata; + sta->last_rx = jiffies; ewma_init(&sta->avg_signal, 1024, 8); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 57681149e37..b2f95966c7f 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -173,7 +173,7 @@ struct sta_ampdu_mlme { /** * enum plink_state - state of a mesh peer link finite state machine * - * @PLINK_LISTEN: initial state, considered the implicit state of non existant + * @PLINK_LISTEN: initial state, considered the implicit state of non existent * mesh peer links * @PLINK_OPN_SNT: mesh plink open frame has been sent to this mesh peer * @PLINK_OPN_RCVD: mesh plink open frame has been received from this mesh peer diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index ce4596ed126..bd1224fd216 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -237,6 +237,10 @@ ieee80211_tx_h_dynamic_ps(struct ieee80211_tx_data *tx) &local->dynamic_ps_disable_work); } + /* Don't restart the timer if we're not disassociated */ + if (!ifmgd->associated) + return TX_CONTINUE; + mod_timer(&local->dynamic_ps_timer, jiffies + msecs_to_jiffies(local->hw.conf.dynamic_ps_timeout)); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index c3f988aa115..32bff6d86cb 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -652,7 +652,6 @@ comment "Xtables matches" config NETFILTER_XT_MATCH_ADDRTYPE tristate '"addrtype" address type match support' depends on NETFILTER_ADVANCED - depends on (IPV6 || IPV6=n) ---help--- This option allows you to match what routing thinks of an address, eg. UNICAST, LOCAL, BROADCAST, ... diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index bca96990218..a113ff06692 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -338,8 +338,7 @@ bitmap_ip_head(struct ip_set *set, struct sk_buff *skb) NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip)); if (map->netmask != 32) NLA_PUT_U8(skb, IPSET_ATTR_NETMASK, map->netmask); - NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, - htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)); NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, htonl(sizeof(*map) + map->memsize)); if (with_timeout(map->timeout)) diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index 5e790172def..a274300b6a5 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -343,6 +343,10 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb, ipset_adtfn adtfn = set->variant->adt[adt]; struct ipmac data; + /* MAC can be src only */ + if (!(flags & IPSET_DIM_TWO_SRC)) + return 0; + data.id = ntohl(ip4addr(skb, flags & IPSET_DIM_ONE_SRC)); if (data.id < map->first_ip || data.id > map->last_ip) return -IPSET_ERR_BITMAP_RANGE; @@ -434,8 +438,7 @@ bitmap_ipmac_head(struct ip_set *set, struct sk_buff *skb) goto nla_put_failure; NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, htonl(map->first_ip)); NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip)); - NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, - htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)); NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, htonl(sizeof(*map) + (map->last_ip - map->first_ip + 1) * map->dsize)); diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index 165f09b1a9c..6b38eb8f6ed 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -320,8 +320,7 @@ bitmap_port_head(struct ip_set *set, struct sk_buff *skb) goto nla_put_failure; NLA_PUT_NET16(skb, IPSET_ATTR_PORT, htons(map->first_port)); NLA_PUT_NET16(skb, IPSET_ATTR_PORT_TO, htons(map->last_port)); - NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, - htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)); NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, htonl(sizeof(*map) + map->memsize)); if (with_timeout(map->timeout)) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 618a615acc9..72d1ac611fd 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -26,6 +26,7 @@ static LIST_HEAD(ip_set_type_list); /* all registered set types */ static DEFINE_MUTEX(ip_set_type_mutex); /* protects ip_set_type_list */ +static DEFINE_RWLOCK(ip_set_ref_lock); /* protects the set refs */ static struct ip_set **ip_set_list; /* all individual sets */ static ip_set_id_t ip_set_max = CONFIG_IP_SET_MAX; /* max number of sets */ @@ -94,16 +95,28 @@ static int find_set_type_get(const char *name, u8 family, u8 revision, struct ip_set_type **found) { + struct ip_set_type *type; + int err; + rcu_read_lock(); *found = find_set_type(name, family, revision); if (*found) { - int err = !try_module_get((*found)->me); - rcu_read_unlock(); - return err ? -EFAULT : 0; + err = !try_module_get((*found)->me) ? -EFAULT : 0; + goto unlock; } + /* Make sure the type is loaded but we don't support the revision */ + list_for_each_entry_rcu(type, &ip_set_type_list, list) + if (STREQ(type->name, name)) { + err = -IPSET_ERR_FIND_TYPE; + goto unlock; + } rcu_read_unlock(); return try_to_load_type(name); + +unlock: + rcu_read_unlock(); + return err; } /* Find a given set type by name and family. @@ -116,7 +129,7 @@ find_set_type_minmax(const char *name, u8 family, u8 *min, u8 *max) struct ip_set_type *type; bool found = false; - *min = *max = 0; + *min = 255; *max = 0; rcu_read_lock(); list_for_each_entry_rcu(type, &ip_set_type_list, list) if (STREQ(type->name, name) && @@ -124,7 +137,7 @@ find_set_type_minmax(const char *name, u8 family, u8 *min, u8 *max) found = true; if (type->revision < *min) *min = type->revision; - else if (type->revision > *max) + if (type->revision > *max) *max = type->revision; } rcu_read_unlock(); @@ -289,13 +302,18 @@ EXPORT_SYMBOL_GPL(ip_set_get_ipaddr6); static inline void __ip_set_get(ip_set_id_t index) { - atomic_inc(&ip_set_list[index]->ref); + write_lock_bh(&ip_set_ref_lock); + ip_set_list[index]->ref++; + write_unlock_bh(&ip_set_ref_lock); } static inline void __ip_set_put(ip_set_id_t index) { - atomic_dec(&ip_set_list[index]->ref); + write_lock_bh(&ip_set_ref_lock); + BUG_ON(ip_set_list[index]->ref == 0); + ip_set_list[index]->ref--; + write_unlock_bh(&ip_set_ref_lock); } /* @@ -312,7 +330,7 @@ ip_set_test(ip_set_id_t index, const struct sk_buff *skb, struct ip_set *set = ip_set_list[index]; int ret = 0; - BUG_ON(set == NULL || atomic_read(&set->ref) == 0); + BUG_ON(set == NULL); pr_debug("set %s, index %u\n", set->name, index); if (dim < set->type->dimension || @@ -344,7 +362,7 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb, struct ip_set *set = ip_set_list[index]; int ret; - BUG_ON(set == NULL || atomic_read(&set->ref) == 0); + BUG_ON(set == NULL); pr_debug("set %s, index %u\n", set->name, index); if (dim < set->type->dimension || @@ -366,7 +384,7 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb, struct ip_set *set = ip_set_list[index]; int ret = 0; - BUG_ON(set == NULL || atomic_read(&set->ref) == 0); + BUG_ON(set == NULL); pr_debug("set %s, index %u\n", set->name, index); if (dim < set->type->dimension || @@ -385,7 +403,6 @@ EXPORT_SYMBOL_GPL(ip_set_del); * Find set by name, reference it once. The reference makes sure the * thing pointed to, does not go away under our feet. * - * The nfnl mutex must already be activated. */ ip_set_id_t ip_set_get_byname(const char *name, struct ip_set **set) @@ -411,15 +428,12 @@ EXPORT_SYMBOL_GPL(ip_set_get_byname); * reference count by 1. The caller shall not assume the index * to be valid, after calling this function. * - * The nfnl mutex must already be activated. */ void ip_set_put_byindex(ip_set_id_t index) { - if (ip_set_list[index] != NULL) { - BUG_ON(atomic_read(&ip_set_list[index]->ref) == 0); + if (ip_set_list[index] != NULL) __ip_set_put(index); - } } EXPORT_SYMBOL_GPL(ip_set_put_byindex); @@ -429,7 +443,6 @@ EXPORT_SYMBOL_GPL(ip_set_put_byindex); * can't be destroyed. The set cannot be renamed due to * the referencing either. * - * The nfnl mutex must already be activated. */ const char * ip_set_name_byindex(ip_set_id_t index) @@ -437,7 +450,7 @@ ip_set_name_byindex(ip_set_id_t index) const struct ip_set *set = ip_set_list[index]; BUG_ON(set == NULL); - BUG_ON(atomic_read(&set->ref) == 0); + BUG_ON(set->ref == 0); /* Referenced, so it's safe */ return set->name; @@ -503,10 +516,7 @@ void ip_set_nfnl_put(ip_set_id_t index) { nfnl_lock(); - if (ip_set_list[index] != NULL) { - BUG_ON(atomic_read(&ip_set_list[index]->ref) == 0); - __ip_set_put(index); - } + ip_set_put_byindex(index); nfnl_unlock(); } EXPORT_SYMBOL_GPL(ip_set_nfnl_put); @@ -514,7 +524,7 @@ EXPORT_SYMBOL_GPL(ip_set_nfnl_put); /* * Communication protocol with userspace over netlink. * - * We already locked by nfnl_lock. + * The commands are serialized by the nfnl mutex. */ static inline bool @@ -645,7 +655,6 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, return -ENOMEM; rwlock_init(&set->lock); strlcpy(set->name, name, IPSET_MAXNAMELEN); - atomic_set(&set->ref, 0); set->family = family; /* @@ -678,8 +687,8 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, /* * Here, we have a valid, constructed set and we are protected - * by nfnl_lock. Find the first free index in ip_set_list and - * check clashing. + * by the nfnl mutex. Find the first free index in ip_set_list + * and check clashing. */ if ((ret = find_free_id(set->name, &index, &clash)) != 0) { /* If this is the same set and requested, ignore error */ @@ -739,31 +748,51 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb, const struct nlattr * const attr[]) { ip_set_id_t i; + int ret = 0; if (unlikely(protocol_failed(attr))) return -IPSET_ERR_PROTOCOL; - /* References are protected by the nfnl mutex */ + /* Commands are serialized and references are + * protected by the ip_set_ref_lock. + * External systems (i.e. xt_set) must call + * ip_set_put|get_nfnl_* functions, that way we + * can safely check references here. + * + * list:set timer can only decrement the reference + * counter, so if it's already zero, we can proceed + * without holding the lock. + */ + read_lock_bh(&ip_set_ref_lock); if (!attr[IPSET_ATTR_SETNAME]) { for (i = 0; i < ip_set_max; i++) { - if (ip_set_list[i] != NULL && - (atomic_read(&ip_set_list[i]->ref))) - return -IPSET_ERR_BUSY; + if (ip_set_list[i] != NULL && ip_set_list[i]->ref) { + ret = IPSET_ERR_BUSY; + goto out; + } } + read_unlock_bh(&ip_set_ref_lock); for (i = 0; i < ip_set_max; i++) { if (ip_set_list[i] != NULL) ip_set_destroy_set(i); } } else { i = find_set_id(nla_data(attr[IPSET_ATTR_SETNAME])); - if (i == IPSET_INVALID_ID) - return -ENOENT; - else if (atomic_read(&ip_set_list[i]->ref)) - return -IPSET_ERR_BUSY; + if (i == IPSET_INVALID_ID) { + ret = -ENOENT; + goto out; + } else if (ip_set_list[i]->ref) { + ret = -IPSET_ERR_BUSY; + goto out; + } + read_unlock_bh(&ip_set_ref_lock); ip_set_destroy_set(i); } return 0; +out: + read_unlock_bh(&ip_set_ref_lock); + return ret; } /* Flush sets */ @@ -822,6 +851,7 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set; const char *name2; ip_set_id_t i; + int ret = 0; if (unlikely(protocol_failed(attr) || attr[IPSET_ATTR_SETNAME] == NULL || @@ -831,25 +861,33 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb, set = find_set(nla_data(attr[IPSET_ATTR_SETNAME])); if (set == NULL) return -ENOENT; - if (atomic_read(&set->ref) != 0) - return -IPSET_ERR_REFERENCED; + + read_lock_bh(&ip_set_ref_lock); + if (set->ref != 0) { + ret = -IPSET_ERR_REFERENCED; + goto out; + } name2 = nla_data(attr[IPSET_ATTR_SETNAME2]); for (i = 0; i < ip_set_max; i++) { if (ip_set_list[i] != NULL && - STREQ(ip_set_list[i]->name, name2)) - return -IPSET_ERR_EXIST_SETNAME2; + STREQ(ip_set_list[i]->name, name2)) { + ret = -IPSET_ERR_EXIST_SETNAME2; + goto out; + } } strncpy(set->name, name2, IPSET_MAXNAMELEN); - return 0; +out: + read_unlock_bh(&ip_set_ref_lock); + return ret; } /* Swap two sets so that name/index points to the other. * References and set names are also swapped. * - * We are protected by the nfnl mutex and references are - * manipulated only by holding the mutex. The kernel interfaces + * The commands are serialized by the nfnl mutex and references are + * protected by the ip_set_ref_lock. The kernel interfaces * do not hold the mutex but the pointer settings are atomic * so the ip_set_list always contains valid pointers to the sets. */ @@ -862,7 +900,6 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb, struct ip_set *from, *to; ip_set_id_t from_id, to_id; char from_name[IPSET_MAXNAMELEN]; - u32 from_ref; if (unlikely(protocol_failed(attr) || attr[IPSET_ATTR_SETNAME] == NULL || @@ -881,23 +918,21 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb, to = ip_set_list[to_id]; /* Features must not change. - * Not an artifical restriction anymore, as we must prevent + * Not an artificial restriction anymore, as we must prevent * possible loops created by swapping in setlist type of sets. */ if (!(from->type->features == to->type->features && from->type->family == to->type->family)) return -IPSET_ERR_TYPE_MISMATCH; - /* No magic here: ref munging protected by the nfnl_lock */ strncpy(from_name, from->name, IPSET_MAXNAMELEN); - from_ref = atomic_read(&from->ref); - strncpy(from->name, to->name, IPSET_MAXNAMELEN); - atomic_set(&from->ref, atomic_read(&to->ref)); strncpy(to->name, from_name, IPSET_MAXNAMELEN); - atomic_set(&to->ref, from_ref); + write_lock_bh(&ip_set_ref_lock); + swap(from->ref, to->ref); ip_set_list[from_id] = to; ip_set_list[to_id] = from; + write_unlock_bh(&ip_set_ref_lock); return 0; } @@ -914,7 +949,7 @@ ip_set_dump_done(struct netlink_callback *cb) { if (cb->args[2]) { pr_debug("release set %s\n", ip_set_list[cb->args[1]]->name); - __ip_set_put((ip_set_id_t) cb->args[1]); + ip_set_put_byindex((ip_set_id_t) cb->args[1]); } return 0; } @@ -987,8 +1022,9 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb) if (cb->args[1] >= ip_set_max) goto out; - pr_debug("args[0]: %ld args[1]: %ld\n", cb->args[0], cb->args[1]); max = cb->args[0] == DUMP_ONE ? cb->args[1] + 1 : ip_set_max; +dump_last: + pr_debug("args[0]: %ld args[1]: %ld\n", cb->args[0], cb->args[1]); for (; cb->args[1] < max; cb->args[1]++) { index = (ip_set_id_t) cb->args[1]; set = ip_set_list[index]; @@ -1003,8 +1039,8 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb) * so that lists (unions of sets) are dumped last. */ if (cb->args[0] != DUMP_ONE && - !((cb->args[0] == DUMP_ALL) ^ - (set->type->features & IPSET_DUMP_LAST))) + ((cb->args[0] == DUMP_ALL) == + !!(set->type->features & IPSET_DUMP_LAST))) continue; pr_debug("List set: %s\n", set->name); if (!cb->args[2]) { @@ -1048,6 +1084,12 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb) goto release_refcount; } } + /* If we dump all sets, continue with dumping last ones */ + if (cb->args[0] == DUMP_ALL) { + cb->args[0] = DUMP_LAST; + cb->args[1] = 0; + goto dump_last; + } goto out; nla_put_failure: @@ -1056,13 +1098,8 @@ release_refcount: /* If there was an error or set is done, release set */ if (ret || !cb->args[2]) { pr_debug("release set %s\n", ip_set_list[index]->name); - __ip_set_put(index); + ip_set_put_byindex(index); } - - /* If we dump all sets, continue with dumping last ones */ - if (cb->args[0] == DUMP_ALL && cb->args[1] >= max && !cb->args[2]) - cb->args[0] = DUMP_LAST; - out: if (nlh) { nlmsg_end(skb, nlh); diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index adbe787ea5d..b9214145d35 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -150,6 +150,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_ipport4_elem data = { }; u32 ip, ip_to, p, port, port_to; u32 timeout = h->timeout; + bool with_ports = false; int ret; if (unlikely(!tb[IPSET_ATTR_IP] || @@ -172,21 +173,15 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_PROTO]) { data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); + with_ports = ip_set_proto_with_ports(data.proto); if (data.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else return -IPSET_ERR_MISSING_PROTO; - switch (data.proto) { - case IPPROTO_UDP: - case IPPROTO_TCP: - case IPPROTO_ICMP: - break; - default: + if (!(with_ports || data.proto == IPPROTO_ICMP)) data.port = 0; - break; - } if (tb[IPSET_ATTR_TIMEOUT]) { if (!with_timeout(h->timeout)) @@ -195,7 +190,6 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], } if (adt == IPSET_TEST || - !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) || !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR] || tb[IPSET_ATTR_PORT_TO])) { ret = adtfn(set, &data, timeout); @@ -219,13 +213,12 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], } else ip_to = ip; - port = ntohs(data.port); - if (tb[IPSET_ATTR_PORT_TO]) { + port_to = port = ntohs(data.port); + if (with_ports && tb[IPSET_ATTR_PORT_TO]) { port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port > port_to) swap(port, port_to); - } else - port_to = port; + } for (; !before(ip_to, ip); ip++) for (p = port; p <= port_to; p++) { @@ -361,6 +354,7 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_ipport6_elem data = { }; u32 port, port_to; u32 timeout = h->timeout; + bool with_ports = false; int ret; if (unlikely(!tb[IPSET_ATTR_IP] || @@ -385,21 +379,15 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_PROTO]) { data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); + with_ports = ip_set_proto_with_ports(data.proto); if (data.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else return -IPSET_ERR_MISSING_PROTO; - switch (data.proto) { - case IPPROTO_UDP: - case IPPROTO_TCP: - case IPPROTO_ICMPV6: - break; - default: + if (!(with_ports || data.proto == IPPROTO_ICMPV6)) data.port = 0; - break; - } if (tb[IPSET_ATTR_TIMEOUT]) { if (!with_timeout(h->timeout)) @@ -407,9 +395,7 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[], timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); } - if (adt == IPSET_TEST || - !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) || - !tb[IPSET_ATTR_PORT_TO]) { + if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &data, timeout); return ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index 22e23abb86c..4642872df6e 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -154,6 +154,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_ipportip4_elem data = { }; u32 ip, ip_to, p, port, port_to; u32 timeout = h->timeout; + bool with_ports = false; int ret; if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || @@ -180,21 +181,15 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_PROTO]) { data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); + with_ports = ip_set_proto_with_ports(data.proto); if (data.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else return -IPSET_ERR_MISSING_PROTO; - switch (data.proto) { - case IPPROTO_UDP: - case IPPROTO_TCP: - case IPPROTO_ICMP: - break; - default: + if (!(with_ports || data.proto == IPPROTO_ICMP)) data.port = 0; - break; - } if (tb[IPSET_ATTR_TIMEOUT]) { if (!with_timeout(h->timeout)) @@ -203,7 +198,6 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], } if (adt == IPSET_TEST || - !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) || !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR] || tb[IPSET_ATTR_PORT_TO])) { ret = adtfn(set, &data, timeout); @@ -227,13 +221,12 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], } else ip_to = ip; - port = ntohs(data.port); - if (tb[IPSET_ATTR_PORT_TO]) { + port_to = port = ntohs(data.port); + if (with_ports && tb[IPSET_ATTR_PORT_TO]) { port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port > port_to) swap(port, port_to); - } else - port_to = port; + } for (; !before(ip_to, ip); ip++) for (p = port; p <= port_to; p++) { @@ -375,6 +368,7 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_ipportip6_elem data = { }; u32 port, port_to; u32 timeout = h->timeout; + bool with_ports = false; int ret; if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || @@ -403,21 +397,15 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_PROTO]) { data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); + with_ports = ip_set_proto_with_ports(data.proto); if (data.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else return -IPSET_ERR_MISSING_PROTO; - switch (data.proto) { - case IPPROTO_UDP: - case IPPROTO_TCP: - case IPPROTO_ICMPV6: - break; - default: + if (!(with_ports || data.proto == IPPROTO_ICMPV6)) data.port = 0; - break; - } if (tb[IPSET_ATTR_TIMEOUT]) { if (!with_timeout(h->timeout)) @@ -425,9 +413,7 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[], timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); } - if (adt == IPSET_TEST || - !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) || - !tb[IPSET_ATTR_PORT_TO]) { + if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &data, timeout); return ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 6033e8b54bb..2cb84a54b7a 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -174,6 +174,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_ipportnet4_elem data = { .cidr = HOST_MASK }; u32 ip, ip_to, p, port, port_to; u32 timeout = h->timeout; + bool with_ports = false; int ret; if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || @@ -208,21 +209,15 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_PROTO]) { data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); + with_ports = ip_set_proto_with_ports(data.proto); if (data.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else return -IPSET_ERR_MISSING_PROTO; - switch (data.proto) { - case IPPROTO_UDP: - case IPPROTO_TCP: - case IPPROTO_ICMP: - break; - default: + if (!(with_ports || data.proto == IPPROTO_ICMP)) data.port = 0; - break; - } if (tb[IPSET_ATTR_TIMEOUT]) { if (!with_timeout(h->timeout)) @@ -231,7 +226,6 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], } if (adt == IPSET_TEST || - !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) || !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR] || tb[IPSET_ATTR_PORT_TO])) { ret = adtfn(set, &data, timeout); @@ -255,13 +249,12 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], } else ip_to = ip; - port = ntohs(data.port); - if (tb[IPSET_ATTR_PORT_TO]) { + port_to = port = ntohs(data.port); + if (with_ports && tb[IPSET_ATTR_PORT_TO]) { port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port > port_to) swap(port, port_to); - } else - port_to = port; + } for (; !before(ip_to, ip); ip++) for (p = port; p <= port_to; p++) { @@ -429,6 +422,7 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_ipportnet6_elem data = { .cidr = HOST_MASK }; u32 port, port_to; u32 timeout = h->timeout; + bool with_ports = false; int ret; if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || @@ -465,21 +459,15 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_PROTO]) { data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); + with_ports = ip_set_proto_with_ports(data.proto); if (data.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else return -IPSET_ERR_MISSING_PROTO; - switch (data.proto) { - case IPPROTO_UDP: - case IPPROTO_TCP: - case IPPROTO_ICMPV6: - break; - default: + if (!(with_ports || data.proto == IPPROTO_ICMPV6)) data.port = 0; - break; - } if (tb[IPSET_ATTR_TIMEOUT]) { if (!with_timeout(h->timeout)) @@ -487,9 +475,7 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); } - if (adt == IPSET_TEST || - !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) || - !tb[IPSET_ATTR_PORT_TO]) { + if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &data, timeout); return ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index 34a165626ee..8598676f2a0 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -170,6 +170,7 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_netport4_elem data = { .cidr = HOST_MASK }; u32 port, port_to; u32 timeout = h->timeout; + bool with_ports = false; int ret; if (unlikely(!tb[IPSET_ATTR_IP] || @@ -198,21 +199,15 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_PROTO]) { data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); + with_ports = ip_set_proto_with_ports(data.proto); if (data.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else return -IPSET_ERR_MISSING_PROTO; - switch (data.proto) { - case IPPROTO_UDP: - case IPPROTO_TCP: - case IPPROTO_ICMP: - break; - default: + if (!(with_ports || data.proto == IPPROTO_ICMP)) data.port = 0; - break; - } if (tb[IPSET_ATTR_TIMEOUT]) { if (!with_timeout(h->timeout)) @@ -220,9 +215,7 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); } - if (adt == IPSET_TEST || - !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) || - !tb[IPSET_ATTR_PORT_TO]) { + if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &data, timeout); return ip_set_eexist(ret, flags) ? 0 : ret; } @@ -390,6 +383,7 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_netport6_elem data = { .cidr = HOST_MASK }; u32 port, port_to; u32 timeout = h->timeout; + bool with_ports = false; int ret; if (unlikely(!tb[IPSET_ATTR_IP] || @@ -418,21 +412,15 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_PROTO]) { data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); + with_ports = ip_set_proto_with_ports(data.proto); if (data.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else return -IPSET_ERR_MISSING_PROTO; - switch (data.proto) { - case IPPROTO_UDP: - case IPPROTO_TCP: - case IPPROTO_ICMPV6: - break; - default: + if (!(with_ports || data.proto == IPPROTO_ICMPV6)) data.port = 0; - break; - } if (tb[IPSET_ATTR_TIMEOUT]) { if (!with_timeout(h->timeout)) @@ -440,9 +428,7 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); } - if (adt == IPSET_TEST || - !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) || - !tb[IPSET_ATTR_PORT_TO]) { + if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &data, timeout); return ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index a47c32982f0..e9159e99fc4 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -43,14 +43,19 @@ struct list_set { static inline struct set_elem * list_set_elem(const struct list_set *map, u32 id) { - return (struct set_elem *)((char *)map->members + id * map->dsize); + return (struct set_elem *)((void *)map->members + id * map->dsize); +} + +static inline struct set_telem * +list_set_telem(const struct list_set *map, u32 id) +{ + return (struct set_telem *)((void *)map->members + id * map->dsize); } static inline bool list_set_timeout(const struct list_set *map, u32 id) { - const struct set_telem *elem = - (const struct set_telem *) list_set_elem(map, id); + const struct set_telem *elem = list_set_telem(map, id); return ip_set_timeout_test(elem->timeout); } @@ -58,19 +63,11 @@ list_set_timeout(const struct list_set *map, u32 id) static inline bool list_set_expired(const struct list_set *map, u32 id) { - const struct set_telem *elem = - (const struct set_telem *) list_set_elem(map, id); + const struct set_telem *elem = list_set_telem(map, id); return ip_set_timeout_expired(elem->timeout); } -static inline int -list_set_exist(const struct set_telem *elem) -{ - return elem->id != IPSET_INVALID_ID && - !ip_set_timeout_expired(elem->timeout); -} - /* Set list without and with timeout */ static int @@ -146,11 +143,11 @@ list_elem_tadd(struct list_set *map, u32 i, ip_set_id_t id, struct set_telem *e; for (; i < map->size; i++) { - e = (struct set_telem *)list_set_elem(map, i); + e = list_set_telem(map, i); swap(e->id, id); + swap(e->timeout, timeout); if (e->id == IPSET_INVALID_ID) break; - swap(e->timeout, timeout); } } @@ -164,7 +161,7 @@ list_set_add(struct list_set *map, u32 i, ip_set_id_t id, /* Last element replaced: e.g. add new,before,last */ ip_set_put_byindex(e->id); if (with_timeout(map->timeout)) - list_elem_tadd(map, i, id, timeout); + list_elem_tadd(map, i, id, ip_set_timeout_set(timeout)); else list_elem_add(map, i, id); @@ -172,11 +169,11 @@ list_set_add(struct list_set *map, u32 i, ip_set_id_t id, } static int -list_set_del(struct list_set *map, ip_set_id_t id, u32 i) +list_set_del(struct list_set *map, u32 i) { struct set_elem *a = list_set_elem(map, i), *b; - ip_set_put_byindex(id); + ip_set_put_byindex(a->id); for (; i < map->size - 1; i++) { b = list_set_elem(map, i + 1); @@ -308,11 +305,11 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[], (before == 0 || (before > 0 && next_id_eq(map, i, refid)))) - ret = list_set_del(map, id, i); + ret = list_set_del(map, i); else if (before < 0 && elem->id == refid && next_id_eq(map, i, id)) - ret = list_set_del(map, id, i + 1); + ret = list_set_del(map, i + 1); } break; default: @@ -369,8 +366,7 @@ list_set_head(struct ip_set *set, struct sk_buff *skb) NLA_PUT_NET32(skb, IPSET_ATTR_SIZE, htonl(map->size)); if (with_timeout(map->timeout)) NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout)); - NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, - htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)); NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, htonl(sizeof(*map) + map->size * map->dsize)); ipset_nest_end(skb, nested); @@ -461,16 +457,13 @@ list_set_gc(unsigned long ul_set) struct set_telem *e; u32 i; - /* We run parallel with other readers (test element) - * but adding/deleting new entries is locked out */ - read_lock_bh(&set->lock); - for (i = map->size - 1; i >= 0; i--) { - e = (struct set_telem *) list_set_elem(map, i); - if (e->id != IPSET_INVALID_ID && - list_set_expired(map, i)) - list_set_del(map, e->id, i); + write_lock_bh(&set->lock); + for (i = 0; i < map->size; i++) { + e = list_set_telem(map, i); + if (e->id != IPSET_INVALID_ID && list_set_expired(map, i)) + list_set_del(map, i); } - read_unlock_bh(&set->lock); + write_unlock_bh(&set->lock); map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ; add_timer(&map->gc); diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 5c48ffb60c2..059af3120be 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -43,6 +43,8 @@ EXPORT_SYMBOL(register_ip_vs_app); EXPORT_SYMBOL(unregister_ip_vs_app); EXPORT_SYMBOL(register_ip_vs_app_inc); +static DEFINE_MUTEX(__ip_vs_app_mutex); + /* * Get an ip_vs_app object */ @@ -167,14 +169,13 @@ int register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto, __u16 port) { - struct netns_ipvs *ipvs = net_ipvs(net); int result; - mutex_lock(&ipvs->app_mutex); + mutex_lock(&__ip_vs_app_mutex); result = ip_vs_app_inc_new(net, app, proto, port); - mutex_unlock(&ipvs->app_mutex); + mutex_unlock(&__ip_vs_app_mutex); return result; } @@ -189,11 +190,11 @@ int register_ip_vs_app(struct net *net, struct ip_vs_app *app) /* increase the module use count */ ip_vs_use_count_inc(); - mutex_lock(&ipvs->app_mutex); + mutex_lock(&__ip_vs_app_mutex); list_add(&app->a_list, &ipvs->app_list); - mutex_unlock(&ipvs->app_mutex); + mutex_unlock(&__ip_vs_app_mutex); return 0; } @@ -205,10 +206,9 @@ int register_ip_vs_app(struct net *net, struct ip_vs_app *app) */ void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app) { - struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_app *inc, *nxt; - mutex_lock(&ipvs->app_mutex); + mutex_lock(&__ip_vs_app_mutex); list_for_each_entry_safe(inc, nxt, &app->incs_list, a_list) { ip_vs_app_inc_release(net, inc); @@ -216,7 +216,7 @@ void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app) list_del(&app->a_list); - mutex_unlock(&ipvs->app_mutex); + mutex_unlock(&__ip_vs_app_mutex); /* decrease the module use count */ ip_vs_use_count_dec(); @@ -501,7 +501,7 @@ static void *ip_vs_app_seq_start(struct seq_file *seq, loff_t *pos) struct net *net = seq_file_net(seq); struct netns_ipvs *ipvs = net_ipvs(net); - mutex_lock(&ipvs->app_mutex); + mutex_lock(&__ip_vs_app_mutex); return *pos ? ip_vs_app_idx(ipvs, *pos - 1) : SEQ_START_TOKEN; } @@ -535,9 +535,7 @@ static void *ip_vs_app_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void ip_vs_app_seq_stop(struct seq_file *seq, void *v) { - struct netns_ipvs *ipvs = net_ipvs(seq_file_net(seq)); - - mutex_unlock(&ipvs->app_mutex); + mutex_unlock(&__ip_vs_app_mutex); } static int ip_vs_app_seq_show(struct seq_file *seq, void *v) @@ -574,40 +572,30 @@ static const struct file_operations ip_vs_app_fops = { .open = ip_vs_app_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, }; #endif -static int __net_init __ip_vs_app_init(struct net *net) +int __net_init __ip_vs_app_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); INIT_LIST_HEAD(&ipvs->app_list); - __mutex_init(&ipvs->app_mutex, "ipvs->app_mutex", &ipvs->app_key); proc_net_fops_create(net, "ip_vs_app", 0, &ip_vs_app_fops); return 0; } -static void __net_exit __ip_vs_app_cleanup(struct net *net) +void __net_exit __ip_vs_app_cleanup(struct net *net) { proc_net_remove(net, "ip_vs_app"); } -static struct pernet_operations ip_vs_app_ops = { - .init = __ip_vs_app_init, - .exit = __ip_vs_app_cleanup, -}; - int __init ip_vs_app_init(void) { - int rv; - - rv = register_pernet_subsys(&ip_vs_app_ops); - return rv; + return 0; } void ip_vs_app_cleanup(void) { - unregister_pernet_subsys(&ip_vs_app_ops); } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index f289306cbf1..bf28ac2fc99 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -595,7 +595,7 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) atomic_inc(&dest->inactconns); } else { /* It is a persistent connection/template, so increase - the peristent connection counter */ + the persistent connection counter */ atomic_inc(&dest->persistconns); } @@ -657,7 +657,7 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp) } } else { /* It is a persistent connection/template, so decrease - the peristent connection counter */ + the persistent connection counter */ atomic_dec(&dest->persistconns); } @@ -1046,7 +1046,7 @@ static const struct file_operations ip_vs_conn_fops = { .open = ip_vs_conn_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, }; static const char *ip_vs_origin_name(unsigned flags) @@ -1114,7 +1114,7 @@ static const struct file_operations ip_vs_conn_sync_fops = { .open = ip_vs_conn_sync_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, }; #endif @@ -1258,22 +1258,17 @@ int __net_init __ip_vs_conn_init(struct net *net) return 0; } -static void __net_exit __ip_vs_conn_cleanup(struct net *net) +void __net_exit __ip_vs_conn_cleanup(struct net *net) { /* flush all the connection entries first */ ip_vs_conn_flush(net); proc_net_remove(net, "ip_vs_conn"); proc_net_remove(net, "ip_vs_conn_sync"); } -static struct pernet_operations ipvs_conn_ops = { - .init = __ip_vs_conn_init, - .exit = __ip_vs_conn_cleanup, -}; int __init ip_vs_conn_init(void) { int idx; - int retc; /* Compute size and mask */ ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; @@ -1309,17 +1304,14 @@ int __init ip_vs_conn_init(void) rwlock_init(&__ip_vs_conntbl_lock_array[idx].l); } - retc = register_pernet_subsys(&ipvs_conn_ops); - /* calculate the random value for connection hash */ get_random_bytes(&ip_vs_conn_rnd, sizeof(ip_vs_conn_rnd)); - return retc; + return 0; } void ip_vs_conn_cleanup(void) { - unregister_pernet_subsys(&ipvs_conn_ops); /* Release the empty cache */ kmem_cache_destroy(ip_vs_conn_cachep); vfree(ip_vs_conn_tab); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 07accf6b240..a74dae6c5db 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1113,6 +1113,9 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) return NF_ACCEPT; net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { @@ -1343,6 +1346,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) return NF_ACCEPT; /* The packet looks wrong, ignore */ net = skb_net(skb); + pd = ip_vs_proto_data_get(net, cih->protocol); if (!pd) return NF_ACCEPT; @@ -1529,6 +1533,11 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) IP_VS_DBG_ADDR(af, &iph.daddr), hooknum); return NF_ACCEPT; } + /* ipvs enabled in this netns ? */ + net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); /* Bad... Do not break raw sockets */ @@ -1562,7 +1571,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } - net = skb_net(skb); /* Protocol supported? */ pd = ip_vs_proto_data_get(net, iph.protocol); if (unlikely(!pd)) @@ -1588,7 +1596,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) } IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet"); - net = skb_net(skb); ipvs = net_ipvs(net); /* Check the server status */ if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { @@ -1743,10 +1750,16 @@ ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb, int (*okfn)(struct sk_buff *)) { int r; + struct net *net; if (ip_hdr(skb)->protocol != IPPROTO_ICMP) return NF_ACCEPT; + /* ipvs enabled in this netns ? */ + net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + return ip_vs_in_icmp(skb, &r, hooknum); } @@ -1757,10 +1770,16 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb, int (*okfn)(struct sk_buff *)) { int r; + struct net *net; if (ipv6_hdr(skb)->nexthdr != IPPROTO_ICMPV6) return NF_ACCEPT; + /* ipvs enabled in this netns ? */ + net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + return ip_vs_in_icmp_v6(skb, &r, hooknum); } #endif @@ -1884,19 +1903,70 @@ static int __net_init __ip_vs_init(struct net *net) pr_err("%s(): no memory.\n", __func__); return -ENOMEM; } + /* Hold the beast until a service is registerd */ + ipvs->enable = 0; ipvs->net = net; /* Counters used for creating unique names */ ipvs->gen = atomic_read(&ipvs_netns_cnt); atomic_inc(&ipvs_netns_cnt); net->ipvs = ipvs; + + if (__ip_vs_estimator_init(net) < 0) + goto estimator_fail; + + if (__ip_vs_control_init(net) < 0) + goto control_fail; + + if (__ip_vs_protocol_init(net) < 0) + goto protocol_fail; + + if (__ip_vs_app_init(net) < 0) + goto app_fail; + + if (__ip_vs_conn_init(net) < 0) + goto conn_fail; + + if (__ip_vs_sync_init(net) < 0) + goto sync_fail; + printk(KERN_INFO "IPVS: Creating netns size=%zu id=%d\n", sizeof(struct netns_ipvs), ipvs->gen); return 0; +/* + * Error handling + */ + +sync_fail: + __ip_vs_conn_cleanup(net); +conn_fail: + __ip_vs_app_cleanup(net); +app_fail: + __ip_vs_protocol_cleanup(net); +protocol_fail: + __ip_vs_control_cleanup(net); +control_fail: + __ip_vs_estimator_cleanup(net); +estimator_fail: + return -ENOMEM; } static void __net_exit __ip_vs_cleanup(struct net *net) { - IP_VS_DBG(10, "ipvs netns %d released\n", net_ipvs(net)->gen); + __ip_vs_service_cleanup(net); /* ip_vs_flush() with locks */ + __ip_vs_conn_cleanup(net); + __ip_vs_app_cleanup(net); + __ip_vs_protocol_cleanup(net); + __ip_vs_control_cleanup(net); + __ip_vs_estimator_cleanup(net); + IP_VS_DBG(2, "ipvs netns %d released\n", net_ipvs(net)->gen); +} + +static void __net_exit __ip_vs_dev_cleanup(struct net *net) +{ + EnterFunction(2); + net_ipvs(net)->enable = 0; /* Disable packet reception */ + __ip_vs_sync_cleanup(net); + LeaveFunction(2); } static struct pernet_operations ipvs_core_ops = { @@ -1906,6 +1976,10 @@ static struct pernet_operations ipvs_core_ops = { .size = sizeof(struct netns_ipvs), }; +static struct pernet_operations ipvs_core_dev_ops = { + .exit = __ip_vs_dev_cleanup, +}; + /* * Initialize IP Virtual Server */ @@ -1913,10 +1987,6 @@ static int __init ip_vs_init(void) { int ret; - ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */ - if (ret < 0) - return ret; - ip_vs_estimator_init(); ret = ip_vs_control_init(); if (ret < 0) { @@ -1944,15 +2014,28 @@ static int __init ip_vs_init(void) goto cleanup_conn; } + ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */ + if (ret < 0) + goto cleanup_sync; + + ret = register_pernet_device(&ipvs_core_dev_ops); + if (ret < 0) + goto cleanup_sub; + ret = nf_register_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); if (ret < 0) { pr_err("can't register hooks.\n"); - goto cleanup_sync; + goto cleanup_dev; } pr_info("ipvs loaded.\n"); + return ret; +cleanup_dev: + unregister_pernet_device(&ipvs_core_dev_ops); +cleanup_sub: + unregister_pernet_subsys(&ipvs_core_ops); cleanup_sync: ip_vs_sync_cleanup(); cleanup_conn: @@ -1964,20 +2047,20 @@ cleanup_sync: ip_vs_control_cleanup(); cleanup_estimator: ip_vs_estimator_cleanup(); - unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ return ret; } static void __exit ip_vs_cleanup(void) { nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); + unregister_pernet_device(&ipvs_core_dev_ops); + unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ ip_vs_sync_cleanup(); ip_vs_conn_cleanup(); ip_vs_app_cleanup(); ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); ip_vs_estimator_cleanup(); - unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ pr_info("ipvs unloaded.\n"); } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index b799cea31f9..37890f228b1 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -69,6 +69,11 @@ int ip_vs_get_debug_level(void) } #endif + +/* Protos */ +static void __ip_vs_del_service(struct ip_vs_service *svc); + + #ifdef CONFIG_IP_VS_IPV6 /* Taken from rt6_fill_node() in net/ipv6/route.c, is there a better way? */ static int __ip_vs_addr_is_local_v6(struct net *net, @@ -1214,6 +1219,8 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, write_unlock_bh(&__ip_vs_svc_lock); *svc_p = svc; + /* Now there is a service - full throttle */ + ipvs->enable = 1; return 0; @@ -1472,6 +1479,84 @@ static int ip_vs_flush(struct net *net) return 0; } +/* + * Delete service by {netns} in the service table. + * Called by __ip_vs_cleanup() + */ +void __ip_vs_service_cleanup(struct net *net) +{ + EnterFunction(2); + /* Check for "full" addressed entries */ + mutex_lock(&__ip_vs_mutex); + ip_vs_flush(net); + mutex_unlock(&__ip_vs_mutex); + LeaveFunction(2); +} +/* + * Release dst hold by dst_cache + */ +static inline void +__ip_vs_dev_reset(struct ip_vs_dest *dest, struct net_device *dev) +{ + spin_lock_bh(&dest->dst_lock); + if (dest->dst_cache && dest->dst_cache->dev == dev) { + IP_VS_DBG_BUF(3, "Reset dev:%s dest %s:%u ,dest->refcnt=%d\n", + dev->name, + IP_VS_DBG_ADDR(dest->af, &dest->addr), + ntohs(dest->port), + atomic_read(&dest->refcnt)); + ip_vs_dst_reset(dest); + } + spin_unlock_bh(&dest->dst_lock); + +} +/* + * Netdev event receiver + * Currently only NETDEV_UNREGISTER is handled, i.e. if we hold a reference to + * a device that is "unregister" it must be released. + */ +static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct net_device *dev = ptr; + struct net *net = dev_net(dev); + struct ip_vs_service *svc; + struct ip_vs_dest *dest; + unsigned int idx; + + if (event != NETDEV_UNREGISTER) + return NOTIFY_DONE; + IP_VS_DBG(3, "%s() dev=%s\n", __func__, dev->name); + EnterFunction(2); + mutex_lock(&__ip_vs_mutex); + for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { + list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { + if (net_eq(svc->net, net)) { + list_for_each_entry(dest, &svc->destinations, + n_list) { + __ip_vs_dev_reset(dest, dev); + } + } + } + + list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { + if (net_eq(svc->net, net)) { + list_for_each_entry(dest, &svc->destinations, + n_list) { + __ip_vs_dev_reset(dest, dev); + } + } + + } + } + + list_for_each_entry(dest, &net_ipvs(net)->dest_trash, n_list) { + __ip_vs_dev_reset(dest, dev); + } + mutex_unlock(&__ip_vs_mutex); + LeaveFunction(2); + return NOTIFY_DONE; +} /* * Zero counters in a service or all services @@ -1981,7 +2066,7 @@ static const struct file_operations ip_vs_info_fops = { .open = ip_vs_info_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = seq_release_net, }; #endif @@ -2024,7 +2109,7 @@ static const struct file_operations ip_vs_stats_fops = { .open = ip_vs_stats_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = single_release_net, }; static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v) @@ -2093,7 +2178,7 @@ static const struct file_operations ip_vs_stats_percpu_fops = { .open = ip_vs_stats_percpu_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = single_release_net, }; #endif @@ -3120,7 +3205,7 @@ nla_put_failure: static int ip_vs_genl_dump_daemons(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb_net(skb); + struct net *net = skb_sknet(skb); struct netns_ipvs *ipvs = net_ipvs(net); mutex_lock(&__ip_vs_mutex); @@ -3588,6 +3673,10 @@ void __net_init __ip_vs_control_cleanup_sysctl(struct net *net) { } #endif +static struct notifier_block ip_vs_dst_notifier = { + .notifier_call = ip_vs_dst_event, +}; + int __net_init __ip_vs_control_init(struct net *net) { int idx; @@ -3605,7 +3694,7 @@ int __net_init __ip_vs_control_init(struct net *net) /* procfs stats */ ipvs->tot_stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats); - if (ipvs->tot_stats.cpustats) { + if (!ipvs->tot_stats.cpustats) { pr_err("%s(): alloc_percpu.\n", __func__); return -ENOMEM; } @@ -3626,7 +3715,7 @@ err: return -ENOMEM; } -static void __net_exit __ip_vs_control_cleanup(struct net *net) +void __net_exit __ip_vs_control_cleanup(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -3639,11 +3728,6 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net) free_percpu(ipvs->tot_stats.cpustats); } -static struct pernet_operations ipvs_control_ops = { - .init = __ip_vs_control_init, - .exit = __ip_vs_control_cleanup, -}; - int __init ip_vs_control_init(void) { int idx; @@ -3657,33 +3741,32 @@ int __init ip_vs_control_init(void) INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]); } - ret = register_pernet_subsys(&ipvs_control_ops); - if (ret) { - pr_err("cannot register namespace.\n"); - goto err; - } - smp_wmb(); /* Do we really need it now ? */ ret = nf_register_sockopt(&ip_vs_sockopts); if (ret) { pr_err("cannot register sockopt.\n"); - goto err_net; + goto err_sock; } ret = ip_vs_genl_register(); if (ret) { pr_err("cannot register Generic Netlink interface.\n"); - nf_unregister_sockopt(&ip_vs_sockopts); - goto err_net; + goto err_genl; } + ret = register_netdevice_notifier(&ip_vs_dst_notifier); + if (ret < 0) + goto err_notf; + LeaveFunction(2); return 0; -err_net: - unregister_pernet_subsys(&ipvs_control_ops); -err: +err_notf: + ip_vs_genl_unregister(); +err_genl: + nf_unregister_sockopt(&ip_vs_sockopts); +err_sock: return ret; } @@ -3691,7 +3774,6 @@ err: void ip_vs_control_cleanup(void) { EnterFunction(2); - unregister_pernet_subsys(&ipvs_control_ops); ip_vs_genl_unregister(); nf_unregister_sockopt(&ip_vs_sockopts); LeaveFunction(2); diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 8c8766ca56a..508cce98777 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -192,7 +192,7 @@ void ip_vs_read_estimator(struct ip_vs_stats_user *dst, dst->outbps = (e->outbps + 0xF) >> 5; } -static int __net_init __ip_vs_estimator_init(struct net *net) +int __net_init __ip_vs_estimator_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -203,24 +203,16 @@ static int __net_init __ip_vs_estimator_init(struct net *net) return 0; } -static void __net_exit __ip_vs_estimator_exit(struct net *net) +void __net_exit __ip_vs_estimator_cleanup(struct net *net) { del_timer_sync(&net_ipvs(net)->est_timer); } -static struct pernet_operations ip_vs_app_ops = { - .init = __ip_vs_estimator_init, - .exit = __ip_vs_estimator_exit, -}; int __init ip_vs_estimator_init(void) { - int rv; - - rv = register_pernet_subsys(&ip_vs_app_ops); - return rv; + return 0; } void ip_vs_estimator_cleanup(void) { - unregister_pernet_subsys(&ip_vs_app_ops); } diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index f276df9896b..87e40ea77a9 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -131,7 +131,7 @@ static inline void ip_vs_lblc_free(struct ip_vs_lblc_entry *en) { list_del(&en->list); /* - * We don't kfree dest because it is refered either by its service + * We don't kfree dest because it is referred either by its service * or the trash dest list. */ atomic_dec(&en->dest->refcnt); diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index cb1c9913d38..90f618ab6dd 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -152,7 +152,7 @@ static void ip_vs_dest_set_eraseall(struct ip_vs_dest_set *set) write_lock(&set->lock); list_for_each_entry_safe(e, ep, &set->list, list) { /* - * We don't kfree dest because it is refered either + * We don't kfree dest because it is referred either * by its service or by the trash dest list. */ atomic_dec(&e->dest->refcnt); diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index 17484a4416e..eb86028536f 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -316,7 +316,7 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp, /* * per network name-space init */ -static int __net_init __ip_vs_protocol_init(struct net *net) +int __net_init __ip_vs_protocol_init(struct net *net) { #ifdef CONFIG_IP_VS_PROTO_TCP register_ip_vs_proto_netns(net, &ip_vs_protocol_tcp); @@ -336,7 +336,7 @@ static int __net_init __ip_vs_protocol_init(struct net *net) return 0; } -static void __net_exit __ip_vs_protocol_cleanup(struct net *net) +void __net_exit __ip_vs_protocol_cleanup(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_proto_data *pd; @@ -349,11 +349,6 @@ static void __net_exit __ip_vs_protocol_cleanup(struct net *net) } } -static struct pernet_operations ipvs_proto_ops = { - .init = __ip_vs_protocol_init, - .exit = __ip_vs_protocol_cleanup, -}; - int __init ip_vs_protocol_init(void) { char protocols[64]; @@ -382,7 +377,6 @@ int __init ip_vs_protocol_init(void) REGISTER_PROTOCOL(&ip_vs_protocol_esp); #endif pr_info("Registered protocols (%s)\n", &protocols[2]); - return register_pernet_subsys(&ipvs_proto_ops); return 0; } @@ -393,7 +387,6 @@ void ip_vs_protocol_cleanup(void) struct ip_vs_protocol *pp; int i; - unregister_pernet_subsys(&ipvs_proto_ops); /* unregister all the ipvs protocols */ for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { while ((pp = ip_vs_proto_table[i]) != NULL) diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index b027ccc49f4..d12ed53ec95 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -566,7 +566,7 @@ static struct ipvs_sctp_nextstate * SHUTDOWN sent from the client, waitinf for SHUT ACK from the server */ /* - * We recieved the data chuck, keep the state unchanged. I assume + * We received the data chuck, keep the state unchanged. I assume * that still data chuncks can be received by both the peers in * SHUDOWN state */ @@ -633,7 +633,7 @@ static struct ipvs_sctp_nextstate * SHUTDOWN sent from the server, waitinf for SHUTDOWN ACK from client */ /* - * We recieved the data chuck, keep the state unchanged. I assume + * We received the data chuck, keep the state unchanged. I assume * that still data chuncks can be received by both the peers in * SHUDOWN state */ @@ -701,7 +701,7 @@ static struct ipvs_sctp_nextstate * SHUTDOWN ACK from the client, awaiting for SHUTDOWN COM from server */ /* - * We recieved the data chuck, keep the state unchanged. I assume + * We received the data chuck, keep the state unchanged. I assume * that still data chuncks can be received by both the peers in * SHUDOWN state */ @@ -771,7 +771,7 @@ static struct ipvs_sctp_nextstate * SHUTDOWN ACK from the server, awaiting for SHUTDOWN COM from client */ /* - * We recieved the data chuck, keep the state unchanged. I assume + * We received the data chuck, keep the state unchanged. I assume * that still data chuncks can be received by both the peers in * SHUDOWN state */ diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 3e7961e85e9..e292e5bddc7 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1303,13 +1303,18 @@ static struct socket *make_send_sock(struct net *net) struct socket *sock; int result; - /* First create a socket */ - result = __sock_create(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock, 1); + /* First create a socket move it to right name space later */ + result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); } - + /* + * Kernel sockets that are a part of a namespace, should not + * hold a reference to a namespace in order to allow to stop it. + * After sk_change_net should be released using sk_release_kernel. + */ + sk_change_net(sock->sk, net); result = set_mcast_if(sock->sk, ipvs->master_mcast_ifn); if (result < 0) { pr_err("Error setting outbound mcast interface\n"); @@ -1334,8 +1339,8 @@ static struct socket *make_send_sock(struct net *net) return sock; - error: - sock_release(sock); +error: + sk_release_kernel(sock->sk); return ERR_PTR(result); } @@ -1350,12 +1355,17 @@ static struct socket *make_receive_sock(struct net *net) int result; /* First create a socket */ - result = __sock_create(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock, 1); + result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); } - + /* + * Kernel sockets that are a part of a namespace, should not + * hold a reference to a namespace in order to allow to stop it. + * After sk_change_net should be released using sk_release_kernel. + */ + sk_change_net(sock->sk, net); /* it is equivalent to the REUSEADDR option in user-space */ sock->sk->sk_reuse = 1; @@ -1377,8 +1387,8 @@ static struct socket *make_receive_sock(struct net *net) return sock; - error: - sock_release(sock); +error: + sk_release_kernel(sock->sk); return ERR_PTR(result); } @@ -1473,7 +1483,7 @@ static int sync_thread_master(void *data) ip_vs_sync_buff_release(sb); /* release the sending multicast socket */ - sock_release(tinfo->sock); + sk_release_kernel(tinfo->sock->sk); kfree(tinfo); return 0; @@ -1513,7 +1523,7 @@ static int sync_thread_backup(void *data) } /* release the sending multicast socket */ - sock_release(tinfo->sock); + sk_release_kernel(tinfo->sock->sk); kfree(tinfo->buf); kfree(tinfo); @@ -1601,7 +1611,7 @@ outtinfo: outbuf: kfree(buf); outsocket: - sock_release(sock); + sk_release_kernel(sock->sk); out: return result; } @@ -1610,6 +1620,7 @@ out: int stop_sync_thread(struct net *net, int state) { struct netns_ipvs *ipvs = net_ipvs(net); + int retc = -EINVAL; IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current)); @@ -1629,7 +1640,7 @@ int stop_sync_thread(struct net *net, int state) spin_lock_bh(&ipvs->sync_lock); ipvs->sync_state &= ~IP_VS_STATE_MASTER; spin_unlock_bh(&ipvs->sync_lock); - kthread_stop(ipvs->master_thread); + retc = kthread_stop(ipvs->master_thread); ipvs->master_thread = NULL; } else if (state == IP_VS_STATE_BACKUP) { if (!ipvs->backup_thread) @@ -1639,22 +1650,20 @@ int stop_sync_thread(struct net *net, int state) task_pid_nr(ipvs->backup_thread)); ipvs->sync_state &= ~IP_VS_STATE_BACKUP; - kthread_stop(ipvs->backup_thread); + retc = kthread_stop(ipvs->backup_thread); ipvs->backup_thread = NULL; - } else { - return -EINVAL; } /* decrease the module use count */ ip_vs_use_count_dec(); - return 0; + return retc; } /* * Initialize data struct for each netns */ -static int __net_init __ip_vs_sync_init(struct net *net) +int __net_init __ip_vs_sync_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -1668,24 +1677,24 @@ static int __net_init __ip_vs_sync_init(struct net *net) return 0; } -static void __ip_vs_sync_cleanup(struct net *net) +void __ip_vs_sync_cleanup(struct net *net) { - stop_sync_thread(net, IP_VS_STATE_MASTER); - stop_sync_thread(net, IP_VS_STATE_BACKUP); -} + int retc; -static struct pernet_operations ipvs_sync_ops = { - .init = __ip_vs_sync_init, - .exit = __ip_vs_sync_cleanup, -}; + retc = stop_sync_thread(net, IP_VS_STATE_MASTER); + if (retc && retc != -ESRCH) + pr_err("Failed to stop Master Daemon\n"); + retc = stop_sync_thread(net, IP_VS_STATE_BACKUP); + if (retc && retc != -ESRCH) + pr_err("Failed to stop Backup Daemon\n"); +} int __init ip_vs_sync_init(void) { - return register_pernet_subsys(&ipvs_sync_ops); + return 0; } void ip_vs_sync_cleanup(void) { - unregister_pernet_subsys(&ipvs_sync_ops); } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 941286ca911..2e1c11f7841 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -453,7 +453,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) REJECT will give spurious warnings here. */ /* NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 1); */ - /* No external references means noone else could have + /* No external references means no one else could have confirmed us. */ NF_CT_ASSERT(!nf_ct_is_confirmed(ct)); pr_debug("Confirming conntrack %p\n", ct); @@ -901,7 +901,7 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, ret = l3proto->get_l4proto(skb, skb_network_offset(skb), &dataoff, &protonum); if (ret <= 0) { - pr_debug("not prepared to track yet or error occured\n"); + pr_debug("not prepared to track yet or error occurred\n"); NF_CT_STAT_INC_ATOMIC(net, error); NF_CT_STAT_INC_ATOMIC(net, invalid); ret = -ret; diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c index 867882313e4..bcd5ed6b713 100644 --- a/net/netfilter/nf_conntrack_h323_asn1.c +++ b/net/netfilter/nf_conntrack_h323_asn1.c @@ -631,7 +631,7 @@ static int decode_seqof(bitstr_t *bs, const struct field_t *f, CHECK_BOUND(bs, 2); count = *bs->cur++; count <<= 8; - count = *bs->cur++; + count += *bs->cur++; break; case SEMI: BYTE_ALIGN(bs); diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 533a183e666..18b2ce5c8ce 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -731,10 +731,10 @@ static int callforward_do_filter(const union nf_inet_addr *src, memset(&fl2, 0, sizeof(fl2)); fl2.daddr = dst->ip; - if (!afinfo->route((struct dst_entry **)&rt1, - flowi4_to_flowi(&fl1))) { - if (!afinfo->route((struct dst_entry **)&rt2, - flowi4_to_flowi(&fl2))) { + if (!afinfo->route(&init_net, (struct dst_entry **)&rt1, + flowi4_to_flowi(&fl1), false)) { + if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, + flowi4_to_flowi(&fl2), false)) { if (rt1->rt_gateway == rt2->rt_gateway && rt1->dst.dev == rt2->dst.dev) ret = 1; @@ -755,10 +755,10 @@ static int callforward_do_filter(const union nf_inet_addr *src, memset(&fl2, 0, sizeof(fl2)); ipv6_addr_copy(&fl2.daddr, &dst->in6); - if (!afinfo->route((struct dst_entry **)&rt1, - flowi6_to_flowi(&fl1))) { - if (!afinfo->route((struct dst_entry **)&rt2, - flowi6_to_flowi(&fl2))) { + if (!afinfo->route(&init_net, (struct dst_entry **)&rt1, + flowi6_to_flowi(&fl1), false)) { + if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, + flowi6_to_flowi(&fl2), false)) { if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway, sizeof(rt1->rt6i_gateway)) && rt1->dst.dev == rt2->dst.dev) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 30bf8a167fc..482e90c6185 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1334,6 +1334,7 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, struct nf_conn *ct; int err = -EINVAL; struct nf_conntrack_helper *helper; + struct nf_conn_tstamp *tstamp; ct = nf_conntrack_alloc(net, zone, otuple, rtuple, GFP_ATOMIC); if (IS_ERR(ct)) @@ -1451,6 +1452,9 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, __set_bit(IPS_EXPECTED_BIT, &ct->status); ct->master = master_ct; } + tstamp = nf_conn_tstamp_find(ct); + if (tstamp) + tstamp->start = ktime_to_ns(ktime_get_real()); add_timer(&ct->timeout); nf_conntrack_hash_insert(ct); diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 9ae57c57c50..2e664a69d7d 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -98,7 +98,7 @@ static const char * const dccp_state_names[] = { #define sIV CT_DCCP_INVALID /* - * DCCP state transistion table + * DCCP state transition table * * The assumption is the same as for TCP tracking: * diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 6f4ee70f460..6772b115465 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -107,9 +107,9 @@ static const u8 sctp_conntracks[2][9][SCTP_CONNTRACK_MAX] = { /* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, /* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA}, /* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA}, -/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Cant have Stale cookie*/ +/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Can't have Stale cookie*/ /* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA},/* 5.2.4 - Big TODO */ -/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Cant come in orig dir */ +/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Can't come in orig dir */ /* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL} }, { @@ -121,7 +121,7 @@ static const u8 sctp_conntracks[2][9][SCTP_CONNTRACK_MAX] = { /* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA}, /* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA}, /* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA}, -/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Cant come in reply dir */ +/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Can't come in reply dir */ /* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA}, /* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL} } diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index bcf47eb518e..237cc1981b8 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -707,7 +707,7 @@ static const char *ct_sdp_header_search(const char *dptr, const char *limit, } /* Locate a SDP header (optionally a substring within the header value), - * optionally stopping at the first occurence of the term header, parse + * optionally stopping at the first occurrence of the term header, parse * it and return the offset and length of the data we're interested in. */ int ct_sip_get_sdp_header(const struct nf_conn *ct, const char *dptr, diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 5ab22e2bbd7..5b466cd1272 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -134,7 +134,7 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_afinfo *afinfo; const struct nf_queue_handler *qh; - /* QUEUE == DROP if noone is waiting, to be safe. */ + /* QUEUE == DROP if no one is waiting, to be safe. */ rcu_read_lock(); qh = rcu_dereference(queue_handler[pf]); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index a9adf4c6b29..8a025a585d2 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -455,6 +455,7 @@ void xt_compat_flush_offsets(u_int8_t af) vfree(xt[af].compat_tab); xt[af].compat_tab = NULL; xt[af].number = 0; + xt[af].cur = 0; } } EXPORT_SYMBOL_GPL(xt_compat_flush_offsets); @@ -473,8 +474,7 @@ int xt_compat_calc_jump(u_int8_t af, unsigned int offset) else return mid ? tmp[mid - 1].delta : 0; } - WARN_ON_ONCE(1); - return 0; + return left ? tmp[left - 1].delta : 0; } EXPORT_SYMBOL_GPL(xt_compat_calc_jump); diff --git a/net/netfilter/xt_DSCP.c b/net/netfilter/xt_DSCP.c index 0a229191e55..ae8271652ef 100644 --- a/net/netfilter/xt_DSCP.c +++ b/net/netfilter/xt_DSCP.c @@ -99,7 +99,7 @@ tos_tg6(struct sk_buff *skb, const struct xt_action_param *par) u_int8_t orig, nv; orig = ipv6_get_dsfield(iph); - nv = (orig & info->tos_mask) ^ info->tos_value; + nv = (orig & ~info->tos_mask) ^ info->tos_value; if (orig != nv) { if (!skb_make_writable(skb, sizeof(struct iphdr))) diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 6e6b46cb1db..9e63b43faee 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -166,7 +166,7 @@ static u_int32_t tcpmss_reverse_mtu(const struct sk_buff *skb, rcu_read_lock(); ai = nf_get_afinfo(family); if (ai != NULL) - ai->route((struct dst_entry **)&rt, &fl); + ai->route(&init_net, (struct dst_entry **)&rt, &fl, false); rcu_read_unlock(); if (rt != NULL) { diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c index 2220b85e951..b77d383cec7 100644 --- a/net/netfilter/xt_addrtype.c +++ b/net/netfilter/xt_addrtype.c @@ -32,11 +32,32 @@ MODULE_ALIAS("ipt_addrtype"); MODULE_ALIAS("ip6t_addrtype"); #if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) -static u32 xt_addrtype_rt6_to_type(const struct rt6_info *rt) +static u32 match_lookup_rt6(struct net *net, const struct net_device *dev, + const struct in6_addr *addr) { + const struct nf_afinfo *afinfo; + struct flowi6 flow; + struct rt6_info *rt; u32 ret; + int route_err; - if (!rt) + memset(&flow, 0, sizeof(flow)); + ipv6_addr_copy(&flow.daddr, addr); + if (dev) + flow.flowi6_oif = dev->ifindex; + + rcu_read_lock(); + + afinfo = nf_get_afinfo(NFPROTO_IPV6); + if (afinfo != NULL) + route_err = afinfo->route(net, (struct dst_entry **)&rt, + flowi6_to_flowi(&flow), !!dev); + else + route_err = 1; + + rcu_read_unlock(); + + if (route_err) return XT_ADDRTYPE_UNREACHABLE; if (rt->rt6i_flags & RTF_REJECT) @@ -48,6 +69,9 @@ static u32 xt_addrtype_rt6_to_type(const struct rt6_info *rt) ret |= XT_ADDRTYPE_LOCAL; if (rt->rt6i_flags & RTF_ANYCAST) ret |= XT_ADDRTYPE_ANYCAST; + + + dst_release(&rt->dst); return ret; } @@ -65,18 +89,8 @@ static bool match_type6(struct net *net, const struct net_device *dev, return false; if ((XT_ADDRTYPE_LOCAL | XT_ADDRTYPE_ANYCAST | - XT_ADDRTYPE_UNREACHABLE) & mask) { - struct rt6_info *rt; - u32 type; - int ifindex = dev ? dev->ifindex : 0; - - rt = rt6_lookup(net, addr, NULL, ifindex, !!dev); - - type = xt_addrtype_rt6_to_type(rt); - - dst_release(&rt->dst); - return !!(mask & type); - } + XT_ADDRTYPE_UNREACHABLE) & mask) + return !!(mask & match_lookup_rt6(net, dev, addr)); return true; } diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c index 2c0086a4751..61805d7b38a 100644 --- a/net/netfilter/xt_conntrack.c +++ b/net/netfilter/xt_conntrack.c @@ -195,7 +195,7 @@ conntrack_mt(const struct sk_buff *skb, struct xt_action_param *par, return info->match_flags & XT_CONNTRACK_STATE; if ((info->match_flags & XT_CONNTRACK_DIRECTION) && (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) ^ - !!(info->invert_flags & XT_CONNTRACK_DIRECTION)) + !(info->invert_flags & XT_CONNTRACK_DIRECTION)) return false; if (info->match_flags & XT_CONNTRACK_ORIGSRC) @@ -272,11 +272,6 @@ static int conntrack_mt_check(const struct xt_mtchk_param *par) { int ret; - if (strcmp(par->table, "raw") == 0) { - pr_info("state is undetermined at the time of raw table\n"); - return -EINVAL; - } - ret = nf_ct_l3proto_try_module_get(par->family); if (ret < 0) pr_info("cannot load conntrack support for proto=%u\n", diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c index 061d48cec13..b3babaed771 100644 --- a/net/netfilter/xt_set.c +++ b/net/netfilter/xt_set.c @@ -81,6 +81,7 @@ set_match_v0_checkentry(const struct xt_mtchk_param *par) if (info->match_set.u.flags[IPSET_DIM_MAX-1] != 0) { pr_warning("Protocol error: set match dimension " "is over the limit!\n"); + ip_set_nfnl_put(info->match_set.index); return -ERANGE; } @@ -135,6 +136,8 @@ set_target_v0_checkentry(const struct xt_tgchk_param *par) if (index == IPSET_INVALID_ID) { pr_warning("Cannot find del_set index %u as target\n", info->del_set.index); + if (info->add_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->add_set.index); return -ENOENT; } } @@ -142,6 +145,10 @@ set_target_v0_checkentry(const struct xt_tgchk_param *par) info->del_set.u.flags[IPSET_DIM_MAX-1] != 0) { pr_warning("Protocol error: SET target dimension " "is over the limit!\n"); + if (info->add_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->add_set.index); + if (info->del_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->del_set.index); return -ERANGE; } @@ -192,6 +199,7 @@ set_match_checkentry(const struct xt_mtchk_param *par) if (info->match_set.dim > IPSET_DIM_MAX) { pr_warning("Protocol error: set match dimension " "is over the limit!\n"); + ip_set_nfnl_put(info->match_set.index); return -ERANGE; } @@ -219,7 +227,7 @@ set_target(struct sk_buff *skb, const struct xt_action_param *par) if (info->del_set.index != IPSET_INVALID_ID) ip_set_del(info->del_set.index, skb, par->family, - info->add_set.dim, + info->del_set.dim, info->del_set.flags); return XT_CONTINUE; @@ -245,13 +253,19 @@ set_target_checkentry(const struct xt_tgchk_param *par) if (index == IPSET_INVALID_ID) { pr_warning("Cannot find del_set index %u as target\n", info->del_set.index); + if (info->add_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->add_set.index); return -ENOENT; } } if (info->add_set.dim > IPSET_DIM_MAX || - info->del_set.flags > IPSET_DIM_MAX) { + info->del_set.dim > IPSET_DIM_MAX) { pr_warning("Protocol error: SET target dimension " "is over the limit!\n"); + if (info->add_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->add_set.index); + if (info->del_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->del_set.index); return -ERANGE; } diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index d37b7f80fa3..de0d8e4cbfb 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -109,7 +109,7 @@ static void netlbl_domhsh_free_entry(struct rcu_head *entry) * * Description: * This is the hashing function for the domain hash table, it returns the - * correct bucket number for the domain. The caller is responsibile for + * correct bucket number for the domain. The caller is responsible for * ensuring that the hash table is protected with either a RCU read lock or the * hash table lock. * @@ -134,7 +134,7 @@ static u32 netlbl_domhsh_hash(const char *key) * * Description: * Searches the domain hash table and returns a pointer to the hash table - * entry if found, otherwise NULL is returned. The caller is responsibile for + * entry if found, otherwise NULL is returned. The caller is responsible for * ensuring that the hash table is protected with either a RCU read lock or the * hash table lock. * @@ -165,7 +165,7 @@ static struct netlbl_dom_map *netlbl_domhsh_search(const char *domain) * Searches the domain hash table and returns a pointer to the hash table * entry if an exact match is found, if an exact match is not present in the * hash table then the default entry is returned if valid otherwise NULL is - * returned. The caller is responsibile ensuring that the hash table is + * returned. The caller is responsible ensuring that the hash table is * protected with either a RCU read lock or the hash table lock. * */ @@ -193,7 +193,7 @@ static struct netlbl_dom_map *netlbl_domhsh_search_def(const char *domain) * * Description: * Generate an audit record for adding a new NetLabel/LSM mapping entry with - * the given information. Caller is responsibile for holding the necessary + * the given information. Caller is responsible for holding the necessary * locks. * */ @@ -605,7 +605,7 @@ int netlbl_domhsh_remove_default(struct netlbl_audit *audit_info) * * Description: * Look through the domain hash table searching for an entry to match @domain, - * return a pointer to a copy of the entry or NULL. The caller is responsibile + * return a pointer to a copy of the entry or NULL. The caller is responsible * for ensuring that rcu_read_[un]lock() is called. * */ diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index 998e85e895d..4f251b19fbc 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -259,7 +259,7 @@ add_failure: * * Description: * This function is a helper function used by the LISTALL and LISTDEF command - * handlers. The caller is responsibile for ensuring that the RCU read lock + * handlers. The caller is responsible for ensuring that the RCU read lock * is held. Returns zero on success, negative values on failure. * */ diff --git a/net/rds/cong.c b/net/rds/cong.c index 75ea686f27d..6daaa49d133 100644 --- a/net/rds/cong.c +++ b/net/rds/cong.c @@ -33,8 +33,7 @@ #include <linux/slab.h> #include <linux/types.h> #include <linux/rbtree.h> - -#include <asm-generic/bitops/le.h> +#include <linux/bitops.h> #include "rds.h" @@ -285,7 +284,7 @@ void rds_cong_set_bit(struct rds_cong_map *map, __be16 port) i = be16_to_cpu(port) / RDS_CONG_MAP_PAGE_BITS; off = be16_to_cpu(port) % RDS_CONG_MAP_PAGE_BITS; - generic___set_le_bit(off, (void *)map->m_page_addrs[i]); + __set_bit_le(off, (void *)map->m_page_addrs[i]); } void rds_cong_clear_bit(struct rds_cong_map *map, __be16 port) @@ -299,7 +298,7 @@ void rds_cong_clear_bit(struct rds_cong_map *map, __be16 port) i = be16_to_cpu(port) / RDS_CONG_MAP_PAGE_BITS; off = be16_to_cpu(port) % RDS_CONG_MAP_PAGE_BITS; - generic___clear_le_bit(off, (void *)map->m_page_addrs[i]); + __clear_bit_le(off, (void *)map->m_page_addrs[i]); } static int rds_cong_test_bit(struct rds_cong_map *map, __be16 port) @@ -310,7 +309,7 @@ static int rds_cong_test_bit(struct rds_cong_map *map, __be16 port) i = be16_to_cpu(port) / RDS_CONG_MAP_PAGE_BITS; off = be16_to_cpu(port) % RDS_CONG_MAP_PAGE_BITS; - return generic_test_le_bit(off, (void *)map->m_page_addrs[i]); + return test_bit_le(off, (void *)map->m_page_addrs[i]); } void rds_cong_add_socket(struct rds_sock *rs) diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index c47a511f203..7c4dce8fa5e 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -355,7 +355,7 @@ void rds_ib_send_cq_comp_handler(struct ib_cq *cq, void *context) * * Conceptually, we have two counters: * - send credits: this tells us how many WRs we're allowed - * to submit without overruning the reciever's queue. For + * to submit without overruning the receiver's queue. For * each SEND WR we post, we decrement this by one. * * - posted credits: this tells us how many WRs we recently diff --git a/net/rds/iw_cm.c b/net/rds/iw_cm.c index 712cf2d1f28..3a60a15d1b4 100644 --- a/net/rds/iw_cm.c +++ b/net/rds/iw_cm.c @@ -181,7 +181,7 @@ static int rds_iw_init_qp_attrs(struct ib_qp_init_attr *attr, unsigned int send_size, recv_size; int ret; - /* The offset of 1 is to accomodate the additional ACK WR. */ + /* The offset of 1 is to accommodate the additional ACK WR. */ send_size = min_t(unsigned int, rds_iwdev->max_wrs, rds_iw_sysctl_max_send_wr + 1); recv_size = min_t(unsigned int, rds_iwdev->max_wrs, rds_iw_sysctl_max_recv_wr + 1); rds_iw_ring_resize(send_ring, send_size - 1); diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c index 59509e9a9e7..6deaa77495e 100644 --- a/net/rds/iw_rdma.c +++ b/net/rds/iw_rdma.c @@ -122,7 +122,7 @@ static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwd #else /* FIXME - needs to compare the local and remote * ipaddr/port tuple, but the ipaddr is the only - * available infomation in the rds_sock (as the rest are + * available information in the rds_sock (as the rest are * zero'ed. It doesn't appear to be properly populated * during connection setup... */ diff --git a/net/rds/iw_send.c b/net/rds/iw_send.c index 6280ea020d4..545d8ee3efb 100644 --- a/net/rds/iw_send.c +++ b/net/rds/iw_send.c @@ -307,7 +307,7 @@ void rds_iw_send_cq_comp_handler(struct ib_cq *cq, void *context) * * Conceptually, we have two counters: * - send credits: this tells us how many WRs we're allowed - * to submit without overruning the reciever's queue. For + * to submit without overruning the receiver's queue. For * each SEND WR we post, we decrement this by one. * * - posted credits: this tells us how many WRs we recently diff --git a/net/rds/send.c b/net/rds/send.c index 35b9c2e9caf..d58ae5f9339 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -116,7 +116,7 @@ static void release_in_xmit(struct rds_connection *conn) } /* - * We're making the concious trade-off here to only send one message + * We're making the conscious trade-off here to only send one message * down the connection at a time. * Pro: * - tx queueing is a simple fifo list diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 5ee0c62046a..a80aef6e3d1 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -978,7 +978,7 @@ int rose_rx_call_request(struct sk_buff *skb, struct net_device *dev, struct ros struct sock *make; struct rose_sock *make_rose; struct rose_facilities_struct facilities; - int n, len; + int n; skb->sk = NULL; /* Initially we don't know who it's for */ @@ -987,9 +987,9 @@ int rose_rx_call_request(struct sk_buff *skb, struct net_device *dev, struct ros */ memset(&facilities, 0x00, sizeof(struct rose_facilities_struct)); - len = (((skb->data[3] >> 4) & 0x0F) + 1) >> 1; - len += (((skb->data[3] >> 0) & 0x0F) + 1) >> 1; - if (!rose_parse_facilities(skb->data + len + 4, &facilities)) { + if (!rose_parse_facilities(skb->data + ROSE_CALL_REQ_FACILITIES_OFF, + skb->len - ROSE_CALL_REQ_FACILITIES_OFF, + &facilities)) { rose_transmit_clear_request(neigh, lci, ROSE_INVALID_FACILITY, 76); return 0; } diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c index ae4a9d99aec..344456206b7 100644 --- a/net/rose/rose_loopback.c +++ b/net/rose/rose_loopback.c @@ -73,9 +73,20 @@ static void rose_loopback_timer(unsigned long param) unsigned int lci_i, lci_o; while ((skb = skb_dequeue(&loopback_queue)) != NULL) { + if (skb->len < ROSE_MIN_LEN) { + kfree_skb(skb); + continue; + } lci_i = ((skb->data[0] << 8) & 0xF00) + ((skb->data[1] << 0) & 0x0FF); frametype = skb->data[2]; - dest = (rose_address *)(skb->data + 4); + if (frametype == ROSE_CALL_REQUEST && + (skb->len <= ROSE_CALL_REQ_FACILITIES_OFF || + skb->data[ROSE_CALL_REQ_ADDR_LEN_OFF] != + ROSE_CALL_REQ_ADDR_LEN_VAL)) { + kfree_skb(skb); + continue; + } + dest = (rose_address *)(skb->data + ROSE_CALL_REQ_DEST_ADDR_OFF); lci_o = ROSE_DEFAULT_MAXVC + 1 - lci_i; skb_reset_transport_header(skb); diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index 88a77e90e7e..479cae57d18 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -587,7 +587,7 @@ static int rose_clear_routes(void) /* * Check that the device given is a valid AX.25 interface that is "up". - * called whith RTNL + * called with RTNL */ static struct net_device *rose_ax25_dev_find(char *devname) { @@ -861,7 +861,7 @@ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25) unsigned int lci, new_lci; unsigned char cause, diagnostic; struct net_device *dev; - int len, res = 0; + int res = 0; char buf[11]; #if 0 @@ -869,10 +869,17 @@ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25) return res; #endif + if (skb->len < ROSE_MIN_LEN) + return res; frametype = skb->data[2]; lci = ((skb->data[0] << 8) & 0xF00) + ((skb->data[1] << 0) & 0x0FF); - src_addr = (rose_address *)(skb->data + 9); - dest_addr = (rose_address *)(skb->data + 4); + if (frametype == ROSE_CALL_REQUEST && + (skb->len <= ROSE_CALL_REQ_FACILITIES_OFF || + skb->data[ROSE_CALL_REQ_ADDR_LEN_OFF] != + ROSE_CALL_REQ_ADDR_LEN_VAL)) + return res; + src_addr = (rose_address *)(skb->data + ROSE_CALL_REQ_SRC_ADDR_OFF); + dest_addr = (rose_address *)(skb->data + ROSE_CALL_REQ_DEST_ADDR_OFF); spin_lock_bh(&rose_neigh_list_lock); spin_lock_bh(&rose_route_list_lock); @@ -1010,12 +1017,11 @@ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25) goto out; } - len = (((skb->data[3] >> 4) & 0x0F) + 1) >> 1; - len += (((skb->data[3] >> 0) & 0x0F) + 1) >> 1; - memset(&facilities, 0x00, sizeof(struct rose_facilities_struct)); - if (!rose_parse_facilities(skb->data + len + 4, &facilities)) { + if (!rose_parse_facilities(skb->data + ROSE_CALL_REQ_FACILITIES_OFF, + skb->len - ROSE_CALL_REQ_FACILITIES_OFF, + &facilities)) { rose_transmit_clear_request(rose_neigh, lci, ROSE_INVALID_FACILITY, 76); goto out; } diff --git a/net/rose/rose_subr.c b/net/rose/rose_subr.c index 1734abba26a..f6c71caa94b 100644 --- a/net/rose/rose_subr.c +++ b/net/rose/rose_subr.c @@ -142,7 +142,7 @@ void rose_write_internal(struct sock *sk, int frametype) *dptr++ = ROSE_GFI | lci1; *dptr++ = lci2; *dptr++ = frametype; - *dptr++ = 0xAA; + *dptr++ = ROSE_CALL_REQ_ADDR_LEN_VAL; memcpy(dptr, &rose->dest_addr, ROSE_ADDR_LEN); dptr += ROSE_ADDR_LEN; memcpy(dptr, &rose->source_addr, ROSE_ADDR_LEN); @@ -246,12 +246,16 @@ static int rose_parse_national(unsigned char *p, struct rose_facilities_struct * do { switch (*p & 0xC0) { case 0x00: + if (len < 2) + return -1; p += 2; n += 2; len -= 2; break; case 0x40: + if (len < 3) + return -1; if (*p == FAC_NATIONAL_RAND) facilities->rand = ((p[1] << 8) & 0xFF00) + ((p[2] << 0) & 0x00FF); p += 3; @@ -260,40 +264,61 @@ static int rose_parse_national(unsigned char *p, struct rose_facilities_struct * break; case 0x80: + if (len < 4) + return -1; p += 4; n += 4; len -= 4; break; case 0xC0: + if (len < 2) + return -1; l = p[1]; + if (len < 2 + l) + return -1; if (*p == FAC_NATIONAL_DEST_DIGI) { if (!fac_national_digis_received) { + if (l < AX25_ADDR_LEN) + return -1; memcpy(&facilities->source_digis[0], p + 2, AX25_ADDR_LEN); facilities->source_ndigis = 1; } } else if (*p == FAC_NATIONAL_SRC_DIGI) { if (!fac_national_digis_received) { + if (l < AX25_ADDR_LEN) + return -1; memcpy(&facilities->dest_digis[0], p + 2, AX25_ADDR_LEN); facilities->dest_ndigis = 1; } } else if (*p == FAC_NATIONAL_FAIL_CALL) { + if (l < AX25_ADDR_LEN) + return -1; memcpy(&facilities->fail_call, p + 2, AX25_ADDR_LEN); } else if (*p == FAC_NATIONAL_FAIL_ADD) { + if (l < 1 + ROSE_ADDR_LEN) + return -1; memcpy(&facilities->fail_addr, p + 3, ROSE_ADDR_LEN); } else if (*p == FAC_NATIONAL_DIGIS) { + if (l % AX25_ADDR_LEN) + return -1; fac_national_digis_received = 1; facilities->source_ndigis = 0; facilities->dest_ndigis = 0; for (pt = p + 2, lg = 0 ; lg < l ; pt += AX25_ADDR_LEN, lg += AX25_ADDR_LEN) { - if (pt[6] & AX25_HBIT) + if (pt[6] & AX25_HBIT) { + if (facilities->dest_ndigis >= ROSE_MAX_DIGIS) + return -1; memcpy(&facilities->dest_digis[facilities->dest_ndigis++], pt, AX25_ADDR_LEN); - else + } else { + if (facilities->source_ndigis >= ROSE_MAX_DIGIS) + return -1; memcpy(&facilities->source_digis[facilities->source_ndigis++], pt, AX25_ADDR_LEN); + } } } p += l + 2; @@ -314,25 +339,38 @@ static int rose_parse_ccitt(unsigned char *p, struct rose_facilities_struct *fac do { switch (*p & 0xC0) { case 0x00: + if (len < 2) + return -1; p += 2; n += 2; len -= 2; break; case 0x40: + if (len < 3) + return -1; p += 3; n += 3; len -= 3; break; case 0x80: + if (len < 4) + return -1; p += 4; n += 4; len -= 4; break; case 0xC0: + if (len < 2) + return -1; l = p[1]; + + /* Prevent overflows*/ + if (l < 10 || l > 20) + return -1; + if (*p == FAC_CCITT_DEST_NSAP) { memcpy(&facilities->source_addr, p + 7, ROSE_ADDR_LEN); memcpy(callsign, p + 12, l - 10); @@ -355,45 +393,44 @@ static int rose_parse_ccitt(unsigned char *p, struct rose_facilities_struct *fac return n; } -int rose_parse_facilities(unsigned char *p, +int rose_parse_facilities(unsigned char *p, unsigned packet_len, struct rose_facilities_struct *facilities) { int facilities_len, len; facilities_len = *p++; - if (facilities_len == 0) + if (facilities_len == 0 || (unsigned)facilities_len > packet_len) return 0; - while (facilities_len > 0) { - if (*p == 0x00) { - facilities_len--; - p++; - - switch (*p) { - case FAC_NATIONAL: /* National */ - len = rose_parse_national(p + 1, facilities, facilities_len - 1); - facilities_len -= len + 1; - p += len + 1; - break; - - case FAC_CCITT: /* CCITT */ - len = rose_parse_ccitt(p + 1, facilities, facilities_len - 1); - facilities_len -= len + 1; - p += len + 1; - break; - - default: - printk(KERN_DEBUG "ROSE: rose_parse_facilities - unknown facilities family %02X\n", *p); - facilities_len--; - p++; - break; - } - } else - break; /* Error in facilities format */ + while (facilities_len >= 3 && *p == 0x00) { + facilities_len--; + p++; + + switch (*p) { + case FAC_NATIONAL: /* National */ + len = rose_parse_national(p + 1, facilities, facilities_len - 1); + break; + + case FAC_CCITT: /* CCITT */ + len = rose_parse_ccitt(p + 1, facilities, facilities_len - 1); + break; + + default: + printk(KERN_DEBUG "ROSE: rose_parse_facilities - unknown facilities family %02X\n", *p); + len = 1; + break; + } + + if (len < 0) + return 0; + if (WARN_ON(len >= facilities_len)) + return 0; + facilities_len -= len + 1; + p += len + 1; } - return 1; + return facilities_len == 0; } static int rose_create_facilities(unsigned char *buffer, struct rose_sock *rose) diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 15873e14cb5..14b42f4ad79 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -999,7 +999,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, void *arg) switch (n->nlmsg_type) { case RTM_NEWACTION: /* we are going to assume all other flags - * imply create only if it doesnt exist + * imply create only if it doesn't exist * Note that CREATE | EXCL implies that * but since we want avoid ambiguity (eg when flags * is zero) then just set this diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 50c7c06c019..7affe9a9275 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -161,7 +161,7 @@ static int tcf_pedit(struct sk_buff *skb, struct tc_action *a, } if (offset > 0 && offset > skb->len) { pr_info("tc filter pedit" - " offset %d cant exceed pkt length %d\n", + " offset %d can't exceed pkt length %d\n", offset, skb->len); goto bad; } diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index a4de67eca82..49130e8abff 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -47,7 +47,7 @@ * on the meta type. Obviously, the length of the data must also * be provided for non-numeric types. * - * Additionaly, type dependant modifiers such as shift operators + * Additionally, type dependent modifiers such as shift operators * or mask may be applied to extend the functionaliy. As of now, * the variable length type supports shifting the byte string to * the right, eating up any number of octets and thus supporting diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index e1429a85091..29b942ce9e8 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -183,7 +183,7 @@ static inline struct htb_class *htb_find(u32 handle, struct Qdisc *sch) * filters in qdisc and in inner nodes (if higher filter points to the inner * node). If we end up with classid MAJOR:0 we enqueue the skb into special * internal fifo (direct). These packets then go directly thru. If we still - * have no valid leaf we try to use MAJOR:default leaf. It still unsuccessfull + * have no valid leaf we try to use MAJOR:default leaf. It still unsuccessful * then finish and return direct queue. */ #define HTB_DIRECT ((struct htb_class *)-1L) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index edbbf7ad662..69c35f6cd13 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -160,7 +160,7 @@ static bool loss_4state(struct netem_sched_data *q) u32 rnd = net_random(); /* - * Makes a comparision between rnd and the transition + * Makes a comparison between rnd and the transition * probabilities outgoing from the current state, then decides the * next state and if the next packet has to be transmitted or lost. * The four states correspond to: @@ -212,9 +212,9 @@ static bool loss_4state(struct netem_sched_data *q) * Generates losses according to the Gilbert-Elliot loss model or * its special cases (Gilbert or Simple Gilbert) * - * Makes a comparision between random number and the transition + * Makes a comparison between random number and the transition * probabilities outgoing from the current state, then decides the - * next state. A second random number is extracted and the comparision + * next state. A second random number is extracted and the comparison * with the loss probability of the current state decides if the next * packet will be transmitted or lost. */ diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 6b04287913c..1a21c571aa0 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -569,6 +569,8 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc, sctp_assoc_set_primary(asoc, transport); if (asoc->peer.active_path == peer) asoc->peer.active_path = transport; + if (asoc->peer.retran_path == peer) + asoc->peer.retran_path = transport; if (asoc->peer.last_data_from == peer) asoc->peer.last_data_from = transport; @@ -1323,6 +1325,8 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc) if (t) asoc->peer.retran_path = t; + else + t = asoc->peer.retran_path; SCTP_DEBUG_PRINTK_IPADDR("sctp_assoc_update_retran_path:association" " %p addr: ", @@ -1593,7 +1597,7 @@ void sctp_assoc_clean_asconf_ack_cache(const struct sctp_association *asoc) struct sctp_chunk *ack; struct sctp_chunk *tmp; - /* We can remove all the entries from the queue upto + /* We can remove all the entries from the queue up to * the "Peer-Sequence-Number". */ list_for_each_entry_safe(ack, tmp, &asoc->asconf_ack_list, diff --git a/net/sctp/auth.c b/net/sctp/auth.c index ddbbf7c81fa..865e68fef21 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -113,7 +113,7 @@ struct sctp_shared_key *sctp_auth_shkey_create(__u16 key_id, gfp_t gfp) return new; } -/* Free the shared key stucture */ +/* Free the shared key structure */ static void sctp_auth_shkey_free(struct sctp_shared_key *sh_key) { BUG_ON(!list_empty(&sh_key->key_list)); @@ -122,7 +122,7 @@ static void sctp_auth_shkey_free(struct sctp_shared_key *sh_key) kfree(sh_key); } -/* Destory the entire key list. This is done during the +/* Destroy the entire key list. This is done during the * associon and endpoint free process. */ void sctp_auth_destroy_keys(struct list_head *keys) @@ -324,7 +324,7 @@ static struct sctp_auth_bytes *sctp_auth_asoc_create_secret( if (!peer_key_vector || !local_key_vector) goto out; - /* Figure out the order in wich the key_vectors will be + /* Figure out the order in which the key_vectors will be * added to the endpoint shared key. * SCTP-AUTH, Section 6.1: * This is performed by selecting the numerically smaller key diff --git a/net/sctp/input.c b/net/sctp/input.c index 826661be73e..5436c692116 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -1034,7 +1034,7 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( * association. * * This means that any chunks that can help us identify the association need -* to be looked at to find this assocation. +* to be looked at to find this association. */ static struct sctp_association *__sctp_rcv_walk_lookup(struct sk_buff *skb, const union sctp_addr *laddr, diff --git a/net/sctp/output.c b/net/sctp/output.c index 60600d337a3..b4f3cf06d8d 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -510,7 +510,7 @@ int sctp_packet_transmit(struct sctp_packet *packet) sh->checksum = sctp_end_cksum(crc32); } else { if (dst->dev->features & NETIF_F_SCTP_CSUM) { - /* no need to seed psuedo checksum for SCTP */ + /* no need to seed pseudo checksum for SCTP */ nskb->ip_summed = CHECKSUM_PARTIAL; nskb->csum_start = (skb_transport_header(nskb) - nskb->head); diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 26dc005113a..bf92a5b68f8 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -177,13 +177,13 @@ static inline int sctp_cacc_skip_3_2(struct sctp_transport *primary, __u32 tsn) * 3) If the missing report count for TSN t is to be * incremented according to [RFC2960] and * [SCTP_STEWART-2002], and CHANGEOVER_ACTIVE is set, - * then the sender MUST futher execute steps 3.1 and + * then the sender MUST further execute steps 3.1 and * 3.2 to determine if the missing report count for * TSN t SHOULD NOT be incremented. * * 3.3) If 3.1 and 3.2 do not dictate that the missing * report count for t should not be incremented, then - * the sender SOULD increment missing report count for + * the sender SHOULD increment missing report count for * t (according to [RFC2960] and [SCTP_STEWART_2002]). */ static inline int sctp_cacc_skip(struct sctp_transport *primary, @@ -843,7 +843,7 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) case SCTP_CID_ECN_CWR: case SCTP_CID_ASCONF_ACK: one_packet = 1; - /* Fall throught */ + /* Fall through */ case SCTP_CID_SACK: case SCTP_CID_HEARTBEAT: diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 152976ec0b7..d5bf91d04f6 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1205,7 +1205,7 @@ SCTP_STATIC __init int sctp_init(void) if ((sctp_assoc_hashsize > (64 * 1024)) && order > 0) continue; sctp_assoc_hashtable = (struct sctp_hashbucket *) - __get_free_pages(GFP_ATOMIC, order); + __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, order); } while (!sctp_assoc_hashtable && --order > 0); if (!sctp_assoc_hashtable) { pr_err("Failed association hash alloc\n"); @@ -1238,7 +1238,7 @@ SCTP_STATIC __init int sctp_init(void) if ((sctp_port_hashsize > (64 * 1024)) && order > 0) continue; sctp_port_hashtable = (struct sctp_bind_hashbucket *) - __get_free_pages(GFP_ATOMIC, order); + __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, order); } while (!sctp_port_hashtable && --order > 0); if (!sctp_port_hashtable) { pr_err("Failed bind hash alloc\n"); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index de98665db52..b3434cc7d0c 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -3106,10 +3106,10 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, /* create an ASCONF_ACK chunk. * Based on the definitions of parameters, we know that the size of - * ASCONF_ACK parameters are less than or equal to the twice of ASCONF + * ASCONF_ACK parameters are less than or equal to the fourfold of ASCONF * parameters. */ - asconf_ack = sctp_make_asconf_ack(asoc, serial, chunk_len * 2); + asconf_ack = sctp_make_asconf_ack(asoc, serial, chunk_len * 4); if (!asconf_ack) goto done; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index b21b218d564..5f86ee4b54c 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -482,7 +482,7 @@ static void sctp_do_8_2_transport_strike(struct sctp_association *asoc, * If the timer was a heartbeat, we only increment error counts * when we already have an outstanding HEARTBEAT that has not * been acknowledged. - * Additionaly, some tranport states inhibit error increments. + * Additionally, some tranport states inhibit error increments. */ if (!is_hb) { asoc->overall_error_count++; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 4b4eb7c96bb..76792083c37 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -551,7 +551,7 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(const struct sctp_endpoint *ep, * * This means that if we only want to abort associations * in an authenticated way (i.e AUTH+ABORT), then we - * can't destroy this association just becuase the packet + * can't destroy this association just because the packet * was malformed. */ if (sctp_auth_recv_cid(SCTP_CID_ABORT, asoc)) @@ -1546,7 +1546,7 @@ cleanup: } /* - * Handle simultanous INIT. + * Handle simultaneous INIT. * This means we started an INIT and then we got an INIT request from * our peer. * @@ -2079,7 +2079,7 @@ sctp_disposition_t sctp_sf_shutdown_pending_abort( * RFC 2960, Section 3.3.7 * If an endpoint receives an ABORT with a format error or for an * association that doesn't exist, it MUST silently discard it. - * Becasue the length is "invalid", we can't really discard just + * Because the length is "invalid", we can't really discard just * as we do not know its true length. So, to be safe, discard the * packet. */ @@ -2120,7 +2120,7 @@ sctp_disposition_t sctp_sf_shutdown_sent_abort(const struct sctp_endpoint *ep, * RFC 2960, Section 3.3.7 * If an endpoint receives an ABORT with a format error or for an * association that doesn't exist, it MUST silently discard it. - * Becasue the length is "invalid", we can't really discard just + * Because the length is "invalid", we can't really discard just * as we do not know its true length. So, to be safe, discard the * packet. */ @@ -2381,7 +2381,7 @@ sctp_disposition_t sctp_sf_do_9_1_abort(const struct sctp_endpoint *ep, * RFC 2960, Section 3.3.7 * If an endpoint receives an ABORT with a format error or for an * association that doesn't exist, it MUST silently discard it. - * Becasue the length is "invalid", we can't really discard just + * Because the length is "invalid", we can't really discard just * as we do not know its true length. So, to be safe, discard the * packet. */ @@ -2448,7 +2448,7 @@ sctp_disposition_t sctp_sf_cookie_wait_abort(const struct sctp_endpoint *ep, * RFC 2960, Section 3.3.7 * If an endpoint receives an ABORT with a format error or for an * association that doesn't exist, it MUST silently discard it. - * Becasue the length is "invalid", we can't really discard just + * Because the length is "invalid", we can't really discard just * as we do not know its true length. So, to be safe, discard the * packet. */ @@ -3855,7 +3855,7 @@ gen_shutdown: } /* - * SCTP-AUTH Section 6.3 Receving authenticated chukns + * SCTP-AUTH Section 6.3 Receiving authenticated chukns * * The receiver MUST use the HMAC algorithm indicated in the HMAC * Identifier field. If this algorithm was not specified by the @@ -4231,7 +4231,7 @@ static sctp_disposition_t sctp_sf_abort_violation( * * This means that if we only want to abort associations * in an authenticated way (i.e AUTH+ABORT), then we - * can't destroy this association just becuase the packet + * can't destroy this association just because the packet * was malformed. */ if (sctp_auth_recv_cid(SCTP_CID_ABORT, asoc)) @@ -4402,9 +4402,9 @@ static sctp_disposition_t sctp_sf_violation_ctsn( } /* Handle protocol violation of an invalid chunk bundling. For example, - * when we have an association and we recieve bundled INIT-ACK, or + * when we have an association and we receive bundled INIT-ACK, or * SHUDOWN-COMPLETE, our peer is clearly violationg the "MUST NOT bundle" - * statement from the specs. Additinally, there might be an attacker + * statement from the specs. Additionally, there might be an attacker * on the path and we may not want to continue this communication. */ static sctp_disposition_t sctp_sf_violation_chunk( diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 3951a10605b..deb82e35a10 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1193,7 +1193,7 @@ out_free: * an endpoint that is multi-homed. Much like sctp_bindx() this call * allows a caller to specify multiple addresses at which a peer can be * reached. The way the SCTP stack uses the list of addresses to set up - * the association is implementation dependant. This function only + * the association is implementation dependent. This function only * specifies that the stack will try to make use of all the addresses in * the list when needed. * diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index aa72e89c3ee..61b1f5ada96 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -554,7 +554,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_send_failed( memcpy(&ssf->ssf_info, &chunk->sinfo, sizeof(struct sctp_sndrcvinfo)); /* Per TSVWG discussion with Randy. Allow the application to - * ressemble a fragmented message. + * reassemble a fragmented message. */ ssf->ssf_info.sinfo_flags = chunk->chunk_hdr->flags; diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 17678189d05..f2d1de7f2ff 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -240,7 +240,7 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) } else { /* * If fragment interleave is enabled, we - * can queue this to the recieve queue instead + * can queue this to the receive queue instead * of the lobby. */ if (sctp_sk(sk)->frag_interleave) diff --git a/net/socket.c b/net/socket.c index 937d0fcf74b..310d16b1b3c 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2588,23 +2588,123 @@ static int dev_ifconf(struct net *net, struct compat_ifconf __user *uifc32) static int ethtool_ioctl(struct net *net, struct compat_ifreq __user *ifr32) { + struct compat_ethtool_rxnfc __user *compat_rxnfc; + bool convert_in = false, convert_out = false; + size_t buf_size = ALIGN(sizeof(struct ifreq), 8); + struct ethtool_rxnfc __user *rxnfc; struct ifreq __user *ifr; + u32 rule_cnt = 0, actual_rule_cnt; + u32 ethcmd; u32 data; - void __user *datap; + int ret; + + if (get_user(data, &ifr32->ifr_ifru.ifru_data)) + return -EFAULT; - ifr = compat_alloc_user_space(sizeof(*ifr)); + compat_rxnfc = compat_ptr(data); - if (copy_in_user(&ifr->ifr_name, &ifr32->ifr_name, IFNAMSIZ)) + if (get_user(ethcmd, &compat_rxnfc->cmd)) return -EFAULT; - if (get_user(data, &ifr32->ifr_ifru.ifru_data)) + /* Most ethtool structures are defined without padding. + * Unfortunately struct ethtool_rxnfc is an exception. + */ + switch (ethcmd) { + default: + break; + case ETHTOOL_GRXCLSRLALL: + /* Buffer size is variable */ + if (get_user(rule_cnt, &compat_rxnfc->rule_cnt)) + return -EFAULT; + if (rule_cnt > KMALLOC_MAX_SIZE / sizeof(u32)) + return -ENOMEM; + buf_size += rule_cnt * sizeof(u32); + /* fall through */ + case ETHTOOL_GRXRINGS: + case ETHTOOL_GRXCLSRLCNT: + case ETHTOOL_GRXCLSRULE: + convert_out = true; + /* fall through */ + case ETHTOOL_SRXCLSRLDEL: + case ETHTOOL_SRXCLSRLINS: + buf_size += sizeof(struct ethtool_rxnfc); + convert_in = true; + break; + } + + ifr = compat_alloc_user_space(buf_size); + rxnfc = (void *)ifr + ALIGN(sizeof(struct ifreq), 8); + + if (copy_in_user(&ifr->ifr_name, &ifr32->ifr_name, IFNAMSIZ)) return -EFAULT; - datap = compat_ptr(data); - if (put_user(datap, &ifr->ifr_ifru.ifru_data)) + if (put_user(convert_in ? rxnfc : compat_ptr(data), + &ifr->ifr_ifru.ifru_data)) return -EFAULT; - return dev_ioctl(net, SIOCETHTOOL, ifr); + if (convert_in) { + /* We expect there to be holes between fs.m_u and + * fs.ring_cookie and at the end of fs, but nowhere else. + */ + BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.m_u) + + sizeof(compat_rxnfc->fs.m_u) != + offsetof(struct ethtool_rxnfc, fs.m_u) + + sizeof(rxnfc->fs.m_u)); + BUILD_BUG_ON( + offsetof(struct compat_ethtool_rxnfc, fs.location) - + offsetof(struct compat_ethtool_rxnfc, fs.ring_cookie) != + offsetof(struct ethtool_rxnfc, fs.location) - + offsetof(struct ethtool_rxnfc, fs.ring_cookie)); + + if (copy_in_user(rxnfc, compat_rxnfc, + (void *)(&rxnfc->fs.m_u + 1) - + (void *)rxnfc) || + copy_in_user(&rxnfc->fs.ring_cookie, + &compat_rxnfc->fs.ring_cookie, + (void *)(&rxnfc->fs.location + 1) - + (void *)&rxnfc->fs.ring_cookie) || + copy_in_user(&rxnfc->rule_cnt, &compat_rxnfc->rule_cnt, + sizeof(rxnfc->rule_cnt))) + return -EFAULT; + } + + ret = dev_ioctl(net, SIOCETHTOOL, ifr); + if (ret) + return ret; + + if (convert_out) { + if (copy_in_user(compat_rxnfc, rxnfc, + (const void *)(&rxnfc->fs.m_u + 1) - + (const void *)rxnfc) || + copy_in_user(&compat_rxnfc->fs.ring_cookie, + &rxnfc->fs.ring_cookie, + (const void *)(&rxnfc->fs.location + 1) - + (const void *)&rxnfc->fs.ring_cookie) || + copy_in_user(&compat_rxnfc->rule_cnt, &rxnfc->rule_cnt, + sizeof(rxnfc->rule_cnt))) + return -EFAULT; + + if (ethcmd == ETHTOOL_GRXCLSRLALL) { + /* As an optimisation, we only copy the actual + * number of rules that the underlying + * function returned. Since Mallory might + * change the rule count in user memory, we + * check that it is less than the rule count + * originally given (as the user buffer size), + * which has been range-checked. + */ + if (get_user(actual_rule_cnt, &rxnfc->rule_cnt)) + return -EFAULT; + if (actual_rule_cnt < rule_cnt) + rule_cnt = actual_rule_cnt; + if (copy_in_user(&compat_rxnfc->rule_locs[0], + &rxnfc->rule_locs[0], + rule_cnt * sizeof(u32))) + return -EFAULT; + } + } + + return 0; } static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32) @@ -2886,7 +2986,7 @@ out: /* Since old style bridge ioctl's endup using SIOCDEVPRIVATE * for some operations; this forces use of the newer bridge-utils that - * use compatiable ioctls + * use compatible ioctls */ static int old_bridge_ioctl(compat_ulong_t __user *argp) { diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index 8873fd8ddac..b2198e65d8b 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -18,14 +18,13 @@ config SUNRPC_XPRT_RDMA If unsure, say N. config RPCSEC_GSS_KRB5 - tristate + tristate "Secure RPC: Kerberos V mechanism" depends on SUNRPC && CRYPTO - prompt "Secure RPC: Kerberos V mechanism" if !(NFS_V4 || NFSD_V4) + depends on CRYPTO_MD5 && CRYPTO_DES && CRYPTO_CBC && CRYPTO_CTS + depends on CRYPTO_ECB && CRYPTO_HMAC && CRYPTO_SHA1 && CRYPTO_AES + depends on CRYPTO_ARC4 default y select SUNRPC_GSS - select CRYPTO_MD5 - select CRYPTO_DES - select CRYPTO_CBC help Choose Y here to enable Secure RPC using the Kerberos version 5 GSS-API mechanism (RFC 1964). diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index f3914d0c507..339ba64cce1 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -520,7 +520,7 @@ gss_refresh_upcall(struct rpc_task *task) warn_gssd(); task->tk_timeout = 15*HZ; rpc_sleep_on(&pipe_version_rpc_waitqueue, task, NULL); - return 0; + return -EAGAIN; } if (IS_ERR(gss_msg)) { err = PTR_ERR(gss_msg); @@ -563,10 +563,12 @@ retry: if (PTR_ERR(gss_msg) == -EAGAIN) { err = wait_event_interruptible_timeout(pipe_version_waitqueue, pipe_version >= 0, 15*HZ); + if (pipe_version < 0) { + warn_gssd(); + err = -EACCES; + } if (err) goto out; - if (pipe_version < 0) - warn_gssd(); goto retry; } if (IS_ERR(gss_msg)) { diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 9022f0a6503..0a9a2ec2e46 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -427,7 +427,7 @@ static int context_derive_keys_rc4(struct krb5_ctx *ctx) { struct crypto_hash *hmac; - static const char sigkeyconstant[] = "signaturekey"; + char sigkeyconstant[] = "signaturekey"; int slen = strlen(sigkeyconstant) + 1; /* include null terminator */ struct hash_desc desc; struct scatterlist sg[1]; diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index 8b4061049d7..e3c36a27441 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -160,6 +160,28 @@ gss_mech_get_by_name(const char *name) EXPORT_SYMBOL_GPL(gss_mech_get_by_name); +struct gss_api_mech * +gss_mech_get_by_OID(struct xdr_netobj *obj) +{ + struct gss_api_mech *pos, *gm = NULL; + + spin_lock(®istered_mechs_lock); + list_for_each_entry(pos, ®istered_mechs, gm_list) { + if (obj->len == pos->gm_oid.len) { + if (0 == memcmp(obj->data, pos->gm_oid.data, obj->len)) { + if (try_module_get(pos->gm_owner)) + gm = pos; + break; + } + } + } + spin_unlock(®istered_mechs_lock); + return gm; + +} + +EXPORT_SYMBOL_GPL(gss_mech_get_by_OID); + static inline int mech_supports_pseudoflavor(struct gss_api_mech *gm, u32 pseudoflavor) { @@ -193,6 +215,22 @@ gss_mech_get_by_pseudoflavor(u32 pseudoflavor) EXPORT_SYMBOL_GPL(gss_mech_get_by_pseudoflavor); +int gss_mech_list_pseudoflavors(rpc_authflavor_t *array_ptr) +{ + struct gss_api_mech *pos = NULL; + int i = 0; + + spin_lock(®istered_mechs_lock); + list_for_each_entry(pos, ®istered_mechs, gm_list) { + array_ptr[i] = pos->gm_pfs->pseudoflavor; + i++; + } + spin_unlock(®istered_mechs_lock); + return i; +} + +EXPORT_SYMBOL_GPL(gss_mech_list_pseudoflavors); + u32 gss_svc_to_pseudoflavor(struct gss_api_mech *gm, u32 service) { diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index bcdae78fdfc..8d0f7d3c71c 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1101,7 +1101,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) /* credential is: * version(==1), proc(0,1,2,3), seq, service (1,2,3), handle - * at least 5 u32s, and is preceeded by length, so that makes 6. + * at least 5 u32s, and is preceded by length, so that makes 6. */ if (argv->iov_len < 5 * 4) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index e7a96e478f6..8d83f9d4871 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1508,7 +1508,10 @@ call_timeout(struct rpc_task *task) if (clnt->cl_chatty) printk(KERN_NOTICE "%s: server %s not responding, timed out\n", clnt->cl_protname, clnt->cl_server); - rpc_exit(task, -EIO); + if (task->tk_flags & RPC_TASK_TIMEOUT) + rpc_exit(task, -ETIMEDOUT); + else + rpc_exit(task, -EIO); return; } diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index ffb687671da..6b43ee7221d 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -860,8 +860,10 @@ static void rpc_release_resources_task(struct rpc_task *task) { if (task->tk_rqstp) xprt_release(task); - if (task->tk_msg.rpc_cred) + if (task->tk_msg.rpc_cred) { put_rpccred(task->tk_msg.rpc_cred); + task->tk_msg.rpc_cred = NULL; + } rpc_task_release_client(task); } diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 30916b06c12..c8e10216c11 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -38,6 +38,14 @@ struct unix_domain { extern struct auth_ops svcauth_unix; +static void svcauth_unix_domain_release(struct auth_domain *dom) +{ + struct unix_domain *ud = container_of(dom, struct unix_domain, h); + + kfree(dom->name); + kfree(ud); +} + struct auth_domain *unix_domain_find(char *name) { struct auth_domain *rv; @@ -47,7 +55,7 @@ struct auth_domain *unix_domain_find(char *name) while(1) { if (rv) { if (new && rv != &new->h) - auth_domain_put(&new->h); + svcauth_unix_domain_release(&new->h); if (rv->flavour != &svcauth_unix) { auth_domain_put(rv); @@ -74,14 +82,6 @@ struct auth_domain *unix_domain_find(char *name) } EXPORT_SYMBOL_GPL(unix_domain_find); -static void svcauth_unix_domain_release(struct auth_domain *dom) -{ - struct unix_domain *ud = container_of(dom, struct unix_domain, h); - - kfree(dom->name); - kfree(ud); -} - /************************************************** * cache for IP address to unix_domain diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 9494c376735..ce5eb68a966 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -906,6 +906,7 @@ void xprt_transmit(struct rpc_task *task) } dprintk("RPC: %5u xmit complete\n", task->tk_pid); + task->tk_flags |= RPC_TASK_SENT; spin_lock_bh(&xprt->transport_lock); xprt->ops->set_retrans_timeout(task); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index be96d429b47..bf005d3c65e 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -504,7 +504,7 @@ static int xs_nospace(struct rpc_task *task) * EAGAIN: The socket was blocked, please call again later to * complete the request * ENOTCONN: Caller needs to invoke connect logic then call again - * other: Some other error occured, the request was not sent + * other: Some other error occurred, the request was not sent */ static int xs_udp_send_request(struct rpc_task *task) { @@ -590,7 +590,7 @@ static inline void xs_encode_tcp_record_marker(struct xdr_buf *buf) * EAGAIN: The socket was blocked, please call again later to * complete the request * ENOTCONN: Caller needs to invoke connect logic then call again - * other: Some other error occured, the request was not sent + * other: Some other error occurred, the request was not sent * * XXX: In the case of soft timeouts, should we eventually give up * if sendmsg is not able to make progress? @@ -710,6 +710,8 @@ static void xs_reset_transport(struct sock_xprt *transport) if (sk == NULL) return; + transport->srcport = 0; + write_lock_bh(&sk->sk_callback_lock); transport->inet = NULL; transport->sock = NULL; diff --git a/net/tipc/link.c b/net/tipc/link.c index 43639ff1cbe..ebf338f7b14 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -2471,7 +2471,7 @@ exit: * A pending message being re-assembled must store certain values * to handle subsequent fragments correctly. The following functions * help storing these values in unused, available fields in the - * pending message. This makes dynamic memory allocation unecessary. + * pending message. This makes dynamic memory allocation unnecessary. */ static void set_long_msg_seqno(struct sk_buff *buf, u32 seqno) diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index c9fa6dfcf28..80025a1b3bf 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -160,7 +160,7 @@ void tipc_named_withdraw(struct publication *publ) buf = named_prepare_buf(WITHDRAWAL, ITEM_SIZE, 0); if (!buf) { - warn("Withdrawl distribution failure\n"); + warn("Withdrawal distribution failure\n"); return; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 1663e1a2efd..b1d75beb7e2 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -207,7 +207,7 @@ static int unix_mkname(struct sockaddr_un *sunaddr, int len, unsigned *hashp) /* * This may look like an off by one error but it is a bit more * subtle. 108 is the longest valid AF_UNIX path for a binding. - * sun_path[108] doesnt as such exist. However in kernel space + * sun_path[108] doesn't as such exist. However in kernel space * we are guaranteed that it is a valid memory location in our * kernel address buffer. */ @@ -524,6 +524,8 @@ static int unix_dgram_connect(struct socket *, struct sockaddr *, int, int); static int unix_seqpacket_sendmsg(struct kiocb *, struct socket *, struct msghdr *, size_t); +static int unix_seqpacket_recvmsg(struct kiocb *, struct socket *, + struct msghdr *, size_t, int); static const struct proto_ops unix_stream_ops = { .family = PF_UNIX, @@ -583,7 +585,7 @@ static const struct proto_ops unix_seqpacket_ops = { .setsockopt = sock_no_setsockopt, .getsockopt = sock_no_getsockopt, .sendmsg = unix_seqpacket_sendmsg, - .recvmsg = unix_dgram_recvmsg, + .recvmsg = unix_seqpacket_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, }; @@ -1699,6 +1701,18 @@ static int unix_seqpacket_sendmsg(struct kiocb *kiocb, struct socket *sock, return unix_dgram_sendmsg(kiocb, sock, msg, len); } +static int unix_seqpacket_recvmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *msg, size_t size, + int flags) +{ + struct sock *sk = sock->sk; + + if (sk->sk_state != TCP_ESTABLISHED) + return -ENOTCONN; + + return unix_dgram_recvmsg(iocb, sock, msg, size, flags); +} + static void unix_copy_addr(struct msghdr *msg, struct sock *sk) { struct unix_sock *u = unix_sk(sk); diff --git a/net/wanrouter/wanproc.c b/net/wanrouter/wanproc.c index 11f25c7a7a0..f346395314b 100644 --- a/net/wanrouter/wanproc.c +++ b/net/wanrouter/wanproc.c @@ -51,7 +51,7 @@ /* * Structures for interfacing with the /proc filesystem. - * Router creates its own directory /proc/net/router with the folowing + * Router creates its own directory /proc/net/router with the following * entries: * config device configuration * status global device statistics diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 3332d5bce31..ab801a1097b 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -809,7 +809,7 @@ static void handle_channel(struct wiphy *wiphy, if (r) { /* * We will disable all channels that do not match our - * recieved regulatory rule unless the hint is coming + * received regulatory rule unless the hint is coming * from a Country IE and the Country IE had no information * about a band. The IEEE 802.11 spec allows for an AP * to send only a subset of the regulatory rules allowed, @@ -838,7 +838,7 @@ static void handle_channel(struct wiphy *wiphy, request_wiphy && request_wiphy == wiphy && request_wiphy->flags & WIPHY_FLAG_STRICT_REGULATORY) { /* - * This gaurantees the driver's requested regulatory domain + * This guarantees the driver's requested regulatory domain * will always be used as a base for further regulatory * settings */ diff --git a/net/wireless/scan.c b/net/wireless/scan.c index ea427f418f6..fbf6f33ae4d 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -124,6 +124,15 @@ void cfg80211_bss_age(struct cfg80211_registered_device *dev, } /* must hold dev->bss_lock! */ +static void __cfg80211_unlink_bss(struct cfg80211_registered_device *dev, + struct cfg80211_internal_bss *bss) +{ + list_del_init(&bss->list); + rb_erase(&bss->rbn, &dev->bss_tree); + kref_put(&bss->ref, bss_release); +} + +/* must hold dev->bss_lock! */ void cfg80211_bss_expire(struct cfg80211_registered_device *dev) { struct cfg80211_internal_bss *bss, *tmp; @@ -134,9 +143,7 @@ void cfg80211_bss_expire(struct cfg80211_registered_device *dev) continue; if (!time_after(jiffies, bss->ts + IEEE80211_SCAN_RESULT_EXPIRE)) continue; - list_del(&bss->list); - rb_erase(&bss->rbn, &dev->bss_tree); - kref_put(&bss->ref, bss_release); + __cfg80211_unlink_bss(dev, bss); expired = true; } @@ -585,16 +592,23 @@ cfg80211_inform_bss_frame(struct wiphy *wiphy, struct cfg80211_internal_bss *res; size_t ielen = len - offsetof(struct ieee80211_mgmt, u.probe_resp.variable); - size_t privsz = wiphy->bss_priv_size; + size_t privsz; + + if (WARN_ON(!mgmt)) + return NULL; + + if (WARN_ON(!wiphy)) + return NULL; if (WARN_ON(wiphy->signal_type == CFG80211_SIGNAL_TYPE_UNSPEC && (signal < 0 || signal > 100))) return NULL; - if (WARN_ON(!mgmt || !wiphy || - len < offsetof(struct ieee80211_mgmt, u.probe_resp.variable))) + if (WARN_ON(len < offsetof(struct ieee80211_mgmt, u.probe_resp.variable))) return NULL; + privsz = wiphy->bss_priv_size; + res = kzalloc(sizeof(*res) + privsz + ielen, gfp); if (!res) return NULL; @@ -662,11 +676,8 @@ void cfg80211_unlink_bss(struct wiphy *wiphy, struct cfg80211_bss *pub) spin_lock_bh(&dev->bss_lock); if (!list_empty(&bss->list)) { - list_del_init(&bss->list); + __cfg80211_unlink_bss(dev, bss); dev->bss_generation++; - rb_erase(&bss->rbn, &dev->bss_tree); - - kref_put(&bss->ref, bss_release); } spin_unlock_bh(&dev->bss_lock); } diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c index 406207515b5..f77e4e75f91 100644 --- a/net/x25/x25_facilities.c +++ b/net/x25/x25_facilities.c @@ -31,7 +31,7 @@ * x25_parse_facilities - Parse facilities from skb into the facilities structs * * @skb: sk_buff to parse - * @facilities: Regular facilites, updated as facilities are found + * @facilities: Regular facilities, updated as facilities are found * @dte_facs: ITU DTE facilities, updated as DTE facilities are found * @vc_fac_mask: mask is updated with all facilities found * diff --git a/net/x25/x25_forward.c b/net/x25/x25_forward.c index 25a81079396..c541b622ae1 100644 --- a/net/x25/x25_forward.c +++ b/net/x25/x25_forward.c @@ -31,7 +31,7 @@ int x25_forward_call(struct x25_address *dest_addr, struct x25_neigh *from, goto out_no_route; if ((neigh_new = x25_get_neigh(rt->dev)) == NULL) { - /* This shouldnt happen, if it occurs somehow + /* This shouldn't happen, if it occurs somehow * do something sensible */ goto out_put_route; @@ -45,7 +45,7 @@ int x25_forward_call(struct x25_address *dest_addr, struct x25_neigh *from, } /* Remote end sending a call request on an already - * established LCI? It shouldnt happen, just in case.. + * established LCI? It shouldn't happen, just in case.. */ read_lock_bh(&x25_forward_list_lock); list_for_each(entry, &x25_forward_list) { diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 872065ca7f8..a026b0ef244 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -173,7 +173,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) goto drop_unlock; } - if (x->props.replay_window && x->repl->check(x, skb, seq)) { + if (x->repl->check(x, skb, seq)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR); goto drop_unlock; } @@ -190,6 +190,8 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) XFRM_SKB_CB(skb)->seq.input.low = seq; XFRM_SKB_CB(skb)->seq.input.hi = seq_hi; + skb_dst_force(skb); + nexthdr = x->type->input(x, skb); if (nexthdr == -EINPROGRESS) diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 1aba03f449c..47bacd8c025 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -78,6 +78,8 @@ static int xfrm_output_one(struct sk_buff *skb, int err) spin_unlock_bh(&x->lock); + skb_dst_force(skb); + err = x->type->output(x, skb); if (err == -EINPROGRESS) goto out_exit; @@ -94,7 +96,7 @@ resume: err = -EHOSTUNREACH; goto error_nolock; } - skb_dst_set(skb, dst_clone(dst)); + skb_dst_set(skb, dst); x = dst->xfrm; } while (x && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL)); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 15792d8b627..b4d745ea8ee 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1406,6 +1406,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, struct net *net = xp_net(policy); unsigned long now = jiffies; struct net_device *dev; + struct xfrm_mode *inner_mode; struct dst_entry *dst_prev = NULL; struct dst_entry *dst0 = NULL; int i = 0; @@ -1436,6 +1437,17 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, goto put_states; } + if (xfrm[i]->sel.family == AF_UNSPEC) { + inner_mode = xfrm_ip2inner_mode(xfrm[i], + xfrm_af2proto(family)); + if (!inner_mode) { + err = -EAFNOSUPPORT; + dst_release(dst); + goto put_states; + } + } else + inner_mode = xfrm[i]->inner_mode; + if (!dst_prev) dst0 = dst1; else { @@ -1464,7 +1476,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, dst1->lastuse = now; dst1->input = dst_discard; - dst1->output = xfrm[i]->outer_mode->afinfo->output; + dst1->output = inner_mode->afinfo->output; dst1->next = dst_prev; dst_prev = dst1; diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index 2f5be5b1574..47f1b8638df 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -118,6 +118,9 @@ static int xfrm_replay_check(struct xfrm_state *x, u32 diff; u32 seq = ntohl(net_seq); + if (!x->props.replay_window) + return 0; + if (unlikely(seq == 0)) goto err; @@ -193,9 +196,14 @@ static int xfrm_replay_check_bmp(struct xfrm_state *x, { unsigned int bitnr, nr; struct xfrm_replay_state_esn *replay_esn = x->replay_esn; + u32 pos; u32 seq = ntohl(net_seq); u32 diff = replay_esn->seq - seq; - u32 pos = (replay_esn->seq - 1) % replay_esn->replay_window; + + if (!replay_esn->replay_window) + return 0; + + pos = (replay_esn->seq - 1) % replay_esn->replay_window; if (unlikely(seq == 0)) goto err; @@ -373,12 +381,17 @@ static int xfrm_replay_check_esn(struct xfrm_state *x, unsigned int bitnr, nr; u32 diff; struct xfrm_replay_state_esn *replay_esn = x->replay_esn; + u32 pos; u32 seq = ntohl(net_seq); - u32 pos = (replay_esn->seq - 1) % replay_esn->replay_window; u32 wsize = replay_esn->replay_window; u32 top = replay_esn->seq; u32 bottom = top - wsize + 1; + if (!wsize) + return 0; + + pos = (replay_esn->seq - 1) % replay_esn->replay_window; + if (unlikely(seq == 0 && replay_esn->seq_hi == 0 && (replay_esn->seq < replay_esn->replay_window - 1))) goto err; @@ -519,9 +532,12 @@ int xfrm_init_replay(struct xfrm_state *x) if (replay_esn) { if (replay_esn->replay_window > - replay_esn->bmp_len * sizeof(__u32)) + replay_esn->bmp_len * sizeof(__u32) * 8) return -EINVAL; + if ((x->props.flags & XFRM_STATE_ESN) && replay_esn->replay_window == 0) + return -EINVAL; + if ((x->props.flags & XFRM_STATE_ESN) && x->replay_esn) x->repl = &xfrm_replay_esn; else diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index d575f053486..dd78536d40d 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1181,6 +1181,12 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp) goto error; } + if (orig->replay_esn) { + err = xfrm_replay_clone(x, orig); + if (err) + goto error; + } + memcpy(&x->mark, &orig->mark, sizeof(x->mark)); err = xfrm_init_state(x); @@ -1907,7 +1913,7 @@ int xfrm_state_mtu(struct xfrm_state *x, int mtu) return res; } -int xfrm_init_state(struct xfrm_state *x) +int __xfrm_init_state(struct xfrm_state *x, bool init_replay) { struct xfrm_state_afinfo *afinfo; struct xfrm_mode *inner_mode; @@ -1980,12 +1986,25 @@ int xfrm_init_state(struct xfrm_state *x) if (x->outer_mode == NULL) goto error; + if (init_replay) { + err = xfrm_init_replay(x); + if (err) + goto error; + } + x->km.state = XFRM_STATE_VALID; error: return err; } +EXPORT_SYMBOL(__xfrm_init_state); + +int xfrm_init_state(struct xfrm_state *x) +{ + return __xfrm_init_state(x, true); +} + EXPORT_SYMBOL(xfrm_init_state); int __net_init xfrm_state_init(struct net *net) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 706385ae3e4..c658cb3bc7c 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -124,9 +124,15 @@ static inline int verify_replay(struct xfrm_usersa_info *p, { struct nlattr *rt = attrs[XFRMA_REPLAY_ESN_VAL]; + if ((p->flags & XFRM_STATE_ESN) && !rt) + return -EINVAL; + if (!rt) return 0; + if (p->id.proto != IPPROTO_ESP) + return -EINVAL; + if (p->replay_window != 0) return -EINVAL; @@ -360,6 +366,23 @@ static int attach_aead(struct xfrm_algo_aead **algpp, u8 *props, return 0; } +static inline int xfrm_replay_verify_len(struct xfrm_replay_state_esn *replay_esn, + struct nlattr *rp) +{ + struct xfrm_replay_state_esn *up; + + if (!replay_esn || !rp) + return 0; + + up = nla_data(rp); + + if (xfrm_replay_state_esn_len(replay_esn) != + xfrm_replay_state_esn_len(up)) + return -EINVAL; + + return 0; +} + static int xfrm_alloc_replay_state_esn(struct xfrm_replay_state_esn **replay_esn, struct xfrm_replay_state_esn **preplay_esn, struct nlattr *rta) @@ -511,7 +534,7 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, xfrm_mark_get(attrs, &x->mark); - err = xfrm_init_state(x); + err = __xfrm_init_state(x, false); if (err) goto error; @@ -874,7 +897,7 @@ static int build_spdinfo(struct sk_buff *skb, struct net *net, u32 *f; nlh = nlmsg_put(skb, pid, seq, XFRM_MSG_NEWSPDINFO, sizeof(u32), 0); - if (nlh == NULL) /* shouldnt really happen ... */ + if (nlh == NULL) /* shouldn't really happen ... */ return -EMSGSIZE; f = nlmsg_data(nlh); @@ -934,7 +957,7 @@ static int build_sadinfo(struct sk_buff *skb, struct net *net, u32 *f; nlh = nlmsg_put(skb, pid, seq, XFRM_MSG_NEWSADINFO, sizeof(u32), 0); - if (nlh == NULL) /* shouldnt really happen ... */ + if (nlh == NULL) /* shouldn't really happen ... */ return -EMSGSIZE; f = nlmsg_data(nlh); @@ -1341,7 +1364,7 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (!xp) return err; - /* shouldnt excl be based on nlh flags?? + /* shouldn't excl be based on nlh flags?? * Aha! this is anti-netlink really i.e more pfkey derived * in netlink excl is a flag and you wouldnt need * a type XFRM_MSG_UPDPOLICY - JHS */ @@ -1766,6 +1789,10 @@ static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh, if (x->km.state != XFRM_STATE_VALID) goto out; + err = xfrm_replay_verify_len(x->replay_esn, rp); + if (err) + goto out; + spin_lock_bh(&x->lock); xfrm_update_ae_params(x, attrs); spin_unlock_bh(&x->lock); |